Merge branch 'core/percpu' into stackprotector

Conflicts:
	arch/x86/include/asm/pda.h
	arch/x86/include/asm/system.h

Also, moved include/asm-x86/stackprotector.h to arch/x86/include/asm.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

9 files changed, 127 insertions, 83 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 4c056b5d6a95..37242c405f16 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -535,7 +535,7 @@ static int vmalloc_fault(unsigned long address)
            happen within a race in page table update. In the later
            case just flush. */
 
-        pgd = pgd_offset(current->mm ?: &init_mm, address);
+        pgd = pgd_offset(current->active_mm, address);
         pgd_ref = pgd_offset_k(address);
         if (pgd_none(*pgd_ref))
                 return -1;
@@ -670,7 +670,6 @@ 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
@@ -866,25 +865,14 @@ no_context:
         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 8655b5bb0963..4a6989e47a53 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,7 +49,6 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
-#include <asm/smp.h>
 
 unsigned int __VMALLOC_RESERVE = 128 << 20;
 
@@ -328,6 +327,8 @@ 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;
@@ -435,8 +436,12 @@ 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)
@@ -1075,7 +1080,7 @@ 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 9f7a0d24d42a..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;
diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c
index 41f1b5c00a1d..268f8255280f 100644
--- a/arch/x86/mm/k8topology_64.c
+++ b/arch/x86/mm/k8topology_64.c
@@ -81,7 +81,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
         unsigned numnodes, cores, bits, apicid_base;
         unsigned long prevbase;
         struct bootnode nodes[8];
-        unsigned char nodeids[8];
         int i, j, nb, found = 0;
         u32 nodeid, reg;
 
@@ -110,7 +109,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
                 limit = read_pci_config(0, nb, 1, 0x44 + i*8);
 
                 nodeid = limit & 7;
-                nodeids[i] = nodeid;
                 if ((base & 3) == 0) {
                         if (i < numnodes)
                                 printk("Skipping disabled node %d\n", i);
@@ -179,9 +177,6 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
 
                 nodes[nodeid].start = base;
                 nodes[nodeid].end = limit;
-                e820_register_active_regions(nodeid,
-                                nodes[nodeid].start >> PAGE_SHIFT,
-                                nodes[nodeid].end >> PAGE_SHIFT);
 
                 prevbase = base;
 
@@ -211,12 +206,15 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
         }
 
         for (i = 0; i < 8; i++) {
-                if (nodes[i].start != nodes[i].end) {
-                        nodeid = nodeids[i];
-                        for (j = apicid_base; j < cores + apicid_base; j++)
-                                apicid_to_node[(nodeid << bits) + j] = i;
-                        setup_node_bootmem(i, nodes[i].start, nodes[i].end);
-                }
+                if (nodes[i].start == nodes[i].end)
+                        continue;
+
+                e820_register_active_regions(i,
+                                nodes[i].start >> PAGE_SHIFT,
+                                nodes[i].end >> PAGE_SHIFT);
+                for (j = apicid_base; j < cores + apicid_base; j++)
+                        apicid_to_node[(i << bits) + j] = i;
+                setup_node_bootmem(i, nodes[i].start, nodes[i].end);
         }
 
         numa_init_array();
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/pageattr.c b/arch/x86/mm/pageattr.c
index e89d24815f26..4cf30dee8161 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -555,10 +555,12 @@ repeat:
         if (!pte_val(old_pte)) {
                 if (!primary)
                         return 0;
-                WARN(1, KERN_WARNING "CPA: called for zero pte. "
-                       "vaddr = %lx cpa->vaddr = %lx\n", address,
-                       *cpa->vaddr);
-                return -EINVAL;
+
+                /*
+                 *  Special error value returned, indicating that the mapping
+                 * did not exist at this address.
+                 */
+                return -EFAULT;
         }
 
         if (level == PG_LEVEL_4K) {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 85cbd3cd3723..3be399013de6 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -333,11 +333,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
                                               req_type & _PAGE_CACHE_MASK);
         }
 
-        is_range_ram = pagerange_is_ram(start, end);
-        if (is_range_ram == 1)
-                return reserve_ram_pages_type(start, end, req_type, new_type);
-        else if (is_range_ram < 0)
-                return -EINVAL;
+        /*
+         * For legacy reasons, some parts of the physical address range in the
+         * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+         * the e820 tables).  So we will track the memory attributes of this
+         * legacy 1MB region using the linear memtype_list always.
+         */
+        if (end >= ISA_END_ADDRESS) {
+                is_range_ram = pagerange_is_ram(start, end);
+                if (is_range_ram == 1)
+                        return reserve_ram_pages_type(start, end, req_type,
+                                                      new_type);
+                else if (is_range_ram < 0)
+                        return -EINVAL;
+        }
 
         new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
         if (!new)
@@ -437,11 +446,19 @@ int free_memtype(u64 start, u64 end)
         if (is_ISA_range(start, end - 1))
                 return 0;
 
-        is_range_ram = pagerange_is_ram(start, end);
-        if (is_range_ram == 1)
-                return free_ram_pages_type(start, end);
-        else if (is_range_ram < 0)
-                return -EINVAL;
+        /*
+         * For legacy reasons, some parts of the physical address range in the
+         * legacy 1MB region is treated as non-RAM (even when listed as RAM in
+         * the e820 tables).  So we will track the memory attributes of this
+         * legacy 1MB region using the linear memtype_list always.
+         */
+        if (end >= ISA_END_ADDRESS) {
+                is_range_ram = pagerange_is_ram(start, end);
+                if (is_range_ram == 1)
+                        return free_ram_pages_type(start, end);
+                else if (is_range_ram < 0)
+                        return -EINVAL;
+        }
 
         spin_lock(&memtype_lock);
         list_for_each_entry(entry, &memtype_list, nd) {
@@ -505,6 +522,35 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 }
 #endif /* CONFIG_STRICT_DEVMEM */
 
+/*
+ * Change the memory type for the physial address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+static int kernel_map_sync_memtype(u64 base, unsigned long size,
+                                        unsigned long flags)
+{
+        unsigned long id_sz;
+        int ret;
+
+        if (!pat_enabled || base >= __pa(high_memory))
+                return 0;
+
+        id_sz = (__pa(high_memory) < base + size) ?
+                                                __pa(high_memory) - base :
+                                                size;
+
+        ret = ioremap_change_attr((unsigned long)__va(base), id_sz, flags);
+        /*
+         * -EFAULT return means that the addr was not valid and did not have
+         * any identity mapping. That case is a success for
+         * kernel_map_sync_memtype.
+         */
+        if (ret == -EFAULT)
+                ret = 0;
+
+        return ret;
+}
+
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                                 unsigned long size, pgprot_t *vma_prot)
 {
@@ -555,9 +601,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
         if (retval < 0)
                 return 0;
 
-        if (((pfn < max_low_pfn_mapped) ||
-             (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) &&
-            ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
+        if (kernel_map_sync_memtype(offset, size, flags)) {
                 free_memtype(offset, offset + size);
                 printk(KERN_INFO
                 "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
@@ -601,12 +645,13 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_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)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
+                                int strict_prot)
 {
         int is_ram = 0;
-        int id_sz, ret;
+        int ret;
         unsigned long flags;
-        unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
+        unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
 
         is_ram = pagerange_is_ram(paddr, paddr + size);
 
@@ -625,26 +670,27 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t vma_prot)
                 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;
+                if (strict_prot || !is_new_memtype_allowed(want_flags, 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;
+                }
+                /*
+                 * We allow returning different type than the one requested in
+                 * non strict case.
+                 */
+                *vma_prot = __pgprot((pgprot_val(*vma_prot) &
+                                      (~_PAGE_CACHE_MASK)) |
+                                     flags);
         }
 
-        /* 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) {
+        if (kernel_map_sync_memtype(paddr, size, flags)) {
                 free_memtype(paddr, paddr + size);
                 printk(KERN_ERR
                         "%s:%d reserve_pfn_range ioremap_change_attr failed %s "
@@ -689,6 +735,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
         unsigned long vma_start = vma->vm_start;
         unsigned long vma_end = vma->vm_end;
         unsigned long vma_size = vma_end - vma_start;
+        pgprot_t pgprot;
 
         if (!pat_enabled)
                 return 0;
@@ -702,7 +749,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
                         WARN_ON_ONCE(1);
                         return -EINVAL;
                 }
-                return reserve_pfn_range(paddr, vma_size, __pgprot(prot));
+                pgprot = __pgprot(prot);
+                return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
         }
 
         /* reserve entire vma page by page, using pfn and prot from pte */
@@ -710,7 +758,8 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
                 if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
                         continue;
 
-                retval = reserve_pfn_range(paddr, PAGE_SIZE, __pgprot(prot));
+                pgprot = __pgprot(prot);
+                retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
                 if (retval)
                         goto cleanup_ret;
         }
@@ -741,7 +790,7 @@ cleanup_ret:
  * 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,
+int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
                         unsigned long pfn, unsigned long size)
 {
         int retval = 0;
@@ -758,14 +807,14 @@ int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t prot,
         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);
+                return reserve_pfn_range(paddr, vma_size, prot, 0);
         }
 
         /* 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);
+                retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
                 if (retval)
                         goto cleanup_ret;
         }
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)