/*
* machine_kexec.c - handle transition of Linux booting another kernel
- * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com>
+ * Copyright (C) 2002-2005 Eric Biederman <ebiederm@xmission.com>
*
* This source code is licensed under the GNU General Public License,
* Version 2. See the file COPYING for more details.
#include <linux/mm.h>
#include <linux/kexec.h>
-#include <linux/delay.h>
#include <linux/string.h>
#include <linux/reboot.h>
-#include <asm/pda.h>
#include <asm/pgtable.h>
-#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/io.h>
-#include <asm/apic.h>
-#include <asm/cpufeature.h>
-#include <asm/hw_irq.h>
-
-#define LEVEL0_SIZE (1UL << 12UL)
-#define LEVEL1_SIZE (1UL << 21UL)
-#define LEVEL2_SIZE (1UL << 30UL)
-#define LEVEL3_SIZE (1UL << 39UL)
-#define LEVEL4_SIZE (1UL << 48UL)
-
-#define L0_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define L1_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE)
-#define L2_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define L3_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-static void init_level2_page(
- uint64_t *level2p, unsigned long addr)
+
+#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;
+
addr &= PAGE_MASK;
- end_addr = addr + LEVEL2_SIZE;
- while(addr < end_addr) {
- *(level2p++) = addr | L1_ATTR;
- addr += LEVEL1_SIZE;
+ end_addr = addr + PUD_SIZE;
+ while (addr < end_addr) {
+ set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
+ addr += PMD_SIZE;
}
}
-static int init_level3_page(struct kimage *image,
- uint64_t *level3p, unsigned long addr, unsigned long last_addr)
+static int init_level3_page(struct kimage *image, pud_t *level3p,
+ unsigned long addr, unsigned long last_addr)
{
unsigned long end_addr;
int result;
+
result = 0;
addr &= PAGE_MASK;
- end_addr = addr + LEVEL3_SIZE;
- while((addr < last_addr) && (addr < end_addr)) {
+ end_addr = addr + PGDIR_SIZE;
+ while ((addr < last_addr) && (addr < end_addr)) {
struct page *page;
- uint64_t *level2p;
+ pmd_t *level2p;
+
page = kimage_alloc_control_pages(image, 0);
if (!page) {
result = -ENOMEM;
goto out;
}
- level2p = (uint64_t *)page_address(page);
+ level2p = (pmd_t *)page_address(page);
init_level2_page(level2p, addr);
- *(level3p++) = __pa(level2p) | L2_ATTR;
- addr += LEVEL2_SIZE;
+ set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
+ addr += PUD_SIZE;
}
/* clear the unused entries */
- while(addr < end_addr) {
- *(level3p++) = 0;
- addr += LEVEL2_SIZE;
+ while (addr < end_addr) {
+ pud_clear(level3p++);
+ addr += PUD_SIZE;
}
out:
return result;
}
-static int init_level4_page(struct kimage *image,
- uint64_t *level4p, unsigned long addr, unsigned long last_addr)
+static int init_level4_page(struct kimage *image, pgd_t *level4p,
+ unsigned long addr, unsigned long last_addr)
{
unsigned long end_addr;
int result;
+
result = 0;
addr &= PAGE_MASK;
- end_addr = addr + LEVEL4_SIZE;
- while((addr < last_addr) && (addr < end_addr)) {
+ end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
+ while ((addr < last_addr) && (addr < end_addr)) {
struct page *page;
- uint64_t *level3p;
+ pud_t *level3p;
+
page = kimage_alloc_control_pages(image, 0);
if (!page) {
result = -ENOMEM;
goto out;
}
- level3p = (uint64_t *)page_address(page);
+ level3p = (pud_t *)page_address(page);
result = init_level3_page(image, level3p, addr, last_addr);
if (result) {
goto out;
}
- *(level4p++) = __pa(level3p) | L3_ATTR;
- addr += LEVEL3_SIZE;
+ set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
+ addr += PGDIR_SIZE;
}
/* clear the unused entries */
- while(addr < end_addr) {
- *(level4p++) = 0;
- addr += LEVEL3_SIZE;
+ while (addr < end_addr) {
+ pgd_clear(level4p++);
+ addr += PGDIR_SIZE;
}
- out:
+out:
return result;
}
static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
{
- uint64_t *level4p;
- level4p = (uint64_t *)__va(start_pgtable);
- return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT);
+ pgd_t *level4p;
+ level4p = (pgd_t *)__va(start_pgtable);
+ return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT);
}
-static void set_idt(void *newidt, __u16 limit)
+static void set_idt(void *newidt, u16 limit)
{
- unsigned char curidt[10];
+ struct desc_ptr curidt;
/* x86-64 supports unaliged loads & stores */
- (*(__u16 *)(curidt)) = limit;
- (*(__u64 *)(curidt +2)) = (unsigned long)(newidt);
+ curidt.size = limit;
+ curidt.address = (unsigned long)newidt;
__asm__ __volatile__ (
- "lidt %0\n"
- : "=m" (curidt)
+ "lidtq %0\n"
+ : : "m" (curidt)
);
};
-static void set_gdt(void *newgdt, __u16 limit)
+static void set_gdt(void *newgdt, u16 limit)
{
- unsigned char curgdt[10];
+ struct desc_ptr curgdt;
/* x86-64 supports unaligned loads & stores */
- (*(__u16 *)(curgdt)) = limit;
- (*(__u64 *)(curgdt +2)) = (unsigned long)(newgdt);
+ curgdt.size = limit;
+ curgdt.address = (unsigned long)newgdt;
__asm__ __volatile__ (
- "lgdt %0\n"
- : "=m" (curgdt)
+ "lgdtq %0\n"
+ : : "m" (curgdt)
);
};
static void load_segments(void)
{
__asm__ __volatile__ (
- "\tmovl $"STR(__KERNEL_DS)",%eax\n"
- "\tmovl %eax,%ds\n"
- "\tmovl %eax,%es\n"
- "\tmovl %eax,%ss\n"
- "\tmovl %eax,%fs\n"
- "\tmovl %eax,%gs\n"
+ "\tmovl %0,%%ds\n"
+ "\tmovl %0,%%es\n"
+ "\tmovl %0,%%ss\n"
+ "\tmovl %0,%%fs\n"
+ "\tmovl %0,%%gs\n"
+ : : "a" (__KERNEL_DS) : "memory"
);
-#undef STR
-#undef __STR
}
-typedef void (*relocate_new_kernel_t)(
- unsigned long indirection_page, unsigned long control_code_buffer,
- unsigned long start_address, unsigned long pgtable);
-
-const extern unsigned char relocate_new_kernel[];
-extern void relocate_new_kernel_end(void);
-const extern unsigned long relocate_new_kernel_size;
-
int machine_kexec_prepare(struct kimage *image)
{
- unsigned long start_pgtable, control_code_buffer;
+ unsigned long start_pgtable;
int result;
/* Calculate the offsets */
- start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
- control_code_buffer = start_pgtable + 4096UL;
+ start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
/* Setup the identity mapped 64bit page table */
result = init_pgtable(image, start_pgtable);
- if (result) {
+ if (result)
return result;
- }
-
- /* Place the code in the reboot code buffer */
- memcpy(__va(control_code_buffer), relocate_new_kernel, relocate_new_kernel_size);
return 0;
}
* Do not allocate memory (or fail in any way) in machine_kexec().
* We are past the point of no return, committed to rebooting now.
*/
-void machine_kexec(struct kimage *image)
+NORET_TYPE void machine_kexec(struct kimage *image)
{
- unsigned long indirection_page;
- unsigned long control_code_buffer;
- unsigned long start_pgtable;
- relocate_new_kernel_t rnk;
+ unsigned long page_list[PAGES_NR];
+ void *control_page;
/* Interrupts aren't acceptable while we reboot */
local_irq_disable();
- /* Calculate the offsets */
- indirection_page = image->head & PAGE_MASK;
- start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
- control_code_buffer = start_pgtable + 4096UL;
-
- /* Set the low half of the page table to my identity mapped
- * page table for kexec. Leave the high half pointing at the
- * kernel pages. Don't bother to flush the global pages
- * as that will happen when I fully switch to my identity mapped
- * page table anyway.
- */
- memcpy((void *)read_pda(level4_pgt), __va(start_pgtable), PAGE_SIZE/2);
- __flush_tlb();
+ control_page = page_address(image->control_code_page) + PAGE_SIZE;
+ memcpy(control_page, relocate_kernel, PAGE_SIZE);
+ page_list[PA_CONTROL_PAGE] = __pa(control_page);
+ page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+ page_list[PA_PGD] = __pa(kexec_pgd);
+ page_list[VA_PGD] = (unsigned long)kexec_pgd;
+ page_list[PA_PUD_0] = __pa(kexec_pud0);
+ page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
+ page_list[PA_PMD_0] = __pa(kexec_pmd0);
+ page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
+ page_list[PA_PTE_0] = __pa(kexec_pte0);
+ page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
+ page_list[PA_PUD_1] = __pa(kexec_pud1);
+ page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
+ page_list[PA_PMD_1] = __pa(kexec_pmd1);
+ page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
+ page_list[PA_PTE_1] = __pa(kexec_pte1);
+ page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
- /* The segment registers are funny things, they are
- * automatically loaded from a table, in memory wherever you
- * set them to a specific selector, but this table is never
- * accessed again unless you set the segment to a different selector.
- *
- * The more common model are caches where the behide
- * the scenes work is done, but is also dropped at arbitrary
- * times.
+ page_list[PA_TABLE_PAGE] =
+ (unsigned long)__pa(page_address(image->control_code_page));
+
+ /* 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
+ * descriptor table in memory accessed.
*
* I take advantage of this here by force loading the
* segments, before I zap the gdt with an invalid value.
*/
set_gdt(phys_to_virt(0),0);
set_idt(phys_to_virt(0),0);
+
/* now call it */
- rnk = (relocate_new_kernel_t) control_code_buffer;
- (*rnk)(indirection_page, control_code_buffer, image->start, start_pgtable);
+ relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
+ image->start);
}
+
+/* crashkernel=size@addr specifies the location to reserve for
+ * a crash kernel. By reserving this memory we guarantee
+ * that linux never set's it up as a DMA target.
+ * Useful for holding code to do something appropriate
+ * after a kernel panic.
+ */
+static int __init setup_crashkernel(char *arg)
+{
+ unsigned long size, base;
+ char *p;
+ if (!arg)
+ return -EINVAL;
+ size = memparse(arg, &p);
+ if (arg == p)
+ return -EINVAL;
+ if (*p == '@') {
+ base = memparse(p+1, &p);
+ /* FIXME: Do I want a sanity check to validate the
+ * memory range? Yes you do, but it's too early for
+ * e820 -AK */
+ crashk_res.start = base;
+ crashk_res.end = base + size - 1;
+ }
+ return 0;
+}
+early_param("crashkernel", setup_crashkernel);
+