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 <[email protected]>: (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()
  ...

Documentation/DMA-API.txt

@@ -104,6 +104,13 @@ crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated
 from this pool must not cross 4KByte boundaries.
 
 
+	void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
+			      dma_addr_t *handle)
+
+Wraps dma_pool_alloc() and also zeroes the returned memory if the
+allocation attempt succeeded.
+
+
 	void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags,
 			dma_addr_t *dma_handle);
 

Documentation/blockdev/zram.txt

@@ -144,7 +144,8 @@ mem_used_max      RW    the maximum amount memory zram have consumed to
                         store compressed data
 mem_limit         RW    the maximum amount of memory ZRAM can use to store
                         the compressed data
-num_migrated      RO    the number of objects migrated migrated by compaction
+pages_compacted   RO    the number of pages freed during compaction
+                        (available only via zram<id>/mm_stat node)
 compact           WO    trigger memory compaction
 
 WARNING

Documentation/filesystems/dax.txt

@@ -60,9 +60,10 @@ Filesystem support consists of
 - implementing the direct_IO address space operation, and calling
   dax_do_io() instead of blockdev_direct_IO() if S_DAX is set
 - implementing an mmap file operation for DAX files which sets the
-  VM_MIXEDMAP flag on the VMA, and setting the vm_ops to include handlers
-  for fault and page_mkwrite (which should probably call dax_fault() and
-  dax_mkwrite(), passing the appropriate get_block() callback)
+  VM_MIXEDMAP and VM_HUGEPAGE flags on the VMA, and setting the vm_ops to
+  include handlers for fault, pmd_fault and page_mkwrite (which should
+  probably call dax_fault(), dax_pmd_fault() and dax_mkwrite(), passing the
+  appropriate get_block() callback)
 - calling dax_truncate_page() instead of block_truncate_page() for DAX files
 - calling dax_zero_page_range() instead of zero_user() for DAX files
 - ensuring that there is sufficient locking between reads, writes,

Documentation/filesystems/proc.txt

@@ -424,6 +424,7 @@ Private_Dirty:         0 kB
 Referenced:          892 kB
 Anonymous:             0 kB
 Swap:                  0 kB
+SwapPss:               0 kB
 KernelPageSize:        4 kB
 MMUPageSize:           4 kB
 Locked:              374 kB
@@ -433,16 +434,23 @@ the first of these lines shows the same information as is displayed for the
 mapping in /proc/PID/maps.  The remaining lines show the size of the mapping
 (size), the amount of the mapping that is currently resident in RAM (RSS), the
 process' proportional share of this mapping (PSS), the number of clean and
-dirty private pages in the mapping.  Note that even a page which is part of a
-MAP_SHARED mapping, but has only a single pte mapped, i.e.  is currently used
-by only one process, is accounted as private and not as shared.  "Referenced"
-indicates the amount of memory currently marked as referenced or accessed.
+dirty private pages in the mapping.
+
+The "proportional set size" (PSS) of a process is the count of pages it has
+in memory, where each page is divided by the number of processes sharing it.
+So if a process has 1000 pages all to itself, and 1000 shared with one other
+process, its PSS will be 1500.
+Note that even a page which is part of a MAP_SHARED mapping, but has only
+a single pte mapped, i.e.  is currently used by only one process, is accounted
+as private and not as shared.
+"Referenced" indicates the amount of memory currently marked as referenced or
+accessed.
 "Anonymous" shows the amount of memory that does not belong to any file.  Even
 a mapping associated with a file may contain anonymous pages: when MAP_PRIVATE
 and a page is modified, the file page is replaced by a private anonymous copy.
 "Swap" shows how much would-be-anonymous memory is also used, but out on
 swap.
-
+"SwapPss" shows proportional swap share of this mapping.
 "VmFlags" field deserves a separate description. This member represents the kernel
 flags associated with the particular virtual memory area in two letter encoded
 manner. The codes are the following:

Documentation/sysctl/vm.txt

@@ -349,7 +349,7 @@ zone[i]'s protection[j] is calculated by following expression.
 
 (i < j):
   zone[i]->protection[j]
-  = (total sums of present_pages from zone[i+1] to zone[j] on the node)
+  = (total sums of managed_pages from zone[i+1] to zone[j] on the node)
     / lowmem_reserve_ratio[i];
 (i = j):
    (should not be protected. = 0;
@@ -360,7 +360,7 @@ The default values of lowmem_reserve_ratio[i] are
     256 (if zone[i] means DMA or DMA32 zone)
     32  (others).
 As above expression, they are reciprocal number of ratio.
-256 means 1/256. # of protection pages becomes about "0.39%" of total present
+256 means 1/256. # of protection pages becomes about "0.39%" of total managed
 pages of higher zones on the node.
 
 If you would like to protect more pages, smaller values are effective.

Documentation/sysrq.txt

@@ -75,7 +75,8 @@ On all -  write a character to /proc/sysrq-trigger.  e.g.:
 
 'e'     - Send a SIGTERM to all processes, except for init.
 
-'f'	- Will call oom_kill to kill a memory hog process.
+'f'	- Will call the oom killer to kill a memory hog process, but do not
+	  panic if nothing can be killed.
 
 'g'	- Used by kgdb (kernel debugger)
 

Documentation/vm/hugetlbpage.txt

@@ -329,7 +329,14 @@ Examples
 
 3) hugepage-mmap:  see tools/testing/selftests/vm/hugepage-mmap.c
 
-4) The libhugetlbfs (http://libhugetlbfs.sourceforge.net) library provides a
-   wide range of userspace tools to help with huge page usability, environment
-   setup, and control. Furthermore it provides useful test cases that should be
-   used when modifying code to ensure no regressions are introduced.
+4) The libhugetlbfs (https://github.com/libhugetlbfs/libhugetlbfs) library
+   provides a wide range of userspace tools to help with huge page usability,
+   environment setup, and control.
+
+Kernel development regression testing
+=====================================
+
+The most complete set of hugetlb tests are in the libhugetlbfs repository.
+If you modify any hugetlb related code, use the libhugetlbfs test suite
+to check for regressions.  In addition, if you add any new hugetlb
+functionality, please add appropriate tests to libhugetlbfs.

Documentation/vm/pagemap.txt

@@ -16,11 +16,17 @@ There are three components to pagemap:
     * Bits 0-4   swap type if swapped
     * Bits 5-54  swap offset if swapped
     * Bit  55    pte is soft-dirty (see Documentation/vm/soft-dirty.txt)
-    * Bits 56-60 zero
-    * Bit  61    page is file-page or shared-anon
+    * Bit  56    page exclusively mapped (since 4.2)
+    * Bits 57-60 zero
+    * Bit  61    page is file-page or shared-anon (since 3.5)
     * Bit  62    page swapped
     * Bit  63    page present
 
+   Since Linux 4.0 only users with the CAP_SYS_ADMIN capability can get PFNs.
+   In 4.0 and 4.1 opens by unprivileged fail with -EPERM.  Starting from
+   4.2 the PFN field is zeroed if the user does not have CAP_SYS_ADMIN.
+   Reason: information about PFNs helps in exploiting Rowhammer vulnerability.
+
    If the page is not present but in swap, then the PFN contains an
    encoding of the swap file number and the page's offset into the
    swap. Unmapped pages return a null PFN. This allows determining
@@ -159,3 +165,8 @@ Other notes:
 Reading from any of the files will return -EINVAL if you are not starting
 the read on an 8-byte boundary (e.g., if you sought an odd number of bytes
 into the file), or if the size of the read is not a multiple of 8 bytes.
+
+Before Linux 3.11 pagemap bits 55-60 were used for "page-shift" (which is
+always 12 at most architectures). Since Linux 3.11 their meaning changes
+after first clear of soft-dirty bits. Since Linux 4.2 they are used for
+flags unconditionally.

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();

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;
 

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) {

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))

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);
 

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>

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,

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);

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);
 	}