Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Peter Anvin:
 "This is a huge set of several partly interrelated (and concurrently
  developed) changes, which is why the branch history is messier than
  one would like.

  The *really* big items are two humonguous patchsets mostly developed
  by Yinghai Lu at my request, which completely revamps the way we
  create initial page tables.  In particular, rather than estimating how
  much memory we will need for page tables and then build them into that
  memory -- a calculation that has shown to be incredibly fragile -- we
  now build them (on 64 bits) with the aid of a "pseudo-linear mode" --
  a #PF handler which creates temporary page tables on demand.

  This has several advantages:

  1. It makes it much easier to support things that need access to data
     very early (a followon patchset uses this to load microcode way
     early in the kernel startup).

  2. It allows the kernel and all the kernel data objects to be invoked
     from above the 4 GB limit.  This allows kdump to work on very large
     systems.

  3. It greatly reduces the difference between Xen and native (Xen's
     equivalent of the #PF handler are the temporary page tables created
     by the domain builder), eliminating a bunch of fragile hooks.

  The patch series also gets us a bit closer to W^X.

  Additional work in this pull is the 64-bit get_user() work which you
  were also involved with, and a bunch of cleanups/speedups to
  __phys_addr()/__pa()."

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (105 commits)
  x86, mm: Move reserving low memory later in initialization
  x86, doc: Clarify the use of asm("%edx") in uaccess.h
  x86, mm: Redesign get_user with a __builtin_choose_expr hack
  x86: Be consistent with data size in getuser.S
  x86, mm: Use a bitfield to mask nuisance get_user() warnings
  x86/kvm: Fix compile warning in kvm_register_steal_time()
  x86-32: Add support for 64bit get_user()
  x86-32, mm: Remove reference to alloc_remap()
  x86-32, mm: Remove reference to resume_map_numa_kva()
  x86-32, mm: Rip out x86_32 NUMA remapping code
  x86/numa: Use __pa_nodebug() instead
  x86: Don't panic if can not alloc buffer for swiotlb
  mm: Add alloc_bootmem_low_pages_nopanic()
  x86, 64bit, mm: hibernate use generic mapping_init
  x86, 64bit, mm: Mark data/bss/brk to nx
  x86: Merge early kernel reserve for 32bit and 64bit
  x86: Add Crash kernel low reservation
  x86, kdump: Remove crashkernel range find limit for 64bit
  memblock: Add memblock_mem_size()
  x86, boot: Not need to check setup_header version for setup_data
  ...

18 files changed, 111 insertions, 106 deletions

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index adcc0ae73d09..223042086f4e 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -1,20 +1,14 @@
-#ifndef _ASM_X86_INIT_32_H
-#define _ASM_X86_INIT_32_H
+#ifndef _ASM_X86_INIT_H
+#define _ASM_X86_INIT_H
 
-#ifdef CONFIG_X86_32
-extern void __init early_ioremap_page_table_range_init(void);
-#endif
+struct x86_mapping_info {
+        void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
+        void *context;                   /* context for alloc_pgt_page */
+        unsigned long pmd_flag;          /* page flag for PMD entry */
+        bool kernel_mapping;             /* kernel mapping or ident mapping */
+};
 
-extern void __init zone_sizes_init(void);
+int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
+                                unsigned long addr, unsigned long end);
 
-extern unsigned long __init
-kernel_physical_mapping_init(unsigned long start,
-                             unsigned long end,
-                             unsigned long page_size_mask);
-
-
-extern unsigned long __initdata pgt_buf_start;
-extern unsigned long __meminitdata pgt_buf_end;
-extern unsigned long __meminitdata pgt_buf_top;
-
-#endif /* _ASM_X86_INIT_32_H */
+#endif /* _ASM_X86_INIT_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 6080d2694bad..17483a492f18 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -48,11 +48,11 @@
 # define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64)
 #else
 /* Maximum physical address we can use pages from */
-# define KEXEC_SOURCE_MEMORY_LIMIT      (0xFFFFFFFFFFUL)
+# define KEXEC_SOURCE_MEMORY_LIMIT      (MAXMEM-1)
 /* Maximum address we can reach in physical address mode */
-# define KEXEC_DESTINATION_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+# define KEXEC_DESTINATION_MEMORY_LIMIT (MAXMEM-1)
 /* Maximum address we can use for the control pages */
-# define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
+# define KEXEC_CONTROL_MEMORY_LIMIT     (MAXMEM-1)
 
 /* Allocate one page for the pdp and the second for the code */
 # define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index eb05fb3b02fb..8a9b3e288cb4 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -14,12 +14,6 @@ extern struct pglist_data *node_data[];
 
 #include <asm/numaq.h>
 
-extern void resume_map_numa_kva(pgd_t *pgd);
-
-#else /* !CONFIG_NUMA */
-
-static inline void resume_map_numa_kva(pgd_t *pgd) {}
-
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 49119fcea2dc..52560a2038e1 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -54,8 +54,6 @@ static inline int numa_cpu_node(int cpu)
 
 #ifdef CONFIG_X86_32
 # include <asm/numa_32.h>
-#else
-# include <asm/numa_64.h>
 #endif
 
 #ifdef CONFIG_NUMA
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
deleted file mode 100644
index 0c05f7ae46e8..000000000000
--- a/arch/x86/include/asm/numa_64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_X86_NUMA_64_H
-#define _ASM_X86_NUMA_64_H
-
-extern unsigned long numa_free_all_bootmem(void);
-
-#endif /* _ASM_X86_NUMA_64_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
index 8ca82839288a..c87892442e53 100644
--- a/arch/x86/include/asm/page.h
+++ b/arch/x86/include/asm/page.h
@@ -17,6 +17,10 @@
 
 struct page;
 
+#include <linux/range.h>
+extern struct range pfn_mapped[];
+extern int nr_pfn_mapped;
+
 static inline void clear_user_page(void *page, unsigned long vaddr,
                                    struct page *pg)
 {
@@ -44,7 +48,8 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
  * case properly. Once all supported versions of gcc understand it, we can
  * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated)
  */
-#define __pa_symbol(x)  __pa(__phys_reloc_hide((unsigned long)(x)))
+#define __pa_symbol(x) \
+        __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x)))
 
 #define __va(x)                 ((void *)((unsigned long)(x)+PAGE_OFFSET))
 
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
index da4e762406f7..4d550d04b609 100644
--- a/arch/x86/include/asm/page_32.h
+++ b/arch/x86/include/asm/page_32.h
@@ -15,6 +15,7 @@ extern unsigned long __phys_addr(unsigned long);
 #else
 #define __phys_addr(x)          __phys_addr_nodebug(x)
 #endif
+#define __phys_addr_symbol(x)   __phys_addr(x)
 #define __phys_reloc_hide(x)    RELOC_HIDE((x), 0)
 
 #ifdef CONFIG_FLATMEM
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index 072694ed81a5..0f1ddee6a0ce 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -3,4 +3,40 @@
 
 #include <asm/page_64_types.h>
 
+#ifndef __ASSEMBLY__
+
+/* duplicated to the one in bootmem.h */
+extern unsigned long max_pfn;
+extern unsigned long phys_base;
+
+static inline unsigned long __phys_addr_nodebug(unsigned long x)
+{
+        unsigned long y = x - __START_KERNEL_map;
+
+        /* use the carry flag to determine if x was < __START_KERNEL_map */
+        x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET));
+
+        return x;
+}
+
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern unsigned long __phys_addr(unsigned long);
+extern unsigned long __phys_addr_symbol(unsigned long);
+#else
+#define __phys_addr(x)          __phys_addr_nodebug(x)
+#define __phys_addr_symbol(x) \
+        ((unsigned long)(x) - __START_KERNEL_map + phys_base)
+#endif
+
+#define __phys_reloc_hide(x)    (x)
+
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)          ((pfn) < max_pfn)
+#endif
+
+void clear_page(void *page);
+void copy_page(void *to, void *from);
+
+#endif  /* !__ASSEMBLY__ */
+
 #endif /* _ASM_X86_PAGE_64_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 320f7bb95f76..8b491e66eaa8 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -50,26 +50,4 @@
 #define KERNEL_IMAGE_SIZE       (512 * 1024 * 1024)
 #define KERNEL_IMAGE_START      _AC(0xffffffff80000000, UL)
 
-#ifndef __ASSEMBLY__
-void clear_page(void *page);
-void copy_page(void *to, void *from);
-
-/* duplicated to the one in bootmem.h */
-extern unsigned long max_pfn;
-extern unsigned long phys_base;
-
-extern unsigned long __phys_addr(unsigned long);
-#define __phys_reloc_hide(x)    (x)
-
-#define vmemmap ((struct page *)VMEMMAP_START)
-
-extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
-extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
-
-#endif  /* !__ASSEMBLY__ */
-
-#ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)          ((pfn) < max_pfn)
-#endif
-
 #endif /* _ASM_X86_PAGE_64_DEFS_H */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index e21fdd10479f..54c97879195e 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,6 +51,8 @@ static inline phys_addr_t get_max_mapped(void)
         return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
 }
 
+bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
+
 extern unsigned long init_memory_mapping(unsigned long start,
                                          unsigned long end);
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index fc304279b559..1e672234c4ff 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -395,6 +395,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
 
 #ifndef __ASSEMBLY__
 #include <linux/mm_types.h>
+#include <linux/log2.h>
 
 static inline int pte_none(pte_t pte)
 {
@@ -620,6 +621,8 @@ static inline int pgd_none(pgd_t pgd)
 #ifndef __ASSEMBLY__
 
 extern int direct_gbpages;
+void init_mem_mapping(void);
+void early_alloc_pgt_buf(void);
 
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
@@ -786,6 +789,20 @@ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
        memcpy(dst, src, count * sizeof(pgd_t));
 }
 
+#define PTE_SHIFT ilog2(PTRS_PER_PTE)
+static inline int page_level_shift(enum pg_level level)
+{
+        return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT;
+}
+static inline unsigned long page_level_size(enum pg_level level)
+{
+        return 1UL << page_level_shift(level);
+}
+static inline unsigned long page_level_mask(enum pg_level level)
+{
+        return ~(page_level_size(level) - 1);
+}
+
 /*
  * The x86 doesn't have any external MMU info: the kernel page
  * tables contain all the necessary information.
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 615b0c78449f..e22c1dbf7feb 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -180,6 +180,11 @@ extern void cleanup_highmap(void);
 
 #define __HAVE_ARCH_PTE_SAME
 
+#define vmemmap ((struct page *)VMEMMAP_START)
+
+extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
+extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_64_H */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 766ea16fbbbd..2d883440cb9a 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_PGTABLE_64_DEFS_H
 #define _ASM_X86_PGTABLE_64_DEFS_H
 
+#include <asm/sparsemem.h>
+
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
 
@@ -60,4 +62,6 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
 
+#define EARLY_DYNAMIC_PAGE_TABLES       64
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 3c32db8c539d..e6423002c10b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -321,7 +321,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
-extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_init(void);
 #else
@@ -331,7 +330,7 @@ extern void native_pagetable_init(void);
 struct seq_file;
 extern void arch_report_meminfo(struct seq_file *m);
 
-enum {
+enum pg_level {
         PG_LEVEL_NONE,
         PG_LEVEL_4K,
         PG_LEVEL_2M,
@@ -352,6 +351,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern phys_addr_t slow_virt_to_phys(void *__address);
 
 #endif  /* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d172588efae5..8277941cbe99 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -721,6 +721,7 @@ extern void enable_sep_cpu(void);
 extern int sysenter_setup(void);
 
 extern void early_trap_init(void);
+void early_trap_pf_init(void);
 
 /* Defined in head.S */
 extern struct desc_ptr          early_gdt_descr;
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index fe1ec5bcd846..9c6b890d5e7a 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -58,6 +58,7 @@ extern unsigned char boot_gdt[];
 extern unsigned char secondary_startup_64[];
 #endif
 
-extern void __init setup_real_mode(void);
+void reserve_real_mode(void);
+void setup_real_mode(void);
 
 #endif /* _ARCH_X86_REALMODE_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1709801d18ec..5ee26875baea 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -125,13 +125,12 @@ extern int __get_user_4(void);
 extern int __get_user_8(void);
 extern int __get_user_bad(void);
 
-#define __get_user_x(size, ret, x, ptr)               \
-        asm volatile("call __get_user_" #size         \
-                     : "=a" (ret), "=d" (x)           \
-                     : "0" (ptr))                     \
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
+/*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __inttype(x) \
+__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 
 /**
  * get_user: - Get a simple variable from user space.
@@ -150,38 +149,26 @@ extern int __get_user_bad(void);
  * Returns zero on success, or -EFAULT on error.
  * On error, the variable @x is set to zero.
  */
-#ifdef CONFIG_X86_32
-#define __get_user_8(__ret_gu, __val_gu, ptr)                           \
-                __get_user_x(X, __ret_gu, __val_gu, ptr)
-#else
-#define __get_user_8(__ret_gu, __val_gu, ptr)                           \
-                __get_user_x(8, __ret_gu, __val_gu, ptr)
-#endif
-
+/*
+ * Careful: we have to cast the result to the type of the pointer
+ * for sign reasons.
+ *
+ * The use of %edx as the register specifier is a bit of a
+ * simplification, as gcc only cares about it as the starting point
+ * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits
+ * (%ecx being the next register in gcc's x86 register sequence), and
+ * %rdx on 64 bits.
+ */
 #define get_user(x, ptr)                                                \
 ({                                                                      \
         int __ret_gu;                                                   \
-        unsigned long __val_gu;                                         \
+        register __inttype(*(ptr)) __val_gu asm("%edx");                \
         __chk_user_ptr(ptr);                                            \
         might_fault();                                                  \
-        switch (sizeof(*(ptr))) {                                       \
-        case 1:                                                         \
-                __get_user_x(1, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 2:                                                         \
-                __get_user_x(2, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 4:                                                         \
-                __get_user_x(4, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        case 8:                                                         \
-                __get_user_8(__ret_gu, __val_gu, ptr);                  \
-                break;                                                  \
-        default:                                                        \
-                __get_user_x(X, __ret_gu, __val_gu, ptr);               \
-                break;                                                  \
-        }                                                               \
-        (x) = (__typeof__(*(ptr)))__val_gu;                             \
+        asm volatile("call __get_user_%P3"                              \
+                     : "=a" (__ret_gu), "=r" (__val_gu)                 \
+                     : "0" (ptr), "i" (sizeof(*(ptr))));                \
+        (x) = (__typeof__(*(ptr))) __val_gu;                            \
         __ret_gu;                                                       \
 })
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 7669941cc9d2..d8d99222b36a 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -69,17 +69,6 @@ struct x86_init_oem {
 };
 
 /**
- * struct x86_init_mapping - platform specific initial kernel pagetable setup
- * @pagetable_reserve:  reserve a range of addresses for kernel pagetable usage
- *
- * For more details on the purpose of this hook, look in
- * init_memory_mapping and the commit that added it.
- */
-struct x86_init_mapping {
-        void (*pagetable_reserve)(u64 start, u64 end);
-};
-
-/**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_init:     platform specific paging initialization call to setup
  *                      the kernel pagetables and prepare accessors functions.
@@ -136,7 +125,6 @@ struct x86_init_ops {
         struct x86_init_mpparse         mpparse;
         struct x86_init_irqs            irqs;
         struct x86_init_oem             oem;
-        struct x86_init_mapping         mapping;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
         struct x86_init_iommu           iommu;