5 files changed, 85 insertions, 10 deletions

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index ec9eeb89975..b6bcc9fa360 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -519,6 +519,68 @@ void __cpuinit *per_cpu_init(void)
 }
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_VIRTUAL_MEM_MAP
+static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i)
+{
+	unsigned long end_address, hole_next_pfn;
+	unsigned long stop_address;
+
+	end_address = (unsigned long) &vmem_map[pgdat->node_start_pfn + i];
+	end_address = PAGE_ALIGN(end_address);
+
+	stop_address = (unsigned long) &vmem_map[
+		pgdat->node_start_pfn + pgdat->node_spanned_pages];
+
+	do {
+		pgd_t *pgd;
+		pud_t *pud;
+		pmd_t *pmd;
+		pte_t *pte;
+
+		pgd = pgd_offset_k(end_address);
+		if (pgd_none(*pgd)) {
+			end_address += PGDIR_SIZE;
+			continue;
+		}
+
+		pud = pud_offset(pgd, end_address);
+		if (pud_none(*pud)) {
+			end_address += PUD_SIZE;
+			continue;
+		}
+
+		pmd = pmd_offset(pud, end_address);
+		if (pmd_none(*pmd)) {
+			end_address += PMD_SIZE;
+			continue;
+		}
+
+		pte = pte_offset_kernel(pmd, end_address);
+retry_pte:
+		if (pte_none(*pte)) {
+			end_address += PAGE_SIZE;
+			pte++;
+			if ((end_address < stop_address) &&
+			    (end_address != ALIGN(end_address, 1UL << PMD_SHIFT)))
+				goto retry_pte;
+			continue;
+		}
+		/* Found next valid vmem_map page */
+		break;
+	} while (end_address < stop_address);
+
+	end_address = min(end_address, stop_address);
+	end_address = end_address - (unsigned long) vmem_map + sizeof(struct page) - 1;
+	hole_next_pfn = end_address / sizeof(struct page);
+	return hole_next_pfn - pgdat->node_start_pfn;
+}
+#else
+static inline int find_next_valid_pfn_for_pgdat(pg_data_t *pgdat, int i)
+{
+	return i + 1;
+}
+#endif
+
 /**
  * show_mem - give short summary of memory stats
  *
@@ -547,8 +609,10 @@ void show_mem(void)
 			struct page *page;
 			if (pfn_valid(pgdat->node_start_pfn + i))
 				page = pfn_to_page(pgdat->node_start_pfn + i);
-			else
+			else {
+				i = find_next_valid_pfn_for_pgdat(pgdat, i) - 1;
 				continue;
+			}
 			if (PageReserved(page))
 				reserved++;
 			else if (PageSwapCache(page))
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index af7eb087dca..d98ec49570b 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -60,6 +60,9 @@ ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *re
 	struct siginfo si;
 	unsigned long mask;
 
+	/* mmap_sem is performance critical.... */
+	prefetchw(&mm->mmap_sem);
+
 	/*
 	 * If we're in an interrupt or have no user context, we must not take the fault..
 	 */
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 2ef1151cde9..cafa8776a53 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -109,6 +109,7 @@ lazy_mmu_prot_update (pte_t pte)
 {
 	unsigned long addr;
 	struct page *page;
+	unsigned long order;
 
 	if (!pte_exec(pte))
 		return;				/* not an executable page... */
@@ -119,7 +120,12 @@ lazy_mmu_prot_update (pte_t pte)
 	if (test_bit(PG_arch_1, &page->flags))
 		return;				/* i-cache is already coherent with d-cache */
 
-	flush_icache_range(addr, addr + PAGE_SIZE);
+	if (PageCompound(page)) {
+		order = (unsigned long) (page[1].lru.prev);
+		flush_icache_range(addr, addr + (1UL << order << PAGE_SHIFT));
+	}
+	else
+		flush_icache_range(addr, addr + PAGE_SIZE);
 	set_bit(PG_arch_1, &page->flags);	/* mark page as clean */
 }
 
diff --git a/arch/ia64/mm/ioremap.c b/arch/ia64/mm/ioremap.c
index 62328621f99..643ccc6960c 100644
--- a/arch/ia64/mm/ioremap.c
+++ b/arch/ia64/mm/ioremap.c
@@ -21,12 +21,12 @@ __ioremap (unsigned long offset, unsigned long size)
 void __iomem *
 ioremap (unsigned long offset, unsigned long size)
 {
-	if (efi_mem_attribute_range(offset, size, EFI_MEMORY_UC))
-		return __ioremap(offset, size);
-
 	if (efi_mem_attribute_range(offset, size, EFI_MEMORY_WB))
 		return phys_to_virt(offset);
 
+	if (efi_mem_attribute_range(offset, size, EFI_MEMORY_UC))
+		return __ioremap(offset, size);
+
 	/*
 	 * Someday this should check ACPI resources so we
 	 * can do the right thing for hot-plugged regions.
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 6a4eec9113e..4dbbca0b5e9 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -156,17 +156,19 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 		nbits = purge.max_bits;
 	start &= ~((1UL << nbits) - 1);
 
-# ifdef CONFIG_SMP
-	platform_global_tlb_purge(mm, start, end, nbits);
-# else
 	preempt_disable();
+#ifdef CONFIG_SMP
+	if (mm != current->active_mm || cpus_weight(mm->cpu_vm_mask) != 1) {
+		platform_global_tlb_purge(mm, start, end, nbits);
+		preempt_enable();
+		return;
+	}
+#endif
 	do {
 		ia64_ptcl(start, (nbits<<2));
 		start += (1UL << nbits);
 	} while (start < end);
 	preempt_enable();
-# endif
-
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
 EXPORT_SYMBOL(flush_tlb_range);