3 files changed, 28 insertions, 18 deletions

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index f6679a7fb8ca..b91e48512425 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -56,9 +56,16 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
 }
 
 /*
- * search for a shareable pmd page for hugetlb.
+ * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
+ * and returns the corresponding pte. While this is not necessary for the
+ * !shared pmd case because we can allocate the pmd later as well, it makes the
+ * code much cleaner. pmd allocation is essential for the shared case because
+ * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * racing tasks could either miss the sharing (see huge_pte_offset) or select a
+ * bad pmd for sharing.
  */
-static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+static pte_t *
+huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 {
         struct vm_area_struct *vma = find_vma(mm, addr);
         struct address_space *mapping = vma->vm_file->f_mapping;
@@ -68,9 +75,10 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
         struct vm_area_struct *svma;
         unsigned long saddr;
         pte_t *spte = NULL;
+        pte_t *pte;
 
         if (!vma_shareable(vma, addr))
-                return;
+                return (pte_t *)pmd_alloc(mm, pud, addr);
 
         mutex_lock(&mapping->i_mmap_mutex);
         vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
@@ -97,7 +105,9 @@ static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
                 put_page(virt_to_page(spte));
         spin_unlock(&mm->page_table_lock);
 out:
+        pte = (pte_t *)pmd_alloc(mm, pud, addr);
         mutex_unlock(&mapping->i_mmap_mutex);
+        return pte;
 }
 
 /*
@@ -142,8 +152,9 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
                 } else {
                         BUG_ON(sz != PMD_SIZE);
                         if (pud_none(*pud))
-                                huge_pmd_share(mm, addr, pud);
-                        pte = (pte_t *) pmd_alloc(mm, pud, addr);
+                                pte = huge_pmd_share(mm, addr, pud);
+                        else
+                                pte = (pte_t *)pmd_alloc(mm, pud, addr);
                 }
         }
         BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 931930a96160..a718e0d23503 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
         /*
          * On success we use clflush, when the CPU supports it to
-         * avoid the wbindv. If the CPU does not support it, in the
-         * error case, and during early boot (for EFI) we fall back
-         * to cpa_flush_all (which uses wbinvd):
+         * avoid the wbindv. If the CPU does not support it and in the
+         * error case we fall back to cpa_flush_all (which uses
+         * wbindv):
          */
-        if (early_boot_irqs_disabled)
-                __cpa_flush_all((void *)(long)cache);
-        else if (!ret && cpu_has_clflush) {
+        if (!ret && cpu_has_clflush) {
                 if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
                         cpa_flush_array(addr, numpages, cache,
                                         cpa.flags, pages);
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 4599c3e8bcb6..4ddf497ca65b 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -142,23 +142,23 @@ static inline int save_add_info(void) {return 0;}
 #endif
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */
-void __init
+int __init
 acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 {
         u64 start, end;
         int node, pxm;
 
         if (srat_disabled())
-                return;
+                return -1;
         if (ma->header.length != sizeof(struct acpi_srat_mem_affinity)) {
                 bad_srat();
-                return;
+                return -1;
         }
         if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
-                return;
+                return -1;
 
         if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
-                return;
+                return -1;
         start = ma->base_address;
         end = start + ma->length;
         pxm = ma->proximity_domain;
@@ -168,12 +168,12 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
         if (node < 0) {
                 printk(KERN_ERR "SRAT: Too many proximity domains.\n");
                 bad_srat();
-                return;
+                return -1;
         }
 
         if (numa_add_memblk(node, start, end) < 0) {
                 bad_srat();
-                return;
+                return -1;
         }
 
         node_set(node, numa_nodes_parsed);
@@ -181,6 +181,7 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
         printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
                node, pxm,
                (unsigned long long) start, (unsigned long long) end - 1);
+        return 0;
 }
 
 void __init acpi_numa_arch_fixup(void) {}