1 files changed, 146 insertions, 105 deletions

diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 576a03db451..679cef0791c 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -9,108 +9,125 @@
 #include <linux/mm.h>
 #include <linux/kexec.h>
 #include <linux/string.h>
+#include <linux/gfp.h>
 #include <linux/reboot.h>
 #include <linux/numa.h>
+#include <linux/ftrace.h>
+#include <linux/io.h>
+#include <linux/suspend.h>
+
+#include <asm/init.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
-#include <asm/io.h>
-
-#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
-static u64 kexec_pgd[512] PAGE_ALIGNED;
-static u64 kexec_pud0[512] PAGE_ALIGNED;
-static u64 kexec_pmd0[512] PAGE_ALIGNED;
-static u64 kexec_pte0[512] PAGE_ALIGNED;
-static u64 kexec_pud1[512] PAGE_ALIGNED;
-static u64 kexec_pmd1[512] PAGE_ALIGNED;
-static u64 kexec_pte1[512] PAGE_ALIGNED;
-
-static void init_level2_page(pmd_t *level2p, unsigned long addr)
-{
-	unsigned long end_addr;
+#include <asm/debugreg.h>
 
-	addr &= PAGE_MASK;
-	end_addr = addr + PUD_SIZE;
-	while (addr < end_addr) {
-		set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
-		addr += PMD_SIZE;
-	}
+static void free_transition_pgtable(struct kimage *image)
+{
+	free_page((unsigned long)image->arch.pud);
+	free_page((unsigned long)image->arch.pmd);
+	free_page((unsigned long)image->arch.pte);
 }
 
-static int init_level3_page(struct kimage *image, pud_t *level3p,
-				unsigned long addr, unsigned long last_addr)
+static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 {
-	unsigned long end_addr;
-	int result;
-
-	result = 0;
-	addr &= PAGE_MASK;
-	end_addr = addr + PGDIR_SIZE;
-	while ((addr < last_addr) && (addr < end_addr)) {
-		struct page *page;
-		pmd_t *level2p;
-
-		page = kimage_alloc_control_pages(image, 0);
-		if (!page) {
-			result = -ENOMEM;
-			goto out;
-		}
-		level2p = (pmd_t *)page_address(page);
-		init_level2_page(level2p, addr);
-		set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
-		addr += PUD_SIZE;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long vaddr, paddr;
+	int result = -ENOMEM;
+
+	vaddr = (unsigned long)relocate_kernel;
+	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
+	pgd += pgd_index(vaddr);
+	if (!pgd_present(*pgd)) {
+		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pud)
+			goto err;
+		image->arch.pud = pud;
+		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
+	pud = pud_offset(pgd, vaddr);
+	if (!pud_present(*pud)) {
+		pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pmd)
+			goto err;
+		image->arch.pmd = pmd;
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
 	}
-	/* clear the unused entries */
-	while (addr < end_addr) {
-		pud_clear(level3p++);
-		addr += PUD_SIZE;
+	pmd = pmd_offset(pud, vaddr);
+	if (!pmd_present(*pmd)) {
+		pte = (pte_t *)get_zeroed_page(GFP_KERNEL);
+		if (!pte)
+			goto err;
+		image->arch.pte = pte;
+		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE));
 	}
-out:
+	pte = pte_offset_kernel(pmd, vaddr);
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+	return 0;
+err:
+	free_transition_pgtable(image);
 	return result;
 }
 
-
-static int init_level4_page(struct kimage *image, pgd_t *level4p,
-				unsigned long addr, unsigned long last_addr)
+static void *alloc_pgt_page(void *data)
 {
-	unsigned long end_addr;
-	int result;
-
-	result = 0;
-	addr &= PAGE_MASK;
-	end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
-	while ((addr < last_addr) && (addr < end_addr)) {
-		struct page *page;
-		pud_t *level3p;
-
-		page = kimage_alloc_control_pages(image, 0);
-		if (!page) {
-			result = -ENOMEM;
-			goto out;
-		}
-		level3p = (pud_t *)page_address(page);
-		result = init_level3_page(image, level3p, addr, last_addr);
-		if (result) {
-			goto out;
-		}
-		set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
-		addr += PGDIR_SIZE;
+	struct kimage *image = (struct kimage *)data;
+	struct page *page;
+	void *p = NULL;
+
+	page = kimage_alloc_control_pages(image, 0);
+	if (page) {
+		p = page_address(page);
+		clear_page(p);
 	}
-	/* clear the unused entries */
-	while (addr < end_addr) {
-		pgd_clear(level4p++);
-		addr += PGDIR_SIZE;
-	}
-out:
-	return result;
-}
 
+	return p;
+}
 
 static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 {
+	struct x86_mapping_info info = {
+		.alloc_pgt_page	= alloc_pgt_page,
+		.context	= image,
+		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+	};
+	unsigned long mstart, mend;
 	pgd_t *level4p;
+	int result;
+	int i;
+
 	level4p = (pgd_t *)__va(start_pgtable);
- 	return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT);
+	clear_page(level4p);
+	for (i = 0; i < nr_pfn_mapped; i++) {
+		mstart = pfn_mapped[i].start << PAGE_SHIFT;
+		mend   = pfn_mapped[i].end << PAGE_SHIFT;
+
+		result = kernel_ident_mapping_init(&info,
+						 level4p, mstart, mend);
+		if (result)
+			return result;
+	}
+
+	/*
+	 * segments's mem ranges could be outside 0 ~ max_pfn,
+	 * for example when jump back to original kernel from kexeced kernel.
+	 * or first kernel is booted with user mem map, and second kernel
+	 * could be loaded out of that range.
+	 */
+	for (i = 0; i < image->nr_segments; i++) {
+		mstart = image->segment[i].mem;
+		mend   = mstart + image->segment[i].memsz;
+
+		result = kernel_ident_mapping_init(&info,
+						 level4p, mstart, mend);
+
+		if (result)
+			return result;
+	}
+
+	return init_transition_pgtable(image, level4p);
 }
 
 static void set_idt(void *newidt, u16 limit)
@@ -172,45 +189,57 @@ int machine_kexec_prepare(struct kimage *image)
 
 void machine_kexec_cleanup(struct kimage *image)
 {
-	return;
+	free_transition_pgtable(image);
 }
 
 /*
  * 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;
+	int save_ftrace_enabled;
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (image->preserve_context)
+		save_processor_state();
+#endif
+
+	save_ftrace_enabled = __ftrace_enabled_save();
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
+	hw_breakpoint_disable();
+
+	if (image->preserve_context) {
+#ifdef CONFIG_X86_IO_APIC
+		/*
+		 * We need to put APICs in legacy mode so that we can
+		 * get timer interrupts in second kernel. kexec/kdump
+		 * paths already have calls to disable_IO_APIC() in
+		 * one form or other. kexec jump path also need
+		 * one.
+		 */
+		disable_IO_APIC();
+#endif
+	}
 
 	control_page = page_address(image->control_code_page) + PAGE_SIZE;
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
 
 	page_list[PA_CONTROL_PAGE] = virt_to_phys(control_page);
-	page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
-	page_list[PA_PGD] = virt_to_phys(&kexec_pgd);
-	page_list[VA_PGD] = (unsigned long)kexec_pgd;
-	page_list[PA_PUD_0] = virt_to_phys(&kexec_pud0);
-	page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
-	page_list[PA_PMD_0] = virt_to_phys(&kexec_pmd0);
-	page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
-	page_list[PA_PTE_0] = virt_to_phys(&kexec_pte0);
-	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
-	page_list[PA_PUD_1] = virt_to_phys(&kexec_pud1);
-	page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
-	page_list[PA_PMD_1] = virt_to_phys(&kexec_pmd1);
-	page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
-	page_list[PA_PTE_1] = virt_to_phys(&kexec_pte1);
-	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
-
+	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
 	page_list[PA_TABLE_PAGE] =
 	  (unsigned long)__pa(page_address(image->control_code_page));
 
-	/* The segment registers are funny things, they have both a
+	if (image->type == KEXEC_TYPE_DEFAULT)
+		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
 	 * set to a specific selector, the invisible part is loaded
 	 * with from a table in memory.  At no other time is the
@@ -220,15 +249,25 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	 * segments, before I zap the gdt with an invalid value.
 	 */
 	load_segments();
-	/* The gdt & idt are now invalid.
+	/*
+	 * The gdt & idt are now invalid.
 	 * If you want to load them you must set up your own idt & gdt.
 	 */
-	set_gdt(phys_to_virt(0),0);
-	set_idt(phys_to_virt(0),0);
+	set_gdt(phys_to_virt(0), 0);
+	set_idt(phys_to_virt(0), 0);
 
 	/* now call it */
-	relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
-			image->start);
+	image->start = relocate_kernel((unsigned long)image->head,
+				       (unsigned long)page_list,
+				       image->start,
+				       image->preserve_context);
+
+#ifdef CONFIG_KEXEC_JUMP
+	if (image->preserve_context)
+		restore_processor_state();
+#endif
+
+	__ftrace_enabled_restore(save_ftrace_enabled);
 }
 
 void arch_crash_save_vmcoreinfo(void)
@@ -240,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(node_data);
 	VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+			      (unsigned long)&_text - __START_KERNEL);
 }