12 files changed, 121 insertions, 116 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 9b5a9f59a478..06630d26e56d 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,9 +1,10 @@
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o gup.o
+	    pat.o pgtable.o physaddr.o gup.o setup_nx.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_physaddr.o		:= $(nostackp)
+CFLAGS_setup_nx.o		:= $(nostackp)
 
 obj-$(CONFIG_SMP)		+= tlb.o
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 775a020990a5..f4cee9028cf0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -10,7 +10,7 @@
 #include <linux/bootmem.h>		/* max_low_pfn			*/
 #include <linux/kprobes.h>		/* __kprobes, ...		*/
 #include <linux/mmiotrace.h>		/* kmmio_handler, ...		*/
-#include <linux/perf_counter.h>		/* perf_swcounter_event		*/
+#include <linux/perf_event.h>		/* perf_sw_event		*/
 
 #include <asm/traps.h>			/* dotraplinkage, ...		*/
 #include <asm/pgalloc.h>		/* pgd_*(), ...			*/
@@ -167,6 +167,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address,
 	info.si_errno	= 0;
 	info.si_code	= si_code;
 	info.si_addr	= (void __user *)address;
+	info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0;
 
 	force_sig_info(si_signo, &info, tsk);
 }
@@ -790,10 +791,12 @@ out_of_memory(struct pt_regs *regs, unsigned long error_code,
 }
 
 static void
-do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
+	  unsigned int fault)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
+	int code = BUS_ADRERR;
 
 	up_read(&mm->mmap_sem);
 
@@ -809,7 +812,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 	tsk->thread.error_code	= error_code;
 	tsk->thread.trap_no	= 14;
 
-	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+#ifdef CONFIG_MEMORY_FAILURE
+	if (fault & VM_FAULT_HWPOISON) {
+		printk(KERN_ERR
+	"MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+			tsk->comm, tsk->pid, address);
+		code = BUS_MCEERR_AR;
+	}
+#endif
+	force_sig_info_fault(SIGBUS, code, address, tsk);
 }
 
 static noinline void
@@ -819,8 +830,8 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
 	if (fault & VM_FAULT_OOM) {
 		out_of_memory(regs, error_code, address);
 	} else {
-		if (fault & VM_FAULT_SIGBUS)
-			do_sigbus(regs, error_code, address);
+		if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))
+			do_sigbus(regs, error_code, address, fault);
 		else
 			BUG();
 	}
@@ -1017,7 +1028,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(error_code & PF_RSVD))
 		pgtable_bad(regs, error_code, address);
 
-	perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
 
 	/*
 	 * If we're in an interrupt, have no user context or are running
@@ -1114,11 +1125,11 @@ good_area:
 
 	if (fault & VM_FAULT_MAJOR) {
 		tsk->maj_flt++;
-		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
 				     regs, address);
 	} else {
 		tsk->min_flt++;
-		perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+		perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
 				     regs, address);
 	}
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 0607119cef94..73ffd5536f62 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -28,69 +28,6 @@ int direct_gbpages
 #endif
 ;
 
-int nx_enabled;
-
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-static int disable_nx __cpuinitdata;
-
-/*
- * noexec = on|off
- *
- * Control non-executable mappings for processes.
- *
- * on      Enable
- * off     Disable
- */
-static int __init noexec_setup(char *str)
-{
-	if (!str)
-		return -EINVAL;
-	if (!strncmp(str, "on", 2)) {
-		__supported_pte_mask |= _PAGE_NX;
-		disable_nx = 0;
-	} else if (!strncmp(str, "off", 3)) {
-		disable_nx = 1;
-		__supported_pte_mask &= ~_PAGE_NX;
-	}
-	return 0;
-}
-early_param("noexec", noexec_setup);
-#endif
-
-#ifdef CONFIG_X86_PAE
-static void __init set_nx(void)
-{
-	unsigned int v[4], l, h;
-
-	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
-		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
-
-		if ((v[3] & (1 << 20)) && !disable_nx) {
-			rdmsr(MSR_EFER, l, h);
-			l |= EFER_NX;
-			wrmsr(MSR_EFER, l, h);
-			nx_enabled = 1;
-			__supported_pte_mask |= _PAGE_NX;
-		}
-	}
-}
-#else
-static inline void set_nx(void)
-{
-}
-#endif
-
-#ifdef CONFIG_X86_64
-void __cpuinit check_efer(void)
-{
-	unsigned long efer;
-
-	rdmsrl(MSR_EFER, efer);
-	if (!(efer & EFER_NX) || disable_nx)
-		__supported_pte_mask &= ~_PAGE_NX;
-}
-#endif
-
 static void __init find_early_table_space(unsigned long end, int use_pse,
 					  int use_gbpages)
 {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 3cd7711bb949..30938c1d8d5d 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -84,7 +84,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 #ifdef CONFIG_X86_PAE
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
 		if (after_bootmem)
-			pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+			pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
 		else
 			pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
@@ -116,7 +116,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 #endif
 			if (!page_table)
 				page_table =
-				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+				(pte_t *)alloc_bootmem_pages(PAGE_SIZE);
 		} else
 			page_table = (pte_t *)alloc_low_page();
 
@@ -857,8 +857,6 @@ static void __init test_wp_bit(void)
 	}
 }
 
-static struct kcore_list kcore_mem, kcore_vmalloc;
-
 void __init mem_init(void)
 {
 	int codesize, reservedpages, datasize, initsize;
@@ -886,13 +884,9 @@ void __init mem_init(void)
 	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
 
-	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
-	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
-		   VMALLOC_END-VMALLOC_START);
-
 	printk(KERN_INFO "Memory: %luk/%luk available (%dk kernel code, "
 			"%dk reserved, %dk data, %dk init, %ldk highmem)\n",
-		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+		nr_free_pages() << (PAGE_SHIFT-10),
 		num_physpages << (PAGE_SHIFT-10),
 		codesize >> 10,
 		reservedpages << (PAGE_SHIFT-10),
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ea56b8cbb6a6..5a4398a6006b 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -647,8 +647,7 @@ EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
-			 kcore_modules, kcore_vsyscall;
+static struct kcore_list kcore_vsyscall;
 
 void __init mem_init(void)
 {
@@ -677,17 +676,12 @@ void __init mem_init(void)
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
 
 	/* Register memory areas for /proc/kcore */
-	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
-	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
-		   VMALLOC_END-VMALLOC_START);
-	kclist_add(&kcore_kernel, &_stext, _end - _stext);
-	kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
 	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
-				 VSYSCALL_END - VSYSCALL_START);
+			 VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);
 
 	printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
 			 "%ldk absent, %ldk reserved, %ldk data, %ldk init)\n",
-		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
+		nr_free_pages() << (PAGE_SHIFT-10),
 		max_pfn << (PAGE_SHIFT-10),
 		codesize >> 10,
 		absent_pages << (PAGE_SHIFT-10),
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 334e63ca7b2b..2feb9bdedaaf 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -170,8 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 				(unsigned long long)phys_addr,
 				(unsigned long long)(phys_addr + size),
 				prot_val, new_prot_val);
-			free_memtype(phys_addr, phys_addr + size);
-			return NULL;
+			goto err_free_memtype;
 		}
 		prot_val = new_prot_val;
 	}
@@ -197,26 +196,25 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	 */
 	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
-		return NULL;
+		goto err_free_memtype;
 	area->phys_addr = phys_addr;
 	vaddr = (unsigned long) area->addr;
 
-	if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
-		free_memtype(phys_addr, phys_addr + size);
-		free_vm_area(area);
-		return NULL;
-	}
+	if (kernel_map_sync_memtype(phys_addr, size, prot_val))
+		goto err_free_area;
 
-	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
-		free_memtype(phys_addr, phys_addr + size);
-		free_vm_area(area);
-		return NULL;
-	}
+	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
+		goto err_free_area;
 
 	ret_addr = (void __iomem *) (vaddr + offset);
 	mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr);
 
 	return ret_addr;
+err_free_area:
+	free_vm_area(area);
+err_free_memtype:
+	free_memtype(phys_addr, phys_addr + size);
+	return NULL;
 }
 
 /**
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index 528bf954eb74..8cc183344140 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -225,9 +225,6 @@ void kmemcheck_hide(struct pt_regs *regs)
 
 	BUG_ON(!irqs_disabled());
 
-	if (data->balance == 0)
-		return;
-
 	if (unlikely(data->balance != 1)) {
 		kmemcheck_show_all();
 		kmemcheck_error_save_bug(regs);
diff --git a/arch/x86/mm/kmemcheck/shadow.c b/arch/x86/mm/kmemcheck/shadow.c
index e773b6bd0079..3f66b82076a3 100644
--- a/arch/x86/mm/kmemcheck/shadow.c
+++ b/arch/x86/mm/kmemcheck/shadow.c
@@ -1,7 +1,6 @@
 #include <linux/kmemcheck.h>
 #include <linux/module.h>
 #include <linux/mm.h>
-#include <linux/module.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 24952fdc7e40..dd38bfbefd1f 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -144,6 +144,7 @@ void clflush_cache_range(void *vaddr, unsigned int size)
 
 	mb();
 }
+EXPORT_SYMBOL_GPL(clflush_cache_range);
 
 static void __cpa_flush_all(void *arg)
 {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 7257cf3decf9..e78cd0ec2bcf 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -81,6 +81,7 @@ enum {
 void pat_init(void)
 {
 	u64 pat;
+	bool boot_cpu = !boot_pat_state;
 
 	if (!pat_enabled)
 		return;
@@ -122,8 +123,10 @@ void pat_init(void)
 		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
-	printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
-	       smp_processor_id(), boot_pat_state, pat);
+
+	if (boot_cpu)
+		printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
+		       smp_processor_id(), boot_pat_state, pat);
 }
 
 #undef PAT
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
new file mode 100644
index 000000000000..513d8ed5d2ec
--- /dev/null
+++ b/arch/x86/mm/setup_nx.c
@@ -0,0 +1,69 @@
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+
+#include <asm/pgtable.h>
+
+int nx_enabled;
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+static int disable_nx __cpuinitdata;
+
+/*
+ * noexec = on|off
+ *
+ * Control non-executable mappings for processes.
+ *
+ * on      Enable
+ * off     Disable
+ */
+static int __init noexec_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+	if (!strncmp(str, "on", 2)) {
+		__supported_pte_mask |= _PAGE_NX;
+		disable_nx = 0;
+	} else if (!strncmp(str, "off", 3)) {
+		disable_nx = 1;
+		__supported_pte_mask &= ~_PAGE_NX;
+	}
+	return 0;
+}
+early_param("noexec", noexec_setup);
+#endif
+
+#ifdef CONFIG_X86_PAE
+void __init set_nx(void)
+{
+	unsigned int v[4], l, h;
+
+	if (cpu_has_pae && (cpuid_eax(0x80000000) > 0x80000001)) {
+		cpuid(0x80000001, &v[0], &v[1], &v[2], &v[3]);
+
+		if ((v[3] & (1 << 20)) && !disable_nx) {
+			rdmsr(MSR_EFER, l, h);
+			l |= EFER_NX;
+			wrmsr(MSR_EFER, l, h);
+			nx_enabled = 1;
+			__supported_pte_mask |= _PAGE_NX;
+		}
+	}
+}
+#else
+void set_nx(void)
+{
+}
+#endif
+
+#ifdef CONFIG_X86_64
+void __cpuinit check_efer(void)
+{
+	unsigned long efer;
+
+	rdmsrl(MSR_EFER, efer);
+	if (!(efer & EFER_NX) || disable_nx)
+		__supported_pte_mask &= ~_PAGE_NX;
+}
+#endif
+
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index c814e144a3f0..36fe08eeb5c3 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -59,7 +59,8 @@ void leave_mm(int cpu)
 {
 	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
 		BUG();
-	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
+	cpumask_clear_cpu(cpu,
+			  mm_cpumask(percpu_read(cpu_tlbstate.active_mm)));
 	load_cr3(swapper_pg_dir);
 }
 EXPORT_SYMBOL_GPL(leave_mm);
@@ -234,8 +235,8 @@ void flush_tlb_current_task(void)
 	preempt_disable();
 
 	local_flush_tlb();
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
@@ -249,8 +250,8 @@ void flush_tlb_mm(struct mm_struct *mm)
 		else
 			leave_mm(smp_processor_id());
 	}
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
 
 	preempt_enable();
 }
@@ -268,8 +269,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
 			leave_mm(smp_processor_id());
 	}
 
-	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(&mm->cpu_vm_mask, mm, va);
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, va);
 
 	preempt_enable();
 }