9 files changed, 366 insertions, 25 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 59f89b434b45..fea4565ff576 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,7 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
             pat.o pgtable.o gup.o
 
-obj-$(CONFIG_X86_32)            += pgtable_32.o
+obj-$(CONFIG_X86_32)            += pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP)        += dump_pagetables.o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 31e8730fa246..20ef272c412c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -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;
@@ -849,11 +851,12 @@ 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
 
 /*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 8396868e82c5..800e1d94c1b5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -67,7 +67,7 @@ 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 +77,6 @@ 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 +91,17 @@ 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 +126,8 @@ 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));
@@ -334,7 +332,6 @@ int devmem_is_allowed(unsigned long pagenr)
         return 0;
 }
 
-#ifdef CONFIG_HIGHMEM
 pte_t *kmap_pte;
 pgprot_t kmap_prot;
 
@@ -357,6 +354,7 @@ static void __init kmap_init(void)
         kmap_prot = PAGE_KERNEL;
 }
 
+#ifdef CONFIG_HIGHMEM
 static void __init permanent_kmaps_init(pgd_t *pgd_base)
 {
         unsigned long vaddr;
@@ -436,7 +434,6 @@ static void __init set_highmem_pages_init(void)
 #endif /* !CONFIG_NUMA */
 
 #else
-# define kmap_init()                            do { } while (0)
 # define permanent_kmaps_init(pgd_base)         do { } while (0)
 # define set_highmem_pages_init()       do { } while (0)
 #endif /* CONFIG_HIGHMEM */
@@ -970,8 +967,6 @@ void __init mem_init(void)
         int codesize, reservedpages, datasize, initsize;
         int tmp;
 
-        start_periodic_check_for_corruption();
-
 #ifdef CONFIG_FLATMEM
         BUG_ON(!mem_map);
 #endif
@@ -1041,11 +1036,25 @@ 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)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9db01db6e3cd..9f7a0d24d42a 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -902,8 +902,6 @@ 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/iomap_32.c b/arch/x86/mm/iomap_32.c
new file mode 100644
index 000000000000..d0151d8ce452
--- /dev/null
+++ b/arch/x86/mm/iomap_32.c
@@ -0,0 +1,59 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <asm/iomap.h>
+#include <linux/module.h>
+
+/* Map 'pfn' using fixed map 'type' and protections 'prot'
+ */
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
+{
+        enum fixed_addresses idx;
+        unsigned long vaddr;
+
+        pagefault_disable();
+
+        idx = type + KM_TYPE_NR*smp_processor_id();
+        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+        set_pte(kmap_pte-idx, pfn_pte(pfn, prot));
+        arch_flush_lazy_mmu_mode();
+
+        return (void*) vaddr;
+}
+EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type)
+{
+        unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
+        enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
+
+        /*
+         * Force other mappings to Oops if they'll try to access this pte
+         * without first remap it.  Keeping stale mappings around is a bad idea
+         * also, in case the page changes cacheability attributes or becomes
+         * a protected page in a hypervisor.
+         */
+        if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+                kpte_clear_flush(kmap_pte-idx, vaddr);
+
+        arch_flush_lazy_mmu_mode();
+        pagefault_enable();
+}
+EXPORT_SYMBOL_GPL(iounmap_atomic);
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 847c164725f4..8518c678d83f 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
         }
 }
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ *                       during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+        int node;
+
+        for_each_online_node(node) {
+                unsigned long start_va, start_pfn, size, pfn;
+
+                start_va = (unsigned long)node_remap_start_vaddr[node];
+                start_pfn = node_remap_start_pfn[node];
+                size = node_remap_size[node];
+
+                printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+                for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+                        unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+                        pgd_t *pgd = pgd_base + pgd_index(vaddr);
+                        pud_t *pud = pud_offset(pgd, vaddr);
+                        pmd_t *pmd = pmd_offset(pud, vaddr);
+
+                        set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+                                                PAGE_KERNEL_LARGE_EXEC));
+
+                        printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+                                __FUNCTION__, vaddr, start_pfn + pfn);
+                }
+        }
+}
+#endif
+
 static unsigned long calculate_numa_remap_pages(void)
 {
         int nid;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f1dc1b75d166..e89d24815f26 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -67,18 +67,18 @@ static void split_page_count(int level)
 
 void arch_report_meminfo(struct seq_file *m)
 {
-        seq_printf(m, "DirectMap4k:  %8lu kB\n",
+        seq_printf(m, "DirectMap4k:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_4K] << 2);
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-        seq_printf(m, "DirectMap2M:  %8lu kB\n",
+        seq_printf(m, "DirectMap2M:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_2M] << 11);
 #else
-        seq_printf(m, "DirectMap4M:  %8lu kB\n",
+        seq_printf(m, "DirectMap4M:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_2M] << 12);
 #endif
 #ifdef CONFIG_X86_64
         if (direct_gbpages)
-                seq_printf(m, "DirectMap1G:  %8lu kB\n",
+                seq_printf(m, "DirectMap1G:    %8lu kB\n",
                         direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
 }
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index eb1bf000d12e..541bcc944a5b 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;
+        u64 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;
+        u64 base_paddr;
+        u64 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 = (u64)vma->vm_pgoff << PAGE_SHIFT;
+                return reserve_pfn_range(paddr, vma_size, prot);
+        }
+
+        /* reserve page by page using pfn and size */
+        base_paddr = (u64)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;
+        u64 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 = (u64)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 = (u64)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 */