Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:
 "Almost all of the rest of MM.  There was an unusually large amount of
  MM material this time"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (141 commits)
  zpool: remove no-op module init/exit
  mm: zbud: constify the zbud_ops
  mm: zpool: constify the zpool_ops
  mm: swap: zswap: maybe_preload & refactoring
  zram: unify error reporting
  zsmalloc: remove null check from destroy_handle_cache()
  zsmalloc: do not take class lock in zs_shrinker_count()
  zsmalloc: use class->pages_per_zspage
  zsmalloc: consider ZS_ALMOST_FULL as migrate source
  zsmalloc: partial page ordering within a fullness_list
  zsmalloc: use shrinker to trigger auto-compaction
  zsmalloc: account the number of compacted pages
  zsmalloc/zram: introduce zs_pool_stats api
  zsmalloc: cosmetic compaction code adjustments
  zsmalloc: introduce zs_can_compact() function
  zsmalloc: always keep per-class stats
  zsmalloc: drop unused variable `nr_to_migrate'
  mm/memblock.c: fix comment in __next_mem_range()
  mm/page_alloc.c: fix type information of memoryless node
  memory-hotplug: fix comments in zone_spanned_pages_in_node() and zone_spanned_pages_in_node()
  ...

9 files changed, 73 insertions, 33 deletions

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 8884788..6bab21f 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -339,6 +339,67 @@ static void __init request_standard_resources(void)
 	}
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+/*
+ * Relocate initrd if it is not completely within the linear mapping.
+ * This would be the case if mem= cuts out all or part of it.
+ */
+static void __init relocate_initrd(void)
+{
+	phys_addr_t orig_start = __virt_to_phys(initrd_start);
+	phys_addr_t orig_end = __virt_to_phys(initrd_end);
+	phys_addr_t ram_end = memblock_end_of_DRAM();
+	phys_addr_t new_start;
+	unsigned long size, to_free = 0;
+	void *dest;
+
+	if (orig_end <= ram_end)
+		return;
+
+	/*
+	 * Any of the original initrd which overlaps the linear map should
+	 * be freed after relocating.
+	 */
+	if (orig_start < ram_end)
+		to_free = ram_end - orig_start;
+
+	size = orig_end - orig_start;
+
+	/* initrd needs to be relocated completely inside linear mapping */
+	new_start = memblock_find_in_range(0, PFN_PHYS(max_pfn),
+					   size, PAGE_SIZE);
+	if (!new_start)
+		panic("Cannot relocate initrd of size %ld\n", size);
+	memblock_reserve(new_start, size);
+
+	initrd_start = __phys_to_virt(new_start);
+	initrd_end   = initrd_start + size;
+
+	pr_info("Moving initrd from [%llx-%llx] to [%llx-%llx]\n",
+		orig_start, orig_start + size - 1,
+		new_start, new_start + size - 1);
+
+	dest = (void *)initrd_start;
+
+	if (to_free) {
+		memcpy(dest, (void *)__phys_to_virt(orig_start), to_free);
+		dest += to_free;
+	}
+
+	copy_from_early_mem(dest, orig_start + to_free, size - to_free);
+
+	if (to_free) {
+		pr_info("Freeing original RAMDISK from [%llx-%llx]\n",
+			orig_start, orig_start + to_free - 1);
+		memblock_free(orig_start, to_free);
+	}
+}
+#else
+static inline void __init relocate_initrd(void)
+{
+}
+#endif
+
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
@@ -372,6 +433,7 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_table_init();
 
 	paging_init();
+	relocate_initrd();
 	request_standard_resources();
 
 	early_ioremap_reset();
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 344387a..a6d6190 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1140,13 +1140,9 @@ sba_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 
 #ifdef CONFIG_NUMA
 	{
-		int node = ioc->node;
 		struct page *page;
 
-		if (node == NUMA_NO_NODE)
-			node = numa_node_id();
-
-		page = alloc_pages_exact_node(node, flags, get_order(size));
+		page = alloc_pages_node(ioc->node, flags, get_order(size));
 		if (unlikely(!page))
 			return NULL;
 
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 20e8a9b..f3976da 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -97,7 +97,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
 
 	/* attempt to allocate a granule's worth of cached memory pages */
 
-	page = alloc_pages_exact_node(nid,
+	page = __alloc_pages_node(nid,
 				GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
 				IA64_GRANULE_SHIFT-PAGE_SHIFT);
 	if (!page) {
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index d0853e8..8f59907 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -92,7 +92,7 @@ static void *sn_dma_alloc_coherent(struct device *dev, size_t size,
 	 */
 	node = pcibus_to_node(pdev->bus);
 	if (likely(node >=0)) {
-		struct page *p = alloc_pages_exact_node(node,
+		struct page *p = __alloc_pages_node(node,
 						flags, get_order(size));
 
 		if (likely(p))
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index e865d74..2d4f60c 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,7 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
 
 	area->nid = nid;
 	area->order = order;
-	area->pages = alloc_pages_exact_node(area->nid,
+	area->pages = __alloc_pages_node(area->nid,
 						GFP_KERNEL|__GFP_THISNODE,
 						area->order);
 
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index f06b36a..91b963a 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -14,7 +14,7 @@
 #include <asm-generic/4level-fixup.h>
 
 #include <linux/spinlock.h>
-#include <linux/swap.h>
+#include <linux/mm_types.h>
 #include <asm/types.h>
 #include <asm/pgtsrmmu.h>
 #include <asm/vaddrs.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b143c2d..baadbf9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -317,15 +317,12 @@ static u64 __init get_ramdisk_size(void)
 	return ramdisk_size;
 }
 
-#define MAX_MAP_CHUNK	(NR_FIX_BTMAPS << PAGE_SHIFT)
 static void __init relocate_initrd(void)
 {
 	/* Assume only end is not page aligned */
 	u64 ramdisk_image = get_ramdisk_image();
 	u64 ramdisk_size  = get_ramdisk_size();
 	u64 area_size     = PAGE_ALIGN(ramdisk_size);
-	unsigned long slop, clen, mapaddr;
-	char *p, *q;
 
 	/* We need to move the initrd down into directly mapped mem */
 	relocated_ramdisk = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
@@ -343,25 +340,8 @@ static void __init relocate_initrd(void)
 	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
 	       relocated_ramdisk, relocated_ramdisk + ramdisk_size - 1);
 
-	q = (char *)initrd_start;
-
-	/* Copy the initrd */
-	while (ramdisk_size) {
-		slop = ramdisk_image & ~PAGE_MASK;
-		clen = ramdisk_size;
-		if (clen > MAX_MAP_CHUNK-slop)
-			clen = MAX_MAP_CHUNK-slop;
-		mapaddr = ramdisk_image & PAGE_MASK;
-		p = early_memremap(mapaddr, clen+slop);
-		memcpy(q, p+slop, clen);
-		early_memunmap(p, clen+slop);
-		q += clen;
-		ramdisk_image += clen;
-		ramdisk_size  -= clen;
-	}
+	copy_from_early_mem((void *)initrd_start, ramdisk_image, ramdisk_size);
 
-	ramdisk_image = get_ramdisk_image();
-	ramdisk_size  = get_ramdisk_size();
 	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
 		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4a4eec30..148ea20 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3150,7 +3150,7 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 	struct page *pages;
 	struct vmcs *vmcs;
 
-	pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order);
+	pages = __alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
 	if (!pages)
 		return NULL;
 	vmcs = page_address(pages);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 4053bb5..c3b3f65 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -246,8 +246,10 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 		bi->start = max(bi->start, low);
 		bi->end = min(bi->end, high);
 
-		/* and there's no empty block */
-		if (bi->start >= bi->end)
+		/* and there's no empty or non-exist block */
+		if (bi->start >= bi->end ||
+		    !memblock_overlaps_region(&memblock.memory,
+			bi->start, bi->end - bi->start))
 			numa_remove_memblk_from(i--, mi);
 	}