9 files changed, 294 insertions, 48 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index fea4565ff576..d8cc96a2738f 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -8,9 +8,8 @@ obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
-obj-$(CONFIG_MMIOTRACE_HOOKS)	+= kmmio.o
 obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
-mmiotrace-y			:= pf_in.o mmio-mod.o
+mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 31e8730fa246..9e268b6b204e 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -53,7 +53,7 @@
 
 static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
-#ifdef CONFIG_MMIOTRACE_HOOKS
+#ifdef CONFIG_MMIOTRACE
 	if (unlikely(is_kmmio_active()))
 		if (kmmio_handler(regs, addr) == 1)
 			return -1;
@@ -393,7 +393,7 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
 			printk(KERN_CRIT "kernel tried to execute "
 				"NX-protected page - exploit attempt? "
-				"(uid: %d)\n", current->uid);
+				"(uid: %d)\n", current_uid());
 	}
 #endif
 
@@ -413,6 +413,7 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 				 unsigned long error_code)
 {
 	unsigned long flags = oops_begin();
+	int sig = SIGKILL;
 	struct task_struct *tsk;
 
 	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
@@ -423,8 +424,8 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
 	if (__die("Bad pagetable", regs, error_code))
-		regs = NULL;
-	oops_end(flags, regs, SIGKILL);
+		sig = 0;
+	oops_end(flags, regs, sig);
 }
 #endif
 
@@ -590,6 +591,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	int fault;
 #ifdef CONFIG_X86_64
 	unsigned long flags;
+	int sig;
 #endif
 
 	tsk = current;
@@ -665,7 +667,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	if (unlikely(in_atomic() || !mm))
 		goto bad_area_nosemaphore;
 
-again:
 	/*
 	 * When running in the kernel we expect faults to occur only to
 	 * addresses in user space.  All other faults represent errors in the
@@ -849,32 +850,22 @@ no_context:
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
 #else
+	sig = SIGKILL;
 	if (__die("Oops", regs, error_code))
-		regs = NULL;
+		sig = 0;
 	/* Executive summary in case the body of the oops scrolled away */
 	printk(KERN_EMERG "CR2: %016lx\n", address);
-	oops_end(flags, regs, SIGKILL);
+	oops_end(flags, regs, sig);
 #endif
 
-/*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
 out_of_memory:
+	/*
+	 * We ran out of memory, call the OOM killer, and return the userspace
+	 * (which will retry the fault, or kill us if we got oom-killed).
+	 */
 	up_read(&mm->mmap_sem);
-	if (is_global_init(tsk)) {
-		yield();
-		/*
-		 * Re-lookup the vma - in theory the vma tree might
-		 * have changed:
-		 */
-		goto again;
-	}
-
-	printk("VM: killing process %s\n", tsk->comm);
-	if (error_code & PF_USER)
-		do_group_exit(SIGKILL);
-	goto no_context;
+	pagefault_out_of_memory();
+	return;
 
 do_sigbus:
 	up_read(&mm->mmap_sem);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c483f4242079..88f1b10de3be 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
+#include <linux/pci.h>
 #include <linux/pfn.h>
 #include <linux/poison.h>
 #include <linux/bootmem.h>
@@ -67,7 +68,7 @@ static unsigned long __meminitdata table_top;
 
 static int __initdata after_init_bootmem;
 
-static __init void *alloc_low_page(unsigned long *phys)
+static __init void *alloc_low_page(void)
 {
 	unsigned long pfn = table_end++;
 	void *adr;
@@ -77,7 +78,6 @@ static __init void *alloc_low_page(unsigned long *phys)
 
 	adr = __va(pfn * PAGE_SIZE);
 	memset(adr, 0, PAGE_SIZE);
-	*phys  = pfn * PAGE_SIZE;
 	return adr;
 }
 
@@ -92,16 +92,17 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 	pmd_t *pmd_table;
 
 #ifdef CONFIG_X86_PAE
-	unsigned long phys;
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
 		if (after_init_bootmem)
 			pmd_table = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 		else
-			pmd_table = (pmd_t *)alloc_low_page(&phys);
+			pmd_table = (pmd_t *)alloc_low_page();
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
 	}
 #endif
 	pud = pud_offset(pgd, 0);
@@ -126,10 +127,8 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 			if (!page_table)
 				page_table =
 				(pte_t *)alloc_bootmem_low_pages(PAGE_SIZE);
-		} else {
-			unsigned long phys;
-			page_table = (pte_t *)alloc_low_page(&phys);
-		}
+		} else
+			page_table = (pte_t *)alloc_low_page();
 
 		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -329,6 +328,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
@@ -436,8 +437,12 @@ static void __init set_highmem_pages_init(void)
 #endif /* !CONFIG_NUMA */
 
 #else
-# define permanent_kmaps_init(pgd_base)		do { } while (0)
-# define set_highmem_pages_init()	do { } while (0)
+static inline void permanent_kmaps_init(pgd_t *pgd_base)
+{
+}
+static inline void set_highmem_pages_init(void)
+{
+}
 #endif /* CONFIG_HIGHMEM */
 
 void __init native_pagetable_setup_start(pgd_t *base)
@@ -969,7 +974,7 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
-	start_periodic_check_for_corruption();
+	pci_iommu_alloc();
 
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
@@ -1040,11 +1045,25 @@ void __init mem_init(void)
 		(unsigned long)&_text, (unsigned long)&_etext,
 		((unsigned long)&_etext - (unsigned long)&_text) >> 10);
 
+	/*
+	 * Check boundaries twice: Some fundamental inconsistencies can
+	 * be detected at build time already.
+	 */
+#define __FIXADDR_TOP (-PAGE_SIZE)
+#ifdef CONFIG_HIGHMEM
+	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
+	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
+#endif
+#define high_memory (-128UL << 20)
+	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
+#undef high_memory
+#undef __FIXADDR_TOP
+
 #ifdef CONFIG_HIGHMEM
 	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
 	BUG_ON(VMALLOC_END				> PKMAP_BASE);
 #endif
-	BUG_ON(VMALLOC_START				> VMALLOC_END);
+	BUG_ON(VMALLOC_START				>= VMALLOC_END);
 	BUG_ON((unsigned long)high_memory		> VMALLOC_START);
 
 	if (boot_cpu_data.wp_works_ok < 0)
@@ -1062,7 +1081,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	return __add_pages(zone, start_pfn, nr_pages);
+	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
 #endif
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9db01db6e3cd..23f68e77ad1f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -857,7 +857,7 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	if (last_mapped_pfn > max_pfn_mapped)
 		max_pfn_mapped = last_mapped_pfn;
 
-	ret = __add_pages(zone, start_pfn, nr_pages);
+	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 	WARN_ON_ONCE(ret);
 
 	return ret;
@@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
@@ -902,8 +904,6 @@ void __init mem_init(void)
 	long codesize, reservedpages, datasize, initsize;
 	unsigned long absent_pages;
 
-	start_periodic_check_for_corruption();
-
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4c4307ff3e0..bd85d42819e1 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -223,7 +223,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	 * Check if the request spans more than any BAR in the iomem resource
 	 * tree.
 	 */
-	WARN_ON(iomem_map_sanity_check(phys_addr, size));
+	WARN_ONCE(iomem_map_sanity_check(phys_addr, size),
+		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
 
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 8518c678d83f..d1f7439d173c 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -239,7 +239,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 		start_pfn = node_remap_start_pfn[node];
 		size = node_remap_size[node];
 
-		printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+		printk(KERN_DEBUG "%s: node %d\n", __func__, node);
 
 		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
 			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
@@ -251,7 +251,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 						PAGE_KERNEL_LARGE_EXEC));
 
 			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
-				__FUNCTION__, vaddr, start_pfn + pfn);
+				__func__, vaddr, start_pfn + pfn);
 		}
 	}
 }
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index cebcbf152d46..71a14f89f89e 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -278,7 +278,7 @@ void __init numa_init_array(void)
 	int rr, i;
 
 	rr = first_node(node_online_map);
-	for (i = 0; i < NR_CPUS; i++) {
+	for (i = 0; i < nr_cpu_ids; i++) {
 		if (early_cpu_to_node(i) != NUMA_NO_NODE)
 			continue;
 		numa_set_node(i, rr);
@@ -549,7 +549,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn)
 	memnodemap[0] = 0;
 	node_set_online(0);
 	node_set(0, node_possible_map);
-	for (i = 0; i < NR_CPUS; i++)
+	for (i = 0; i < nr_cpu_ids; i++)
 		numa_set_node(i, 0);
 	e820_register_active_regions(0, start_pfn, last_pfn);
 	setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index eb1bf000d12e..85cbd3cd3723 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -596,6 +596,242 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 	free_memtype(addr, addr + size);
 }
 
+/*
+ * Internal interface to reserve a range of physical memory with prot.
+ * Reserved non RAM regions only and after successful reserve_memtype,
+ * this func also keeps identity mapping (if any) in sync with this new prot.
+ */
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
+{
+	int is_ram = 0;
+	int id_sz, ret;
+	unsigned long flags;
+	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+
+	is_ram = pagerange_is_ram(paddr, paddr + size);
+
+	if (is_ram != 0) {
+		/*
+		 * For mapping RAM pages, drivers need to call
+		 * set_memory_[uc|wc|wb] directly, for reserve and free, before
+		 * setting up the PTE.
+		 */
+		WARN_ON_ONCE(1);
+		return 0;
+	}
+
+	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+	if (ret)
+		return ret;
+
+	if (flags != want_flags) {
+		free_memtype(paddr, paddr + size);
+		printk(KERN_ERR
+		"%s:%d map pfn expected mapping type %s for %Lx-%Lx, got %s\n",
+			current->comm, current->pid,
+			cattr_name(want_flags),
+			(unsigned long long)paddr,
+			(unsigned long long)(paddr + size),
+			cattr_name(flags));
+		return -EINVAL;
+	}
+
+	/* Need to keep identity mapping in sync */
+	if (paddr >= __pa(high_memory))
+		return 0;
+
+	id_sz = (__pa(high_memory) < paddr + size) ?
+				__pa(high_memory) - paddr :
+				size;
+
+	if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+		free_memtype(paddr, paddr + size);
+		printk(KERN_ERR
+			"%s:%d reserve_pfn_range ioremap_change_attr failed %s "
+			"for %Lx-%Lx\n",
+			current->comm, current->pid,
+			cattr_name(flags),
+			(unsigned long long)paddr,
+			(unsigned long long)(paddr + size));
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
+ * Internal interface to free a range of physical memory.
+ * Frees non RAM regions only.
+ */
+static void free_pfn_range(u64 paddr, unsigned long size)
+{
+	int is_ram;
+
+	is_ram = pagerange_is_ram(paddr, paddr + size);
+	if (is_ram == 0)
+		free_memtype(paddr, paddr + size);
+}
+
+/*
+ * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * copied through copy_page_range().
+ *
+ * If the vma has a linear pfn mapping for the entire range, we get the prot
+ * from pte and reserve the entire vma range with single reserve_pfn_range call.
+ * Otherwise, we reserve the entire vma range, my ging through the PTEs page
+ * by page to get physical address and protection.
+ */
+int track_pfn_vma_copy(struct vm_area_struct *vma)
+{
+	int retval = 0;
+	unsigned long i, j;
+	resource_size_t paddr;
+	unsigned long prot;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return 0;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/*
+		 * reserve the whole chunk covered by vma. We need the
+		 * starting address and protection from pte.
+		 */
+		if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+			WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
+		return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+	}
+
+	/* reserve entire vma page by page, using pfn and prot from pte */
+	for (i = 0; i < vma_size; i += PAGE_SIZE) {
+		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+			continue;
+
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+		if (retval)
+			goto cleanup_ret;
+	}
+	return 0;
+
+cleanup_ret:
+	/* Reserve error: Cleanup partial reservation and return error */
+	for (j = 0; j < i; j += PAGE_SIZE) {
+		if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
+			continue;
+
+		free_pfn_range(paddr, PAGE_SIZE);
+	}
+
+	return retval;
+}
+
+/*
+ * track_pfn_vma_new is called when a _new_ pfn mapping is being established
+ * for physical range indicated by pfn and size.
+ *
+ * prot is passed in as a parameter for the new mapping. If the vma has a
+ * linear pfn mapping for the entire range reserve the entire vma range with
+ * single reserve_pfn_range call.
+ * Otherwise, we look t the pfn and size and reserve only the specified range
+ * page by page.
+ *
+ * Note that this function can be called with caller trying to map only a
+ * subrange/page inside the vma.
+ */
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
+			unsigned long pfn, unsigned long size)
+{
+	int retval = 0;
+	unsigned long i, j;
+	resource_size_t base_paddr;
+	resource_size_t paddr;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return 0;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/* reserve the whole chunk starting from vm_pgoff */
+		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		return reserve_pfn_range(paddr, vma_size, prot);
+	}
+
+	/* reserve page by page using pfn and size */
+	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		paddr = base_paddr + i;
+		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot);
+		if (retval)
+			goto cleanup_ret;
+	}
+	return 0;
+
+cleanup_ret:
+	/* Reserve error: Cleanup partial reservation and return error */
+	for (j = 0; j < i; j += PAGE_SIZE) {
+		paddr = base_paddr + j;
+		free_pfn_range(paddr, PAGE_SIZE);
+	}
+
+	return retval;
+}
+
+/*
+ * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack can be called for a specific region indicated by pfn and size or
+ * can be for the entire vma (in which case size can be zero).
+ */
+void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
+			unsigned long size)
+{
+	unsigned long i;
+	resource_size_t paddr;
+	unsigned long prot;
+	unsigned long vma_start = vma->vm_start;
+	unsigned long vma_end = vma->vm_end;
+	unsigned long vma_size = vma_end - vma_start;
+
+	if (!pat_enabled)
+		return;
+
+	if (is_linear_pfn_mapping(vma)) {
+		/* free the whole chunk starting from vm_pgoff */
+		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+		free_pfn_range(paddr, vma_size);
+		return;
+	}
+
+	if (size != 0 && size != vma_size) {
+		/* free page by page, using pfn and size */
+		paddr = (resource_size_t)pfn << PAGE_SHIFT;
+		for (i = 0; i < size; i += PAGE_SIZE) {
+			paddr = paddr + i;
+			free_pfn_range(paddr, PAGE_SIZE);
+		}
+	} else {
+		/* free entire vma, page by page, using the pfn from pte */
+		for (i = 0; i < vma_size; i += PAGE_SIZE) {
+			if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
+				continue;
+
+			free_pfn_range(paddr, PAGE_SIZE);
+		}
+	}
+}
+
+pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	if (pat_enabled)
+		return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+	else
+		return pgprot_noncached(prot);
+}
+
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
 /* get Nth element of the linked list */
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 51c0a2fc14fe..09737c8af074 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -382,7 +382,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		if (!node_online(i))
 			setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 
-	for (i = 0; i < NR_CPUS; i++) {
+	for (i = 0; i < nr_cpu_ids; i++) {
 		int node = early_cpu_to_node(i);
 
 		if (node == NUMA_NO_NODE)