Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - the v9fs maintainers have been missing for a long time. I've taken
   over v9fs patch slinging.

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (116 commits)
  mm,oom_reaper: check for MMF_OOM_SKIP before complaining
  mm/ksm: fix interaction with THP
  mm/memblock.c: cast constant ULLONG_MAX to phys_addr_t
  headers: untangle kmemleak.h from mm.h
  include/linux/mmdebug.h: make VM_WARN* non-rvals
  mm/page_isolation.c: make start_isolate_page_range() fail if already isolated
  mm: change return type to vm_fault_t
  mm, oom: remove 3% bonus for CAP_SYS_ADMIN processes
  mm, page_alloc: wakeup kcompactd even if kswapd cannot free more memory
  kernel/fork.c: detect early free of a live mm
  mm: make counting of list_lru_one::nr_items lockless
  mm/swap_state.c: make bool enable_vma_readahead and swap_vma_readahead() static
  block_invalidatepage(): only release page if the full page was invalidated
  mm: kernel-doc: add missing parameter descriptions
  mm/swap.c: remove @cold parameter description for release_pages()
  mm/nommu: remove description of alloc_vm_area
  zram: drop max_zpage_size and use zs_huge_class_size()
  zsmalloc: introduce zs_huge_class_size()
  mm: fix races between swapoff and flush dcache
  fs/direct-io.c: minor cleanups in do_blockdev_direct_IO
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -1840,30 +1840,29 @@
 	keepinitrd	[HW,ARM]
 
 	kernelcore=	[KNL,X86,IA-64,PPC]
-			Format: nn[KMGTPE] | "mirror"
-			This parameter
-			specifies the amount of memory usable by the kernel
-			for non-movable allocations.  The requested amount is
-			spread evenly throughout all nodes in the system. The
-			remaining memory in each node is used for Movable
-			pages. In the event, a node is too small to have both
-			kernelcore and Movable pages, kernelcore pages will
-			take priority and other nodes will have a larger number
-			of Movable pages.  The Movable zone is used for the
-			allocation of pages that may be reclaimed or moved
-			by the page migration subsystem.  This means that
-			HugeTLB pages may not be allocated from this zone.
-			Note that allocations like PTEs-from-HighMem still
-			use the HighMem zone if it exists, and the Normal
+			Format: nn[KMGTPE] | nn% | "mirror"
+			This parameter specifies the amount of memory usable by
+			the kernel for non-movable allocations.  The requested
+			amount is spread evenly throughout all nodes in the
+			system as ZONE_NORMAL.  The remaining memory is used for
+			movable memory in its own zone, ZONE_MOVABLE.  In the
+			event, a node is too small to have both ZONE_NORMAL and
+			ZONE_MOVABLE, kernelcore memory will take priority and
+			other nodes will have a larger ZONE_MOVABLE.
+
+			ZONE_MOVABLE is used for the allocation of pages that
+			may be reclaimed or moved by the page migration
+			subsystem.  Note that allocations like PTEs-from-HighMem
+			still use the HighMem zone if it exists, and the Normal
 			zone if it does not.
 
-			Instead of specifying the amount of memory (nn[KMGTPE]),
-			you can specify "mirror" option. In case "mirror"
+			It is possible to specify the exact amount of memory in
+			the form of "nn[KMGTPE]", a percentage of total system
+			memory in the form of "nn%", or "mirror".  If "mirror"
 			option is specified, mirrored (reliable) memory is used
 			for non-movable allocations and remaining memory is used
-			for Movable pages. nn[KMGTPE] and "mirror" are exclusive,
-			so you can NOT specify nn[KMGTPE] and "mirror" at the same
-			time.
+			for Movable pages.  "nn[KMGTPE]", "nn%", and "mirror"
+			are exclusive, so you cannot specify multiple forms.
 
 	kgdbdbgp=	[KGDB,HW] kgdb over EHCI usb debug port.
 			Format: <Controller#>[,poll interval]
@@ -2377,13 +2376,14 @@
 	mousedev.yres=	[MOUSE] Vertical screen resolution, used for devices
 			reporting absolute coordinates, such as tablets
 
-	movablecore=nn[KMG]	[KNL,X86,IA-64,PPC] This parameter
-			is similar to kernelcore except it specifies the
-			amount of memory used for migratable allocations.
-			If both kernelcore and movablecore is specified,
-			then kernelcore will be at *least* the specified
-			value but may be more. If movablecore on its own
-			is specified, the administrator must be careful
+	movablecore=	[KNL,X86,IA-64,PPC]
+			Format: nn[KMGTPE] | nn%
+			This parameter is the complement to kernelcore=, it
+			specifies the amount of memory used for migratable
+			allocations.  If both kernelcore and movablecore is
+			specified, then kernelcore will be at *least* the
+			specified value but may be more.  If movablecore on its
+			own is specified, the administrator must be careful
 			that the amount of memory usable for all allocations
 			is not too small.
 

Documentation/trace/postprocess/trace-vmscan-postprocess.pl

@@ -111,7 +111,7 @@ my $regex_direct_begin_default = 'order=([0-9]*) may_writepage=([0-9]*) gfp_flag
 my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)';
 my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
 my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
-my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)';
+my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)';
 my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) classzone_idx=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)';
 my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
 my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
@@ -201,7 +201,7 @@ $regex_kswapd_sleep = generate_traceevent_regex(
 $regex_wakeup_kswapd = generate_traceevent_regex(
 			"vmscan/mm_vmscan_wakeup_kswapd",
 			$regex_wakeup_kswapd_default,
-			"nid", "zid", "order");
+			"nid", "zid", "order", "gfp_flags");
 $regex_lru_isolate = generate_traceevent_regex(
 			"vmscan/mm_vmscan_lru_isolate",
 			$regex_lru_isolate_default,

arch/arc/mm/cache.c

@@ -833,7 +833,7 @@ void flush_dcache_page(struct page *page)
 	}
 
 	/* don't handle anon pages here */
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!mapping)
 		return;
 

arch/arm/boot/compressed/misc.c

@@ -128,12 +128,7 @@ asmlinkage void __div0(void)
 	error("Attempting division by 0!");
 }
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -150,8 +145,6 @@ decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
 {
 	int ret;
 
-	__stack_chk_guard_setup();
-
 	output_data		= (unsigned char *)output_start;
 	free_mem_ptr		= free_mem_ptr_p;
 	free_mem_end_ptr	= free_mem_ptr_end_p;

arch/arm/mm/copypage-v4mc.c

@@ -70,7 +70,7 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 	void *kto = kmap_atomic(to);
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	raw_spin_lock(&minicache_lock);
 

arch/arm/mm/copypage-v6.c

@@ -76,7 +76,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 	unsigned long kfrom, kto;
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	/* FIXME: not highmem safe */
 	discard_old_kernel_data(page_address(to));

arch/arm/mm/copypage-xscale.c

@@ -90,7 +90,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 	void *kto = kmap_atomic(to);
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	raw_spin_lock(&minicache_lock);
 

arch/arm/mm/fault-armv.c

@@ -195,7 +195,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 	if (mapping) {

arch/arm/mm/flush.c

@@ -285,7 +285,7 @@ void __sync_icache_dcache(pte_t pteval)
 
 	page = pfn_to_page(pfn);
 	if (cache_is_vipt_aliasing())
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 	else
 		mapping = NULL;
 
@@ -333,7 +333,7 @@ void flush_dcache_page(struct page *page)
 		return;
 	}
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	if (!cache_ops_need_broadcast() &&
 	    mapping && !page_mapcount(page))
@@ -363,7 +363,7 @@ void flush_kernel_dcache_page(struct page *page)
 	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
 		struct address_space *mapping;
 
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 
 		if (!mapping || mapping_mapped(mapping)) {
 			void *addr;

arch/mips/boot/compressed/decompress.c

@@ -76,12 +76,7 @@ void error(char *x)
 #include "../../../../lib/decompress_unxz.c"
 #endif
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -92,8 +87,6 @@ void decompress_kernel(unsigned long boot_heap_start)
 {
 	unsigned long zimage_start, zimage_size;
 
-	__stack_chk_guard_setup();
-
 	zimage_start = (unsigned long)(&__image_begin);
 	zimage_size = (unsigned long)(&__image_end) -
 	    (unsigned long)(&__image_begin);

arch/mips/mm/cache.c

@@ -86,7 +86,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 
 void __flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 	unsigned long addr;
 
 	if (mapping && !mapping_mapped(mapping)) {

arch/nios2/mm/cacheflush.c

@@ -180,7 +180,7 @@ void flush_dcache_page(struct page *page)
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	/* Flush this page if there are aliases. */
 	if (mapping && !mapping_mapped(mapping)) {
@@ -215,7 +215,7 @@ void update_mmu_cache(struct vm_area_struct *vma,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 

arch/parisc/kernel/cache.c

@@ -88,7 +88,8 @@ update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 		return;
 
 	page = pfn_to_page(pfn);
-	if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) {
+	if (page_mapping_file(page) &&
+	    test_bit(PG_dcache_dirty, &page->flags)) {
 		flush_kernel_dcache_page_addr(pfn_va(pfn));
 		clear_bit(PG_dcache_dirty, &page->flags);
 	} else if (parisc_requires_coherency())
@@ -304,7 +305,7 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
 	unsigned long addr, old_addr = 0;

arch/powerpc/include/asm/hugetlb.h

@@ -117,12 +117,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-/*
- * The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs
- * to override the version in mm/hugetlb.c
- */
-#define vma_mmu_pagesize vma_mmu_pagesize
-
 /*
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.

arch/powerpc/mm/hugetlbpage.c

@@ -568,10 +568,7 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 	if (!radix_enabled())
 		return 1UL << mmu_psize_to_shift(psize);
 #endif
-	if (!is_vm_hugetlb_page(vma))
-		return PAGE_SIZE;
-
-	return huge_page_size(hstate_vma(vma));
+	return vma_kernel_pagesize(vma);
 }
 
 static inline bool is_power_of_4(unsigned long x)

arch/powerpc/mm/mmu_context_iommu.c

@@ -112,7 +112,7 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	put_page(page); /* Drop the gup reference */
 
 	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
-				NULL, 0, MIGRATE_SYNC, MR_CMA);
+				NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
 	if (ret) {
 		if (!list_empty(&cma_migrate_pages))
 			putback_movable_pages(&cma_migrate_pages);

arch/powerpc/sysdev/dart_iommu.c

@@ -38,6 +38,7 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>

arch/powerpc/sysdev/msi_bitmap.c

@@ -10,6 +10,7 @@
 
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/kmemleak.h>
 #include <linux/bitmap.h>
 #include <linux/bootmem.h>
 #include <asm/msi_bitmap.h>

arch/s390/kernel/nmi.c

@@ -15,7 +15,7 @@
 #include <linux/hardirq.h>
 #include <linux/log2.h>
 #include <linux/kprobes.h>
-#include <linux/slab.h>
+#include <linux/kmemleak.h>
 #include <linux/time.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>

arch/s390/kernel/smp.c

@@ -27,7 +27,6 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/kernel_stat.h>
-#include <linux/kmemleak.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irqflags.h>

arch/sh/boot/compressed/misc.c

@@ -104,12 +104,7 @@ static void error(char *x)
 	while(1);	/* Halt */
 }
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -130,8 +125,6 @@ void decompress_kernel(void)
 {
 	unsigned long output_addr;
 
-	__stack_chk_guard_setup();
-
 #ifdef CONFIG_SUPERH64
 	output_addr = (CONFIG_MEMORY_START + 0x2000);
 #else

arch/sh/mm/cache-sh4.c

@@ -112,7 +112,7 @@ static void sh4_flush_dcache_page(void *arg)
 	struct page *page = arg;
 	unsigned long addr = (unsigned long)page_address(page);
 #ifndef CONFIG_SMP
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);

arch/sh/mm/cache-sh7705.c

@@ -136,7 +136,7 @@ static void __flush_dcache_page(unsigned long phys)
 static void sh7705_flush_dcache_page(void *arg)
 {
 	struct page *page = arg;
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);

arch/sparc/kernel/irq_64.c

@@ -22,7 +22,6 @@
 #include <linux/seq_file.h>
 #include <linux/ftrace.h>
 #include <linux/irq.h>
-#include <linux/kmemleak.h>
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>

arch/sparc/kernel/smp_64.c

@@ -929,9 +929,9 @@ static inline void __local_flush_dcache_page(struct page *page)
 #ifdef DCACHE_ALIASING_POSSIBLE
 	__flush_dcache_page(page_address(page),
 			    ((tlb_type == spitfire) &&
-			     page_mapping(page) != NULL));
+			     page_mapping_file(page) != NULL));
 #else
-	if (page_mapping(page) != NULL &&
+	if (page_mapping_file(page) != NULL &&
 	    tlb_type == spitfire)
 		__flush_icache_page(__pa(page_address(page)));
 #endif
@@ -958,7 +958,7 @@ void smp_flush_dcache_page_impl(struct page *page, int cpu)
 
 		if (tlb_type == spitfire) {
 			data0 = ((u64)&xcall_flush_dcache_page_spitfire);
-			if (page_mapping(page) != NULL)
+			if (page_mapping_file(page) != NULL)
 				data0 |= ((u64)1 << 32);
 		} else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
 #ifdef DCACHE_ALIASING_POSSIBLE
@@ -994,7 +994,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	pg_addr = page_address(page);
 	if (tlb_type == spitfire) {
 		data0 = ((u64)&xcall_flush_dcache_page_spitfire);
-		if (page_mapping(page) != NULL)
+		if (page_mapping_file(page) != NULL)
 			data0 |= ((u64)1 << 32);
 	} else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
 #ifdef DCACHE_ALIASING_POSSIBLE

arch/sparc/mm/init_64.c

@@ -206,9 +206,9 @@ inline void flush_dcache_page_impl(struct page *page)
 #ifdef DCACHE_ALIASING_POSSIBLE
 	__flush_dcache_page(page_address(page),
 			    ((tlb_type == spitfire) &&
-			     page_mapping(page) != NULL));
+			     page_mapping_file(page) != NULL));
 #else
-	if (page_mapping(page) != NULL &&
+	if (page_mapping_file(page) != NULL &&
 	    tlb_type == spitfire)
 		__flush_icache_page(__pa(page_address(page)));
 #endif
@@ -490,7 +490,7 @@ void flush_dcache_page(struct page *page)
 
 	this_cpu = get_cpu();
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (mapping && !mapping_mapped(mapping)) {
 		int dirty = test_bit(PG_dcache_dirty, &page->flags);
 		if (dirty) {

arch/sparc/mm/tlb.c

@@ -128,7 +128,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 			goto no_cache_flush;
 
 		/* A real file page? */
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 		if (!mapping)
 			goto no_cache_flush;
 

arch/unicore32/mm/flush.c

@@ -83,7 +83,7 @@ void flush_dcache_page(struct page *page)
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);

arch/unicore32/mm/mmu.c

@@ -503,7 +503,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 	if (mapping)

arch/x86/kernel/pci-dma.c

@@ -6,7 +6,6 @@
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/kmemleak.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>

arch/x86/mm/init_64.c

@@ -1328,14 +1328,39 @@ int kern_addr_valid(unsigned long addr)
 	return pfn_valid(pte_pfn(*pte));
 }
 
+/*
+ * Block size is the minimum amount of memory which can be hotplugged or
+ * hotremoved. It must be power of two and must be equal or larger than
+ * MIN_MEMORY_BLOCK_SIZE.
+ */
+#define MAX_BLOCK_SIZE (2UL << 30)
+
+/* Amount of ram needed to start using large blocks */
+#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+
 static unsigned long probe_memory_block_size(void)
 {
-	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
+	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
+	unsigned long bz;
 
-	/* if system is UV or has 64GB of RAM or more, use large blocks */
-	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
-		bz = 2UL << 30; /* 2GB */
+	/* If this is UV system, always set 2G block size */
+	if (is_uv_system()) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
 
+	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
+	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
+		bz = MIN_MEMORY_BLOCK_SIZE;
+		goto done;
+	}
+
+	/* Find the largest allowed block size that aligns to memory end */
+	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+		if (IS_ALIGNED(boot_mem_end, bz))
+			break;
+	}
+done:
 	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;

arch/xtensa/mm/cache.c

@@ -127,7 +127,7 @@ EXPORT_SYMBOL(copy_user_highpage);
 
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	/*
 	 * If we have a mapping but the page is not mapped to user-space

drivers/base/memory.c

@@ -187,13 +187,14 @@ int memory_isolate_notify(unsigned long val, void *v)
 }
 
 /*
- * The probe routines leave the pages reserved, just as the bootmem code does.
- * Make sure they're still that way.
+ * The probe routines leave the pages uninitialized, just as the bootmem code
+ * does. Make sure we do not access them, but instead use only information from
+ * within sections.
  */
-static bool pages_correctly_reserved(unsigned long start_pfn)
+static bool pages_correctly_probed(unsigned long start_pfn)
 {
-	int i, j;
-	struct page *page;
+	unsigned long section_nr = pfn_to_section_nr(start_pfn);
+	unsigned long section_nr_end = section_nr + sections_per_block;
 	unsigned long pfn = start_pfn;
 
 	/*
@@ -201,21 +202,24 @@ static bool pages_correctly_reserved(unsigned long start_pfn)
 	 * SPARSEMEM_VMEMMAP. We lookup the page once per section
 	 * and assume memmap is contiguous within each section
 	 */
-	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
+	for (; section_nr < section_nr_end; section_nr++) {
 		if (WARN_ON_ONCE(!pfn_valid(pfn)))
 			return false;
-		page = pfn_to_page(pfn);
-
-		for (j = 0; j < PAGES_PER_SECTION; j++) {
-			if (PageReserved(page + j))
-				continue;
-
-			printk(KERN_WARNING "section number %ld page number %d "
-				"not reserved, was it already online?\n",
-				pfn_to_section_nr(pfn), j);
 
+		if (!present_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) not present",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
+			return false;
+		} else if (!valid_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) no valid memmap",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
+			return false;
+		} else if (online_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) is already online",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
 			return false;
 		}
+		pfn += PAGES_PER_SECTION;
 	}
 
 	return true;
@@ -237,7 +241,7 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 
 	switch (action) {
 	case MEM_ONLINE:
-		if (!pages_correctly_reserved(start_pfn))
+		if (!pages_correctly_probed(start_pfn))
 			return -EBUSY;
 
 		ret = online_pages(start_pfn, nr_pages, online_type);
@@ -708,7 +712,7 @@ static int add_memory_block(int base_section_nr)
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
  */
-int register_new_memory(int nid, struct mem_section *section)
+int hotplug_memory_register(int nid, struct mem_section *section)
 {
 	int ret = 0;
 	struct memory_block *mem;
@@ -727,7 +731,7 @@ int register_new_memory(int nid, struct mem_section *section)
 	}
 
 	if (mem->section_count == sections_per_block)
-		ret = register_mem_sect_under_node(mem, nid);
+		ret = register_mem_sect_under_node(mem, nid, false);
 out:
 	mutex_unlock(&mem_sysfs_mutex);
 	return ret;

drivers/base/node.c

@@ -399,13 +399,16 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 }
 
 /* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
+int register_mem_sect_under_node(struct memory_block *mem_blk, int nid,
+				 bool check_nid)
 {
 	int ret;
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
 
 	if (!mem_blk)
 		return -EFAULT;
+
+	mem_blk->nid = nid;
 	if (!node_online(nid))
 		return 0;
 
@@ -425,11 +428,18 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 			continue;
 		}
 
-		page_nid = get_nid_for_pfn(pfn);
-		if (page_nid < 0)
-			continue;
-		if (page_nid != nid)
-			continue;
+		/*
+		 * We need to check if page belongs to nid only for the boot
+		 * case, during hotplug we know that all pages in the memory
+		 * block belong to the same node.
+		 */
+		if (check_nid) {
+			page_nid = get_nid_for_pfn(pfn);
+			if (page_nid < 0)
+				continue;
+			if (page_nid != nid)
+				continue;
+		}
 		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
@@ -504,7 +514,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 
 		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
 
-		ret = register_mem_sect_under_node(mem_blk, nid);
+		ret = register_mem_sect_under_node(mem_blk, nid, true);
 		if (!err)
 			err = ret;
 

drivers/block/zram/zram_drv.c

@@ -44,6 +44,11 @@ static const char *default_compressor = "lzo";
 
 /* Module params (documentation at end) */
 static unsigned int num_devices = 1;
+/*
+ * Pages that compress to sizes equals or greater than this are stored
+ * uncompressed in memory.
+ */
+static size_t huge_class_size;
 
 static void zram_free_page(struct zram *zram, size_t index);
 
@@ -786,6 +791,8 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
 		return false;
 	}
 
+	if (!huge_class_size)
+		huge_class_size = zs_huge_class_size(zram->mem_pool);
 	return true;
 }
 
@@ -965,7 +972,7 @@ compress_again:
 		return ret;
 	}
 
-	if (unlikely(comp_len > max_zpage_size)) {
+	if (unlikely(comp_len >= huge_class_size)) {
 		if (zram_wb_enabled(zram) && allow_wb) {
 			zcomp_stream_put(zram->comp);
 			ret = write_to_bdev(zram, bvec, index, bio, &element);

drivers/block/zram/zram_drv.h

@@ -21,22 +21,6 @@
 
 #include "zcomp.h"
 
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- *   ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
 #define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
 #define ZRAM_LOGICAL_BLOCK_SHIFT 12

drivers/dax/device.c

@@ -439,10 +439,20 @@ static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	return dax_region->align;
+}
+
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
 	.split = dev_dax_split,
+	.pagesize = dev_dax_pagesize,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)

drivers/iommu/exynos-iommu.c

@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/interrupt.h>
+#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>

drivers/iommu/mtk_iommu_v1.c

@@ -25,7 +25,6 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
-#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>

drivers/net/ethernet/ti/cpsw.c

@@ -35,6 +35,7 @@
 #include <linux/of_net.h>
 #include <linux/of_device.h>
 #include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
 
 #include <linux/pinctrl/consumer.h>
 

drivers/net/wireless/realtek/rtlwifi/pci.c

@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");

drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c

@@ -32,7 +32,6 @@
 #include "../rtl8192ce/def.h"
 #include "fw_common.h"
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 
 static void _rtl92c_enable_fw_download(struct ieee80211_hw *hw, bool enable)
 {

drivers/staging/rtl8188eu/hal/fw.c

@@ -30,7 +30,7 @@
 #include "rtl8188e_hal.h"
 
 #include <linux/firmware.h>
-#include <linux/kmemleak.h>
+#include <linux/slab.h>
 
 static void _rtl88e_enable_fw_download(struct adapter *adapt, bool enable)
 {

drivers/staging/rtlwifi/pci.c

@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");

drivers/virtio/virtio_ring.c

@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/hrtimer.h>
-#include <linux/kmemleak.h>
 #include <linux/dma-mapping.h>
 #include <xen/xen.h>
 

fs/9p/v9fs.c

@@ -292,6 +292,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 #ifdef CONFIG_9P_FSCACHE
 			kfree(v9ses->cachetag);
 			v9ses->cachetag = match_strdup(&args[0]);
+			if (!v9ses->cachetag) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
 #endif
 			break;
 		case Opt_cache:
@@ -471,6 +475,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	return fid;
 
 err_clnt:
+#ifdef CONFIG_9P_FSCACHE
+	kfree(v9ses->cachetag);
+#endif
 	p9_client_destroy(v9ses->clnt);
 err_names:
 	kfree(v9ses->uname);

fs/9p/vfs_inode.c

@@ -578,6 +578,24 @@ static int v9fs_at_to_dotl_flags(int flags)
 	return rflags;
 }
 
+/**
+ * v9fs_dec_count - helper functon to drop i_nlink.
+ *
+ * If a directory had nlink <= 2 (including . and ..), then we should not drop
+ * the link count, which indicates the underlying exported fs doesn't maintain
+ * nlink accurately. e.g.
+ * - overlayfs sets nlink to 1 for merged dir
+ * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more
+ *   than EXT4_LINK_MAX (65000) links.
+ *
+ * @inode: inode whose nlink is being dropped
+ */
+static void v9fs_dec_count(struct inode *inode)
+{
+	if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+		drop_nlink(inode);
+}
+
 /**
  * v9fs_remove - helper function to remove files and directories
  * @dir: directory inode that is being deleted
@@ -621,9 +639,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 		 */
 		if (flags & AT_REMOVEDIR) {
 			clear_nlink(inode);
-			drop_nlink(dir);
+			v9fs_dec_count(dir);
 		} else
-			drop_nlink(inode);
+			v9fs_dec_count(inode);
 
 		v9fs_invalidate_inode_attr(inode);
 		v9fs_invalidate_inode_attr(dir);
@@ -1024,12 +1042,12 @@ clunk_newdir:
 			if (S_ISDIR(new_inode->i_mode))
 				clear_nlink(new_inode);
 			else
-				drop_nlink(new_inode);
+				v9fs_dec_count(new_inode);
 		}
 		if (S_ISDIR(old_inode->i_mode)) {
 			if (!new_inode)
 				inc_nlink(new_dir);
-			drop_nlink(old_dir);
+			v9fs_dec_count(old_dir);
 		}
 		v9fs_invalidate_inode_attr(old_inode);
 		v9fs_invalidate_inode_attr(old_dir);

fs/9p/vfs_super.c

@@ -94,7 +94,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 	if (v9ses->cache)
 		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
 
-	sb->s_flags |= SB_ACTIVE | SB_DIRSYNC | SB_NOATIME;
+	sb->s_flags |= SB_ACTIVE | SB_DIRSYNC;
 	if (!v9ses->cache)
 		sb->s_flags |= SB_SYNCHRONOUS;
 

fs/block_dev.c

@@ -1324,7 +1324,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
  * @bdev: struct bdev to adjust.
  *
  * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs.
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
  */
 void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 {
@@ -1337,7 +1338,8 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 		       "%s: detected capacity change from %lld to %lld\n",
 		       disk->disk_name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
-		flush_disk(bdev, false);
+		if (bdev_size > disk_size)
+			flush_disk(bdev, false);
 	}
 }
 EXPORT_SYMBOL(check_disk_size_change);

fs/buffer.c

@@ -1511,7 +1511,7 @@ void block_invalidatepage(struct page *page, unsigned int offset,
 	 * The get_block cached value has been unconditionally invalidated,
 	 * so real IO is not possible anymore.
 	 */
-	if (offset == 0)
+	if (length == PAGE_SIZE)
 		try_to_release_page(page, 0);
 out:
 	return;

fs/direct-io.c

@@ -1177,9 +1177,9 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	unsigned blkbits = i_blkbits;
 	unsigned blocksize_mask = (1 << blkbits) - 1;
 	ssize_t retval = -EINVAL;
-	size_t count = iov_iter_count(iter);
+	const size_t count = iov_iter_count(iter);
 	loff_t offset = iocb->ki_pos;
-	loff_t end = offset + count;
+	const loff_t end = offset + count;
 	struct dio *dio;
 	struct dio_submit sdio = { 0, };
 	struct buffer_head map_bh = { 0, };
@@ -1200,7 +1200,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	}
 
 	/* watch out for a 0 len io from a tricksy fs */
-	if (iov_iter_rw(iter) == READ && !iov_iter_count(iter))
+	if (iov_iter_rw(iter) == READ && !count)
 		return 0;
 
 	dio = kmem_cache_alloc(dio_cache, GFP_KERNEL);
@@ -1315,8 +1315,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 	dio->should_dirty = (iter->type == ITER_IOVEC);
 	sdio.iter = iter;
-	sdio.final_block_in_request =
-		(offset + iov_iter_count(iter)) >> blkbits;
+	sdio.final_block_in_request = end >> blkbits;
 
 	/*
 	 * In case of non-aligned buffers, we may need 2 more

fs/hugetlbfs/inode.c

@@ -138,10 +138,14 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	/*
 	 * page based offset in vm_pgoff could be sufficiently large to
-	 * overflow a (l)off_t when converted to byte offset.
+	 * overflow a loff_t when converted to byte offset.  This can
+	 * only happen on architectures where sizeof(loff_t) ==
+	 * sizeof(unsigned long).  So, only check in those instances.
 	 */
-	if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
-		return -EINVAL;
+	if (sizeof(unsigned long) == sizeof(loff_t)) {
+		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
+			return -EINVAL;
+	}
 
 	/* must be huge page aligned */
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))

fs/ocfs2/alloc.c

@@ -7119,7 +7119,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 			goto out_commit;
 		did_quota = 1;
 
-		data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+		data_ac->ac_resv = &oi->ip_la_data_resv;
 
 		ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off,
 					   &num);

fs/ocfs2/aops.c

@@ -346,7 +346,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	unlock = 0;
 
 out_alloc:
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+	up_read(&oi->ip_alloc_sem);
 out_inode_unlock:
 	ocfs2_inode_unlock(inode, 0);
 out:
@@ -2213,7 +2213,7 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	down_write(&oi->ip_alloc_sem);
 
 	if (first_get_block) {
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		if (ocfs2_sparse_alloc(osb))
 			ret = ocfs2_zero_tail(inode, di_bh, pos);
 		else
 			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,

fs/ocfs2/aops.h

@@ -78,7 +78,7 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 /*
  * Using a named enum representing lock types in terms of #N bit stored in
  * iocb->private, which is going to be used for communication between
- * ocfs2_dio_end_io() and ocfs2_file_aio_write/read().
+ * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
  */
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,

fs/ocfs2/cluster/heartbeat.c

@@ -570,7 +570,16 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg,
 		     current_page, vec_len, vec_start);
 
 		len = bio_add_page(bio, page, vec_len, vec_start);
-		if (len != vec_len) break;
+		if (len != vec_len) {
+			mlog(ML_ERROR, "Adding page[%d] to bio failed, "
+			     "page %p, len %d, vec_len %u, vec_start %u, "
+			     "bi_sector %llu\n", current_page, page, len,
+			     vec_len, vec_start,
+			     (unsigned long long)bio->bi_iter.bi_sector);
+			bio_put(bio);
+			bio = ERR_PTR(-EIO);
+			return bio;
+		}
 
 		cs += vec_len / (PAGE_SIZE/spp);
 		vec_start = 0;

fs/ocfs2/dir.c

@@ -3072,7 +3072,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 			 * We need to return the correct block within the
 			 * cluster which should hold our entry.
 			 */
-			off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb),
+			off = ocfs2_dx_dir_hash_idx(osb,
 						    &lookup->dl_hinfo);
 			get_bh(dx_leaves[off]);
 			lookup->dl_dx_leaf_bh = dx_leaves[off];

fs/ocfs2/dlm/dlmast.c

@@ -224,14 +224,12 @@ void dlm_do_local_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 		      struct dlm_lock *lock)
 {
 	dlm_astlockfunc_t *fn;
-	struct dlm_lockstatus *lksb;
 
 	mlog(0, "%s: res %.*s, lock %u:%llu, Local AST\n", dlm->name,
 	     res->lockname.len, res->lockname.name,
 	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
 
-	lksb = lock->lksb;
 	fn = lock->ast;
 	BUG_ON(lock->ml.node != dlm->node_num);
 

fs/ocfs2/dlm/dlmcommon.h

@@ -140,6 +140,7 @@ struct dlm_ctxt
 	u8 node_num;
 	u32 key;
 	u8  joining_node;
+	u8 migrate_done; /* set to 1 means node has migrated all lock resources */
 	wait_queue_head_t dlm_join_events;
 	unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
@@ -960,13 +961,10 @@ static inline int dlm_send_proxy_ast(struct dlm_ctxt *dlm,
 void dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 void __dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 
-u8 dlm_nm_this_node(struct dlm_ctxt *dlm);
 void dlm_kick_thread(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 
 
-int dlm_nm_init(struct dlm_ctxt *dlm);
-int dlm_heartbeat_init(struct dlm_ctxt *dlm);
 void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data);
 void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data);
 

fs/ocfs2/dlm/dlmdomain.c

@@ -461,6 +461,19 @@ redo_bucket:
 		cond_resched_lock(&dlm->spinlock);
 		num += n;
 	}
+
+	if (!num) {
+		if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+			mlog(0, "%s: perhaps there are more lock resources "
+			     "need to be migrated after dlm recovery\n", dlm->name);
+			ret = -EAGAIN;
+		} else {
+			mlog(0, "%s: we won't do dlm recovery after migrating "
+			     "all lock resources\n", dlm->name);
+			dlm->migrate_done = 1;
+		}
+	}
+
 	spin_unlock(&dlm->spinlock);
 	wake_up(&dlm->dlm_thread_wq);
 
@@ -675,20 +688,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
 	spin_unlock(&dlm->spinlock);
 }
 
-int dlm_shutting_down(struct dlm_ctxt *dlm)
-{
-	int ret = 0;
-
-	spin_lock(&dlm_domain_lock);
-
-	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
-		ret = 1;
-
-	spin_unlock(&dlm_domain_lock);
-
-	return ret;
-}
-
 void dlm_unregister_domain(struct dlm_ctxt *dlm)
 {
 	int leave = 0;
@@ -2052,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN;
 	init_waitqueue_head(&dlm->dlm_join_events);
 
+	dlm->migrate_done = 0;
+
 	dlm->reco.new_master = O2NM_INVALID_NODE_NUM;
 	dlm->reco.dead_node = O2NM_INVALID_NODE_NUM;
 

fs/ocfs2/dlm/dlmdomain.h

@@ -28,7 +28,30 @@
 extern spinlock_t dlm_domain_lock;
 extern struct list_head dlm_domains;
 
-int dlm_shutting_down(struct dlm_ctxt *dlm);
+static inline int dlm_joined(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_JOINED)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
+static inline int dlm_shutting_down(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
 void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
 					int node_num);
 

fs/ocfs2/dlm/dlmlock.c

@@ -77,8 +77,7 @@ int dlm_init_lock_cache(void)
 
 void dlm_destroy_lock_cache(void)
 {
-	if (dlm_lock_cache)
-		kmem_cache_destroy(dlm_lock_cache);
+	kmem_cache_destroy(dlm_lock_cache);
 }
 
 /* Tell us whether we can grant a new lock request.

fs/ocfs2/dlm/dlmmaster.c

@@ -414,8 +414,7 @@ int dlm_init_mle_cache(void)
 
 void dlm_destroy_mle_cache(void)
 {
-	if (dlm_mle_cache)
-		kmem_cache_destroy(dlm_mle_cache);
+	kmem_cache_destroy(dlm_mle_cache);
 }
 
 static void dlm_mle_release(struct kref *kref)
@@ -472,15 +471,11 @@ bail:
 
 void dlm_destroy_master_caches(void)
 {
-	if (dlm_lockname_cache) {
-		kmem_cache_destroy(dlm_lockname_cache);
-		dlm_lockname_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockname_cache);
+	dlm_lockname_cache = NULL;
 
-	if (dlm_lockres_cache) {
-		kmem_cache_destroy(dlm_lockres_cache);
-		dlm_lockres_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockres_cache);
+	dlm_lockres_cache = NULL;
 }
 
 static void dlm_lockres_release(struct kref *kref)
@@ -2495,13 +2490,13 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 }
 
 /*
- * A migrateable resource is one that is :
+ * A migratable resource is one that is :
  * 1. locally mastered, and,
  * 2. zero local locks, and,
  * 3. one or more non-local locks, or, one or more references
  * Returns 1 if yes, 0 if not.
  */
-static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
+static int dlm_is_lockres_migratable(struct dlm_ctxt *dlm,
 				      struct dlm_lock_resource *res)
 {
 	enum dlm_lockres_list idx;
@@ -2532,7 +2527,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 				continue;
 			}
 			cookie = be64_to_cpu(lock->ml.cookie);
-			mlog(0, "%s: Not migrateable res %.*s, lock %u:%llu on "
+			mlog(0, "%s: Not migratable res %.*s, lock %u:%llu on "
 			     "%s list\n", dlm->name, res->lockname.len,
 			     res->lockname.name,
 			     dlm_get_lock_cookie_node(cookie),
@@ -2548,7 +2543,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 			return 0;
 	}
 
-	mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len,
+	mlog(0, "%s: res %.*s, Migratable\n", dlm->name, res->lockname.len,
 	     res->lockname.name);
 
 	return 1;
@@ -2792,7 +2787,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	assert_spin_locked(&dlm->spinlock);
 
 	spin_lock(&res->spinlock);
-	if (dlm_is_lockres_migrateable(dlm, res))
+	if (dlm_is_lockres_migratable(dlm, res))
 		target = dlm_pick_migration_target(dlm, res);
 	spin_unlock(&res->spinlock);
 

fs/ocfs2/dlm/dlmrecovery.c

@@ -62,7 +62,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_request_all_locks(struct dlm_ctxt *dlm,
 				 u8 request_from, u8 dead_node);
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm);
 
 static inline int dlm_num_locks_in_lockres(struct dlm_lock_resource *res);
 static void dlm_init_migratable_lockres(struct dlm_migratable_lockres *mres,
@@ -423,12 +423,11 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm)
 
 static void dlm_begin_recovery(struct dlm_ctxt *dlm)
 {
-	spin_lock(&dlm->spinlock);
+	assert_spin_locked(&dlm->spinlock);
 	BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE);
 	printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n",
 	       dlm->name, dlm->reco.dead_node);
 	dlm->reco.state |= DLM_RECO_STATE_ACTIVE;
-	spin_unlock(&dlm->spinlock);
 }
 
 static void dlm_end_recovery(struct dlm_ctxt *dlm)
@@ -456,6 +455,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 
 	spin_lock(&dlm->spinlock);
 
+	if (dlm->migrate_done) {
+		mlog(0, "%s: no need do recovery after migrating all "
+		     "lock resources\n", dlm->name);
+		spin_unlock(&dlm->spinlock);
+		return 0;
+	}
+
 	/* check to see if the new master has died */
 	if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM &&
 	    test_bit(dlm->reco.new_master, dlm->recovery_map)) {
@@ -490,12 +496,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n",
 	     dlm->name, task_pid_nr(dlm->dlm_reco_thread_task),
 	     dlm->reco.dead_node);
-	spin_unlock(&dlm->spinlock);
 
 	/* take write barrier */
 	/* (stops the list reshuffling thread, proxy ast handling) */
 	dlm_begin_recovery(dlm);
 
+	spin_unlock(&dlm->spinlock);
+
 	if (dlm->reco.new_master == dlm->node_num)
 		goto master_here;
 
@@ -739,7 +746,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 	}
 
 	if (destroy)
-		dlm_destroy_recovery_area(dlm, dead_node);
+		dlm_destroy_recovery_area(dlm);
 
 	return status;
 }
@@ -764,7 +771,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 
 		ndata = kzalloc(sizeof(*ndata), GFP_NOFS);
 		if (!ndata) {
-			dlm_destroy_recovery_area(dlm, dead_node);
+			dlm_destroy_recovery_area(dlm);
 			return -ENOMEM;
 		}
 		ndata->node_num = num;
@@ -778,7 +785,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 	return 0;
 }
 
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm)
 {
 	struct dlm_reco_node_data *ndata, *next;
 	LIST_HEAD(tmplist);
@@ -1378,6 +1385,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	if (!dlm_grab(dlm))
 		return -EINVAL;
 
+	if (!dlm_joined(dlm)) {
+		mlog(ML_ERROR, "Domain %s not joined! "
+			  "lockres %.*s, master %u\n",
+			  dlm->name, mres->lockname_len,
+			  mres->lockname, mres->master);
+		dlm_put(dlm);
+		return -EINVAL;
+	}
+
 	BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION)));
 
 	real_master = mres->master;
@@ -1807,7 +1823,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 	int i, j, bad;
 	struct dlm_lock *lock;
 	u8 from = O2NM_MAX_NODES;
-	unsigned int added = 0;
 	__be64 c;
 
 	mlog(0, "running %d locks for this lockres\n", mres->num_locks);
@@ -1823,7 +1838,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			spin_lock(&res->spinlock);
 			dlm_lockres_set_refmap_bit(dlm, res, from);
 			spin_unlock(&res->spinlock);
-			added++;
 			break;
 		}
 		BUG_ON(ml->highest_blocked != LKM_IVMODE);
@@ -1911,7 +1925,6 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			/* do not alter lock refcount.  switching lists. */
 			list_move_tail(&lock->list, queue);
 			spin_unlock(&res->spinlock);
-			added++;
 
 			mlog(0, "just reordered a local lock!\n");
 			continue;
@@ -2037,7 +2050,6 @@ skip_lvb:
 			     "setting refmap bit\n", dlm->name,
 			     res->lockname.len, res->lockname.name, ml->node);
 			dlm_lockres_set_refmap_bit(dlm, res, ml->node);
-			added++;
 		}
 		spin_unlock(&res->spinlock);
 	}
@@ -2331,13 +2343,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 	__dlm_dirty_lockres(dlm, res);
 }
 
-/* if this node is the recovery master, and there are no
- * locks for a given lockres owned by this node that are in
- * either PR or EX mode, zero out the lvb before requesting.
- *
- */
-
-
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 {
 	struct dlm_lock_resource *res;

fs/ocfs2/dlmglue.c

@@ -1756,8 +1756,7 @@ int ocfs2_rw_lock(struct inode *inode, int write)
 
 	level = write ? DLM_LOCK_EX : DLM_LOCK_PR;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, level, 0,
-				    0);
+	status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1796,7 +1795,7 @@ void ocfs2_rw_unlock(struct inode *inode, int write)
 	     write ? "EXMODE" : "PRMODE");
 
 	if (!ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*
@@ -1816,8 +1815,7 @@ int ocfs2_open_lock(struct inode *inode)
 
 	lockres = &OCFS2_I(inode)->ip_open_lockres;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    DLM_LOCK_PR, 0, 0);
+	status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_PR, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1854,8 +1852,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	 * other nodes and the -EAGAIN will indicate to the caller that
 	 * this inode is still in use.
 	 */
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    level, DLM_LKF_NOQUEUE, 0);
+	status = ocfs2_cluster_lock(osb, lockres, level, DLM_LKF_NOQUEUE, 0);
 
 out:
 	return status;
@@ -1876,11 +1873,9 @@ void ocfs2_open_unlock(struct inode *inode)
 		goto out;
 
 	if(lockres->l_ro_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_PR);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_PR);
 	if(lockres->l_ex_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_EX);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
 
 out:
 	return;
@@ -2601,9 +2596,9 @@ void ocfs2_inode_unlock(struct inode *inode,
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     ex ? "EXMODE" : "PRMODE");
 
-	if (!ocfs2_is_hard_readonly(OCFS2_SB(inode->i_sb)) &&
+	if (!ocfs2_is_hard_readonly(osb) &&
 	    !ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*

fs/ocfs2/file.c

@@ -101,7 +101,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
 	trace_ocfs2_file_open(inode, file, file->f_path.dentry,
-			      (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			      (unsigned long long)oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name, mode);
 
@@ -116,7 +116,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	/* Check that the inode hasn't been wiped from disk by another
 	 * node. If it hasn't then we're safe as long as we hold the
 	 * spin lock until our increment of open count. */
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED) {
+	if (oi->ip_flags & OCFS2_INODE_DELETED) {
 		spin_unlock(&oi->ip_lock);
 
 		status = -ENOENT;
@@ -190,7 +190,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
 	bool needs_barrier = false;
 
 	trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
-			      OCFS2_I(inode)->ip_blkno,
+			      oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name,
 			      (unsigned long long)datasync);
@@ -296,7 +296,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	ocfs2_journal_dirty(handle, bh);
 
 out_commit:
-	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	return ret;
 }
@@ -2257,7 +2257,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
+	trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
 		file->f_path.dentry->d_name.len,
 		file->f_path.dentry->d_name.name,
@@ -2405,7 +2405,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
+	trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry,
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			filp->f_path.dentry->d_name.len,
 			filp->f_path.dentry->d_name.name,
@@ -2448,7 +2448,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	 *
 	 * Take and drop the meta data lock to update inode fields
 	 * like i_size. This allows the checks down below
-	 * generic_file_aio_read() a chance of actually working.
+	 * generic_file_read_iter() a chance of actually working.
 	 */
 	ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
 				     !nowait);
@@ -2460,7 +2460,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	ocfs2_inode_unlock(inode, lock_level);
 
 	ret = generic_file_read_iter(iocb, to);
-	trace_generic_file_aio_read_ret(ret);
+	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));

fs/ocfs2/filecheck.c

@@ -53,36 +53,6 @@ static const char * const ocfs2_filecheck_errs[] = {
 	"UNSUPPORTED"
 };
 
-static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
-static LIST_HEAD(ocfs2_filecheck_sysfs_list);
-
-struct ocfs2_filecheck {
-	struct list_head fc_head;	/* File check entry list head */
-	spinlock_t fc_lock;
-	unsigned int fc_max;	/* Maximum number of entry in list */
-	unsigned int fc_size;	/* Current entry count in list */
-	unsigned int fc_done;	/* Finished entry count in list */
-};
-
-struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per mounting */
-	struct list_head fs_list;
-	atomic_t fs_count;
-	struct super_block *fs_sb;
-	struct kset *fs_devicekset;
-	struct kset *fs_fcheckkset;
-	struct ocfs2_filecheck *fs_fcheck;
-};
-
-#define OCFS2_FILECHECK_MAXSIZE		100
-#define OCFS2_FILECHECK_MINSIZE		10
-
-/* File check operation type */
-enum {
-	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
-	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
-	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
-};
-
 struct ocfs2_filecheck_entry {
 	struct list_head fe_list;
 	unsigned long fe_ino;
@@ -110,35 +80,84 @@ ocfs2_filecheck_error(int errno)
 	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    char *buf);
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
-				     struct kobj_attribute *attr,
-				     const char *buf, size_t count);
-static struct kobj_attribute ocfs2_attr_filecheck_chk =
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf);
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count);
+static struct kobj_attribute ocfs2_filecheck_attr_chk =
 					__ATTR(check, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_fix =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_fix =
 					__ATTR(fix, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_set =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_set =
 					__ATTR(set, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct attribute *ocfs2_filecheck_attrs[] = {
+	&ocfs2_filecheck_attr_chk.attr,
+	&ocfs2_filecheck_attr_fix.attr,
+	&ocfs2_filecheck_attr_set.attr,
+	NULL
+};
+
+static void ocfs2_filecheck_release(struct kobject *kobj)
+{
+	struct ocfs2_filecheck_sysfs_entry *entry = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
+
+	complete(&entry->fs_kobj_unregister);
+}
+
+static ssize_t
+ocfs2_filecheck_show(struct kobject *kobj, struct attribute *attr, char *buf)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->show)
+		ret = kattr->show(kobj, kattr, buf);
+	kobject_put(kobj);
+	return ret;
+}
+
+static ssize_t
+ocfs2_filecheck_store(struct kobject *kobj, struct attribute *attr,
+			const char *buf, size_t count)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->store)
+		ret = kattr->store(kobj, kattr, buf, count);
+	kobject_put(kobj);
+	return ret;
+}
+
+static const struct sysfs_ops ocfs2_filecheck_ops = {
+	.show = ocfs2_filecheck_show,
+	.store = ocfs2_filecheck_store,
+};
+
+static struct kobj_type ocfs2_ktype_filecheck = {
+	.default_attrs = ocfs2_filecheck_attrs,
+	.sysfs_ops = &ocfs2_filecheck_ops,
+	.release = ocfs2_filecheck_release,
+};
 
 static void
 ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 {
 	struct ocfs2_filecheck_entry *p;
 
-	if (!atomic_dec_and_test(&entry->fs_count)) {
-		wait_var_event(&entry->fs_count,
-			       !atomic_read(&entry->fs_count));
-	}
-
 	spin_lock(&entry->fs_fcheck->fc_lock);
 	while (!list_empty(&entry->fs_fcheck->fc_head)) {
 		p = list_first_entry(&entry->fs_fcheck->fc_head,
@@ -149,151 +168,48 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 	}
 	spin_unlock(&entry->fs_fcheck->fc_lock);
 
-	kset_unregister(entry->fs_fcheckkset);
-	kset_unregister(entry->fs_devicekset);
 	kfree(entry->fs_fcheck);
-	kfree(entry);
-}
-
-static void
-ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	entry->fs_fcheck = NULL;
 }
 
-static int ocfs2_filecheck_sysfs_del(const char *devname)
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb)
 {
-	struct ocfs2_filecheck_sysfs_entry *p;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			list_del(&p->fs_list);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			ocfs2_filecheck_sysfs_free(p);
-			return 0;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return 1;
-}
-
-static void
-ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	if (atomic_dec_and_test(&entry->fs_count))
-		wake_up_var(&entry->fs_count);
-}
-
-static struct ocfs2_filecheck_sysfs_entry *
-ocfs2_filecheck_sysfs_get(const char *devname)
-{
-	struct ocfs2_filecheck_sysfs_entry *p = NULL;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			atomic_inc(&p->fs_count);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			return p;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return NULL;
-}
-
-int ocfs2_filecheck_create_sysfs(struct super_block *sb)
-{
-	int ret = 0;
-	struct kset *device_kset = NULL;
-	struct kset *fcheck_kset = NULL;
-	struct ocfs2_filecheck *fcheck = NULL;
-	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
-	struct attribute **attrs = NULL;
-	struct attribute_group attrgp;
-
-	if (!ocfs2_kset)
-		return -ENOMEM;
-
-	attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS);
-	if (!attrs) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		attrs[0] = &ocfs2_attr_filecheck_chk.attr;
-		attrs[1] = &ocfs2_attr_filecheck_fix.attr;
-		attrs[2] = &ocfs2_attr_filecheck_set.attr;
-		attrs[3] = NULL;
-		memset(&attrgp, 0, sizeof(attrgp));
-		attrgp.attrs = attrs;
-	}
+	int ret;
+	struct ocfs2_filecheck *fcheck;
+	struct ocfs2_filecheck_sysfs_entry *entry = &osb->osb_fc_ent;
 
 	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
-	if (!fcheck) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		INIT_LIST_HEAD(&fcheck->fc_head);
-		spin_lock_init(&fcheck->fc_lock);
-		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
-		fcheck->fc_size = 0;
-		fcheck->fc_done = 0;
-	}
-
-	if (strlen(sb->s_id) <= 0) {
-		mlog(ML_ERROR,
-		"Cannot get device basename when create filecheck sysfs\n");
-		ret = -ENODEV;
-		goto error;
-	}
-
-	device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj);
-	if (!device_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	fcheck_kset = kset_create_and_add("filecheck", NULL,
-					  &device_kset->kobj);
-	if (!fcheck_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp);
-	if (ret)
-		goto error;
+	if (!fcheck)
+		return -ENOMEM;
 
-	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
-	if (!entry) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		atomic_set(&entry->fs_count, 1);
-		entry->fs_sb = sb;
-		entry->fs_devicekset = device_kset;
-		entry->fs_fcheckkset = fcheck_kset;
-		entry->fs_fcheck = fcheck;
-		ocfs2_filecheck_sysfs_add(entry);
+	INIT_LIST_HEAD(&fcheck->fc_head);
+	spin_lock_init(&fcheck->fc_lock);
+	fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+	fcheck->fc_size = 0;
+	fcheck->fc_done = 0;
+
+	entry->fs_kobj.kset = osb->osb_dev_kset;
+	init_completion(&entry->fs_kobj_unregister);
+	ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck,
+					NULL, "filecheck");
+	if (ret) {
+		kfree(fcheck);
+		return ret;
 	}
 
-	kfree(attrs);
+	entry->fs_fcheck = fcheck;
 	return 0;
-
-error:
-	kfree(attrs);
-	kfree(entry);
-	kfree(fcheck);
-	kset_unregister(fcheck_kset);
-	kset_unregister(device_kset);
-	return ret;
 }
 
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb)
 {
-	return ocfs2_filecheck_sysfs_del(sb->s_id);
+	if (!osb->osb_fc_ent.fs_fcheck)
+		return;
+
+	kobject_del(&osb->osb_fc_ent.fs_kobj);
+	kobject_put(&osb->osb_fc_ent.fs_kobj);
+	wait_for_completion(&osb->osb_fc_ent.fs_kobj_unregister);
+	ocfs2_filecheck_sysfs_free(&osb->osb_fc_ent);
 }
 
 static int
@@ -310,7 +226,7 @@ ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
 	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
-		mlog(ML_ERROR,
+		mlog(ML_NOTICE,
 		"Cannot set online file check maximum entry number "
 		"to %u due to too many pending entries(%u)\n",
 		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
@@ -387,7 +303,7 @@ ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count,
 	return 0;
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
 				    struct kobj_attribute *attr,
 				    char *buf)
 {
@@ -395,19 +311,12 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
 	unsigned int type;
 	struct ocfs2_filecheck_entry *p;
-	struct ocfs2_filecheck_sysfs_entry *ent;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (ocfs2_filecheck_type_parse(attr->attr.name, &type))
 		return -EINVAL;
 
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->name);
-		return -ENODEV;
-	}
-
 	if (type == OCFS2_FILECHECK_TYPE_SET) {
 		spin_lock(&ent->fs_fcheck->fc_lock);
 		total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max);
@@ -441,11 +350,26 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return total;
 }
 
-static int
+static inline int
+ocfs2_filecheck_is_dup_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned long ino)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (!p->fe_done) {
+			if (p->fe_ino == ino)
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int
 ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
 {
 	struct ocfs2_filecheck_entry *p;
@@ -484,21 +408,21 @@ static void
 ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			   struct ocfs2_filecheck_entry *entry)
 {
-	entry->fe_done = 1;
 	spin_lock(&ent->fs_fcheck->fc_lock);
+	entry->fe_done = 1;
 	ent->fs_fcheck->fc_done++;
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 }
 
 static unsigned int
-ocfs2_filecheck_handle(struct super_block *sb,
+ocfs2_filecheck_handle(struct ocfs2_super *osb,
 		       unsigned long ino, unsigned int flags)
 {
 	unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS;
 	struct inode *inode = NULL;
 	int rc;
 
-	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	inode = ocfs2_iget(osb, ino, flags, 0);
 	if (IS_ERR(inode)) {
 		rc = (int)(-(long)inode);
 		if (rc >= OCFS2_FILECHECK_ERR_START &&
@@ -516,11 +440,14 @@ static void
 ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			     struct ocfs2_filecheck_entry *entry)
 {
+	struct ocfs2_super *osb = container_of(ent, struct ocfs2_super,
+						osb_fc_ent);
+
 	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
 	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
 	else
 		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
@@ -528,30 +455,21 @@ ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 	ocfs2_filecheck_done_entry(ent, entry);
 }
 
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
 				     struct kobj_attribute *attr,
 				     const char *buf, size_t count)
 {
+	ssize_t ret = 0;
 	struct ocfs2_filecheck_args args;
 	struct ocfs2_filecheck_entry *entry;
-	struct ocfs2_filecheck_sysfs_entry *ent;
-	ssize_t ret = 0;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (count == 0)
 		return count;
 
-	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) {
-		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args))
 		return -EINVAL;
-	}
-
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->parent->name);
-		return -ENODEV;
-	}
 
 	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
 		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
@@ -565,13 +483,16 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 	}
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
-	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
-	    (ent->fs_fcheck->fc_done == 0)) {
-		mlog(ML_ERROR,
+	if (ocfs2_filecheck_is_dup_entry(ent, args.fa_ino)) {
+		ret = -EEXIST;
+		kfree(entry);
+	} else if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		(ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_NOTICE,
 		"Cannot do more file check "
 		"since file check queue(%u) is full now\n",
 		ent->fs_fcheck->fc_max);
-		ret = -EBUSY;
+		ret = -EAGAIN;
 		kfree(entry);
 	} else {
 		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
@@ -596,6 +517,5 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 		ocfs2_filecheck_handle_entry(ent, entry);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return (!ret ? count : ret);
 }

fs/ocfs2/filecheck.h

@@ -43,7 +43,32 @@ enum {
 #define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
 #define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
 
-int ocfs2_filecheck_create_sysfs(struct super_block *sb);
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* Finished entry count in list */
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
+};
+
+struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per partition */
+	struct kobject fs_kobj;
+	struct completion fs_kobj_unregister;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb);
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb);
 
 #endif  /* FILECHECK_H */

fs/ocfs2/inode.c

@@ -1135,7 +1135,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink);
 
-	mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL,
+	mlog_bug_on_msg(osb == NULL,
 			"Inode=%lu\n", inode->i_ino);
 
 	dquot_drop(inode);
@@ -1150,7 +1150,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres);
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres);
 
-	ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
+	ocfs2_resv_discard(&osb->osb_la_resmap,
 			   &oi->ip_la_data_resv);
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 
@@ -1160,7 +1160,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * exception here are successfully wiped inodes - their
 	 * metadata can now be considered to be part of the system
 	 * inodes from which it came. */
-	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED))
+	if (!(oi->ip_flags & OCFS2_INODE_DELETED))
 		ocfs2_checkpoint_inode(inode);
 
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
@@ -1223,7 +1223,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * the journal is flushed before journal shutdown. Thus it is safe to
 	 * have inodes get cleaned up after journal shutdown.
 	 */
-	jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
+	jbd2_journal_release_jbd_inode(osb->journal->j_journal,
 				       &oi->ip_jinode);
 }
 

fs/ocfs2/namei.c

@@ -525,7 +525,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	 * these are used by the support functions here and in
 	 * callers. */
 	inode->i_ino = ino_from_blkno(osb->sb, fe_blkno);
-	OCFS2_I(inode)->ip_blkno = fe_blkno;
+	oi->ip_blkno = fe_blkno;
 	spin_lock(&osb->osb_lock);
 	inode->i_generation = osb->s_next_generation++;
 	spin_unlock(&osb->osb_lock);
@@ -1186,8 +1186,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 bail:
 	if (status)

fs/ocfs2/ocfs2.h

@@ -50,6 +50,8 @@
 
 #include "reservations.h"
 
+#include "filecheck.h"
+
 /* Caching of metadata buffers */
 
 /* Most user visible OCFS2 inodes will have very few pieces of
@@ -472,6 +474,12 @@ struct ocfs2_super
 	 * workqueue and schedule on our own.
 	 */
 	struct workqueue_struct *ocfs2_wq;
+
+	/* sysfs directory per partition */
+	struct kset *osb_dev_kset;
+
+	/* file check related stuff */
+	struct ocfs2_filecheck_sysfs_entry osb_fc_ent;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)

fs/ocfs2/ocfs2_trace.h

@@ -1311,11 +1311,11 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_release);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_sync_file);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_write_iter);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter);
 
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
 
@@ -1467,7 +1467,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write,
 		  __entry->saved_pos, __entry->count, __entry->wait)
 );
 
-DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
+DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret);
 
 /* End of trace events for fs/ocfs2/file.c. */
 

fs/ocfs2/refcounttree.c

@@ -573,7 +573,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
 	BUG_ON(ocfs2_is_refcount_inode(inode));
 
 	trace_ocfs2_create_refcount_tree(
-		(unsigned long long)OCFS2_I(inode)->ip_blkno);
+		(unsigned long long)oi->ip_blkno);
 
 	ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac);
 	if (ret) {
@@ -3359,7 +3359,7 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	unsigned int ext_flags;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
+	if (!ocfs2_refcount_tree(osb)) {
 		return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
 				   inode->i_ino);
 	}
@@ -3707,7 +3707,7 @@ int ocfs2_add_refcount_flag(struct inode *inode,
 	trace_ocfs2_add_refcount_flag(ref_blocks, credits);
 
 	if (ref_blocks) {
-		ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_reserve_new_metadata_blocks(osb,
 							ref_blocks, &meta_ac);
 		if (ret) {
 			mlog_errno(ret);
@@ -4766,8 +4766,8 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 		*bh2 = *bh1;
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 	return 0;
 

fs/ocfs2/suballoc.c

@@ -79,8 +79,6 @@ static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
 	return ocfs2_which_suballoc_group(res->sr_blkno, res->sr_bit_offset);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
 static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
 static int ocfs2_block_group_fill(handle_t *handle,
 				  struct inode *alloc_inode,
@@ -387,7 +385,7 @@ static int ocfs2_block_group_fill(handle_t *handle,
 
 	memset(bg, 0, sb->s_blocksize);
 	strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE);
-	bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+	bg->bg_generation = cpu_to_le32(osb->fs_generation);
 	bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1,
 						osb->s_feature_incompat));
 	bg->bg_chain = cpu_to_le16(my_chain);
@@ -1521,7 +1519,7 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 				OCFS2_I(inode)->ip_clusters, max_bits);
 		}
 
-		ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_block_group_find_clear_bits(osb,
 							group_bh, bits_wanted,
 							max_bits, res);
 		if (ret)
@@ -2626,53 +2624,6 @@ int ocfs2_release_clusters(handle_t *handle,
 				    _ocfs2_clear_bit);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg)
-{
-	printk("Block Group:\n");
-	printk("bg_signature:       %s\n", bg->bg_signature);
-	printk("bg_size:            %u\n", bg->bg_size);
-	printk("bg_bits:            %u\n", bg->bg_bits);
-	printk("bg_free_bits_count: %u\n", bg->bg_free_bits_count);
-	printk("bg_chain:           %u\n", bg->bg_chain);
-	printk("bg_generation:      %u\n", le32_to_cpu(bg->bg_generation));
-	printk("bg_next_group:      %llu\n",
-	       (unsigned long long)bg->bg_next_group);
-	printk("bg_parent_dinode:   %llu\n",
-	       (unsigned long long)bg->bg_parent_dinode);
-	printk("bg_blkno:           %llu\n",
-	       (unsigned long long)bg->bg_blkno);
-}
-
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe)
-{
-	int i;
-
-	printk("Suballoc Inode %llu:\n", (unsigned long long)fe->i_blkno);
-	printk("i_signature:                  %s\n", fe->i_signature);
-	printk("i_size:                       %llu\n",
-	       (unsigned long long)fe->i_size);
-	printk("i_clusters:                   %u\n", fe->i_clusters);
-	printk("i_generation:                 %u\n",
-	       le32_to_cpu(fe->i_generation));
-	printk("id1.bitmap1.i_used:           %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_used));
-	printk("id1.bitmap1.i_total:          %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_total));
-	printk("id2.i_chain.cl_cpg:           %u\n", fe->id2.i_chain.cl_cpg);
-	printk("id2.i_chain.cl_bpc:           %u\n", fe->id2.i_chain.cl_bpc);
-	printk("id2.i_chain.cl_count:         %u\n", fe->id2.i_chain.cl_count);
-	printk("id2.i_chain.cl_next_free_rec: %u\n",
-	       fe->id2.i_chain.cl_next_free_rec);
-	for(i = 0; i < fe->id2.i_chain.cl_next_free_rec; i++) {
-		printk("fe->id2.i_chain.cl_recs[%d].c_free:  %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_free);
-		printk("fe->id2.i_chain.cl_recs[%d].c_total: %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_total);
-		printk("fe->id2.i_chain.cl_recs[%d].c_blkno: %llu\n", i,
-		       (unsigned long long)fe->id2.i_chain.cl_recs[i].c_blkno);
-	}
-}
-
 /*
  * For a given allocation, determine which allocators will need to be
  * accessed, and lock them, reserving the appropriate number of bits.

fs/ocfs2/super.c

@@ -423,10 +423,10 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait)
 		ocfs2_schedule_truncate_log_flush(osb, 0);
 	}
 
-	if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
+	if (jbd2_journal_start_commit(osb->journal->j_journal,
 				      &target)) {
 		if (wait)
-			jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
+			jbd2_log_wait_commit(osb->journal->j_journal,
 					     target);
 	}
 	return 0;
@@ -1161,6 +1161,23 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	ocfs2_complete_mount_recovery(osb);
 
+	osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL,
+						&ocfs2_kset->kobj);
+	if (!osb->osb_dev_kset) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id);
+		goto read_super_error;
+	}
+
+	/* Create filecheck sysfs related directories/files at
+	 * /sys/fs/ocfs2/<devname>/filecheck */
+	if (ocfs2_filecheck_create_sysfs(osb)) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create filecheck sysfs directory at "
+			"/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id);
+		goto read_super_error;
+	}
+
 	if (ocfs2_mount_local(osb))
 		snprintf(nodestr, sizeof(nodestr), "local");
 	else
@@ -1199,9 +1216,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
-	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
-	ocfs2_filecheck_create_sysfs(sb);
-
 	return status;
 
 read_super_error:
@@ -1653,7 +1667,6 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
-	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1768,12 +1781,9 @@ static int ocfs2_initialize_mem_caches(void)
 					NULL);
 	if (!ocfs2_inode_cachep || !ocfs2_dquot_cachep ||
 	    !ocfs2_qf_chunk_cachep) {
-		if (ocfs2_inode_cachep)
-			kmem_cache_destroy(ocfs2_inode_cachep);
-		if (ocfs2_dquot_cachep)
-			kmem_cache_destroy(ocfs2_dquot_cachep);
-		if (ocfs2_qf_chunk_cachep)
-			kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+		kmem_cache_destroy(ocfs2_inode_cachep);
+		kmem_cache_destroy(ocfs2_dquot_cachep);
+		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 		return -ENOMEM;
 	}
 
@@ -1787,16 +1797,13 @@ static void ocfs2_free_mem_caches(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	if (ocfs2_inode_cachep)
-		kmem_cache_destroy(ocfs2_inode_cachep);
+	kmem_cache_destroy(ocfs2_inode_cachep);
 	ocfs2_inode_cachep = NULL;
 
-	if (ocfs2_dquot_cachep)
-		kmem_cache_destroy(ocfs2_dquot_cachep);
+	kmem_cache_destroy(ocfs2_dquot_cachep);
 	ocfs2_dquot_cachep = NULL;
 
-	if (ocfs2_qf_chunk_cachep)
-		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+	kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 	ocfs2_qf_chunk_cachep = NULL;
 }
 
@@ -1899,6 +1906,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	osb = OCFS2_SB(sb);
 	BUG_ON(!osb);
 
+	/* Remove file check sysfs related directores/files,
+	 * and wait for the pending file check operations */
+	ocfs2_filecheck_remove_sysfs(osb);
+
+	kset_unregister(osb->osb_dev_kset);
+
 	debugfs_remove(osb->osb_ctxt);
 
 	/* Orphan scan should be stopped as early as possible */

fs/ocfs2/uptodate.c

@@ -633,6 +633,5 @@ int __init init_ocfs2_uptodate_cache(void)
 
 void exit_ocfs2_uptodate_cache(void)
 {
-	if (ocfs2_uptodate_cachep)
-		kmem_cache_destroy(ocfs2_uptodate_cachep);
+	kmem_cache_destroy(ocfs2_uptodate_cachep);
 }

fs/ocfs2/xattr.c

@@ -3564,7 +3564,7 @@ int ocfs2_xattr_set(struct inode *inode,
 		.not_found = -ENODATA,
 	};
 
-	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+	if (!ocfs2_supports_xattr(osb))
 		return -EOPNOTSUPP;
 
 	/*

include/linux/fault-inject.h

@@ -64,10 +64,11 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name,
 
 struct kmem_cache;
 
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #ifdef CONFIG_FAILSLAB
-extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags);
+extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #else
-static inline bool should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
 	return false;
 }

include/linux/kasan.h

@@ -43,7 +43,7 @@ void kasan_unpoison_stack_above_sp_to(const void *watermark);
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
 
-void kasan_cache_create(struct kmem_cache *cache, size_t *size,
+void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 			slab_flags_t *flags);
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
@@ -92,7 +92,7 @@ static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
 
 static inline void kasan_cache_create(struct kmem_cache *cache,
-				      size_t *size,
+				      unsigned int *size,
 				      slab_flags_t *flags) {}
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}

include/linux/list_lru.h

@@ -32,6 +32,7 @@ struct list_lru_one {
 };
 
 struct list_lru_memcg {
+	struct rcu_head		rcu;
 	/* array of per cgroup lists, indexed by memcg_cache_id */
 	struct list_lru_one	*lru[0];
 };
@@ -43,7 +44,7 @@ struct list_lru_node {
 	struct list_lru_one	lru;
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
-	struct list_lru_memcg	*memcg_lrus;
+	struct list_lru_memcg	__rcu *memcg_lrus;
 #endif
 	long nr_items;
 } ____cacheline_aligned_in_smp;

include/linux/memblock.h

@@ -416,21 +416,11 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end)
 {
 }
 #endif
-
-extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-		phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
 	return 0;
 }
-
-static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-		phys_addr_t end_addr)
-{
-	return 0;
-}
-
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */

include/linux/memory.h

@@ -33,6 +33,7 @@ struct memory_block {
 	void *hw;			/* optional pointer to fw/hw data */
 	int (*phys_callback)(struct memory_block *);
 	struct device dev;
+	int nid;			/* NID for this memory block */
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -109,7 +110,7 @@ extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
-extern int register_new_memory(int, struct mem_section *);
+int hotplug_memory_register(int nid, struct mem_section *section);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern int unregister_memory_section(struct mem_section *);
 #endif

include/linux/memory_hotplug.h

@@ -51,24 +51,6 @@ enum {
 	MMOP_ONLINE_MOVABLE,
 };
 
-/*
- * pgdat resizing functions
- */
-static inline
-void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
-{
-	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
-}
-static inline
-void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
-{
-	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
-}
-static inline
-void pgdat_resize_init(struct pglist_data *pgdat)
-{
-	spin_lock_init(&pgdat->node_size_lock);
-}
 /*
  * Zone resizing functions
  *
@@ -246,13 +228,6 @@ extern void clear_zone_contiguous(struct zone *zone);
 	___page;				\
  })
 
-/*
- * Stub functions for when hotplug is off
- */
-static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
-static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
-static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
-
 static inline unsigned zone_span_seqbegin(struct zone *zone)
 {
 	return 0;
@@ -293,6 +268,34 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
+/*
+ * pgdat resizing functions
+ */
+static inline
+void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_init(struct pglist_data *pgdat)
+{
+	spin_lock_init(&pgdat->node_size_lock);
+}
+#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
+/*
+ * Stub functions for when hotplug is off
+ */
+static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
+#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);

include/linux/migrate.h

@@ -25,7 +25,7 @@ enum migrate_reason {
 	MR_SYSCALL,		/* also applies to cpusets */
 	MR_MEMPOLICY_MBIND,
 	MR_NUMA_MISPLACED,
-	MR_CMA,
+	MR_CONTIG_RANGE,
 	MR_TYPES
 };
 

include/linux/mm.h

@@ -386,17 +386,19 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*split)(struct vm_area_struct * area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct * area);
-	int (*fault)(struct vm_fault *vmf);
-	int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
+	vm_fault_t (*fault)(struct vm_fault *vmf);
+	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
+			enum page_entry_size pe_size);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
+	unsigned long (*pagesize)(struct vm_area_struct * area);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
-	int (*page_mkwrite)(struct vm_fault *vmf);
+	vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
 
 	/* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
-	int (*pfn_mkwrite)(struct vm_fault *vmf);
+	vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
 
 	/* called by access_process_vm when get_user_pages() fails, typically
 	 * for use by special VMAs that can switch between memory and hardware
@@ -903,7 +905,9 @@ extern int page_to_nid(const struct page *page);
 #else
 static inline int page_to_nid(const struct page *page)
 {
-	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
+	struct page *p = (struct page *)page;
+
+	return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
 }
 #endif
 
@@ -1152,6 +1156,7 @@ static inline pgoff_t page_index(struct page *page)
 
 bool page_mapped(struct page *page);
 struct address_space *page_mapping(struct page *page);
+struct address_space *page_mapping_file(struct page *page);
 
 /*
  * Return true only if the page has been allocated with
@@ -2420,6 +2425,44 @@ int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
+static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
+				unsigned long addr, struct page *page)
+{
+	int err = vm_insert_page(vma, addr, page);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma,
+				unsigned long addr, pfn_t pfn)
+{
+	int err = vm_insert_mixed(vma, addr, pfn);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long pfn)
+{
+	int err = vm_insert_pfn(vma, addr, pfn);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
 
 struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int foll_flags,
@@ -2589,7 +2632,7 @@ extern int get_hwpoison_page(struct page *page);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
-extern atomic_long_t num_poisoned_pages;
+extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(struct page *page, int flags);
 
 
@@ -2611,6 +2654,7 @@ enum mf_action_page_type {
 	MF_MSG_POISONED_HUGE,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
+	MF_MSG_NON_PMD_HUGE,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,

include/linux/mm_types.h

@@ -22,6 +22,8 @@
 #endif
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
+typedef int vm_fault_t;
+
 struct address_space;
 struct mem_cgroup;
 struct hmm;

include/linux/mmdebug.h

@@ -37,10 +37,10 @@ void dump_mm(const struct mm_struct *mm);
 			BUG();						\
 		}							\
 	} while (0)
-#define VM_WARN_ON(cond) WARN_ON(cond)
-#define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
-#define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
-#define VM_WARN(cond, format...) WARN(cond, format)
+#define VM_WARN_ON(cond) (void)WARN_ON(cond)
+#define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+#define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
+#define VM_WARN(cond, format...) (void)WARN(cond, format)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)

include/linux/mmzone.h

@@ -633,14 +633,15 @@ typedef struct pglist_data {
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
 #endif
-#ifdef CONFIG_MEMORY_HOTPLUG
+#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 	/*
 	 * Must be held any time you expect node_start_pfn, node_present_pages
 	 * or node_spanned_pages stay constant.  Holding this will also
 	 * guarantee that any pfn_valid() stays that way.
 	 *
 	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
-	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG.
+	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
+	 * or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
 	 *
 	 * Nests above zone->lock and zone->span_seqlock
 	 */
@@ -775,7 +776,8 @@ static inline bool is_dev_zone(const struct zone *zone)
 #include <linux/memory_hotplug.h>
 
 void build_all_zonelists(pg_data_t *pgdat);
-void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
+void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
+		   enum zone_type classzone_idx);
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			 int classzone_idx, unsigned int alloc_flags,
 			 long free_pages);

include/linux/node.h

@@ -67,7 +67,7 @@ extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
-						int nid);
+						int nid, bool check_nid);
 extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 					   unsigned long phys_index);
 
@@ -97,7 +97,7 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	return 0;
 }
 static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
-							int nid)
+							int nid, bool check_nid)
 {
 	return 0;
 }

include/linux/page-flags.h

@@ -156,9 +156,18 @@ static __always_inline int PageCompound(struct page *page)
 	return test_bit(PG_head, &page->flags) || PageTail(page);
 }
 
+#define	PAGE_POISON_PATTERN	-1l
+static inline int PagePoisoned(const struct page *page)
+{
+	return page->flags == PAGE_POISON_PATTERN;
+}
+
 /*
  * Page flags policies wrt compound pages
  *
+ * PF_POISONED_CHECK
+ *     check if this struct page poisoned/uninitialized
+ *
  * PF_ANY:
  *     the page flag is relevant for small, head and tail pages.
  *
@@ -176,17 +185,20 @@ static __always_inline int PageCompound(struct page *page)
  * PF_NO_COMPOUND:
  *     the page flag is not relevant for compound pages.
  */
-#define PF_ANY(page, enforce)	page
-#define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_POISONED_CHECK(page) ({					\
+		VM_BUG_ON_PGFLAGS(PagePoisoned(page), page);		\
+		page; })
+#define PF_ANY(page, enforce)	PF_POISONED_CHECK(page)
+#define PF_HEAD(page, enforce)	PF_POISONED_CHECK(compound_head(page))
 #define PF_ONLY_HEAD(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(PageTail(page), page);		\
-		page;})
+		PF_POISONED_CHECK(page); })
 #define PF_NO_TAIL(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page);	\
-		compound_head(page);})
+		PF_POISONED_CHECK(compound_head(page)); })
 #define PF_NO_COMPOUND(page, enforce) ({				\
 		VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page);	\
-		page;})
+		PF_POISONED_CHECK(page); })
 
 /*
  * Macros to create function definitions for page flags

include/linux/page_ref.h

@@ -175,8 +175,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 	VM_BUG_ON_PAGE(page_count(page) != 0, page);
 	VM_BUG_ON(count == 0);
 
-	smp_mb();
-	atomic_set(&page->_refcount, count);
+	atomic_set_release(&page->_refcount, count);
 	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
 		__page_ref_unfreeze(page, count);
 }

include/linux/slab.h

@@ -125,7 +125,6 @@
 #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
 				(unsigned long)ZERO_SIZE_PTR)
 
-#include <linux/kmemleak.h>
 #include <linux/kasan.h>
 
 struct mem_cgroup;
@@ -137,12 +136,13 @@ bool slab_is_available(void);
 
 extern bool usercopy_fallback;
 
-struct kmem_cache *kmem_cache_create(const char *name, size_t size,
-			size_t align, slab_flags_t flags,
+struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
+			unsigned int align, slab_flags_t flags,
 			void (*ctor)(void *));
 struct kmem_cache *kmem_cache_create_usercopy(const char *name,
-			size_t size, size_t align, slab_flags_t flags,
-			size_t useroffset, size_t usersize,
+			unsigned int size, unsigned int align,
+			slab_flags_t flags,
+			unsigned int useroffset, unsigned int usersize,
 			void (*ctor)(void *));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
@@ -308,7 +308,7 @@ extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
  * 2 = 129 .. 192 bytes
  * n = 2^(n-1)+1 .. 2^n
  */
-static __always_inline int kmalloc_index(size_t size)
+static __always_inline unsigned int kmalloc_index(size_t size)
 {
 	if (!size)
 		return 0;
@@ -504,7 +504,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 			return kmalloc_large(size, flags);
 #ifndef CONFIG_SLOB
 		if (!(flags & GFP_DMA)) {
-			int index = kmalloc_index(size);
+			unsigned int index = kmalloc_index(size);
 
 			if (!index)
 				return ZERO_SIZE_PTR;
@@ -522,11 +522,11 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
  * return size or 0 if a kmalloc cache for that
  * size does not exist
  */
-static __always_inline int kmalloc_size(int n)
+static __always_inline unsigned int kmalloc_size(unsigned int n)
 {
 #ifndef CONFIG_SLOB
 	if (n > 2)
-		return 1 << n;
+		return 1U << n;
 
 	if (n == 1 && KMALLOC_MIN_SIZE <= 32)
 		return 96;
@@ -542,7 +542,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 #ifndef CONFIG_SLOB
 	if (__builtin_constant_p(size) &&
 		size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) {
-		int i = kmalloc_index(size);
+		unsigned int i = kmalloc_index(size);
 
 		if (!i)
 			return ZERO_SIZE_PTR;

include/linux/slab_def.h

@@ -85,8 +85,8 @@ struct kmem_cache {
 	unsigned int *random_seq;
 #endif
 
-	size_t useroffset;		/* Usercopy region offset */
-	size_t usersize;		/* Usercopy region size */
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
 
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };

include/linux/slub_def.h

@@ -73,7 +73,7 @@ struct kmem_cache_cpu {
  * given order would contain.
  */
 struct kmem_cache_order_objects {
-	unsigned long x;
+	unsigned int x;
 };
 
 /*
@@ -84,11 +84,12 @@ struct kmem_cache {
 	/* Used for retriving partial slabs etc */
 	slab_flags_t flags;
 	unsigned long min_partial;
-	int size;		/* The size of an object including meta data */
-	int object_size;	/* The size of an object without meta data */
-	int offset;		/* Free pointer offset. */
+	unsigned int size;	/* The size of an object including meta data */
+	unsigned int object_size;/* The size of an object without meta data */
+	unsigned int offset;	/* Free pointer offset. */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
-	int cpu_partial;	/* Number of per cpu partial objects to keep around */
+	/* Number of per cpu partial objects to keep around */
+	unsigned int cpu_partial;
 #endif
 	struct kmem_cache_order_objects oo;
 
@@ -98,10 +99,10 @@ struct kmem_cache {
 	gfp_t allocflags;	/* gfp flags to use on each alloc */
 	int refcount;		/* Refcount for slab cache destroy */
 	void (*ctor)(void *);
-	int inuse;		/* Offset to metadata */
-	int align;		/* Alignment */
-	int reserved;		/* Reserved bytes at the end of slabs */
-	int red_left_pad;	/* Left redzone padding size */
+	unsigned int inuse;		/* Offset to metadata */
+	unsigned int align;		/* Alignment */
+	unsigned int reserved;		/* Reserved bytes at the end of slabs */
+	unsigned int red_left_pad;	/* Left redzone padding size */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
 #ifdef CONFIG_SYSFS
@@ -110,7 +111,8 @@ struct kmem_cache {
 #endif
 #ifdef CONFIG_MEMCG
 	struct memcg_cache_params memcg_params;
-	int max_attr_size; /* for propagation, maximum size of a stored attr */
+	/* for propagation, maximum size of a stored attr */
+	unsigned int max_attr_size;
 #ifdef CONFIG_SYSFS
 	struct kset *memcg_kset;
 #endif
@@ -124,7 +126,7 @@ struct kmem_cache {
 	/*
 	 * Defragmentation by allocating from a remote node.
 	 */
-	int remote_node_defrag_ratio;
+	unsigned int remote_node_defrag_ratio;
 #endif
 
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
@@ -135,8 +137,8 @@ struct kmem_cache {
 	struct kasan_cache kasan_info;
 #endif
 
-	size_t useroffset;		/* Usercopy region offset */
-	size_t usersize;		/* Usercopy region size */
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
 
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };

include/linux/swap.h

@@ -400,7 +400,6 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 #define SWAP_ADDRESS_SPACE_SHIFT	14
 #define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
 extern struct address_space *swapper_spaces[];
-extern bool swap_vma_readahead;
 #define swap_address_space(entry)			    \
 	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
 		>> SWAP_ADDRESS_SPACE_SHIFT])
@@ -422,14 +421,10 @@ extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated);
-extern struct page *swapin_readahead(swp_entry_t, gfp_t,
-			struct vm_area_struct *vma, unsigned long addr);
-
-extern struct page *swap_readahead_detect(struct vm_fault *vmf,
-					  struct vma_swap_readahead *swap_ra);
-extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
-					   struct vm_fault *vmf,
-					   struct vma_swap_readahead *swap_ra);
+extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
+				struct vm_fault *vmf);
+extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
+				struct vm_fault *vmf);
 
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
@@ -437,11 +432,6 @@ extern long total_swap_pages;
 extern atomic_t nr_rotate_swap;
 extern bool has_usable_swap(void);
 
-static inline bool swap_use_vma_readahead(void)
-{
-	return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap);
-}
-
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
 {
@@ -537,26 +527,14 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp)
 {
 }
 
-static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
-			struct vm_area_struct *vma, unsigned long addr)
+static inline struct page *swap_cluster_readahead(swp_entry_t entry,
+				gfp_t gfp_mask, struct vm_fault *vmf)
 {
 	return NULL;
 }
 
-static inline bool swap_use_vma_readahead(void)
-{
-	return false;
-}
-
-static inline struct page *swap_readahead_detect(
-	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
-{
-	return NULL;
-}
-
-static inline struct page *do_swap_page_readahead(
-	swp_entry_t fentry, gfp_t gfp_mask,
-	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
+static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
+			struct vm_fault *vmf)
 {
 	return NULL;
 }

include/linux/zsmalloc.h

@@ -47,6 +47,8 @@ void zs_destroy_pool(struct zs_pool *pool);
 unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags);
 void zs_free(struct zs_pool *pool, unsigned long obj);
 
+size_t zs_huge_class_size(struct zs_pool *pool);
+
 void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 			enum zs_mapmode mm);
 void zs_unmap_object(struct zs_pool *pool, unsigned long handle);

include/net/sock.h

@@ -1114,8 +1114,8 @@ struct proto {
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
 	slab_flags_t		slab_flags;
-	size_t			useroffset;	/* Usercopy region offset */
-	size_t			usersize;	/* Usercopy region size */
+	unsigned int		useroffset;	/* Usercopy region offset */
+	unsigned int		usersize;	/* Usercopy region size */
 
 	struct percpu_counter	*orphan_count;
 

include/trace/events/migrate.h

@@ -20,7 +20,7 @@
 	EM( MR_SYSCALL,		"syscall_or_cpuset")		\
 	EM( MR_MEMPOLICY_MBIND,	"mempolicy_mbind")		\
 	EM( MR_NUMA_MISPLACED,	"numa_misplaced")		\
-	EMe(MR_CMA,		"cma")
+	EMe(MR_CONTIG_RANGE,	"contig_range")
 
 /*
  * First define the enums in the above macros to be exported to userspace

include/trace/events/vmscan.h

@@ -78,26 +78,29 @@ TRACE_EVENT(mm_vmscan_kswapd_wake,
 
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
-	TP_PROTO(int nid, int zid, int order),
+	TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags),
 
-	TP_ARGS(nid, zid, order),
+	TP_ARGS(nid, zid, order, gfp_flags),
 
 	TP_STRUCT__entry(
-		__field(	int,		nid	)
-		__field(	int,		zid	)
-		__field(	int,		order	)
+		__field(	int,	nid		)
+		__field(	int,	zid		)
+		__field(	int,	order		)
+		__field(	gfp_t,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->nid		= nid;
 		__entry->zid		= zid;
 		__entry->order		= order;
+		__entry->gfp_flags	= gfp_flags;
 	),
 
-	TP_printk("nid=%d zid=%d order=%d",
+	TP_printk("nid=%d zid=%d order=%d gfp_flags=%s",
 		__entry->nid,
 		__entry->zid,
-		__entry->order)
+		__entry->order,
+		show_gfp_flags(__entry->gfp_flags))
 );
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,

kernel/fork.c

@@ -595,6 +595,8 @@ static void check_mm(struct mm_struct *mm)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
+	WARN_ON_ONCE(mm == current->mm);
+	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	hmm_mm_destroy(mm);