Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, mm: Unify kernel_physical_mapping_init() API
  x86, mm: Allow highmem user page tables to be disabled at boot time
  x86: Do not reserve brk for DMI if it's not going to be used
  x86: Convert tlbstate_lock to raw_spinlock
  x86: Use the generic page_is_ram()
  x86: Remove BIOS data range from e820
  Move page_is_ram() declaration to mm.h
  Generic page_is_ram: use __weak
  resources: introduce generic page_is_ram()

5 files changed, 35 insertions, 56 deletions

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d406c52..e71c5cb 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -266,16 +266,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	if (!after_bootmem)
 		find_early_table_space(end, use_pse, use_gbpages);
 
-#ifdef CONFIG_X86_32
-	for (i = 0; i < nr_range; i++)
-		kernel_physical_mapping_init(mr[i].start, mr[i].end,
-					     mr[i].page_size_mask);
-	ret = end;
-#else /* CONFIG_X86_64 */
 	for (i = 0; i < nr_range; i++)
 		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
 						   mr[i].page_size_mask);
-#endif
 
 #ifdef CONFIG_X86_32
 	early_ioremap_page_table_range_init();
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 9a0c258..2226f2c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -241,6 +241,7 @@ kernel_physical_mapping_init(unsigned long start,
 			     unsigned long page_size_mask)
 {
 	int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
+	unsigned long last_map_addr = end;
 	unsigned long start_pfn, end_pfn;
 	pgd_t *pgd_base = swapper_pg_dir;
 	int pgd_idx, pmd_idx, pte_ofs;
@@ -341,9 +342,10 @@ repeat:
 					prot = PAGE_KERNEL_EXEC;
 
 				pages_4k++;
-				if (mapping_iter == 1)
+				if (mapping_iter == 1) {
 					set_pte(pte, pfn_pte(pfn, init_prot));
-				else
+					last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
+				} else
 					set_pte(pte, pfn_pte(pfn, prot));
 			}
 		}
@@ -368,7 +370,7 @@ repeat:
 		mapping_iter = 2;
 		goto repeat;
 	}
-	return 0;
+	return last_map_addr;
 }
 
 pte_t *kmap_pte;
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 03c75ff..5eb1ba7 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -24,43 +24,6 @@
 
 #include "physaddr.h"
 
-int page_is_ram(unsigned long pagenr)
-{
-	resource_size_t addr, end;
-	int i;
-
-	/*
-	 * A special case is the first 4Kb of memory;
-	 * This is a BIOS owned area, not kernel ram, but generally
-	 * not listed as such in the E820 table.
-	 */
-	if (pagenr == 0)
-		return 0;
-
-	/*
-	 * Second special case: Some BIOSen report the PC BIOS
-	 * area (640->1Mb) as ram even though it is not.
-	 */
-	if (pagenr >= (BIOS_BEGIN >> PAGE_SHIFT) &&
-		    pagenr < (BIOS_END >> PAGE_SHIFT))
-		return 0;
-
-	for (i = 0; i < e820.nr_map; i++) {
-		/*
-		 * Not usable memory:
-		 */
-		if (e820.map[i].type != E820_RAM)
-			continue;
-		addr = (e820.map[i].addr + PAGE_SIZE-1) >> PAGE_SHIFT;
-		end = (e820.map[i].addr + e820.map[i].size) >> PAGE_SHIFT;
-
-
-		if ((pagenr >= addr) && (pagenr < end))
-			return 1;
-	}
-	return 0;
-}
-
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ed34f5e..c9ba9de 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -6,6 +6,14 @@
 
 #define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
 
+#ifdef CONFIG_HIGHPTE
+#define PGALLOC_USER_GFP __GFP_HIGHMEM
+#else
+#define PGALLOC_USER_GFP 0
+#endif
+
+gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
+
 pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	return (pte_t *)__get_free_page(PGALLOC_GFP);
@@ -15,16 +23,29 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
 	struct page *pte;
 
-#ifdef CONFIG_HIGHPTE
-	pte = alloc_pages(PGALLOC_GFP | __GFP_HIGHMEM, 0);
-#else
-	pte = alloc_pages(PGALLOC_GFP, 0);
-#endif
+	pte = alloc_pages(__userpte_alloc_gfp, 0);
 	if (pte)
 		pgtable_page_ctor(pte);
 	return pte;
 }
 
+static int __init setup_userpte(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	/*
+	 * "userpte=nohigh" disables allocation of user pagetables in
+	 * high memory.
+	 */
+	if (strcmp(arg, "nohigh") == 0)
+		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
+	else
+		return -EINVAL;
+	return 0;
+}
+early_param("userpte", setup_userpte);
+
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	pgtable_page_dtor(pte);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 65b58e4..426f3a1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -41,7 +41,7 @@ union smp_flush_state {
 	struct {
 		struct mm_struct *flush_mm;
 		unsigned long flush_va;
-		spinlock_t tlbstate_lock;
+		raw_spinlock_t tlbstate_lock;
 		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
 	};
 	char pad[INTERNODE_CACHE_BYTES];
@@ -181,7 +181,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
 	 * probably not worth checking this for a cache-hot lock.
 	 */
-	spin_lock(&f->tlbstate_lock);
+	raw_spin_lock(&f->tlbstate_lock);
 
 	f->flush_mm = mm;
 	f->flush_va = va;
@@ -199,7 +199,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask,
 
 	f->flush_mm = NULL;
 	f->flush_va = 0;
-	spin_unlock(&f->tlbstate_lock);
+	raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
@@ -223,7 +223,7 @@ static int __cpuinit init_smp_flush(void)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
-		spin_lock_init(&flush_state[i].tlbstate_lock);
+		raw_spin_lock_init(&flush_state[i].tlbstate_lock);
 
 	return 0;
 }