Merge branch 'akpm' (patchbomb from Andrew Morton)

Merge incoming from Andrew Morton:
 - Various misc things.
 - arch/sh updates.
 - Part of ocfs2.  Review is slow.
 - Slab updates.
 - Most of -mm.
 - printk updates.
 - lib/ updates.
 - checkpatch updates.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (226 commits)
  checkpatch: update $declaration_macros, add uninitialized_var
  checkpatch: warn on missing spaces in broken up quoted
  checkpatch: fix false positives for --strict "space after cast" test
  checkpatch: fix false positive MISSING_BREAK warnings with --file
  checkpatch: add test for native c90 types in unusual order
  checkpatch: add signed generic types
  checkpatch: add short int to c variable types
  checkpatch: add for_each tests to indentation and brace tests
  checkpatch: fix brace style misuses of else and while
  checkpatch: add --fix option for a couple OPEN_BRACE misuses
  checkpatch: use the correct indentation for which()
  checkpatch: add fix_insert_line and fix_delete_line helpers
  checkpatch: add ability to insert and delete lines to patch/file
  checkpatch: add an index variable for fixed lines
  checkpatch: warn on break after goto or return with same tab indentation
  checkpatch: emit a warning on file add/move/delete
  checkpatch: add test for commit id formatting style in commit log
  checkpatch: emit fewer kmalloc_array/kcalloc conversion warnings
  checkpatch: improve "no space after cast" test
  checkpatch: allow multiple const * types
  ...

Documentation/RCU/whatisRCU.txt

@@ -818,7 +818,7 @@ RCU pointer/list update:
 	list_add_tail_rcu
 	list_del_rcu
 	list_replace_rcu
-	hlist_add_after_rcu
+	hlist_add_behind_rcu
 	hlist_add_before_rcu
 	hlist_add_head_rcu
 	hlist_del_rcu

Documentation/kernel-parameters.txt

@@ -1716,8 +1716,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			7 (KERN_DEBUG)		debug-level messages
 
 	log_buf_len=n[KMG]	Sets the size of the printk ring buffer,
-			in bytes.  n must be a power of two.  The default
-			size is set in the kernel config file.
+			in bytes.  n must be a power of two and greater
+			than the minimal size. The minimal size is defined
+			by LOG_BUF_SHIFT kernel config parameter. There is
+			also CONFIG_LOG_CPU_MAX_BUF_SHIFT config parameter
+			that allows to increase the default size depending on
+			the number of CPUs. See init/Kconfig for more details.
 
 	logo.nologo	[FB] Disables display of the built-in Linux logo.
 			This may be used to provide more screen space for

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

@@ -47,6 +47,10 @@ use constant HIGH_KSWAPD_REWAKEUP		=> 21;
 use constant HIGH_NR_SCANNED			=> 22;
 use constant HIGH_NR_TAKEN			=> 23;
 use constant HIGH_NR_RECLAIMED			=> 24;
+use constant HIGH_NR_FILE_SCANNED		=> 25;
+use constant HIGH_NR_ANON_SCANNED		=> 26;
+use constant HIGH_NR_FILE_RECLAIMED		=> 27;
+use constant HIGH_NR_ANON_RECLAIMED		=> 28;
 
 my %perprocesspid;
 my %perprocess;
@@ -56,14 +60,18 @@ my $opt_read_procstat;
 
 my $total_wakeup_kswapd;
 my ($total_direct_reclaim, $total_direct_nr_scanned);
+my ($total_direct_nr_file_scanned, $total_direct_nr_anon_scanned);
 my ($total_direct_latency, $total_kswapd_latency);
 my ($total_direct_nr_reclaimed);
+my ($total_direct_nr_file_reclaimed, $total_direct_nr_anon_reclaimed);
 my ($total_direct_writepage_file_sync, $total_direct_writepage_file_async);
 my ($total_direct_writepage_anon_sync, $total_direct_writepage_anon_async);
 my ($total_kswapd_nr_scanned, $total_kswapd_wake);
+my ($total_kswapd_nr_file_scanned, $total_kswapd_nr_anon_scanned);
 my ($total_kswapd_writepage_file_sync, $total_kswapd_writepage_file_async);
 my ($total_kswapd_writepage_anon_sync, $total_kswapd_writepage_anon_async);
 my ($total_kswapd_nr_reclaimed);
+my ($total_kswapd_nr_file_reclaimed, $total_kswapd_nr_anon_reclaimed);
 
 # Catch sigint and exit on request
 my $sigint_report = 0;
@@ -374,6 +382,7 @@ EVENT_PROCESS:
 			}
 			my $isolate_mode = $1;
 			my $nr_scanned = $4;
+			my $file = $6;
 
 			# To closer match vmstat scanning statistics, only count isolate_both
 			# and isolate_inactive as scanning. isolate_active is rotation
@@ -382,6 +391,11 @@ EVENT_PROCESS:
 			# isolate_both     == 3
 			if ($isolate_mode != 2) {
 				$perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+				if ($file == 1) {
+					$perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED} += $nr_scanned;
+				} else {
+					$perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED} += $nr_scanned;
+				}
 			}
 		} elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
 			$details = $6;
@@ -391,8 +405,19 @@ EVENT_PROCESS:
 				print "         $regex_lru_shrink_inactive/o\n";
 				next;
 			}
+
 			my $nr_reclaimed = $4;
+			my $flags = $6;
+			my $file = 0;
+			if ($flags =~ /RECLAIM_WB_FILE/) {
+				$file = 1;
+			}
 			$perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED} += $nr_reclaimed;
+			if ($file) {
+				$perprocesspid{$process_pid}->{HIGH_NR_FILE_RECLAIMED} += $nr_reclaimed;
+			} else {
+				$perprocesspid{$process_pid}->{HIGH_NR_ANON_RECLAIMED} += $nr_reclaimed;
+			}
 		} elsif ($tracepoint eq "mm_vmscan_writepage") {
 			$details = $6;
 			if ($details !~ /$regex_writepage/o) {
@@ -493,7 +518,11 @@ sub dump_stats {
 		$total_direct_reclaim += $stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN};
 		$total_wakeup_kswapd += $stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
 		$total_direct_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+		$total_direct_nr_file_scanned += $stats{$process_pid}->{HIGH_NR_FILE_SCANNED};
+		$total_direct_nr_anon_scanned += $stats{$process_pid}->{HIGH_NR_ANON_SCANNED};
 		$total_direct_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED};
+		$total_direct_nr_file_reclaimed += $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED};
+		$total_direct_nr_anon_reclaimed += $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED};
 		$total_direct_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
 		$total_direct_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
 		$total_direct_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
@@ -513,7 +542,11 @@ sub dump_stats {
 			$stats{$process_pid}->{MM_VMSCAN_DIRECT_RECLAIM_BEGIN},
 			$stats{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD},
 			$stats{$process_pid}->{HIGH_NR_SCANNED},
+			$stats{$process_pid}->{HIGH_NR_FILE_SCANNED},
+			$stats{$process_pid}->{HIGH_NR_ANON_SCANNED},
 			$stats{$process_pid}->{HIGH_NR_RECLAIMED},
+			$stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED},
+			$stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED},
 			$stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
 			$stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC},
 			$this_reclaim_delay / 1000);
@@ -552,7 +585,11 @@ sub dump_stats {
 
 		$total_kswapd_wake += $stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE};
 		$total_kswapd_nr_scanned += $stats{$process_pid}->{HIGH_NR_SCANNED};
+		$total_kswapd_nr_file_scanned += $stats{$process_pid}->{HIGH_NR_FILE_SCANNED};
+		$total_kswapd_nr_anon_scanned += $stats{$process_pid}->{HIGH_NR_ANON_SCANNED};
 		$total_kswapd_nr_reclaimed += $stats{$process_pid}->{HIGH_NR_RECLAIMED};
+		$total_kswapd_nr_file_reclaimed += $stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED};
+		$total_kswapd_nr_anon_reclaimed += $stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED};
 		$total_kswapd_writepage_file_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
 		$total_kswapd_writepage_anon_sync += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
 		$total_kswapd_writepage_file_async += $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};
@@ -563,7 +600,11 @@ sub dump_stats {
 			$stats{$process_pid}->{MM_VMSCAN_KSWAPD_WAKE},
 			$stats{$process_pid}->{HIGH_KSWAPD_REWAKEUP},
 			$stats{$process_pid}->{HIGH_NR_SCANNED},
+			$stats{$process_pid}->{HIGH_NR_FILE_SCANNED},
+			$stats{$process_pid}->{HIGH_NR_ANON_SCANNED},
 			$stats{$process_pid}->{HIGH_NR_RECLAIMED},
+			$stats{$process_pid}->{HIGH_NR_FILE_RECLAIMED},
+			$stats{$process_pid}->{HIGH_NR_ANON_RECLAIMED},
 			$stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC},
 			$stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} + $stats{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_ASYNC});
 
@@ -594,7 +635,11 @@ sub dump_stats {
 	print "\nSummary\n";
 	print "Direct reclaims:     			$total_direct_reclaim\n";
 	print "Direct reclaim pages scanned:		$total_direct_nr_scanned\n";
+	print "Direct reclaim file pages scanned:	$total_direct_nr_file_scanned\n";
+	print "Direct reclaim anon pages scanned:	$total_direct_nr_anon_scanned\n";
 	print "Direct reclaim pages reclaimed:		$total_direct_nr_reclaimed\n";
+	print "Direct reclaim file pages reclaimed:	$total_direct_nr_file_reclaimed\n";
+	print "Direct reclaim anon pages reclaimed:	$total_direct_nr_anon_reclaimed\n";
 	print "Direct reclaim write file sync I/O:	$total_direct_writepage_file_sync\n";
 	print "Direct reclaim write anon sync I/O:	$total_direct_writepage_anon_sync\n";
 	print "Direct reclaim write file async I/O:	$total_direct_writepage_file_async\n";
@@ -604,7 +649,11 @@ sub dump_stats {
 	print "\n";
 	print "Kswapd wakeups:				$total_kswapd_wake\n";
 	print "Kswapd pages scanned:			$total_kswapd_nr_scanned\n";
+	print "Kswapd file pages scanned:		$total_kswapd_nr_file_scanned\n";
+	print "Kswapd anon pages scanned:		$total_kswapd_nr_anon_scanned\n";
 	print "Kswapd pages reclaimed:			$total_kswapd_nr_reclaimed\n";
+	print "Kswapd file pages reclaimed:		$total_kswapd_nr_file_reclaimed\n";
+	print "Kswapd anon pages reclaimed:		$total_kswapd_nr_anon_reclaimed\n";
 	print "Kswapd reclaim write file sync I/O:	$total_kswapd_writepage_file_sync\n";
 	print "Kswapd reclaim write anon sync I/O:	$total_kswapd_writepage_anon_sync\n";
 	print "Kswapd reclaim write file async I/O:	$total_kswapd_writepage_file_async\n";
@@ -629,7 +678,11 @@ sub aggregate_perprocesspid() {
 		$perprocess{$process}->{MM_VMSCAN_WAKEUP_KSWAPD} += $perprocesspid{$process_pid}->{MM_VMSCAN_WAKEUP_KSWAPD};
 		$perprocess{$process}->{HIGH_KSWAPD_REWAKEUP} += $perprocesspid{$process_pid}->{HIGH_KSWAPD_REWAKEUP};
 		$perprocess{$process}->{HIGH_NR_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_SCANNED};
+		$perprocess{$process}->{HIGH_NR_FILE_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_FILE_SCANNED};
+		$perprocess{$process}->{HIGH_NR_ANON_SCANNED} += $perprocesspid{$process_pid}->{HIGH_NR_ANON_SCANNED};
 		$perprocess{$process}->{HIGH_NR_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_RECLAIMED};
+		$perprocess{$process}->{HIGH_NR_FILE_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_FILE_RECLAIMED};
+		$perprocess{$process}->{HIGH_NR_ANON_RECLAIMED} += $perprocesspid{$process_pid}->{HIGH_NR_ANON_RECLAIMED};
 		$perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_SYNC};
 		$perprocess{$process}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_ANON_SYNC};
 		$perprocess{$process}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC} += $perprocesspid{$process_pid}->{MM_VMSCAN_WRITEPAGE_FILE_ASYNC};

Makefile

@@ -621,6 +621,9 @@ else
 KBUILD_CFLAGS	+= -O2
 endif
 
+# Tell gcc to never replace conditional load with a non-conditional one
+KBUILD_CFLAGS	+= $(call cc-option,--param=allow-store-data-races=0)
+
 ifdef CONFIG_READABLE_ASM
 # Disable optimizations that make assembler listings hard to read.
 # reorder blocks reorders the control in the function
@@ -636,6 +639,22 @@ KBUILD_CFLAGS += $(call cc-option,-Wframe-larger-than=${CONFIG_FRAME_WARN})
 endif
 
 # Handle stack protector mode.
+#
+# Since kbuild can potentially perform two passes (first with the old
+# .config values and then with updated .config values), we cannot error out
+# if a desired compiler option is unsupported. If we were to error, kbuild
+# could never get to the second pass and actually notice that we changed
+# the option to something that was supported.
+#
+# Additionally, we don't want to fallback and/or silently change which compiler
+# flags will be used, since that leads to producing kernels with different
+# security feature characteristics depending on the compiler used. ("But I
+# selected CC_STACKPROTECTOR_STRONG! Why did it build with _REGULAR?!")
+#
+# The middle ground is to warn here so that the failed option is obvious, but
+# to let the build fail with bad compiler flags so that we can't produce a
+# kernel when there is a CONFIG and compiler mismatch.
+#
 ifdef CONFIG_CC_STACKPROTECTOR_REGULAR
   stackp-flag := -fstack-protector
   ifeq ($(call cc-option, $(stackp-flag)),)

arch/arm/mm/dma-mapping.c

@@ -26,6 +26,7 @@
 #include <linux/io.h>
 #include <linux/vmalloc.h>
 #include <linux/sizes.h>
+#include <linux/cma.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>

arch/ia64/mm/init.c

@@ -631,7 +631,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	pgdat = NODE_DATA(nid);
 
-	zone = pgdat->node_zones + ZONE_NORMAL;
+	zone = pgdat->node_zones +
+		zone_for_memory(nid, start, size, ZONE_NORMAL);
 	ret = __add_pages(nid, zone, start_pfn, nr_pages);
 
 	if (ret)

arch/powerpc/kvm/Makefile

@@ -90,7 +90,6 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
-	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
 endif
 

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -37,8 +37,6 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
-#include "book3s_hv_cma.h"
-
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
@@ -64,10 +62,10 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	}
 
 	kvm->arch.hpt_cma_alloc = 0;
-	VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
 	page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
 	if (page) {
 		hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+		memset((void *)hpt, 0, (1 << order));
 		kvm->arch.hpt_cma_alloc = 1;
 	}
 

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -16,12 +16,14 @@
 #include <linux/init.h>
 #include <linux/memblock.h>
 #include <linux/sizes.h>
+#include <linux/cma.h>
 
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
-#include "book3s_hv_cma.h"
+#define KVM_CMA_CHUNK_ORDER	18
+
 /*
  * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
  * should be power of 2.
@@ -43,6 +45,8 @@ static unsigned long kvm_cma_resv_ratio = 5;
 unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT;	/* 128MB */
 EXPORT_SYMBOL_GPL(kvm_rma_pages);
 
+static struct cma *kvm_cma;
+
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
 static inline int lpcr_rmls(unsigned long rma_size)
@@ -97,7 +101,7 @@ struct kvm_rma_info *kvm_alloc_rma()
 	ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
 	if (!ri)
 		return NULL;
-	page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages);
+	page = cma_alloc(kvm_cma, kvm_rma_pages, get_order(kvm_rma_pages));
 	if (!page)
 		goto err_out;
 	atomic_set(&ri->use_count, 1);
@@ -112,7 +116,7 @@ EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 void kvm_release_rma(struct kvm_rma_info *ri)
 {
 	if (atomic_dec_and_test(&ri->use_count)) {
-		kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages);
+		cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages);
 		kfree(ri);
 	}
 }
@@ -131,16 +135,18 @@ struct page *kvm_alloc_hpt(unsigned long nr_pages)
 {
 	unsigned long align_pages = HPT_ALIGN_PAGES;
 
+	VM_BUG_ON(get_order(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+
 	/* Old CPUs require HPT aligned on a multiple of its size */
 	if (!cpu_has_feature(CPU_FTR_ARCH_206))
 		align_pages = nr_pages;
-	return kvm_alloc_cma(nr_pages, align_pages);
+	return cma_alloc(kvm_cma, nr_pages, get_order(align_pages));
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
 
 void kvm_release_hpt(struct page *page, unsigned long nr_pages)
 {
-	kvm_release_cma(page, nr_pages);
+	cma_release(kvm_cma, page, nr_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_release_hpt);
 
@@ -179,7 +185,8 @@ void __init kvm_cma_reserve(void)
 			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
 
 		align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
-		kvm_cma_declare_contiguous(selected_size, align_size);
+		cma_declare_contiguous(0, selected_size, 0, align_size,
+			KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
 	}
 }
 

arch/powerpc/kvm/book3s_hv_cma.c

@@ -1,240 +0,0 @@
-/*
- * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
- * for DMA mapping framework
- *
- * Copyright IBM Corporation, 2013
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License or (at your optional) any later version of the license.
- *
- */
-#define pr_fmt(fmt) "kvm_cma: " fmt
-
-#ifdef CONFIG_CMA_DEBUG
-#ifndef DEBUG
-#  define DEBUG
-#endif
-#endif
-
-#include <linux/memblock.h>
-#include <linux/mutex.h>
-#include <linux/sizes.h>
-#include <linux/slab.h>
-
-#include "book3s_hv_cma.h"
-
-struct kvm_cma {
-	unsigned long	base_pfn;
-	unsigned long	count;
-	unsigned long	*bitmap;
-};
-
-static DEFINE_MUTEX(kvm_cma_mutex);
-static struct kvm_cma kvm_cma_area;
-
-/**
- * kvm_cma_declare_contiguous() - reserve area for contiguous memory handling
- *			          for kvm hash pagetable
- * @size:  Size of the reserved memory.
- * @alignment:  Alignment for the contiguous memory area
- *
- * This function reserves memory for kvm cma area. It should be
- * called by arch code when early allocator (memblock or bootmem)
- * is still activate.
- */
-long __init kvm_cma_declare_contiguous(phys_addr_t size, phys_addr_t alignment)
-{
-	long base_pfn;
-	phys_addr_t addr;
-	struct kvm_cma *cma = &kvm_cma_area;
-
-	pr_debug("%s(size %lx)\n", __func__, (unsigned long)size);
-
-	if (!size)
-		return -EINVAL;
-	/*
-	 * Sanitise input arguments.
-	 * We should be pageblock aligned for CMA.
-	 */
-	alignment = max(alignment, (phys_addr_t)(PAGE_SIZE << pageblock_order));
-	size = ALIGN(size, alignment);
-	/*
-	 * Reserve memory
-	 * Use __memblock_alloc_base() since
-	 * memblock_alloc_base() panic()s.
-	 */
-	addr = __memblock_alloc_base(size, alignment, 0);
-	if (!addr) {
-		base_pfn = -ENOMEM;
-		goto err;
-	} else
-		base_pfn = PFN_DOWN(addr);
-
-	/*
-	 * Each reserved area must be initialised later, when more kernel
-	 * subsystems (like slab allocator) are available.
-	 */
-	cma->base_pfn = base_pfn;
-	cma->count    = size >> PAGE_SHIFT;
-	pr_info("CMA: reserved %ld MiB\n", (unsigned long)size / SZ_1M);
-	return 0;
-err:
-	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
-	return base_pfn;
-}
-
-/**
- * kvm_alloc_cma() - allocate pages from contiguous area
- * @nr_pages: Requested number of pages.
- * @align_pages: Requested alignment in number of pages
- *
- * This function allocates memory buffer for hash pagetable.
- */
-struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
-{
-	int ret;
-	struct page *page = NULL;
-	struct kvm_cma *cma = &kvm_cma_area;
-	unsigned long chunk_count, nr_chunk;
-	unsigned long mask, pfn, pageno, start = 0;
-
-
-	if (!cma || !cma->count)
-		return NULL;
-
-	pr_debug("%s(cma %p, count %lu, align pages %lu)\n", __func__,
-		 (void *)cma, nr_pages, align_pages);
-
-	if (!nr_pages)
-		return NULL;
-	/*
-	 * align mask with chunk size. The bit tracks pages in chunk size
-	 */
-	VM_BUG_ON(!is_power_of_2(align_pages));
-	mask = (align_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)) - 1;
-	BUILD_BUG_ON(PAGE_SHIFT > KVM_CMA_CHUNK_ORDER);
-
-	chunk_count = cma->count >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
-	nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
-
-	mutex_lock(&kvm_cma_mutex);
-	for (;;) {
-		pageno = bitmap_find_next_zero_area(cma->bitmap, chunk_count,
-						    start, nr_chunk, mask);
-		if (pageno >= chunk_count)
-			break;
-
-		pfn = cma->base_pfn + (pageno << (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT));
-		ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA);
-		if (ret == 0) {
-			bitmap_set(cma->bitmap, pageno, nr_chunk);
-			page = pfn_to_page(pfn);
-			memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT);
-			break;
-		} else if (ret != -EBUSY) {
-			break;
-		}
-		pr_debug("%s(): memory range at %p is busy, retrying\n",
-			 __func__, pfn_to_page(pfn));
-		/* try again with a bit different memory target */
-		start = pageno + mask + 1;
-	}
-	mutex_unlock(&kvm_cma_mutex);
-	pr_debug("%s(): returned %p\n", __func__, page);
-	return page;
-}
-
-/**
- * kvm_release_cma() - release allocated pages for hash pagetable
- * @pages: Allocated pages.
- * @nr_pages: Number of allocated pages.
- *
- * This function releases memory allocated by kvm_alloc_cma().
- * It returns false when provided pages do not belong to contiguous area and
- * true otherwise.
- */
-bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
-{
-	unsigned long pfn;
-	unsigned long nr_chunk;
-	struct kvm_cma *cma = &kvm_cma_area;
-
-	if (!cma || !pages)
-		return false;
-
-	pr_debug("%s(page %p count %lu)\n", __func__, (void *)pages, nr_pages);
-
-	pfn = page_to_pfn(pages);
-
-	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
-		return false;
-
-	VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count);
-	nr_chunk = nr_pages >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
-
-	mutex_lock(&kvm_cma_mutex);
-	bitmap_clear(cma->bitmap,
-		     (pfn - cma->base_pfn) >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT),
-		     nr_chunk);
-	free_contig_range(pfn, nr_pages);
-	mutex_unlock(&kvm_cma_mutex);
-
-	return true;
-}
-
-static int __init kvm_cma_activate_area(unsigned long base_pfn,
-					unsigned long count)
-{
-	unsigned long pfn = base_pfn;
-	unsigned i = count >> pageblock_order;
-	struct zone *zone;
-
-	WARN_ON_ONCE(!pfn_valid(pfn));
-	zone = page_zone(pfn_to_page(pfn));
-	do {
-		unsigned j;
-		base_pfn = pfn;
-		for (j = pageblock_nr_pages; j; --j, pfn++) {
-			WARN_ON_ONCE(!pfn_valid(pfn));
-			/*
-			 * alloc_contig_range requires the pfn range
-			 * specified to be in the same zone. Make this
-			 * simple by forcing the entire CMA resv range
-			 * to be in the same zone.
-			 */
-			if (page_zone(pfn_to_page(pfn)) != zone)
-				return -EINVAL;
-		}
-		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
-	} while (--i);
-	return 0;
-}
-
-static int __init kvm_cma_init_reserved_areas(void)
-{
-	int bitmap_size, ret;
-	unsigned long chunk_count;
-	struct kvm_cma *cma = &kvm_cma_area;
-
-	pr_debug("%s()\n", __func__);
-	if (!cma->count)
-		return 0;
-	chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
-	bitmap_size = BITS_TO_LONGS(chunk_count) * sizeof(long);
-	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!cma->bitmap)
-		return -ENOMEM;
-
-	ret = kvm_cma_activate_area(cma->base_pfn, cma->count);
-	if (ret)
-		goto error;
-	return 0;
-
-error:
-	kfree(cma->bitmap);
-	return ret;
-}
-core_initcall(kvm_cma_init_reserved_areas);

arch/powerpc/kvm/book3s_hv_cma.h

@@ -1,27 +0,0 @@
-/*
- * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
- * for DMA mapping framework
- *
- * Copyright IBM Corporation, 2013
- * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License or (at your optional) any later version of the license.
- *
- */
-
-#ifndef __POWERPC_KVM_CMA_ALLOC_H__
-#define __POWERPC_KVM_CMA_ALLOC_H__
-/*
- * Both RMA and Hash page allocation will be multiple of 256K.
- */
-#define KVM_CMA_CHUNK_ORDER	18
-
-extern struct page *kvm_alloc_cma(unsigned long nr_pages,
-				  unsigned long align_pages);
-extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages);
-extern long kvm_cma_declare_contiguous(phys_addr_t size,
-				       phys_addr_t alignment) __init;
-#endif

arch/powerpc/mm/mem.c

@@ -128,7 +128,8 @@ int arch_add_memory(int nid, u64 start, u64 size)
 		return -EINVAL;
 
 	/* this should work for most non-highmem platforms */
-	zone = pgdata->node_zones;
+	zone = pgdata->node_zones +
+		zone_for_memory(nid, start, size, 0);
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }

arch/score/include/uapi/asm/ptrace.h

@@ -4,17 +4,6 @@
 #define PTRACE_GETREGS		12
 #define PTRACE_SETREGS		13
 
-#define PC		32
-#define CONDITION	33
-#define ECR		34
-#define EMA		35
-#define CEH		36
-#define CEL		37
-#define COUNTER		38
-#define LDCR		39
-#define STCR		40
-#define PSR		41
-
 #define SINGLESTEP16_INSN	0x7006
 #define SINGLESTEP32_INSN	0x840C8000
 #define BREAKPOINT16_INSN	0x7002		/* work on SPG300 */

arch/sh/drivers/dma/Kconfig

@@ -12,9 +12,8 @@ config SH_DMA_IRQ_MULTI
 	default y if CPU_SUBTYPE_SH7750  || CPU_SUBTYPE_SH7751  || \
 		     CPU_SUBTYPE_SH7750S || CPU_SUBTYPE_SH7750R || \
 		     CPU_SUBTYPE_SH7751R || CPU_SUBTYPE_SH7091  || \
-		     CPU_SUBTYPE_SH7763  || CPU_SUBTYPE_SH7764  || \
-		     CPU_SUBTYPE_SH7780  || CPU_SUBTYPE_SH7785  || \
-		     CPU_SUBTYPE_SH7760
+		     CPU_SUBTYPE_SH7763  || CPU_SUBTYPE_SH7780  || \
+		     CPU_SUBTYPE_SH7785  || CPU_SUBTYPE_SH7760
 
 config SH_DMA_API
 	depends on SH_DMA

arch/sh/include/asm/io_noioport.h

@@ -34,6 +34,17 @@ static inline void outl(unsigned int x, unsigned long port)
 	BUG();
 }
 
+static inline void __iomem *ioport_map(unsigned long port, unsigned int size)
+{
+	BUG();
+	return NULL;
+}
+
+static inline void ioport_unmap(void __iomem *addr)
+{
+	BUG();
+}
+
 #define inb_p(addr)	inb(addr)
 #define inw_p(addr)	inw(addr)
 #define inl_p(addr)	inl(addr)

arch/sh/include/cpu-sh4/cpu/dma-register.h

@@ -32,7 +32,6 @@
 #define CHCR_TS_HIGH_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
 #elif defined(CONFIG_CPU_SUBTYPE_SH7757) || \
 	defined(CONFIG_CPU_SUBTYPE_SH7763) || \
-	defined(CONFIG_CPU_SUBTYPE_SH7764) || \
 	defined(CONFIG_CPU_SUBTYPE_SH7780) || \
 	defined(CONFIG_CPU_SUBTYPE_SH7785)
 #define CHCR_TS_LOW_MASK	0x00000018

arch/sh/include/cpu-sh4a/cpu/dma.h

@@ -14,8 +14,7 @@
 #define DMTE4_IRQ	evt2irq(0xb80)
 #define DMAE0_IRQ	evt2irq(0xbc0)	/* DMA Error IRQ*/
 #define SH_DMAC_BASE0	0xFE008020
-#elif defined(CONFIG_CPU_SUBTYPE_SH7763) || \
-	defined(CONFIG_CPU_SUBTYPE_SH7764)
+#elif defined(CONFIG_CPU_SUBTYPE_SH7763)
 #define DMTE0_IRQ	evt2irq(0x640)
 #define DMTE4_IRQ	evt2irq(0x780)
 #define DMAE0_IRQ	evt2irq(0x6c0)

arch/sh/kernel/cpu/sh4a/clock-sh7724.c

@@ -307,7 +307,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_ICK_ID("fck", "sh-tmu.0", &mstp_clks[HWBLK_TMU0]),
 	CLKDEV_ICK_ID("fck", "sh-tmu.1", &mstp_clks[HWBLK_TMU1]),
 
-	CLKDEV_ICK_ID("fck", "sh-cmt-16.0", &mstp_clks[HWBLK_CMT]),
+	CLKDEV_ICK_ID("fck", "sh-cmt-32.0", &mstp_clks[HWBLK_CMT]),
 	CLKDEV_DEV_ID("sh-wdt.0", &mstp_clks[HWBLK_RWDT]),
 	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[HWBLK_DMAC1]),
 
@@ -332,6 +332,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("tsif0", &mstp_clks[HWBLK_TSIF]),
 	CLKDEV_DEV_ID("renesas_usbhs.1", &mstp_clks[HWBLK_USB1]),
 	CLKDEV_DEV_ID("renesas_usbhs.0", &mstp_clks[HWBLK_USB0]),
+	CLKDEV_CON_ID("usb1", &mstp_clks[HWBLK_USB1]),
+	CLKDEV_CON_ID("usb0", &mstp_clks[HWBLK_USB0]),
 	CLKDEV_CON_ID("2dg0", &mstp_clks[HWBLK_2DG]),
 	CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[HWBLK_SDHI0]),
 	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[HWBLK_SDHI1]),

arch/sh/kernel/time.c

@@ -80,10 +80,8 @@ static int __init rtc_generic_init(void)
 		return -ENODEV;
 
 	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 module_init(rtc_generic_init);
 

arch/sh/mm/asids-debugfs.c

@@ -67,10 +67,8 @@ static int __init asids_debugfs_init(void)
 					   NULL, &asids_debugfs_fops);
 	if (!asids_dentry)
 		return -ENOMEM;
-	if (IS_ERR(asids_dentry))
-		return PTR_ERR(asids_dentry);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(asids_dentry);
 }
 module_init(asids_debugfs_init);
 

arch/sh/mm/init.c

@@ -495,8 +495,9 @@ int arch_add_memory(int nid, u64 start, u64 size)
 	pgdat = NODE_DATA(nid);
 
 	/* We only have ZONE_NORMAL, so this is easy.. */
-	ret = __add_pages(nid, pgdat->node_zones + ZONE_NORMAL,
-				start_pfn, nr_pages);
+	ret = __add_pages(nid, pgdat->node_zones +
+			zone_for_memory(nid, start, size, ZONE_NORMAL),
+			start_pfn, nr_pages);
 	if (unlikely(ret))
 		printk("%s: Failed, __add_pages() == %d\n", __func__, ret);
 

arch/tile/kernel/module.c

@@ -58,7 +58,7 @@ void *module_alloc(unsigned long size)
 	area->nr_pages = npages;
 	area->pages = pages;
 
-	if (map_vm_area(area, prot_rwx, &pages)) {
+	if (map_vm_area(area, prot_rwx, pages)) {
 		vunmap(area->addr);
 		goto error;
 	}

arch/x86/mm/fault.c

@@ -1218,7 +1218,8 @@ good_area:
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
-	 * the fault:
+	 * the fault.  Since we never set FAULT_FLAG_RETRY_NOWAIT, if
+	 * we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
 

arch/x86/mm/init_32.c

@@ -825,7 +825,8 @@ void __init mem_init(void)
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdata = NODE_DATA(nid);
-	struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
+	struct zone *zone = pgdata->node_zones +
+		zone_for_memory(nid, start, size, ZONE_HIGHMEM);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 

arch/x86/mm/init_64.c

@@ -691,7 +691,8 @@ static void  update_end_of_memory_vars(u64 start, u64 size)
 int arch_add_memory(int nid, u64 start, u64 size)
 {
 	struct pglist_data *pgdat = NODE_DATA(nid);
-	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
+	struct zone *zone = pgdat->node_zones +
+		zone_for_memory(nid, start, size, ZONE_NORMAL);
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 	int ret;

drivers/ata/Kconfig

@@ -16,6 +16,7 @@ menuconfig ATA
 	depends on BLOCK
 	depends on !(M32R || M68K || S390) || BROKEN
 	select SCSI
+	select GLOB
 	---help---
 	  If you want to use an ATA hard disk, ATA tape drive, ATA CD-ROM or
 	  any other ATA device under Linux, say Y and make sure that you know

drivers/ata/libata-core.c

@@ -59,6 +59,7 @@
 #include <linux/async.h>
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/glob.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -4250,73 +4251,6 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	{ }
 };
 
-/**
- *	glob_match - match a text string against a glob-style pattern
- *	@text: the string to be examined
- *	@pattern: the glob-style pattern to be matched against
- *
- *	Either/both of text and pattern can be empty strings.
- *
- *	Match text against a glob-style pattern, with wildcards and simple sets:
- *
- *		?	matches any single character.
- *		*	matches any run of characters.
- *		[xyz]	matches a single character from the set: x, y, or z.
- *		[a-d]	matches a single character from the range: a, b, c, or d.
- *		[a-d0-9] matches a single character from either range.
- *
- *	The special characters ?, [, -, or *, can be matched using a set, eg. [*]
- *	Behaviour with malformed patterns is undefined, though generally reasonable.
- *
- *	Sample patterns:  "SD1?",  "SD1[0-5]",  "*R0",  "SD*1?[012]*xx"
- *
- *	This function uses one level of recursion per '*' in pattern.
- *	Since it calls _nothing_ else, and has _no_ explicit local variables,
- *	this will not cause stack problems for any reasonable use here.
- *
- *	RETURNS:
- *	0 on match, 1 otherwise.
- */
-static int glob_match (const char *text, const char *pattern)
-{
-	do {
-		/* Match single character or a '?' wildcard */
-		if (*text == *pattern || *pattern == '?') {
-			if (!*pattern++)
-				return 0;  /* End of both strings: match */
-		} else {
-			/* Match single char against a '[' bracketed ']' pattern set */
-			if (!*text || *pattern != '[')
-				break;  /* Not a pattern set */
-			while (*++pattern && *pattern != ']' && *text != *pattern) {
-				if (*pattern == '-' && *(pattern - 1) != '[')
-					if (*text > *(pattern - 1) && *text < *(pattern + 1)) {
-						++pattern;
-						break;
-					}
-			}
-			if (!*pattern || *pattern == ']')
-				return 1;  /* No match */
-			while (*pattern && *pattern++ != ']');
-		}
-	} while (*++text && *pattern);
-
-	/* Match any run of chars against a '*' wildcard */
-	if (*pattern == '*') {
-		if (!*++pattern)
-			return 0;  /* Match: avoid recursion at end of pattern */
-		/* Loop to handle additional pattern chars after the wildcard */
-		while (*text) {
-			if (glob_match(text, pattern) == 0)
-				return 0;  /* Remainder matched */
-			++text;  /* Absorb (match) this char and try again */
-		}
-	}
-	if (!*text && !*pattern)
-		return 0;  /* End of both strings: match */
-	return 1;  /* No match */
-}
-
 static unsigned long ata_dev_blacklisted(const struct ata_device *dev)
 {
 	unsigned char model_num[ATA_ID_PROD_LEN + 1];
@@ -4327,10 +4261,10 @@ static unsigned long ata_dev_blacklisted(const struct ata_device *dev)
 	ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev));
 
 	while (ad->model_num) {
-		if (!glob_match(model_num, ad->model_num)) {
+		if (glob_match(model_num, ad->model_num)) {
 			if (ad->model_rev == NULL)
 				return ad->horkage;
-			if (!glob_match(model_rev, ad->model_rev))
+			if (glob_match(model_rev, ad->model_rev))
 				return ad->horkage;
 		}
 		ad++;

drivers/base/Kconfig

@@ -289,16 +289,6 @@ config CMA_ALIGNMENT
 
 	  If unsure, leave the default value "8".
 
-config CMA_AREAS
-	int "Maximum count of the CMA device-private areas"
-	default 7
-	help
-	  CMA allows to create CMA areas for particular devices. This parameter
-	  sets the maximum number of such device private CMA areas in the
-	  system.
-
-	  If unsure, leave the default value "7".
-
 endif
 
 endmenu

drivers/base/dma-contiguous.c

@@ -24,23 +24,9 @@
 
 #include <linux/memblock.h>
 #include <linux/err.h>
-#include <linux/mm.h>
-#include <linux/mutex.h>
-#include <linux/page-isolation.h>
 #include <linux/sizes.h>
-#include <linux/slab.h>
-#include <linux/swap.h>
-#include <linux/mm_types.h>
 #include <linux/dma-contiguous.h>
-
-struct cma {
-	unsigned long	base_pfn;
-	unsigned long	count;
-	unsigned long	*bitmap;
-	struct mutex	lock;
-};
-
-struct cma *dma_contiguous_default_area;
+#include <linux/cma.h>
 
 #ifdef CONFIG_CMA_SIZE_MBYTES
 #define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
@@ -48,6 +34,8 @@ struct cma *dma_contiguous_default_area;
 #define CMA_SIZE_MBYTES 0
 #endif
 
+struct cma *dma_contiguous_default_area;
+
 /*
  * Default global CMA area size can be defined in kernel's .config.
  * This is useful mainly for distro maintainers to create a kernel
@@ -154,65 +142,6 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 	}
 }
 
-static DEFINE_MUTEX(cma_mutex);
-
-static int __init cma_activate_area(struct cma *cma)
-{
-	int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
-	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
-	unsigned i = cma->count >> pageblock_order;
-	struct zone *zone;
-
-	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-
-	if (!cma->bitmap)
-		return -ENOMEM;
-
-	WARN_ON_ONCE(!pfn_valid(pfn));
-	zone = page_zone(pfn_to_page(pfn));
-
-	do {
-		unsigned j;
-		base_pfn = pfn;
-		for (j = pageblock_nr_pages; j; --j, pfn++) {
-			WARN_ON_ONCE(!pfn_valid(pfn));
-			/*
-			 * alloc_contig_range requires the pfn range
-			 * specified to be in the same zone. Make this
-			 * simple by forcing the entire CMA resv range
-			 * to be in the same zone.
-			 */
-			if (page_zone(pfn_to_page(pfn)) != zone)
-				goto err;
-		}
-		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
-	} while (--i);
-
-	mutex_init(&cma->lock);
-	return 0;
-
-err:
-	kfree(cma->bitmap);
-	return -EINVAL;
-}
-
-static struct cma cma_areas[MAX_CMA_AREAS];
-static unsigned cma_area_count;
-
-static int __init cma_init_reserved_areas(void)
-{
-	int i;
-
-	for (i = 0; i < cma_area_count; i++) {
-		int ret = cma_activate_area(&cma_areas[i]);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-core_initcall(cma_init_reserved_areas);
-
 /**
  * dma_contiguous_reserve_area() - reserve custom contiguous area
  * @size: Size of the reserved area (in bytes),
@@ -234,72 +163,17 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
 				       phys_addr_t limit, struct cma **res_cma,
 				       bool fixed)
 {
-	struct cma *cma = &cma_areas[cma_area_count];
-	phys_addr_t alignment;
-	int ret = 0;
+	int ret;
 
-	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
-		 (unsigned long)size, (unsigned long)base,
-		 (unsigned long)limit);
-
-	/* Sanity checks */
-	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
-		pr_err("Not enough slots for CMA reserved regions!\n");
-		return -ENOSPC;
-	}
-
-	if (!size)
-		return -EINVAL;
-
-	/* Sanitise input arguments */
-	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
-	base = ALIGN(base, alignment);
-	size = ALIGN(size, alignment);
-	limit &= ~(alignment - 1);
-
-	/* Reserve memory */
-	if (base && fixed) {
-		if (memblock_is_region_reserved(base, size) ||
-		    memblock_reserve(base, size) < 0) {
-			ret = -EBUSY;
-			goto err;
-		}
-	} else {
-		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
-							limit);
-		if (!addr) {
-			ret = -ENOMEM;
-			goto err;
-		} else {
-			base = addr;
-		}
-	}
-
-	/*
-	 * Each reserved area must be initialised later, when more kernel
-	 * subsystems (like slab allocator) are available.
-	 */
-	cma->base_pfn = PFN_DOWN(base);
-	cma->count = size >> PAGE_SHIFT;
-	*res_cma = cma;
-	cma_area_count++;
-
-	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
-		(unsigned long)base);
+	ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed, res_cma);
+	if (ret)
+		return ret;
 
 	/* Architecture specific contiguous memory fixup. */
-	dma_contiguous_early_fixup(base, size);
-	return 0;
-err:
-	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
-	return ret;
-}
+	dma_contiguous_early_fixup(cma_get_base(*res_cma),
+				cma_get_size(*res_cma));
 
-static void clear_cma_bitmap(struct cma *cma, unsigned long pfn, int count)
-{
-	mutex_lock(&cma->lock);
-	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
-	mutex_unlock(&cma->lock);
+	return 0;
 }
 
 /**
@@ -316,62 +190,10 @@ static void clear_cma_bitmap(struct cma *cma, unsigned long pfn, int count)
 struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 				       unsigned int align)
 {
-	unsigned long mask, pfn, pageno, start = 0;
-	struct cma *cma = dev_get_cma_area(dev);
-	struct page *page = NULL;
-	int ret;
-
-	if (!cma || !cma->count)
-		return NULL;
-
 	if (align > CONFIG_CMA_ALIGNMENT)
 		align = CONFIG_CMA_ALIGNMENT;
 
-	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
-		 count, align);
-
-	if (!count)
-		return NULL;
-
-	mask = (1 << align) - 1;
-
-
-	for (;;) {
-		mutex_lock(&cma->lock);
-		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
-						    start, count, mask);
-		if (pageno >= cma->count) {
-			mutex_unlock(&cma->lock);
-			break;
-		}
-		bitmap_set(cma->bitmap, pageno, count);
-		/*
-		 * It's safe to drop the lock here. We've marked this region for
-		 * our exclusive use. If the migration fails we will take the
-		 * lock again and unmark it.
-		 */
-		mutex_unlock(&cma->lock);
-
-		pfn = cma->base_pfn + pageno;
-		mutex_lock(&cma_mutex);
-		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
-		mutex_unlock(&cma_mutex);
-		if (ret == 0) {
-			page = pfn_to_page(pfn);
-			break;
-		} else if (ret != -EBUSY) {
-			clear_cma_bitmap(cma, pfn, count);
-			break;
-		}
-		clear_cma_bitmap(cma, pfn, count);
-		pr_debug("%s(): memory range at %p is busy, retrying\n",
-			 __func__, pfn_to_page(pfn));
-		/* try again with a bit different memory target */
-		start = pageno + mask + 1;
-	}
-
-	pr_debug("%s(): returned %p\n", __func__, page);
-	return page;
+	return cma_alloc(dev_get_cma_area(dev), count, align);
 }
 
 /**
@@ -387,23 +209,5 @@ struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 				 int count)
 {
-	struct cma *cma = dev_get_cma_area(dev);
-	unsigned long pfn;
-
-	if (!cma || !pages)
-		return false;
-
-	pr_debug("%s(page %p)\n", __func__, (void *)pages);
-
-	pfn = page_to_pfn(pages);
-
-	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
-		return false;
-
-	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
-
-	free_contig_range(pfn, count);
-	clear_cma_bitmap(cma, pfn, count);
-
-	return true;
+	return cma_release(dev_get_cma_area(dev), pages, count);
 }

drivers/base/memory.c

@@ -284,7 +284,7 @@ static int memory_subsys_online(struct device *dev)
 	 * attribute and need to set the online_type.
 	 */
 	if (mem->online_type < 0)
-		mem->online_type = ONLINE_KEEP;
+		mem->online_type = MMOP_ONLINE_KEEP;
 
 	ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
 
@@ -315,23 +315,23 @@ store_mem_state(struct device *dev,
 	if (ret)
 		return ret;
 
-	if (!strncmp(buf, "online_kernel", min_t(int, count, 13)))
-		online_type = ONLINE_KERNEL;
-	else if (!strncmp(buf, "online_movable", min_t(int, count, 14)))
-		online_type = ONLINE_MOVABLE;
-	else if (!strncmp(buf, "online", min_t(int, count, 6)))
-		online_type = ONLINE_KEEP;
-	else if (!strncmp(buf, "offline", min_t(int, count, 7)))
-		online_type = -1;
+	if (sysfs_streq(buf, "online_kernel"))
+		online_type = MMOP_ONLINE_KERNEL;
+	else if (sysfs_streq(buf, "online_movable"))
+		online_type = MMOP_ONLINE_MOVABLE;
+	else if (sysfs_streq(buf, "online"))
+		online_type = MMOP_ONLINE_KEEP;
+	else if (sysfs_streq(buf, "offline"))
+		online_type = MMOP_OFFLINE;
 	else {
 		ret = -EINVAL;
 		goto err;
 	}
 
 	switch (online_type) {
-	case ONLINE_KERNEL:
-	case ONLINE_MOVABLE:
-	case ONLINE_KEEP:
+	case MMOP_ONLINE_KERNEL:
+	case MMOP_ONLINE_MOVABLE:
+	case MMOP_ONLINE_KEEP:
 		/*
 		 * mem->online_type is not protected so there can be a
 		 * race here.  However, when racing online, the first
@@ -342,7 +342,7 @@ store_mem_state(struct device *dev,
 		mem->online_type = online_type;
 		ret = device_online(&mem->dev);
 		break;
-	case -1:
+	case MMOP_OFFLINE:
 		ret = device_offline(&mem->dev);
 		break;
 	default:
@@ -406,7 +406,9 @@ memory_probe_store(struct device *dev, struct device_attribute *attr,
 	int i, ret;
 	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;
 
-	phys_addr = simple_strtoull(buf, NULL, 0);
+	ret = kstrtoull(buf, 0, &phys_addr);
+	if (ret)
+		return ret;
 
 	if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
 		return -EINVAL;

drivers/base/node.c

@@ -126,7 +126,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
 		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
-		       nid, K(node_page_state(nid, NR_SHMEM)),
+		       nid, K(i.sharedram),
 		       nid, node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
 		       nid, K(node_page_state(nid, NR_PAGETABLE)),

drivers/block/zram/zram_drv.c

@@ -183,19 +183,32 @@ static ssize_t comp_algorithm_store(struct device *dev,
 static int zram_test_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	return meta->table[index].flags & BIT(flag);
+	return meta->table[index].value & BIT(flag);
 }
 
 static void zram_set_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	meta->table[index].flags |= BIT(flag);
+	meta->table[index].value |= BIT(flag);
 }
 
 static void zram_clear_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
 {
-	meta->table[index].flags &= ~BIT(flag);
+	meta->table[index].value &= ~BIT(flag);
+}
+
+static size_t zram_get_obj_size(struct zram_meta *meta, u32 index)
+{
+	return meta->table[index].value & (BIT(ZRAM_FLAG_SHIFT) - 1);
+}
+
+static void zram_set_obj_size(struct zram_meta *meta,
+					u32 index, size_t size)
+{
+	unsigned long flags = meta->table[index].value >> ZRAM_FLAG_SHIFT;
+
+	meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
 }
 
 static inline int is_partial_io(struct bio_vec *bvec)
@@ -255,7 +268,6 @@ static struct zram_meta *zram_meta_alloc(u64 disksize)
 		goto free_table;
 	}
 
-	rwlock_init(&meta->tb_lock);
 	return meta;
 
 free_table:
@@ -304,7 +316,12 @@ static void handle_zero_page(struct bio_vec *bvec)
 	flush_dcache_page(page);
 }
 
-/* NOTE: caller should hold meta->tb_lock with write-side */
+
+/*
+ * To protect concurrent access to the same index entry,
+ * caller should hold this table index entry's bit_spinlock to
+ * indicate this index entry is accessing.
+ */
 static void zram_free_page(struct zram *zram, size_t index)
 {
 	struct zram_meta *meta = zram->meta;
@@ -324,11 +341,12 @@ static void zram_free_page(struct zram *zram, size_t index)
 
 	zs_free(meta->mem_pool, handle);
 
-	atomic64_sub(meta->table[index].size, &zram->stats.compr_data_size);
+	atomic64_sub(zram_get_obj_size(meta, index),
+			&zram->stats.compr_data_size);
 	atomic64_dec(&zram->stats.pages_stored);
 
 	meta->table[index].handle = 0;
-	meta->table[index].size = 0;
+	zram_set_obj_size(meta, index, 0);
 }
 
 static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
@@ -337,14 +355,14 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	unsigned char *cmem;
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle;
-	u16 size;
+	size_t size;
 
-	read_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	handle = meta->table[index].handle;
-	size = meta->table[index].size;
+	size = zram_get_obj_size(meta, index);
 
 	if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
-		read_unlock(&meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 		clear_page(mem);
 		return 0;
 	}
@@ -355,7 +373,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	else
 		ret = zcomp_decompress(zram->comp, cmem, size, mem);
 	zs_unmap_object(meta->mem_pool, handle);
-	read_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	/* Should NEVER happen. Return bio error if it does. */
 	if (unlikely(ret)) {
@@ -376,14 +394,14 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 	struct zram_meta *meta = zram->meta;
 	page = bvec->bv_page;
 
-	read_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	if (unlikely(!meta->table[index].handle) ||
 			zram_test_flag(meta, index, ZRAM_ZERO)) {
-		read_unlock(&meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 		handle_zero_page(bvec);
 		return 0;
 	}
-	read_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	if (is_partial_io(bvec))
 		/* Use  a temporary buffer to decompress the page */
@@ -461,10 +479,10 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	if (page_zero_filled(uncmem)) {
 		kunmap_atomic(user_mem);
 		/* Free memory associated with this sector now. */
-		write_lock(&zram->meta->tb_lock);
+		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
 		zram_set_flag(meta, index, ZRAM_ZERO);
-		write_unlock(&zram->meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 		atomic64_inc(&zram->stats.zero_pages);
 		ret = 0;
@@ -514,12 +532,12 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	 * Free memory associated with this sector
 	 * before overwriting unused sectors.
 	 */
-	write_lock(&zram->meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	zram_free_page(zram, index);
 
 	meta->table[index].handle = handle;
-	meta->table[index].size = clen;
-	write_unlock(&zram->meta->tb_lock);
+	zram_set_obj_size(meta, index, clen);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 
 	/* Update stats */
 	atomic64_add(clen, &zram->stats.compr_data_size);
@@ -560,6 +578,7 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 			     int offset, struct bio *bio)
 {
 	size_t n = bio->bi_iter.bi_size;
+	struct zram_meta *meta = zram->meta;
 
 	/*
 	 * zram manages data in physical block size units. Because logical block
@@ -580,13 +599,9 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 
 	while (n >= PAGE_SIZE) {
-		/*
-		 * Discard request can be large so the lock hold times could be
-		 * lengthy.  So take the lock once per page.
-		 */
-		write_lock(&zram->meta->tb_lock);
+		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
-		write_unlock(&zram->meta->tb_lock);
+		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 		index++;
 		n -= PAGE_SIZE;
 	}
@@ -821,9 +836,9 @@ static void zram_slot_free_notify(struct block_device *bdev,
 	zram = bdev->bd_disk->private_data;
 	meta = zram->meta;
 
-	write_lock(&meta->tb_lock);
+	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 	zram_free_page(zram, index);
-	write_unlock(&meta->tb_lock);
+	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
 	atomic64_inc(&zram->stats.notify_free);
 }
 

drivers/block/zram/zram_drv.h

@@ -43,7 +43,6 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
 /*-- End of configurable params */
 
 #define SECTOR_SHIFT		9
-#define SECTOR_SIZE		(1 << SECTOR_SHIFT)
 #define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
 #define ZRAM_LOGICAL_BLOCK_SHIFT 12
@@ -51,10 +50,24 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
 #define ZRAM_SECTOR_PER_LOGICAL_BLOCK	\
 	(1 << (ZRAM_LOGICAL_BLOCK_SHIFT - SECTOR_SHIFT))
 
-/* Flags for zram pages (table[page_no].flags) */
+
+/*
+ * The lower ZRAM_FLAG_SHIFT bits of table.value is for
+ * object size (excluding header), the higher bits is for
+ * zram_pageflags.
+ *
+ * zram is mainly used for memory efficiency so we want to keep memory
+ * footprint small so we can squeeze size and flags into a field.
+ * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header),
+ * the higher bits is for zram_pageflags.
+ */
+#define ZRAM_FLAG_SHIFT 24
+
+/* Flags for zram pages (table[page_no].value) */
 enum zram_pageflags {
 	/* Page consists entirely of zeros */
-	ZRAM_ZERO,
+	ZRAM_ZERO = ZRAM_FLAG_SHIFT + 1,
+	ZRAM_ACCESS,	/* page in now accessed */
 
 	__NR_ZRAM_PAGEFLAGS,
 };
@@ -62,11 +75,10 @@ enum zram_pageflags {
 /*-- Data structures */
 
 /* Allocated for each disk page */
-struct table {
+struct zram_table_entry {
 	unsigned long handle;
-	u16 size;	/* object size (excluding header) */
-	u8 flags;
-} __aligned(4);
+	unsigned long value;
+};
 
 struct zram_stats {
 	atomic64_t compr_data_size;	/* compressed size of pages stored */
@@ -81,8 +93,7 @@ struct zram_stats {
 };
 
 struct zram_meta {
-	rwlock_t tb_lock;	/* protect table */
-	struct table *table;
+	struct zram_table_entry *table;
 	struct zs_pool *mem_pool;
 };
 

drivers/firmware/memmap.c

@@ -286,7 +286,11 @@ int __meminit firmware_map_add_hotplug(u64 start, u64 end, const char *type)
 {
 	struct firmware_map_entry *entry;
 
-	entry = firmware_map_find_entry_bootmem(start, end, type);
+	entry = firmware_map_find_entry(start, end - 1, type);
+	if (entry)
+		return 0;
+
+	entry = firmware_map_find_entry_bootmem(start, end - 1, type);
 	if (!entry) {
 		entry = kzalloc(sizeof(struct firmware_map_entry), GFP_ATOMIC);
 		if (!entry)

drivers/gpu/drm/drm_hashtab.c

@@ -125,7 +125,7 @@ int drm_ht_insert_item(struct drm_open_hash *ht, struct drm_hash_item *item)
 		parent = &entry->head;
 	}
 	if (parent) {
-		hlist_add_after_rcu(parent, &item->head);
+		hlist_add_behind_rcu(&item->head, parent);
 	} else {
 		hlist_add_head_rcu(&item->head, h_list);
 	}

drivers/hwmon/asus_atk0110.c

@@ -688,7 +688,7 @@ static int atk_debugfs_gitm_get(void *p, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(atk_debugfs_gitm,
 			atk_debugfs_gitm_get,
 			NULL,
-			"0x%08llx\n")
+			"0x%08llx\n");
 
 static int atk_acpi_print(char *buf, size_t sz, union acpi_object *obj)
 {

drivers/lguest/core.c

@@ -42,7 +42,6 @@ DEFINE_MUTEX(lguest_lock);
 static __init int map_switcher(void)
 {
 	int i, err;
-	struct page **pagep;
 
 	/*
 	 * Map the Switcher in to high memory.
@@ -110,11 +109,9 @@ static __init int map_switcher(void)
 	 * This code actually sets up the pages we've allocated to appear at
 	 * switcher_addr.  map_vm_area() takes the vma we allocated above, the
 	 * kind of pages we're mapping (kernel pages), and a pointer to our
-	 * array of struct pages.  It increments that pointer, but we don't
-	 * care.
+	 * array of struct pages.
 	 */
-	pagep = lg_switcher_pages;
-	err = map_vm_area(switcher_vma, PAGE_KERNEL_EXEC, &pagep);
+	err = map_vm_area(switcher_vma, PAGE_KERNEL_EXEC, lg_switcher_pages);
 	if (err) {
 		printk("lguest: map_vm_area failed: %i\n", err);
 		goto free_vma;

drivers/net/ethernet/intel/i40e/i40e_ethtool.c

@@ -1948,7 +1948,7 @@ static int i40e_update_ethtool_fdir_entry(struct i40e_vsi *vsi,
 
 	/* add filter to the list */
 	if (parent)
-		hlist_add_after(&parent->fdir_node, &input->fdir_node);
+		hlist_add_behind(&input->fdir_node, &parent->fdir_node);
 	else
 		hlist_add_head(&input->fdir_node,
 			       &pf->fdir_filter_list);

drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c

@@ -2517,7 +2517,7 @@ static int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter,
 
 	/* add filter to the list */
 	if (parent)
-		hlist_add_after(&parent->fdir_node, &input->fdir_node);
+		hlist_add_behind(&input->fdir_node, &parent->fdir_node);
 	else
 		hlist_add_head(&input->fdir_node,
 			       &adapter->fdir_filter_list);

drivers/staging/android/binder.c

@@ -585,7 +585,6 @@ static int binder_update_page_range(struct binder_proc *proc, int allocate,
 
 	for (page_addr = start; page_addr < end; page_addr += PAGE_SIZE) {
 		int ret;
-		struct page **page_array_ptr;
 
 		page = &proc->pages[(page_addr - proc->buffer) / PAGE_SIZE];
 
@@ -598,8 +597,7 @@ static int binder_update_page_range(struct binder_proc *proc, int allocate,
 		}
 		tmp_area.addr = page_addr;
 		tmp_area.size = PAGE_SIZE + PAGE_SIZE /* guard page? */;
-		page_array_ptr = page;
-		ret = map_vm_area(&tmp_area, PAGE_KERNEL, &page_array_ptr);
+		ret = map_vm_area(&tmp_area, PAGE_KERNEL, page);
 		if (ret) {
 			pr_err("%d: binder_alloc_buf failed to map page at %p in kernel\n",
 			       proc->pid, page_addr);

drivers/staging/lustre/lustre/libcfs/hash.c

@@ -351,7 +351,7 @@ cfs_hash_dh_hnode_add(struct cfs_hash *hs, struct cfs_hash_bd *bd,
 					    cfs_hash_dhead_t, dh_head);
 
 	if (dh->dh_tail != NULL) /* not empty */
-		hlist_add_after(dh->dh_tail, hnode);
+		hlist_add_behind(hnode, dh->dh_tail);
 	else /* empty list */
 		hlist_add_head(hnode, &dh->dh_head);
 	dh->dh_tail = hnode;
@@ -406,7 +406,7 @@ cfs_hash_dd_hnode_add(struct cfs_hash *hs, struct cfs_hash_bd *bd,
 						cfs_hash_dhead_dep_t, dd_head);
 
 	if (dh->dd_tail != NULL) /* not empty */
-		hlist_add_after(dh->dd_tail, hnode);
+		hlist_add_behind(hnode, dh->dd_tail);
 	else /* empty list */
 		hlist_add_head(hnode, &dh->dd_head);
 	dh->dd_tail = hnode;

drivers/tty/sysrq.c

@@ -355,7 +355,7 @@ static struct sysrq_key_op sysrq_term_op = {
 
 static void moom_callback(struct work_struct *ignored)
 {
-	out_of_memory(node_zonelist(first_online_node, GFP_KERNEL), GFP_KERNEL,
+	out_of_memory(node_zonelist(first_memory_node, GFP_KERNEL), GFP_KERNEL,
 		      0, NULL, true);
 }
 

fs/fscache/main.c

@@ -67,7 +67,7 @@ static int fscache_max_active_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
-struct ctl_table fscache_sysctls[] = {
+static struct ctl_table fscache_sysctls[] = {
 	{
 		.procname	= "object_max_active",
 		.data		= &fscache_object_max_active,
@@ -87,7 +87,7 @@ struct ctl_table fscache_sysctls[] = {
 	{}
 };
 
-struct ctl_table fscache_sysctls_root[] = {
+static struct ctl_table fscache_sysctls_root[] = {
 	{
 		.procname	= "fscache",
 		.mode		= 0555,

fs/logfs/readwrite.c

@@ -1019,11 +1019,11 @@ static int __logfs_is_valid_block(struct inode *inode, u64 bix, u64 ofs)
 /**
  * logfs_is_valid_block - check whether this block is still valid
  *
- * @sb	- superblock
- * @ofs	- block physical offset
- * @ino	- block inode number
- * @bix	- block index
- * @level - block level
+ * @sb:		superblock
+ * @ofs:	block physical offset
+ * @ino:	block inode number
+ * @bix:	block index
+ * @gc_level:	block level
  *
  * Returns 0 if the block is invalid, 1 if it is valid and 2 if it will
  * become invalid once the journal is written.
@@ -2226,10 +2226,9 @@ void btree_write_block(struct logfs_block *block)
  *
  * @inode:		parent inode (ifile or directory)
  * @buf:		object to write (inode or dentry)
- * @n:			object size
- * @_pos:		object number (file position in blocks/objects)
+ * @count:		object size
+ * @bix:		block index
  * @flags:		write flags
- * @lock:		0 if write lock is already taken, 1 otherwise
  * @shadow_tree:	shadow below this inode
  *
  * FIXME: All caller of this put a 200-300 byte variable on the stack,

fs/namespace.c

@@ -798,7 +798,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 	list_splice(&head, n->list.prev);
 
 	if (shadows)
-		hlist_add_after_rcu(&shadows->mnt_hash, &mnt->mnt_hash);
+		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
 	else
 		hlist_add_head_rcu(&mnt->mnt_hash,
 				m_hash(&parent->mnt, mnt->mnt_mountpoint));

fs/notify/fanotify/fanotify.c

@@ -70,8 +70,15 @@ static int fanotify_get_response(struct fsnotify_group *group,
 	wait_event(group->fanotify_data.access_waitq, event->response ||
 				atomic_read(&group->fanotify_data.bypass_perm));
 
-	if (!event->response) /* bypass_perm set */
+	if (!event->response) {	/* bypass_perm set */
+		/*
+		 * Event was canceled because group is being destroyed. Remove
+		 * it from group's event list because we are responsible for
+		 * freeing the permission event.
+		 */
+		fsnotify_remove_event(group, &event->fae.fse);
 		return 0;
+	}
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
@@ -210,7 +217,7 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 		return -ENOMEM;
 
 	fsn_event = &event->fse;
-	ret = fsnotify_add_notify_event(group, fsn_event, fanotify_merge);
+	ret = fsnotify_add_event(group, fsn_event, fanotify_merge);
 	if (ret) {
 		/* Permission events shouldn't be merged */
 		BUG_ON(ret == 1 && mask & FAN_ALL_PERM_EVENTS);

fs/notify/fanotify/fanotify_user.c

@@ -66,7 +66,7 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 
 	/* held the notification_mutex the whole time, so this is the
 	 * same event we peeked above */
-	return fsnotify_remove_notify_event(group);
+	return fsnotify_remove_first_event(group);
 }
 
 static int create_fd(struct fsnotify_group *group,
@@ -359,6 +359,11 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
 
+	/*
+	 * There may be still new events arriving in the notification queue
+	 * but since userspace cannot use fanotify fd anymore, no event can
+	 * enter or leave access_list by now.
+	 */
 	spin_lock(&group->fanotify_data.access_lock);
 
 	atomic_inc(&group->fanotify_data.bypass_perm);
@@ -373,6 +378,13 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	}
 	spin_unlock(&group->fanotify_data.access_lock);
 
+	/*
+	 * Since bypass_perm is set, newly queued events will not wait for
+	 * access response. Wake up the already sleeping ones now.
+	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
+	 * processes sleeping in fanotify_handle_event() waiting for access
+	 * response and thus also for all permission events to be freed.
+	 */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 

fs/notify/inode_mark.c

@@ -232,7 +232,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 
 	BUG_ON(last == NULL);
 	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_after_rcu(&last->i.i_list, &mark->i.i_list);
+	hlist_add_behind_rcu(&mark->i.i_list, &last->i.i_list);
 out:
 	fsnotify_recalc_inode_mask_locked(inode);
 	spin_unlock(&inode->i_lock);

fs/notify/inotify/inotify_fsnotify.c

@@ -108,7 +108,7 @@ int inotify_handle_event(struct fsnotify_group *group,
 	if (len)
 		strcpy(event->name, file_name);
 
-	ret = fsnotify_add_notify_event(group, fsn_event, inotify_merge);
+	ret = fsnotify_add_event(group, fsn_event, inotify_merge);
 	if (ret) {
 		/* Our event wasn't used in the end. Free it. */
 		fsnotify_destroy_event(group, fsn_event);

fs/notify/inotify/inotify_user.c

@@ -149,7 +149,7 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 	if (fsnotify_notify_queue_is_empty(group))
 		return NULL;
 
-	event = fsnotify_peek_notify_event(group);
+	event = fsnotify_peek_first_event(group);
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
@@ -159,7 +159,7 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 
 	/* held the notification_mutex the whole time, so this is the
 	 * same event we peeked above */
-	fsnotify_remove_notify_event(group);
+	fsnotify_remove_first_event(group);
 
 	return event;
 }

fs/notify/notification.c

@@ -73,7 +73,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
 	/* Overflow events are per-group and we don't want to free them */
 	if (!event || event->mask == FS_Q_OVERFLOW)
 		return;
-
+	/* If the event is still queued, we have a problem... */
+	WARN_ON(!list_empty(&event->list));
 	group->ops->free_event(event);
 }
 
@@ -83,10 +84,10 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
  * added to the queue, 1 if the event was merged with some other queued event,
  * 2 if the queue of events has overflown.
  */
-int fsnotify_add_notify_event(struct fsnotify_group *group,
-			      struct fsnotify_event *event,
-			      int (*merge)(struct list_head *,
-					   struct fsnotify_event *))
+int fsnotify_add_event(struct fsnotify_group *group,
+		       struct fsnotify_event *event,
+		       int (*merge)(struct list_head *,
+				    struct fsnotify_event *))
 {
 	int ret = 0;
 	struct list_head *list = &group->notification_list;
@@ -124,11 +125,26 @@ queue:
 	return ret;
 }
 
+/*
+ * Remove @event from group's notification queue. It is the responsibility of
+ * the caller to destroy the event.
+ */
+void fsnotify_remove_event(struct fsnotify_group *group,
+			   struct fsnotify_event *event)
+{
+	mutex_lock(&group->notification_mutex);
+	if (!list_empty(&event->list)) {
+		list_del_init(&event->list);
+		group->q_len--;
+	}
+	mutex_unlock(&group->notification_mutex);
+}
+
 /*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event
  */
-struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group)
+struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group)
 {
 	struct fsnotify_event *event;
 
@@ -140,7 +156,7 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
 				 struct fsnotify_event, list);
 	/*
 	 * We need to init list head for the case of overflow event so that
-	 * check in fsnotify_add_notify_events() works
+	 * check in fsnotify_add_event() works
 	 */
 	list_del_init(&event->list);
 	group->q_len--;
@@ -149,9 +165,10 @@ struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group
 }
 
 /*
- * This will not remove the event, that must be done with fsnotify_remove_notify_event()
+ * This will not remove the event, that must be done with
+ * fsnotify_remove_first_event()
  */
-struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group)
+struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group)
 {
 	BUG_ON(!mutex_is_locked(&group->notification_mutex));
 
@@ -169,7 +186,7 @@ void fsnotify_flush_notify(struct fsnotify_group *group)
 
 	mutex_lock(&group->notification_mutex);
 	while (!fsnotify_notify_queue_is_empty(group)) {
-		event = fsnotify_remove_notify_event(group);
+		event = fsnotify_remove_first_event(group);
 		fsnotify_destroy_event(group, event);
 	}
 	mutex_unlock(&group->notification_mutex);

fs/notify/vfsmount_mark.c

@@ -191,7 +191,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 
 	BUG_ON(last == NULL);
 	/* mark should be the last entry.  last is the current last entry */
-	hlist_add_after_rcu(&last->m.m_list, &mark->m.m_list);
+	hlist_add_behind_rcu(&mark->m.m_list, &last->m.m_list);
 out:
 	fsnotify_recalc_vfsmount_mask_locked(mnt);
 	spin_unlock(&mnt->mnt_root->d_lock);

fs/ntfs/file.c

@@ -74,8 +74,6 @@ static int ntfs_file_open(struct inode *vi, struct file *filp)
  * ntfs_attr_extend_initialized - extend the initialized size of an attribute
  * @ni:			ntfs inode of the attribute to extend
  * @new_init_size:	requested new initialized size in bytes
- * @cached_page:	store any allocated but unused page here
- * @lru_pvec:		lru-buffering pagevec of the caller
  *
  * Extend the initialized size of an attribute described by the ntfs inode @ni
  * to @new_init_size bytes.  This involves zeroing any non-sparse space between
@@ -395,7 +393,6 @@ static inline void ntfs_fault_in_pages_readable_iovec(const struct iovec *iov,
  * @nr_pages:	number of page cache pages to obtain
  * @pages:	array of pages in which to return the obtained page cache pages
  * @cached_page: allocated but as yet unused page
- * @lru_pvec:	lru-buffering pagevec of caller
  *
  * Obtain @nr_pages locked page cache pages from the mapping @mapping and
  * starting at index @index.

fs/ocfs2/alloc.c

@@ -4961,6 +4961,15 @@ leftright:
 
 		el = path_leaf_el(path);
 		split_index = ocfs2_search_extent_list(el, cpos);
+		if (split_index == -1) {
+			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
+					"Owner %llu has an extent at cpos %u "
+					"which can no longer be found.\n",
+					(unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),
+					cpos);
+			ret = -EROFS;
+			goto out;
+		}
 		goto leftright;
 	}
 out:
@@ -5135,7 +5144,7 @@ int ocfs2_change_extent_flag(handle_t *handle,
 	el = path_leaf_el(left_path);
 
 	index = ocfs2_search_extent_list(el, cpos);
-	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+	if (index == -1) {
 		ocfs2_error(sb,
 			    "Owner %llu has an extent at cpos %u which can no "
 			    "longer be found.\n",
@@ -5491,7 +5500,7 @@ int ocfs2_remove_extent(handle_t *handle,
 
 	el = path_leaf_el(path);
 	index = ocfs2_search_extent_list(el, cpos);
-	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+	if (index == -1) {
 		ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
 			    "Owner %llu has an extent at cpos %u which can no "
 			    "longer be found.\n",
@@ -5557,7 +5566,7 @@ int ocfs2_remove_extent(handle_t *handle,
 
 		el = path_leaf_el(path);
 		index = ocfs2_search_extent_list(el, cpos);
-		if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+		if (index == -1) {
 			ocfs2_error(ocfs2_metadata_cache_get_super(et->et_ci),
 				    "Owner %llu: split at cpos %u lost record.",
 				    (unsigned long long)ocfs2_metadata_cache_owner(et->et_ci),

fs/ocfs2/dlm/dlmdomain.c

@@ -1923,12 +1923,11 @@ static int dlm_join_domain(struct dlm_ctxt *dlm)
 				goto bail;
 			}
 
-			if (total_backoff >
-			    msecs_to_jiffies(DLM_JOIN_TIMEOUT_MSECS)) {
+			if (total_backoff > DLM_JOIN_TIMEOUT_MSECS) {
 				status = -ERESTARTSYS;
 				mlog(ML_NOTICE, "Timed out joining dlm domain "
 				     "%s after %u msecs\n", dlm->name,
-				     jiffies_to_msecs(total_backoff));
+				     total_backoff);
 				goto bail;
 			}
 

fs/ocfs2/dlm/dlmmaster.c

@@ -2405,6 +2405,10 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 	if (res->state & DLM_LOCK_RES_MIGRATING)
 		return 0;
 
+	/* delay migration when the lockres is in RECOCERING state */
+	if (res->state & DLM_LOCK_RES_RECOVERING)
+		return 0;
+
 	if (res->owner != dlm->node_num)
 		return 0;
 

fs/ocfs2/move_extents.c

@@ -98,7 +98,7 @@ static int __ocfs2_move_extent(handle_t *handle,
 	el = path_leaf_el(path);
 
 	index = ocfs2_search_extent_list(el, cpos);
-	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+	if (index == -1) {
 		ocfs2_error(inode->i_sb,
 			    "Inode %llu has an extent at cpos %u which can no "
 			    "longer be found.\n",

fs/ocfs2/refcounttree.c

@@ -3109,7 +3109,7 @@ static int ocfs2_clear_ext_refcount(handle_t *handle,
 	el = path_leaf_el(path);
 
 	index = ocfs2_search_extent_list(el, cpos);
-	if (index == -1 || index >= le16_to_cpu(el->l_next_free_rec)) {
+	if (index == -1) {
 		ocfs2_error(sb,
 			    "Inode %llu has an extent at cpos %u which can no "
 			    "longer be found.\n",

fs/ocfs2/slot_map.c

@@ -382,7 +382,7 @@ static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
 
 	trace_ocfs2_map_slot_buffers(bytes, si->si_blocks);
 
-	si->si_bh = kzalloc(sizeof(struct buffer_head *) * si->si_blocks,
+	si->si_bh = kcalloc(si->si_blocks, sizeof(struct buffer_head *),
 			    GFP_KERNEL);
 	if (!si->si_bh) {
 		status = -ENOMEM;

fs/proc/meminfo.c

@@ -168,7 +168,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(global_page_state(NR_WRITEBACK)),
 		K(global_page_state(NR_ANON_PAGES)),
 		K(global_page_state(NR_FILE_MAPPED)),
-		K(global_page_state(NR_SHMEM)),
+		K(i.sharedram),
 		K(global_page_state(NR_SLAB_RECLAIMABLE) +
 				global_page_state(NR_SLAB_UNRECLAIMABLE)),
 		K(global_page_state(NR_SLAB_RECLAIMABLE)),

fs/proc/task_mmu.c

@@ -925,15 +925,30 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 				struct mm_walk *walk)
 {
 	struct pagemapread *pm = walk->private;
-	unsigned long addr;
+	unsigned long addr = start;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
-	for (addr = start; addr < end; addr += PAGE_SIZE) {
-		err = add_to_pagemap(addr, &pme, pm);
-		if (err)
-			break;
+	while (addr < end) {
+		struct vm_area_struct *vma = find_vma(walk->mm, addr);
+		pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
+		unsigned long vm_end;
+
+		if (!vma) {
+			vm_end = end;
+		} else {
+			vm_end = min(end, vma->vm_end);
+			if (vma->vm_flags & VM_SOFTDIRTY)
+				pme.pme |= PM_STATUS2(pm->v2, __PM_SOFT_DIRTY);
+		}
+
+		for (; addr < vm_end; addr += PAGE_SIZE) {
+			err = add_to_pagemap(addr, &pme, pm);
+			if (err)
+				goto out;
+		}
 	}
+
+out:
 	return err;
 }
 

fs/squashfs/file_direct.c

@@ -44,7 +44,7 @@ int squashfs_readpage_block(struct page *target_page, u64 block, int bsize)
 
 	pages = end_index - start_index + 1;
 
-	page = kmalloc(sizeof(void *) * pages, GFP_KERNEL);
+	page = kmalloc_array(pages, sizeof(void *), GFP_KERNEL);
 	if (page == NULL)
 		return res;
 

fs/squashfs/super.c

@@ -27,6 +27,8 @@
  * the filesystem.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/fs.h>
 #include <linux/vfs.h>
 #include <linux/slab.h>
@@ -448,8 +450,7 @@ static int __init init_squashfs_fs(void)
 		return err;
 	}
 
-	printk(KERN_INFO "squashfs: version 4.0 (2009/01/31) "
-		"Phillip Lougher\n");
+	pr_info("version 4.0 (2009/01/31) Phillip Lougher\n");
 
 	return 0;
 }

include/linux/bitmap.h

@@ -88,32 +88,32 @@
  * lib/bitmap.c provides these functions:
  */
 
-extern int __bitmap_empty(const unsigned long *bitmap, int bits);
-extern int __bitmap_full(const unsigned long *bitmap, int bits);
+extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits);
+extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits);
 extern int __bitmap_equal(const unsigned long *bitmap1,
-                	const unsigned long *bitmap2, int bits);
+			  const unsigned long *bitmap2, unsigned int nbits);
 extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
-			int bits);
+			unsigned int nbits);
 extern void __bitmap_shift_right(unsigned long *dst,
                         const unsigned long *src, int shift, int bits);
 extern void __bitmap_shift_left(unsigned long *dst,
                         const unsigned long *src, int shift, int bits);
 extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
 extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
 extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
 extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
 extern int __bitmap_intersects(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
 extern int __bitmap_subset(const unsigned long *bitmap1,
-			const unsigned long *bitmap2, int bits);
-extern int __bitmap_weight(const unsigned long *bitmap, int bits);
+			const unsigned long *bitmap2, unsigned int nbits);
+extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 
-extern void bitmap_set(unsigned long *map, int i, int len);
-extern void bitmap_clear(unsigned long *map, int start, int nr);
+extern void bitmap_set(unsigned long *map, unsigned int start, int len);
+extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
 extern unsigned long bitmap_find_next_zero_area(unsigned long *map,
 					 unsigned long size,
 					 unsigned long start,
@@ -140,9 +140,9 @@ extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
 		const unsigned long *relmap, int bits);
 extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 		int sz, int bits);
-extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
-extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
-extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
+extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
+extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
+extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
 extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
 extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
 
@@ -188,15 +188,15 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 }
 
 static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
-		return (*dst = *src1 & *src2) != 0;
+		return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_and(dst, src1, src2, nbits);
 }
 
 static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 | *src2;
@@ -205,7 +205,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 }
 
 static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 ^ *src2;
@@ -214,24 +214,24 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 }
 
 static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
-		return (*dst = *src1 & ~(*src2)) != 0;
+		return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_andnot(dst, src1, src2, nbits);
 }
 
 static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
-			int nbits)
+			unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
-		*dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
+		*dst = ~(*src);
 	else
 		__bitmap_complement(dst, src, nbits);
 }
 
 static inline int bitmap_equal(const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -240,7 +240,7 @@ static inline int bitmap_equal(const unsigned long *src1,
 }
 
 static inline int bitmap_intersects(const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
@@ -249,7 +249,7 @@ static inline int bitmap_intersects(const unsigned long *src1,
 }
 
 static inline int bitmap_subset(const unsigned long *src1,
-			const unsigned long *src2, int nbits)
+			const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
@@ -257,7 +257,7 @@ static inline int bitmap_subset(const unsigned long *src1,
 		return __bitmap_subset(src1, src2, nbits);
 }
 
-static inline int bitmap_empty(const unsigned long *src, int nbits)
+static inline int bitmap_empty(const unsigned long *src, unsigned nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -265,7 +265,7 @@ static inline int bitmap_empty(const unsigned long *src, int nbits)
 		return __bitmap_empty(src, nbits);
 }
 
-static inline int bitmap_full(const unsigned long *src, int nbits)
+static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -273,7 +273,7 @@ static inline int bitmap_full(const unsigned long *src, int nbits)
 		return __bitmap_full(src, nbits);
 }
 
-static inline int bitmap_weight(const unsigned long *src, int nbits)
+static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -284,7 +284,7 @@ static inline void bitmap_shift_right(unsigned long *dst,
 			const unsigned long *src, int n, int nbits)
 {
 	if (small_const_nbits(nbits))
-		*dst = *src >> n;
+		*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> n;
 	else
 		__bitmap_shift_right(dst, src, n, nbits);
 }

include/linux/byteorder/generic.h

@@ -2,7 +2,7 @@
 #define _LINUX_BYTEORDER_GENERIC_H
 
 /*
- * linux/byteorder_generic.h
+ * linux/byteorder/generic.h
  * Generic Byte-reordering support
  *
  * The "... p" macros, like le64_to_cpup, can be used with pointers

include/linux/cma.h

@@ -0,0 +1,27 @@
+#ifndef __CMA_H__
+#define __CMA_H__
+
+/*
+ * There is always at least global CMA area and a few optional
+ * areas configured in kernel .config.
+ */
+#ifdef CONFIG_CMA_AREAS
+#define MAX_CMA_AREAS	(1 + CONFIG_CMA_AREAS)
+
+#else
+#define MAX_CMA_AREAS	(0)
+
+#endif
+
+struct cma;
+
+extern phys_addr_t cma_get_base(struct cma *cma);
+extern unsigned long cma_get_size(struct cma *cma);
+
+extern int __init cma_declare_contiguous(phys_addr_t size,
+			phys_addr_t base, phys_addr_t limit,
+			phys_addr_t alignment, unsigned int order_per_bit,
+			bool fixed, struct cma **res_cma);
+extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align);
+extern bool cma_release(struct cma *cma, struct page *pages, int count);
+#endif

include/linux/dma-contiguous.h

@@ -53,18 +53,13 @@
 
 #ifdef __KERNEL__
 
+#include <linux/device.h>
+
 struct cma;
 struct page;
-struct device;
 
 #ifdef CONFIG_DMA_CMA
 
-/*
- * There is always at least global CMA area and a few optional device
- * private areas configured in kernel .config.
- */
-#define MAX_CMA_AREAS	(1 + CONFIG_CMA_AREAS)
-
 extern struct cma *dma_contiguous_default_area;
 
 static inline struct cma *dev_get_cma_area(struct device *dev)
@@ -123,8 +118,6 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 
 #else
 
-#define MAX_CMA_AREAS	(0)
-
 static inline struct cma *dev_get_cma_area(struct device *dev)
 {
 	return NULL;

include/linux/fs.h

@@ -2688,7 +2688,7 @@ static const struct file_operations __fops = {				\
 	.read	 = simple_attr_read,					\
 	.write	 = simple_attr_write,					\
 	.llseek	 = generic_file_llseek,					\
-};
+}
 
 static inline __printf(1, 2)
 void __simple_attr_check_format(const char *fmt, ...)

include/linux/fsnotify_backend.h

@@ -322,16 +322,18 @@ extern int fsnotify_fasync(int fd, struct file *file, int on);
 extern void fsnotify_destroy_event(struct fsnotify_group *group,
 				   struct fsnotify_event *event);
 /* attach the event to the group notification queue */
-extern int fsnotify_add_notify_event(struct fsnotify_group *group,
-				     struct fsnotify_event *event,
-				     int (*merge)(struct list_head *,
-						  struct fsnotify_event *));
+extern int fsnotify_add_event(struct fsnotify_group *group,
+			      struct fsnotify_event *event,
+			      int (*merge)(struct list_head *,
+					   struct fsnotify_event *));
+/* Remove passed event from groups notification queue */
+extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event);
 /* true if the group notification queue is empty */
 extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
 /* return, but do not dequeue the first event on the notification queue */
-extern struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group);
+extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group);
 /* return AND dequeue the first event on the notification queue */
-extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group);
+extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group);
 
 /* functions used to manipulate the marks attached to inodes */
 

include/linux/gfp.h

@@ -360,7 +360,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask);
 void *alloc_pages_exact(size_t size, gfp_t gfp_mask);
 void free_pages_exact(void *virt, size_t size);
 /* This is different from alloc_pages_exact_node !!! */
-void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
+void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask);
 
 #define __get_free_page(gfp_mask) \
 		__get_free_pages((gfp_mask), 0)

include/linux/glob.h

@@ -0,0 +1,9 @@
+#ifndef _LINUX_GLOB_H
+#define _LINUX_GLOB_H
+
+#include <linux/types.h>	/* For bool */
+#include <linux/compiler.h>	/* For __pure */
+
+bool __pure glob_match(char const *pat, char const *str);
+
+#endif	/* _LINUX_GLOB_H */

include/linux/highmem.h

@@ -93,7 +93,7 @@ static inline int kmap_atomic_idx_push(void)
 
 #ifdef CONFIG_DEBUG_HIGHMEM
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
-	BUG_ON(idx > KM_TYPE_NR);
+	BUG_ON(idx >= KM_TYPE_NR);
 #endif
 	return idx;
 }

include/linux/huge_mm.h

@@ -93,10 +93,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
 #endif /* CONFIG_DEBUG_VM */
 
 extern unsigned long transparent_hugepage_flags;
-extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-			  pmd_t *dst_pmd, pmd_t *src_pmd,
-			  struct vm_area_struct *vma,
-			  unsigned long addr, unsigned long end);
 extern int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {

include/linux/hugetlb.h

@@ -87,7 +87,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
 #endif
 
 extern unsigned long hugepages_treat_as_movable;
-extern const unsigned long hugetlb_zero, hugetlb_infinity;
 extern int sysctl_hugetlb_shm_group;
 extern struct list_head huge_boot_pages;
 

include/linux/kernel.h

@@ -493,11 +493,6 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte)
 	return buf;
 }
 
-static inline char * __deprecated pack_hex_byte(char *buf, u8 byte)
-{
-	return hex_byte_pack(buf, byte);
-}
-
 extern int hex_to_bin(char ch);
 extern int __must_check hex2bin(u8 *dst, const char *src, size_t count);
 

include/linux/klist.h

@@ -44,7 +44,7 @@ struct klist_node {
 
 extern void klist_add_tail(struct klist_node *n, struct klist *k);
 extern void klist_add_head(struct klist_node *n, struct klist *k);
-extern void klist_add_after(struct klist_node *n, struct klist_node *pos);
+extern void klist_add_behind(struct klist_node *n, struct klist_node *pos);
 extern void klist_add_before(struct klist_node *n, struct klist_node *pos);
 
 extern void klist_del(struct klist_node *n);

include/linux/list.h

@@ -654,15 +654,15 @@ static inline void hlist_add_before(struct hlist_node *n,
 	*(n->pprev) = n;
 }
 
-static inline void hlist_add_after(struct hlist_node *n,
-					struct hlist_node *next)
+static inline void hlist_add_behind(struct hlist_node *n,
+				    struct hlist_node *prev)
 {
-	next->next = n->next;
-	n->next = next;
-	next->pprev = &n->next;
+	n->next = prev->next;
+	prev->next = n;
+	n->pprev = &prev->next;
 
-	if(next->next)
-		next->next->pprev  = &next->next;
+	if (n->next)
+		n->next->pprev  = &n->next;
 }
 
 /* after that we'll appear to be on some hlist and hlist_del will work */

include/linux/memblock.h

@@ -249,7 +249,7 @@ phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
 /*
  * Set the allocation direction to bottom-up or top-down.
  */
-static inline void memblock_set_bottom_up(bool enable)
+static inline void __init memblock_set_bottom_up(bool enable)
 {
 	memblock.bottom_up = enable;
 }
@@ -264,7 +264,7 @@ static inline bool memblock_bottom_up(void)
 	return memblock.bottom_up;
 }
 #else
-static inline void memblock_set_bottom_up(bool enable) {}
+static inline void __init memblock_set_bottom_up(bool enable) {}
 static inline bool memblock_bottom_up(void) { return false; }
 #endif
 

include/linux/memory_hotplug.h

@@ -26,11 +26,12 @@ enum {
 	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
 };
 
-/* Types for control the zone type of onlined memory */
+/* Types for control the zone type of onlined and offlined memory */
 enum {
-	ONLINE_KEEP,
-	ONLINE_KERNEL,
-	ONLINE_MOVABLE,
+	MMOP_OFFLINE = -1,
+	MMOP_ONLINE_KEEP,
+	MMOP_ONLINE_KERNEL,
+	MMOP_ONLINE_MOVABLE,
 };
 
 /*
@@ -258,6 +259,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {}
 extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
+extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default);
 extern int arch_add_memory(int nid, u64 start, u64 size);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);

include/linux/mmdebug.h

@@ -20,11 +20,13 @@ extern void dump_page_badflags(struct page *page, const char *reason,
 	} 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)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
 #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #endif
 
 #ifdef CONFIG_DEBUG_VIRTUAL

include/linux/mmu_notifier.h

@@ -170,6 +170,8 @@ extern int __mmu_notifier_register(struct mmu_notifier *mn,
 				   struct mm_struct *mm);
 extern void mmu_notifier_unregister(struct mmu_notifier *mn,
 				    struct mm_struct *mm);
+extern void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
+					       struct mm_struct *mm);
 extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
@@ -288,6 +290,10 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	set_pte_at(___mm, ___address, __ptep, ___pte);			\
 })
 
+extern void mmu_notifier_call_srcu(struct rcu_head *rcu,
+				   void (*func)(struct rcu_head *rcu));
+extern void mmu_notifier_synchronize(void);
+
 #else /* CONFIG_MMU_NOTIFIER */
 
 static inline void mmu_notifier_release(struct mm_struct *mm)

include/linux/mmzone.h

@@ -143,6 +143,7 @@ enum zone_stat_item {
 	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
+	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 #ifdef CONFIG_NUMA
 	NUMA_HIT,		/* allocated in intended node */
 	NUMA_MISS,		/* allocated in non intended node */
@@ -324,18 +325,11 @@ enum zone_type {
 #ifndef __GENERATING_BOUNDS_H
 
 struct zone {
-	/* Fields commonly accessed by the page allocator */
+	/* Read-mostly fields */
 
 	/* zone watermarks, access with *_wmark_pages(zone) macros */
 	unsigned long watermark[NR_WMARK];
 
-	/*
-	 * When free pages are below this point, additional steps are taken
-	 * when reading the number of free pages to avoid per-cpu counter
-	 * drift allowing watermarks to be breached
-	 */
-	unsigned long percpu_drift_mark;
-
 	/*
 	 * We don't know if the memory that we're going to allocate will be freeable
 	 * or/and it will be released eventually, so to avoid totally wasting several
@@ -344,7 +338,20 @@ struct zone {
 	 * on the higher zones). This array is recalculated at runtime if the
 	 * sysctl_lowmem_reserve_ratio sysctl changes.
 	 */
-	unsigned long		lowmem_reserve[MAX_NR_ZONES];
+	long lowmem_reserve[MAX_NR_ZONES];
+
+#ifdef CONFIG_NUMA
+	int node;
+#endif
+
+	/*
+	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+	 * this zone's LRU.  Maintained by the pageout code.
+	 */
+	unsigned int inactive_ratio;
+
+	struct pglist_data	*zone_pgdat;
+	struct per_cpu_pageset __percpu *pageset;
 
 	/*
 	 * This is a per-zone reserve of pages that should not be
@@ -352,34 +359,6 @@ struct zone {
 	 */
 	unsigned long		dirty_balance_reserve;
 
-#ifdef CONFIG_NUMA
-	int node;
-	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
-	 */
-	unsigned long		min_unmapped_pages;
-	unsigned long		min_slab_pages;
-#endif
-	struct per_cpu_pageset __percpu *pageset;
-	/*
-	 * free areas of different sizes
-	 */
-	spinlock_t		lock;
-#if defined CONFIG_COMPACTION || defined CONFIG_CMA
-	/* Set to true when the PG_migrate_skip bits should be cleared */
-	bool			compact_blockskip_flush;
-
-	/* pfn where compaction free scanner should start */
-	unsigned long		compact_cached_free_pfn;
-	/* pfn where async and sync compaction migration scanner should start */
-	unsigned long		compact_cached_migrate_pfn[2];
-#endif
-#ifdef CONFIG_MEMORY_HOTPLUG
-	/* see spanned/present_pages for more description */
-	seqlock_t		span_seqlock;
-#endif
-	struct free_area	free_area[MAX_ORDER];
-
 #ifndef CONFIG_SPARSEMEM
 	/*
 	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -388,74 +367,14 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_COMPACTION
+#ifdef CONFIG_NUMA
 	/*
-	 * On compaction failure, 1<<compact_defer_shift compactions
-	 * are skipped before trying again. The number attempted since
-	 * last failure is tracked with compact_considered.
+	 * zone reclaim becomes active if more unmapped pages exist.
 	 */
-	unsigned int		compact_considered;
-	unsigned int		compact_defer_shift;
-	int			compact_order_failed;
-#endif
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
+#endif /* CONFIG_NUMA */
 
-	ZONE_PADDING(_pad1_)
-
-	/* Fields commonly accessed by the page reclaim scanner */
-	spinlock_t		lru_lock;
-	struct lruvec		lruvec;
-
-	/* Evictions & activations on the inactive file list */
-	atomic_long_t		inactive_age;
-
-	unsigned long		pages_scanned;	   /* since last reclaim */
-	unsigned long		flags;		   /* zone flags, see below */
-
-	/* Zone statistics */
-	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
-
-	/*
-	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
-	 * this zone's LRU.  Maintained by the pageout code.
-	 */
-	unsigned int inactive_ratio;
-
-
-	ZONE_PADDING(_pad2_)
-	/* Rarely used or read-mostly fields */
-
-	/*
-	 * wait_table		-- the array holding the hash table
-	 * wait_table_hash_nr_entries	-- the size of the hash table array
-	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
-	 *
-	 * The purpose of all these is to keep track of the people
-	 * waiting for a page to become available and make them
-	 * runnable again when possible. The trouble is that this
-	 * consumes a lot of space, especially when so few things
-	 * wait on pages at a given time. So instead of using
-	 * per-page waitqueues, we use a waitqueue hash table.
-	 *
-	 * The bucket discipline is to sleep on the same queue when
-	 * colliding and wake all in that wait queue when removing.
-	 * When something wakes, it must check to be sure its page is
-	 * truly available, a la thundering herd. The cost of a
-	 * collision is great, but given the expected load of the
-	 * table, they should be so rare as to be outweighed by the
-	 * benefits from the saved space.
-	 *
-	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
-	 * primary users of these fields, and in mm/page_alloc.c
-	 * free_area_init_core() performs the initialization of them.
-	 */
-	wait_queue_head_t	* wait_table;
-	unsigned long		wait_table_hash_nr_entries;
-	unsigned long		wait_table_bits;
-
-	/*
-	 * Discontig memory support fields.
-	 */
-	struct pglist_data	*zone_pgdat;
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
@@ -500,9 +419,11 @@ struct zone {
 	 * adjust_managed_page_count() should be used instead of directly
 	 * touching zone->managed_pages and totalram_pages.
 	 */
+	unsigned long		managed_pages;
 	unsigned long		spanned_pages;
 	unsigned long		present_pages;
-	unsigned long		managed_pages;
+
+	const char		*name;
 
 	/*
 	 * Number of MIGRATE_RESEVE page block. To maintain for just
@@ -510,10 +431,94 @@ struct zone {
 	 */
 	int			nr_migrate_reserve_block;
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+	/* see spanned/present_pages for more description */
+	seqlock_t		span_seqlock;
+#endif
+
 	/*
-	 * rarely used fields:
+	 * wait_table		-- the array holding the hash table
+	 * wait_table_hash_nr_entries	-- the size of the hash table array
+	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
+	 *
+	 * The purpose of all these is to keep track of the people
+	 * waiting for a page to become available and make them
+	 * runnable again when possible. The trouble is that this
+	 * consumes a lot of space, especially when so few things
+	 * wait on pages at a given time. So instead of using
+	 * per-page waitqueues, we use a waitqueue hash table.
+	 *
+	 * The bucket discipline is to sleep on the same queue when
+	 * colliding and wake all in that wait queue when removing.
+	 * When something wakes, it must check to be sure its page is
+	 * truly available, a la thundering herd. The cost of a
+	 * collision is great, but given the expected load of the
+	 * table, they should be so rare as to be outweighed by the
+	 * benefits from the saved space.
+	 *
+	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
+	 * primary users of these fields, and in mm/page_alloc.c
+	 * free_area_init_core() performs the initialization of them.
 	 */
-	const char		*name;
+	wait_queue_head_t	*wait_table;
+	unsigned long		wait_table_hash_nr_entries;
+	unsigned long		wait_table_bits;
+
+	ZONE_PADDING(_pad1_)
+
+	/* Write-intensive fields used from the page allocator */
+	spinlock_t		lock;
+
+	/* free areas of different sizes */
+	struct free_area	free_area[MAX_ORDER];
+
+	/* zone flags, see below */
+	unsigned long		flags;
+
+	ZONE_PADDING(_pad2_)
+
+	/* Write-intensive fields used by page reclaim */
+
+	/* Fields commonly accessed by the page reclaim scanner */
+	spinlock_t		lru_lock;
+	struct lruvec		lruvec;
+
+	/* Evictions & activations on the inactive file list */
+	atomic_long_t		inactive_age;
+
+	/*
+	 * When free pages are below this point, additional steps are taken
+	 * when reading the number of free pages to avoid per-cpu counter
+	 * drift allowing watermarks to be breached
+	 */
+	unsigned long percpu_drift_mark;
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* pfn where compaction free scanner should start */
+	unsigned long		compact_cached_free_pfn;
+	/* pfn where async and sync compaction migration scanner should start */
+	unsigned long		compact_cached_migrate_pfn[2];
+#endif
+
+#ifdef CONFIG_COMPACTION
+	/*
+	 * On compaction failure, 1<<compact_defer_shift compactions
+	 * are skipped before trying again. The number attempted since
+	 * last failure is tracked with compact_considered.
+	 */
+	unsigned int		compact_considered;
+	unsigned int		compact_defer_shift;
+	int			compact_order_failed;
+#endif
+
+#if defined CONFIG_COMPACTION || defined CONFIG_CMA
+	/* Set to true when the PG_migrate_skip bits should be cleared */
+	bool			compact_blockskip_flush;
+#endif
+
+	ZONE_PADDING(_pad3_)
+	/* Zone statistics */
+	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
 typedef enum {
@@ -529,6 +534,7 @@ typedef enum {
 	ZONE_WRITEBACK,			/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
+	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
 } zone_flags_t;
 
 static inline void zone_set_flag(struct zone *zone, zone_flags_t flag)
@@ -566,6 +572,11 @@ static inline int zone_is_reclaim_locked(const struct zone *zone)
 	return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags);
 }
 
+static inline int zone_is_fair_depleted(const struct zone *zone)
+{
+	return test_bit(ZONE_FAIR_DEPLETED, &zone->flags);
+}
+
 static inline int zone_is_oom_locked(const struct zone *zone)
 {
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
@@ -872,6 +883,8 @@ static inline int zone_movable_is_highmem(void)
 {
 #if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
 	return movable_zone == ZONE_HIGHMEM;
+#elif defined(CONFIG_HIGHMEM)
+	return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
 #else
 	return 0;
 #endif

include/linux/nodemask.h

@@ -430,7 +430,15 @@ static inline int num_node_state(enum node_states state)
 	for_each_node_mask((__node), node_states[__state])
 
 #define first_online_node	first_node(node_states[N_ONLINE])
-#define next_online_node(nid)	next_node((nid), node_states[N_ONLINE])
+#define first_memory_node	first_node(node_states[N_MEMORY])
+static inline int next_online_node(int nid)
+{
+	return next_node(nid, node_states[N_ONLINE]);
+}
+static inline int next_memory_node(int nid)
+{
+	return next_node(nid, node_states[N_MEMORY]);
+}
 
 extern int nr_node_ids;
 extern int nr_online_nodes;
@@ -471,6 +479,7 @@ static inline int num_node_state(enum node_states state)
 	for ( (node) = 0; (node) == 0; (node) = 1)
 
 #define first_online_node	0
+#define first_memory_node	0
 #define next_online_node(nid)	(MAX_NUMNODES)
 #define nr_node_ids		1
 #define nr_online_nodes		1

include/linux/oom.h

@@ -55,8 +55,8 @@ extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 			     struct mem_cgroup *memcg, nodemask_t *nodemask,
 			     const char *message);
 
-extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
-extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
+extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags);
+extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags);
 
 extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask,
 			       int order, const nodemask_t *nodemask);

include/linux/page-flags.h

@@ -171,13 +171,12 @@ static inline int __TestClearPage##uname(struct page *page)		\
 #define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname)		\
 	__SETPAGEFLAG(uname, lname)  __CLEARPAGEFLAG(uname, lname)
 
-#define PAGEFLAG_FALSE(uname) 						\
-static inline int Page##uname(const struct page *page)			\
-			{ return 0; }
-
 #define TESTSCFLAG(uname, lname)					\
 	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
 
+#define TESTPAGEFLAG_FALSE(uname)					\
+static inline int Page##uname(const struct page *page) { return 0; }
+
 #define SETPAGEFLAG_NOOP(uname)						\
 static inline void SetPage##uname(struct page *page) {  }
 
@@ -187,12 +186,21 @@ static inline void ClearPage##uname(struct page *page) {  }
 #define __CLEARPAGEFLAG_NOOP(uname)					\
 static inline void __ClearPage##uname(struct page *page) {  }
 
+#define TESTSETFLAG_FALSE(uname)					\
+static inline int TestSetPage##uname(struct page *page) { return 0; }
+
 #define TESTCLEARFLAG_FALSE(uname)					\
 static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 #define __TESTCLEARFLAG_FALSE(uname)					\
 static inline int __TestClearPage##uname(struct page *page) { return 0; }
 
+#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname)			\
+	SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname)
+
+#define TESTSCFLAG_FALSE(uname)						\
+	TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
+
 struct page;	/* forward declaration */
 
 TESTPAGEFLAG(Locked, locked)
@@ -248,7 +256,6 @@ PAGEFLAG_FALSE(HighMem)
 PAGEFLAG(SwapCache, swapcache)
 #else
 PAGEFLAG_FALSE(SwapCache)
-	SETPAGEFLAG_NOOP(SwapCache) CLEARPAGEFLAG_NOOP(SwapCache)
 #endif
 
 PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
@@ -258,8 +265,8 @@ PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
 PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
 	TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
 #else
-PAGEFLAG_FALSE(Mlocked) SETPAGEFLAG_NOOP(Mlocked)
-	TESTCLEARFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
+PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
+	TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
 #endif
 
 #ifdef CONFIG_ARCH_USES_PG_UNCACHED

include/linux/pagemap.h

@@ -484,6 +484,9 @@ static inline int lock_page_killable(struct page *page)
 /*
  * lock_page_or_retry - Lock the page, unless this would block and the
  * caller indicated that it can handle a retry.
+ *
+ * Return value and mmap_sem implications depend on flags; see
+ * __lock_page_or_retry().
  */
 static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				     unsigned int flags)

include/linux/printk.h

@@ -31,7 +31,7 @@ static inline const char *printk_skip_level(const char *buffer)
 }
 
 /* printk's without a loglevel use this.. */
-#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL
+#define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT
 
 /* We show everything that is MORE important than this.. */
 #define CONSOLE_LOGLEVEL_SILENT  0 /* Mum's the word */

include/linux/rculist.h

@@ -432,9 +432,9 @@ static inline void hlist_add_before_rcu(struct hlist_node *n,
 }
 
 /**
- * hlist_add_after_rcu
- * @prev: the existing element to add the new element after.
+ * hlist_add_behind_rcu
  * @n: the new element to add to the hash list.
+ * @prev: the existing element to add the new element after.
  *
  * Description:
  * Adds the specified element to the specified hlist
@@ -449,8 +449,8 @@ static inline void hlist_add_before_rcu(struct hlist_node *n,
  * hlist_for_each_entry_rcu(), used to prevent memory-consistency
  * problems on Alpha CPUs.
  */
-static inline void hlist_add_after_rcu(struct hlist_node *prev,
-				       struct hlist_node *n)
+static inline void hlist_add_behind_rcu(struct hlist_node *n,
+					struct hlist_node *prev)
 {
 	n->next = prev->next;
 	n->pprev = &prev->next;

include/linux/swap.h

@@ -311,7 +311,6 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail,
 			 struct lruvec *lruvec, struct list_head *head);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
-extern void init_page_accessed(struct page *page);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
 extern void lru_add_drain_all(void);

include/linux/vmalloc.h

@@ -113,7 +113,7 @@ extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
 
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
-			struct page ***pages);
+			struct page **pages);
 #ifdef CONFIG_MMU
 extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
 				    pgprot_t prot, struct page **pages);

include/linux/zbud.h

@@ -11,7 +11,7 @@ struct zbud_ops {
 
 struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops);
 void zbud_destroy_pool(struct zbud_pool *pool);
-int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp,
+int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp,
 	unsigned long *handle);
 void zbud_free(struct zbud_pool *pool, unsigned long handle);
 int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries);

include/linux/zlib.h

@@ -493,64 +493,6 @@ extern int deflateInit2 (z_streamp strm,
    method). msg is set to null if there is no error message.  deflateInit2 does
    not perform any compression: this will be done by deflate().
 */
-                            
-#if 0
-extern int zlib_deflateSetDictionary (z_streamp strm,
-						     const Byte *dictionary,
-						     uInt  dictLength);
-#endif
-/*
-     Initializes the compression dictionary from the given byte sequence
-   without producing any compressed output. This function must be called
-   immediately after deflateInit, deflateInit2 or deflateReset, before any
-   call of deflate. The compressor and decompressor must use exactly the same
-   dictionary (see inflateSetDictionary).
-
-     The dictionary should consist of strings (byte sequences) that are likely
-   to be encountered later in the data to be compressed, with the most commonly
-   used strings preferably put towards the end of the dictionary. Using a
-   dictionary is most useful when the data to be compressed is short and can be
-   predicted with good accuracy; the data can then be compressed better than
-   with the default empty dictionary.
-
-     Depending on the size of the compression data structures selected by
-   deflateInit or deflateInit2, a part of the dictionary may in effect be
-   discarded, for example if the dictionary is larger than the window size in
-   deflate or deflate2. Thus the strings most likely to be useful should be
-   put at the end of the dictionary, not at the front.
-
-     Upon return of this function, strm->adler is set to the Adler32 value
-   of the dictionary; the decompressor may later use this value to determine
-   which dictionary has been used by the compressor. (The Adler32 value
-   applies to the whole dictionary even if only a subset of the dictionary is
-   actually used by the compressor.)
-
-     deflateSetDictionary returns Z_OK if success, or Z_STREAM_ERROR if a
-   parameter is invalid (such as NULL dictionary) or the stream state is
-   inconsistent (for example if deflate has already been called for this stream
-   or if the compression method is bsort). deflateSetDictionary does not
-   perform any compression: this will be done by deflate().
-*/
-
-#if 0
-extern int zlib_deflateCopy (z_streamp dest, z_streamp source);
-#endif
-
-/*
-     Sets the destination stream as a complete copy of the source stream.
-
-     This function can be useful when several compression strategies will be
-   tried, for example when there are several ways of pre-processing the input
-   data with a filter. The streams that will be discarded should then be freed
-   by calling deflateEnd.  Note that deflateCopy duplicates the internal
-   compression state which can be quite large, so this strategy is slow and
-   can consume lots of memory.
-
-     deflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not
-   enough memory, Z_STREAM_ERROR if the source stream state was inconsistent
-   (such as zalloc being NULL). msg is left unchanged in both source and
-   destination.
-*/
 
 extern int zlib_deflateReset (z_streamp strm);
 /*
@@ -568,27 +510,6 @@ static inline unsigned long deflateBound(unsigned long s)
 	return s + ((s + 7) >> 3) + ((s + 63) >> 6) + 11;
 }
 
-#if 0
-extern int zlib_deflateParams (z_streamp strm, int level, int strategy);
-#endif
-/*
-     Dynamically update the compression level and compression strategy.  The
-   interpretation of level and strategy is as in deflateInit2.  This can be
-   used to switch between compression and straight copy of the input data, or
-   to switch to a different kind of input data requiring a different
-   strategy. If the compression level is changed, the input available so far
-   is compressed with the old level (and may be flushed); the new level will
-   take effect only at the next call of deflate().
-
-     Before the call of deflateParams, the stream state must be set as for
-   a call of deflate(), since the currently available input may have to
-   be compressed and flushed. In particular, strm->avail_out must be non-zero.
-
-     deflateParams returns Z_OK if success, Z_STREAM_ERROR if the source
-   stream state was inconsistent or if a parameter was invalid, Z_BUF_ERROR
-   if strm->avail_out was zero.
-*/
-
 /*   
 extern int inflateInit2 (z_streamp strm, int  windowBits);
 
@@ -631,45 +552,6 @@ extern int inflateInit2 (z_streamp strm, int  windowBits);
    and avail_out are unchanged.)
 */
 
-extern int zlib_inflateSetDictionary (z_streamp strm,
-						     const Byte *dictionary,
-						     uInt  dictLength);
-/*
-     Initializes the decompression dictionary from the given uncompressed byte
-   sequence. This function must be called immediately after a call of inflate,
-   if that call returned Z_NEED_DICT. The dictionary chosen by the compressor
-   can be determined from the adler32 value returned by that call of inflate.
-   The compressor and decompressor must use exactly the same dictionary (see
-   deflateSetDictionary).  For raw inflate, this function can be called
-   immediately after inflateInit2() or inflateReset() and before any call of
-   inflate() to set the dictionary.  The application must insure that the
-   dictionary that was used for compression is provided.
-
-     inflateSetDictionary returns Z_OK if success, Z_STREAM_ERROR if a
-   parameter is invalid (such as NULL dictionary) or the stream state is
-   inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the
-   expected one (incorrect adler32 value). inflateSetDictionary does not
-   perform any decompression: this will be done by subsequent calls of
-   inflate().
-*/
-
-#if 0
-extern int zlib_inflateSync (z_streamp strm);
-#endif
-/* 
-    Skips invalid compressed data until a full flush point (see above the
-  description of deflate with Z_FULL_FLUSH) can be found, or until all
-  available input is skipped. No output is provided.
-
-    inflateSync returns Z_OK if a full flush point has been found, Z_BUF_ERROR
-  if no more input was provided, Z_DATA_ERROR if no flush point has been found,
-  or Z_STREAM_ERROR if the stream structure was inconsistent. In the success
-  case, the application may save the current current value of total_in which
-  indicates where valid compressed data was found. In the error case, the
-  application may repeatedly call inflateSync, providing more input each time,
-  until success or end of the input data.
-*/
-
 extern int zlib_inflateReset (z_streamp strm);
 /*
      This function is equivalent to inflateEnd followed by inflateInit,

include/linux/zpool.h

@@ -0,0 +1,106 @@
+/*
+ * zpool memory storage api
+ *
+ * Copyright (C) 2014 Dan Streetman
+ *
+ * This is a common frontend for the zbud and zsmalloc memory
+ * storage pool implementations.  Typically, this is used to
+ * store compressed memory.
+ */
+
+#ifndef _ZPOOL_H_
+#define _ZPOOL_H_
+
+struct zpool;
+
+struct zpool_ops {
+	int (*evict)(struct zpool *pool, unsigned long handle);
+};
+
+/*
+ * Control how a handle is mapped.  It will be ignored if the
+ * implementation does not support it.  Its use is optional.
+ * Note that this does not refer to memory protection, it
+ * refers to how the memory will be copied in/out if copying
+ * is necessary during mapping; read-write is the safest as
+ * it copies the existing memory in on map, and copies the
+ * changed memory back out on unmap.  Write-only does not copy
+ * in the memory and should only be used for initialization.
+ * If in doubt, use ZPOOL_MM_DEFAULT which is read-write.
+ */
+enum zpool_mapmode {
+	ZPOOL_MM_RW, /* normal read-write mapping */
+	ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */
+	ZPOOL_MM_WO, /* write-only (no copy-in at map time) */
+
+	ZPOOL_MM_DEFAULT = ZPOOL_MM_RW
+};
+
+struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops);
+
+char *zpool_get_type(struct zpool *pool);
+
+void zpool_destroy_pool(struct zpool *pool);
+
+int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp,
+			unsigned long *handle);
+
+void zpool_free(struct zpool *pool, unsigned long handle);
+
+int zpool_shrink(struct zpool *pool, unsigned int pages,
+			unsigned int *reclaimed);
+
+void *zpool_map_handle(struct zpool *pool, unsigned long handle,
+			enum zpool_mapmode mm);
+
+void zpool_unmap_handle(struct zpool *pool, unsigned long handle);
+
+u64 zpool_get_total_size(struct zpool *pool);
+
+
+/**
+ * struct zpool_driver - driver implementation for zpool
+ * @type:	name of the driver.
+ * @list:	entry in the list of zpool drivers.
+ * @create:	create a new pool.
+ * @destroy:	destroy a pool.
+ * @malloc:	allocate mem from a pool.
+ * @free:	free mem from a pool.
+ * @shrink:	shrink the pool.
+ * @map:	map a handle.
+ * @unmap:	unmap a handle.
+ * @total_size:	get total size of a pool.
+ *
+ * This is created by a zpool implementation and registered
+ * with zpool.
+ */
+struct zpool_driver {
+	char *type;
+	struct module *owner;
+	atomic_t refcount;
+	struct list_head list;
+
+	void *(*create)(gfp_t gfp, struct zpool_ops *ops);
+	void (*destroy)(void *pool);
+
+	int (*malloc)(void *pool, size_t size, gfp_t gfp,
+				unsigned long *handle);
+	void (*free)(void *pool, unsigned long handle);
+
+	int (*shrink)(void *pool, unsigned int pages,
+				unsigned int *reclaimed);
+
+	void *(*map)(void *pool, unsigned long handle,
+				enum zpool_mapmode mm);
+	void (*unmap)(void *pool, unsigned long handle);
+
+	u64 (*total_size)(void *pool);
+};
+
+void zpool_register_driver(struct zpool_driver *driver);
+
+int zpool_unregister_driver(struct zpool_driver *driver);
+
+int zpool_evict(void *pool, unsigned long handle);
+
+#endif

include/trace/events/migrate.h

@@ -17,6 +17,7 @@
 	{MR_MEMORY_HOTPLUG,	"memory_hotplug"},		\
 	{MR_SYSCALL,		"syscall_or_cpuset"},		\
 	{MR_MEMPOLICY_MBIND,	"mempolicy_mbind"},		\
+	{MR_NUMA_MISPLACED,	"numa_misplaced"},		\
 	{MR_CMA,		"cma"}
 
 TRACE_EVENT(mm_migrate_pages,

include/trace/events/pagemap.h

@@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion,
 
 	TP_PROTO(
 		struct page *page,
-		unsigned long pfn,
-		int lru,
-		unsigned long flags
+		int lru
 	),
 
-	TP_ARGS(page, pfn, lru, flags),
+	TP_ARGS(page, lru),
 
 	TP_STRUCT__entry(
 		__field(struct page *,	page	)
@@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion,
 
 	TP_fast_assign(
 		__entry->page	= page;
-		__entry->pfn	= pfn;
+		__entry->pfn	= page_to_pfn(page);
 		__entry->lru	= lru;
-		__entry->flags	= flags;
+		__entry->flags	= trace_pagemap_flags(page);
 	),
 
 	/* Flag format is based on page-types.c formatting for pagemap */
@@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion,
 
 TRACE_EVENT(mm_lru_activate,
 
-	TP_PROTO(struct page *page, unsigned long pfn),
+	TP_PROTO(struct page *page),
 
-	TP_ARGS(page, pfn),
+	TP_ARGS(page),
 
 	TP_STRUCT__entry(
 		__field(struct page *,	page	)
@@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate,
 
 	TP_fast_assign(
 		__entry->page	= page;
-		__entry->pfn	= pfn;
+		__entry->pfn	= page_to_pfn(page);
 	),
 
 	/* Flag format is based on page-types.c formatting for pagemap */

init/Kconfig

@@ -807,15 +807,53 @@ config LOG_BUF_SHIFT
 	range 12 21
 	default 17
 	help
-	  Select kernel log buffer size as a power of 2.
+	  Select the minimal kernel log buffer size as a power of 2.
+	  The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
+	  parameter, see below. Any higher size also might be forced
+	  by "log_buf_len" boot parameter.
+
 	  Examples:
-	  	     17 => 128 KB
+		     17 => 128 KB
 		     16 => 64 KB
-	             15 => 32 KB
-	             14 => 16 KB
+		     15 => 32 KB
+		     14 => 16 KB
 		     13 =>  8 KB
 		     12 =>  4 KB
 
+config LOG_CPU_MAX_BUF_SHIFT
+	int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
+	range 0 21
+	default 12 if !BASE_SMALL
+	default 0 if BASE_SMALL
+	help
+	  This option allows to increase the default ring buffer size
+	  according to the number of CPUs. The value defines the contribution
+	  of each CPU as a power of 2. The used space is typically only few
+	  lines however it might be much more when problems are reported,
+	  e.g. backtraces.
+
+	  The increased size means that a new buffer has to be allocated and
+	  the original static one is unused. It makes sense only on systems
+	  with more CPUs. Therefore this value is used only when the sum of
+	  contributions is greater than the half of the default kernel ring
+	  buffer as defined by LOG_BUF_SHIFT. The default values are set
+	  so that more than 64 CPUs are needed to trigger the allocation.
+
+	  Also this option is ignored when "log_buf_len" kernel parameter is
+	  used as it forces an exact (power of two) size of the ring buffer.
+
+	  The number of possible CPUs is used for this computation ignoring
+	  hotplugging making the compuation optimal for the the worst case
+	  scenerio while allowing a simple algorithm to be used from bootup.
+
+	  Examples shift values and their meaning:
+		     17 => 128 KB for each CPU
+		     16 =>  64 KB for each CPU
+		     15 =>  32 KB for each CPU
+		     14 =>  16 KB for each CPU
+		     13 =>   8 KB for each CPU
+		     12 =>   4 KB for each CPU
+
 #
 # Architectures with an unreliable sched_clock() should select this:
 #

kernel/auditfilter.c

@@ -106,7 +106,7 @@ static inline struct audit_entry *audit_init_entry(u32 field_count)
 	if (unlikely(!entry))
 		return NULL;
 
-	fields = kzalloc(sizeof(*fields) * field_count, GFP_KERNEL);
+	fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL);
 	if (unlikely(!fields)) {
 		kfree(entry);
 		return NULL;
@@ -160,7 +160,7 @@ static __u32 *classes[AUDIT_SYSCALL_CLASSES];
 
 int __init audit_register_class(int class, unsigned *list)
 {
-	__u32 *p = kzalloc(AUDIT_BITMASK_SIZE * sizeof(__u32), GFP_KERNEL);
+	__u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 	while (*list != ~0U) {

kernel/exit.c

@@ -455,6 +455,7 @@ static void exit_mm(struct task_struct * tsk)
 	task_unlock(tsk);
 	mm_update_next_owner(mm);
 	mmput(mm);
+	clear_thread_flag(TIF_MEMDIE);
 }
 
 /*

kernel/printk/printk.c

@@ -45,6 +45,7 @@
 #include <linux/poll.h>
 #include <linux/irq_work.h>
 #include <linux/utsname.h>
+#include <linux/ctype.h>
 
 #include <asm/uaccess.h>
 
@@ -56,7 +57,7 @@
 
 int console_printk[4] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* console_loglevel */
-	DEFAULT_MESSAGE_LOGLEVEL,	/* default_message_loglevel */
+	MESSAGE_LOGLEVEL_DEFAULT,	/* default_message_loglevel */
 	CONSOLE_LOGLEVEL_MIN,		/* minimum_console_loglevel */
 	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
 };
@@ -113,9 +114,9 @@ static int __down_trylock_console_sem(unsigned long ip)
  * This is used for debugging the mess that is the VT code by
  * keeping track if we have the console semaphore held. It's
  * definitely not the perfect debug tool (we don't know if _WE_
- * hold it are racing, but it helps tracking those weird code
- * path in the console code where we end up in places I want
- * locked without the console sempahore held
+ * hold it and are racing, but it helps tracking those weird code
+ * paths in the console code where we end up in places I want
+ * locked without the console sempahore held).
  */
 static int console_locked, console_suspended;
 
@@ -146,8 +147,8 @@ static int console_may_schedule;
  * the overall length of the record.
  *
  * The heads to the first and last entry in the buffer, as well as the
- * sequence numbers of these both entries are maintained when messages
- * are stored..
+ * sequence numbers of these entries are maintained when messages are
+ * stored.
  *
  * If the heads indicate available messages, the length in the header
  * tells the start next message. A length == 0 for the next message
@@ -257,7 +258,7 @@ static u64 clear_seq;
 static u32 clear_idx;
 
 #define PREFIX_MAX		32
-#define LOG_LINE_MAX		1024 - PREFIX_MAX
+#define LOG_LINE_MAX		(1024 - PREFIX_MAX)
 
 /* record buffer */
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
@@ -266,6 +267,7 @@ static u32 clear_idx;
 #define LOG_ALIGN __alignof__(struct printk_log)
 #endif
 #define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
+#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)
 static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
@@ -344,7 +346,7 @@ static int log_make_free_space(u32 msg_size)
 	while (log_first_seq < log_next_seq) {
 		if (logbuf_has_space(msg_size, false))
 			return 0;
-		/* drop old messages until we have enough continuous space */
+		/* drop old messages until we have enough contiguous space */
 		log_first_idx = log_next(log_first_idx);
 		log_first_seq++;
 	}
@@ -453,11 +455,7 @@ static int log_store(int facility, int level,
 	return msg->text_len;
 }
 
-#ifdef CONFIG_SECURITY_DMESG_RESTRICT
-int dmesg_restrict = 1;
-#else
-int dmesg_restrict;
-#endif
+int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT);
 
 static int syslog_action_restricted(int type)
 {
@@ -828,34 +826,74 @@ void log_buf_kexec_setup(void)
 /* requested log_buf_len from kernel cmdline */
 static unsigned long __initdata new_log_buf_len;
 
+/* we practice scaling the ring buffer by powers of 2 */
+static void __init log_buf_len_update(unsigned size)
+{
+	if (size)
+		size = roundup_pow_of_two(size);
+	if (size > log_buf_len)
+		new_log_buf_len = size;
+}
+
 /* save requested log_buf_len since it's too early to process it */
 static int __init log_buf_len_setup(char *str)
 {
 	unsigned size = memparse(str, &str);
 
-	if (size)
-		size = roundup_pow_of_two(size);
-	if (size > log_buf_len)
-		new_log_buf_len = size;
+	log_buf_len_update(size);
 
 	return 0;
 }
 early_param("log_buf_len", log_buf_len_setup);
 
+static void __init log_buf_add_cpu(void)
+{
+	unsigned int cpu_extra;
+
+	/*
+	 * archs should set up cpu_possible_bits properly with
+	 * set_cpu_possible() after setup_arch() but just in
+	 * case lets ensure this is valid.
+	 */
+	if (num_possible_cpus() == 1)
+		return;
+
+	cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN;
+
+	/* by default this will only continue through for large > 64 CPUs */
+	if (cpu_extra <= __LOG_BUF_LEN / 2)
+		return;
+
+	pr_info("log_buf_len individual max cpu contribution: %d bytes\n",
+		__LOG_CPU_MAX_BUF_LEN);
+	pr_info("log_buf_len total cpu_extra contributions: %d bytes\n",
+		cpu_extra);
+	pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN);
+
+	log_buf_len_update(cpu_extra + __LOG_BUF_LEN);
+}
+
 void __init setup_log_buf(int early)
 {
 	unsigned long flags;
 	char *new_log_buf;
 	int free;
 
+	if (log_buf != __log_buf)
+		return;
+
+	if (!early && !new_log_buf_len)
+		log_buf_add_cpu();
+
 	if (!new_log_buf_len)
 		return;
 
 	if (early) {
 		new_log_buf =
-			memblock_virt_alloc(new_log_buf_len, PAGE_SIZE);
+			memblock_virt_alloc(new_log_buf_len, LOG_ALIGN);
 	} else {
-		new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, 0);
+		new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len,
+							  LOG_ALIGN);
 	}
 
 	if (unlikely(!new_log_buf)) {
@@ -872,7 +910,7 @@ void __init setup_log_buf(int early)
 	memcpy(log_buf, __log_buf, __LOG_BUF_LEN);
 	raw_spin_unlock_irqrestore(&logbuf_lock, flags);
 
-	pr_info("log_buf_len: %d\n", log_buf_len);
+	pr_info("log_buf_len: %d bytes\n", log_buf_len);
 	pr_info("early log buf free: %d(%d%%)\n",
 		free, (free * 100) / __LOG_BUF_LEN);
 }
@@ -881,7 +919,7 @@ static bool __read_mostly ignore_loglevel;
 
 static int __init ignore_loglevel_setup(char *str)
 {
-	ignore_loglevel = 1;
+	ignore_loglevel = true;
 	pr_info("debug: ignoring loglevel setting.\n");
 
 	return 0;
@@ -947,11 +985,7 @@ static inline void boot_delay_msec(int level)
 }
 #endif
 
-#if defined(CONFIG_PRINTK_TIME)
-static bool printk_time = 1;
-#else
-static bool printk_time;
-#endif
+static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME);
 module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);
 
 static size_t print_time(u64 ts, char *buf)
@@ -1310,7 +1344,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			 * for pending data, not the size; return the count of
 			 * records, not the length.
 			 */
-			error = log_next_idx - syslog_idx;
+			error = log_next_seq - syslog_seq;
 		} else {
 			u64 seq = syslog_seq;
 			u32 idx = syslog_idx;
@@ -1416,10 +1450,9 @@ static int have_callable_console(void)
 /*
  * Can we actually use the console at this time on this cpu?
  *
- * Console drivers may assume that per-cpu resources have
- * been allocated. So unless they're explicitly marked as
- * being able to cope (CON_ANYTIME) don't call them until
- * this CPU is officially up.
+ * Console drivers may assume that per-cpu resources have been allocated. So
+ * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
+ * call them until this CPU is officially up.
  */
 static inline int can_use_console(unsigned int cpu)
 {
@@ -1432,8 +1465,10 @@ static inline int can_use_console(unsigned int cpu)
  * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  */
-static int console_trylock_for_printk(unsigned int cpu)
+static int console_trylock_for_printk(void)
 {
+	unsigned int cpu = smp_processor_id();
+
 	if (!console_trylock())
 		return 0;
 	/*
@@ -1476,7 +1511,7 @@ static struct cont {
 	struct task_struct *owner;	/* task of first print*/
 	u64 ts_nsec;			/* time of first print */
 	u8 level;			/* log level of first message */
-	u8 facility;			/* log level of first message */
+	u8 facility;			/* log facility of first message */
 	enum log_flags flags;		/* prefix, newline flags */
 	bool flushed:1;			/* buffer sealed and committed */
 } cont;
@@ -1608,7 +1643,8 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (!oops_in_progress && !lockdep_recursing(current)) {
 			recursion_bug = 1;
-			goto out_restore_irqs;
+			local_irq_restore(flags);
+			return 0;
 		}
 		zap_locks();
 	}
@@ -1716,21 +1752,30 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
+	lockdep_on();
+	local_irq_restore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
 	if (!in_sched) {
+		lockdep_off();
+		/*
+		 * Disable preemption to avoid being preempted while holding
+		 * console_sem which would prevent anyone from printing to
+		 * console
+		 */
+		preempt_disable();
+
 		/*
 		 * Try to acquire and then immediately release the console
 		 * semaphore.  The release will print out buffers and wake up
 		 * /dev/kmsg and syslog() users.
 		 */
-		if (console_trylock_for_printk(this_cpu))
+		if (console_trylock_for_printk())
 			console_unlock();
+		preempt_enable();
+		lockdep_on();
 	}
 
-	lockdep_on();
-out_restore_irqs:
-	local_irq_restore(flags);
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
@@ -1802,7 +1847,7 @@ EXPORT_SYMBOL(printk);
 
 #define LOG_LINE_MAX		0
 #define PREFIX_MAX		0
-#define LOG_LINE_MAX 0
+
 static u64 syslog_seq;
 static u32 syslog_idx;
 static u64 console_seq;
@@ -1881,11 +1926,12 @@ static int __add_preferred_console(char *name, int idx, char *options,
 	return 0;
 }
 /*
- * Set up a list of consoles.  Called from init/main.c
+ * Set up a console.  Called via do_early_param() in init/main.c
+ * for each "console=" parameter in the boot command line.
  */
 static int __init console_setup(char *str)
 {
-	char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for index */
+	char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */
 	char *s, *options, *brl_options = NULL;
 	int idx;
 
@@ -1902,7 +1948,8 @@ static int __init console_setup(char *str)
 		strncpy(buf, str, sizeof(buf) - 1);
 	}
 	buf[sizeof(buf) - 1] = 0;
-	if ((options = strchr(str, ',')) != NULL)
+	options = strchr(str, ',');
+	if (options)
 		*(options++) = 0;
 #ifdef __sparc__
 	if (!strcmp(str, "ttya"))
@@ -1911,7 +1958,7 @@ static int __init console_setup(char *str)
 		strcpy(buf, "ttyS1");
 #endif
 	for (s = buf; *s; s++)
-		if ((*s >= '0' && *s <= '9') || *s == ',')
+		if (isdigit(*s) || *s == ',')
 			break;
 	idx = simple_strtoul(s, NULL, 10);
 	*s = 0;
@@ -1950,7 +1997,6 @@ int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, cha
 	     i++, c++)
 		if (strcmp(c->name, name) == 0 && c->index == idx) {
 			strlcpy(c->name, name_new, sizeof(c->name));
-			c->name[sizeof(c->name) - 1] = 0;
 			c->options = options;
 			c->index = idx_new;
 			return i;
@@ -1959,12 +2005,12 @@ int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, cha
 	return -1;
 }
 
-bool console_suspend_enabled = 1;
+bool console_suspend_enabled = true;
 EXPORT_SYMBOL(console_suspend_enabled);
 
 static int __init console_suspend_disable(char *str)
 {
-	console_suspend_enabled = 0;
+	console_suspend_enabled = false;
 	return 1;
 }
 __setup("no_console_suspend", console_suspend_disable);
@@ -2045,8 +2091,8 @@ EXPORT_SYMBOL(console_lock);
 /**
  * console_trylock - try to lock the console system for exclusive use.
  *
- * Tried to acquire a lock which guarantees that the caller has
- * exclusive access to the console system and the console_drivers list.
+ * Try to acquire a lock which guarantees that the caller has exclusive
+ * access to the console system and the console_drivers list.
  *
  * returns 1 on success, and 0 on failure to acquire the lock.
  */
@@ -2618,14 +2664,13 @@ EXPORT_SYMBOL(__printk_ratelimit);
 bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 			unsigned int interval_msecs)
 {
-	if (*caller_jiffies == 0
-			|| !time_in_range(jiffies, *caller_jiffies,
-					*caller_jiffies
-					+ msecs_to_jiffies(interval_msecs))) {
-		*caller_jiffies = jiffies;
-		return true;
-	}
-	return false;
+	unsigned long elapsed = jiffies - *caller_jiffies;
+
+	if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs))
+		return false;
+
+	*caller_jiffies = jiffies;
+	return true;
 }
 EXPORT_SYMBOL(printk_timed_ratelimit);
 

kernel/smp.c

@@ -670,7 +670,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 			if (cond_func(cpu, info)) {
 				ret = smp_call_function_single(cpu, func,
 								info, wait);
-				WARN_ON_ONCE(!ret);
+				WARN_ON_ONCE(ret);
 			}
 		preempt_enable();
 	}