x86 candidate patches for review II: 64bit relocatable kernel

Index: linux/include/asm-x86_64/const.h
===================================================================
@@ -0,0 +1,20 @@
+/* const.h: Macros for dealing with constants.  */
+
+#ifndef _X86_64_CONST_H
+#define _X86_64_CONST_H
+
+/* Some constant macros are used in both assembler and
+ * C code.  Therefore we cannot annotate them always with
+ * 'UL' and other type specificers unilaterally.  We
+ * use the following macros to deal with this.
+ */
+
+#ifdef __ASSEMBLY__
+#define _AC(X,Y)	X
+#else
+#define __AC(X,Y)	(X##Y)
+#define _AC(X,Y)	__AC(X,Y)
+#endif
+
+
+#endif /* !(_X86_64_CONST_H) */

Index: linux/include/asm-x86_64/page.h
===================================================================
@@ -1,14 +1,11 @@
 #ifndef _X86_64_PAGE_H
 #define _X86_64_PAGE_H
 
+#include <asm/const.h>
 
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT	12
-#ifdef __ASSEMBLY__
-#define PAGE_SIZE	(0x1 << PAGE_SHIFT)
-#else
-#define PAGE_SIZE	(1UL << PAGE_SHIFT)
-#endif
+#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
 #define PAGE_MASK	(~(PAGE_SIZE-1))
 #define PHYSICAL_PAGE_MASK	(~(PAGE_SIZE-1) & __PHYSICAL_MASK)
 

@@ -33,10 +30,10 @@
 #define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
 
 #define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
-#define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
+#define LARGE_PAGE_SIZE (_AC(1,UL) << PMD_SHIFT)
 
 #define HPAGE_SHIFT PMD_SHIFT
-#define HPAGE_SIZE	((1UL) << HPAGE_SHIFT)
+#define HPAGE_SIZE	(_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 

@@ -76,29 +73,24 @@ typedef struct { unsigned long pgprot; }
 #define __pgd(x) ((pgd_t) { (x) } )
 #define __pgprot(x)	((pgprot_t) { (x) } )
 
-#define __PHYSICAL_START	((unsigned long)CONFIG_PHYSICAL_START)
-#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
-#define __START_KERNEL_map	0xffffffff80000000UL
-#define __PAGE_OFFSET           0xffff810000000000UL
+#endif /* !__ASSEMBLY__ */
 
-#else
 #define __PHYSICAL_START	CONFIG_PHYSICAL_START
 #define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	0xffffffff80000000
 #define __PAGE_OFFSET           0xffff810000000000
-#endif /* !__ASSEMBLY__ */
 
 /* to align the pointer to the (next) page boundary */
 #define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)
 
 /* See Documentation/x86_64/mm.txt for a description of the memory map. */
 #define __PHYSICAL_MASK_SHIFT	46
-#define __PHYSICAL_MASK		((1UL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __PHYSICAL_MASK		((_AC(1,UL) << __PHYSICAL_MASK_SHIFT) - 1)
 #define __VIRTUAL_MASK_SHIFT	48
-#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK		((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - 1)
 
-#define KERNEL_TEXT_SIZE  (40UL*1024*1024)
-#define KERNEL_TEXT_START 0xffffffff80000000UL 
+#define KERNEL_TEXT_SIZE  (40*1024*1024)
+#define KERNEL_TEXT_START 0xffffffff80000000
 
 #ifndef __ASSEMBLY__
 

@@ -106,7 +98,7 @@ typedef struct { unsigned long pgprot; }
 
 #endif /* __ASSEMBLY__ */
 
-#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
+#define PAGE_OFFSET		__PAGE_OFFSET
 
 /* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol.
    Otherwise you risk miscompilation. */ 

Index: linux/include/asm-x86_64/pgtable.h
===================================================================
@@ -1,6 +1,9 @@
 #ifndef _X86_64_PGTABLE_H
 #define _X86_64_PGTABLE_H
 
+#include <asm/const.h>
+#ifndef __ASSEMBLY__
+
 /*
  * This file contains the functions and defines necessary to modify and use
  * the x86-64 page table tree.

@@ -30,6 +33,8 @@ extern void clear_kernel_mapping(unsigne
 extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
 #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
+#endif /* !__ASSEMBLY__ */
+
 /*
  * PGDIR_SHIFT determines what a top-level page table entry can map
  */

@@ -54,6 +59,8 @@ extern unsigned long empty_zero_page[PAG
  */
 #define PTRS_PER_PTE	512
 
+#ifndef __ASSEMBLY__
+
 #define pte_ERROR(e) \
 	printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
 #define pmd_ERROR(e) \

@@ -117,22 +124,23 @@ static inline pte_t ptep_get_and_clear_f
 
 #define pte_pgprot(a)	(__pgprot((a).pte & ~PHYSICAL_PAGE_MASK))
 
-#define PMD_SIZE	(1UL << PMD_SHIFT)
+#endif /* !__ASSEMBLY__ */
+
+#define PMD_SIZE	(_AC(1,UL) << PMD_SHIFT)
 #define PMD_MASK	(~(PMD_SIZE-1))
-#define PUD_SIZE	(1UL << PUD_SHIFT)
+#define PUD_SIZE	(_AC(1,UL) << PUD_SHIFT)
 #define PUD_MASK	(~(PUD_SIZE-1))
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_SIZE	(_AC(1,UL) << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
 #define USER_PTRS_PER_PGD	((TASK_SIZE-1)/PGDIR_SIZE+1)
 #define FIRST_USER_ADDRESS	0
 
-#ifndef __ASSEMBLY__
-#define MAXMEM		 0x3fffffffffffUL
-#define VMALLOC_START    0xffffc20000000000UL
-#define VMALLOC_END      0xffffe1ffffffffffUL
-#define MODULES_VADDR    0xffffffff88000000UL
-#define MODULES_END      0xfffffffffff00000UL
+#define MAXMEM		 0x3fffffffffff
+#define VMALLOC_START    0xffffc20000000000
+#define VMALLOC_END      0xffffe1ffffffffff
+#define MODULES_VADDR    0xffffffff88000000
+#define MODULES_END      0xfffffffffff00000
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
 #define _PAGE_BIT_PRESENT	0

@@ -158,7 +166,7 @@ static inline pte_t ptep_get_and_clear_f
 #define _PAGE_GLOBAL	0x100	/* Global TLB entry */
 
 #define _PAGE_PROTNONE	0x080	/* If not present */
-#define _PAGE_NX        (1UL<<_PAGE_BIT_NX)
+#define _PAGE_NX        (_AC(1,UL)<<_PAGE_BIT_NX)
 
 #define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)

@@ -220,6 +228,8 @@ static inline pte_t ptep_get_and_clear_f
 #define __S110	PAGE_SHARED_EXEC
 #define __S111	PAGE_SHARED_EXEC
 
+#ifndef __ASSEMBLY__
+
 static inline unsigned long pgd_bad(pgd_t pgd)
 {
 	return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);

@@ -405,8 +415,6 @@ extern spinlock_t pgd_lock;
 extern struct page *pgd_list;
 void vmalloc_sync_all(void);
 
-#endif /* !__ASSEMBLY__ */
-
 extern int kern_addr_valid(unsigned long addr); 
 
 #define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\

@@ -436,5 +444,6 @@ extern int kern_addr_valid(unsigned long
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 #define __HAVE_ARCH_PTE_SAME
 #include <asm-generic/pgtable.h>
+#endif /* !__ASSEMBLY__ */
 
 #endif /* _X86_64_PGTABLE_H */

165 lines not on this page · raw message

Index: linux/include/asm-x86_64/segment.h
===================================================================
@@ -6,7 +6,7 @@
 #define __KERNEL_CS	0x10
 #define __KERNEL_DS	0x18
 
-#define __KERNEL32_CS   0x38
+#define __KERNEL32_CS   0x08
 
 /* 
  * we cannot use the same code segment descriptor for user and kernel

Index: linux/arch/x86_64/kernel/pci-calgary.c
===================================================================
@@ -507,7 +507,7 @@ error:
 	return ret;
 }
 
-static struct dma_mapping_ops calgary_dma_ops = {
+static const struct dma_mapping_ops calgary_dma_ops = {
 	.alloc_coherent = calgary_alloc_coherent,
 	.map_single = calgary_map_single,
 	.unmap_single = calgary_unmap_single,

Index: linux/arch/x86_64/kernel/pci-gart.c
===================================================================
@@ -556,7 +556,7 @@ static __init int init_k8_gatt(struct ag
 
 extern int agp_amd64_init(void);
 
-static struct dma_mapping_ops gart_dma_ops = {
+static const struct dma_mapping_ops gart_dma_ops = {
 	.mapping_error = NULL,
 	.map_single = gart_map_single,
 	.map_simple = gart_map_simple,

Index: linux/arch/x86_64/kernel/pci-nommu.c
===================================================================
@@ -79,7 +79,7 @@ void nommu_unmap_sg(struct device *dev, 
 {
 }
 
-struct dma_mapping_ops nommu_dma_ops = {
+const struct dma_mapping_ops nommu_dma_ops = {
 	.map_single = nommu_map_single,
 	.unmap_single = nommu_unmap_single,
 	.map_sg = nommu_map_sg,

Index: linux/arch/x86_64/kernel/pci-swiotlb.c
===================================================================
@@ -12,7 +12,7 @@
 int swiotlb __read_mostly;
 EXPORT_SYMBOL(swiotlb);
 
-struct dma_mapping_ops swiotlb_dma_ops = {
+const struct dma_mapping_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc_coherent = swiotlb_alloc_coherent,
 	.free_coherent = swiotlb_free_coherent,

Index: linux/arch/x86_64/mm/init.c
===================================================================
@@ -46,7 +46,7 @@
 #define Dprintk(x...)
 #endif
 
-struct dma_mapping_ops* dma_ops;
+const struct dma_mapping_ops* dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static unsigned long dma_reserve __initdata;

Index: linux/include/asm-x86_64/dma-mapping.h
===================================================================
@@ -52,7 +52,7 @@ struct dma_mapping_ops {
 };
 
 extern dma_addr_t bad_dma_address;
-extern struct dma_mapping_ops* dma_ops;
+extern const struct dma_mapping_ops* dma_ops;
 extern int iommu_merge;
 
 static inline int dma_mapping_error(dma_addr_t dma_addr)

Index: linux/arch/x86_64/kernel/suspend.c
===================================================================
@@ -33,7 +33,6 @@ void __save_processor_state(struct saved
 	asm volatile ("str %0"  : "=m" (ctxt->tr));
 
 	/* XMM0..XMM15 should be handled by kernel_fpu_begin(). */
-	/* EFER should be constant for kernel version, no need to handle it. */
 	/*
 	 * segment registers
 	 */

@@ -50,6 +49,7 @@ void __save_processor_state(struct saved
 	/*
 	 * control registers 
 	 */
+	rdmsrl(MSR_EFER, ctxt->efer);
 	asm volatile ("movq %%cr0, %0" : "=r" (ctxt->cr0));
 	asm volatile ("movq %%cr2, %0" : "=r" (ctxt->cr2));
 	asm volatile ("movq %%cr3, %0" : "=r" (ctxt->cr3));

@@ -75,6 +75,7 @@ void __restore_processor_state(struct sa
 	/*
 	 * control registers
 	 */
+	wrmsrl(MSR_EFER, ctxt->efer);
 	asm volatile ("movq %0, %%cr8" :: "r" (ctxt->cr8));
 	asm volatile ("movq %0, %%cr4" :: "r" (ctxt->cr4));
 	asm volatile ("movq %0, %%cr3" :: "r" (ctxt->cr3));

Index: linux/include/asm-x86_64/suspend.h
===================================================================
@@ -17,6 +17,7 @@ struct saved_context {
   	u16 ds, es, fs, gs, ss;
 	unsigned long gs_base, gs_kernel_base, fs_base;
 	unsigned long cr0, cr2, cr3, cr4, cr8;
+	unsigned long efer;
 	u16 gdt_pad;
 	u16 gdt_limit;
 	unsigned long gdt_base;

Index: linux/include/asm-x86_64/pgtable.h
===================================================================
@@ -14,7 +14,6 @@
 #include <asm/pda.h>
 
 extern pud_t level3_kernel_pgt[512];
-extern pud_t level3_physmem_pgt[512];
 extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pgd_t init_level4_pgt[];

Index: linux/arch/x86_64/kernel/head64.c
===================================================================
@@ -29,25 +29,24 @@ static void __init clear_bss(void)
 }
 
 #define NEW_CL_POINTER		0x228	/* Relative to real mode data */
-#define OLD_CL_MAGIC_ADDR	0x90020
+#define OLD_CL_MAGIC_ADDR	0x20
 #define OLD_CL_MAGIC            0xA33F
-#define OLD_CL_BASE_ADDR        0x90000
-#define OLD_CL_OFFSET           0x90022
+#define OLD_CL_OFFSET           0x22
 
 static void __init copy_bootdata(char *real_mode_data)
 {
-	int new_data;
+	unsigned long new_data;
 	char * command_line;
 
 	memcpy(x86_boot_params, real_mode_data, BOOT_PARAM_SIZE);
-	new_data = *(int *) (x86_boot_params + NEW_CL_POINTER);
+	new_data = *(u32 *) (x86_boot_params + NEW_CL_POINTER);
 	if (!new_data) {
-		if (OLD_CL_MAGIC != * (u16 *) OLD_CL_MAGIC_ADDR) {
+		if (OLD_CL_MAGIC != *(u16 *)(real_mode_data + OLD_CL_MAGIC_ADDR)) {
 			return;
 		}
-		new_data = OLD_CL_BASE_ADDR + * (u16 *) OLD_CL_OFFSET;
+		new_data = __pa(real_mode_data) + *(u16 *)(real_mode_data + OLD_CL_OFFSET);
 	}
-	command_line = (char *) ((u64)(new_data));
+	command_line = __va(new_data);
 	memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
 }
 

@@ -74,7 +73,7 @@ void __init x86_64_start_kernel(char * r
  		cpu_pda(i) = &boot_cpu_pda[i];
 
 	pda_init(0);
-	copy_bootdata(real_mode_data);
+	copy_bootdata(__va(real_mode_data));
 #ifdef CONFIG_SMP
 	cpu_set(0, cpu_online_map);
 #endif

Index: linux/arch/x86_64/kernel/early_printk.c
===================================================================
@@ -11,11 +11,10 @@
 
 #ifdef __i386__
 #include <asm/setup.h>
-#define VGABASE		(__ISA_IO_base + 0xb8000)
 #else
 #include <asm/bootsetup.h>
-#define VGABASE		((void __iomem *)0xffffffff800b8000UL)
 #endif
+#define VGABASE		(__ISA_IO_base + 0xb8000)
 
 static int max_ypos = 25, max_xpos = 80;
 static int current_ypos = 25, current_xpos = 0;

Index: linux/arch/x86_64/kernel/acpi/sleep.c
===================================================================
@@ -60,19 +60,6 @@ extern char wakeup_start, wakeup_end;
 
 extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 
-static pgd_t low_ptr;
-
-static void init_low_mapping(void)
-{
-	pgd_t *slot0 = pgd_offset(current->mm, 0UL);
-	low_ptr = *slot0;
-	/* FIXME: We're playing with the current task's page tables here, which
-	 * is potentially dangerous on SMP systems.
-	 */
-	set_pgd(slot0, *pgd_offset(current->mm, PAGE_OFFSET));
-	local_flush_tlb();
-}
-
 /**
  * acpi_save_state_mem - save kernel state
  *

@@ -81,8 +68,6 @@ static void init_low_mapping(void)
  */
 int acpi_save_state_mem(void)
 {
-	init_low_mapping();
-
 	memcpy((void *)acpi_wakeup_address, &wakeup_start,
 	       &wakeup_end - &wakeup_start);
 	acpi_copy_wakeup_routine(acpi_wakeup_address);

@@ -95,8 +80,6 @@ int acpi_save_state_mem(void)
  */
 void acpi_restore_state_mem(void)
 {
-	set_pgd(pgd_offset(current->mm, 0UL), low_ptr);
-	local_flush_tlb();
 }
 
 /**

@@ -109,10 +92,11 @@ void acpi_restore_state_mem(void)
  */
 void __init acpi_reserve_bootmem(void)
 {
-	acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE);
-	if ((&wakeup_end - &wakeup_start) > PAGE_SIZE)
+	acpi_wakeup_address = (unsigned long)alloc_bootmem_low(PAGE_SIZE*2);
+	if ((&wakeup_end - &wakeup_start) > (PAGE_SIZE*2))
 		printk(KERN_CRIT
-		       "ACPI: Wakeup code way too big, will crash on attempt to suspend\n");
+		       "ACPI: Wakeup code way too big, will crash on attempt"
+		       " to suspend\n");
 }
 
 static int __init acpi_sleep_setup(char *str)

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -205,10 +205,10 @@ static void discover_ebda(void)
 	 * there is a real-mode segmented pointer pointing to the 
 	 * 4K EBDA area at 0x40E
 	 */
-	ebda_addr = *(unsigned short *)EBDA_ADDR_POINTER;
+	ebda_addr = *(unsigned short *)__va(EBDA_ADDR_POINTER);
 	ebda_addr <<= 4;
 
-	ebda_size = *(unsigned short *)(unsigned long)ebda_addr;
+	ebda_size = *(unsigned short *)__va(ebda_addr);
 
 	/* Round EBDA up to pages */
 	if (ebda_size == 0)

Index: linux/arch/x86_64/kernel/head64.c
===================================================================
@@ -18,8 +18,16 @@
 #include <asm/setup.h>
 #include <asm/desc.h>
 #include <asm/pgtable.h>
+#include <asm/tlbflush.h>
 #include <asm/sections.h>
 
+static void __init zap_identity_mappings(void)
+{
+	pgd_t *pgd = pgd_offset_k(0UL);
+	pgd_clear(pgd);
+	__flush_tlb();
+}
+
 /* Don't add a printk in there. printk relies on the PDA which is not initialized 
    yet. */
 static void __init clear_bss(void)

@@ -57,18 +65,15 @@ void __init x86_64_start_kernel(char * r
 	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 
+	/* Make NULL pointers segfault */
+	zap_identity_mappings();
+
 	for (i = 0; i < IDT_ENTRIES; i++)
 		set_intr_gate(i, early_idt_handler);
 	asm volatile("lidt %0" :: "m" (idt_descr));
 
 	early_printk("Kernel alive\n");
 
-	/*
-	 * switch to init_level4_pgt from boot_level4_pgt
-	 */
-	memcpy(init_level4_pgt, boot_level4_pgt, PTRS_PER_PGD*sizeof(pgd_t));
-	asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
-
  	for (i = 0; i < NR_CPUS; i++)
  		cpu_pda(i) = &boot_cpu_pda[i];
 

Index: linux/arch/x86_64/kernel/setup64.c
===================================================================
@@ -201,7 +201,6 @@ void __cpuinit cpu_init (void)
 	/* CPU 0 is initialised in head64.c */
 	if (cpu != 0) {
 		pda_init(cpu);
-		zap_low_mappings(cpu);
 	} else 
 		estacks = boot_exception_stacks; 
 

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -274,8 +274,6 @@ void __init setup_arch(char **cmdline_p)
 
 	dmi_scan_machine();
 
-	zap_low_mappings(0);
-
 #ifdef CONFIG_ACPI
 	/*
 	 * Initialize the ACPI boot-time table parser (gets the RSDP and SDT).

Index: linux/arch/x86_64/mm/init.c
===================================================================
@@ -378,21 +378,6 @@ void __meminit init_memory_mapping(unsig
 	__flush_tlb_all();
 }
 
-void __cpuinit zap_low_mappings(int cpu)
-{
-	if (cpu == 0) {
-		pgd_t *pgd = pgd_offset_k(0UL);
-		pgd_clear(pgd);
-	} else {
-		/*
-		 * For AP's, zap the low identity mappings by changing the cr3
-		 * to init_level4_pgt and doing local flush tlb all
-		 */
-		asm volatile("movq %0,%%cr3" :: "r" (__pa_symbol(&init_level4_pgt)));
-	}
-	__flush_tlb_all();
-}
-
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {

@@ -569,15 +554,6 @@ void __init mem_init(void)
 		reservedpages << (PAGE_SHIFT-10),
 		datasize >> 10,
 		initsize >> 10);
-
-#ifdef CONFIG_SMP
-	/*
-	 * Sync boot_level4_pgt mappings with the init_level4_pgt
-	 * except for the low identity mappings which are already zapped
-	 * in init_level4_pgt. This sync-up is essential for AP's bringup
-	 */
-	memcpy(boot_level4_pgt+1, init_level4_pgt+1, (PTRS_PER_PGD-1)*sizeof(pgd_t));
-#endif
 }
 
 void free_init_pages(char *what, unsigned long begin, unsigned long end)

Index: linux/include/asm-x86_64/pgtable.h
===================================================================
@@ -17,7 +17,6 @@ extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
 extern pgd_t init_level4_pgt[];
-extern pgd_t boot_level4_pgt[];
 extern unsigned long __supported_pte_mask;
 
 #define swapper_pg_dir init_level4_pgt

Index: linux/include/asm-x86_64/proto.h
===================================================================
@@ -11,8 +11,6 @@ struct pt_regs;
 extern void start_kernel(void);
 extern void pda_init(int); 
 
-extern void zap_low_mappings(int cpu);
-
 extern void early_idt_handler(void);
 
 extern void mcheck_init(struct cpuinfo_x86 *c);

Index: linux/arch/i386/kernel/alternative.c
===================================================================
@@ -402,8 +402,8 @@ void __init alternative_instructions(voi
 						_text, _etext);
 		}
 		free_init_pages("SMP alternatives",
-				(unsigned long)__smp_alt_begin,
-				(unsigned long)__smp_alt_end);
+				__pa_symbol(&__smp_alt_begin),
+				__pa_symbol(&__smp_alt_end));
 	} else {
 		alternatives_smp_save(__smp_alt_instructions,
 				      __smp_alt_instructions_end);

Index: linux/arch/i386/mm/init.c
===================================================================
@@ -774,10 +774,11 @@ void free_init_pages(char *what, unsigne
 	unsigned long addr;
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
+		struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
+		ClearPageReserved(page);
+		init_page_count(page);
+		memset(page_address(page), POISON_FREE_INITMEM, PAGE_SIZE);
+		__free_page(page);
 		totalram_pages++;
 	}
 	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);

@@ -786,14 +787,14 @@ void free_init_pages(char *what, unsigne
 void free_initmem(void)
 {
 	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+			__pa_symbol(&__init_begin),
+			__pa_symbol(&__init_end));
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	free_init_pages("initrd memory", __pa(start), __pa(end));
 }
 #endif
 

Index: linux/arch/x86_64/kernel/machine_kexec.c
===================================================================
@@ -191,19 +191,19 @@ NORET_TYPE void machine_kexec(struct kim
 
 	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[PA_PGD] = __pa_symbol(&kexec_pgd);
 	page_list[VA_PGD] = (unsigned long)kexec_pgd;
-	page_list[PA_PUD_0] = __pa(kexec_pud0);
+	page_list[PA_PUD_0] = __pa_symbol(&kexec_pud0);
 	page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
-	page_list[PA_PMD_0] = __pa(kexec_pmd0);
+	page_list[PA_PMD_0] = __pa_symbol(&kexec_pmd0);
 	page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
-	page_list[PA_PTE_0] = __pa(kexec_pte0);
+	page_list[PA_PTE_0] = __pa_symbol(&kexec_pte0);
 	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
-	page_list[PA_PUD_1] = __pa(kexec_pud1);
+	page_list[PA_PUD_1] = __pa_symbol(&kexec_pud1);
 	page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
-	page_list[PA_PMD_1] = __pa(kexec_pmd1);
+	page_list[PA_PMD_1] = __pa_symbol(&kexec_pmd1);
 	page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
-	page_list[PA_PTE_1] = __pa(kexec_pte1);
+	page_list[PA_PTE_1] = __pa_symbol(&kexec_pte1);
 	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
 
 	page_list[PA_TABLE_PAGE] =

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -243,11 +243,12 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_code = (unsigned long) &_etext;
 	init_mm.end_data = (unsigned long) &_edata;
 	init_mm.brk = (unsigned long) &_end;
+	init_mm.pgd = __va(__pa_symbol(&init_level4_pgt));
 
-	code_resource.start = virt_to_phys(&_text);
-	code_resource.end = virt_to_phys(&_etext)-1;
-	data_resource.start = virt_to_phys(&_etext);
-	data_resource.end = virt_to_phys(&_edata)-1;
+	code_resource.start = __pa_symbol(&_text);
+	code_resource.end = __pa_symbol(&_etext)-1;
+	data_resource.start = __pa_symbol(&_etext);
+	data_resource.end = __pa_symbol(&_edata)-1;
 
 	early_identify_cpu(&boot_cpu_data);
 

Index: linux/arch/x86_64/kernel/smp.c
===================================================================
@@ -76,7 +76,7 @@ static inline void leave_mm(int cpu)
 	if (read_pda(mmu_state) == TLBSTATE_OK)
 		BUG();
 	cpu_clear(cpu, read_pda(active_mm)->cpu_vm_mask);
-	load_cr3(swapper_pg_dir);
+	load_cr3(init_mm.pgd);
 }
 
 /*

Index: linux/arch/x86_64/kernel/vsyscall.c
===================================================================
@@ -45,6 +45,11 @@
 
 #define __vsyscall(nr) __attribute__ ((unused,__section__(".vsyscall_" #nr)))
 #define __syscall_clobber "r11","rcx","memory"
+#define __pa_vsymbol(x)			\
+	({unsigned long v;  		\
+	extern char __vsyscall_0; 	\
+	  asm("" : "=r" (v) : "0" (x)); \
+	  ((v - VSYSCALL_FIRST_PAGE) + __pa_symbol(&__vsyscall_0)); })
 
 struct vsyscall_gtod_data_t {
 	seqlock_t lock;

@@ -224,10 +229,10 @@ static int vsyscall_sysctl_change(ctl_ta
 		return ret;
 	/* gcc has some trouble with __va(__pa()), so just do it this
 	   way. */
-	map1 = ioremap(__pa_symbol(&vsysc1), 2);
+	map1 = ioremap(__pa_vsymbol(&vsysc1), 2);
 	if (!map1)
 		return -ENOMEM;
-	map2 = ioremap(__pa_symbol(&vsysc2), 2);
+	map2 = ioremap(__pa_vsymbol(&vsysc2), 2);
 	if (!map2) {
 		ret = -ENOMEM;
 		goto out;

Index: linux/arch/x86_64/mm/init.c
===================================================================
@@ -565,11 +565,11 @@ void free_init_pages(char *what, unsigne
 
 	printk(KERN_INFO "Freeing %s: %ldk freed\n", what, (end - begin) >> 10);
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
+		struct page *page = pfn_to_page(addr >> PAGE_SHIFT);
+		ClearPageReserved(page);
+		init_page_count(page);
+		memset(page_address(page), POISON_FREE_INITMEM, PAGE_SIZE);
+		__free_page(page);
 		totalram_pages++;
 	}
 }

@@ -579,17 +579,18 @@ void free_initmem(void)
 	memset(__initdata_begin, POISON_FREE_INITDATA,
 		__initdata_end - __initdata_begin);
 	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+			__pa_symbol(&__init_begin),
+			__pa_symbol(&__init_end));
 }
 
 #ifdef CONFIG_DEBUG_RODATA
 
 void mark_rodata_ro(void)
 {
-	unsigned long addr = (unsigned long)__start_rodata;
+	unsigned long addr = (unsigned long)__va(__pa_symbol(&__start_rodata));
+	unsigned long end  = (unsigned long)__va(__pa_symbol(&__end_rodata));
 
-	for (; addr < (unsigned long)__end_rodata; addr += PAGE_SIZE)
+	for (; addr < end; addr += PAGE_SIZE)
 		change_page_attr_addr(addr, 1, PAGE_KERNEL_RO);
 
 	printk ("Write protecting the kernel read-only data: %luk\n",

@@ -608,7 +609,7 @@ void mark_rodata_ro(void)
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	free_init_pages("initrd memory", start, end);
+	free_init_pages("initrd memory", __pa(start), __pa(end));
 }
 #endif
 

Index: linux/arch/x86_64/mm/pageattr.c
===================================================================
@@ -51,7 +51,6 @@ static struct page *split_large_page(uns
 	SetPagePrivate(base);
 	page_private(base) = 0;
 
-	address = __pa(address);
 	addr = address & LARGE_PAGE_MASK; 
 	pbase = (pte_t *)page_address(base);
 	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {

@@ -101,13 +100,12 @@ static inline void save_page(struct page
  * No more special protections in this 2/4MB area - revert to a
  * large page again. 
  */
-static void revert_page(unsigned long address, pgprot_t ref_prot)
+static void revert_page(unsigned long address, unsigned long pfn, pgprot_t ref_prot)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t large_pte;
-	unsigned long pfn;
 
 	pgd = pgd_offset_k(address);
 	BUG_ON(pgd_none(*pgd));

@@ -115,7 +113,6 @@ static void revert_page(unsigned long ad
 	BUG_ON(pud_none(*pud));
 	pmd = pmd_offset(pud, address);
 	BUG_ON(pmd_val(*pmd) & _PAGE_PSE);
-	pfn = (__pa(address) & LARGE_PAGE_MASK) >> PAGE_SHIFT;
 	large_pte = pfn_pte(pfn, ref_prot);
 	large_pte = pte_mkhuge(large_pte);
 	set_pte((pte_t *)pmd, large_pte);

@@ -141,7 +138,8 @@ __change_page_attr(unsigned long address
  			 */
 			struct page *split;
 			ref_prot2 = pte_pgprot(pte_clrhuge(*kpte));
-			split = split_large_page(address, prot, ref_prot2);
+			split = split_large_page(pfn << PAGE_SHIFT, prot,
+							ref_prot2);
 			if (!split)
 				return -ENOMEM;
 			set_pte(kpte, mk_pte(split, ref_prot2));

@@ -160,7 +158,7 @@ __change_page_attr(unsigned long address
 
 	if (page_private(kpte_page) == 0) {
 		save_page(kpte_page);
-		revert_page(address, ref_prot);
+		revert_page(address, pfn, ref_prot);
  	}
 	return 0;
 } 

@@ -180,6 +178,7 @@ __change_page_attr(unsigned long address
  */
 int change_page_attr_addr(unsigned long address, int numpages, pgprot_t prot)
 {
+	unsigned long phys_base_pfn = __pa_symbol(__START_KERNEL_map) >> PAGE_SHIFT;
 	int err = 0; 
 	int i; 
 

@@ -192,10 +191,11 @@ int change_page_attr_addr(unsigned long 
 			break; 
 		/* Handle kernel mapping too which aliases part of the
 		 * lowmem */
-		if (__pa(address) < KERNEL_TEXT_SIZE) {
+		if ((pfn >= phys_base_pfn) &&
+			((pfn - phys_base_pfn) < (KERNEL_TEXT_SIZE >> PAGE_SHIFT))) {
 			unsigned long addr2;
 			pgprot_t prot2;
-			addr2 = __START_KERNEL_map + __pa(address);
+			addr2 = __START_KERNEL_map + ((pfn - phys_base_pfn) << PAGE_SHIFT);
 			/* Make sure the kernel mappings stay executable */
 			prot2 = pte_pgprot(pte_mkexec(pfn_pte(0, prot)));
 			err = __change_page_attr(addr2, pfn, prot2,

Index: linux/include/asm-x86_64/page.h
===================================================================
@@ -102,17 +102,15 @@ typedef struct { unsigned long pgprot; }
 
 /* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol.
    Otherwise you risk miscompilation. */ 
-#define __pa(x)			(((unsigned long)(x)>=__START_KERNEL_map)?(unsigned long)(x) - (unsigned long)__START_KERNEL_map:(unsigned long)(x) - PAGE_OFFSET)
+#define __pa(x)			((unsigned long)(x) - PAGE_OFFSET)
 /* __pa_symbol should be used for C visible symbols.
    This seems to be the official gcc blessed way to do such arithmetic. */ 
 #define __pa_symbol(x)		\
 	({unsigned long v;  \
 	  asm("" : "=r" (v) : "0" (x)); \
-	  __pa(v); })
+	  (v - __START_KERNEL_map); })
 
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
-#define __boot_va(x)		__va(x)
-#define __boot_pa(x)		__pa(x)
 #ifdef CONFIG_FLATMEM
 #define pfn_valid(pfn)		((pfn) < end_pfn)
 #endif

Index: linux/include/asm-x86_64/pgtable.h
===================================================================
@@ -19,7 +19,7 @@ extern pmd_t level2_kernel_pgt[512];
 extern pgd_t init_level4_pgt[];
 extern unsigned long __supported_pte_mask;
 
-#define swapper_pg_dir init_level4_pgt
+#define swapper_pg_dir ((pgd_t *)NULL)
 
 extern void paging_init(void);
 extern void clear_kernel_mapping(unsigned long addr, unsigned long size);

@@ -29,7 +29,7 @@ extern void clear_kernel_mapping(unsigne
  * for zero-mapped memory areas etc..
  */
 extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#define ZERO_PAGE(vaddr) (pfn_to_page(__pa_symbol(&empty_zero_page) >> PAGE_SHIFT))
 
 #endif /* !__ASSEMBLY__ */
 

Index: linux/kernel/power/swap.c
===================================================================
@@ -33,12 +33,14 @@ extern char resume_file[];
 
 #define SWSUSP_SIG	"S1SUSPEND"
 
-static struct swsusp_header {
+struct swsusp_header {
 	char reserved[PAGE_SIZE - 20 - sizeof(sector_t)];
 	sector_t image;
 	char	orig_sig[10];
 	char	sig[10];
-} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
+} __attribute__((packed));
+
+static struct swsusp_header *swsusp_header;
 
 /*
  * General things

@@ -141,14 +143,14 @@ static int mark_swapfiles(sector_t start
 {
 	int error;
 
-	bio_read_page(swsusp_resume_block, &swsusp_header, NULL);
-	if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
-	    !memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
-		memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
-		memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
-		swsusp_header.image = start;
+	bio_read_page(swsusp_resume_block, swsusp_header, NULL);
+	if (!memcmp("SWAP-SPACE",swsusp_header->sig, 10) ||
+	    !memcmp("SWAPSPACE2",swsusp_header->sig, 10)) {
+		memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10);
+		memcpy(swsusp_header->sig,SWSUSP_SIG, 10);
+		swsusp_header->image = start;
 		error = bio_write_page(swsusp_resume_block,
-					&swsusp_header, NULL);
+					swsusp_header, NULL);
 	} else {
 		printk(KERN_ERR "swsusp: Swap header not found!\n");
 		error = -ENODEV;

@@ -564,7 +566,7 @@ int swsusp_read(void)
 	if (error < PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
-	error = get_swap_reader(&handle, swsusp_header.image);
+	error = get_swap_reader(&handle, swsusp_header->image);
 	if (!error)
 		error = swap_read_page(&handle, header, NULL);
 	if (!error)

@@ -591,17 +593,17 @@ int swsusp_check(void)
 	resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
 	if (!IS_ERR(resume_bdev)) {
 		set_blocksize(resume_bdev, PAGE_SIZE);
-		memset(&swsusp_header, 0, sizeof(swsusp_header));
+		memset(swsusp_header, 0, sizeof(PAGE_SIZE));
 		error = bio_read_page(swsusp_resume_block,
-					&swsusp_header, NULL);
+					swsusp_header, NULL);
 		if (error)
 			return error;
 
-		if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
-			memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
+		if (!memcmp(SWSUSP_SIG, swsusp_header->sig, 10)) {
+			memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10);
 			/* Reset swap signature now */
 			error = bio_write_page(swsusp_resume_block,
-						&swsusp_header, NULL);
+						swsusp_header, NULL);
 		} else {
 			return -EINVAL;
 		}

@@ -632,3 +634,13 @@ void swsusp_close(void)
 
 	blkdev_put(resume_bdev);
 }
+
+static int swsusp_header_init(void)
+{
+	swsusp_header = (struct swsusp_header*) __get_free_page(GFP_KERNEL);
+	if (!swsusp_header)
+		panic("Could not allocate memory for swsusp_header\n");
+	return 0;
+}
+
+core_initcall(swsusp_header_init);

Index: linux/arch/x86_64/boot/compressed/misc.c
===================================================================
@@ -358,7 +358,7 @@ asmlinkage void decompress_kernel(void *
 	insize = input_len;
 	inptr  = 0;
 
-	if ((ulg)output & 0x1fffffUL)
+	if ((ulg)output & (__KERNEL_ALIGN - 1))
 		error("Destination address not 2M aligned");
 	if ((ulg)output >= 0xffffffffffUL)
 		error("Destination address too large");

Index: linux/arch/x86_64/kernel/head64.c
===================================================================
@@ -62,6 +62,13 @@ void __init x86_64_start_kernel(char * r
 {
 	int i;
 
+	/*
+	 * Make sure kernel is aligned to 2MB address. Catching it at compile
+	 * time is better. Change your config file and compile the kernel
+	 * for a 2MB aligned address (CONFIG_PHYSICAL_START)
+	 */
+	BUILD_BUG_ON(CONFIG_PHYSICAL_START & (__KERNEL_ALIGN - 1));
+
 	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 

Index: linux/include/asm-x86_64/page.h
===================================================================
@@ -78,6 +78,7 @@ extern unsigned long phys_base;
 #endif /* !__ASSEMBLY__ */
 
 #define __PHYSICAL_START	CONFIG_PHYSICAL_START
+#define __KERNEL_ALIGN		0x200000
 #define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
 #define __START_KERNEL_map	0xffffffff80000000
 #define __PAGE_OFFSET           0xffff810000000000

310 lines not on this page · raw message

Index: linux/include/asm-x86_64/page.h
===================================================================
@@ -61,6 +61,8 @@ typedef struct { unsigned long pgd; } pg
 
 typedef struct { unsigned long pgprot; } pgprot_t;
 
+extern unsigned long phys_base;
+
 #define pte_val(x)	((x).pte)
 #define pmd_val(x)	((x).pmd)
 #define pud_val(x)	((x).pud)

@@ -101,14 +103,14 @@ typedef struct { unsigned long pgprot; }
 #define PAGE_OFFSET		__PAGE_OFFSET
 
 /* Note: __pa(&symbol_visible_to_c) should be always replaced with __pa_symbol.
-   Otherwise you risk miscompilation. */ 
+   Otherwise you risk miscompilation. */
 #define __pa(x)			((unsigned long)(x) - PAGE_OFFSET)
 /* __pa_symbol should be used for C visible symbols.
    This seems to be the official gcc blessed way to do such arithmetic. */ 
 #define __pa_symbol(x)		\
 	({unsigned long v;  \
 	  asm("" : "=r" (v) : "0" (x)); \
-	  (v - __START_KERNEL_map); })
+	  ((v - __START_KERNEL_map) + phys_base); })
 
 #define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
 #ifdef CONFIG_FLATMEM

Index: linux/arch/i386/power/suspend.c
===================================================================
@@ -16,6 +16,9 @@
 /* Defined in arch/i386/power/swsusp.S */
 extern int restore_image(void);
 
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
 /* Pointer to the temporary resume page tables */
 pgd_t *resume_pg_dir;
 

@@ -156,3 +159,14 @@ int swsusp_arch_resume(void)
 	restore_image();
 	return 0;
 }
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}

Index: linux/arch/powerpc/kernel/suspend.c
===================================================================
@@ -0,0 +1,24 @@
+/*
+ * Suspend support specific for power.
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2002 Pavel Machek <[email protected]>
+ * Copyright (c) 2001 Patrick Mochel <[email protected]>
+ */
+
+#include <asm/page.h>
+
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}

Index: linux/arch/x86_64/kernel/suspend.c
===================================================================
@@ -13,6 +13,9 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
+/* References to section boundaries */
+extern const void __nosave_begin, __nosave_end;
+
 struct saved_context saved_context;
 
 unsigned long saved_context_eax, saved_context_ebx, saved_context_ecx, saved_context_edx;

@@ -220,4 +223,15 @@ int swsusp_arch_resume(void)
 	restore_image();
 	return 0;
 }
+
+/*
+ *	pfn_is_nosave - check if given pfn is in the 'nosave' section
+ */
+
+int pfn_is_nosave(unsigned long pfn)
+{
+	unsigned long nosave_begin_pfn = __pa_symbol(&__nosave_begin) >> PAGE_SHIFT;
+	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa_symbol(&__nosave_end)) >> PAGE_SHIFT;
+	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
+}
 #endif /* CONFIG_SOFTWARE_SUSPEND */

Index: linux/kernel/power/power.h
===================================================================
@@ -23,6 +23,8 @@ static inline int pm_suspend_disk(void)
 }
 #endif
 
+extern int pfn_is_nosave(unsigned long);
+
 extern struct mutex pm_mutex;
 
 #define power_attr(_name) \

@@ -37,9 +39,6 @@ static struct subsys_attribute _name##_a
 
 extern struct subsystem power_subsys;
 
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
 /* Preferred image size in bytes (default 500 MB) */
 extern unsigned long image_size;
 extern int in_suspend;

Index: linux/kernel/power/snapshot.c
===================================================================
@@ -651,17 +651,6 @@ static inline unsigned int count_highmem
 #endif /* CONFIG_HIGHMEM */
 
 /**
- *	pfn_is_nosave - check if given pfn is in the 'nosave' section
- */
-
-static inline int pfn_is_nosave(unsigned long pfn)
-{
-	unsigned long nosave_begin_pfn = __pa(&__nosave_begin) >> PAGE_SHIFT;
-	unsigned long nosave_end_pfn = PAGE_ALIGN(__pa(&__nosave_end)) >> PAGE_SHIFT;
-	return (pfn >= nosave_begin_pfn) && (pfn < nosave_end_pfn);
-}
-
-/**
  *	saveable - Determine whether a non-highmem page should be included in
  *	the suspend image.
  *

Index: linux/include/asm-x86_64/suspend.h
===================================================================
@@ -45,12 +45,12 @@ extern unsigned long saved_context_eflag
 extern void fix_processor_context(void);
 
 #ifdef CONFIG_ACPI_SLEEP
-extern unsigned long saved_eip;
-extern unsigned long saved_esp;
-extern unsigned long saved_ebp;
-extern unsigned long saved_ebx;
-extern unsigned long saved_esi;
-extern unsigned long saved_edi;
+extern unsigned long saved_rip;
+extern unsigned long saved_rsp;
+extern unsigned long saved_rbp;
+extern unsigned long saved_rbx;
+extern unsigned long saved_rsi;
+extern unsigned long saved_rdi;
 
 /* routines for saving/restoring kernel state */
 extern int acpi_save_state_mem(void);

Index: linux/arch/x86_64/kernel/setup.c
===================================================================
@@ -329,15 +329,8 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 #ifdef CONFIG_SMP
-	/*
-	 * But first pinch a few for the stack/trampoline stuff
-	 * FIXME: Don't need the extra page at 4K, but need to fix
-	 * trampoline before removing it. (see the GDT stuff)
-	 */
-	reserve_bootmem_generic(PAGE_SIZE, PAGE_SIZE);
-
 	/* Reserve SMP trampoline */
-	reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, PAGE_SIZE);
+	reserve_bootmem_generic(SMP_TRAMPOLINE_BASE, 2*PAGE_SIZE);
 #endif
 
 #ifdef CONFIG_ACPI_SLEEP

diff -r 9a673a220ad6 Documentation/lguest/lguest.c
@@ -30,10 +30,12 @@
 #include <termios.h>
 #include <getopt.h>
 #include <zlib.h>
+typedef unsigned long long u64;
 typedef uint32_t u32;
 typedef uint16_t u16;
 typedef uint8_t u8;
 #include "../../include/linux/lguest_launcher.h"
+#include "../../include/asm-i386/e820.h"
 
 #define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
 #define NET_PEERNUM 1

@@ -915,10 +917,10 @@ static void usage(void)
 
 int main(int argc, char *argv[])
 {
-	unsigned long mem, pgdir, start, page_offset;
+	unsigned long mem, pgdir, start, page_offset, initrd_size = 0;
 	int c, lguest_fd, waker_fd;
 	struct device_list device_list;
-	struct lguest_boot_info *boot = (void *)0;
+	void *boot = (void *)0;
 	const char *initrd_name = NULL;
 
 	device_list.max_infd = -1;

@@ -966,15 +968,24 @@ int main(int argc, char *argv[])
 	map_device_descriptors(&device_list, mem);
 
 	/* Map the initrd image if requested */
-	if (initrd_name)
-		boot->initrd_size = load_initrd(initrd_name, mem);
+	if (initrd_name) {
+		initrd_size = load_initrd(initrd_name, mem);
+		*(unsigned long *)(boot+0x218) = mem - initrd_size;
+		*(unsigned long *)(boot+0x21c) = initrd_size;
+	}
 
 	/* Set up the initial linar pagetables. */
-	pgdir = setup_pagetables(mem, boot->initrd_size, page_offset);
-
-	/* Give the guest the boot information it needs. */
-	concat(boot->cmdline, argv+optind+2);
-	boot->max_pfn = mem/getpagesize();
+	pgdir = setup_pagetables(mem, initrd_size, page_offset);
+
+	/* E820 memory map: ours is a simple, single region. */
+	*(char*)(boot+E820NR) = 1;
+	*((struct e820entry *)(boot+E820MAP)) 
+		= ((struct e820entry) { 0, mem, E820_RAM });
+	/* Command line pointer and command line (at 4096) */
+	*(void **)(boot + 0x228) = boot + 4096;
+	concat(boot + 4096, argv+optind+2);
+	/* Paravirt type: 1 == lguest */
+	*(int *)(boot + 0x23c) = 1;
 
 	lguest_fd = tell_kernel(pgdir, start, page_offset);
 	waker_fd = setup_waker(&device_list);

diff -r 9a673a220ad6 drivers/lguest/lguest.c
@@ -53,7 +53,6 @@ struct lguest_data lguest_data = {
 	.blocked_interrupts = { 1 }, /* Block timer interrupts */
 };
 struct lguest_device_desc *lguest_devices;
-static __initdata const struct lguest_boot_info *boot = __va(0);
 
 static enum paravirt_lazy_mode lazy_mode;
 static void lguest_lazy_mode(enum paravirt_lazy_mode mode)

@@ -378,8 +377,7 @@ static __init char *lguest_memory_setup(
 	/* We do this here because lockcheck barfs if before start_kernel */
 	atomic_notifier_chain_register(&panic_notifier_list, &paniced);
 
-	e820.nr_map = 0;
-	add_memory_region(0, PFN_PHYS(boot->max_pfn), E820_RAM);
+	add_memory_region(E820_MAP->addr, E820_MAP->size, E820_MAP->type);
 	return "LGUEST";
 }
 

@@ -410,8 +408,14 @@ static unsigned lguest_patch(u8 type, u1
 	return insn_len;
 }
 
-__init void lguest_init(void)
-{
+__init void lguest_init(void *boot)
+{
+	/* Copy boot parameters first. */
+	memcpy(boot_params, boot, PARAM_SIZE);
+	memcpy(boot_command_line,
+	       __va(*(unsigned long *)(boot_params + NEW_CL_POINTER)),
+	       COMMAND_LINE_SIZE);
+
 	paravirt_ops.name = "lguest";
 	paravirt_ops.paravirt_enabled = 1;
 	paravirt_ops.kernel_rpl = 1;

@@ -460,7 +464,6 @@ __init void lguest_init(void)
 	paravirt_ops.wbinvd = lguest_wbinvd;
 
 	hcall(LHCALL_LGUEST_INIT, __pa(&lguest_data), 0, 0);
-	strncpy(boot_command_line, boot->cmdline, COMMAND_LINE_SIZE);
 
 	/* We use top of mem for initial pagetables. */
 	init_pg_tables_end = __pa(pg0);

@@ -487,14 +490,6 @@ __init void lguest_init(void)
 
 	add_preferred_console("hvc", 0, NULL);
 
-	if (boot->initrd_size) {
-		/* We stash this at top of memory. */
-		INITRD_START = boot->max_pfn*PAGE_SIZE - boot->initrd_size;
-		INITRD_SIZE = boot->initrd_size;
-		LOADER_TYPE = 0xFF;
-	}
-
 	pm_power_off = lguest_power_off;
 	start_kernel();
 }
-paravirt_probe(lguest_maybe_init);

diff -r 9a673a220ad6 drivers/lguest/lguest_user.c
@@ -7,13 +7,11 @@ static void setup_regs(struct lguest_reg
 static void setup_regs(struct lguest_regs *regs, unsigned long start)
 {
 	/* Write out stack in format lguest expects, so we can switch to it. */
-	regs->edi = LGUEST_MAGIC_EDI;
-	regs->ebp = LGUEST_MAGIC_EBP;
-	regs->esi = LGUEST_MAGIC_ESI;
 	regs->ds = regs->es = regs->ss = __KERNEL_DS|GUEST_PL;
 	regs->cs = __KERNEL_CS|GUEST_PL;
 	regs->eflags = 0x202; 	/* Interrupts enabled. */
 	regs->eip = start;
+	/* esi points to our boot information (physical address 0) */
 }
 
 /* + addr */

diff -r 9a673a220ad6 include/asm-i386/paravirt.h
@@ -221,11 +221,6 @@ struct paravirt_ops
 	void (*irq_enable_sysexit)(void);
 	void (*iret)(void);
 };
-
-/* Mark a paravirt probe function. */
-#define paravirt_probe(fn)						\
- static asmlinkage void (*__paravirtprobe_##fn)(void) __attribute_used__ \
-		__attribute__((__section__(".paravirtprobe"))) = fn
 
 extern struct paravirt_ops paravirt_ops;
 

diff -r 9a673a220ad6 include/linux/lguest.h
@@ -2,11 +2,6 @@
  * this is subject to wild and random change between versions. */
 #ifndef _ASM_LGUEST_H
 #define _ASM_LGUEST_H
-
-/* These are randomly chosen numbers which indicate we're an lguest at boot */
-#define LGUEST_MAGIC_EBP 0x4C687970
-#define LGUEST_MAGIC_EDI 0x652D4D65
-#define LGUEST_MAGIC_ESI 0xFFFFFFFF
 
 #ifndef __ASSEMBLY__
 #include <asm/irq.h>

diff -r 9a673a220ad6 include/linux/lguest_launcher.h
@@ -15,14 +15,6 @@ struct lguest_dma
  	u32 used_len;
 	u32 addr[LGUEST_MAX_DMA_SECTIONS];
 	u16 len[LGUEST_MAX_DMA_SECTIONS];
-};
-
-/* This is found at address 0. */
-struct lguest_boot_info
-{
-	u32 max_pfn;
-	u32 initrd_size;
-	char cmdline[256];
 };
 
 struct lguest_block_page

diff -r 9a673a220ad6 Documentation/lguest/lguest.c
@@ -30,10 +30,12 @@
 #include <termios.h>
 #include <getopt.h>
 #include <zlib.h>
+typedef unsigned long long u64;
 typedef uint32_t u32;
 typedef uint16_t u16;
 typedef uint8_t u8;
 #include "../../include/linux/lguest_launcher.h"
+#include "../../include/asm-i386/e820.h"
 
 #define PAGE_PRESENT 0x7 	/* Present, RW, Execute */
 #define NET_PEERNUM 1

@@ -915,10 +917,10 @@ static void usage(void)
 
 int main(int argc, char *argv[])
 {
-	unsigned long mem, pgdir, start, page_offset;
+	unsigned long mem, pgdir, start, page_offset, initrd_size = 0;
 	int c, lguest_fd, waker_fd;
 	struct device_list device_list;
-	struct lguest_boot_info *boot = (void *)0;
+	void *boot = (void *)0;
 	const char *initrd_name = NULL;
 
 	device_list.max_infd = -1;

@@ -966,15 +968,24 @@ int main(int argc, char *argv[])
 	map_device_descriptors(&device_list, mem);
 
 	/* Map the initrd image if requested */
-	if (initrd_name)
-		boot->initrd_size = load_initrd(initrd_name, mem);
+	if (initrd_name) {
+		initrd_size = load_initrd(initrd_name, mem);
+		*(unsigned long *)(boot+0x218) = mem - initrd_size;
+		*(unsigned long *)(boot+0x21c) = initrd_size;
+	}
 
 	/* Set up the initial linar pagetables. */
-	pgdir = setup_pagetables(mem, boot->initrd_size, page_offset);
-
-	/* Give the guest the boot information it needs. */
-	concat(boot->cmdline, argv+optind+2);
-	boot->max_pfn = mem/getpagesize();
+	pgdir = setup_pagetables(mem, initrd_size, page_offset);
+
+	/* E820 memory map: ours is a simple, single region. */
+	*(char*)(boot+E820NR) = 1;
+	*((struct e820entry *)(boot+E820MAP)) 
+		= ((struct e820entry) { 0, mem, E820_RAM });
+	/* Command line pointer and command line (at 4096) */
+	*(void **)(boot + 0x228) = boot + 4096;
+	concat(boot + 4096, argv+optind+2);
+	/* Paravirt type: 1 == lguest */
+	*(int *)(boot + 0x23c) = 1;
 
 	lguest_fd = tell_kernel(pgdir, start, page_offset);
 	waker_fd = setup_waker(&device_list);

diff -r 9a673a220ad6 drivers/lguest/lguest.c
@@ -53,7 +53,6 @@ struct lguest_data lguest_data = {
 	.blocked_interrupts = { 1 }, /* Block timer interrupts */
 };
 struct lguest_device_desc *lguest_devices;
-static __initdata const struct lguest_boot_info *boot = __va(0);
 
 static enum paravirt_lazy_mode lazy_mode;
 static void lguest_lazy_mode(enum paravirt_lazy_mode mode)

@@ -378,8 +377,7 @@ static __init char *lguest_memory_setup(
 	/* We do this here because lockcheck barfs if before start_kernel */
 	atomic_notifier_chain_register(&panic_notifier_list, &paniced);
 
-	e820.nr_map = 0;
-	add_memory_region(0, PFN_PHYS(boot->max_pfn), E820_RAM);
+	add_memory_region(E820_MAP->addr, E820_MAP->size, E820_MAP->type);
 	return "LGUEST";
 }
 

@@ -410,8 +408,14 @@ static unsigned lguest_patch(u8 type, u1
 	return insn_len;
 }
 
-__init void lguest_init(void)
-{
+__init void lguest_init(void *boot)
+{
+	/* Copy boot parameters first. */
+	memcpy(boot_params, boot, PARAM_SIZE);
+	memcpy(boot_command_line,
+	       __va(*(unsigned long *)(boot_params + NEW_CL_POINTER)),
+	       COMMAND_LINE_SIZE);
+
 	paravirt_ops.name = "lguest";
 	paravirt_ops.paravirt_enabled = 1;
 	paravirt_ops.kernel_rpl = 1;

@@ -460,7 +464,6 @@ __init void lguest_init(void)
 	paravirt_ops.wbinvd = lguest_wbinvd;
 
 	hcall(LHCALL_LGUEST_INIT, __pa(&lguest_data), 0, 0);
-	strncpy(boot_command_line, boot->cmdline, COMMAND_LINE_SIZE);
 
 	/* We use top of mem for initial pagetables. */
 	init_pg_tables_end = __pa(pg0);

@@ -487,14 +490,6 @@ __init void lguest_init(void)
 
 	add_preferred_console("hvc", 0, NULL);
 
-	if (boot->initrd_size) {
-		/* We stash this at top of memory. */
-		INITRD_START = boot->max_pfn*PAGE_SIZE - boot->initrd_size;
-		INITRD_SIZE = boot->initrd_size;
-		LOADER_TYPE = 0xFF;
-	}
-
 	pm_power_off = lguest_power_off;
 	start_kernel();
 }
-paravirt_probe(lguest_maybe_init);

diff -r 9a673a220ad6 drivers/lguest/lguest_user.c
@@ -7,13 +7,11 @@ static void setup_regs(struct lguest_reg
 static void setup_regs(struct lguest_regs *regs, unsigned long start)
 {
 	/* Write out stack in format lguest expects, so we can switch to it. */
-	regs->edi = LGUEST_MAGIC_EDI;
-	regs->ebp = LGUEST_MAGIC_EBP;
-	regs->esi = LGUEST_MAGIC_ESI;
 	regs->ds = regs->es = regs->ss = __KERNEL_DS|GUEST_PL;
 	regs->cs = __KERNEL_CS|GUEST_PL;
 	regs->eflags = 0x202; 	/* Interrupts enabled. */
 	regs->eip = start;
+	/* esi points to our boot information (physical address 0) */
 }
 
 /* + addr */