Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (22 commits)
  x86: fix system without memory on node0
  x86, mm: Fix node_possible_map logic
  mm, x86: remove MEMORY_HOTPLUG_RESERVE related code
  x86: make sparse mem work in non-NUMA mode
  x86: process.c, remove useless headers
  x86: merge process.c a bit
  x86: use sparse_memory_present_with_active_regions() on UMA
  x86: unify 64-bit UMA and NUMA paging_init()
  x86: Allow 1MB of slack between the e820 map and SRAT, not 4GB
  x86: Sanity check the e820 against the SRAT table using e820 map only
  x86: clean up and and print out initial max_pfn_mapped
  x86/pci: remove rounding quirk from e820_setup_gap()
  x86, e820, pci: reserve extra free space near end of RAM
  x86: fix typo in address space documentation
  x86: 46 bit physical address support on 64 bits
  x86, mm: fault.c, use printk_once() in is_errata93()
  x86: move per-cpu mmu_gathers to mm/init.c
  x86: move max_pfn_mapped and max_low_pfn_mapped to setup.c
  x86: unify noexec handling
  x86: remove (null) in /sys kernel_page_tables
  ...

6 files changed, 72 insertions, 38 deletions

diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 00628130292..7271fa33d79 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -617,7 +617,7 @@ __init int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
  */
 __init void e820_setup_gap(void)
 {
-	unsigned long gapstart, gapsize, round;
+	unsigned long gapstart, gapsize;
 	int found;
 
 	gapstart = 0x10000000;
@@ -635,14 +635,9 @@ __init void e820_setup_gap(void)
 #endif
 
 	/*
-	 * See how much we want to round up: start off with
-	 * rounding to the next 1MB area.
+	 * e820_reserve_resources_late protect stolen RAM already
 	 */
-	round = 0x100000;
-	while ((gapsize >> 4) > round)
-		round += round;
-	/* Fun with two's complement */
-	pci_mem_start = (gapstart + round) & -round;
+	pci_mem_start = gapstart;
 
 	printk(KERN_INFO
 	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
@@ -1371,6 +1366,23 @@ void __init e820_reserve_resources(void)
 	}
 }
 
+/* How much should we pad RAM ending depending on where it is? */
+static unsigned long ram_alignment(resource_size_t pos)
+{
+	unsigned long mb = pos >> 20;
+
+	/* To 64kB in the first megabyte */
+	if (!mb)
+		return 64*1024;
+
+	/* To 1MB in the first 16MB */
+	if (mb < 16)
+		return 1024*1024;
+
+	/* To 32MB for anything above that */
+	return 32*1024*1024;
+}
+
 void __init e820_reserve_resources_late(void)
 {
 	int i;
@@ -1382,6 +1394,24 @@ void __init e820_reserve_resources_late(void)
 			insert_resource_expand_to_fit(&iomem_resource, res);
 		res++;
 	}
+
+	/*
+	 * Try to bump up RAM regions to reasonable boundaries to
+	 * avoid stolen RAM:
+	 */
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *entry = &e820_saved.map[i];
+		resource_size_t start, end;
+
+		if (entry->type != E820_RAM)
+			continue;
+		start = entry->addr + entry->size;
+		end = round_up(start, ram_alignment(start));
+		if (start == end)
+			continue;
+		reserve_region_with_split(&iomem_resource, start,
+						  end - 1, "RAM buffer");
+	}
 }
 
 char *__init default_machine_specific_memory_setup(void)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3e21e38d7e3..e22d63bdc8f 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/pm.h>
 #include <linux/clockchips.h>
+#include <linux/random.h>
 #include <trace/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
@@ -614,3 +615,16 @@ static int __init idle_setup(char *str)
 }
 early_param("idle", idle_setup);
 
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_int() % 8192;
+	return sp & ~0xf;
+}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+	unsigned long range_end = mm->brk + 0x02000000;
+	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
+}
+
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 76f8f84043a..56d50b7d71d 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -9,8 +9,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -33,7 +31,6 @@
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/personality.h>
 #include <linux/tick.h>
 #include <linux/percpu.h>
@@ -497,15 +494,3 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b751a41392b..9d6b20e6cd8 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -14,8 +14,6 @@
  * This file handles the architecture-dependent parts of process handling..
  */
 
-#include <stdarg.h>
-
 #include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
@@ -32,7 +30,6 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>
 #include <linux/notifier.h>
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
@@ -660,15 +657,3 @@ long sys_arch_prctl(int code, unsigned long addr)
 	return do_arch_prctl(current, code, addr);
 }
 
-unsigned long arch_align_stack(unsigned long sp)
-{
-	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
-	return sp & ~0xf;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
-	unsigned long range_end = mm->brk + 0x02000000;
-	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
-}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 7791eef95b9..d1c636bf31a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,14 @@
 #define ARCH_SETUP
 #endif
 
+/*
+ * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
+ * The direct mapping extends to max_pfn_mapped, so that we can directly access
+ * apertures, ACPI and other tables without having to play with fixmaps.
+ */
+unsigned long max_low_pfn_mapped;
+unsigned long max_pfn_mapped;
+
 RESERVE_BRK(dmi_alloc, 65536);
 
 unsigned int boot_cpu_id __read_mostly;
@@ -860,12 +868,16 @@ void __init setup_arch(char **cmdline_p)
 		max_low_pfn = max_pfn;
 
 	high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
+	max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT;
 #endif
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 	setup_bios_corruption_check();
 #endif
 
+	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
+			max_pfn_mapped<<PAGE_SHIFT);
+
 	reserve_brk();
 
 	/* max_pfn_mapped is updated here */
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 8f0e13be36b..9c3f0823e6a 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -425,6 +425,14 @@ void __init setup_per_cpu_areas(void)
 	early_per_cpu_ptr(x86_cpu_to_node_map) = NULL;
 #endif
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_NUMA)
+	/*
+	 * make sure boot cpu node_number is right, when boot cpu is on the
+	 * node that doesn't have mem installed
+	 */
+	per_cpu(node_number, boot_cpu_id) = cpu_to_node(boot_cpu_id);
+#endif
+
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();