Merge branches 'x86/acpi', 'x86/asm', 'x86/cpudetect', 'x86/crashdump',...

Merge branches 'x86/acpi', 'x86/asm', 'x86/cpudetect', 'x86/crashdump', 'x86/debug', 'x86/defconfig', 'x86/doc', 'x86/header-fixes', 'x86/headers' and 'x86/minor-fixes' into x86/core

arch/ia64/kernel/acpi.c

@@ -199,6 +199,10 @@ char *__init __acpi_map_table(unsigned long phys_addr, unsigned long size)
 	return __va(phys_addr);
 }
 
+char *__init __acpi_unmap_table(unsigned long virt_addr, unsigned long size)
+{
+}
+
 /* --------------------------------------------------------------------------
                             Boot-time Table Parsing
    -------------------------------------------------------------------------- */

arch/x86/include/asm/acpi.h

@@ -102,9 +102,6 @@ static inline void disable_acpi(void)
 	acpi_noirq = 1;
 }
 
-/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
-#define FIX_ACPI_PAGES 4
-
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }

arch/x86/include/asm/calling.h

 /*
- * Some macros to handle stack frames in assembly.
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+  arguments           |  callee-saved      | extra caller-saved | return
+ [callee-clobbered]   |                    | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11             | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+   functions when it sees tail-call optimization possibilities) rflags is
+   clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*]  In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+      bit more complex: up to 128 bits width we return small structures
+      straight in rax, rdx. For structures larger than that (3 words or
+      larger) the caller puts a pointer to an on-stack return struct
+      [allocated in the caller's stack frame] into the first argument - i.e.
+      into rdi. All other arguments shift up by one in this case.
+      Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+  arguments         | callee-saved        | extra caller-saved | return
+ [callee-clobbered] |                     | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx        | ebx edi esi ebp [*] | <none>             | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+   is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*]  In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+      semantics as on 64-bit: edx can be used for a second return value
+      (i.e. covering integer and structure sizes up to 64 bits) - after that
+      it gets more complex and more expensive: 3-word or larger struct returns
+      get done in the caller's frame and the pointer to the return struct goes
+      into regparm0, i.e. eax - the other arguments shift up and the
+      function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
  */
 
 #define R15		  0
@@ -9,7 +59,7 @@
 #define RBP		 32
 #define RBX		 40
 
-/* arguments: interrupts/non tracing syscalls only save upto here*/
+/* arguments: interrupts/non tracing syscalls only save up to here: */
 #define R11		 48
 #define R10		 56
 #define R9		 64
@@ -22,7 +72,7 @@
 #define ORIG_RAX	120       /* + error_code */
 /* end of arguments */
 
-/* cpu exception frame or undefined in case of fast syscall. */
+/* cpu exception frame or undefined in case of fast syscall: */
 #define RIP		128
 #define CS		136
 #define EFLAGS		144

arch/x86/include/asm/fixmap_32.h

@@ -95,10 +95,6 @@ enum fixed_addresses {
 			(__end_of_permanent_fixed_addresses & 255),
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
 	FIX_WP_TEST,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif

arch/x86/include/asm/fixmap_64.h

@@ -50,10 +50,6 @@ enum fixed_addresses {
 	FIX_PARAVIRT_BOOTMAP,
 #endif
 	__end_of_permanent_fixed_addresses,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
 	FIX_OHCI1394_BASE,
 #endif

arch/x86/include/asm/io.h

@@ -5,6 +5,7 @@
 
 #include <linux/compiler.h>
 #include <asm-generic/int-ll64.h>
+#include <asm/page.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -80,6 +81,95 @@ static inline void writeq(__u64 val, volatile void __iomem *addr)
 #define readq			readq
 #define writeq			writeq
 
+/**
+ *	virt_to_phys	-	map virtual addresses to physical
+ *	@address: address to remap
+ *
+ *	The returned physical address is the physical (CPU) mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses directly mapped or allocated via kmalloc.
+ *
+ *	This function does not give bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline phys_addr_t virt_to_phys(volatile void *address)
+{
+	return __pa(address);
+}
+
+/**
+ *	phys_to_virt	-	map physical address to virtual
+ *	@address: address to remap
+ *
+ *	The returned virtual address is a current CPU mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses that have a kernel mapping
+ *
+ *	This function does not handle bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline void *phys_to_virt(phys_addr_t address)
+{
+	return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus virt_to_phys
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * If the area you are trying to map is a PCI BAR you should have a
+ * look at pci_iomap().
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
+
+/*
+ * The default ioremap() behavior is non-cached:
+ */
+static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
+{
+	return ioremap_nocache(offset, size);
+}
+
+extern void iounmap(volatile void __iomem *addr);
+
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+
 #ifdef CONFIG_X86_32
 # include "io_32.h"
 #else

arch/x86/include/asm/io_32.h

@@ -51,92 +51,6 @@
  */
 #define xlate_dev_kmem_ptr(p)	p
 
-/**
- *	virt_to_phys	-	map virtual addresses to physical
- *	@address: address to remap
- *
- *	The returned physical address is the physical (CPU) mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses directly mapped or allocated via kmalloc.
- *
- *	This function does not give bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-/**
- *	phys_to_virt	-	map physical address to virtual
- *	@address: address to remap
- *
- *	The returned virtual address is a current CPU mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses that have a kernel mapping
- *
- *	This function does not handle bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
-/**
- * ioremap     -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * If the area you are trying to map is a PCI BAR you should have a
- * look at pci_iomap().
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
 static inline void
 memset_io(volatile void __iomem *addr, unsigned char val, int count)
 {

arch/x86/include/asm/io_64.h

@@ -140,67 +140,8 @@ __OUTS(l)
 
 #include <linux/vmalloc.h>
 
-#ifndef __i386__
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-#endif
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
 #include <asm-generic/iomap.h>
 
-/*
- * This one maps high address device memory and turns off caching for that area.
- * it's useful if some control registers are in such an area and write combining
- * or read caching is not desirable:
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
 void __memcpy_fromio(void *, unsigned long, unsigned);
 void __memcpy_toio(unsigned long, const void *, unsigned);
 

arch/x86/include/asm/kexec.h

@@ -9,23 +9,8 @@
 # define PAGES_NR		4
 #else
 # define PA_CONTROL_PAGE	0
-# define VA_CONTROL_PAGE	1
-# define PA_PGD			2
-# define VA_PGD			3
-# define PA_PUD_0		4
-# define VA_PUD_0		5
-# define PA_PMD_0		6
-# define VA_PMD_0		7
-# define PA_PTE_0		8
-# define VA_PTE_0		9
-# define PA_PUD_1		10
-# define VA_PUD_1		11
-# define PA_PMD_1		12
-# define VA_PMD_1		13
-# define PA_PTE_1		14
-# define VA_PTE_1		15
-# define PA_TABLE_PAGE		16
-# define PAGES_NR		17
+# define PA_TABLE_PAGE		1
+# define PAGES_NR		2
 #endif
 
 #ifdef CONFIG_X86_32
@@ -157,9 +142,9 @@ relocate_kernel(unsigned long indirection_page,
 		unsigned long start_address) ATTRIB_NORET;
 #endif
 
-#ifdef CONFIG_X86_32
 #define ARCH_HAS_KIMAGE_ARCH
 
+#ifdef CONFIG_X86_32
 struct kimage_arch {
 	pgd_t *pgd;
 #ifdef CONFIG_X86_PAE
@@ -169,6 +154,12 @@ struct kimage_arch {
 	pte_t *pte0;
 	pte_t *pte1;
 };
+#else
+struct kimage_arch {
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+};
 #endif
 
 #endif /* __ASSEMBLY__ */

arch/x86/include/asm/page.h

@@ -95,6 +95,11 @@ static inline pgdval_t native_pgd_val(pgd_t pgd)
 	return pgd.pgd;
 }
 
+static inline pgdval_t pgd_flags(pgd_t pgd)
+{
+	return native_pgd_val(pgd) & PTE_FLAGS_MASK;
+}
+
 #if PAGETABLE_LEVELS >= 3
 #if PAGETABLE_LEVELS == 4
 typedef struct { pudval_t pud; } pud_t;
@@ -117,6 +122,11 @@ static inline pudval_t native_pud_val(pud_t pud)
 }
 #endif	/* PAGETABLE_LEVELS == 4 */
 
+static inline pudval_t pud_flags(pud_t pud)
+{
+	return native_pud_val(pud) & PTE_FLAGS_MASK;
+}
+
 typedef struct { pmdval_t pmd; } pmd_t;
 
 static inline pmd_t native_make_pmd(pmdval_t val)
@@ -128,6 +138,7 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 {
 	return pmd.pmd;
 }
+
 #else  /* PAGETABLE_LEVELS == 2 */
 #include <asm-generic/pgtable-nopmd.h>
 
@@ -137,6 +148,11 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 }
 #endif	/* PAGETABLE_LEVELS >= 3 */
 
+static inline pmdval_t pmd_flags(pmd_t pmd)
+{
+	return native_pmd_val(pmd) & PTE_FLAGS_MASK;
+}
+
 static inline pte_t native_make_pte(pteval_t val)
 {
 	return (pte_t) { .pte = val };

arch/x86/include/asm/pgtable-2level.h

@@ -53,8 +53,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define pte_none(x)		(!(x).pte_low)
-
 /*
  * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
  * split up the 29 bits of offset into this range:

arch/x86/include/asm/pgtable-3level.h

@@ -18,21 +18,6 @@
 	printk("%s:%d: bad pgd %p(%016Lx).\n",				\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
-static inline int pud_none(pud_t pud)
-{
-	return pud_val(pud) == 0;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-	return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
-}
-
-static inline int pud_present(pud_t pud)
-{
-	return pud_val(pud) & _PAGE_PRESENT;
-}
-
 /* Rules for using set_pte: the pte being assigned *must* be
  * either not present or in a state where the hardware will
  * not attempt to update the pte.  In places where this is
@@ -120,15 +105,6 @@ static inline void pud_clear(pud_t *pudp)
 		write_cr3(pgd);
 }
 
-#define pud_page(pud) pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
-
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *)pud_page_vaddr(*(pud)) +	\
-				  pmd_index(address))
-
 #ifdef CONFIG_SMP
 static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 {
@@ -145,17 +121,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
 #define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
 #endif
 
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t a, pte_t b)
-{
-	return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
-}
-
-static inline int pte_none(pte_t pte)
-{
-	return !pte.pte_low && !pte.pte_high;
-}
-
 /*
  * Bits 0, 6 and 7 are taken in the low part of the pte,
  * put the 32 bits of offset into the high part.

arch/x86/include/asm/pgtable.h

 #ifndef _ASM_X86_PGTABLE_H
 #define _ASM_X86_PGTABLE_H
 
+#include <asm/page.h>
+
 #define FIRST_USER_ADDRESS	0
 
 #define _PAGE_BIT_PRESENT	0	/* is present */
@@ -236,7 +238,7 @@ static inline unsigned long pte_pfn(pte_t pte)
 
 static inline int pmd_large(pmd_t pte)
 {
-	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+	return (pmd_flags(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
 		(_PAGE_PSE | _PAGE_PRESENT);
 }
 
@@ -465,6 +467,190 @@ static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
 # include "pgtable_64.h"
 #endif
 
+#ifndef __ASSEMBLY__
+#include <linux/mm_types.h>
+
+static inline int pte_none(pte_t pte)
+{
+	return !pte.pte;
+}
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t a, pte_t b)
+{
+	return a.pte == b.pte;
+}
+
+static inline int pte_present(pte_t a)
+{
+	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
+
+static inline int pmd_present(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_PRESENT;
+}
+
+static inline int pmd_none(pmd_t pmd)
+{
+	/* Only check low word on 32-bit platforms, since it might be
+	   out of sync with upper half. */
+	return (unsigned long)native_pmd_val(pmd) == 0;
+}
+
+static inline unsigned long pmd_page_vaddr(pmd_t pmd)
+{
+	return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pmd_page(pmd)	pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+static inline unsigned pmd_index(unsigned long address)
+{
+	return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
+}
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * (Currently stuck as a macro because of indirect forward reference
+ * to linux/mm.h:page_to_nid())
+ */
+#define mk_pte(page, pgprot)   pfn_pte(page_to_pfn(page), (pgprot))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this function returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+static inline unsigned pte_index(unsigned long address)
+{
+	return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
+}
+
+static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
+{
+	return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
+
+static inline unsigned long pages_to_mb(unsigned long npg)
+{
+	return npg >> (20 - PAGE_SHIFT);
+}
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#if PAGETABLE_LEVELS == 2
+static inline int pud_large(pud_t pud)
+{
+	return 0;
+}
+#endif
+
+#if PAGETABLE_LEVELS > 2
+static inline int pud_none(pud_t pud)
+{
+	return native_pud_val(pud) == 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pud_page_vaddr(pud_t pud)
+{
+	return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pud_page(pud)		pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
+
+/* Find an entry in the second-level page table.. */
+static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
+{
+	return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
+}
+
+static inline unsigned long pmd_pfn(pmd_t pmd)
+{
+	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+static inline int pud_large(pud_t pud)
+{
+	return (pud_flags(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+		(_PAGE_PSE | _PAGE_PRESENT);
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+#endif	/* PAGETABLE_LEVELS > 2 */
+
+#if PAGETABLE_LEVELS > 3
+static inline int pgd_present(pgd_t pgd)
+{
+	return pgd_flags(pgd) & _PAGE_PRESENT;
+}
+
+static inline unsigned long pgd_page_vaddr(pgd_t pgd)
+{
+	return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
+}
+
+/*
+ * Currently stuck as a macro due to indirect forward reference to
+ * linux/mmzone.h's __section_mem_map_addr() definition:
+ */
+#define pgd_page(pgd)		pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
+
+/* to find an entry in a page-table-directory. */
+static inline unsigned pud_index(unsigned long address)
+{
+	return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
+}
+
+static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
+{
+	return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
+}
+
+static inline int pgd_bad(pgd_t pgd)
+{
+	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+}
+
+static inline int pgd_none(pgd_t pgd)
+{
+	return !native_pgd_val(pgd);
+}
+#endif	/* PAGETABLE_LEVELS > 3 */
+
+#endif	/* __ASSEMBLY__ */
+
 /*
  * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
  *

arch/x86/include/asm/pgtable_32.h

@@ -85,55 +85,12 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 /* The boot page tables (all created as a single array) */
 extern unsigned long pg0[];
 
-#define pte_present(x)	((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
-#define pmd_none(x)	(!(unsigned long)pmd_val((x)))
-#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
-#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
 #ifdef CONFIG_X86_PAE
 # include <asm/pgtable-3level.h>
 #else
 # include <asm/pgtable-2level.h>
 #endif
 
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
-
-static inline int pud_large(pud_t pud) { return 0; }
-
-/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-#define pmd_index(address)				\
-	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this macro returns the index of the entry in the pte page which would
- * control the given virtual address
- */
-#define pte_index(address)					\
-	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address)				\
-	((pte_t *)pmd_page_vaddr(*(dir)) +  pte_index((address)))
-
-#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_page_vaddr(pmd)					\
-	((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK))
-
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address)					\
 	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +		\
@@ -176,7 +133,4 @@ do {						\
 #define kern_addr_valid(kaddr)	(0)
 #endif
 
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
-	remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 #endif /* _ASM_X86_PGTABLE_32_H */

arch/x86/include/asm/pgtable_64.h

@@ -66,9 +66,6 @@ extern void paging_init(void);
 	printk("%s:%d: bad pgd %p(%016lx).\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
-#define pgd_none(x)	(!pgd_val(x))
-#define pud_none(x)	(!pud_val(x))
-
 struct mm_struct;
 
 void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
@@ -133,8 +130,6 @@ static inline void native_pgd_clear(pgd_t *pgd)
 	native_set_pgd(pgd, native_make_pgd(0));
 }
 
-#define pte_same(a, b)		((a).pte == (b).pte)
-
 #endif /* !__ASSEMBLY__ */
 
 #define PMD_SIZE	(_AC(1, UL) << PMD_SHIFT)
@@ -155,26 +150,6 @@ static inline void native_pgd_clear(pgd_t *pgd)
 
 #ifndef __ASSEMBLY__
 
-static inline int pgd_bad(pgd_t pgd)
-{
-	return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-	return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pmd_bad(pmd_t pmd)
-{
-	return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-#define pte_none(x)	(!pte_val((x)))
-#define pte_present(x)	(pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-#define pages_to_mb(x)	((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
-
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
@@ -183,41 +158,12 @@ static inline int pmd_bad(pmd_t pmd)
 /*
  * Level 4 access.
  */
-#define pgd_page_vaddr(pgd)						\
-	((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
-#define pgd_page(pgd)		(pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
 static inline int pgd_large(pgd_t pgd) { return 0; }
 #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
-/* to find an entry in a page-table-directory. */
-#define pud_page_vaddr(pud)						\
-	((unsigned long)__va(pud_val((pud)) & PHYSICAL_PAGE_MASK))
-#define pud_page(pud)	(pfn_to_page(pud_val((pud)) >> PAGE_SHIFT))
-#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
-#define pud_offset(pgd, address)					\
-	((pud_t *)pgd_page_vaddr(*(pgd)) + pud_index((address)))
-#define pud_present(pud) (pud_val((pud)) & _PAGE_PRESENT)
-
-static inline int pud_large(pud_t pte)
-{
-	return (pud_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
-		(_PAGE_PSE | _PAGE_PRESENT);
-}
 
 /* PMD  - Level 2 access */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
-#define pmd_page(pmd)		(pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-#define pmd_offset(dir, address) ((pmd_t *)pud_page_vaddr(*(dir)) + \
-				  pmd_index(address))
-#define pmd_none(x)	(!pmd_val((x)))
-#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
-#define pfn_pmd(nr, prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val((prot))))
-#define pmd_pfn(x)  ((pmd_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
-
 #define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
 #define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) |	\
 					    _PAGE_FILE })
@@ -225,13 +171,6 @@ static inline int pud_large(pud_t pte)
 
 /* PTE - Level 1 access. */
 
-/* page, protection -> pte */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn((page)), (pgprot))
-
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
-					 pte_index((address)))
-
 /* x86-64 always has all page tables mapped. */
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
 #define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
@@ -265,9 +204,6 @@ extern int direct_gbpages;
 extern int kern_addr_valid(unsigned long addr);
 extern void cleanup_highmap(void);
 
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
-	remap_pfn_range(vma, vaddr, pfn, size, prot)
-
 #define HAVE_ARCH_UNMAPPED_AREA
 #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
 

arch/x86/kernel/acpi/boot.c

@@ -108,35 +108,18 @@ enum acpi_irq_model_id acpi_irq_model = ACPI_IRQ_MODEL_PIC;
  */
 char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 {
-	unsigned long base, offset, mapped_size;
-	int idx;
 
 	if (!phys || !size)
 		return NULL;
 
-	if (phys+size <= (max_low_pfn_mapped << PAGE_SHIFT))
-		return __va(phys);
-
-	offset = phys & (PAGE_SIZE - 1);
-	mapped_size = PAGE_SIZE - offset;
-	clear_fixmap(FIX_ACPI_END);
-	set_fixmap(FIX_ACPI_END, phys);
-	base = fix_to_virt(FIX_ACPI_END);
-
-	/*
-	 * Most cases can be covered by the below.
-	 */
-	idx = FIX_ACPI_END;
-	while (mapped_size < size) {
-		if (--idx < FIX_ACPI_BEGIN)
-			return NULL;	/* cannot handle this */
-		phys += PAGE_SIZE;
-		clear_fixmap(idx);
-		set_fixmap(idx, phys);
-		mapped_size += PAGE_SIZE;
-	}
+	return early_ioremap(phys, size);
+}
+void __init __acpi_unmap_table(char *map, unsigned long size)
+{
+	if (!map || !size)
+		return;
 
-	return ((unsigned char *)base + offset);
+	early_iounmap(map, size);
 }
 
 #ifdef CONFIG_PCI_MMCONFIG

arch/x86/kernel/apic.c

@@ -555,7 +555,8 @@ static void __init lapic_cal_handler(struct clock_event_device *dev)
 	}
 }
 
-static int __init calibrate_by_pmtimer(long deltapm, long *delta)
+static int __init
+calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 {
 	const long pm_100ms = PMTMR_TICKS_PER_SEC / 10;
 	const long pm_thresh = pm_100ms / 100;
@@ -566,7 +567,7 @@ static int __init calibrate_by_pmtimer(long deltapm, long *delta)
 	return -1;
 #endif
 
-	apic_printk(APIC_VERBOSE, "... PM timer delta = %ld\n", deltapm);
+	apic_printk(APIC_VERBOSE, "... PM-Timer delta = %ld\n", deltapm);
 
 	/* Check, if the PM timer is available */
 	if (!deltapm)
@@ -576,19 +577,30 @@ static int __init calibrate_by_pmtimer(long deltapm, long *delta)
 
 	if (deltapm > (pm_100ms - pm_thresh) &&
 	    deltapm < (pm_100ms + pm_thresh)) {
-		apic_printk(APIC_VERBOSE, "... PM timer result ok\n");
-	} else {
-		res = (((u64)deltapm) *  mult) >> 22;
-		do_div(res, 1000000);
-		pr_warning("APIC calibration not consistent "
-			"with PM Timer: %ldms instead of 100ms\n",
-			(long)res);
-		/* Correct the lapic counter value */
-		res = (((u64)(*delta)) * pm_100ms);
+		apic_printk(APIC_VERBOSE, "... PM-Timer result ok\n");
+		return 0;
+	}
+
+	res = (((u64)deltapm) *  mult) >> 22;
+	do_div(res, 1000000);
+	pr_warning("APIC calibration not consistent "
+		   "with PM-Timer: %ldms instead of 100ms\n",(long)res);
+
+	/* Correct the lapic counter value */
+	res = (((u64)(*delta)) * pm_100ms);
+	do_div(res, deltapm);
+	pr_info("APIC delta adjusted to PM-Timer: "
+		"%lu (%ld)\n", (unsigned long)res, *delta);
+	*delta = (long)res;
+
+	/* Correct the tsc counter value */
+	if (cpu_has_tsc) {
+		res = (((u64)(*deltatsc)) * pm_100ms);
 		do_div(res, deltapm);
-		pr_info("APIC delta adjusted to PM-Timer: "
-			"%lu (%ld)\n", (unsigned long)res, *delta);
-		*delta = (long)res;
+		apic_printk(APIC_VERBOSE, "TSC delta adjusted to "
+					  "PM-Timer: %lu (%ld) \n",
+					(unsigned long)res, *deltatsc);
+		*deltatsc = (long)res;
 	}
 
 	return 0;
@@ -599,7 +611,7 @@ static int __init calibrate_APIC_clock(void)
 	struct clock_event_device *levt = &__get_cpu_var(lapic_events);
 	void (*real_handler)(struct clock_event_device *dev);
 	unsigned long deltaj;
-	long delta;
+	long delta, deltatsc;
 	int pm_referenced = 0;
 
 	local_irq_disable();
@@ -629,9 +641,11 @@ static int __init calibrate_APIC_clock(void)
 	delta = lapic_cal_t1 - lapic_cal_t2;
 	apic_printk(APIC_VERBOSE, "... lapic delta = %ld\n", delta);
 
+	deltatsc = (long)(lapic_cal_tsc2 - lapic_cal_tsc1);
+
 	/* we trust the PM based calibration if possible */
 	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
-					&delta);
+					&delta, &deltatsc);
 
 	/* Calculate the scaled math multiplication factor */
 	lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
@@ -649,11 +663,10 @@ static int __init calibrate_APIC_clock(void)
 		    calibration_result);
 
 	if (cpu_has_tsc) {
-		delta = (long)(lapic_cal_tsc2 - lapic_cal_tsc1);
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
 			    "%ld.%04ld MHz.\n",
-			    (delta / LAPIC_CAL_LOOPS) / (1000000 / HZ),
-			    (delta / LAPIC_CAL_LOOPS) % (1000000 / HZ));
+			    (deltatsc / LAPIC_CAL_LOOPS) / (1000000 / HZ),
+			    (deltatsc / LAPIC_CAL_LOOPS) % (1000000 / HZ));
 	}
 
 	apic_printk(APIC_VERBOSE, "..... host bus clock speed is "

arch/x86/kernel/dumpstack.c

@@ -99,7 +99,7 @@ print_context_stack(struct thread_info *tinfo,
 				frame = frame->next_frame;
 				bp = (unsigned long) frame;
 			} else {
-				ops->address(data, addr, bp == 0);
+				ops->address(data, addr, 0);
 			}
 			print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
 		}

arch/x86/kernel/early_printk.c

@@ -13,8 +13,8 @@
 #include <asm/setup.h>
 #include <xen/hvc-console.h>
 #include <asm/pci-direct.h>
-#include <asm/pgtable.h>
 #include <asm/fixmap.h>
+#include <asm/pgtable.h>
 #include <linux/usb/ehci_def.h>
 
 /* Simple VGA output */

arch/x86/kernel/es7000_32.c

@@ -287,24 +287,31 @@ int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
 {
 	struct acpi_table_header *header = NULL;
 	int i = 0;
+	acpi_size tbl_size;
 
-	while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) {
+	while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) {
 		if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) {
 			struct oem_table *t = (struct oem_table *)header;
 
 			oem_addrX = t->OEMTableAddr;
 			oem_size = t->OEMTableSize;
+			early_acpi_os_unmap_memory(header, tbl_size);
 
 			*oem_addr = (unsigned long)__acpi_map_table(oem_addrX,
 								    oem_size);
 			return 0;
 		}
+		early_acpi_os_unmap_memory(header, tbl_size);
 	}
 	return -1;
 }
 
 void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
 {
+	if (!oem_addr)
+		return;
+
+	__acpi_unmap_table((char *)oem_addr, oem_size);
 }
 #endif
 

arch/x86/kernel/machine_kexec_64.c

@@ -18,15 +18,6 @@
 #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;
@@ -107,12 +98,65 @@ static int init_level4_page(struct kimage *image, pgd_t *level4p,
 	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;
+	return init_transition_pgtable(image, level4p);
 }
 
 static void set_idt(void *newidt, u16 limit)
@@ -174,7 +218,7 @@ int machine_kexec_prepare(struct kimage *image)
 
 void machine_kexec_cleanup(struct kimage *image)
 {
-	return;
+	free_transition_pgtable(image);
 }
 
 /*
@@ -195,22 +239,6 @@ void machine_kexec(struct kimage *image)
 	memcpy(control_page, relocate_kernel, PAGE_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[PA_TABLE_PAGE] =
 	  (unsigned long)__pa(page_address(image->control_code_page));
 

arch/x86/kernel/relocate_kernel_64.S

@@ -29,122 +29,6 @@ relocate_kernel:
 	 * %rdx start address
 	 */
 
-	/* map the control page at its virtual address */
-
-	movq	$0x0000ff8000000000, %r10        /* mask */
-	mov	$(39 - 3), %cl                   /* bits to shift */
-	movq	PTR(VA_CONTROL_PAGE)(%rsi), %r11 /* address to map */
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PGD)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PUD_0)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PUD_0)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PMD_0)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PMD_0)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PTE_0)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PTE_0)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_CONTROL_PAGE)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	/* identity map the control page at its physical address */
-
-	movq	$0x0000ff8000000000, %r10        /* mask */
-	mov	$(39 - 3), %cl                   /* bits to shift */
-	movq	PTR(PA_CONTROL_PAGE)(%rsi), %r11 /* address to map */
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PGD)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PUD_1)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PUD_1)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PMD_1)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PMD_1)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_PTE_1)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-	shrq	$9, %r10
-	sub	$9, %cl
-
-	movq	%r11, %r9
-	andq	%r10, %r9
-	shrq	%cl, %r9
-
-	movq	PTR(VA_PTE_1)(%rsi), %r8
-	addq	%r8, %r9
-	movq	PTR(PA_CONTROL_PAGE)(%rsi), %r8
-	orq	$PAGE_ATTR, %r8
-	movq	%r8, (%r9)
-
-relocate_new_kernel:
-	/* %rdi indirection_page
-	 * %rsi page_list
-	 * %rdx start address
-	 */
-
 	/* zero out flags, and disable interrupts */
 	pushq $0
 	popfq
@@ -156,9 +40,8 @@ relocate_new_kernel:
 	/* get physical address of page table now too */
 	movq	PTR(PA_TABLE_PAGE)(%rsi), %rcx
 
-	/* switch to new set of page tables */
-	movq	PTR(PA_PGD)(%rsi), %r9
-	movq	%r9, %cr3
+	/* Switch to the identity mapped page tables */
+	movq	%rcx, %cr3
 
 	/* setup a new stack at the end of the physical control page */
 	lea	PAGE_SIZE(%r8), %rsp
@@ -194,9 +77,7 @@ identity_mapped:
 	jmp 1f
 1:
 
-	/* Switch to the identity mapped page tables,
-	 * and flush the TLB.
-	*/
+	/* Flush the TLB (needed?) */
 	movq	%rcx, %cr3
 
 	/* Do the copies */

arch/x86/kernel/trampoline_64.S

@@ -29,6 +29,7 @@
 #include <asm/page.h>
 #include <asm/msr.h>
 #include <asm/segment.h>
+#include <asm/processor-flags.h>
 
 .section .rodata, "a", @progbits
 
@@ -37,7 +38,7 @@
 ENTRY(trampoline_data)
 r_base = .
 	cli			# We should be safe anyway
-	wbinvd	
+	wbinvd
 	mov	%cs, %ax	# Code and data in the same place
 	mov	%ax, %ds
 	mov	%ax, %es
@@ -73,9 +74,8 @@ r_base = .
 	lidtl	tidt - r_base	# load idt with 0, 0
 	lgdtl	tgdt - r_base	# load gdt with whatever is appropriate
 
-	xor	%ax, %ax
-	inc	%ax		# protected mode (PE) bit
-	lmsw	%ax		# into protected mode
+	mov	$X86_CR0_PE, %ax	# protected mode (PE) bit
+	lmsw	%ax			# into protected mode
 
 	# flush prefetch and jump to startup_32
 	ljmpl	*(startup_32_vector - r_base)
@@ -86,9 +86,8 @@ startup_32:
 	movl	$__KERNEL_DS, %eax	# Initialize the %ds segment register
 	movl	%eax, %ds
 
-	xorl	%eax, %eax
-	btsl	$5, %eax		# Enable PAE mode
-	movl	%eax, %cr4
+	movl	$X86_CR4_PAE, %eax
+	movl	%eax, %cr4		# Enable PAE mode
 
 					# Setup trampoline 4 level pagetables
 	leal	(trampoline_level4_pgt - r_base)(%esi), %eax
@@ -99,9 +98,9 @@ startup_32:
 	xorl	%edx, %edx
 	wrmsr
 
-	xorl	%eax, %eax
-	btsl	$31, %eax		# Enable paging and in turn activate Long Mode
-	btsl	$0, %eax		# Enable protected mode
+	# Enable paging and in turn activate Long Mode
+	# Enable protected mode
+	movl	$(X86_CR0_PG | X86_CR0_PE), %eax
 	movl	%eax, %cr0
 
 	/*

arch/x86/mm/init_32.c

@@ -674,75 +674,97 @@ static int __init parse_highmem(char *arg)
 }
 early_param("highmem", parse_highmem);
 
+#define MSG_HIGHMEM_TOO_BIG \
+	"highmem size (%luMB) is bigger than pages available (%luMB)!\n"
+
+#define MSG_LOWMEM_TOO_SMALL \
+	"highmem size (%luMB) results in <64MB lowmem, ignoring it!\n"
 /*
- * Determine low and high memory ranges:
+ * All of RAM fits into lowmem - but if user wants highmem
+ * artificially via the highmem=x boot parameter then create
+ * it:
  */
-void __init find_low_pfn_range(void)
+void __init lowmem_pfn_init(void)
 {
-	/* it could update max_pfn */
-
 	/* max_low_pfn is 0, we already have early_res support */
-
 	max_low_pfn = max_pfn;
-	if (max_low_pfn > MAXMEM_PFN) {
-		if (highmem_pages == -1)
-			highmem_pages = max_pfn - MAXMEM_PFN;
-		if (highmem_pages + MAXMEM_PFN < max_pfn)
-			max_pfn = MAXMEM_PFN + highmem_pages;
-		if (highmem_pages + MAXMEM_PFN > max_pfn) {
-			printk(KERN_WARNING "only %luMB highmem pages "
-				"available, ignoring highmem size of %uMB.\n",
-				pages_to_mb(max_pfn - MAXMEM_PFN),
+
+	if (highmem_pages == -1)
+		highmem_pages = 0;
+#ifdef CONFIG_HIGHMEM
+	if (highmem_pages >= max_pfn) {
+		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
+			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
+		highmem_pages = 0;
+	}
+	if (highmem_pages) {
+		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
+			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
 				pages_to_mb(highmem_pages));
 			highmem_pages = 0;
 		}
-		max_low_pfn = MAXMEM_PFN;
+		max_low_pfn -= highmem_pages;
+	}
+#else
+	if (highmem_pages)
+		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
+#endif
+}
+
+#define MSG_HIGHMEM_TOO_SMALL \
+	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
+
+#define MSG_HIGHMEM_TRIMMED \
+	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+/*
+ * We have more RAM than fits into lowmem - we try to put it into
+ * highmem, also taking the highmem=x boot parameter into account:
+ */
+void __init highmem_pfn_init(void)
+{
+	max_low_pfn = MAXMEM_PFN;
+
+	if (highmem_pages == -1)
+		highmem_pages = max_pfn - MAXMEM_PFN;
+
+	if (highmem_pages + MAXMEM_PFN < max_pfn)
+		max_pfn = MAXMEM_PFN + highmem_pages;
+
+	if (highmem_pages + MAXMEM_PFN > max_pfn) {
+		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
+			pages_to_mb(max_pfn - MAXMEM_PFN),
+			pages_to_mb(highmem_pages));
+		highmem_pages = 0;
+	}
 #ifndef CONFIG_HIGHMEM
-		/* Maximum memory usable is what is directly addressable */
-		printk(KERN_WARNING "Warning only %ldMB will be used.\n",
-					MAXMEM>>20);
-		if (max_pfn > MAX_NONPAE_PFN)
-			printk(KERN_WARNING
-				 "Use a HIGHMEM64G enabled kernel.\n");
-		else
-			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-		max_pfn = MAXMEM_PFN;
+	/* Maximum memory usable is what is directly addressable */
+	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
+	if (max_pfn > MAX_NONPAE_PFN)
+		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
+	else
+		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
 #ifndef CONFIG_HIGHMEM64G
-		if (max_pfn > MAX_NONPAE_PFN) {
-			max_pfn = MAX_NONPAE_PFN;
-			printk(KERN_WARNING "Warning only 4GB will be used."
-				"Use a HIGHMEM64G enabled kernel.\n");
-		}
+	if (max_pfn > MAX_NONPAE_PFN) {
+		max_pfn = MAX_NONPAE_PFN;
+		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
+	}
 #endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
-	} else {
-		if (highmem_pages == -1)
-			highmem_pages = 0;
-#ifdef CONFIG_HIGHMEM
-		if (highmem_pages >= max_pfn) {
-			printk(KERN_ERR "highmem size specified (%uMB) is "
-				"bigger than pages available (%luMB)!.\n",
-				pages_to_mb(highmem_pages),
-				pages_to_mb(max_pfn));
-			highmem_pages = 0;
-		}
-		if (highmem_pages) {
-			if (max_low_pfn - highmem_pages <
-			    64*1024*1024/PAGE_SIZE){
-				printk(KERN_ERR "highmem size %uMB results in "
-				"smaller than 64MB lowmem, ignoring it.\n"
-					, pages_to_mb(highmem_pages));
-				highmem_pages = 0;
-			}
-			max_low_pfn -= highmem_pages;
-		}
-#else
-		if (highmem_pages)
-			printk(KERN_ERR "ignoring highmem size on non-highmem"
-					" kernel!\n");
-#endif
-	}
+}
+
+/*
+ * Determine low and high memory ranges:
+ */
+void __init find_low_pfn_range(void)
+{
+	/* it could update max_pfn */
+
+	if (max_pfn <= MAXMEM_PFN)
+		lowmem_pfn_init();
+	else
+		highmem_pfn_init();
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES

drivers/acpi/acpica/tbxface.c

@@ -365,7 +365,7 @@ ACPI_EXPORT_SYMBOL(acpi_unload_table_id)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_get_table
+ * FUNCTION:    acpi_get_table_with_size
  *
  * PARAMETERS:  Signature           - ACPI signature of needed table
  *              Instance            - Which instance (for SSDTs)
@@ -377,8 +377,9 @@ ACPI_EXPORT_SYMBOL(acpi_unload_table_id)
  *
  *****************************************************************************/
 acpi_status
-acpi_get_table(char *signature,
-	       u32 instance, struct acpi_table_header **out_table)
+acpi_get_table_with_size(char *signature,
+	       u32 instance, struct acpi_table_header **out_table,
+	       acpi_size *tbl_size)
 {
        u32 i;
        u32 j;
@@ -408,6 +409,7 @@ acpi_get_table(char *signature,
 		    acpi_tb_verify_table(&acpi_gbl_root_table_list.tables[i]);
 		if (ACPI_SUCCESS(status)) {
 			*out_table = acpi_gbl_root_table_list.tables[i].pointer;
+			*tbl_size = acpi_gbl_root_table_list.tables[i].length;
 		}
 
 		if (!acpi_gbl_permanent_mmap) {
@@ -420,6 +422,15 @@ acpi_get_table(char *signature,
 	return (AE_NOT_FOUND);
 }
 
+acpi_status
+acpi_get_table(char *signature,
+	       u32 instance, struct acpi_table_header **out_table)
+{
+	acpi_size tbl_size;
+
+	return acpi_get_table_with_size(signature,
+		       instance, out_table, &tbl_size);
+}
 ACPI_EXPORT_SYMBOL(acpi_get_table)
 
 /*******************************************************************************

drivers/acpi/osl.c

@@ -274,12 +274,19 @@ EXPORT_SYMBOL_GPL(acpi_os_map_memory);
 
 void acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
 {
-	if (acpi_gbl_permanent_mmap) {
+	if (acpi_gbl_permanent_mmap)
 		iounmap(virt);
-	}
+	else
+		__acpi_unmap_table(virt, size);
 }
 EXPORT_SYMBOL_GPL(acpi_os_unmap_memory);
 
+void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
+{
+	if (!acpi_gbl_permanent_mmap)
+		__acpi_unmap_table(virt, size);
+}
+
 #ifdef ACPI_FUTURE_USAGE
 acpi_status
 acpi_os_get_physical_address(void *virt, acpi_physical_address * phys)

drivers/acpi/tables.c

@@ -181,14 +181,15 @@ acpi_table_parse_entries(char *id,
 	struct acpi_subtable_header *entry;
 	unsigned int count = 0;
 	unsigned long table_end;
+	acpi_size tbl_size;
 
 	if (!handler)
 		return -EINVAL;
 
 	if (strncmp(id, ACPI_SIG_MADT, 4) == 0)
-		acpi_get_table(id, acpi_apic_instance, &table_header);
+		acpi_get_table_with_size(id, acpi_apic_instance, &table_header, &tbl_size);
 	else
-		acpi_get_table(id, 0, &table_header);
+		acpi_get_table_with_size(id, 0, &table_header, &tbl_size);
 
 	if (!table_header) {
 		printk(KERN_WARNING PREFIX "%4.4s not present\n", id);
@@ -206,8 +207,10 @@ acpi_table_parse_entries(char *id,
 	       table_end) {
 		if (entry->type == entry_id
 		    && (!max_entries || count++ < max_entries))
-			if (handler(entry, table_end))
+			if (handler(entry, table_end)) {
+				early_acpi_os_unmap_memory((char *)table_header, tbl_size);
 				return -EINVAL;
+			}
 
 		entry = (struct acpi_subtable_header *)
 		    ((unsigned long)entry + entry->length);
@@ -217,6 +220,7 @@ acpi_table_parse_entries(char *id,
 		       "%i found\n", id, entry_id, count - max_entries, count);
 	}
 
+	early_acpi_os_unmap_memory((char *)table_header, tbl_size);
 	return count;
 }
 
@@ -241,17 +245,19 @@ acpi_table_parse_madt(enum acpi_madt_type id,
 int __init acpi_table_parse(char *id, acpi_table_handler handler)
 {
 	struct acpi_table_header *table = NULL;
+	acpi_size tbl_size;
 
 	if (!handler)
 		return -EINVAL;
 
 	if (strncmp(id, ACPI_SIG_MADT, 4) == 0)
-		acpi_get_table(id, acpi_apic_instance, &table);
+		acpi_get_table_with_size(id, acpi_apic_instance, &table, &tbl_size);
 	else
-		acpi_get_table(id, 0, &table);
+		acpi_get_table_with_size(id, 0, &table, &tbl_size);
 
 	if (table) {
 		handler(table);
+		early_acpi_os_unmap_memory(table, tbl_size);
 		return 0;
 	} else
 		return 1;
@@ -265,8 +271,9 @@ int __init acpi_table_parse(char *id, acpi_table_handler handler)
 static void __init check_multiple_madt(void)
 {
 	struct acpi_table_header *table = NULL;
+	acpi_size tbl_size;
 
-	acpi_get_table(ACPI_SIG_MADT, 2, &table);
+	acpi_get_table_with_size(ACPI_SIG_MADT, 2, &table, &tbl_size);
 	if (table) {
 		printk(KERN_WARNING PREFIX
 		       "BIOS bug: multiple APIC/MADT found,"
@@ -275,6 +282,7 @@ static void __init check_multiple_madt(void)
 		       "If \"acpi_apic_instance=%d\" works better, "
 		       "notify linux-acpi@vger.kernel.org\n",
 		       acpi_apic_instance ? 0 : 2);
+		early_acpi_os_unmap_memory(table, tbl_size);
 
 	} else
 		acpi_apic_instance = 0;

drivers/firmware/iscsi_ibft.c

@@ -938,8 +938,8 @@ static int __init ibft_init(void)
 		return -ENOMEM;
 
 	if (ibft_addr) {
-		printk(KERN_INFO "iBFT detected at 0x%lx.\n",
-		       virt_to_phys((void *)ibft_addr));
+		printk(KERN_INFO "iBFT detected at 0x%llx.\n",
+		       (u64)virt_to_phys((void *)ibft_addr));
 
 		rc = ibft_check_device();
 		if (rc)

drivers/gpu/drm/drm_proc.c

@@ -678,9 +678,9 @@ static int drm__vma_info(char *buf, char **start, off_t offset, int request,
 	*start = &buf[offset];
 	*eof = 0;
 
-	DRM_PROC_PRINT("vma use count: %d, high_memory = %p, 0x%08lx\n",
+	DRM_PROC_PRINT("vma use count: %d, high_memory = %p, 0x%llx\n",
 		       atomic_read(&dev->vma_count),
-		       high_memory, virt_to_phys(high_memory));
+		       high_memory, (u64)virt_to_phys(high_memory));
 	list_for_each_entry(pt, &dev->vmalist, head) {
 		if (!(vma = pt->vma))
 			continue;

drivers/net/ne3210.c

@@ -150,7 +150,8 @@ static int __init ne3210_eisa_probe (struct device *device)
 		if (phys_mem < virt_to_phys(high_memory)) {
 			printk(KERN_CRIT "ne3210.c: Card RAM overlaps with normal memory!!!\n");
 			printk(KERN_CRIT "ne3210.c: Use EISA SCU to set card memory below 1MB,\n");
-			printk(KERN_CRIT "ne3210.c: or to an address above 0x%lx.\n", virt_to_phys(high_memory));
+			printk(KERN_CRIT "ne3210.c: or to an address above 0x%llx.\n",
+				(u64)virt_to_phys(high_memory));
 			printk(KERN_CRIT "ne3210.c: Driver NOT installed.\n");
 			retval = -EINVAL;
 			goto out3;

drivers/net/sfc/falcon.c

@@ -338,10 +338,10 @@ static int falcon_alloc_special_buffer(struct efx_nic *efx,
 	nic_data->next_buffer_table += buffer->entries;
 
 	EFX_LOG(efx, "allocating special buffers %d-%d at %llx+%x "
-		"(virt %p phys %lx)\n", buffer->index,
+		"(virt %p phys %llx)\n", buffer->index,
 		buffer->index + buffer->entries - 1,
-		(unsigned long long)buffer->dma_addr, len,
-		buffer->addr, virt_to_phys(buffer->addr));
+		(u64)buffer->dma_addr, len,
+		buffer->addr, (u64)virt_to_phys(buffer->addr));
 
 	return 0;
 }
@@ -353,10 +353,10 @@ static void falcon_free_special_buffer(struct efx_nic *efx,
 		return;
 
 	EFX_LOG(efx, "deallocating special buffers %d-%d at %llx+%x "
-		"(virt %p phys %lx)\n", buffer->index,
+		"(virt %p phys %llx)\n", buffer->index,
 		buffer->index + buffer->entries - 1,
-		(unsigned long long)buffer->dma_addr, buffer->len,
-		buffer->addr, virt_to_phys(buffer->addr));
+		(u64)buffer->dma_addr, buffer->len,
+		buffer->addr, (u64)virt_to_phys(buffer->addr));
 
 	pci_free_consistent(efx->pci_dev, buffer->len, buffer->addr,
 			    buffer->dma_addr);
@@ -2343,10 +2343,10 @@ int falcon_probe_port(struct efx_nic *efx)
 				 FALCON_MAC_STATS_SIZE);
 	if (rc)
 		return rc;
-	EFX_LOG(efx, "stats buffer at %llx (virt %p phys %lx)\n",
-		(unsigned long long)efx->stats_buffer.dma_addr,
+	EFX_LOG(efx, "stats buffer at %llx (virt %p phys %llx)\n",
+		(u64)efx->stats_buffer.dma_addr,
 		efx->stats_buffer.addr,
-		virt_to_phys(efx->stats_buffer.addr));
+		(u64)virt_to_phys(efx->stats_buffer.addr));
 
 	return 0;
 }
@@ -2921,9 +2921,9 @@ int falcon_probe_nic(struct efx_nic *efx)
 		goto fail4;
 	BUG_ON(efx->irq_status.dma_addr & 0x0f);
 
-	EFX_LOG(efx, "INT_KER at %llx (virt %p phys %lx)\n",
-		(unsigned long long)efx->irq_status.dma_addr,
-		efx->irq_status.addr, virt_to_phys(efx->irq_status.addr));
+	EFX_LOG(efx, "INT_KER at %llx (virt %p phys %llx)\n",
+		(u64)efx->irq_status.dma_addr,
+		efx->irq_status.addr, (u64)virt_to_phys(efx->irq_status.addr));
 
 	falcon_probe_spi_devices(efx);
 

drivers/net/wireless/arlan-main.c

@@ -1082,8 +1082,8 @@ static int __init arlan_probe_here(struct net_device *dev,
 	if (arlan_check_fingerprint(memaddr))
 		return -ENODEV;
 
-	printk(KERN_NOTICE "%s: Arlan found at %x, \n ", dev->name, 
-	       (int) virt_to_phys((void*)memaddr));
+	printk(KERN_NOTICE "%s: Arlan found at %llx, \n ", dev->name, 
+	       (u64) virt_to_phys((void*)memaddr));
 
 	ap->card = (void *) memaddr;
 	dev->mem_start = memaddr;

drivers/pci/dmar.c

@@ -42,6 +42,7 @@
 LIST_HEAD(dmar_drhd_units);
 
 static struct acpi_table_header * __initdata dmar_tbl;
+static acpi_size dmar_tbl_size;
 
 static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
 {
@@ -288,8 +289,9 @@ static int __init dmar_table_detect(void)
 	acpi_status status = AE_OK;
 
 	/* if we could find DMAR table, then there are DMAR devices */
-	status = acpi_get_table(ACPI_SIG_DMAR, 0,
-				(struct acpi_table_header **)&dmar_tbl);
+	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
+				(struct acpi_table_header **)&dmar_tbl,
+				&dmar_tbl_size);
 
 	if (ACPI_SUCCESS(status) && !dmar_tbl) {
 		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
@@ -481,6 +483,7 @@ void __init detect_intel_iommu(void)
 			iommu_detected = 1;
 #endif
 	}
+	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
 	dmar_tbl = NULL;
 }
 

include/acpi/acpiosxf.h

@@ -144,6 +144,7 @@ void __iomem *acpi_os_map_memory(acpi_physical_address where,
 				acpi_size length);
 
 void acpi_os_unmap_memory(void __iomem * logical_address, acpi_size size);
+void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size);
 
 #ifdef ACPI_FUTURE_USAGE
 acpi_status

include/acpi/acpixf.h

@@ -130,6 +130,10 @@ acpi_get_table_header(acpi_string signature,
 		      struct acpi_table_header *out_table_header);
 
 acpi_status
+acpi_get_table_with_size(acpi_string signature,
+	       u32 instance, struct acpi_table_header **out_table,
+	       acpi_size *tbl_size);
+acpi_status
 acpi_get_table(acpi_string signature,
 	       u32 instance, struct acpi_table_header **out_table);
 

include/linux/acpi.h

@@ -79,6 +79,7 @@ typedef int (*acpi_table_handler) (struct acpi_table_header *table);
 typedef int (*acpi_table_entry_handler) (struct acpi_subtable_header *header, const unsigned long end);
 
 char * __acpi_map_table (unsigned long phys_addr, unsigned long size);
+void __init __acpi_unmap_table(char *map, unsigned long size);
 int early_acpi_boot_init(void);
 int acpi_boot_init (void);
 int acpi_boot_table_init (void);