10 files changed, 45 insertions, 25 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2dbf6bf4c7e..0d17c8c50ac 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -17,6 +17,7 @@
 #include <asm/traps.h>                  /* dotraplinkage, ...           */
 #include <asm/pgalloc.h>                /* pgd_*(), ...                 */
 #include <asm/kmemcheck.h>              /* kmemcheck_*(), ...           */
+#include <asm/vsyscall.h>
 
 /*
  * Page fault error code bits:
@@ -105,7 +106,7 @@ check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
                  * but for now it's good enough to assume that long
                  * mode only uses well known segments or kernel.
                  */
-                return (!user_mode(regs)) || (regs->cs == __USER_CS);
+                return (!user_mode(regs) || user_64bit_mode(regs));
 #endif
         case 0x60:
                 /* 0x64 thru 0x67 are valid prefixes in all modes. */
@@ -720,6 +721,18 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
                 if (is_errata100(regs, address))
                         return;
 
+#ifdef CONFIG_X86_64
+                /*
+                 * Instruction fetch faults in the vsyscall page might need
+                 * emulation.
+                 */
+                if (unlikely((error_code & PF_INSTR) &&
+                             ((address & ~0xfff) == VSYSCALL_START))) {
+                        if (emulate_vsyscall(regs, address))
+                                return;
+                }
+#endif
+
                 if (unlikely(show_unhandled_signals))
                         show_signal_msg(regs, error_code, address, tsk);
 
@@ -1059,7 +1072,7 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code)
         if (unlikely(error_code & PF_RSVD))
                 pgtable_bad(regs, error_code, address);
 
-        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
         /*
          * If we're in an interrupt, have no user context or are running
@@ -1161,11 +1174,11 @@ good_area:
         if (flags & FAULT_FLAG_ALLOW_RETRY) {
                 if (fault & VM_FAULT_MAJOR) {
                         tsk->maj_flt++;
-                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
                                       regs, address);
                 } else {
                         tsk->min_flt++;
-                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
                                       regs, address);
                 }
                 if (fault & VM_FAULT_RETRY) {
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index dbe34b93137..dd74e46828c 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -108,16 +108,6 @@ static inline void get_head_page_multiple(struct page *page, int nr)
         SetPageReferenced(page);
 }
 
-static inline void get_huge_page_tail(struct page *page)
-{
-        /*
-         * __split_huge_page_refcount() cannot run
-         * from under us.
-         */
-        VM_BUG_ON(atomic_read(&page->_count) < 0);
-        atomic_inc(&page->_count);
-}
-
 static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
                 unsigned long end, int write, struct page **pages, int *nr)
 {
@@ -211,6 +201,8 @@ static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
         do {
                 VM_BUG_ON(compound_head(page) != head);
                 pages[*nr] = page;
+                if (PageTail(page))
+                        get_huge_page_tail(page);
                 (*nr)++;
                 page++;
                 refs++;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index b4996266210..f4f29b19fac 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -45,6 +45,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
         vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
         BUG_ON(!pte_none(*(kmap_pte-idx)));
         set_pte(kmap_pte-idx, mk_pte(page, prot));
+        arch_flush_lazy_mmu_mode();
 
         return (void *)vaddr;
 }
@@ -88,6 +89,7 @@ void __kunmap_atomic(void *kvaddr)
                  */
                 kpte_clear_flush(kmap_pte-idx, vaddr);
                 kmap_atomic_idx_pop();
+                arch_flush_lazy_mmu_mode();
         }
 #ifdef CONFIG_DEBUG_HIGHMEM
         else {
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 30326443ab8..87488b93a65 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -63,9 +63,8 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
 #ifdef CONFIG_X86_32
         /* for fixmap */
         tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
-
-        good_end = max_pfn_mapped << PAGE_SHIFT;
 #endif
+        good_end = max_pfn_mapped << PAGE_SHIFT;
 
         base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE);
         if (base == MEMBLOCK_ERROR)
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index 704a37ceddd..dab41876cdd 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
         e->trace.entries = e->trace_entries;
         e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
         e->trace.skip = 0;
-        save_stack_trace_regs(&e->trace, regs);
+        save_stack_trace_regs(regs, &e->trace);
 
         /* Round address down to nearest 16 bytes */
         shadow_copy = kmemcheck_shadow_lookup(address
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 1dab5194fd9..f927429d07c 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -87,9 +87,9 @@ static unsigned long mmap_rnd(void)
         */
         if (current->flags & PF_RANDOMIZE) {
                 if (mmap_is_ia32())
-                        rnd = (long)get_random_int() % (1<<8);
+                        rnd = get_random_int() % (1<<8);
                 else
-                        rnd = (long)(get_random_int() % (1<<28));
+                        rnd = get_random_int() % (1<<28);
         }
         return rnd << PAGE_SHIFT;
 }
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 3adff7dcc14..67421f38a21 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -34,7 +34,7 @@
 #include <asm/pgtable.h>
 #include <linux/mmiotrace.h>
 #include <asm/e820.h> /* for ISA_START_ADDRESS */
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <linux/percpu.h>
 #include <linux/cpu.h>
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index f5510d889a2..fbeaaf41661 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -496,6 +496,7 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
 
 static int __init numa_register_memblks(struct numa_meminfo *mi)
 {
+        unsigned long uninitialized_var(pfn_align);
         int i, nid;
 
         /* Account for nodes with cpus and no memory */
@@ -511,6 +512,20 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
 
         /* for out of order entries */
         sort_node_map();
+
+        /*
+         * If sections array is gonna be used for pfn -> nid mapping, check
+         * whether its granularity is fine enough.
+         */
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+        pfn_align = node_map_pfn_alignment();
+        if (pfn_align && pfn_align < PAGES_PER_SECTION) {
+                printk(KERN_WARNING "Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
+                       PFN_PHYS(pfn_align) >> 20,
+                       PFN_PHYS(PAGES_PER_SECTION) >> 20);
+                return -EINVAL;
+        }
+#endif
         if (!numa_meminfo_cover_memory(mi))
                 return -EINVAL;
 
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 849a975d3fa..3adebe7e536 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -41,7 +41,7 @@
  *     physnode_map[16-31] = 1;
  *     physnode_map[32- ] = -1;
  */
-s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+s8 physnode_map[MAX_SECTIONS] __read_mostly = { [0 ... (MAX_SECTIONS - 1)] = -1};
 EXPORT_SYMBOL(physnode_map);
 
 void memory_present(int nid, unsigned long start, unsigned long end)
@@ -52,8 +52,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
                         nid, start, end);
         printk(KERN_DEBUG "  Setting physnode_map array to node %d for pfns:\n", nid);
         printk(KERN_DEBUG "  ");
-        for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
-                physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
+        for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
+                physnode_map[pfn / PAGES_PER_SECTION] = nid;
                 printk(KERN_CONT "%lx ", pfn);
         }
         printk(KERN_CONT "\n");
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index e1d10690921..b0086567271 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -123,12 +123,11 @@ static int pageattr_test(void)
         if (print)
                 printk(KERN_INFO "CPA self-test:\n");
 
-        bm = vmalloc((max_pfn_mapped + 7) / 8);
+        bm = vzalloc((max_pfn_mapped + 7) / 8);
         if (!bm) {
                 printk(KERN_ERR "CPA Cannot vmalloc bitmap\n");
                 return -ENOMEM;
         }
-        memset(bm, 0, (max_pfn_mapped + 7) / 8);
 
         failed += print_split(&sa);
         srandom32(100);