9 files changed, 102 insertions, 58 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 2977ea37791f..dfb932dcf136 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,7 +1,6 @@
 obj-y   :=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-            pat.o pgtable.o
+            pat.o pgtable.o gup.o
 
-obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o
 obj-$(CONFIG_X86_32)            += pgtable_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)      += hugetlbpage.o
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 129618ca0ea2..d3746efb060d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -60,7 +60,7 @@ static unsigned long dma_reserve __initdata;
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
-int direct_gbpages __meminitdata
+int direct_gbpages
 #ifdef CONFIG_DIRECT_GBPAGES
                                 = 1
 #endif
@@ -88,7 +88,11 @@ early_param("gbpages", parse_direct_gbpages_on);
 
 int after_bootmem;
 
-static __init void *spp_getpage(void)
+/*
+ * NOTE: This function is marked __ref because it calls __init function
+ * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
+ */
+static __ref void *spp_getpage(void)
 {
         void *ptr;
 
@@ -237,7 +241,7 @@ static unsigned long __initdata table_start;
 static unsigned long __meminitdata table_end;
 static unsigned long __meminitdata table_top;
 
-static __meminit void *alloc_low_page(unsigned long *phys)
+static __ref void *alloc_low_page(unsigned long *phys)
 {
         unsigned long pfn = table_end++;
         void *adr;
@@ -258,7 +262,7 @@ static __meminit void *alloc_low_page(unsigned long *phys)
         return adr;
 }
 
-static __meminit void unmap_low_page(void *adr)
+static __ref void unmap_low_page(void *adr)
 {
         if (after_bootmem)
                 return;
@@ -314,6 +318,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
 {
         unsigned long pages = 0;
         unsigned long last_map_addr = end;
+        unsigned long start = address;
 
         int i = pmd_index(address);
 
@@ -331,16 +336,24 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                 }
 
                 if (pmd_val(*pmd)) {
-                        if (!pmd_large(*pmd))
+                        if (!pmd_large(*pmd)) {
+                                spin_lock(&init_mm.page_table_lock);
                                 last_map_addr = phys_pte_update(pmd, address,
-                                                                 end);
+                                                                end);
+                                spin_unlock(&init_mm.page_table_lock);
+                        }
+                        /* Count entries we're using from level2_ident_pgt */
+                        if (start == 0)
+                                pages++;
                         continue;
                 }
 
                 if (page_size_mask & (1<<PG_LEVEL_2M)) {
                         pages++;
+                        spin_lock(&init_mm.page_table_lock);
                         set_pte((pte_t *)pmd,
                                 pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+                        spin_unlock(&init_mm.page_table_lock);
                         last_map_addr = (address & PMD_MASK) + PMD_SIZE;
                         continue;
                 }
@@ -349,7 +362,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
                 last_map_addr = phys_pte_init(pte, address, end);
                 unmap_low_page(pte);
 
+                spin_lock(&init_mm.page_table_lock);
                 pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
+                spin_unlock(&init_mm.page_table_lock);
         }
         update_page_count(PG_LEVEL_2M, pages);
         return last_map_addr;
@@ -362,9 +377,7 @@ phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
         pmd_t *pmd = pmd_offset(pud, 0);
         unsigned long last_map_addr;
 
-        spin_lock(&init_mm.page_table_lock);
         last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask);
-        spin_unlock(&init_mm.page_table_lock);
         __flush_tlb_all();
         return last_map_addr;
 }
@@ -400,20 +413,21 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
 
                 if (page_size_mask & (1<<PG_LEVEL_1G)) {
                         pages++;
+                        spin_lock(&init_mm.page_table_lock);
                         set_pte((pte_t *)pud,
                                 pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
+                        spin_unlock(&init_mm.page_table_lock);
                         last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
                         continue;
                 }
 
                 pmd = alloc_low_page(&pmd_phys);
-
-                spin_lock(&init_mm.page_table_lock);
                 last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask);
                 unmap_low_page(pmd);
+
+                spin_lock(&init_mm.page_table_lock);
                 pud_populate(&init_mm, pud, __va(pmd_phys));
                 spin_unlock(&init_mm.page_table_lock);
-
         }
         __flush_tlb_all();
         update_page_count(PG_LEVEL_1G, pages);
@@ -505,16 +519,14 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start,
                         continue;
                 }
 
-                if (after_bootmem)
-                        pud = pud_offset(pgd, start & PGDIR_MASK);
-                else
-                        pud = alloc_low_page(&pud_phys);
-
+                pud = alloc_low_page(&pud_phys);
                 last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
                                                  page_size_mask);
                 unmap_low_page(pud);
-                pgd_populate(&init_mm, pgd_offset_k(start),
-                             __va(pud_phys));
+
+                spin_lock(&init_mm.page_table_lock);
+                pgd_populate(&init_mm, pgd, __va(pud_phys));
+                spin_unlock(&init_mm.page_table_lock);
         }
 
         return last_map_addr;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 016f335bbeea..d4b6e6a29ae3 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -170,7 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
         phys_addr &= PAGE_MASK;
         size = PAGE_ALIGN(last_addr+1) - phys_addr;
 
-        retval = reserve_memtype(phys_addr, phys_addr + size,
+        retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
                                                 prot_val, &new_prot_val);
         if (retval) {
                 pr_debug("Warning: reserve_memtype returned %d\n", retval);
@@ -553,13 +553,11 @@ static int __init check_early_ioremap_leak(void)
 {
         if (!early_ioremap_nested)
                 return 0;
-
-        printk(KERN_WARNING
+        WARN(1, KERN_WARNING
                "Debug warning: early ioremap leak of %d areas detected.\n",
-               early_ioremap_nested);
+                early_ioremap_nested);
         printk(KERN_WARNING
-               "please boot with early_ioremap_debug and report the dmesg.\n");
-        WARN_ON(1);
+                "please boot with early_ioremap_debug and report the dmesg.\n");
 
         return 1;
 }
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index e7397e108beb..635b50e85581 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -430,7 +430,9 @@ static void enter_uniprocessor(void)
                                                 "may miss events.\n");
 }
 
-static void leave_uniprocessor(void)
+/* __ref because leave_uniprocessor calls cpu_up which is __cpuinit,
+   but this whole function is ifdefed CONFIG_HOTPLUG_CPU */
+static void __ref leave_uniprocessor(void)
 {
         int cpu;
         int err;
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index 0dcd42eb94e6..d4aa503caaa2 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -221,8 +221,7 @@ static int pageattr_test(void)
         failed += print_split(&sc);
 
         if (failed) {
-                printk(KERN_ERR "NOT PASSED. Please report.\n");
-                WARN_ON(1);
+                WARN(1, KERN_ERR "NOT PASSED. Please report.\n");
                 return -EINVAL;
         } else {
                 if (print)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 65c6e46bf059..43e2f8483e4f 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -55,13 +55,19 @@ static void split_page_count(int level)
 
 int arch_report_meminfo(char *page)
 {
-        int n = sprintf(page, "DirectMap4k:  %8lu\n"
-                        "DirectMap2M:  %8lu\n",
-                        direct_pages_count[PG_LEVEL_4K],
-                        direct_pages_count[PG_LEVEL_2M]);
+        int n = sprintf(page, "DirectMap4k:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_4K] << 2);
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+        n += sprintf(page + n, "DirectMap2M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 11);
+#else
+        n += sprintf(page + n, "DirectMap4M:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_2M] << 12);
+#endif
 #ifdef CONFIG_X86_64
-        n += sprintf(page + n, "DirectMap1G:  %8lu\n",
-                     direct_pages_count[PG_LEVEL_1G]);
+        if (direct_gbpages)
+                n += sprintf(page + n, "DirectMap1G:  %8lu kB\n",
+                        direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
         return n;
 }
@@ -592,10 +598,9 @@ repeat:
         if (!pte_val(old_pte)) {
                 if (!primary)
                         return 0;
-                printk(KERN_WARNING "CPA: called for zero pte. "
+                WARN(1, KERN_WARNING "CPA: called for zero pte. "
                        "vaddr = %lx cpa->vaddr = %lx\n", address,
                        cpa->vaddr);
-                WARN_ON(1);
                 return -EINVAL;
         }
 
@@ -844,7 +849,7 @@ int set_memory_uc(unsigned long addr, int numpages)
         /*
          * for now UC MINUS. see comments in ioremap_nocache()
          */
-        if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+        if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
                             _PAGE_CACHE_UC_MINUS, NULL))
                 return -EINVAL;
 
@@ -863,7 +868,7 @@ int set_memory_wc(unsigned long addr, int numpages)
         if (!pat_enabled)
                 return set_memory_uc(addr, numpages);
 
-        if (reserve_memtype(addr, addr + numpages * PAGE_SIZE,
+        if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
                 _PAGE_CACHE_WC, NULL))
                 return -EINVAL;
 
@@ -879,7 +884,7 @@ int _set_memory_wb(unsigned long addr, int numpages)
 
 int set_memory_wb(unsigned long addr, int numpages)
 {
-        free_memtype(addr, addr + numpages * PAGE_SIZE);
+        free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
 
         return _set_memory_wb(addr, numpages);
 }
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 2fe30916d4b6..2a50e0fa64a5 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -207,6 +207,9 @@ static int chk_conflict(struct memtype *new, struct memtype *entry,
         return -EBUSY;
 }
 
+static struct memtype *cached_entry;
+static u64 cached_start;
+
 /*
  * req_type typically has one of the:
  * - _PAGE_CACHE_WB
@@ -280,11 +283,17 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
         spin_lock(&memtype_lock);
 
+        if (cached_entry && start >= cached_start)
+                entry = cached_entry;
+        else
+                entry = list_entry(&memtype_list, struct memtype, nd);
+
         /* Search for existing mapping that overlaps the current range */
         where = NULL;
-        list_for_each_entry(entry, &memtype_list, nd) {
+        list_for_each_entry_continue(entry, &memtype_list, nd) {
                 if (end <= entry->start) {
                         where = entry->nd.prev;
+                        cached_entry = list_entry(where, struct memtype, nd);
                         break;
                 } else if (start <= entry->start) { /* end > entry->start */
                         err = chk_conflict(new, entry, new_type);
@@ -292,6 +301,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
                                 dprintk("Overlap at 0x%Lx-0x%Lx\n",
                                         entry->start, entry->end);
                                 where = entry->nd.prev;
+                                cached_entry = list_entry(where,
+                                                        struct memtype, nd);
                         }
                         break;
                 } else if (start < entry->end) { /* start > entry->start */
@@ -299,7 +310,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
                         if (!err) {
                                 dprintk("Overlap at 0x%Lx-0x%Lx\n",
                                         entry->start, entry->end);
-                                where = &entry->nd;
+                                cached_entry = list_entry(entry->nd.prev,
+                                                        struct memtype, nd);
+
+                                /*
+                                 * Move to right position in the linked
+                                 * list to add this new entry
+                                 */
+                                list_for_each_entry_continue(entry,
+                                                        &memtype_list, nd) {
+                                        if (start <= entry->start) {
+                                                where = entry->nd.prev;
+                                                break;
+                                        }
+                                }
                         }
                         break;
                 }
@@ -314,6 +338,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
                 return err;
         }
 
+        cached_start = start;
+
         if (where)
                 list_add(&new->nd, where);
         else
@@ -343,6 +369,9 @@ int free_memtype(u64 start, u64 end)
         spin_lock(&memtype_lock);
         list_for_each_entry(entry, &memtype_list, nd) {
                 if (entry->start == start && entry->end == end) {
+                        if (cached_entry == entry || cached_start == start)
+                                cached_entry = NULL;
+
                         list_del(&entry->nd);
                         kfree(entry);
                         err = 0;
@@ -361,14 +390,6 @@ int free_memtype(u64 start, u64 end)
 }
 
 
-/*
- * /dev/mem mmap interface. The memtype used for mapping varies:
- * - Use UC for mappings with O_SYNC flag
- * - Without O_SYNC flag, if there is any conflict in reserve_memtype,
- *   inherit the memtype from existing mapping.
- * - Else use UC_MINUS memtype (for backward compatibility with existing
- *   X drivers.
- */
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
                                 unsigned long size, pgprot_t vma_prot)
 {
@@ -406,14 +427,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                                 unsigned long size, pgprot_t *vma_prot)
 {
         u64 offset = ((u64) pfn) << PAGE_SHIFT;
-        unsigned long flags = _PAGE_CACHE_UC_MINUS;
+        unsigned long flags = -1;
         int retval;
 
         if (!range_is_allowed(pfn, size))
                 return 0;
 
         if (file->f_flags & O_SYNC) {
-                flags = _PAGE_CACHE_UC;
+                flags = _PAGE_CACHE_UC_MINUS;
         }
 
 #ifdef CONFIG_X86_32
@@ -436,13 +457,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 #endif
 
         /*
-         * With O_SYNC, we can only take UC mapping. Fail if we cannot.
+         * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot.
+         *
          * Without O_SYNC, we want to get
          * - WB for WB-able memory and no other conflicting mappings
          * - UC_MINUS for non-WB-able memory with no other conflicting mappings
          * - Inherit from confliting mappings otherwise
          */
-        if (flags != _PAGE_CACHE_UC_MINUS) {
+        if (flags != -1) {
                 retval = reserve_memtype(offset, offset + size, flags, NULL);
         } else {
                 retval = reserve_memtype(offset, offset + size, -1, &flags);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 557b2abceef8..d50302774fe2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -207,6 +207,9 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
         unsigned long addr;
         int i;
 
+        if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
+                return;
+
         pud = pud_offset(pgd, 0);
 
         for (addr = i = 0; i < PREALLOCATED_PMDS;
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 1eb2973a301c..16ae70fc57e7 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -178,7 +178,7 @@ void acpi_numa_arch_fixup(void)
  * start of the node, and that the current "end" address is after
  * the previous one.
  */
-static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
+static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk)
 {
         /*
          * Only add present memory as told by the e820.
@@ -189,10 +189,10 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
         if (memory_chunk->start_pfn >= max_pfn) {
                 printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n",
                         memory_chunk->start_pfn, memory_chunk->end_pfn);
-                return;
+                return -1;
         }
         if (memory_chunk->nid != nid)
-                return;
+                return -1;
 
         if (!node_has_online_mem(nid))
                 node_start_pfn[nid] = memory_chunk->start_pfn;
@@ -202,6 +202,8 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c
 
         if (node_end_pfn[nid] < memory_chunk->end_pfn)
                 node_end_pfn[nid] = memory_chunk->end_pfn;
+
+        return 0;
 }
 
 int __init get_memcfg_from_srat(void)
@@ -259,7 +261,9 @@ int __init get_memcfg_from_srat(void)
                 printk(KERN_DEBUG
                         "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n",
                        j, chunk->nid, chunk->start_pfn, chunk->end_pfn);
-                node_read_chunk(chunk->nid, chunk);
+                if (node_read_chunk(chunk->nid, chunk))
+                        continue;
+
                 e820_register_active_regions(chunk->nid, chunk->start_pfn,
                                              min(chunk->end_pfn, max_pfn));
         }