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

Pull x86 boot updates from Ingo Molnar:
 "The biggest changes in this cycle were:

   - reworking of the e820 code: separate in-kernel and boot-ABI data
     structures and apply a whole range of cleanups to the kernel side.

     No change in functionality.

   - enable KASLR by default: it's used by all major distros and it's
     out of the experimental stage as well.

   - ... misc fixes and cleanups"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  x86/KASLR: Fix kexec kernel boot crash when KASLR randomization fails
  x86/reboot: Turn off KVM when halting a CPU
  x86/boot: Fix BSS corruption/overwrite bug in early x86 kernel startup
  x86: Enable KASLR by default
  boot/param: Move next_arg() function to lib/cmdline.c for later reuse
  x86/boot: Fix Sparse warning by including required header file
  x86/boot/64: Rename start_cpu()
  x86/xen: Update e820 table handling to the new core x86 E820 code
  x86/boot: Fix pr_debug() API braindamage
  xen, x86/headers: Add <linux/device.h> dependency to <asm/xen/page.h>
  x86/boot/e820: Simplify e820__update_table()
  x86/boot/e820: Separate the E820 ABI structures from the in-kernel structures
  x86/boot/e820: Fix and clean up e820_type switch() statements
  x86/boot/e820: Rename the remaining E820 APIs to the e820__*() prefix
  x86/boot/e820: Remove unnecessary #include's
  x86/boot/e820: Rename e820_mark_nosave_regions() to e820__register_nosave_regions()
  x86/boot/e820: Rename e820_reserve_resources*() to e820__reserve_resources*()
  x86/boot/e820: Use bool in query APIs
  x86/boot/e820: Document e820__reserve_setup_data()
  x86/boot/e820: Clean up __e820__update_table() et al
  ...

arch/x86/include/asm/acpi.h

@@ -52,6 +52,8 @@ extern u8 acpi_sci_flags;
 extern int acpi_sci_override_gsi;
 void acpi_pic_sci_set_trigger(unsigned int, u16);
 
+struct device;
+
 extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi,
 				  int trigger, int polarity);
 extern void (*__acpi_unregister_gsi)(u32 gsi);

arch/x86/include/asm/e820.h

@@ -1,73 +0,0 @@
-#ifndef _ASM_X86_E820_H
-#define _ASM_X86_E820_H
-
-/*
- * E820_X_MAX is the maximum size of the extended E820 table.  The extended
- * table may contain up to 3 extra E820 entries per possible NUMA node, so we
- * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128.
- * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h.
- */
-#include <linux/numa.h>
-#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
-
-#include <uapi/asm/e820.h>
-
-#ifndef __ASSEMBLY__
-/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map *e820;
-extern struct e820map *e820_saved;
-
-extern unsigned long pci_mem_start;
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern int e820_all_mapped(u64 start, u64 end, unsigned type);
-extern void e820_add_region(u64 start, u64 size, int type);
-extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map);
-extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
-			       unsigned new_type);
-extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
-			     int checktype);
-extern void update_e820(void);
-extern void e820_setup_gap(void);
-struct setup_data;
-extern void parse_e820_ext(u64 phys_addr, u32 data_len);
-
-#if defined(CONFIG_X86_64) || \
-	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-extern void e820_mark_nosave_regions(unsigned long limit_pfn);
-#else
-static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
-{
-}
-#endif
-
-extern unsigned long e820_end_of_ram_pfn(void);
-extern unsigned long e820_end_of_low_ram_pfn(void);
-extern u64 early_reserve_e820(u64 sizet, u64 align);
-
-void memblock_x86_fill(void);
-void memblock_find_dma_reserve(void);
-
-extern void finish_e820_parsing(void);
-extern void e820_reserve_resources(void);
-extern void e820_reserve_resources_late(void);
-extern void setup_memory_map(void);
-extern char *default_machine_specific_memory_setup(void);
-
-extern void e820_reallocate_tables(void);
-
-/*
- * Returns true iff the specified range [s,e) is completely contained inside
- * the ISA region.
- */
-static inline bool is_ISA_range(u64 s, u64 e)
-{
-	return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS;
-}
-
-#endif /* __ASSEMBLY__ */
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY	(1024*1024)
-#endif /* _ASM_X86_E820_H */

arch/x86/include/asm/e820/api.h

@@ -0,0 +1,50 @@
+#ifndef _ASM_E820_API_H
+#define _ASM_E820_API_H
+
+#include <asm/e820/types.h>
+
+extern struct e820_table *e820_table;
+extern struct e820_table *e820_table_firmware;
+
+extern unsigned long pci_mem_start;
+
+extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type);
+extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
+
+extern void e820__range_add   (u64 start, u64 size, enum e820_type type);
+extern u64  e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
+extern u64  e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+
+extern void e820__print_table(char *who);
+extern int  e820__update_table(struct e820_table *table);
+extern void e820__update_table_print(void);
+
+extern unsigned long e820__end_of_ram_pfn(void);
+extern unsigned long e820__end_of_low_ram_pfn(void);
+
+extern u64  e820__memblock_alloc_reserved(u64 size, u64 align);
+extern void e820__memblock_setup(void);
+
+extern void e820__reserve_setup_data(void);
+extern void e820__finish_early_params(void);
+extern void e820__reserve_resources(void);
+extern void e820__reserve_resources_late(void);
+
+extern void e820__memory_setup(void);
+extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len);
+extern char *e820__memory_setup_default(void);
+extern void e820__setup_pci_gap(void);
+
+extern void e820__reallocate_tables(void);
+extern void e820__register_nosave_regions(unsigned long limit_pfn);
+
+/*
+ * Returns true iff the specified range [start,end) is completely contained inside
+ * the ISA region.
+ */
+static inline bool is_ISA_range(u64 start, u64 end)
+{
+	return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS;
+}
+
+#endif /* _ASM_E820_API_H */

arch/x86/include/asm/e820/types.h

@@ -0,0 +1,104 @@
+#ifndef _ASM_E820_TYPES_H
+#define _ASM_E820_TYPES_H
+
+#include <uapi/asm/bootparam.h>
+
+/*
+ * These are the E820 types known to the kernel:
+ */
+enum e820_type {
+	E820_TYPE_RAM		= 1,
+	E820_TYPE_RESERVED	= 2,
+	E820_TYPE_ACPI		= 3,
+	E820_TYPE_NVS		= 4,
+	E820_TYPE_UNUSABLE	= 5,
+	E820_TYPE_PMEM		= 7,
+
+	/*
+	 * This is a non-standardized way to represent ADR or
+	 * NVDIMM regions that persist over a reboot.
+	 *
+	 * The kernel will ignore their special capabilities
+	 * unless the CONFIG_X86_PMEM_LEGACY=y option is set.
+	 *
+	 * ( Note that older platforms also used 6 for the same
+	 *   type of memory, but newer versions switched to 12 as
+	 *   6 was assigned differently. Some time they will learn... )
+	 */
+	E820_TYPE_PRAM		= 12,
+
+	/*
+	 * Reserved RAM used by the kernel itself if
+	 * CONFIG_INTEL_TXT=y is enabled, memory of this type
+	 * will be included in the S3 integrity calculation
+	 * and so should not include any memory that the BIOS
+	 * might alter over the S3 transition:
+	 */
+	E820_TYPE_RESERVED_KERN	= 128,
+};
+
+/*
+ * A single E820 map entry, describing a memory range of [addr...addr+size-1],
+ * of 'type' memory type:
+ *
+ * (We pack it because there can be thousands of them on large systems.)
+ */
+struct e820_entry {
+	u64			addr;
+	u64			size;
+	enum e820_type		type;
+} __attribute__((packed));
+
+/*
+ * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes
+ * due to the constrained space in the zeropage.
+ *
+ * On large systems we can easily have thousands of nodes with RAM,
+ * which cannot be fit into so few entries - so we have a mechanism
+ * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES
+ * define below.
+ *
+ * ( Those extra entries are enumerated via the EFI memory map, not
+ *   via the legacy zeropage mechanism. )
+ *
+ * Size our internal memory map tables to have room for these additional
+ * entries, based on a heuristic calculation: up to three entries per
+ * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space.
+ *
+ * This allows for bootstrap/firmware quirks such as possible duplicate
+ * E820 entries that might need room in the same arrays, prior to the
+ * call to e820__update_table() to remove duplicates.  The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries.  Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+#include <linux/numa.h>
+
+#define E820_MAX_ENTRIES	(E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES)
+
+/*
+ * The whole array of E820 entries:
+ */
+struct e820_table {
+	__u32 nr_entries;
+	struct e820_entry entries[E820_MAX_ENTRIES];
+};
+
+/*
+ * Various well-known legacy memory ranges in physical memory:
+ */
+#define ISA_START_ADDRESS	0x000a0000
+#define ISA_END_ADDRESS		0x00100000
+
+#define BIOS_BEGIN		0x000a0000
+#define BIOS_END		0x00100000
+
+#define HIGH_MEMORY		0x00100000
+
+#define BIOS_ROM_BASE		0xffe00000
+#define BIOS_ROM_END		0xffffffff
+
+#endif /* _ASM_E820_TYPES_H */

arch/x86/include/asm/gart.h

@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_GART_H
 #define _ASM_X86_GART_H
 
-#include <asm/e820.h>
+#include <asm/e820/api.h>
 
 extern void set_up_gart_resume(u32, u32);
 
@@ -97,7 +97,7 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
 		printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
 		return 0;
 	}
-	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+	if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) {
 		printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
 		return 0;
 	}

arch/x86/include/asm/mpspec.h

@@ -64,7 +64,7 @@ static inline void find_smp_config(void)
 }
 
 #ifdef CONFIG_X86_MPPARSE
-extern void early_reserve_e820_mpc_new(void);
+extern void e820__memblock_alloc_reserved_mpc_new(void);
 extern int enable_update_mptable;
 extern int default_mpc_apic_id(struct mpc_cpu *m);
 extern void default_smp_read_mpc_oem(struct mpc_table *mpc);
@@ -76,7 +76,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str);
 extern void default_find_smp_config(void);
 extern void default_get_smp_config(unsigned int early);
 #else
-static inline void early_reserve_e820_mpc_new(void) { }
+static inline void e820__memblock_alloc_reserved_mpc_new(void) { }
 #define enable_update_mptable 0
 #define default_mpc_apic_id NULL
 #define default_smp_read_mpc_oem NULL

arch/x86/include/asm/pci_x86.h

@@ -4,6 +4,8 @@
  *	(c) 1999 Martin Mares <mj@ucw.cz>
  */
 
+#include <linux/ioport.h>
+
 #undef DEBUG
 
 #ifdef DEBUG

arch/x86/include/asm/pgtable.h

@@ -2,8 +2,6 @@
 #define _ASM_X86_PGTABLE_H
 
 #include <asm/page.h>
-#include <asm/e820.h>
-
 #include <asm/pgtable_types.h>
 
 /*
@@ -845,6 +843,7 @@ static inline int pgd_none(pgd_t pgd)
 extern int direct_gbpages;
 void init_mem_mapping(void);
 void early_alloc_pgt_buf(void);
+extern void memblock_find_dma_reserve(void);
 
 #ifdef CONFIG_X86_64
 /* Realmode trampoline initialization. */

arch/x86/include/asm/xen/page.h

@@ -6,6 +6,7 @@
 #include <linux/spinlock.h>
 #include <linux/pfn.h>
 #include <linux/mm.h>
+#include <linux/device.h>
 
 #include <linux/uaccess.h>
 #include <asm/page.h>