1 files changed, 142 insertions, 37 deletions

diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index c43caa3a91f3..89cea4d44679 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -12,20 +12,47 @@
 #include <linux/reboot.h>
 #include <linux/numa.h>
 #include <linux/ftrace.h>
+#include <linux/io.h>
+#include <linux/suspend.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 int init_one_level2_page(struct kimage *image, pgd_t *pgd,
+                                unsigned long addr)
+{
+        pud_t *pud;
+        pmd_t *pmd;
+        struct page *page;
+        int result = -ENOMEM;
+
+        addr &= PMD_MASK;
+        pgd += pgd_index(addr);
+        if (!pgd_present(*pgd)) {
+                page = kimage_alloc_control_pages(image, 0);
+                if (!page)
+                        goto out;
+                pud = (pud_t *)page_address(page);
+                memset(pud, 0, PAGE_SIZE);
+                set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+        }
+        pud = pud_offset(pgd, addr);
+        if (!pud_present(*pud)) {
+                page = kimage_alloc_control_pages(image, 0);
+                if (!page)
+                        goto out;
+                pmd = (pmd_t *)page_address(page);
+                memset(pmd, 0, PAGE_SIZE);
+                set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE));
+        }
+        pmd = pmd_offset(pud, addr);
+        if (!pmd_present(*pmd))
+                set_pmd(pmd, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
+        result = 0;
+out:
+        return result;
+}
 
 static void init_level2_page(pmd_t *level2p, unsigned long addr)
 {
@@ -92,9 +119,8 @@ static int init_level4_page(struct kimage *image, pgd_t *level4p,
                 }
                 level3p = (pud_t *)page_address(page);
                 result = init_level3_page(image, level3p, addr, last_addr);
-                if (result) {
+                if (result)
                         goto out;
-                }
                 set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
                 addr += PGDIR_SIZE;
         }
@@ -107,12 +133,72 @@ out:
         return result;
 }
 
+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_transition_pgtable(struct kimage *image, pgd_t *pgd)
+{
+        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));
+        }
+        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));
+        }
+        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_pgtable(struct kimage *image, unsigned long start_pgtable)
 {
         pgd_t *level4p;
+        int result;
         level4p = (pgd_t *)__va(start_pgtable);
-        return init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
+        result = init_level4_page(image, level4p, 0, max_pfn << PAGE_SHIFT);
+        if (result)
+                return result;
+        /*
+         * image->start may be outside 0 ~ max_pfn, for example when
+         * jump back to original kernel from kexeced kernel
+         */
+        result = init_one_level2_page(image, level4p, image->start);
+        if (result)
+                return result;
+        return init_transition_pgtable(image, level4p);
 }
 
 static void set_idt(void *newidt, u16 limit)
@@ -174,7 +260,7 @@ int machine_kexec_prepare(struct kimage *image)
 
 void machine_kexec_cleanup(struct kimage *image)
 {
-        return;
+        free_transition_pgtable(image);
 }
 
 /*
@@ -185,36 +271,45 @@ void machine_kexec(struct kimage *image)
 {
         unsigned long page_list[PAGES_NR];
         void *control_page;
+        int save_ftrace_enabled;
 
-        tracer_disable();
+#ifdef CONFIG_KEXEC_JUMP
+        if (kexec_image->preserve_context)
+                save_processor_state();
+#endif
+
+        save_ftrace_enabled = __ftrace_enabled_save();
 
         /* Interrupts aren't acceptable while we reboot */
         local_irq_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
@@ -224,15 +319,25 @@ 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 (kexec_image->preserve_context)
+                restore_processor_state();
+#endif
+
+        __ftrace_enabled_restore(save_ftrace_enabled);
 }
 
 void arch_crash_save_vmcoreinfo(void)