Merge branch 'akpm-current/current'

275 files changed, 6530 insertions, 3315 deletions

diff --git a/.clang-format b/.clang-format
new file mode 100644
index 000000000000..6cdf4aa4e974
--- /dev/null
+++ b/.clang-format
@@ -0,0 +1,429 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# clang-format configuration file. Intended for clang-format >= 4.
+#
+# For more information, see:
+#
+#   Documentation/process/clang-format.rst
+#   https://clang.llvm.org/docs/ClangFormat.html
+#   https://clang.llvm.org/docs/ClangFormatStyleOptions.html
+#
+---
+AccessModifierOffset: -4
+AlignAfterOpenBracket: Align
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+#AlignEscapedNewlines: Left # Unknown to clang-format-4.0
+AlignOperands: true
+AlignTrailingComments: false
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortBlocksOnASingleLine: false
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: None
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: false
+AlwaysBreakTemplateDeclarations: false
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterClass: false
+  AfterControlStatement: false
+  AfterEnum: false
+  AfterFunction: true
+  AfterNamespace: true
+  AfterObjCDeclaration: false
+  AfterStruct: false
+  AfterUnion: false
+  #AfterExternBlock: false # Unknown to clang-format-5.0
+  BeforeCatch: false
+  BeforeElse: false
+  IndentBraces: false
+  #SplitEmptyFunction: true # Unknown to clang-format-4.0
+  #SplitEmptyRecord: true # Unknown to clang-format-4.0
+  #SplitEmptyNamespace: true # Unknown to clang-format-4.0
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Custom
+#BreakBeforeInheritanceComma: false # Unknown to clang-format-4.0
+BreakBeforeTernaryOperators: false
+BreakConstructorInitializersBeforeComma: false
+#BreakConstructorInitializers: BeforeComma # Unknown to clang-format-4.0
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: false
+ColumnLimit: 80
+CommentPragmas: '^ IWYU pragma:'
+#CompactNamespaces: false # Unknown to clang-format-4.0
+ConstructorInitializerAllOnOneLineOrOnePerLine: false
+ConstructorInitializerIndentWidth: 8
+ContinuationIndentWidth: 8
+Cpp11BracedListStyle: false
+DerivePointerAlignment: false
+DisableFormat: false
+ExperimentalAutoDetectBinPacking: false
+#FixNamespaceComments: false # Unknown to clang-format-4.0
+
+# Taken from:
+#   git grep -h '^#define [^[:space:]]*for_each[^[:space:]]*(' include/ \
+#   | sed "s,^#define \([^[:space:]]*for_each[^[:space:]]*\)(.*$,  - '\1'," \
+#   | sort | uniq
+ForEachMacros:
+  - 'apei_estatus_for_each_section'
+  - 'ata_for_each_dev'
+  - 'ata_for_each_link'
+  - 'ax25_for_each'
+  - 'ax25_uid_for_each'
+  - 'bio_for_each_integrity_vec'
+  - '__bio_for_each_segment'
+  - 'bio_for_each_segment'
+  - 'bio_for_each_segment_all'
+  - 'bio_list_for_each'
+  - 'bip_for_each_vec'
+  - 'blkg_for_each_descendant_post'
+  - 'blkg_for_each_descendant_pre'
+  - 'blk_queue_for_each_rl'
+  - 'bond_for_each_slave'
+  - 'bond_for_each_slave_rcu'
+  - 'btree_for_each_safe128'
+  - 'btree_for_each_safe32'
+  - 'btree_for_each_safe64'
+  - 'btree_for_each_safel'
+  - 'card_for_each_dev'
+  - 'cgroup_taskset_for_each'
+  - 'cgroup_taskset_for_each_leader'
+  - 'cpufreq_for_each_entry'
+  - 'cpufreq_for_each_entry_idx'
+  - 'cpufreq_for_each_valid_entry'
+  - 'cpufreq_for_each_valid_entry_idx'
+  - 'css_for_each_child'
+  - 'css_for_each_descendant_post'
+  - 'css_for_each_descendant_pre'
+  - 'device_for_each_child_node'
+  - 'drm_atomic_crtc_for_each_plane'
+  - 'drm_atomic_crtc_state_for_each_plane'
+  - 'drm_atomic_crtc_state_for_each_plane_state'
+  - 'drm_for_each_connector_iter'
+  - 'drm_for_each_crtc'
+  - 'drm_for_each_encoder'
+  - 'drm_for_each_encoder_mask'
+  - 'drm_for_each_fb'
+  - 'drm_for_each_legacy_plane'
+  - 'drm_for_each_plane'
+  - 'drm_for_each_plane_mask'
+  - 'drm_mm_for_each_hole'
+  - 'drm_mm_for_each_node'
+  - 'drm_mm_for_each_node_in_range'
+  - 'drm_mm_for_each_node_safe'
+  - 'for_each_active_drhd_unit'
+  - 'for_each_active_iommu'
+  - 'for_each_available_child_of_node'
+  - 'for_each_bio'
+  - 'for_each_board_func_rsrc'
+  - 'for_each_bvec'
+  - 'for_each_child_of_node'
+  - 'for_each_clear_bit'
+  - 'for_each_clear_bit_from'
+  - 'for_each_cmsghdr'
+  - 'for_each_compatible_node'
+  - 'for_each_console'
+  - 'for_each_cpu'
+  - 'for_each_cpu_and'
+  - 'for_each_cpu_not'
+  - 'for_each_cpu_wrap'
+  - 'for_each_dev_addr'
+  - 'for_each_dma_cap_mask'
+  - 'for_each_drhd_unit'
+  - 'for_each_dss_dev'
+  - 'for_each_efi_memory_desc'
+  - 'for_each_efi_memory_desc_in_map'
+  - 'for_each_endpoint_of_node'
+  - 'for_each_evictable_lru'
+  - 'for_each_fib6_node_rt_rcu'
+  - 'for_each_fib6_walker_rt'
+  - 'for_each_free_mem_range'
+  - 'for_each_free_mem_range_reverse'
+  - 'for_each_func_rsrc'
+  - 'for_each_hstate'
+  - 'for_each_if'
+  - 'for_each_iommu'
+  - 'for_each_ip_tunnel_rcu'
+  - 'for_each_irq_nr'
+  - 'for_each_lru'
+  - 'for_each_matching_node'
+  - 'for_each_matching_node_and_match'
+  - 'for_each_memblock'
+  - 'for_each_memblock_type'
+  - 'for_each_memcg_cache_index'
+  - 'for_each_mem_pfn_range'
+  - 'for_each_mem_range'
+  - 'for_each_mem_range_rev'
+  - 'for_each_migratetype_order'
+  - 'for_each_msi_entry'
+  - 'for_each_net'
+  - 'for_each_netdev'
+  - 'for_each_netdev_continue'
+  - 'for_each_netdev_continue_rcu'
+  - 'for_each_netdev_feature'
+  - 'for_each_netdev_in_bond_rcu'
+  - 'for_each_netdev_rcu'
+  - 'for_each_netdev_reverse'
+  - 'for_each_netdev_safe'
+  - 'for_each_net_rcu'
+  - 'for_each_new_connector_in_state'
+  - 'for_each_new_crtc_in_state'
+  - 'for_each_new_plane_in_state'
+  - 'for_each_new_private_obj_in_state'
+  - 'for_each_node'
+  - 'for_each_node_by_name'
+  - 'for_each_node_by_type'
+  - 'for_each_node_mask'
+  - 'for_each_node_state'
+  - 'for_each_node_with_cpus'
+  - 'for_each_node_with_property'
+  - 'for_each_of_allnodes'
+  - 'for_each_of_allnodes_from'
+  - 'for_each_of_pci_range'
+  - 'for_each_old_connector_in_state'
+  - 'for_each_old_crtc_in_state'
+  - 'for_each_oldnew_connector_in_state'
+  - 'for_each_oldnew_crtc_in_state'
+  - 'for_each_oldnew_plane_in_state'
+  - 'for_each_oldnew_private_obj_in_state'
+  - 'for_each_old_plane_in_state'
+  - 'for_each_old_private_obj_in_state'
+  - 'for_each_online_cpu'
+  - 'for_each_online_node'
+  - 'for_each_online_pgdat'
+  - 'for_each_pci_bridge'
+  - 'for_each_pci_dev'
+  - 'for_each_pci_msi_entry'
+  - 'for_each_populated_zone'
+  - 'for_each_possible_cpu'
+  - 'for_each_present_cpu'
+  - 'for_each_prime_number'
+  - 'for_each_prime_number_from'
+  - 'for_each_process'
+  - 'for_each_process_thread'
+  - 'for_each_property_of_node'
+  - 'for_each_reserved_mem_region'
+  - 'for_each_resv_unavail_range'
+  - 'for_each_rtdcom'
+  - 'for_each_rtdcom_safe'
+  - 'for_each_set_bit'
+  - 'for_each_set_bit_from'
+  - 'for_each_sg'
+  - 'for_each_sg_page'
+  - '__for_each_thread'
+  - 'for_each_thread'
+  - 'for_each_zone'
+  - 'for_each_zone_zonelist'
+  - 'for_each_zone_zonelist_nodemask'
+  - 'fwnode_for_each_available_child_node'
+  - 'fwnode_for_each_child_node'
+  - 'fwnode_graph_for_each_endpoint'
+  - 'gadget_for_each_ep'
+  - 'hash_for_each'
+  - 'hash_for_each_possible'
+  - 'hash_for_each_possible_rcu'
+  - 'hash_for_each_possible_rcu_notrace'
+  - 'hash_for_each_possible_safe'
+  - 'hash_for_each_rcu'
+  - 'hash_for_each_safe'
+  - 'hctx_for_each_ctx'
+  - 'hlist_bl_for_each_entry'
+  - 'hlist_bl_for_each_entry_rcu'
+  - 'hlist_bl_for_each_entry_safe'
+  - 'hlist_for_each'
+  - 'hlist_for_each_entry'
+  - 'hlist_for_each_entry_continue'
+  - 'hlist_for_each_entry_continue_rcu'
+  - 'hlist_for_each_entry_continue_rcu_bh'
+  - 'hlist_for_each_entry_from'
+  - 'hlist_for_each_entry_from_rcu'
+  - 'hlist_for_each_entry_rcu'
+  - 'hlist_for_each_entry_rcu_bh'
+  - 'hlist_for_each_entry_rcu_notrace'
+  - 'hlist_for_each_entry_safe'
+  - '__hlist_for_each_rcu'
+  - 'hlist_for_each_safe'
+  - 'hlist_nulls_for_each_entry'
+  - 'hlist_nulls_for_each_entry_from'
+  - 'hlist_nulls_for_each_entry_rcu'
+  - 'hlist_nulls_for_each_entry_safe'
+  - 'ide_host_for_each_port'
+  - 'ide_port_for_each_dev'
+  - 'ide_port_for_each_present_dev'
+  - 'idr_for_each_entry'
+  - 'idr_for_each_entry_continue'
+  - 'idr_for_each_entry_ul'
+  - 'inet_bind_bucket_for_each'
+  - 'inet_lhash2_for_each_icsk_rcu'
+  - 'iov_for_each'
+  - 'key_for_each'
+  - 'key_for_each_safe'
+  - 'klp_for_each_func'
+  - 'klp_for_each_object'
+  - 'kvm_for_each_memslot'
+  - 'kvm_for_each_vcpu'
+  - 'list_for_each'
+  - 'list_for_each_entry'
+  - 'list_for_each_entry_continue'
+  - 'list_for_each_entry_continue_rcu'
+  - 'list_for_each_entry_continue_reverse'
+  - 'list_for_each_entry_from'
+  - 'list_for_each_entry_from_reverse'
+  - 'list_for_each_entry_lockless'
+  - 'list_for_each_entry_rcu'
+  - 'list_for_each_entry_reverse'
+  - 'list_for_each_entry_safe'
+  - 'list_for_each_entry_safe_continue'
+  - 'list_for_each_entry_safe_from'
+  - 'list_for_each_entry_safe_reverse'
+  - 'list_for_each_prev'
+  - 'list_for_each_prev_safe'
+  - 'list_for_each_safe'
+  - 'llist_for_each'
+  - 'llist_for_each_entry'
+  - 'llist_for_each_entry_safe'
+  - 'llist_for_each_safe'
+  - 'media_device_for_each_entity'
+  - 'media_device_for_each_intf'
+  - 'media_device_for_each_link'
+  - 'media_device_for_each_pad'
+  - 'netdev_for_each_lower_dev'
+  - 'netdev_for_each_lower_private'
+  - 'netdev_for_each_lower_private_rcu'
+  - 'netdev_for_each_mc_addr'
+  - 'netdev_for_each_uc_addr'
+  - 'netdev_for_each_upper_dev_rcu'
+  - 'netdev_hw_addr_list_for_each'
+  - 'nft_rule_for_each_expr'
+  - 'nla_for_each_attr'
+  - 'nla_for_each_nested'
+  - 'nlmsg_for_each_attr'
+  - 'nlmsg_for_each_msg'
+  - 'nr_neigh_for_each'
+  - 'nr_neigh_for_each_safe'
+  - 'nr_node_for_each'
+  - 'nr_node_for_each_safe'
+  - 'of_for_each_phandle'
+  - 'of_property_for_each_string'
+  - 'of_property_for_each_u32'
+  - 'pci_bus_for_each_resource'
+  - 'ping_portaddr_for_each_entry'
+  - 'plist_for_each'
+  - 'plist_for_each_continue'
+  - 'plist_for_each_entry'
+  - 'plist_for_each_entry_continue'
+  - 'plist_for_each_entry_safe'
+  - 'plist_for_each_safe'
+  - 'pnp_for_each_card'
+  - 'pnp_for_each_dev'
+  - 'protocol_for_each_card'
+  - 'protocol_for_each_dev'
+  - 'queue_for_each_hw_ctx'
+  - 'radix_tree_for_each_contig'
+  - 'radix_tree_for_each_slot'
+  - 'radix_tree_for_each_tagged'
+  - 'rbtree_postorder_for_each_entry_safe'
+  - 'resource_list_for_each_entry'
+  - 'resource_list_for_each_entry_safe'
+  - 'rhl_for_each_entry_rcu'
+  - 'rhl_for_each_rcu'
+  - 'rht_for_each'
+  - 'rht_for_each_continue'
+  - 'rht_for_each_entry'
+  - 'rht_for_each_entry_continue'
+  - 'rht_for_each_entry_rcu'
+  - 'rht_for_each_entry_rcu_continue'
+  - 'rht_for_each_entry_safe'
+  - 'rht_for_each_rcu'
+  - 'rht_for_each_rcu_continue'
+  - '__rq_for_each_bio'
+  - 'rq_for_each_segment'
+  - 'scsi_for_each_prot_sg'
+  - 'scsi_for_each_sg'
+  - 'sctp_for_each_hentry'
+  - 'sctp_skb_for_each'
+  - 'shdma_for_each_chan'
+  - '__shost_for_each_device'
+  - 'shost_for_each_device'
+  - 'sk_for_each'
+  - 'sk_for_each_bound'
+  - 'sk_for_each_entry_offset_rcu'
+  - 'sk_for_each_from'
+  - 'sk_for_each_rcu'
+  - 'sk_for_each_safe'
+  - 'sk_nulls_for_each'
+  - 'sk_nulls_for_each_from'
+  - 'sk_nulls_for_each_rcu'
+  - 'snd_pcm_group_for_each_entry'
+  - 'snd_soc_dapm_widget_for_each_path'
+  - 'snd_soc_dapm_widget_for_each_path_safe'
+  - 'snd_soc_dapm_widget_for_each_sink_path'
+  - 'snd_soc_dapm_widget_for_each_source_path'
+  - 'tb_property_for_each'
+  - 'udp_portaddr_for_each_entry'
+  - 'udp_portaddr_for_each_entry_rcu'
+  - 'usb_hub_for_each_child'
+  - 'v4l2_device_for_each_subdev'
+  - 'v4l2_m2m_for_each_dst_buf'
+  - 'v4l2_m2m_for_each_dst_buf_safe'
+  - 'v4l2_m2m_for_each_src_buf'
+  - 'v4l2_m2m_for_each_src_buf_safe'
+  - 'zorro_for_each_dev'
+
+#IncludeBlocks: Preserve # Unknown to clang-format-5.0
+IncludeCategories:
+  - Regex: '.*'
+    Priority: 1
+IncludeIsMainRegex: '(Test)?$'
+IndentCaseLabels: false
+#IndentPPDirectives: None # Unknown to clang-format-5.0
+IndentWidth: 8
+IndentWrappedFunctionNames: true
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd: ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: Inner
+#ObjCBinPackProtocolList: Auto # Unknown to clang-format-5.0
+ObjCBlockIndentWidth: 8
+ObjCSpaceAfterProperty: true
+ObjCSpaceBeforeProtocolList: true
+
+# Taken from git's rules
+#PenaltyBreakAssignment: 10 # Unknown to clang-format-4.0
+PenaltyBreakBeforeFirstCallParameter: 30
+PenaltyBreakComment: 10
+PenaltyBreakFirstLessLess: 0
+PenaltyBreakString: 10
+PenaltyExcessCharacter: 100
+PenaltyReturnTypeOnItsOwnLine: 60
+
+PointerAlignment: Right
+ReflowComments: false
+SortIncludes: false
+#SortUsingDeclarations: false # Unknown to clang-format-4.0
+SpaceAfterCStyleCast: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+#SpaceBeforeCtorInitializerColon: true # Unknown to clang-format-5.0
+#SpaceBeforeInheritanceColon: true # Unknown to clang-format-5.0
+SpaceBeforeParens: ControlStatements
+#SpaceBeforeRangeBasedForLoopColon: true # Unknown to clang-format-5.0
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 1
+SpacesInAngles: false
+SpacesInContainerLiterals: false
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+Standard: Cpp03
+TabWidth: 8
+UseTab: Always
+...
+
diff --git a/.gitignore b/.gitignore
index 1c8189e67467..97ba6b79834c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -84,6 +84,7 @@ modules.builtin
 !.gitignore
 !.mailmap
 !.cocciconfig
+!.clang-format
 
 #
 # Generated include files
diff --git a/Documentation/ABI/testing/sysfs-class-bdi b/Documentation/ABI/testing/sysfs-class-bdi
index d773d5697cf5..3187a18af6da 100644
--- a/Documentation/ABI/testing/sysfs-class-bdi
+++ b/Documentation/ABI/testing/sysfs-class-bdi
@@ -53,3 +53,11 @@ stable_pages_required (read-only)
 
 	If set, the backing device requires that all pages comprising a write
 	request must not be changed until writeout is complete.
+
+strictlimit (read-write)
+
+	Forces per-BDI checks for the share of given device in the write-back
+	cache even before the global background dirty limit is reached. This
+	is useful in situations where the global limit is much higher than
+	affordable for given relatively slow (or untrusted) device. Turning
+	strictlimit on has no visible effect if max_ratio is equal to 100%.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 08e739bfdbd8..d7ed6eab03de 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1846,30 +1846,29 @@
 	keepinitrd	[HW,ARM]
 
 	kernelcore=	[KNL,X86,IA-64,PPC]
-			Format: nn[KMGTPE] | "mirror"
-			This parameter
-			specifies the amount of memory usable by the kernel
-			for non-movable allocations.  The requested amount is
-			spread evenly throughout all nodes in the system. The
-			remaining memory in each node is used for Movable
-			pages. In the event, a node is too small to have both
-			kernelcore and Movable pages, kernelcore pages will
-			take priority and other nodes will have a larger number
-			of Movable pages.  The Movable zone is used for the
-			allocation of pages that may be reclaimed or moved
-			by the page migration subsystem.  This means that
-			HugeTLB pages may not be allocated from this zone.
-			Note that allocations like PTEs-from-HighMem still
-			use the HighMem zone if it exists, and the Normal
+			Format: nn[KMGTPE] | nn% | "mirror"
+			This parameter specifies the amount of memory usable by
+			the kernel for non-movable allocations.  The requested
+			amount is spread evenly throughout all nodes in the
+			system as ZONE_NORMAL.  The remaining memory is used for
+			movable memory in its own zone, ZONE_MOVABLE.  In the
+			event, a node is too small to have both ZONE_NORMAL and
+			ZONE_MOVABLE, kernelcore memory will take priority and
+			other nodes will have a larger ZONE_MOVABLE.
+
+			ZONE_MOVABLE is used for the allocation of pages that
+			may be reclaimed or moved by the page migration
+			subsystem.  Note that allocations like PTEs-from-HighMem
+			still use the HighMem zone if it exists, and the Normal
 			zone if it does not.
 
-			Instead of specifying the amount of memory (nn[KMGTPE]),
-			you can specify "mirror" option. In case "mirror"
+			It is possible to specify the exact amount of memory in
+			the form of "nn[KMGTPE]", a percentage of total system
+			memory in the form of "nn%", or "mirror".  If "mirror"
 			option is specified, mirrored (reliable) memory is used
 			for non-movable allocations and remaining memory is used
-			for Movable pages. nn[KMGTPE] and "mirror" are exclusive,
-			so you can NOT specify nn[KMGTPE] and "mirror" at the same
-			time.
+			for Movable pages.  "nn[KMGTPE]", "nn%", and "mirror"
+			are exclusive, so you cannot specify multiple forms.
 
 	kgdbdbgp=	[KGDB,HW] kgdb over EHCI usb debug port.
 			Format: <Controller#>[,poll interval]
@@ -2386,13 +2385,14 @@
 	mousedev.yres=	[MOUSE] Vertical screen resolution, used for devices
 			reporting absolute coordinates, such as tablets
 
-	movablecore=nn[KMG]	[KNL,X86,IA-64,PPC] This parameter
-			is similar to kernelcore except it specifies the
-			amount of memory used for migratable allocations.
-			If both kernelcore and movablecore is specified,
-			then kernelcore will be at *least* the specified
-			value but may be more. If movablecore on its own
-			is specified, the administrator must be careful
+	movablecore=	[KNL,X86,IA-64,PPC]
+			Format: nn[KMGTPE] | nn%
+			This parameter is the complement to kernelcore=, it
+			specifies the amount of memory used for migratable
+			allocations.  If both kernelcore and movablecore is
+			specified, then kernelcore will be at *least* the
+			specified value but may be more.  If movablecore on its
+			own is specified, the administrator must be careful
 			that the amount of memory usable for all allocations
 			is not too small.
 
diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt
index 74cdeaed9f7a..f728e55602b2 100644
--- a/Documentation/cgroup-v2.txt
+++ b/Documentation/cgroup-v2.txt
@@ -48,6 +48,7 @@ v1 is available under Documentation/cgroup-v1/.
        5-2-1. Memory Interface Files
        5-2-2. Usage Guidelines
        5-2-3. Memory Ownership
+       5-2-4. OOM Killer
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
@@ -1039,6 +1040,31 @@ PAGE_SIZE multiple when read back.
 	high limit is used and monitored properly, this limit's
 	utility is limited to providing the final safety net.
 
+  memory.oom_group
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "0".
+
+	If set, OOM killer will consider the memory cgroup as an
+	indivisible memory consumers and compare it with other memory
+	consumers by it's memory footprint.
+	If such memory cgroup is selected as an OOM victim, all
+	processes belonging to it or it's descendants will be killed.
+
+	This applies to system-wide OOM conditions and reaching
+	the hard memory limit of the cgroup and their ancestor.
+	If OOM condition happens in a descendant cgroup with it's own
+	memory limit, the memory cgroup can't be considered
+	as an OOM victim, and OOM killer will not kill all belonging
+	tasks.
+
+	Also, OOM killer respects the /proc/pid/oom_score_adj value -1000,
+	and will never kill the unkillable task, even if memory.oom_group
+	is set.
+
+	If cgroup-aware OOM killer is not enabled, ENOTSUPP error
+	is returned on attempt to access the file.
+
   memory.events
 	A read-only flat-keyed file which exists on non-root cgroups.
 	The following entries are defined.  Unless specified
@@ -1242,6 +1268,54 @@ to be accessed repeatedly by other cgroups, it may make sense to use
 POSIX_FADV_DONTNEED to relinquish the ownership of memory areas
 belonging to the affected files to ensure correct memory ownership.
 
+OOM Killer
+~~~~~~~~~~
+
+Cgroup v2 memory controller implements a cgroup-aware OOM killer.
+It means that it treats cgroups as first class OOM entities.
+
+Cgroup-aware OOM logic is turned off by default and requires
+passing the "groupoom" option on mounting cgroupfs. It can also
+by remounting cgroupfs with the following command::
+
+  # mount -o remount,groupoom $MOUNT_POINT
+
+Under OOM conditions the memory controller tries to make the best
+choice of a victim, looking for a memory cgroup with the largest
+memory footprint, considering leaf cgroups and cgroups with the
+memory.oom_group option set, which are considered to be an indivisible
+memory consumers.
+
+By default, OOM killer will kill the biggest task in the selected
+memory cgroup. A user can change this behavior by enabling
+the per-cgroup memory.oom_group option. If set, it causes
+the OOM killer to kill all processes attached to the cgroup,
+except processes with oom_score_adj set to -1000.
+
+This affects both system- and cgroup-wide OOMs. For a cgroup-wide OOM
+the memory controller considers only cgroups belonging to the sub-tree
+of the OOM'ing cgroup.
+
+Leaf cgroups and cgroups with oom_group option set are compared based
+on their cumulative memory usage. The root cgroup is treated as a
+leaf memory cgroup as well, so it is compared with other leaf memory
+cgroups. Due to internal implementation restrictions the size of
+the root cgroup is the cumulative sum of oom_badness of all its tasks
+(in other words oom_score_adj of each task is obeyed). Relying on
+oom_score_adj (apart from OOM_SCORE_ADJ_MIN) can lead to over- or
+underestimation of the root cgroup consumption and it is therefore
+discouraged. This might change in the future, however.
+
+If there are no cgroups with the enabled memory controller,
+the OOM killer is using the "traditional" process-based approach.
+
+Please, note that memory charges are not migrating if tasks
+are moved between different memory cgroups. Moving tasks with
+significant memory footprint may affect OOM victim selection logic.
+If it's a case, please, consider creating a common ancestor for
+the source and destination memory cgroups and enabling oom_group
+on ancestor layer.
+
 
 IO
 --
diff --git a/Documentation/process/4.Coding.rst b/Documentation/process/4.Coding.rst
index 26b106071364..eb4b185d168c 100644
--- a/Documentation/process/4.Coding.rst
+++ b/Documentation/process/4.Coding.rst
@@ -58,6 +58,14 @@ can never be transgressed.  If there is a good reason to go against the
 style (a line which becomes far less readable if split to fit within the
 80-column limit, for example), just do it.
 
+Note that you can also use the ``clang-format`` tool to help you with
+these rules, to quickly re-format parts of your code automatically,
+and to review full files in order to spot coding style mistakes,
+typos and possible improvements. It is also handy for sorting ``#includes``,
+for aligning variables/macros, for reflowing text and other similar tasks.
+See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
+for more details.
+
 
 Abstraction layers
 ******************
diff --git a/Documentation/process/clang-format.rst b/Documentation/process/clang-format.rst
new file mode 100644
index 000000000000..a0236d051dcd
--- /dev/null
+++ b/Documentation/process/clang-format.rst
@@ -0,0 +1,185 @@
+.. _clangformat:
+
+clang-format
+============
+
+``clang-format`` is a tool to format C/C++/... code according to
+a set of rules and heuristics. Like most tools, it is not perfect
+nor covers every single case, but it is good enough to be helpful.
+
+``clang-format`` can be used for several purposes:
+
+  - Quickly reformat a block of code to the kernel style. Specially useful
+    when moving code around and aligning/sorting. See clangformatreformat_.
+
+  - Spot style mistakes, typos and possible improvements in files
+    you maintain, patches you review, diffs, etc. See clangformatreview_.
+
+  - Help you follow the coding style rules, specially useful for those
+    new to kernel development or working at the same time in several
+    projects with different coding styles.
+
+Its configuration file is ``.clang-format`` in the root of the kernel tree.
+The rules contained there try to approximate the most common kernel
+coding style. They also try to follow :ref:`Documentation/process/coding-style.rst <codingstyle>`
+as much as possible. Since not all the kernel follows the same style,
+it is possible that you may want to tweak the defaults for a particular
+subsystem or folder. To do so, you can override the defaults by writing
+another ``.clang-format`` file in a subfolder.
+
+The tool itself has already been included in the repositories of popular
+Linux distributions for a long time. Search for ``clang-format`` in
+your repositories. Otherwise, you can either download pre-built
+LLVM/clang binaries or build the source code from:
+
+    http://releases.llvm.org/download.html
+
+See more information about the tool at:
+
+    https://clang.llvm.org/docs/ClangFormat.html
+
+    https://clang.llvm.org/docs/ClangFormatStyleOptions.html
+
+
+.. _clangformatreview:
+
+Review files and patches for coding style
+-----------------------------------------
+
+By running the tool in its inline mode, you can review full subsystems,
+folders or individual files for code style mistakes, typos or improvements.
+
+To do so, you can run something like::
+
+    # Make sure your working directory is clean!
+    clang-format -i kernel/*.[ch]
+
+And then take a look at the git diff.
+
+Counting the lines of such a diff is also useful for improving/tweaking
+the style options in the configuration file; as well as testing new
+``clang-format`` features/versions.
+
+``clang-format`` also supports reading unified diffs, so you can review
+patches and git diffs easily. See the documentation at:
+
+    https://clang.llvm.org/docs/ClangFormat.html#script-for-patch-reformatting
+
+To avoid ``clang-format`` formatting some portion of a file, you can do::
+
+    int formatted_code;
+    // clang-format off
+        void    unformatted_code  ;
+    // clang-format on
+    void formatted_code_again;
+
+While it might be tempting to use this to keep a file always in sync with
+``clang-format``, specially if you are writing new files or if you are
+a maintainer, please note that people might be running different
+``clang-format`` versions or not have it available at all. Therefore,
+you should probably refrain yourself from using this in kernel sources;
+at least until we see if ``clang-format`` becomes commonplace.
+
+
+.. _clangformatreformat:
+
+Reformatting blocks of code
+---------------------------
+
+By using an integration with your text editor, you can reformat arbitrary
+blocks (selections) of code with a single keystroke. This is specially
+useful when moving code around, for complex code that is deeply intended,
+for multi-line macros (and aligning their backslashes), etc.
+
+Remember that you can always tweak the changes afterwards in those cases
+where the tool did not do an optimal job. But as a first approximation,
+it can be very useful.
+
+There are integrations for many popular text editors. For some of them,
+like vim, emacs, BBEdit and Visual Studio you can find support built-in.
+For instructions, read the appropiate section at:
+
+    https://clang.llvm.org/docs/ClangFormat.html
+
+For Atom, Eclipse, Sublime Text, Visual Studio Code, XCode and other
+editors and IDEs you should be able to find ready-to-use plugins.
+
+For this use case, consider using a secondary ``.clang-format``
+so that you can tweak a few options. See clangformatextra_.
+
+
+.. _clangformatmissing:
+
+Missing support
+---------------
+
+``clang-format`` is missing support for some things that are common
+in kernel code. They are easy to remember, so if you use the tool
+regularly, you will quickly learn to avoid/ignore those.
+
+In particular, some very common ones you will notice are:
+
+  - Aligned blocks of one-line ``#defines``, e.g.::
+
+        #define TRACING_MAP_BITS_DEFAULT       11
+        #define TRACING_MAP_BITS_MAX           17
+        #define TRACING_MAP_BITS_MIN           7
+
+    vs.::
+
+        #define TRACING_MAP_BITS_DEFAULT 11
+        #define TRACING_MAP_BITS_MAX 17
+        #define TRACING_MAP_BITS_MIN 7
+
+  - Aligned designated initializers, e.g.::
+
+        static const struct file_operations uprobe_events_ops = {
+                .owner          = THIS_MODULE,
+                .open           = probes_open,
+                .read           = seq_read,
+                .llseek         = seq_lseek,
+                .release        = seq_release,
+                .write          = probes_write,
+        };
+
+    vs.::
+
+        static const struct file_operations uprobe_events_ops = {
+                .owner = THIS_MODULE,
+                .open = probes_open,
+                .read = seq_read,
+                .llseek = seq_lseek,
+                .release = seq_release,
+                .write = probes_write,
+        };
+
+
+.. _clangformatextra:
+
+Extra features/options
+----------------------
+
+Some features/style options are not enabled by default in the configuration
+file in order to minimize the differences between the output and the current
+code. In other words, to make the difference as small as possible,
+which makes reviewing full-file style, as well diffs and patches as easy
+as possible.
+
+In other cases (e.g. particular subsystems/folders/files), the kernel style
+might be different and enabling some of these options may approximate
+better the style there.
+
+For instance:
+
+  - Aligning assignments (``AlignConsecutiveAssignments``).
+
+  - Aligning declarations (``AlignConsecutiveDeclarations``).
+
+  - Reflowing text in comments (``ReflowComments``).
+
+  - Sorting ``#includes`` (``SortIncludes``).
+
+They are typically useful for block re-formatting, rather than full-file.
+You might want to create another ``.clang-format`` file and use that one
+from your editor/IDE instead.
+
diff --git a/Documentation/process/coding-style.rst b/Documentation/process/coding-style.rst
index d98deb62c400..4e7c0a1c427a 100644
--- a/Documentation/process/coding-style.rst
+++ b/Documentation/process/coding-style.rst
@@ -631,6 +631,14 @@ options ``-kr -i8`` (stands for ``K&R, 8 character indents``), or use
 re-formatting you may want to take a look at the man page.  But
 remember: ``indent`` is not a fix for bad programming.
 
+Note that you can also use the ``clang-format`` tool to help you with
+these rules, to quickly re-format parts of your code automatically,
+and to review full files in order to spot coding style mistakes,
+typos and possible improvements. It is also handy for sorting ``#includes``,
+for aligning variables/macros, for reflowing text and other similar tasks.
+See the file :ref:`Documentation/process/clang-format.rst <clangformat>`
+for more details.
+
 
 10) Kconfig configuration files
 -------------------------------
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 412314eebda6..eded671d55eb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -964,32 +964,34 @@ detect a hard lockup condition.
 
 tainted:
 
-Non-zero if the kernel has been tainted.  Numeric values, which
-can be ORed together:
-
-   1 - A module with a non-GPL license has been loaded, this
-       includes modules with no license.
-       Set by modutils >= 2.4.9 and module-init-tools.
-   2 - A module was force loaded by insmod -f.
-       Set by modutils >= 2.4.9 and module-init-tools.
-   4 - Unsafe SMP processors: SMP with CPUs not designed for SMP.
-   8 - A module was forcibly unloaded from the system by rmmod -f.
-  16 - A hardware machine check error occurred on the system.
-  32 - A bad page was discovered on the system.
-  64 - The user has asked that the system be marked "tainted".  This
-       could be because they are running software that directly modifies
-       the hardware, or for other reasons.
- 128 - The system has died.
- 256 - The ACPI DSDT has been overridden with one supplied by the user
-        instead of using the one provided by the hardware.
- 512 - A kernel warning has occurred.
-1024 - A module from drivers/staging was loaded.
-2048 - The system is working around a severe firmware bug.
-4096 - An out-of-tree module has been loaded.
-8192 - An unsigned module has been loaded in a kernel supporting module
-       signature.
-16384 - A soft lockup has previously occurred on the system.
-32768 - The kernel has been live patched.
+Non-zero if the kernel has been tainted. Numeric values, which can be
+ORed together. The letters are seen in "Tainted" line of Oops reports.
+
+     1 (P):  A module with a non-GPL license has been loaded, this
+             includes modules with no license.
+             Set by modutils >= 2.4.9 and module-init-tools.
+     2 (F): A module was force loaded by insmod -f.
+            Set by modutils >= 2.4.9 and module-init-tools.
+     4 (S): Unsafe SMP processors: SMP with CPUs not designed for SMP.
+     8 (R): A module was forcibly unloaded from the system by rmmod -f.
+    16 (M): A hardware machine check error occurred on the system.
+    32 (B): A bad page was discovered on the system.
+    64 (U): The user has asked that the system be marked "tainted". This
+            could be because they are running software that directly modifies
+            the hardware, or for other reasons.
+   128 (D): The system has died.
+   256 (A): The ACPI DSDT has been overridden with one supplied by the user
+            instead of using the one provided by the hardware.
+   512 (W): A kernel warning has occurred.
+  1024 (C): A module from drivers/staging was loaded.
+  2048 (I): The system is working around a severe firmware bug.
+  4096 (O): An out-of-tree module has been loaded.
+  8192 (E): An unsigned module has been loaded in a kernel supporting module
+            signature.
+ 16384 (L): A soft lockup has previously occurred on the system.
+ 32768 (K): The kernel has been live patched.
+ 65536 (X): Auxiliary taint, defined and used by for distros.
+131072 (T): The kernel was built with the struct randomization plugin.
 
 ==============================================================
 
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index ff234d229cbb..17256f2ad919 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -312,8 +312,6 @@ The lowmem_reserve_ratio is an array. You can see them by reading this file.
 % cat /proc/sys/vm/lowmem_reserve_ratio
 256     256     32
 -
-Note: # of this elements is one fewer than number of zones. Because the highest
-      zone's value is not necessary for following calculation.
 
 But, these values are not used directly. The kernel calculates # of protection
 pages for each zones from them. These are shown as array of protection pages
@@ -364,7 +362,8 @@ As above expression, they are reciprocal number of ratio.
 pages of higher zones on the node.
 
 If you would like to protect more pages, smaller values are effective.
-The minimum value is 1 (1/1 -> 100%).
+The minimum value is 1 (1/1 -> 100%). The value less than 1 completely
+disables protection of the pages.
 
 ==============================================================
 
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index ba976805853a..66bfd8396877 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -111,7 +111,7 @@ my $regex_direct_begin_default = 'order=([0-9]*) may_writepage=([0-9]*) gfp_flag
 my $regex_direct_end_default = 'nr_reclaimed=([0-9]*)';
 my $regex_kswapd_wake_default = 'nid=([0-9]*) order=([0-9]*)';
 my $regex_kswapd_sleep_default = 'nid=([0-9]*)';
-my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*)';
+my $regex_wakeup_kswapd_default = 'nid=([0-9]*) zid=([0-9]*) order=([0-9]*) gfp_flags=([A-Z_|]*)';
 my $regex_lru_isolate_default = 'isolate_mode=([0-9]*) classzone_idx=([0-9]*) order=([0-9]*) nr_requested=([0-9]*) nr_scanned=([0-9]*) nr_skipped=([0-9]*) nr_taken=([0-9]*) lru=([a-z_]*)';
 my $regex_lru_shrink_inactive_default = 'nid=([0-9]*) nr_scanned=([0-9]*) nr_reclaimed=([0-9]*) nr_dirty=([0-9]*) nr_writeback=([0-9]*) nr_congested=([0-9]*) nr_immediate=([0-9]*) nr_activate=([0-9]*) nr_ref_keep=([0-9]*) nr_unmap_fail=([0-9]*) priority=([0-9]*) flags=([A-Z_|]*)';
 my $regex_lru_shrink_active_default = 'lru=([A-Z_]*) nr_scanned=([0-9]*) nr_rotated=([0-9]*) priority=([0-9]*)';
@@ -201,7 +201,7 @@ $regex_kswapd_sleep = generate_traceevent_regex(
 $regex_wakeup_kswapd = generate_traceevent_regex(
 			"vmscan/mm_vmscan_wakeup_kswapd",
 			$regex_wakeup_kswapd_default,
-			"nid", "zid", "order");
+			"nid", "zid", "order", "gfp_flags");
 $regex_lru_isolate = generate_traceevent_regex(
 			"vmscan/mm_vmscan_lru_isolate",
 			$regex_lru_isolate_default,
diff --git a/Documentation/vm/hmm.txt b/Documentation/vm/hmm.txt
index 4d3aac9f4a5d..e99b97003982 100644
--- a/Documentation/vm/hmm.txt
+++ b/Documentation/vm/hmm.txt
@@ -1,151 +1,159 @@
 Heterogeneous Memory Management (HMM)
 
-Transparently allow any component of a program to use any memory region of said
-program with a device without using device specific memory allocator. This is
-becoming a requirement to simplify the use of advance heterogeneous computing
-where GPU, DSP or FPGA are use to perform various computations.
-
-This document is divided as follow, in the first section i expose the problems
-related to the use of a device specific allocator. The second section i expose
-the hardware limitations that are inherent to many platforms. The third section
-gives an overview of HMM designs. The fourth section explains how CPU page-
-table mirroring works and what is HMM purpose in this context. Fifth section
-deals with how device memory is represented inside the kernel. Finaly the last
-section present the new migration helper that allow to leverage the device DMA
-engine.
-
-
-1) Problems of using device specific memory allocator:
-2) System bus, device memory characteristics
-3) Share address space and migration
+Provide infrastructure and helpers to integrate non conventional memory (device
+memory like GPU on board memory) into regular kernel code path. Corner stone of
+this being specialize struct page for such memory (see sections 5 to 7 of this
+document).
+
+HMM also provide optional helpers for SVM (Share Virtual Memory) ie allowing a
+device to transparently access program address coherently with the CPU meaning
+that any valid pointer on the CPU is also a valid pointer for the device. This
+is becoming a mandatory to simplify the use of advance heterogeneous computing
+where GPU, DSP, or FPGA are used to perform various computations on behalf of
+a process.
+
+This document is divided as follows: in the first section I expose the problems
+related to using device specific memory allocators. In the second section, I
+expose the hardware limitations that are inherent to many platforms. The third
+section gives an overview of the HMM design. The fourth section explains how
+CPU page-table mirroring works and what is HMM's purpose in this context. The
+fifth section deals with how device memory is represented inside the kernel.
+Finally, the last section presents a new migration helper that allows lever-
+aging the device DMA engine.
+
+
+1) Problems of using a device specific memory allocator:
+2) I/O bus, device memory characteristics
+3) Shared address space and migration
 4) Address space mirroring implementation and API
 5) Represent and manage device memory from core kernel point of view
-6) Migrate to and from device memory
+6) Migration to and from device memory
 7) Memory cgroup (memcg) and rss accounting
 
 
 -------------------------------------------------------------------------------
 
-1) Problems of using device specific memory allocator:
+1) Problems of using a device specific memory allocator:
 
-Device with large amount of on board memory (several giga bytes) like GPU have
-historically manage their memory through dedicated driver specific API. This
-creates a disconnect between memory allocated and managed by device driver and
-regular application memory (private anonymous, share memory or regular file
-back memory). From here on i will refer to this aspect as split address space.
-I use share address space to refer to the opposite situation ie one in which
-any memory region can be use by device transparently.
+Devices with a large amount of on board memory (several giga bytes) like GPUs
+have historically managed their memory through dedicated driver specific APIs.
+This creates a disconnect between memory allocated and managed by a device
+driver and regular application memory (private anonymous, shared memory, or
+regular file backed memory). From here on I will refer to this aspect as split
+address space. I use shared address space to refer to the opposite situation:
+i.e., one in which any application memory region can be used by a device
+transparently.
 
 Split address space because device can only access memory allocated through the
-device specific API. This imply that all memory object in a program are not
-equal from device point of view which complicate large program that rely on a
-wide set of libraries.
+device specific API. This implies that all memory objects in a program are not
+equal from the device point of view which complicates large programs that rely
+on a wide set of libraries.
 
-Concretly this means that code that wants to leverage device like GPU need to
+Concretly this means that code that wants to leverage devices like GPUs need to
 copy object between genericly allocated memory (malloc, mmap private/share/)
 and memory allocated through the device driver API (this still end up with an
 mmap but of the device file).
 
-For flat dataset (array, grid, image, ...) this isn't too hard to achieve but
-complex data-set (list, tree, ...) are hard to get right. Duplicating a complex
-data-set need to re-map all the pointer relations between each of its elements.
-This is error prone and program gets harder to debug because of the duplicate
-data-set.
+For flat data-sets (array, grid, image, ...) this isn't too hard to achieve but
+complex data-sets (list, tree, ...) are hard to get right. Duplicating a
+complex data-set needs to re-map all the pointer relations between each of its
+elements. This is error prone and program gets harder to debug because of the
+duplicate data-set and addresses.
 
-Split address space also means that library can not transparently use data they
-are getting from core program or other library and thus each library might have
-to duplicate its input data-set using specific memory allocator. Large project
-suffer from this and waste resources because of the various memory copy.
+Split address space also means that libraries can not transparently use data
+they are getting from the core program or another library and thus each library
+might have to duplicate its input data-set using the device specific memory
+allocator. Large projects suffer from this and waste resources because of the
+various memory copies.
 
 Duplicating each library API to accept as input or output memory allocted by
 each device specific allocator is not a viable option. It would lead to a
-combinatorial explosions in the library entry points.
+combinatorial explosion in the library entry points.
 
-Finaly with the advance of high level language constructs (in C++ but in other
-language too) it is now possible for compiler to leverage GPU or other devices
-without even the programmer knowledge. Some of compiler identified patterns are
-only do-able with a share address. It is as well more reasonable to use a share
-address space for all the other patterns.
+Finally, with the advance of high level language constructs (in C++ but in
+other languages too) it is now possible for the compiler to leverage GPUs and
+other devices without programmer knowledge. Some compiler identified patterns
+are only do-able with a shared address space. It is also more reasonable to use
+a shared address space for all other patterns.
 
 
 -------------------------------------------------------------------------------
 
-2) System bus, device memory characteristics
+2) I/O bus, device memory characteristics
 
-System bus cripple share address due to few limitations. Most system bus only
+I/O buses cripple shared address due to few limitations. Most I/O buses only
 allow basic memory access from device to main memory, even cache coherency is
-often optional. Access to device memory from CPU is even more limited, most
-often than not it is not cache coherent.
+often optional. Access to device memory from CPU is even more limited. More
+often than not, it is not cache coherent.
 
-If we only consider the PCIE bus than device can access main memory (often
-through an IOMMU) and be cache coherent with the CPUs. However it only allows
-a limited set of atomic operation from device on main memory. This is worse
-in the other direction the CPUs can only access a limited range of the device
+If we only consider the PCIE bus, then a device can access main memory (often
+through an IOMMU) and be cache coherent with the CPUs. However, it only allows
+a limited set of atomic operations from device on main memory. This is worse
+in the other direction, the CPU can only access a limited range of the device
 memory and can not perform atomic operations on it. Thus device memory can not
-be consider like regular memory from kernel point of view.
+be considered the same as regular memory from the kernel point of view.
 
 Another crippling factor is the limited bandwidth (~32GBytes/s with PCIE 4.0
-and 16 lanes). This is 33 times less that fastest GPU memory (1 TBytes/s).
-The final limitation is latency, access to main memory from the device has an
-order of magnitude higher latency than when the device access its own memory.
+and 16 lanes). This is 33 times less than the fastest GPU memory (1 TBytes/s).
+The final limitation is latency. Access to main memory from the device has an
+order of magnitude higher latency than when the device accesses its own memory.
 
-Some platform are developing new system bus or additions/modifications to PCIE
-to address some of those limitations (OpenCAPI, CCIX). They mainly allow two
+Some platforms are developing new I/O buses or additions/modifications to PCIE
+to address some of these limitations (OpenCAPI, CCIX). They mainly allow two
 way cache coherency between CPU and device and allow all atomic operations the
-architecture supports. Saddly not all platform are following this trends and
-some major architecture are left without hardware solutions to those problems.
+architecture supports. Saddly, not all platforms are following this trend and
+some major architectures are left without hardware solutions to these problems.
 
-So for share address space to make sense not only we must allow device to
+So for shared address space to make sense, not only must we allow device to
 access any memory memory but we must also permit any memory to be migrated to
 device memory while device is using it (blocking CPU access while it happens).
 
 
 -------------------------------------------------------------------------------
 
-3) Share address space and migration
+3) Shared address space and migration
 
 HMM intends to provide two main features. First one is to share the address
-space by duplication the CPU page table into the device page table so same
-address point to same memory and this for any valid main memory address in
+space by duplicating the CPU page table in the device page table so the same
+address points to the same physical memory for any valid main memory address in
 the process address space.
 
-To achieve this, HMM offer a set of helpers to populate the device page table
+To achieve this, HMM offers a set of helpers to populate the device page table
 while keeping track of CPU page table updates. Device page table updates are
-not as easy as CPU page table updates. To update the device page table you must
-allow a buffer (or use a pool of pre-allocated buffer) and write GPU specifics
-commands in it to perform the update (unmap, cache invalidations and flush,
-...). This can not be done through common code for all device. Hence why HMM
-provides helpers to factor out everything that can be while leaving the gory
-details to the device driver.
-
-The second mechanism HMM provide is a new kind of ZONE_DEVICE memory that does
-allow to allocate a struct page for each page of the device memory. Those page
-are special because the CPU can not map them. They however allow to migrate
-main memory to device memory using exhisting migration mechanism and everything
-looks like if page was swap out to disk from CPU point of view. Using a struct
-page gives the easiest and cleanest integration with existing mm mechanisms.
-Again here HMM only provide helpers, first to hotplug new ZONE_DEVICE memory
-for the device memory and second to perform migration. Policy decision of what
-and when to migrate things is left to the device driver.
-
-Note that any CPU access to a device page trigger a page fault and a migration
-back to main memory ie when a page backing an given address A is migrated from
-a main memory page to a device page then any CPU access to address A trigger a
-page fault and initiate a migration back to main memory.
-
-
-With this two features, HMM not only allow a device to mirror a process address
-space and keeps both CPU and device page table synchronize, but also allow to
-leverage device memory by migrating part of data-set that is actively use by a
-device.
+not as easy as CPU page table updates. To update the device page table, you must
+allocate a buffer (or use a pool of pre-allocated buffers) and write GPU
+specific commands in it to perform the update (unmap, cache invalidations, and
+flush, ...). This can not be done through common code for all devices. Hence
+why HMM provides helpers to factor out everything that can be while leaving the
+hardware specific details to the device driver.
+
+The second mechanism HMM provides, is a new kind of ZONE_DEVICE memory that
+allows allocating a struct page for each page of the device memory. Those pages
+are special because the CPU can not map them. However, they allow migrating
+main memory to device memory using existing migration mechanisms and everything
+looks like a page is swapped out to disk from the CPU point of view. Using a
+struct page gives the easiest and cleanest integration with existing mm mech-
+anisms. Here again, HMM only provides helpers, first to hotplug new ZONE_DEVICE
+memory for the device memory and second to perform migration. Policy decisions
+of what and when to migrate things is left to the device driver.
+
+Note that any CPU access to a device page triggers a page fault and a migration
+back to main memory. For example, when a page backing a given CPU address A is
+migrated from a main memory page to a device page, then any CPU access to
+address A triggers a page fault and initiates a migration back to main memory.
+
+With these two features, HMM not only allows a device to mirror process address
+space and keeping both CPU and device page table synchronized, but also lever-
+ages device memory by migrating the part of the data-set that is actively being
+used by the device.
 
 
 -------------------------------------------------------------------------------
 
 4) Address space mirroring implementation and API
 
-Address space mirroring main objective is to allow to duplicate range of CPU
-page table into a device page table and HMM helps keeping both synchronize. A
+Address space mirroring's main objective is to allow duplication of a range of
+CPU page table into a device page table; HMM helps keep both synchronized. A
 device driver that want to mirror a process address space must start with the
 registration of an hmm_mirror struct:
 
@@ -155,8 +163,8 @@ registration of an hmm_mirror struct:
                                 struct mm_struct *mm);
 
 The locked variant is to be use when the driver is already holding the mmap_sem
-of the mm in write mode. The mirror struct has a set of callback that are use
-to propagate CPU page table:
+of the mm in write mode. The mirror struct has a set of callbacks that are used
+to propagate CPU page tables:
 
  struct hmm_mirror_ops {
      /* sync_cpu_device_pagetables() - synchronize page tables
@@ -181,13 +189,13 @@ to propagate CPU page table:
                      unsigned long end);
  };
 
-Device driver must perform update to the range following action (turn range
-read only, or fully unmap, ...). Once driver callback returns the device must
-be done with the update.
+The device driver must perform the update action to the range (mark range
+read only, or fully unmap, ...). The device must be done with the update before
+the driver callback returns.
 
 
-When device driver wants to populate a range of virtual address it can use
-either:
+When the device driver wants to populate a range of virtual addresses, it can
+use either:
  int hmm_vma_get_pfns(struct vm_area_struct *vma,
                       struct hmm_range *range,
                       unsigned long start,
@@ -201,17 +209,19 @@ either:
                    bool write,
                    bool block);
 
-First one (hmm_vma_get_pfns()) will only fetch present CPU page table entry and
-will not trigger a page fault on missing or non present entry. The second one
-do trigger page fault on missing or read only entry if write parameter is true.
-Page fault use the generic mm page fault code path just like a CPU page fault.
+The first one (hmm_vma_get_pfns()) will only fetch present CPU page table
+entries and will not trigger a page fault on missing or non present entries.
+The second one does trigger a page fault on missing or read only entry if the
+write parameter is true. Page faults use the generic mm page fault code path
+just like a CPU page fault.
 
-Both function copy CPU page table into their pfns array argument. Each entry in
-that array correspond to an address in the virtual range. HMM provide a set of
-flags to help driver identify special CPU page table entries.
+Both functions copy CPU page table entries into their pfns array argument. Each
+entry in that array corresponds to an address in the virtual range. HMM
+provides a set of flags to help the driver identify special CPU page table
+entries.
 
 Locking with the update() callback is the most important aspect the driver must
-respect in order to keep things properly synchronize. The usage pattern is :
+respect in order to keep things properly synchronized. The usage pattern is:
 
  int driver_populate_range(...)
  {
@@ -233,43 +243,44 @@ respect in order to keep things properly synchronize. The usage pattern is :
       return 0;
  }
 
-The driver->update lock is the same lock that driver takes inside its update()
-callback. That lock must be call before hmm_vma_range_done() to avoid any race
-with a concurrent CPU page table update.
+The driver->update lock is the same lock that the driver takes inside its
+update() callback. That lock must be held before hmm_vma_range_done() to avoid
+any race with a concurrent CPU page table update.
 
-HMM implements all this on top of the mmu_notifier API because we wanted to a
-simpler API and also to be able to perform optimization latter own like doing
-concurrent device update in multi-devices scenario.
+HMM implements all this on top of the mmu_notifier API because we wanted a
+simpler API and also to be able to perform optimizations latter on like doing
+concurrent device updates in multi-devices scenario.
 
-HMM also serve as an impedence missmatch between how CPU page table update are
-done (by CPU write to the page table and TLB flushes) from how device update
-their own page table. Device update is a multi-step process, first appropriate
-commands are write to a buffer, then this buffer is schedule for execution on
-the device. It is only once the device has executed commands in the buffer that
-the update is done. Creating and scheduling update command buffer can happen
-concurrently for multiple devices. Waiting for each device to report commands
-as executed is serialize (there is no point in doing this concurrently).
+HMM also serves as an impedence mismatch between how CPU page table updates
+are done (by CPU write to the page table and TLB flushes) and how devices
+update their own page table. Device updates are a multi-step process. First,
+appropriate commands are writen to a buffer, then this buffer is scheduled for
+execution on the device. It is only once the device has executed commands in
+the buffer that the update is done. Creating and scheduling the update command
+buffer can happen concurrently for multiple devices. Waiting for each device to
+report commands as executed is serialized (there is no point in doing this
+concurrently).
 
 
 -------------------------------------------------------------------------------
 
 5) Represent and manage device memory from core kernel point of view
 
-Several differents design were try to support device memory. First one use
-device specific data structure to keep information about migrated memory and
-HMM hooked itself in various place of mm code to handle any access to address
-that were back by device memory. It turns out that this ended up replicating
-most of the fields of struct page and also needed many kernel code path to be
-updated to understand this new kind of memory.
+Several different designs were tried to support device memory. First one used
+a device specific data structure to keep information about migrated memory and
+HMM hooked itself in various places of mm code to handle any access to
+addresses that were backed by device memory. It turns out that this ended up
+replicating most of the fields of struct page and also needed many kernel code
+paths to be updated to understand this new kind of memory.
 
-Thing is most kernel code path never try to access the memory behind a page
-but only care about struct page contents. Because of this HMM switchted to
-directly using struct page for device memory which left most kernel code path
-un-aware of the difference. We only need to make sure that no one ever try to
-map those page from the CPU side.
+Most kernel code paths never try to access the memory behind a page
+but only care about struct page contents. Because of this, HMM switched to
+directly using struct page for device memory which left most kernel code paths
+unaware of the difference. We only need to make sure that no one ever tries to
+map those pages from the CPU side.
 
-HMM provide a set of helpers to register and hotplug device memory as a new
-region needing struct page. This is offer through a very simple API:
+HMM provides a set of helpers to register and hotplug device memory as a new
+region needing a struct page. This is offered through a very simple API:
 
  struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops,
                                    struct device *device,
@@ -289,18 +300,19 @@ The hmm_devmem_ops is where most of the important things are:
  };
 
 The first callback (free()) happens when the last reference on a device page is
-drop. This means the device page is now free and no longer use by anyone. The
-second callback happens whenever CPU try to access a device page which it can
-not do. This second callback must trigger a migration back to system memory.
+dropped. This means the device page is now free and no longer used by anyone.
+The second callback happens whenever the CPU tries to access a device page
+which it can not do. This second callback must trigger a migration back to
+system memory.
 
 
 -------------------------------------------------------------------------------
 
-6) Migrate to and from device memory
+6) Migration to and from device memory
 
-Because CPU can not access device memory, migration must use device DMA engine
-to perform copy from and to device memory. For this we need a new migration
-helper:
+Because the CPU can not access device memory, migration must use the device DMA
+engine to perform copy from and to device memory. For this we need a new
+migration helper:
 
  int migrate_vma(const struct migrate_vma_ops *ops,
                  struct vm_area_struct *vma,
@@ -311,15 +323,15 @@ helper:
                  unsigned long *dst,
                  void *private);
 
-Unlike other migration function it works on a range of virtual address, there
-is two reasons for that. First device DMA copy has a high setup overhead cost
+Unlike other migration functions it works on a range of virtual address, there
+are two reasons for that. First, device DMA copy has a high setup overhead cost
 and thus batching multiple pages is needed as otherwise the migration overhead
-make the whole excersie pointless. The second reason is because driver trigger
-such migration base on range of address the device is actively accessing.
+makes the whole exersize pointless. The second reason is because the
+migration might be for a range of addresses the device is actively accessing.
 
-The migrate_vma_ops struct define two callbacks. First one (alloc_and_copy())
-control destination memory allocation and copy operation. Second one is there
-to allow device driver to perform cleanup operation after migration.
+The migrate_vma_ops struct defines two callbacks. First one (alloc_and_copy())
+controls destination memory allocation and copy operation. Second one is there
+to allow the device driver to perform cleanup operations after migration.
 
  struct migrate_vma_ops {
      void (*alloc_and_copy)(struct vm_area_struct *vma,
@@ -336,19 +348,19 @@ to allow device driver to perform cleanup operation after migration.
                               void *private);
  };
 
-It is important to stress that this migration helpers allow for hole in the
+It is important to stress that these migration helpers allow for holes in the
 virtual address range. Some pages in the range might not be migrated for all
-the usual reasons (page is pin, page is lock, ...). This helper does not fail
-but just skip over those pages.
+the usual reasons (page is pinned, page is locked, ...). This helper does not
+fail but just skips over those pages.
 
-The alloc_and_copy() might as well decide to not migrate all pages in the
-range (for reasons under the callback control). For those the callback just
-have to leave the corresponding dst entry empty.
+The alloc_and_copy() might decide to not migrate all pages in the
+range (for reasons under the callback control). For those, the callback just
+has to leave the corresponding dst entry empty.
 
-Finaly the migration of the struct page might fails (for file back page) for
+Finally, the migration of the struct page might fail (for file backed page) for
 various reasons (failure to freeze reference, or update page cache, ...). If
-that happens then the finalize_and_map() can catch any pages that was not
-migrated. Note those page were still copied to new page and thus we wasted
+that happens, then the finalize_and_map() can catch any pages that were not
+migrated. Note those pages were still copied to a new page and thus we wasted
 bandwidth but this is considered as a rare event and a price that we are
 willing to pay to keep all the code simpler.
 
@@ -358,27 +370,27 @@ willing to pay to keep all the code simpler.
 7) Memory cgroup (memcg) and rss accounting
 
 For now device memory is accounted as any regular page in rss counters (either
-anonymous if device page is use for anonymous, file if device page is use for
-file back page or shmem if device page is use for share memory). This is a
-deliberate choice to keep existing application that might start using device
-memory without knowing about it to keep runing unimpacted.
-
-Drawbacks is that OOM killer might kill an application using a lot of device
-memory and not a lot of regular system memory and thus not freeing much system
-memory. We want to gather more real world experience on how application and
-system react under memory pressure in the presence of device memory before
+anonymous if device page is used for anonymous, file if device page is used for
+file backed page or shmem if device page is used for shared memory). This is a
+deliberate choice to keep existing applications, that might start using device
+memory without knowing about it, running unimpacted.
+
+A Drawback is that the OOM killer might kill an application using a lot of
+device memory and not a lot of regular system memory and thus not freeing much
+system memory. We want to gather more real world experience on how applications
+and system react under memory pressure in the presence of device memory before
 deciding to account device memory differently.
 
 
-Same decision was made for memory cgroup. Device memory page are accounted
+Same decision was made for memory cgroup. Device memory pages are accounted
 against same memory cgroup a regular page would be accounted to. This does
 simplify migration to and from device memory. This also means that migration
 back from device memory to regular memory can not fail because it would
 go above memory cgroup limit. We might revisit this choice latter on once we
-get more experience in how device memory is use and its impact on memory
+get more experience in how device memory is used and its impact on memory
 resource control.
 
 
-Note that device memory can never be pin nor by device driver nor through GUP
+Note that device memory can never be pinned by device driver nor through GUP
 and thus such memory is always free upon process exit. Or when last reference
-is drop in case of share memory or file back memory.
+is dropped in case of shared memory or file backed memory.
diff --git a/MAINTAINERS b/MAINTAINERS
index 0e698813a380..402d6747a0fc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6410,6 +6410,7 @@ L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/hmm*
 F:	include/linux/hmm*
+F:	Documentation/vm/hmm.txt
 
 HOST AP DRIVER
 M:	Jouni Malinen <j@w1.fi>
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 2072f3451e9c..9dbe645ee127 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -833,7 +833,7 @@ void flush_dcache_page(struct page *page)
 	}
 
 	/* don't handle anon pages here */
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!mapping)
 		return;
 
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 4a247acd1b96..009db7d275f8 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -128,12 +128,7 @@ asmlinkage void __div0(void)
 	error("Attempting division by 0!");
 }
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -150,8 +145,6 @@ decompress_kernel(unsigned long output_start, unsigned long free_mem_ptr_p,
 {
 	int ret;
 
-	__stack_chk_guard_setup();
-
 	output_data		= (unsigned char *)output_start;
 	free_mem_ptr		= free_mem_ptr_p;
 	free_mem_end_ptr	= free_mem_ptr_end_p;
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index 4355f0ec44d6..f98baaec0a15 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -17,6 +17,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/personality.h>	/* For READ_IMPLIES_EXEC */
+
 #ifndef CONFIG_MMU
 
 #include <asm/page-nommu.h>
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 1267e64133b9..0224416cba3c 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -70,7 +70,7 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 	void *kto = kmap_atomic(to);
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	raw_spin_lock(&minicache_lock);
 
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 70423345da26..a698e575e321 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -76,7 +76,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 	unsigned long kfrom, kto;
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	/* FIXME: not highmem safe */
 	discard_old_kernel_data(page_address(to));
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 0fb85025344d..97972379f4d6 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -90,7 +90,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 	void *kto = kmap_atomic(to);
 
 	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
-		__flush_dcache_page(page_mapping(from), from);
+		__flush_dcache_page(page_mapping_file(from), from);
 
 	raw_spin_lock(&minicache_lock);
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index ada8eb206a90..8c398fedbbb6 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -466,6 +466,12 @@ void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
 void __init dma_contiguous_remap(void)
 {
 	int i;
+
+	if (!dma_mmu_remap_num)
+		return;
+
+	/* call flush_cache_all() since CMA area would be large enough */
+	flush_cache_all();
 	for (i = 0; i < dma_mmu_remap_num; i++) {
 		phys_addr_t start = dma_mmu_remap[i].base;
 		phys_addr_t end = start + dma_mmu_remap[i].size;
@@ -498,7 +504,15 @@ void __init dma_contiguous_remap(void)
 		flush_tlb_kernel_range(__phys_to_virt(start),
 				       __phys_to_virt(end));
 
-		iotable_init(&map, 1);
+		/*
+		 * All the memory in CMA region will be on ZONE_MOVABLE.
+		 * If that zone is considered as highmem, the memory in CMA
+		 * region is also considered as highmem even if it's
+		 * physical address belong to lowmem. In this case,
+		 * re-mapping isn't required.
+		 */
+		if (!is_highmem_idx(ZONE_MOVABLE))
+			iotable_init(&map, 1);
 	}
 }
 
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index d9e0d00a6699..4d75dae5ac96 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -195,7 +195,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 	if (mapping) {
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index f1e6190aa7ea..58469623b015 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -285,7 +285,7 @@ void __sync_icache_dcache(pte_t pteval)
 
 	page = pfn_to_page(pfn);
 	if (cache_is_vipt_aliasing())
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 	else
 		mapping = NULL;
 
@@ -333,7 +333,7 @@ void flush_dcache_page(struct page *page)
 		return;
 	}
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	if (!cache_ops_need_broadcast() &&
 	    mapping && !page_mapcount(page))
@@ -363,7 +363,7 @@ void flush_kernel_dcache_page(struct page *page)
 	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
 		struct address_space *mapping;
 
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 
 		if (!mapping || mapping_mapped(mapping)) {
 			void *addr;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index eb1de66517d5..f866870db749 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -21,20 +21,20 @@
 #define MIN_GAP (128*1024*1024UL)
 #define MAX_GAP ((TASK_SIZE)/6*5)
 
-static int mmap_is_legacy(void)
+static int mmap_is_legacy(struct rlimit *rlim_stack)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
 		return 1;
 
-	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	if (rlim_stack->rlim_cur == RLIM_INFINITY)
 		return 1;
 
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_base(unsigned long rnd)
+static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 
 	if (gap < MIN_GAP)
 		gap = MIN_GAP;
@@ -180,18 +180,18 @@ unsigned long arch_mmap_rnd(void)
 	return rnd << PAGE_SHIFT;
 }
 
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = 0UL;
 
 	if (current->flags & PF_RANDOMIZE)
 		random_factor = arch_mmap_rnd();
 
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index decccffb03ca..842c8a5fcd53 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -38,12 +38,12 @@
 #define MIN_GAP (SZ_128M)
 #define MAX_GAP	(STACK_TOP/6*5)
 
-static int mmap_is_legacy(void)
+static int mmap_is_legacy(struct rlimit *rlim_stack)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
 		return 1;
 
-	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	if (rlim_stack->rlim_cur == RLIM_INFINITY)
 		return 1;
 
 	return sysctl_legacy_va_layout;
@@ -62,9 +62,9 @@ unsigned long arch_mmap_rnd(void)
 	return rnd << PAGE_SHIFT;
 }
 
-static unsigned long mmap_base(unsigned long rnd)
+static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = (STACK_RND_MASK << PAGE_SHIFT) + stack_guard_gap;
 
 	/* Values close to RLIM_INFINITY can overflow. */
@@ -83,7 +83,7 @@ static unsigned long mmap_base(unsigned long rnd)
  * This function, called very early during the creation of a new process VM
  * image, sets up which VM layout function to use:
  */
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = 0UL;
 
@@ -94,11 +94,11 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 * Fall back to the standard layout if the personality bit is set, or
 	 * if the expected stack growth is unlimited:
 	 */
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index fdf99e9dd4c3..81df9047e110 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -76,12 +76,7 @@ void error(char *x)
 #include "../../../../lib/decompress_unxz.c"
 #endif
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -92,8 +87,6 @@ void decompress_kernel(unsigned long boot_heap_start)
 {
 	unsigned long zimage_start, zimage_size;
 
-	__stack_chk_guard_setup();
-
 	zimage_start = (unsigned long)(&__image_begin);
 	zimage_size = (unsigned long)(&__image_end) -
 	    (unsigned long)(&__image_begin);
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 44ac64d51827..0d3c656feba0 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -86,7 +86,7 @@ SYSCALL_DEFINE3(cacheflush, unsigned long, addr, unsigned long, bytes,
 
 void __flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 	unsigned long addr;
 
 	if (mapping && !mapping_mapped(mapping)) {
diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c
index 33d3251ecd37..2f616ebeb7e0 100644
--- a/arch/mips/mm/mmap.c
+++ b/arch/mips/mm/mmap.c
@@ -24,20 +24,20 @@ EXPORT_SYMBOL(shm_align_mask);
 #define MIN_GAP (128*1024*1024UL)
 #define MAX_GAP ((TASK_SIZE)/6*5)
 
-static int mmap_is_legacy(void)
+static int mmap_is_legacy(struct rlimit *rlim_stack)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
 		return 1;
 
-	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	if (rlim_stack->rlim_cur == RLIM_INFINITY)
 		return 1;
 
 	return sysctl_legacy_va_layout;
 }
 
-static unsigned long mmap_base(unsigned long rnd)
+static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 
 	if (gap < MIN_GAP)
 		gap = MIN_GAP;
@@ -158,18 +158,18 @@ unsigned long arch_mmap_rnd(void)
 	return rnd << PAGE_SHIFT;
 }
 
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = 0UL;
 
 	if (current->flags & PF_RANDOMIZE)
 		random_factor = arch_mmap_rnd();
 
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/nios2/mm/cacheflush.c b/arch/nios2/mm/cacheflush.c
index 87bf88ed04c6..506f6e1c86d5 100644
--- a/arch/nios2/mm/cacheflush.c
+++ b/arch/nios2/mm/cacheflush.c
@@ -180,7 +180,7 @@ void flush_dcache_page(struct page *page)
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	/* Flush this page if there are aliases. */
 	if (mapping && !mapping_mapped(mapping)) {
@@ -215,7 +215,7 @@ void update_mmu_cache(struct vm_area_struct *vma,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index e3b45546d589..a99da95fc9fd 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -88,7 +88,8 @@ update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
 		return;
 
 	page = pfn_to_page(pfn);
-	if (page_mapping(page) && test_bit(PG_dcache_dirty, &page->flags)) {
+	if (page_mapping_file(page) &&
+	    test_bit(PG_dcache_dirty, &page->flags)) {
 		flush_kernel_dcache_page_addr(pfn_va(pfn));
 		clear_bit(PG_dcache_dirty, &page->flags);
 	} else if (parisc_requires_coherency())
@@ -304,7 +305,7 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
 	unsigned long addr, old_addr = 0;
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 8c99ebbe2bac..43b308cfdf53 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -70,12 +70,18 @@ static inline unsigned long COLOR_ALIGN(unsigned long addr,
  * Top of mmap area (just below the process stack).
  */
 
-static unsigned long mmap_upper_limit(void)
+/*
+ * When called from arch_get_unmapped_area(), rlim_stack will be NULL,
+ * indicating that "current" should be used instead of a passed-in
+ * value from the exec bprm as done with arch_pick_mmap_layout().
+ */
+static unsigned long mmap_upper_limit(struct rlimit *rlim_stack)
 {
 	unsigned long stack_base;
 
 	/* Limit stack size - see setup_arg_pages() in fs/exec.c */
-	stack_base = rlimit_max(RLIMIT_STACK);
+	stack_base = rlim_stack ? rlim_stack->rlim_max
+				: rlimit_max(RLIMIT_STACK);
 	if (stack_base > STACK_SIZE_MAX)
 		stack_base = STACK_SIZE_MAX;
 
@@ -127,7 +133,7 @@ unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	info.flags = 0;
 	info.length = len;
 	info.low_limit = mm->mmap_legacy_base;
-	info.high_limit = mmap_upper_limit();
+	info.high_limit = mmap_upper_limit(NULL);
 	info.align_mask = last_mmap ? (PAGE_MASK & (SHM_COLOUR - 1)) : 0;
 	info.align_offset = shared_align_offset(last_mmap, pgoff);
 	addr = vm_unmapped_area(&info);
@@ -250,10 +256,10 @@ static unsigned long mmap_legacy_base(void)
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	mm->mmap_legacy_base = mmap_legacy_base();
-	mm->mmap_base = mmap_upper_limit();
+	mm->mmap_base = mmap_upper_limit(rlim_stack);
 
 	if (mmap_is_legacy()) {
 		mm->mmap_base = mm->mmap_legacy_base;
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 48f2ed2a71ae..78540c074d70 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -118,12 +118,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long ceiling);
 
 /*
- * The version of vma_mmu_pagesize() in arch/powerpc/mm/hugetlbpage.c needs
- * to override the version in mm/hugetlb.c
- */
-#define vma_mmu_pagesize vma_mmu_pagesize
-
-/*
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index f4153f21d214..1d1c6a22ee3c 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -572,10 +572,7 @@ unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 		return 1UL << mmu_psize_to_shift(psize);
 	}
 #endif
-	if (!is_vm_hugetlb_page(vma))
-		return PAGE_SIZE;
-
-	return huge_page_size(hstate_vma(vma));
+	return vma_kernel_pagesize(vma);
 }
 
 static inline bool is_power_of_4(unsigned long x)
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index d503f344e476..b24ce40acd47 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -39,12 +39,12 @@
 #define MIN_GAP (128*1024*1024)
 #define MAX_GAP (TASK_SIZE/6*5)
 
-static inline int mmap_is_legacy(void)
+static inline int mmap_is_legacy(struct rlimit *rlim_stack)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
 		return 1;
 
-	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	if (rlim_stack->rlim_cur == RLIM_INFINITY)
 		return 1;
 
 	return sysctl_legacy_va_layout;
@@ -76,9 +76,10 @@ static inline unsigned long stack_maxrandom_size(void)
 		return (1<<30);
 }
 
-static inline unsigned long mmap_base(unsigned long rnd)
+static inline unsigned long mmap_base(unsigned long rnd,
+				      struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
 
 	/* Values close to RLIM_INFINITY can overflow. */
@@ -196,26 +197,28 @@ radix__arch_get_unmapped_area_topdown(struct file *filp,
 }
 
 static void radix__arch_pick_mmap_layout(struct mm_struct *mm,
-					unsigned long random_factor)
+					unsigned long random_factor,
+					struct rlimit *rlim_stack)
 {
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = radix__arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = radix__arch_get_unmapped_area_topdown;
 	}
 }
 #else
 /* dummy */
 extern void radix__arch_pick_mmap_layout(struct mm_struct *mm,
-					unsigned long random_factor);
+					unsigned long random_factor,
+					struct rlimit *rlim_stack);
 #endif
 /*
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = 0UL;
 
@@ -223,16 +226,17 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		random_factor = arch_mmap_rnd();
 
 	if (radix_enabled())
-		return radix__arch_pick_mmap_layout(mm, random_factor);
+		return radix__arch_pick_mmap_layout(mm, random_factor,
+						    rlim_stack);
 	/*
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
 	 */
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = TASK_UNMAPPED_BASE;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e0a2d8e806ed..4c615fcb0cf0 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -75,8 +75,7 @@ EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
 /*
  * Taken from alloc_migrate_target with changes to remove CMA allocations
  */
-struct page *new_iommu_non_cma_page(struct page *page, unsigned long private,
-					int **resultp)
+struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
 {
 	gfp_t gfp_mask = GFP_USER;
 	struct page *new_page;
@@ -112,7 +111,7 @@ static int mm_iommu_move_page_from_cma(struct page *page)
 	put_page(page); /* Drop the gup reference */
 
 	ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
-				NULL, 0, MIGRATE_SYNC, MR_CMA);
+				NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
 	if (ret) {
 		if (!list_empty(&cma_migrate_pages))
 			putback_movable_pages(&cma_migrate_pages);
diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c
index a6198d4f0f03..5ca3e22d0512 100644
--- a/arch/powerpc/sysdev/dart_iommu.c
+++ b/arch/powerpc/sysdev/dart_iommu.c
@@ -38,6 +38,7 @@
 #include <linux/suspend.h>
 #include <linux/memblock.h>
 #include <linux/gfp.h>
+#include <linux/kmemleak.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c
index c4dae27172b3..6243a7e537d0 100644
--- a/arch/powerpc/sysdev/msi_bitmap.c
+++ b/arch/powerpc/sysdev/msi_bitmap.c
@@ -10,6 +10,7 @@
 
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/kmemleak.h>
 #include <linux/bitmap.h>
 #include <linux/bootmem.h>
 #include <asm/msi_bitmap.h>
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index c7a627620e5e..8c867b43c8eb 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -15,7 +15,7 @@
 #include <linux/hardirq.h>
 #include <linux/log2.h>
 #include <linux/kprobes.h>
-#include <linux/slab.h>
+#include <linux/kmemleak.h>
 #include <linux/time.h>
 #include <linux/module.h>
 #include <linux/sched/signal.h>
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a4a9fe1934e9..2f8f7d7dd9a8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -27,7 +27,6 @@
 #include <linux/err.h>
 #include <linux/spinlock.h>
 #include <linux/kernel_stat.h>
-#include <linux/kmemleak.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/irqflags.h>
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 831bdcf407bb..0a7627cdb34e 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -37,11 +37,11 @@ static unsigned long stack_maxrandom_size(void)
 #define MIN_GAP (32*1024*1024)
 #define MAX_GAP (STACK_TOP/6*5)
 
-static inline int mmap_is_legacy(void)
+static inline int mmap_is_legacy(struct rlimit *rlim_stack)
 {
 	if (current->personality & ADDR_COMPAT_LAYOUT)
 		return 1;
-	if (rlimit(RLIMIT_STACK) == RLIM_INFINITY)
+	if (rlim_stack->rlim_cur == RLIM_INFINITY)
 		return 1;
 	return sysctl_legacy_va_layout;
 }
@@ -56,9 +56,10 @@ static unsigned long mmap_base_legacy(unsigned long rnd)
 	return TASK_UNMAPPED_BASE + rnd;
 }
 
-static inline unsigned long mmap_base(unsigned long rnd)
+static inline unsigned long mmap_base(unsigned long rnd,
+				      struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 
 	if (gap < MIN_GAP)
 		gap = MIN_GAP;
@@ -184,7 +185,7 @@ check_asce_limit:
  * This function, called very early during the creation of a new
  * process VM image, sets up which VM layout function to use:
  */
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = 0UL;
 
@@ -195,11 +196,11 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
 	 */
-	if (mmap_is_legacy()) {
+	if (mmap_is_legacy(rlim_stack)) {
 		mm->mmap_base = mmap_base_legacy(random_factor);
 		mm->get_unmapped_area = arch_get_unmapped_area;
 	} else {
-		mm->mmap_base = mmap_base(random_factor);
+		mm->mmap_base = mmap_base(random_factor, rlim_stack);
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
diff --git a/arch/sh/boot/compressed/misc.c b/arch/sh/boot/compressed/misc.c
index 627ce8e75e01..c15cac9251b9 100644
--- a/arch/sh/boot/compressed/misc.c
+++ b/arch/sh/boot/compressed/misc.c
@@ -104,12 +104,7 @@ static void error(char *x)
 	while(1);	/* Halt */
 }
 
-unsigned long __stack_chk_guard;
-
-void __stack_chk_guard_setup(void)
-{
-	__stack_chk_guard = 0x000a0dff;
-}
+const unsigned long __stack_chk_guard = 0x000a0dff;
 
 void __stack_chk_fail(void)
 {
@@ -130,8 +125,6 @@ void decompress_kernel(void)
 {
 	unsigned long output_addr;
 
-	__stack_chk_guard_setup();
-
 #ifdef CONFIG_SUPERH64
 	output_addr = (CONFIG_MEMORY_START + 0x2000);
 #else
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 58aaa4f33b81..eee911422cf9 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -112,7 +112,7 @@ static void sh4_flush_dcache_page(void *arg)
 	struct page *page = arg;
 	unsigned long addr = (unsigned long)page_address(page);
 #ifndef CONFIG_SMP
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/sh/mm/cache-sh7705.c b/arch/sh/mm/cache-sh7705.c
index 6cd2aa395817..ed25eba80667 100644
--- a/arch/sh/mm/cache-sh7705.c
+++ b/arch/sh/mm/cache-sh7705.c
@@ -136,7 +136,7 @@ static void __flush_dcache_page(unsigned long phys)
 static void sh7705_flush_dcache_page(void *arg)
 {
 	struct page *page = arg;
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d66dde833f5e..713670e6d13d 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -22,7 +22,6 @@
 #include <linux/seq_file.h>
 #include <linux/ftrace.h>
 #include <linux/irq.h>
-#include <linux/kmemleak.h>
 
 #include <asm/ptrace.h>
 #include <asm/processor.h>
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index c50182cd2f64..d3ea1f3c06a0 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -929,9 +929,9 @@ static inline void __local_flush_dcache_page(struct page *page)
 #ifdef DCACHE_ALIASING_POSSIBLE
 	__flush_dcache_page(page_address(page),
 			    ((tlb_type == spitfire) &&
-			     page_mapping(page) != NULL));
+			     page_mapping_file(page) != NULL));
 #else
-	if (page_mapping(page) != NULL &&
+	if (page_mapping_file(page) != NULL &&
 	    tlb_type == spitfire)
 		__flush_icache_page(__pa(page_address(page)));
 #endif
@@ -958,7 +958,7 @@ void smp_flush_dcache_page_impl(struct page *page, int cpu)
 
 		if (tlb_type == spitfire) {
 			data0 = ((u64)&xcall_flush_dcache_page_spitfire);
-			if (page_mapping(page) != NULL)
+			if (page_mapping_file(page) != NULL)
 				data0 |= ((u64)1 << 32);
 		} else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
 #ifdef DCACHE_ALIASING_POSSIBLE
@@ -994,7 +994,7 @@ void flush_dcache_page_all(struct mm_struct *mm, struct page *page)
 	pg_addr = page_address(page);
 	if (tlb_type == spitfire) {
 		data0 = ((u64)&xcall_flush_dcache_page_spitfire);
-		if (page_mapping(page) != NULL)
+		if (page_mapping_file(page) != NULL)
 			data0 |= ((u64)1 << 32);
 	} else if (tlb_type == cheetah || tlb_type == cheetah_plus) {
 #ifdef DCACHE_ALIASING_POSSIBLE
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 348a17ecdf66..9ef8de63f28b 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -276,7 +276,7 @@ static unsigned long mmap_rnd(void)
 	return rnd << PAGE_SHIFT;
 }
 
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	unsigned long random_factor = mmap_rnd();
 	unsigned long gap;
@@ -285,7 +285,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 * Fall back to the standard layout if the personality
 	 * bit is set, or if the expected stack growth is unlimited:
 	 */
-	gap = rlimit(RLIMIT_STACK);
+	gap = rlim_stack->rlim_cur;
 	if (!test_thread_flag(TIF_32BIT) ||
 	    (current->personality & ADDR_COMPAT_LAYOUT) ||
 	    gap == RLIM_INFINITY ||
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index cb9ebac6663f..8aeb1aabe76e 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -206,9 +206,9 @@ inline void flush_dcache_page_impl(struct page *page)
 #ifdef DCACHE_ALIASING_POSSIBLE
 	__flush_dcache_page(page_address(page),
 			    ((tlb_type == spitfire) &&
-			     page_mapping(page) != NULL));
+			     page_mapping_file(page) != NULL));
 #else
-	if (page_mapping(page) != NULL &&
+	if (page_mapping_file(page) != NULL &&
 	    tlb_type == spitfire)
 		__flush_icache_page(__pa(page_address(page)));
 #endif
@@ -490,7 +490,7 @@ void flush_dcache_page(struct page *page)
 
 	this_cpu = get_cpu();
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (mapping && !mapping_mapped(mapping)) {
 		int dirty = test_bit(PG_dcache_dirty, &page->flags);
 		if (dirty) {
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index b5cfab711651..3d72d2deb13b 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -128,7 +128,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 			goto no_cache_flush;
 
 		/* A real file page? */
-		mapping = page_mapping(page);
+		mapping = page_mapping_file(page);
 		if (!mapping)
 			goto no_cache_flush;
 
diff --git a/arch/unicore32/mm/flush.c b/arch/unicore32/mm/flush.c
index 6d4c096ffa2a..74f4d636df2d 100644
--- a/arch/unicore32/mm/flush.c
+++ b/arch/unicore32/mm/flush.c
@@ -83,7 +83,7 @@ void flush_dcache_page(struct page *page)
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 
 	if (mapping && !mapping_mapped(mapping))
 		clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c
index 4f5a532bee13..0c94b7b4514d 100644
--- a/arch/unicore32/mm/mmu.c
+++ b/arch/unicore32/mm/mmu.c
@@ -503,7 +503,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	if (page == ZERO_PAGE(0))
 		return;
 
-	mapping = page_mapping(page);
+	mapping = page_mapping_file(page);
 	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
 	if (mapping)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 14437116ffea..77625b60a510 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -6,7 +6,6 @@
 #include <linux/bootmem.h>
 #include <linux/gfp.h>
 #include <linux/pci.h>
-#include <linux/kmemleak.h>
 
 #include <asm/proto.h>
 #include <asm/dma.h>
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 45241de66785..dca9abf2b85c 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1328,14 +1328,39 @@ int kern_addr_valid(unsigned long addr)
 	return pfn_valid(pte_pfn(*pte));
 }
 
+/*
+ * Block size is the minimum amount of memory which can be hotplugged or
+ * hotremoved. It must be power of two and must be equal or larger than
+ * MIN_MEMORY_BLOCK_SIZE.
+ */
+#define MAX_BLOCK_SIZE (2UL << 30)
+
+/* Amount of ram needed to start using large blocks */
+#define MEM_SIZE_FOR_LARGE_BLOCK (64UL << 30)
+
 static unsigned long probe_memory_block_size(void)
 {
-	unsigned long bz = MIN_MEMORY_BLOCK_SIZE;
+	unsigned long boot_mem_end = max_pfn << PAGE_SHIFT;
+	unsigned long bz;
 
-	/* if system is UV or has 64GB of RAM or more, use large blocks */
-	if (is_uv_system() || ((max_pfn << PAGE_SHIFT) >= (64UL << 30)))
-		bz = 2UL << 30; /* 2GB */
+	/* If this is UV system, always set 2G block size */
+	if (is_uv_system()) {
+		bz = MAX_BLOCK_SIZE;
+		goto done;
+	}
 
+	/* Use regular block if RAM is smaller than MEM_SIZE_FOR_LARGE_BLOCK */
+	if (boot_mem_end < MEM_SIZE_FOR_LARGE_BLOCK) {
+		bz = MIN_MEMORY_BLOCK_SIZE;
+		goto done;
+	}
+
+	/* Find the largest allowed block size that aligns to memory end */
+	for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+		if (IS_ALIGNED(boot_mem_end, bz))
+			break;
+	}
+done:
 	pr_info("x86/mm: Memory block size: %ldMB\n", bz >> 20);
 
 	return bz;
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 155ecbac9e28..48c591251600 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -90,9 +90,10 @@ unsigned long arch_mmap_rnd(void)
 	return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits);
 }
 
-static unsigned long mmap_base(unsigned long rnd, unsigned long task_size)
+static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
+			       struct rlimit *rlim_stack)
 {
-	unsigned long gap = rlimit(RLIMIT_STACK);
+	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
 	unsigned long gap_min, gap_max;
 
@@ -126,16 +127,17 @@ static unsigned long mmap_legacy_base(unsigned long rnd,
  * process VM image, sets up which VM layout function to use:
  */
 static void arch_pick_mmap_base(unsigned long *base, unsigned long *legacy_base,
-		unsigned long random_factor, unsigned long task_size)
+		unsigned long random_factor, unsigned long task_size,
+		struct rlimit *rlim_stack)
 {
 	*legacy_base = mmap_legacy_base(random_factor, task_size);
 	if (mmap_is_legacy())
 		*base = *legacy_base;
 	else
-		*base = mmap_base(random_factor, task_size);
+		*base = mmap_base(random_factor, task_size, rlim_stack);
 }
 
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	if (mmap_is_legacy())
 		mm->get_unmapped_area = arch_get_unmapped_area;
@@ -143,7 +145,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 
 	arch_pick_mmap_base(&mm->mmap_base, &mm->mmap_legacy_base,
-			arch_rnd(mmap64_rnd_bits), task_size_64bit(0));
+			arch_rnd(mmap64_rnd_bits), task_size_64bit(0),
+			rlim_stack);
 
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
 	/*
@@ -153,7 +156,8 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 	 * mmap_base, the compat syscall uses mmap_compat_base.
 	 */
 	arch_pick_mmap_base(&mm->mmap_compat_base, &mm->mmap_compat_legacy_base,
-			arch_rnd(mmap32_rnd_bits), task_size_32bit());
+			arch_rnd(mmap32_rnd_bits), task_size_32bit(),
+			rlim_stack);
 #endif
 }
 
diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c
index 57dc231a0709..9220dcde7520 100644
--- a/arch/xtensa/mm/cache.c
+++ b/arch/xtensa/mm/cache.c
@@ -127,7 +127,7 @@ EXPORT_SYMBOL(copy_user_highpage);
 
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping = page_mapping_file(page);
 
 	/*
 	 * If we have a mapping but the page is not mapped to user-space
diff --git a/block/genhd.c b/block/genhd.c
index dc7e089373b9..10dcc29b5e9d 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -991,7 +991,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index fe4b24f05f6a..79fcd2bae96b 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -187,13 +187,14 @@ int memory_isolate_notify(unsigned long val, void *v)
 }
 
 /*
- * The probe routines leave the pages reserved, just as the bootmem code does.
- * Make sure they're still that way.
+ * The probe routines leave the pages uninitialized, just as the bootmem code
+ * does. Make sure we do not access them, but instead use only information from
+ * within sections.
  */
-static bool pages_correctly_reserved(unsigned long start_pfn)
+static bool pages_correctly_probed(unsigned long start_pfn)
 {
-	int i, j;
-	struct page *page;
+	unsigned long section_nr = pfn_to_section_nr(start_pfn);
+	unsigned long section_nr_end = section_nr + sections_per_block;
 	unsigned long pfn = start_pfn;
 
 	/*
@@ -201,21 +202,24 @@ static bool pages_correctly_reserved(unsigned long start_pfn)
 	 * SPARSEMEM_VMEMMAP. We lookup the page once per section
 	 * and assume memmap is contiguous within each section
 	 */
-	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
+	for (; section_nr < section_nr_end; section_nr++) {
 		if (WARN_ON_ONCE(!pfn_valid(pfn)))
 			return false;
-		page = pfn_to_page(pfn);
-
-		for (j = 0; j < PAGES_PER_SECTION; j++) {
-			if (PageReserved(page + j))
-				continue;
-
-			printk(KERN_WARNING "section number %ld page number %d "
-				"not reserved, was it already online?\n",
-				pfn_to_section_nr(pfn), j);
 
+		if (!present_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) not present",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
+			return false;
+		} else if (!valid_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) no valid memmap",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
+			return false;
+		} else if (online_section_nr(section_nr)) {
+			pr_warn("section %ld pfn[%lx, %lx) is already online",
+				section_nr, pfn, pfn + PAGES_PER_SECTION);
 			return false;
 		}
+		pfn += PAGES_PER_SECTION;
 	}
 
 	return true;
@@ -237,7 +241,7 @@ memory_block_action(unsigned long phys_index, unsigned long action, int online_t
 
 	switch (action) {
 	case MEM_ONLINE:
-		if (!pages_correctly_reserved(start_pfn))
+		if (!pages_correctly_probed(start_pfn))
 			return -EBUSY;
 
 		ret = online_pages(start_pfn, nr_pages, online_type);
@@ -708,7 +712,7 @@ static int add_memory_block(int base_section_nr)
  * need an interface for the VM to add new memory regions,
  * but without onlining it.
  */
-int register_new_memory(int nid, struct mem_section *section)
+int hotplug_memory_register(int nid, struct mem_section *section)
 {
 	int ret = 0;
 	struct memory_block *mem;
@@ -727,7 +731,7 @@ int register_new_memory(int nid, struct mem_section *section)
 	}
 
 	if (mem->section_count == sections_per_block)
-		ret = register_mem_sect_under_node(mem, nid);
+		ret = register_mem_sect_under_node(mem, nid, false);
 out:
 	mutex_unlock(&mem_sysfs_mutex);
 	return ret;
diff --git a/drivers/base/node.c b/drivers/base/node.c
index c5f81fc621ac..7a3a580821e0 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -399,13 +399,16 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
 }
 
 /* register memory section under specified node if it spans that node */
-int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
+int register_mem_sect_under_node(struct memory_block *mem_blk, int nid,
+				 bool check_nid)
 {
 	int ret;
 	unsigned long pfn, sect_start_pfn, sect_end_pfn;
 
 	if (!mem_blk)
 		return -EFAULT;
+
+	mem_blk->nid = nid;
 	if (!node_online(nid))
 		return 0;
 
@@ -425,11 +428,18 @@ int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
 			continue;
 		}
 
-		page_nid = get_nid_for_pfn(pfn);
-		if (page_nid < 0)
-			continue;
-		if (page_nid != nid)
-			continue;
+		/*
+		 * We need to check if page belongs to nid only for the boot
+		 * case, during hotplug we know that all pages in the memory
+		 * block belong to the same node.
+		 */
+		if (check_nid) {
+			page_nid = get_nid_for_pfn(pfn);
+			if (page_nid < 0)
+				continue;
+			if (page_nid != nid)
+				continue;
+		}
 		ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
 					&mem_blk->dev.kobj,
 					kobject_name(&mem_blk->dev.kobj));
@@ -504,7 +514,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
 
 		mem_blk = find_memory_block_hinted(mem_sect, mem_blk);
 
-		ret = register_mem_sect_under_node(mem_blk, nid);
+		ret = register_mem_sect_under_node(mem_blk, nid, true);
 		if (!err)
 			err = ret;
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 71b449613cfa..0f3fadd71230 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -44,6 +44,11 @@ static const char *default_compressor = "lzo";
 
 /* Module params (documentation at end) */
 static unsigned int num_devices = 1;
+/*
+ * Pages that compress to sizes equals or greater than this are stored
+ * uncompressed in memory.
+ */
+static size_t huge_class_size;
 
 static void zram_free_page(struct zram *zram, size_t index);
 
@@ -786,6 +791,8 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
 		return false;
 	}
 
+	if (!huge_class_size)
+		huge_class_size = zs_huge_class_size(zram->mem_pool);
 	return true;
 }
 
@@ -965,7 +972,7 @@ compress_again:
 		return ret;
 	}
 
-	if (unlikely(comp_len > max_zpage_size)) {
+	if (unlikely(comp_len >= huge_class_size)) {
 		if (zram_wb_enabled(zram) && allow_wb) {
 			zcomp_stream_put(zram->comp);
 			ret = write_to_bdev(zram, bvec, index, bio, &element);
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 1e9bf65c0bfb..008861220723 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -21,22 +21,6 @@
 
 #include "zcomp.h"
 
-/*-- Configurable parameters */
-
-/*
- * Pages that compress to size greater than this are stored
- * uncompressed in memory.
- */
-static const size_t max_zpage_size = PAGE_SIZE / 4 * 3;
-
-/*
- * NOTE: max_zpage_size must be less than or equal to:
- *   ZS_MAX_ALLOC_SIZE. Otherwise, zs_malloc() would
- * always return failure.
- */
-
-/*-- End of configurable params */
-
 #define SECTORS_PER_PAGE_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define SECTORS_PER_PAGE	(1 << SECTORS_PER_PAGE_SHIFT)
 #define ZRAM_LOGICAL_BLOCK_SHIFT 12
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 37be5a306c8f..be8606457f27 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -435,10 +435,20 @@ static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	return dax_region->align;
+}
+
 static const struct vm_operations_struct dax_vm_ops = {
 	.fault = dev_dax_fault,
 	.huge_fault = dev_dax_huge_fault,
 	.split = dev_dax_split,
+	.pagesize = dev_dax_pagesize,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/input/touchscreen/cyttsp4_core.c b/drivers/input/touchscreen/cyttsp4_core.c
index 727c3232517c..f89497940051 100644
--- a/drivers/input/touchscreen/cyttsp4_core.c
+++ b/drivers/input/touchscreen/cyttsp4_core.c
@@ -868,7 +868,7 @@ static void cyttsp4_get_mt_touches(struct cyttsp4_mt_data *md, int num_cur_tch)
 	struct cyttsp4_touch tch;
 	int sig;
 	int i, j, t = 0;
-	int ids[max(CY_TMA1036_MAX_TCH, CY_TMA4XX_MAX_TCH)];
+	int ids[const_max(CY_TMA1036_MAX_TCH, CY_TMA4XX_MAX_TCH)];
 
 	memset(ids, 0, si->si_ofs.tch_abs[CY_TCH_T].max * sizeof(int));
 	for (i = 0; i < num_cur_tch; i++) {
diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c
index 210715f08cf6..85879cfec52f 100644
--- a/drivers/iommu/exynos-iommu.c
+++ b/drivers/iommu/exynos-iommu.c
@@ -17,6 +17,7 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/interrupt.h>
+#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/of_iommu.h>
diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c
index 1b1b77594897..a7c2a973784f 100644
--- a/drivers/iommu/mtk_iommu_v1.c
+++ b/drivers/iommu/mtk_iommu_v1.c
@@ -25,7 +25,6 @@
 #include <linux/io.h>
 #include <linux/iommu.h>
 #include <linux/iopoll.h>
-#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/of_address.h>
 #include <linux/of_iommu.h>
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 1b4af54a4968..30371274409d 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -35,6 +35,7 @@
 #include <linux/of_net.h>
 #include <linux/of_device.h>
 #include <linux/if_vlan.h>
+#include <linux/kmemleak.h>
 
 #include <linux/pinctrl/consumer.h>
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 2437422625bf..57bb8f049e59 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");
diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
index 015476e3f7e5..f3bff66e85d0 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192c/fw_common.c
@@ -32,7 +32,6 @@
 #include "../rtl8192ce/def.h"
 #include "fw_common.h"
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 
 static void _rtl92c_enable_fw_download(struct ieee80211_hw *hw, bool enable)
 {
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 02c5984ab09b..6bb37c18292a 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -295,7 +295,7 @@ static void __init of_unittest_printf(void)
 		return;
 	}
 
-	num_to_str(phandle_str, sizeof(phandle_str), np->phandle);
+	num_to_str(phandle_str, sizeof(phandle_str), np->phandle, 0);
 
 	of_unittest_printf_one(np, "%pOF",  full_name);
 	of_unittest_printf_one(np, "%pOFf", full_name);
diff --git a/drivers/staging/rtl8188eu/hal/fw.c b/drivers/staging/rtl8188eu/hal/fw.c
index 03d091bad13a..6b67b38a6a9f 100644
--- a/drivers/staging/rtl8188eu/hal/fw.c
+++ b/drivers/staging/rtl8188eu/hal/fw.c
@@ -30,7 +30,7 @@
 #include "rtl8188e_hal.h"
 
 #include <linux/firmware.h>
-#include <linux/kmemleak.h>
+#include <linux/slab.h>
 
 static void _rtl88e_enable_fw_download(struct adapter *adapt, bool enable)
 {
diff --git a/drivers/staging/rtlwifi/pci.c b/drivers/staging/rtlwifi/pci.c
index 70a64a5f564a..d56810eabde7 100644
--- a/drivers/staging/rtlwifi/pci.c
+++ b/drivers/staging/rtlwifi/pci.c
@@ -31,7 +31,6 @@
 #include "efuse.h"
 #include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/kmemleak.h>
 #include <linux/module.h>
 
 MODULE_AUTHOR("lizhaoming	<chaoming_li@realsil.com.cn>");
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 71458f493cf8..21d464a29cf8 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -23,7 +23,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/hrtimer.h>
-#include <linux/kmemleak.h>
 #include <linux/dma-mapping.h>
 #include <xen/xen.h>
 
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 8fb89ddc6cc7..e622f0f10502 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -292,6 +292,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 #ifdef CONFIG_9P_FSCACHE
 			kfree(v9ses->cachetag);
 			v9ses->cachetag = match_strdup(&args[0]);
+			if (!v9ses->cachetag) {
+				ret = -ENOMEM;
+				goto free_and_return;
+			}
 #endif
 			break;
 		case Opt_cache:
@@ -471,6 +475,9 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	return fid;
 
 err_clnt:
+#ifdef CONFIG_9P_FSCACHE
+	kfree(v9ses->cachetag);
+#endif
 	p9_client_destroy(v9ses->clnt);
 err_names:
 	kfree(v9ses->uname);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index bdabb2765d1b..9ee534159cc6 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -579,6 +579,24 @@ static int v9fs_at_to_dotl_flags(int flags)
 }
 
 /**
+ * v9fs_dec_count - helper functon to drop i_nlink.
+ *
+ * If a directory had nlink <= 2 (including . and ..), then we should not drop
+ * the link count, which indicates the underlying exported fs doesn't maintain
+ * nlink accurately. e.g.
+ * - overlayfs sets nlink to 1 for merged dir
+ * - ext4 (with dir_nlink feature enabled) sets nlink to 1 if a dir has more
+ *   than EXT4_LINK_MAX (65000) links.
+ *
+ * @inode: inode whose nlink is being dropped
+ */
+static void v9fs_dec_count(struct inode *inode)
+{
+	if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
+		drop_nlink(inode);
+}
+
+/**
  * v9fs_remove - helper function to remove files and directories
  * @dir: directory inode that is being deleted
  * @dentry:  dentry that is being deleted
@@ -621,9 +639,9 @@ static int v9fs_remove(struct inode *dir, struct dentry *dentry, int flags)
 		 */
 		if (flags & AT_REMOVEDIR) {
 			clear_nlink(inode);
-			drop_nlink(dir);
+			v9fs_dec_count(dir);
 		} else
-			drop_nlink(inode);
+			v9fs_dec_count(inode);
 
 		v9fs_invalidate_inode_attr(inode);
 		v9fs_invalidate_inode_attr(dir);
@@ -1024,12 +1042,12 @@ clunk_newdir:
 			if (S_ISDIR(new_inode->i_mode))
 				clear_nlink(new_inode);
 			else
-				drop_nlink(new_inode);
+				v9fs_dec_count(new_inode);
 		}
 		if (S_ISDIR(old_inode->i_mode)) {
 			if (!new_inode)
 				inc_nlink(new_dir);
-			drop_nlink(old_dir);
+			v9fs_dec_count(old_dir);
 		}
 		v9fs_invalidate_inode_attr(old_inode);
 		v9fs_invalidate_inode_attr(old_dir);
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index af03c2a901eb..48ce50484e80 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -94,7 +94,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 	if (v9ses->cache)
 		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
 
-	sb->s_flags |= SB_ACTIVE | SB_DIRSYNC | SB_NOATIME;
+	sb->s_flags |= SB_ACTIVE | SB_DIRSYNC;
 	if (!v9ses->cache)
 		sb->s_flags |= SB_SYNCHRONOUS;
 
diff --git a/fs/Kconfig b/fs/Kconfig
index 1e050e012eb9..6e272b51ded9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -204,6 +204,9 @@ config HUGETLBFS
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
+config MEMFD_CREATE
+	def_bool TMPFS || HUGETLBFS
+
 config ARCH_HAS_GIGANTIC_PAGE
 	bool
 
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index a0c57c37fa21..be9c3dc048ab 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -19,9 +19,6 @@
  */
 static autofs_wqt_t autofs4_next_wait_queue = 1;
 
-/* These are the signals we allow interrupting a pending mount */
-#define SHUTDOWN_SIGS	(sigmask(SIGKILL) | sigmask(SIGINT) | sigmask(SIGQUIT))
-
 void autofs4_catatonic_mode(struct autofs_sb_info *sbi)
 {
 	struct autofs_wait_queue *wq, *nwq;
@@ -486,29 +483,7 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 	 * wq->name.name is NULL iff the lock is already released
 	 * or the mount has been made catatonic.
 	 */
-	if (wq->name.name) {
-		/* Block all but "shutdown" signals while waiting */
-		unsigned long shutdown_sigs_mask;
-		unsigned long irqflags;
-		sigset_t oldset;
-
-		spin_lock_irqsave(&current->sighand->siglock, irqflags);
-		oldset = current->blocked;
-		shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0];
-		siginitsetinv(&current->blocked, shutdown_sigs_mask);
-		recalc_sigpending();
-		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
-
-		wait_event_interruptible(wq->queue, wq->name.name == NULL);
-
-		spin_lock_irqsave(&current->sighand->siglock, irqflags);
-		current->blocked = oldset;
-		recalc_sigpending();
-		spin_unlock_irqrestore(&current->sighand->siglock, irqflags);
-	} else {
-		pr_debug("skipped sleeping\n");
-	}
-
+	wait_event_killable(wq->queue, wq->name.name == NULL);
 	status = wq->status;
 
 	/*
@@ -574,7 +549,7 @@ int autofs4_wait_release(struct autofs_sb_info *sbi, autofs_wqt_t wait_queue_tok
 	kfree(wq->name.name);
 	wq->name.name = NULL;	/* Do not wait on this queue */
 	wq->status = status;
-	wake_up_interruptible(&wq->queue);
+	wake_up(&wq->queue);
 	if (!--wq->wait_ctr)
 		kfree(wq);
 	mutex_unlock(&sbi->wq_mutex);
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index ce1824f47ba6..c3deb2e35f20 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -330,6 +330,7 @@ beyond_if:
 #ifdef __alpha__
 	regs->gp = ex.a_gpvalue;
 #endif
+	finalize_exec(bprm);
 	start_thread(regs, ex.a_entry, current->mm->start_stack);
 	return 0;
 }
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index bdb201230bae..3edca6cb9a33 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1155,6 +1155,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	ELF_PLAT_INIT(regs, reloc_func_desc);
 #endif
 
+	finalize_exec(bprm);
 	start_thread(regs, elf_entry, bprm->p);
 	retval = 0;
 out:
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 429326b6e2e7..d90993adeffa 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -463,6 +463,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm)
 			    dynaddr);
 #endif
 
+	finalize_exec(bprm);
 	/* everything is now ready... get the userspace context ready to roll */
 	entryaddr = interp_params.entry_addr ?: exec_params.entry_addr;
 	start_thread(regs, entryaddr, current->mm->start_stack);
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 5d6b94475f27..82a48e830018 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -994,6 +994,7 @@ static int load_flat_binary(struct linux_binprm *bprm)
 	FLAT_PLAT_INIT(regs);
 #endif
 
+	finalize_exec(bprm);
 	pr_debug("start_thread(regs=0x%p, entry=0x%lx, start_stack=0x%lx)\n",
 		 regs, start_addr, current->mm->start_stack);
 	start_thread(regs, start_addr, current->mm->start_stack);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 19406e489cb3..b54966679833 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1323,7 +1323,8 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
  * @bdev: struct bdev to adjust.
  *
  * This routine checks to see if the bdev size does not match the disk size
- * and adjusts it if it differs.
+ * and adjusts it if it differs. When shrinking the bdev size, its all caches
+ * are freed.
  */
 void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 {
@@ -1336,7 +1337,8 @@ void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
 		       "%s: detected capacity change from %lld to %lld\n",
 		       disk->disk_name, bdev_size, disk_size);
 		i_size_write(bdev->bd_inode, disk_size);
-		flush_disk(bdev, false);
+		if (bdev_size > disk_size)
+			flush_disk(bdev, false);
 	}
 }
 EXPORT_SYMBOL(check_disk_size_change);
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8871286c1a91..ae6d50760dc1 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -346,7 +346,8 @@ static int check_dir_item(struct btrfs_fs_info *fs_info,
 		 */
 		if (key->type == BTRFS_DIR_ITEM_KEY ||
 		    key->type == BTRFS_XATTR_ITEM_KEY) {
-			char namebuf[max(BTRFS_NAME_LEN, XATTR_NAME_MAX)];
+			char namebuf[const_max(BTRFS_NAME_LEN,
+					       XATTR_NAME_MAX)];
 
 			read_extent_buffer(leaf, namebuf,
 					(unsigned long)(di + 1), name_len);
diff --git a/fs/buffer.c b/fs/buffer.c
index 3b2b415f1fcd..17f13191a552 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1511,7 +1511,7 @@ void block_invalidatepage(struct page *page, unsigned int offset,
 	 * The get_block cached value has been unconditionally invalidated,
 	 * so real IO is not possible anymore.
 	 */
-	if (offset == 0)
+	if (length == PAGE_SIZE)
 		try_to_release_page(page, 0);
 out:
 	return;
diff --git a/fs/dcache.c b/fs/dcache.c
index 593079176123..ad0c715f10b8 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -257,11 +257,25 @@ static void __d_free(struct rcu_head *head)
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
+static void __d_free_external_name(struct rcu_head *head)
+{
+	struct external_name *name = container_of(head, struct external_name,
+						  u.head);
+
+	mod_node_page_state(page_pgdat(virt_to_page(name)),
+			    NR_INDIRECTLY_RECLAIMABLE_BYTES,
+			    -ksize(name));
+
+	kfree(name);
+}
+
 static void __d_free_external(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
-	kfree(external_name(dentry));
-	kmem_cache_free(dentry_cache, dentry); 
+
+	__d_free_external_name(&external_name(dentry)->u.head);
+
+	kmem_cache_free(dentry_cache, dentry);
 }
 
 static inline int dname_external(const struct dentry *dentry)
@@ -278,7 +292,8 @@ void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry
 		spin_unlock(&dentry->d_lock);
 		name->name = p->name;
 	} else {
-		memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
+		memcpy(name->inline_name, dentry->d_iname,
+		       dentry->d_name.len + 1);
 		spin_unlock(&dentry->d_lock);
 		name->name = name->inline_name;
 	}
@@ -291,7 +306,7 @@ void release_dentry_name_snapshot(struct name_snapshot *name)
 		struct external_name *p;
 		p = container_of(name->name, struct external_name, name[0]);
 		if (unlikely(atomic_dec_and_test(&p->u.count)))
-			kfree_rcu(p, u.head);
+			call_rcu(&p->u.head, __d_free_external_name);
 	}
 }
 EXPORT_SYMBOL(release_dentry_name_snapshot);
@@ -1617,6 +1632,7 @@ EXPORT_SYMBOL(d_invalidate);
  
 struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 {
+	struct external_name *ext = NULL;
 	struct dentry *dentry;
 	char *dname;
 	int err;
@@ -1637,14 +1653,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 		dname = dentry->d_iname;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
-		struct external_name *p = kmalloc(size + name->len,
-						  GFP_KERNEL_ACCOUNT);
-		if (!p) {
+
+		ext = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT);
+		if (!ext) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
-		atomic_set(&p->u.count, 1);
-		dname = p->name;
+		atomic_set(&ext->u.count, 1);
+		dname = ext->name;
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -1683,6 +1699,12 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 		}
 	}
 
+	if (unlikely(ext)) {
+		pg_data_t *pgdat = page_pgdat(virt_to_page(ext));
+		mod_node_page_state(pgdat, NR_INDIRECTLY_RECLAIMABLE_BYTES,
+				    ksize(ext));
+	}
+
 	this_cpu_inc(nr_dentry);
 
 	return dentry;
@@ -2770,7 +2792,7 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
 		dentry->d_name.hash_len = target->d_name.hash_len;
 	}
 	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
-		kfree_rcu(old_name, u.head);
+		call_rcu(&old_name->u.head, __d_free_external_name);
 }
 
 /*
diff --git a/fs/direct-io.c b/fs/direct-io.c
index ba12ee659673..874607bb6e02 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1177,9 +1177,9 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	unsigned blkbits = i_blkbits;
 	unsigned blocksize_mask = (1 << blkbits) - 1;
 	ssize_t retval = -EINVAL;
-	size_t count = iov_iter_count(iter);
+	const size_t count = iov_iter_count(iter);
 	loff_t offset = iocb->ki_pos;
-	loff_t end = offset + count;
+	const loff_t end = offset + count;
 	struct dio *dio;
 	struct dio_submit sdio = { 0, };
 	struct buffer_head map_bh = { 0, };
@@ -1200,7 +1200,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	}
 
 	/* watch out for a 0 len io from a tricksy fs */
-	if (iov_iter_rw(iter) == READ && !iov_iter_count(iter))
+	if (iov_iter_rw(iter) == READ && !count)
 		return 0;
 
 	dio = kmem_cache_alloc(dio_cache, GFP_KERNEL);
@@ -1315,8 +1315,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 	dio->should_dirty = (iter->type == ITER_IOVEC);
 	sdio.iter = iter;
-	sdio.final_block_in_request =
-		(offset + iov_iter_count(iter)) >> blkbits;
+	sdio.final_block_in_request = end >> blkbits;
 
 	/*
 	 * In case of non-aligned buffers, we may need 2 more
diff --git a/fs/exec.c b/fs/exec.c
index c4154e94f6e4..8d7f314d55ca 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -257,7 +257,7 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 		 *    to work from.
 		 */
 		limit = _STK_LIM / 4 * 3;
-		limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+		limit = min(limit, bprm->rlim_stack.rlim_cur / 4);
 		if (size > limit)
 			goto fail;
 	}
@@ -411,6 +411,11 @@ static int bprm_mm_init(struct linux_binprm *bprm)
 	if (!mm)
 		goto err;
 
+	/* Save current stack limit for all calculations made during exec. */
+	task_lock(current->group_leader);
+	bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK];
+	task_unlock(current->group_leader);
+
 	err = __bprm_mm_init(bprm);
 	if (err)
 		goto err;
@@ -697,7 +702,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 
 #ifdef CONFIG_STACK_GROWSUP
 	/* Limit stack size */
-	stack_base = rlimit_max(RLIMIT_STACK);
+	stack_base = bprm->rlim_stack.rlim_max;
 	if (stack_base > STACK_SIZE_MAX)
 		stack_base = STACK_SIZE_MAX;
 
@@ -770,7 +775,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	 * Align this down to a page boundary as expand_stack
 	 * will align it up.
 	 */
-	rlim_stack = rlimit(RLIMIT_STACK) & PAGE_MASK;
+	rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK;
 #ifdef CONFIG_STACK_GROWSUP
 	if (stack_size + stack_expand > rlim_stack)
 		stack_base = vma->vm_start + rlim_stack;
@@ -1333,6 +1338,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	if (bprm->secureexec) {
 		/* Make sure parent cannot signal privileged process. */
 		current->pdeath_signal = 0;
+		current->signal->pdeath_signal_proc = 0;
 
 		/*
 		 * For secureexec, reset the stack limit to sane default to
@@ -1341,11 +1347,11 @@ void setup_new_exec(struct linux_binprm * bprm)
 		 * RLIMIT_STACK, but after the point of no return to avoid
 		 * needing to clean up the change on failure.
 		 */
-		if (current->signal->rlim[RLIMIT_STACK].rlim_cur > _STK_LIM)
-			current->signal->rlim[RLIMIT_STACK].rlim_cur = _STK_LIM;
+		if (bprm->rlim_stack.rlim_cur > _STK_LIM)
+			bprm->rlim_stack.rlim_cur = _STK_LIM;
 	}
 
-	arch_pick_mmap_layout(current->mm);
+	arch_pick_mmap_layout(current->mm, &bprm->rlim_stack);
 
 	current->sas_ss_sp = current->sas_ss_size = 0;
 
@@ -1378,6 +1384,16 @@ void setup_new_exec(struct linux_binprm * bprm)
 }
 EXPORT_SYMBOL(setup_new_exec);
 
+/* Runs immediately before start_thread() takes over. */
+void finalize_exec(struct linux_binprm *bprm)
+{
+	/* Store any stack rlimit changes before starting thread. */
+	task_lock(current->group_leader);
+	current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack;
+	task_unlock(current->group_leader);
+}
+EXPORT_SYMBOL(finalize_exec);
+
 /*
  * Prepare credentials and lock ->cred_guard_mutex.
  * install_exec_creds() commits the new creds and drops the lock.
diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 3c6a9c156b7a..cfa862ea19d2 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -146,68 +146,82 @@ int  _ore_get_io_state(struct ore_layout *layout,
 			struct ore_io_state **pios)
 {
 	struct ore_io_state *ios;
-	struct page **pages;
-	struct osd_sg_entry *sgilist;
+	size_t size_ios, size_extra, size_total;
+	void *ios_extra;
+
+	/*
+	 * The desired layout looks like this, with the extra_allocation
+	 * items pointed at from fields within ios or per_dev:
+
 	struct __alloc_all_io_state {
 		struct ore_io_state ios;
 		struct ore_per_dev_state per_dev[numdevs];
 		union {
 			struct osd_sg_entry sglist[sgs_per_dev * numdevs];
 			struct page *pages[num_par_pages];
-		};
-	} *_aios;
-
-	if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
-		_aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
-		if (unlikely(!_aios)) {
-			ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
-				   sizeof(*_aios));
+		} extra_allocation;
+	} whole_allocation;
+
+	*/
+
+	/* This should never happen, so abort early if it ever does. */
+	if (sgs_per_dev && num_par_pages) {
+		ORE_DBGMSG("Tried to use both pages and sglist\n");
+		*pios = NULL;
+		return -EINVAL;
+	}
+
+	if (numdevs > (INT_MAX - sizeof(*ios)) /
+		       sizeof(struct ore_per_dev_state))
+		return -ENOMEM;
+	size_ios = sizeof(*ios) + sizeof(struct ore_per_dev_state) * numdevs;
+
+	if (sgs_per_dev * numdevs > INT_MAX / sizeof(struct osd_sg_entry))
+		return -ENOMEM;
+	if (num_par_pages > INT_MAX / sizeof(struct page *))
+		return -ENOMEM;
+	size_extra = max(sizeof(struct osd_sg_entry) * (sgs_per_dev * numdevs),
+			 sizeof(struct page *) * num_par_pages);
+
+	size_total = size_ios + size_extra;
+
+	if (likely(size_total <= PAGE_SIZE)) {
+		ios = kzalloc(size_total, GFP_KERNEL);
+		if (unlikely(!ios)) {
+			ORE_DBGMSG("Failed kzalloc bytes=%zd\n", size_total);
 			*pios = NULL;
 			return -ENOMEM;
 		}
-		pages = num_par_pages ? _aios->pages : NULL;
-		sgilist = sgs_per_dev ? _aios->sglist : NULL;
-		ios = &_aios->ios;
+		ios_extra = (char *)ios + size_ios;
 	} else {
-		struct __alloc_small_io_state {
-			struct ore_io_state ios;
-			struct ore_per_dev_state per_dev[numdevs];
-		} *_aio_small;
-		union __extra_part {
-			struct osd_sg_entry sglist[sgs_per_dev * numdevs];
-			struct page *pages[num_par_pages];
-		} *extra_part;
-
-		_aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
-		if (unlikely(!_aio_small)) {
+		ios = kzalloc(size_ios, GFP_KERNEL);
+		if (unlikely(!ios)) {
 			ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
-				   sizeof(*_aio_small));
+				   size_ios);
 			*pios = NULL;
 			return -ENOMEM;
 		}
-		extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
-		if (unlikely(!extra_part)) {
+		ios_extra = kzalloc(size_extra, GFP_KERNEL);
+		if (unlikely(!ios_extra)) {
 			ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
-				   sizeof(*extra_part));
-			kfree(_aio_small);
+				   size_extra);
+			kfree(ios);
 			*pios = NULL;
 			return -ENOMEM;
 		}
 
-		pages = num_par_pages ? extra_part->pages : NULL;
-		sgilist = sgs_per_dev ? extra_part->sglist : NULL;
 		/* In this case the per_dev[0].sgilist holds the pointer to
 		 * be freed
 		 */
-		ios = &_aio_small->ios;
 		ios->extra_part_alloc = true;
 	}
 
-	if (pages) {
-		ios->parity_pages = pages;
+	if (num_par_pages) {
+		ios->parity_pages = ios_extra;
 		ios->max_par_pages = num_par_pages;
 	}
-	if (sgilist) {
+	if (sgs_per_dev) {
+		struct osd_sg_entry *sgilist = ios_extra;
 		unsigned d;
 
 		for (d = 0; d < numdevs; ++d) {
diff --git a/fs/exofs/ore_raid.c b/fs/exofs/ore_raid.c
index 27cbdb697649..659129d5e9f7 100644
--- a/fs/exofs/ore_raid.c
+++ b/fs/exofs/ore_raid.c
@@ -71,6 +71,11 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
 {
 	struct __stripe_pages_2d *sp2d;
 	unsigned data_devs = group_width - parity;
+
+	/*
+	 * Desired allocation layout is, though when larger than PAGE_SIZE,
+	 * each struct __alloc_1p_arrays is separately allocated:
+
 	struct _alloc_all_bytes {
 		struct __alloc_stripe_pages_2d {
 			struct __stripe_pages_2d sp2d;
@@ -82,55 +87,85 @@ static int _sp2d_alloc(unsigned pages_in_unit, unsigned group_width,
 			char page_is_read[data_devs];
 		} __a1pa[pages_in_unit];
 	} *_aab;
+
 	struct __alloc_1p_arrays *__a1pa;
 	struct __alloc_1p_arrays *__a1pa_end;
-	const unsigned sizeof__a1pa = sizeof(_aab->__a1pa[0]);
+
+	*/
+
+	char *__a1pa;
+	char *__a1pa_end;
+
+	const size_t sizeof_stripe_pages_2d =
+		sizeof(struct __stripe_pages_2d) +
+		sizeof(struct __1_page_stripe) * pages_in_unit;
+	const size_t sizeof__a1pa =
+		ALIGN(sizeof(struct page *) * (2 * group_width) + data_devs,
+		      sizeof(void *));
+	const size_t sizeof__a1pa_arrays = sizeof__a1pa * pages_in_unit;
+	const size_t alloc_total = sizeof_stripe_pages_2d +
+				   sizeof__a1pa_arrays;
+
 	unsigned num_a1pa, alloc_size, i;
 
 	/* FIXME: check these numbers in ore_verify_layout */
-	BUG_ON(sizeof(_aab->__asp2d) > PAGE_SIZE);
+	BUG_ON(sizeof_stripe_pages_2d > PAGE_SIZE);
 	BUG_ON(sizeof__a1pa > PAGE_SIZE);
 
-	if (sizeof(*_aab) > PAGE_SIZE) {
-		num_a1pa = (PAGE_SIZE - sizeof(_aab->__asp2d)) / sizeof__a1pa;
-		alloc_size = sizeof(_aab->__asp2d) + sizeof__a1pa * num_a1pa;
+	/*
+	 * If alloc_total would be larger than PAGE_SIZE, only allocate
+	 * as many a1pa items as would fill the rest of the page, instead
+	 * of the full pages_in_unit count.
+	 */
+	if (alloc_total > PAGE_SIZE) {
+		num_a1pa = (PAGE_SIZE - sizeof_stripe_pages_2d) / sizeof__a1pa;
+		alloc_size = sizeof_stripe_pages_2d + sizeof__a1pa * num_a1pa;
 	} else {
 		num_a1pa = pages_in_unit;
-		alloc_size = sizeof(*_aab);
+		alloc_size = alloc_total;
 	}
 
-	_aab = kzalloc(alloc_size, GFP_KERNEL);
-	if (unlikely(!_aab)) {
+	*psp2d = sp2d = kzalloc(alloc_size, GFP_KERNEL);
+	if (unlikely(!sp2d)) {
 		ORE_DBGMSG("!! Failed to alloc sp2d size=%d\n", alloc_size);
 		return -ENOMEM;
 	}
+	/* From here Just call _sp2d_free */
 
-	sp2d = &_aab->__asp2d.sp2d;
-	*psp2d = sp2d; /* From here Just call _sp2d_free */
-
-	__a1pa = _aab->__a1pa;
-	__a1pa_end = __a1pa + num_a1pa;
+	/* Find start of a1pa area. */
+	__a1pa = (char *)sp2d + sizeof_stripe_pages_2d;
+	/* Find end of the _allocated_ a1pa area. */
+	__a1pa_end = __a1pa + alloc_size;
 
+	/* Allocate additionally needed a1pa items in PAGE_SIZE chunks. */
 	for (i = 0; i < pages_in_unit; ++i) {
 		if (unlikely(__a1pa >= __a1pa_end)) {
 			num_a1pa = min_t(unsigned, PAGE_SIZE / sizeof__a1pa,
 							pages_in_unit - i);
+			alloc_size = sizeof__a1pa * num_a1pa;
 
-			__a1pa = kcalloc(num_a1pa, sizeof__a1pa, GFP_KERNEL);
+			__a1pa = kzalloc(alloc_size, GFP_KERNEL);
 			if (unlikely(!__a1pa)) {
 				ORE_DBGMSG("!! Failed to _alloc_1p_arrays=%d\n",
 					   num_a1pa);
 				return -ENOMEM;
 			}
-			__a1pa_end = __a1pa + num_a1pa;
+			__a1pa_end = __a1pa + alloc_size;
 			/* First *pages is marked for kfree of the buffer */
 			sp2d->_1p_stripes[i].alloc = true;
 		}
 
-		sp2d->_1p_stripes[i].pages = __a1pa->pages;
-		sp2d->_1p_stripes[i].scribble = __a1pa->scribble ;
-		sp2d->_1p_stripes[i].page_is_read = __a1pa->page_is_read;
-		++__a1pa;
+		/*
+		 * Attach all _lp_stripes pointers to the allocation for
+		 * it which was either part of the original PAGE_SIZE
+		 * allocation or the subsequent allocation in this loop.
+		 */
+		sp2d->_1p_stripes[i].pages = (void *)__a1pa;
+		sp2d->_1p_stripes[i].scribble =
+			sp2d->_1p_stripes[i].pages + group_width;
+		sp2d->_1p_stripes[i].page_is_read =
+			(char *)(sp2d->_1p_stripes[i].scribble + group_width);
+		__a1pa += sizeof__a1pa;
 	}
 
 	sp2d->parity = parity;
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 179cd5c2f52a..f3c29e9326f1 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -549,27 +549,26 @@ static int exofs_devs_2_odi(struct exofs_dt_device_info *dt_dev,
 static int __alloc_dev_table(struct exofs_sb_info *sbi, unsigned numdevs,
 		      struct exofs_dev **peds)
 {
-	struct __alloc_ore_devs_and_exofs_devs {
-		/* Twice bigger table: See exofs_init_comps() and comment at
-		 * exofs_read_lookup_dev_table()
-		 */
-		struct ore_dev *oreds[numdevs * 2 - 1];
-		struct exofs_dev eds[numdevs];
-	} *aoded;
+	/* Twice bigger table: See exofs_init_comps() and comment at
+	 * exofs_read_lookup_dev_table()
+	 */
+	size_t numores = numdevs * 2 - 1;
 	struct exofs_dev *eds;
 	unsigned i;
 
-	aoded = kzalloc(sizeof(*aoded), GFP_KERNEL);
-	if (unlikely(!aoded)) {
+	sbi->oc.ods = kzalloc(numores * sizeof(struct ore_dev *) +
+			      numdevs * sizeof(struct exofs_dev), GFP_KERNEL);
+	if (unlikely(!sbi->oc.ods)) {
 		EXOFS_ERR("ERROR: failed allocating Device array[%d]\n",
 			  numdevs);
 		return -ENOMEM;
 	}
 
-	sbi->oc.ods = aoded->oreds;
-	*peds = eds = aoded->eds;
+	/* Start of allocated struct exofs_dev entries */
+	*peds = eds = (void *)sbi->oc.ods[numores];
+	/* Initialize pointers into struct exofs_dev */
 	for (i = 0; i < numdevs; ++i)
-		aoded->oreds[i] = &eds[i].ored;
+		sbi->oc.ods[i] = &eds[i].ored;
 	return 0;
 }
 
diff --git a/fs/fcntl.c b/fs/fcntl.c
index d737ff082472..f93deb1fa16a 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -23,7 +23,7 @@
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
-#include <linux/shmem_fs.h>
+#include <linux/memfd.h>
 #include <linux/compat.h>
 
 #include <linux/poll.h>
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 9a876bb07cac..0f157bbd3e0f 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7119,7 +7119,7 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
 			goto out_commit;
 		did_quota = 1;
 
-		data_ac->ac_resv = &OCFS2_I(inode)->ip_la_data_resv;
+		data_ac->ac_resv = &oi->ip_la_data_resv;
 
 		ret = ocfs2_claim_clusters(handle, data_ac, 1, &bit_off,
 					   &num);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index e8e205bf2e41..302cd7caa4a7 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -346,7 +346,7 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	unlock = 0;
 
 out_alloc:
-	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+	up_read(&oi->ip_alloc_sem);
 out_inode_unlock:
 	ocfs2_inode_unlock(inode, 0);
 out:
@@ -2213,7 +2213,7 @@ static int ocfs2_dio_wr_get_block(struct inode *inode, sector_t iblock,
 	down_write(&oi->ip_alloc_sem);
 
 	if (first_get_block) {
-		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		if (ocfs2_sparse_alloc(osb))
 			ret = ocfs2_zero_tail(inode, di_bh, pos);
 		else
 			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 8614ff069d99..3494a62ed749 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -78,7 +78,7 @@ static inline void ocfs2_iocb_set_rw_locked(struct kiocb *iocb, int level)
 /*
  * Using a named enum representing lock types in terms of #N bit stored in
  * iocb->private, which is going to be used for communication between
- * ocfs2_dio_end_io() and ocfs2_file_aio_write/read().
+ * ocfs2_dio_end_io() and ocfs2_file_write/read_iter().
  */
 enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index 977763d4c27d..b048d4fa3959 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -3072,7 +3072,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 			 * We need to return the correct block within the
 			 * cluster which should hold our entry.
 			 */
-			off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb),
+			off = ocfs2_dx_dir_hash_idx(osb,
 						    &lookup->dl_hinfo);
 			get_bh(dx_leaves[off]);
 			lookup->dl_dx_leaf_bh = dx_leaves[off];
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index fd6bbbbd7d78..39831fc2fd52 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -224,14 +224,12 @@ void dlm_do_local_ast(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 		      struct dlm_lock *lock)
 {
 	dlm_astlockfunc_t *fn;
-	struct dlm_lockstatus *lksb;
 
 	mlog(0, "%s: res %.*s, lock %u:%llu, Local AST\n", dlm->name,
 	     res->lockname.len, res->lockname.name,
 	     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 	     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)));
 
-	lksb = lock->lksb;
 	fn = lock->ast;
 	BUG_ON(lock->ml.node != dlm->node_num);
 
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index e9f3705c4c9f..d06e27ec4be4 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -140,6 +140,7 @@ struct dlm_ctxt
 	u8 node_num;
 	u32 key;
 	u8  joining_node;
+	u8 migrate_done; /* set to 1 means node has migrated all lock resources */
 	wait_queue_head_t dlm_join_events;
 	unsigned long live_nodes_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long domain_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
@@ -960,13 +961,10 @@ static inline int dlm_send_proxy_ast(struct dlm_ctxt *dlm,
 void dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 void __dlm_print_one_lock_resource(struct dlm_lock_resource *res);
 
-u8 dlm_nm_this_node(struct dlm_ctxt *dlm);
 void dlm_kick_thread(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 
 
-int dlm_nm_init(struct dlm_ctxt *dlm);
-int dlm_heartbeat_init(struct dlm_ctxt *dlm);
 void dlm_hb_node_down_cb(struct o2nm_node *node, int idx, void *data);
 void dlm_hb_node_up_cb(struct o2nm_node *node, int idx, void *data);
 
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index e1fea149f50b..425081be6161 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -461,6 +461,19 @@ redo_bucket:
 		cond_resched_lock(&dlm->spinlock);
 		num += n;
 	}
+
+	if (!num) {
+		if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) {
+			mlog(0, "%s: perhaps there are more lock resources "
+			     "need to be migrated after dlm recovery\n", dlm->name);
+			ret = -EAGAIN;
+		} else {
+			mlog(0, "%s: we won't do dlm recovery after migrating "
+			     "all lock resources\n", dlm->name);
+			dlm->migrate_done = 1;
+		}
+	}
+
 	spin_unlock(&dlm->spinlock);
 	wake_up(&dlm->dlm_thread_wq);
 
@@ -675,20 +688,6 @@ static void dlm_leave_domain(struct dlm_ctxt *dlm)
 	spin_unlock(&dlm->spinlock);
 }
 
-int dlm_shutting_down(struct dlm_ctxt *dlm)
-{
-	int ret = 0;
-
-	spin_lock(&dlm_domain_lock);
-
-	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
-		ret = 1;
-
-	spin_unlock(&dlm_domain_lock);
-
-	return ret;
-}
-
 void dlm_unregister_domain(struct dlm_ctxt *dlm)
 {
 	int leave = 0;
@@ -2052,6 +2051,8 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN;
 	init_waitqueue_head(&dlm->dlm_join_events);
 
+	dlm->migrate_done = 0;
+
 	dlm->reco.new_master = O2NM_INVALID_NODE_NUM;
 	dlm->reco.dead_node = O2NM_INVALID_NODE_NUM;
 
diff --git a/fs/ocfs2/dlm/dlmdomain.h b/fs/ocfs2/dlm/dlmdomain.h
index fd6122a38dbd..8a9281411c18 100644
--- a/fs/ocfs2/dlm/dlmdomain.h
+++ b/fs/ocfs2/dlm/dlmdomain.h
@@ -28,7 +28,30 @@
 extern spinlock_t dlm_domain_lock;
 extern struct list_head dlm_domains;
 
-int dlm_shutting_down(struct dlm_ctxt *dlm);
+static inline int dlm_joined(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_JOINED)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
+static inline int dlm_shutting_down(struct dlm_ctxt *dlm)
+{
+	int ret = 0;
+
+	spin_lock(&dlm_domain_lock);
+	if (dlm->dlm_state == DLM_CTXT_IN_SHUTDOWN)
+		ret = 1;
+	spin_unlock(&dlm_domain_lock);
+
+	return ret;
+}
+
 void dlm_fire_domain_eviction_callbacks(struct dlm_ctxt *dlm,
 					int node_num);
 
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 66c2a491f68d..74962315794e 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -77,8 +77,7 @@ int dlm_init_lock_cache(void)
 
 void dlm_destroy_lock_cache(void)
 {
-	if (dlm_lock_cache)
-		kmem_cache_destroy(dlm_lock_cache);
+	kmem_cache_destroy(dlm_lock_cache);
 }
 
 /* Tell us whether we can grant a new lock request.
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a7df226f9449..aaca0949fe53 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -414,8 +414,7 @@ int dlm_init_mle_cache(void)
 
 void dlm_destroy_mle_cache(void)
 {
-	if (dlm_mle_cache)
-		kmem_cache_destroy(dlm_mle_cache);
+	kmem_cache_destroy(dlm_mle_cache);
 }
 
 static void dlm_mle_release(struct kref *kref)
@@ -472,15 +471,11 @@ bail:
 
 void dlm_destroy_master_caches(void)
 {
-	if (dlm_lockname_cache) {
-		kmem_cache_destroy(dlm_lockname_cache);
-		dlm_lockname_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockname_cache);
+	dlm_lockname_cache = NULL;
 
-	if (dlm_lockres_cache) {
-		kmem_cache_destroy(dlm_lockres_cache);
-		dlm_lockres_cache = NULL;
-	}
+	kmem_cache_destroy(dlm_lockres_cache);
+	dlm_lockres_cache = NULL;
 }
 
 static void dlm_lockres_release(struct kref *kref)
@@ -2495,13 +2490,13 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 }
 
 /*
- * A migrateable resource is one that is :
+ * A migratable resource is one that is :
  * 1. locally mastered, and,
  * 2. zero local locks, and,
  * 3. one or more non-local locks, or, one or more references
  * Returns 1 if yes, 0 if not.
  */
-static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
+static int dlm_is_lockres_migratable(struct dlm_ctxt *dlm,
 				      struct dlm_lock_resource *res)
 {
 	enum dlm_lockres_list idx;
@@ -2532,7 +2527,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 				continue;
 			}
 			cookie = be64_to_cpu(lock->ml.cookie);
-			mlog(0, "%s: Not migrateable res %.*s, lock %u:%llu on "
+			mlog(0, "%s: Not migratable res %.*s, lock %u:%llu on "
 			     "%s list\n", dlm->name, res->lockname.len,
 			     res->lockname.name,
 			     dlm_get_lock_cookie_node(cookie),
@@ -2548,7 +2543,7 @@ static int dlm_is_lockres_migrateable(struct dlm_ctxt *dlm,
 			return 0;
 	}
 
-	mlog(0, "%s: res %.*s, Migrateable\n", dlm->name, res->lockname.len,
+	mlog(0, "%s: res %.*s, Migratable\n", dlm->name, res->lockname.len,
 	     res->lockname.name);
 
 	return 1;
@@ -2792,7 +2787,7 @@ int dlm_empty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	assert_spin_locked(&dlm->spinlock);
 
 	spin_lock(&res->spinlock);
-	if (dlm_is_lockres_migrateable(dlm, res))
+	if (dlm_is_lockres_migratable(dlm, res))
 		target = dlm_pick_migration_target(dlm, res);
 	spin_unlock(&res->spinlock);
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ec8f75813beb..b454eb371b77 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -62,7 +62,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
 static int dlm_request_all_locks(struct dlm_ctxt *dlm,
 				 u8 request_from, u8 dead_node);
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node);
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm);
 
 static inline int dlm_num_locks_in_lockres(struct dlm_lock_resource *res);
 static void dlm_init_migratable_lockres(struct dlm_migratable_lockres *mres,
@@ -423,12 +423,11 @@ void dlm_wait_for_recovery(struct dlm_ctxt *dlm)
 
 static void dlm_begin_recovery(struct dlm_ctxt *dlm)
 {
-	spin_lock(&dlm->spinlock);
+	assert_spin_locked(&dlm->spinlock);
 	BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE);
 	printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n",
 	       dlm->name, dlm->reco.dead_node);
 	dlm->reco.state |= DLM_RECO_STATE_ACTIVE;
-	spin_unlock(&dlm->spinlock);
 }
 
 static void dlm_end_recovery(struct dlm_ctxt *dlm)
@@ -456,6 +455,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 
 	spin_lock(&dlm->spinlock);
 
+	if (dlm->migrate_done) {
+		mlog(0, "%s: no need do recovery after migrating all "
+		     "lock resources\n", dlm->name);
+		spin_unlock(&dlm->spinlock);
+		return 0;
+	}
+
 	/* check to see if the new master has died */
 	if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM &&
 	    test_bit(dlm->reco.new_master, dlm->recovery_map)) {
@@ -490,12 +496,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	mlog(0, "%s(%d):recovery thread found node %u in the recovery map!\n",
 	     dlm->name, task_pid_nr(dlm->dlm_reco_thread_task),
 	     dlm->reco.dead_node);
-	spin_unlock(&dlm->spinlock);
 
 	/* take write barrier */
 	/* (stops the list reshuffling thread, proxy ast handling) */
 	dlm_begin_recovery(dlm);
 
+	spin_unlock(&dlm->spinlock);
+
 	if (dlm->reco.new_master == dlm->node_num)
 		goto master_here;
 
@@ -739,7 +746,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 	}
 
 	if (destroy)
-		dlm_destroy_recovery_area(dlm, dead_node);
+		dlm_destroy_recovery_area(dlm);
 
 	return status;
 }
@@ -764,7 +771,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 
 		ndata = kzalloc(sizeof(*ndata), GFP_NOFS);
 		if (!ndata) {
-			dlm_destroy_recovery_area(dlm, dead_node);
+			dlm_destroy_recovery_area(dlm);
 			return -ENOMEM;
 		}
 		ndata->node_num = num;
@@ -778,7 +785,7 @@ static int dlm_init_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
 	return 0;
 }
 
-static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm, u8 dead_node)
+static void dlm_destroy_recovery_area(struct dlm_ctxt *dlm)
 {
 	struct dlm_reco_node_data *ndata, *next;
 	LIST_HEAD(tmplist);
@@ -1378,6 +1385,15 @@ int dlm_mig_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	if (!dlm_grab(dlm))
 		return -EINVAL;
 
+	if (!dlm_joined(dlm)) {
+		mlog(ML_ERROR, "Domain %s not joined! "
+			  "lockres %.*s, master %u\n",
+			  dlm->name, mres->lockname_len,
+			  mres->lockname, mres->master);
+		dlm_put(dlm);
+		return -EINVAL;
+	}
+
 	BUG_ON(!(mres->flags & (DLM_MRES_RECOVERY|DLM_MRES_MIGRATION)));
 
 	real_master = mres->master;
@@ -2331,13 +2347,6 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 	__dlm_dirty_lockres(dlm, res);
 }
 
-/* if this node is the recovery master, and there are no
- * locks for a given lockres owned by this node that are in
- * either PR or EX mode, zero out the lvb before requesting.
- *
- */
-
-
 static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 {
 	struct dlm_lock_resource *res;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index b552d1f8508c..ce33ac354602 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1756,8 +1756,7 @@ int ocfs2_rw_lock(struct inode *inode, int write)
 
 	level = write ? DLM_LOCK_EX : DLM_LOCK_PR;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres, level, 0,
-				    0);
+	status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1796,7 +1795,7 @@ void ocfs2_rw_unlock(struct inode *inode, int write)
 	     write ? "EXMODE" : "PRMODE");
 
 	if (!ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*
@@ -1816,8 +1815,7 @@ int ocfs2_open_lock(struct inode *inode)
 
 	lockres = &OCFS2_I(inode)->ip_open_lockres;
 
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    DLM_LOCK_PR, 0, 0);
+	status = ocfs2_cluster_lock(osb, lockres, DLM_LOCK_PR, 0, 0);
 	if (status < 0)
 		mlog_errno(status);
 
@@ -1854,8 +1852,7 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	 * other nodes and the -EAGAIN will indicate to the caller that
 	 * this inode is still in use.
 	 */
-	status = ocfs2_cluster_lock(OCFS2_SB(inode->i_sb), lockres,
-				    level, DLM_LKF_NOQUEUE, 0);
+	status = ocfs2_cluster_lock(osb, lockres, level, DLM_LKF_NOQUEUE, 0);
 
 out:
 	return status;
@@ -1876,11 +1873,9 @@ void ocfs2_open_unlock(struct inode *inode)
 		goto out;
 
 	if(lockres->l_ro_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_PR);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_PR);
 	if(lockres->l_ex_holders)
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres,
-				     DLM_LOCK_EX);
+		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
 
 out:
 	return;
@@ -2601,9 +2596,9 @@ void ocfs2_inode_unlock(struct inode *inode,
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     ex ? "EXMODE" : "PRMODE");
 
-	if (!ocfs2_is_hard_readonly(OCFS2_SB(inode->i_sb)) &&
+	if (!ocfs2_is_hard_readonly(osb) &&
 	    !ocfs2_mount_local(osb))
-		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
+		ocfs2_cluster_unlock(osb, lockres, level);
 }
 
 /*
@@ -3539,7 +3534,7 @@ static int ocfs2_downconvert_lock(struct ocfs2_super *osb,
 	 * we can recover correctly from node failure. Otherwise, we may get
 	 * invalid LVB in LKB, but without DLM_SBF_VALNOTVALID being set.
 	 */
-	if (!ocfs2_is_o2cb_active() &&
+	if (ocfs2_userspace_stack(osb) &&
 	    lockres->l_ops->flags & LOCK_TYPE_USES_LVB)
 		lvb = 1;
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 5d1784a365a3..6ee94bc23f5b 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -101,7 +101,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
 	trace_ocfs2_file_open(inode, file, file->f_path.dentry,
-			      (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			      (unsigned long long)oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name, mode);
 
@@ -116,7 +116,7 @@ static int ocfs2_file_open(struct inode *inode, struct file *file)
 	/* Check that the inode hasn't been wiped from disk by another
 	 * node. If it hasn't then we're safe as long as we hold the
 	 * spin lock until our increment of open count. */
-	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED) {
+	if (oi->ip_flags & OCFS2_INODE_DELETED) {
 		spin_unlock(&oi->ip_lock);
 
 		status = -ENOENT;
@@ -190,7 +190,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
 	bool needs_barrier = false;
 
 	trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
-			      OCFS2_I(inode)->ip_blkno,
+			      oi->ip_blkno,
 			      file->f_path.dentry->d_name.len,
 			      file->f_path.dentry->d_name.name,
 			      (unsigned long long)datasync);
@@ -296,7 +296,7 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	ocfs2_journal_dirty(handle, bh);
 
 out_commit:
-	ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+	ocfs2_commit_trans(osb, handle);
 out:
 	return ret;
 }
@@ -2257,7 +2257,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
+	trace_ocfs2_file_write_iter(inode, file, file->f_path.dentry,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
 		file->f_path.dentry->d_name.len,
 		file->f_path.dentry->d_name.name,
@@ -2405,7 +2405,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	int direct_io = iocb->ki_flags & IOCB_DIRECT ? 1 : 0;
 	int nowait = iocb->ki_flags & IOCB_NOWAIT ? 1 : 0;
 
-	trace_ocfs2_file_aio_read(inode, filp, filp->f_path.dentry,
+	trace_ocfs2_file_read_iter(inode, filp, filp->f_path.dentry,
 			(unsigned long long)OCFS2_I(inode)->ip_blkno,
 			filp->f_path.dentry->d_name.len,
 			filp->f_path.dentry->d_name.name,
@@ -2448,7 +2448,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	 *
 	 * Take and drop the meta data lock to update inode fields
 	 * like i_size. This allows the checks down below
-	 * generic_file_aio_read() a chance of actually working.
+	 * generic_file_read_iter() a chance of actually working.
 	 */
 	ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
 				     !nowait);
@@ -2460,7 +2460,7 @@ static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	ocfs2_inode_unlock(inode, lock_level);
 
 	ret = generic_file_read_iter(iocb, to);
-	trace_generic_file_aio_read_ret(ret);
+	trace_generic_file_read_iter_ret(ret);
 
 	/* buffered aio wouldn't have proper lock coverage today */
 	BUG_ON(ret == -EIOCBQUEUED && !(iocb->ki_flags & IOCB_DIRECT));
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
index 6b92cb241138..f65f2b2f594d 100644
--- a/fs/ocfs2/filecheck.c
+++ b/fs/ocfs2/filecheck.c
@@ -53,36 +53,6 @@ static const char * const ocfs2_filecheck_errs[] = {
 	"UNSUPPORTED"
 };
 
-static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
-static LIST_HEAD(ocfs2_filecheck_sysfs_list);
-
-struct ocfs2_filecheck {
-	struct list_head fc_head;	/* File check entry list head */
-	spinlock_t fc_lock;
-	unsigned int fc_max;	/* Maximum number of entry in list */
-	unsigned int fc_size;	/* Current entry count in list */
-	unsigned int fc_done;	/* Finished entry count in list */
-};
-
-struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per mounting */
-	struct list_head fs_list;
-	atomic_t fs_count;
-	struct super_block *fs_sb;
-	struct kset *fs_devicekset;
-	struct kset *fs_fcheckkset;
-	struct ocfs2_filecheck *fs_fcheck;
-};
-
-#define OCFS2_FILECHECK_MAXSIZE		100
-#define OCFS2_FILECHECK_MINSIZE		10
-
-/* File check operation type */
-enum {
-	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
-	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
-	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
-};
-
 struct ocfs2_filecheck_entry {
 	struct list_head fe_list;
 	unsigned long fe_ino;
@@ -110,35 +80,84 @@ ocfs2_filecheck_error(int errno)
 	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
-				    struct kobj_attribute *attr,
-				    char *buf);
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
-				     struct kobj_attribute *attr,
-				     const char *buf, size_t count);
-static struct kobj_attribute ocfs2_attr_filecheck_chk =
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf);
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count);
+static struct kobj_attribute ocfs2_filecheck_attr_chk =
 					__ATTR(check, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_fix =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_fix =
 					__ATTR(fix, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
-static struct kobj_attribute ocfs2_attr_filecheck_set =
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct kobj_attribute ocfs2_filecheck_attr_set =
 					__ATTR(set, S_IRUSR | S_IWUSR,
-					ocfs2_filecheck_show,
-					ocfs2_filecheck_store);
+					ocfs2_filecheck_attr_show,
+					ocfs2_filecheck_attr_store);
+static struct attribute *ocfs2_filecheck_attrs[] = {
+	&ocfs2_filecheck_attr_chk.attr,
+	&ocfs2_filecheck_attr_fix.attr,
+	&ocfs2_filecheck_attr_set.attr,
+	NULL
+};
+
+static void ocfs2_filecheck_release(struct kobject *kobj)
+{
+	struct ocfs2_filecheck_sysfs_entry *entry = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
+
+	complete(&entry->fs_kobj_unregister);
+}
+
+static ssize_t
+ocfs2_filecheck_show(struct kobject *kobj, struct attribute *attr, char *buf)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->show)
+		ret = kattr->show(kobj, kattr, buf);
+	kobject_put(kobj);
+	return ret;
+}
+
+static ssize_t
+ocfs2_filecheck_store(struct kobject *kobj, struct attribute *attr,
+			const char *buf, size_t count)
+{
+	ssize_t ret = -EIO;
+	struct kobj_attribute *kattr = container_of(attr,
+					struct kobj_attribute, attr);
+
+	kobject_get(kobj);
+	if (kattr->store)
+		ret = kattr->store(kobj, kattr, buf, count);
+	kobject_put(kobj);
+	return ret;
+}
+
+static const struct sysfs_ops ocfs2_filecheck_ops = {
+	.show = ocfs2_filecheck_show,
+	.store = ocfs2_filecheck_store,
+};
+
+static struct kobj_type ocfs2_ktype_filecheck = {
+	.default_attrs = ocfs2_filecheck_attrs,
+	.sysfs_ops = &ocfs2_filecheck_ops,
+	.release = ocfs2_filecheck_release,
+};
 
 static void
 ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 {
 	struct ocfs2_filecheck_entry *p;
 
-	if (!atomic_dec_and_test(&entry->fs_count)) {
-		wait_var_event(&entry->fs_count,
-			       !atomic_read(&entry->fs_count));
-	}
-
 	spin_lock(&entry->fs_fcheck->fc_lock);
 	while (!list_empty(&entry->fs_fcheck->fc_head)) {
 		p = list_first_entry(&entry->fs_fcheck->fc_head,
@@ -149,151 +168,48 @@ ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
 	}
 	spin_unlock(&entry->fs_fcheck->fc_lock);
 
-	kset_unregister(entry->fs_fcheckkset);
-	kset_unregister(entry->fs_devicekset);
 	kfree(entry->fs_fcheck);
-	kfree(entry);
-}
-
-static void
-ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	entry->fs_fcheck = NULL;
 }
 
-static int ocfs2_filecheck_sysfs_del(const char *devname)
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb)
 {
-	struct ocfs2_filecheck_sysfs_entry *p;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			list_del(&p->fs_list);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			ocfs2_filecheck_sysfs_free(p);
-			return 0;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return 1;
-}
-
-static void
-ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
-{
-	if (atomic_dec_and_test(&entry->fs_count))
-		wake_up_var(&entry->fs_count);
-}
-
-static struct ocfs2_filecheck_sysfs_entry *
-ocfs2_filecheck_sysfs_get(const char *devname)
-{
-	struct ocfs2_filecheck_sysfs_entry *p = NULL;
-
-	spin_lock(&ocfs2_filecheck_sysfs_lock);
-	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
-		if (!strcmp(p->fs_sb->s_id, devname)) {
-			atomic_inc(&p->fs_count);
-			spin_unlock(&ocfs2_filecheck_sysfs_lock);
-			return p;
-		}
-	}
-	spin_unlock(&ocfs2_filecheck_sysfs_lock);
-	return NULL;
-}
-
-int ocfs2_filecheck_create_sysfs(struct super_block *sb)
-{
-	int ret = 0;
-	struct kset *device_kset = NULL;
-	struct kset *fcheck_kset = NULL;
-	struct ocfs2_filecheck *fcheck = NULL;
-	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
-	struct attribute **attrs = NULL;
-	struct attribute_group attrgp;
-
-	if (!ocfs2_kset)
-		return -ENOMEM;
-
-	attrs = kmalloc(sizeof(struct attribute *) * 4, GFP_NOFS);
-	if (!attrs) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		attrs[0] = &ocfs2_attr_filecheck_chk.attr;
-		attrs[1] = &ocfs2_attr_filecheck_fix.attr;
-		attrs[2] = &ocfs2_attr_filecheck_set.attr;
-		attrs[3] = NULL;
-		memset(&attrgp, 0, sizeof(attrgp));
-		attrgp.attrs = attrs;
-	}
+	int ret;
+	struct ocfs2_filecheck *fcheck;
+	struct ocfs2_filecheck_sysfs_entry *entry = &osb->osb_fc_ent;
 
 	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
-	if (!fcheck) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		INIT_LIST_HEAD(&fcheck->fc_head);
-		spin_lock_init(&fcheck->fc_lock);
-		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
-		fcheck->fc_size = 0;
-		fcheck->fc_done = 0;
-	}
-
-	if (strlen(sb->s_id) <= 0) {
-		mlog(ML_ERROR,
-		"Cannot get device basename when create filecheck sysfs\n");
-		ret = -ENODEV;
-		goto error;
-	}
-
-	device_kset = kset_create_and_add(sb->s_id, NULL, &ocfs2_kset->kobj);
-	if (!device_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	fcheck_kset = kset_create_and_add("filecheck", NULL,
-					  &device_kset->kobj);
-	if (!fcheck_kset) {
-		ret = -ENOMEM;
-		goto error;
-	}
-
-	ret = sysfs_create_group(&fcheck_kset->kobj, &attrgp);
-	if (ret)
-		goto error;
+	if (!fcheck)
+		return -ENOMEM;
 
-	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
-	if (!entry) {
-		ret = -ENOMEM;
-		goto error;
-	} else {
-		atomic_set(&entry->fs_count, 1);
-		entry->fs_sb = sb;
-		entry->fs_devicekset = device_kset;
-		entry->fs_fcheckkset = fcheck_kset;
-		entry->fs_fcheck = fcheck;
-		ocfs2_filecheck_sysfs_add(entry);
+	INIT_LIST_HEAD(&fcheck->fc_head);
+	spin_lock_init(&fcheck->fc_lock);
+	fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+	fcheck->fc_size = 0;
+	fcheck->fc_done = 0;
+
+	entry->fs_kobj.kset = osb->osb_dev_kset;
+	init_completion(&entry->fs_kobj_unregister);
+	ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck,
+					NULL, "filecheck");
+	if (ret) {
+		kfree(fcheck);
+		return ret;
 	}
 
-	kfree(attrs);
+	entry->fs_fcheck = fcheck;
 	return 0;
-
-error:
-	kfree(attrs);
-	kfree(entry);
-	kfree(fcheck);
-	kset_unregister(fcheck_kset);
-	kset_unregister(device_kset);
-	return ret;
 }
 
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb)
 {
-	return ocfs2_filecheck_sysfs_del(sb->s_id);
+	if (!osb->osb_fc_ent.fs_fcheck)
+		return;
+
+	kobject_del(&osb->osb_fc_ent.fs_kobj);
+	kobject_put(&osb->osb_fc_ent.fs_kobj);
+	wait_for_completion(&osb->osb_fc_ent.fs_kobj_unregister);
+	ocfs2_filecheck_sysfs_free(&osb->osb_fc_ent);
 }
 
 static int
@@ -310,7 +226,7 @@ ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
 	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
-		mlog(ML_ERROR,
+		mlog(ML_NOTICE,
 		"Cannot set online file check maximum entry number "
 		"to %u due to too many pending entries(%u)\n",
 		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
@@ -387,7 +303,7 @@ ocfs2_filecheck_args_parse(const char *name, const char *buf, size_t count,
 	return 0;
 }
 
-static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_show(struct kobject *kobj,
 				    struct kobj_attribute *attr,
 				    char *buf)
 {
@@ -395,19 +311,12 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
 	unsigned int type;
 	struct ocfs2_filecheck_entry *p;
-	struct ocfs2_filecheck_sysfs_entry *ent;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (ocfs2_filecheck_type_parse(attr->attr.name, &type))
 		return -EINVAL;
 
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->name);
-		return -ENODEV;
-	}
-
 	if (type == OCFS2_FILECHECK_TYPE_SET) {
 		spin_lock(&ent->fs_fcheck->fc_lock);
 		total = snprintf(buf, remain, "%u\n", ent->fs_fcheck->fc_max);
@@ -441,11 +350,26 @@ static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return total;
 }
 
-static int
+static inline int
+ocfs2_filecheck_is_dup_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned long ino)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (!p->fe_done) {
+			if (p->fe_ino == ino)
+				return 1;
+		}
+	}
+
+	return 0;
+}
+
+static inline int
 ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
 {
 	struct ocfs2_filecheck_entry *p;
@@ -484,21 +408,21 @@ static void
 ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			   struct ocfs2_filecheck_entry *entry)
 {
-	entry->fe_done = 1;
 	spin_lock(&ent->fs_fcheck->fc_lock);
+	entry->fe_done = 1;
 	ent->fs_fcheck->fc_done++;
 	spin_unlock(&ent->fs_fcheck->fc_lock);
 }
 
 static unsigned int
-ocfs2_filecheck_handle(struct super_block *sb,
+ocfs2_filecheck_handle(struct ocfs2_super *osb,
 		       unsigned long ino, unsigned int flags)
 {
 	unsigned int ret = OCFS2_FILECHECK_ERR_SUCCESS;
 	struct inode *inode = NULL;
 	int rc;
 
-	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	inode = ocfs2_iget(osb, ino, flags, 0);
 	if (IS_ERR(inode)) {
 		rc = (int)(-(long)inode);
 		if (rc >= OCFS2_FILECHECK_ERR_START &&
@@ -516,11 +440,14 @@ static void
 ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 			     struct ocfs2_filecheck_entry *entry)
 {
+	struct ocfs2_super *osb = container_of(ent, struct ocfs2_super,
+						osb_fc_ent);
+
 	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
 	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
-		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+		entry->fe_status = ocfs2_filecheck_handle(osb,
 				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
 	else
 		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
@@ -528,30 +455,21 @@ ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
 	ocfs2_filecheck_done_entry(ent, entry);
 }
 
-static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+static ssize_t ocfs2_filecheck_attr_store(struct kobject *kobj,
 				     struct kobj_attribute *attr,
 				     const char *buf, size_t count)
 {
+	ssize_t ret = 0;
 	struct ocfs2_filecheck_args args;
 	struct ocfs2_filecheck_entry *entry;
-	struct ocfs2_filecheck_sysfs_entry *ent;
-	ssize_t ret = 0;
+	struct ocfs2_filecheck_sysfs_entry *ent = container_of(kobj,
+				struct ocfs2_filecheck_sysfs_entry, fs_kobj);
 
 	if (count == 0)
 		return count;
 
-	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args)) {
-		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+	if (ocfs2_filecheck_args_parse(attr->attr.name, buf, count, &args))
 		return -EINVAL;
-	}
-
-	ent = ocfs2_filecheck_sysfs_get(kobj->parent->name);
-	if (!ent) {
-		mlog(ML_ERROR,
-		"Cannot get the corresponding entry via device basename %s\n",
-		kobj->parent->name);
-		return -ENODEV;
-	}
 
 	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
 		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
@@ -565,13 +483,16 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 	}
 
 	spin_lock(&ent->fs_fcheck->fc_lock);
-	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
-	    (ent->fs_fcheck->fc_done == 0)) {
-		mlog(ML_ERROR,
+	if (ocfs2_filecheck_is_dup_entry(ent, args.fa_ino)) {
+		ret = -EEXIST;
+		kfree(entry);
+	} else if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		(ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_NOTICE,
 		"Cannot do more file check "
 		"since file check queue(%u) is full now\n",
 		ent->fs_fcheck->fc_max);
-		ret = -EBUSY;
+		ret = -EAGAIN;
 		kfree(entry);
 	} else {
 		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
@@ -596,6 +517,5 @@ static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
 		ocfs2_filecheck_handle_entry(ent, entry);
 
 exit:
-	ocfs2_filecheck_sysfs_put(ent);
 	return (!ret ? count : ret);
 }
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
index e5cd002a2c09..6a22ee79e8d0 100644
--- a/fs/ocfs2/filecheck.h
+++ b/fs/ocfs2/filecheck.h
@@ -43,7 +43,32 @@ enum {
 #define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
 #define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
 
-int ocfs2_filecheck_create_sysfs(struct super_block *sb);
-int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* Finished entry count in list */
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file(inode) */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file(inode) */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set entry list maximum size */
+};
+
+struct ocfs2_filecheck_sysfs_entry {	/* sysfs entry per partition */
+	struct kobject fs_kobj;
+	struct completion fs_kobj_unregister;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+
+int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb);
+void ocfs2_filecheck_remove_sysfs(struct ocfs2_super *osb);
 
 #endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index d51b80edd972..ddc3e9470c87 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1135,7 +1135,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	trace_ocfs2_clear_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink);
 
-	mlog_bug_on_msg(OCFS2_SB(inode->i_sb) == NULL,
+	mlog_bug_on_msg(osb == NULL,
 			"Inode=%lu\n", inode->i_ino);
 
 	dquot_drop(inode);
@@ -1150,7 +1150,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_inode_lockres);
 	ocfs2_mark_lockres_freeing(osb, &oi->ip_open_lockres);
 
-	ocfs2_resv_discard(&OCFS2_SB(inode->i_sb)->osb_la_resmap,
+	ocfs2_resv_discard(&osb->osb_la_resmap,
 			   &oi->ip_la_data_resv);
 	ocfs2_resv_init_once(&oi->ip_la_data_resv);
 
@@ -1160,7 +1160,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * exception here are successfully wiped inodes - their
 	 * metadata can now be considered to be part of the system
 	 * inodes from which it came. */
-	if (!(OCFS2_I(inode)->ip_flags & OCFS2_INODE_DELETED))
+	if (!(oi->ip_flags & OCFS2_INODE_DELETED))
 		ocfs2_checkpoint_inode(inode);
 
 	mlog_bug_on_msg(!list_empty(&oi->ip_io_markers),
@@ -1223,7 +1223,7 @@ static void ocfs2_clear_inode(struct inode *inode)
 	 * the journal is flushed before journal shutdown. Thus it is safe to
 	 * have inodes get cleaned up after journal shutdown.
 	 */
-	jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
+	jbd2_journal_release_jbd_inode(osb->journal->j_journal,
 				       &oi->ip_jinode);
 }
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index e5dcea6cee5f..b63c97f4318e 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1378,15 +1378,23 @@ static int __ocfs2_recovery_thread(void *arg)
 	int rm_quota_used = 0, i;
 	struct ocfs2_quota_recovery *qrec;
 
+	/* Whether the quota supported. */
+	int quota_enabled = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_USRQUOTA)
+		|| OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb,
+			OCFS2_FEATURE_RO_COMPAT_GRPQUOTA);
+
 	status = ocfs2_wait_on_mount(osb);
 	if (status < 0) {
 		goto bail;
 	}
 
-	rm_quota = kzalloc(osb->max_slots * sizeof(int), GFP_NOFS);
-	if (!rm_quota) {
-		status = -ENOMEM;
-		goto bail;
+	if (quota_enabled) {
+		rm_quota = kcalloc(osb->max_slots, sizeof(int), GFP_NOFS);
+		if (!rm_quota) {
+			status = -ENOMEM;
+			goto bail;
+		}
 	}
 restart:
 	status = ocfs2_super_lock(osb, 1);
@@ -1422,9 +1430,14 @@ restart:
 		 * then quota usage would be out of sync until some node takes
 		 * the slot. So we remember which nodes need quota recovery
 		 * and when everything else is done, we recover quotas. */
-		for (i = 0; i < rm_quota_used && rm_quota[i] != slot_num; i++);
-		if (i == rm_quota_used)
-			rm_quota[rm_quota_used++] = slot_num;
+		if (quota_enabled) {
+			for (i = 0; i < rm_quota_used
+					&& rm_quota[i] != slot_num; i++)
+				;
+
+			if (i == rm_quota_used)
+				rm_quota[rm_quota_used++] = slot_num;
+		}
 
 		status = ocfs2_recover_node(osb, node_num, slot_num);
 skip_recovery:
@@ -1452,16 +1465,19 @@ skip_recovery:
 	/* Now it is right time to recover quotas... We have to do this under
 	 * superblock lock so that no one can start using the slot (and crash)
 	 * before we recover it */
-	for (i = 0; i < rm_quota_used; i++) {
-		qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
-		if (IS_ERR(qrec)) {
-			status = PTR_ERR(qrec);
-			mlog_errno(status);
-			continue;
+	if (quota_enabled) {
+		for (i = 0; i < rm_quota_used; i++) {
+			qrec = ocfs2_begin_quota_recovery(osb, rm_quota[i]);
+			if (IS_ERR(qrec)) {
+				status = PTR_ERR(qrec);
+				mlog_errno(status);
+				continue;
+			}
+			ocfs2_queue_recovery_completion(osb->journal,
+					rm_quota[i],
+					NULL, NULL, qrec,
+					ORPHAN_NEED_TRUNCATE);
 		}
-		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec,
-						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
@@ -1483,7 +1499,8 @@ bail:
 
 	mutex_unlock(&osb->recovery_lock);
 
-	kfree(rm_quota);
+	if (quota_enabled)
+		kfree(rm_quota);
 
 	/* no one is callint kthread_stop() for us so the kthread() api
 	 * requires that we call do_exit().  And it isn't exported, but
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index c801eddc4bf3..8dd6f703c819 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -525,7 +525,7 @@ static int __ocfs2_mknod_locked(struct inode *dir,
 	 * these are used by the support functions here and in
 	 * callers. */
 	inode->i_ino = ino_from_blkno(osb->sb, fe_blkno);
-	OCFS2_I(inode)->ip_blkno = fe_blkno;
+	oi->ip_blkno = fe_blkno;
 	spin_lock(&osb->osb_lock);
 	inode->i_generation = osb->s_next_generation++;
 	spin_unlock(&osb->osb_lock);
@@ -1186,8 +1186,8 @@ static int ocfs2_double_lock(struct ocfs2_super *osb,
 	}
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 bail:
 	if (status)
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 6867eef2e06b..4f86ac0027b5 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -50,6 +50,8 @@
 
 #include "reservations.h"
 
+#include "filecheck.h"
+
 /* Caching of metadata buffers */
 
 /* Most user visible OCFS2 inodes will have very few pieces of
@@ -472,6 +474,12 @@ struct ocfs2_super
 	 * workqueue and schedule on our own.
 	 */
 	struct workqueue_struct *ocfs2_wq;
+
+	/* sysfs directory per partition */
+	struct kset *osb_dev_kset;
+
+	/* file check related stuff */
+	struct ocfs2_filecheck_sysfs_entry osb_fc_ent;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index e2a11aaece10..2ee76a90ba8f 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1311,11 +1311,11 @@ DEFINE_OCFS2_FILE_OPS(ocfs2_file_release);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_sync_file);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_write);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_write_iter);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
-DEFINE_OCFS2_FILE_OPS(ocfs2_file_aio_read);
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter);
 
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
 
@@ -1467,7 +1467,7 @@ TRACE_EVENT(ocfs2_prepare_inode_for_write,
 		  __entry->saved_pos, __entry->count, __entry->wait)
 );
 
-DEFINE_OCFS2_INT_EVENT(generic_file_aio_read_ret);
+DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret);
 
 /* End of trace events for fs/ocfs2/file.c. */
 
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index ab156e35ec00..01c6b3894406 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -573,7 +573,7 @@ static int ocfs2_create_refcount_tree(struct inode *inode,
 	BUG_ON(ocfs2_is_refcount_inode(inode));
 
 	trace_ocfs2_create_refcount_tree(
-		(unsigned long long)OCFS2_I(inode)->ip_blkno);
+		(unsigned long long)oi->ip_blkno);
 
 	ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac);
 	if (ret) {
@@ -3359,7 +3359,7 @@ static int ocfs2_replace_cow(struct ocfs2_cow_context *context)
 	unsigned int ext_flags;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) {
+	if (!ocfs2_refcount_tree(osb)) {
 		return ocfs2_error(inode->i_sb, "Inode %lu want to use refcount tree, but the feature bit is not set in the super block\n",
 				   inode->i_ino);
 	}
@@ -3707,7 +3707,7 @@ int ocfs2_add_refcount_flag(struct inode *inode,
 	trace_ocfs2_add_refcount_flag(ref_blocks, credits);
 
 	if (ref_blocks) {
-		ret = ocfs2_reserve_new_metadata_blocks(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_reserve_new_metadata_blocks(osb,
 							ref_blocks, &meta_ac);
 		if (ret) {
 			mlog_errno(ret);
@@ -4766,8 +4766,8 @@ static int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 		*bh2 = *bh1;
 
 	trace_ocfs2_double_lock_end(
-			(unsigned long long)OCFS2_I(inode1)->ip_blkno,
-			(unsigned long long)OCFS2_I(inode2)->ip_blkno);
+			(unsigned long long)oi1->ip_blkno,
+			(unsigned long long)oi2->ip_blkno);
 
 	return 0;
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index d6c350ba25b9..c4b029c43464 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -48,12 +48,6 @@ static char ocfs2_hb_ctl_path[OCFS2_MAX_HB_CTL_PATH] = "/sbin/ocfs2_hb_ctl";
  */
 static struct ocfs2_stack_plugin *active_stack;
 
-inline int ocfs2_is_o2cb_active(void)
-{
-	return !strcmp(active_stack->sp_name, OCFS2_STACK_PLUGIN_O2CB);
-}
-EXPORT_SYMBOL_GPL(ocfs2_is_o2cb_active);
-
 static struct ocfs2_stack_plugin *ocfs2_stack_lookup(const char *name)
 {
 	struct ocfs2_stack_plugin *p;
diff --git a/fs/ocfs2/stackglue.h b/fs/ocfs2/stackglue.h
index e3036e1790e8..f2dce10fae54 100644
--- a/fs/ocfs2/stackglue.h
+++ b/fs/ocfs2/stackglue.h
@@ -298,9 +298,6 @@ void ocfs2_stack_glue_set_max_proto_version(struct ocfs2_protocol_version *max_p
 int ocfs2_stack_glue_register(struct ocfs2_stack_plugin *plugin);
 void ocfs2_stack_glue_unregister(struct ocfs2_stack_plugin *plugin);
 
-/* In ocfs2_downconvert_lock(), we need to know which stack we are using */
-int ocfs2_is_o2cb_active(void);
-
 extern struct kset *ocfs2_kset;
 
 #endif  /* STACKGLUE_H */
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index d8f5f6ce99dc..f7c972fbed6a 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -79,8 +79,6 @@ static u64 ocfs2_group_from_res(struct ocfs2_suballoc_result *res)
 	return ocfs2_which_suballoc_group(res->sr_blkno, res->sr_bit_offset);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg);
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe);
 static inline u16 ocfs2_find_victim_chain(struct ocfs2_chain_list *cl);
 static int ocfs2_block_group_fill(handle_t *handle,
 				  struct inode *alloc_inode,
@@ -387,7 +385,7 @@ static int ocfs2_block_group_fill(handle_t *handle,
 
 	memset(bg, 0, sb->s_blocksize);
 	strcpy(bg->bg_signature, OCFS2_GROUP_DESC_SIGNATURE);
-	bg->bg_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+	bg->bg_generation = cpu_to_le32(osb->fs_generation);
 	bg->bg_size = cpu_to_le16(ocfs2_group_bitmap_size(sb, 1,
 						osb->s_feature_incompat));
 	bg->bg_chain = cpu_to_le16(my_chain);
@@ -1521,7 +1519,7 @@ static int ocfs2_cluster_group_search(struct inode *inode,
 				OCFS2_I(inode)->ip_clusters, max_bits);
 		}
 
-		ret = ocfs2_block_group_find_clear_bits(OCFS2_SB(inode->i_sb),
+		ret = ocfs2_block_group_find_clear_bits(osb,
 							group_bh, bits_wanted,
 							max_bits, res);
 		if (ret)
@@ -2626,53 +2624,6 @@ int ocfs2_release_clusters(handle_t *handle,
 				    _ocfs2_clear_bit);
 }
 
-static inline void ocfs2_debug_bg(struct ocfs2_group_desc *bg)
-{
-	printk("Block Group:\n");
-	printk("bg_signature:       %s\n", bg->bg_signature);
-	printk("bg_size:            %u\n", bg->bg_size);
-	printk("bg_bits:            %u\n", bg->bg_bits);
-	printk("bg_free_bits_count: %u\n", bg->bg_free_bits_count);
-	printk("bg_chain:           %u\n", bg->bg_chain);
-	printk("bg_generation:      %u\n", le32_to_cpu(bg->bg_generation));
-	printk("bg_next_group:      %llu\n",
-	       (unsigned long long)bg->bg_next_group);
-	printk("bg_parent_dinode:   %llu\n",
-	       (unsigned long long)bg->bg_parent_dinode);
-	printk("bg_blkno:           %llu\n",
-	       (unsigned long long)bg->bg_blkno);
-}
-
-static inline void ocfs2_debug_suballoc_inode(struct ocfs2_dinode *fe)
-{
-	int i;
-
-	printk("Suballoc Inode %llu:\n", (unsigned long long)fe->i_blkno);
-	printk("i_signature:                  %s\n", fe->i_signature);
-	printk("i_size:                       %llu\n",
-	       (unsigned long long)fe->i_size);
-	printk("i_clusters:                   %u\n", fe->i_clusters);
-	printk("i_generation:                 %u\n",
-	       le32_to_cpu(fe->i_generation));
-	printk("id1.bitmap1.i_used:           %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_used));
-	printk("id1.bitmap1.i_total:          %u\n",
-	       le32_to_cpu(fe->id1.bitmap1.i_total));
-	printk("id2.i_chain.cl_cpg:           %u\n", fe->id2.i_chain.cl_cpg);
-	printk("id2.i_chain.cl_bpc:           %u\n", fe->id2.i_chain.cl_bpc);
-	printk("id2.i_chain.cl_count:         %u\n", fe->id2.i_chain.cl_count);
-	printk("id2.i_chain.cl_next_free_rec: %u\n",
-	       fe->id2.i_chain.cl_next_free_rec);
-	for(i = 0; i < fe->id2.i_chain.cl_next_free_rec; i++) {
-		printk("fe->id2.i_chain.cl_recs[%d].c_free:  %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_free);
-		printk("fe->id2.i_chain.cl_recs[%d].c_total: %u\n", i,
-		       fe->id2.i_chain.cl_recs[i].c_total);
-		printk("fe->id2.i_chain.cl_recs[%d].c_blkno: %llu\n", i,
-		       (unsigned long long)fe->id2.i_chain.cl_recs[i].c_blkno);
-	}
-}
-
 /*
  * For a given allocation, determine which allocators will need to be
  * accessed, and lock them, reserving the appropriate number of bits.
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index ffa4952d432b..3415e0b09398 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -423,10 +423,10 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait)
 		ocfs2_schedule_truncate_log_flush(osb, 0);
 	}
 
-	if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
+	if (jbd2_journal_start_commit(osb->journal->j_journal,
 				      &target)) {
 		if (wait)
-			jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
+			jbd2_log_wait_commit(osb->journal->j_journal,
 					     target);
 	}
 	return 0;
@@ -1161,6 +1161,23 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	ocfs2_complete_mount_recovery(osb);
 
+	osb->osb_dev_kset = kset_create_and_add(sb->s_id, NULL,
+						&ocfs2_kset->kobj);
+	if (!osb->osb_dev_kset) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create device kset %s.\n", sb->s_id);
+		goto read_super_error;
+	}
+
+	/* Create filecheck sysfs related directories/files at
+	 * /sys/fs/ocfs2/<devname>/filecheck */
+	if (ocfs2_filecheck_create_sysfs(osb)) {
+		status = -ENOMEM;
+		mlog(ML_ERROR, "Unable to create filecheck sysfs directory at "
+			"/sys/fs/ocfs2/%s/filecheck.\n", sb->s_id);
+		goto read_super_error;
+	}
+
 	if (ocfs2_mount_local(osb))
 		snprintf(nodestr, sizeof(nodestr), "local");
 	else
@@ -1199,9 +1216,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	/* Start this when the mount is almost sure of being successful */
 	ocfs2_orphan_scan_start(osb);
 
-	/* Create filecheck sysfile /sys/fs/ocfs2/<devname>/filecheck */
-	ocfs2_filecheck_create_sysfs(sb);
-
 	return status;
 
 read_super_error:
@@ -1653,7 +1667,6 @@ static void ocfs2_put_super(struct super_block *sb)
 
 	ocfs2_sync_blockdev(sb);
 	ocfs2_dismount_volume(sb, 0);
-	ocfs2_filecheck_remove_sysfs(sb);
 }
 
 static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
@@ -1768,12 +1781,9 @@ static int ocfs2_initialize_mem_caches(void)
 					NULL);
 	if (!ocfs2_inode_cachep || !ocfs2_dquot_cachep ||
 	    !ocfs2_qf_chunk_cachep) {
-		if (ocfs2_inode_cachep)
-			kmem_cache_destroy(ocfs2_inode_cachep);
-		if (ocfs2_dquot_cachep)
-			kmem_cache_destroy(ocfs2_dquot_cachep);
-		if (ocfs2_qf_chunk_cachep)
-			kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+		kmem_cache_destroy(ocfs2_inode_cachep);
+		kmem_cache_destroy(ocfs2_dquot_cachep);
+		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 		return -ENOMEM;
 	}
 
@@ -1787,16 +1797,13 @@ static void ocfs2_free_mem_caches(void)
 	 * destroy cache.
 	 */
 	rcu_barrier();
-	if (ocfs2_inode_cachep)
-		kmem_cache_destroy(ocfs2_inode_cachep);
+	kmem_cache_destroy(ocfs2_inode_cachep);
 	ocfs2_inode_cachep = NULL;
 
-	if (ocfs2_dquot_cachep)
-		kmem_cache_destroy(ocfs2_dquot_cachep);
+	kmem_cache_destroy(ocfs2_dquot_cachep);
 	ocfs2_dquot_cachep = NULL;
 
-	if (ocfs2_qf_chunk_cachep)
-		kmem_cache_destroy(ocfs2_qf_chunk_cachep);
+	kmem_cache_destroy(ocfs2_qf_chunk_cachep);
 	ocfs2_qf_chunk_cachep = NULL;
 }
 
@@ -1899,6 +1906,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	osb = OCFS2_SB(sb);
 	BUG_ON(!osb);
 
+	/* Remove file check sysfs related directores/files,
+	 * and wait for the pending file check operations */
+	ocfs2_filecheck_remove_sysfs(osb);
+
+	kset_unregister(osb->osb_dev_kset);
+
 	debugfs_remove(osb->osb_ctxt);
 
 	/* Orphan scan should be stopped as early as possible */
diff --git a/fs/ocfs2/uptodate.c b/fs/ocfs2/uptodate.c
index 82e17b076ce7..78f09c76ab3c 100644
--- a/fs/ocfs2/uptodate.c
+++ b/fs/ocfs2/uptodate.c
@@ -633,6 +633,5 @@ int __init init_ocfs2_uptodate_cache(void)
 
 void exit_ocfs2_uptodate_cache(void)
 {
-	if (ocfs2_uptodate_cachep)
-		kmem_cache_destroy(ocfs2_uptodate_cachep);
+	kmem_cache_destroy(ocfs2_uptodate_cachep);
 }
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index c261c1dfd374..3a24ce3deb01 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -3564,7 +3564,7 @@ int ocfs2_xattr_set(struct inode *inode,
 		.not_found = -ENODATA,
 	};
 
-	if (!ocfs2_supports_xattr(OCFS2_SB(inode->i_sb)))
+	if (!ocfs2_supports_xattr(osb))
 		return -EOPNOTSUPP;
 
 	/*
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 598803576e4c..ae2c807fd719 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -141,25 +141,12 @@ static inline const char *get_task_state(struct task_struct *tsk)
 	return task_state_array[task_state_index(tsk)];
 }
 
-static inline int get_task_umask(struct task_struct *tsk)
-{
-	struct fs_struct *fs;
-	int umask = -ENOENT;
-
-	task_lock(tsk);
-	fs = tsk->fs;
-	if (fs)
-		umask = fs->umask;
-	task_unlock(tsk);
-	return umask;
-}
-
 static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *p)
 {
 	struct user_namespace *user_ns = seq_user_ns(m);
 	struct group_info *group_info;
-	int g, umask;
+	int g, umask = -1;
 	struct task_struct *tracer;
 	const struct cred *cred;
 	pid_t ppid, tpid = 0, tgid, ngid;
@@ -177,17 +164,18 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	ngid = task_numa_group_id(p);
 	cred = get_task_cred(p);
 
-	umask = get_task_umask(p);
-	if (umask >= 0)
-		seq_printf(m, "Umask:\t%#04o\n", umask);
-
 	task_lock(p);
+	if (p->fs)
+		umask = p->fs->umask;
 	if (p->files)
 		max_fds = files_fdtable(p->files)->max_fds;
 	task_unlock(p);
 	rcu_read_unlock();
 
-	seq_printf(m, "State:\t%s", get_task_state(p));
+	if (umask >= 0)
+		seq_printf(m, "Umask:\t%#04o\n", umask);
+	seq_puts(m, "State:\t");
+	seq_puts(m, get_task_state(p));
 
 	seq_put_decimal_ull(m, "\nTgid:\t", tgid);
 	seq_put_decimal_ull(m, "\nNgid:\t", ngid);
@@ -313,8 +301,8 @@ static void render_cap_t(struct seq_file *m, const char *header,
 
 	seq_puts(m, header);
 	CAP_FOR_EACH_U32(__capi) {
-		seq_printf(m, "%08x",
-			   a->cap[CAP_LAST_U32 - __capi]);
+		seq_put_hex_ll(m, NULL,
+			   a->cap[CAP_LAST_U32 - __capi], 8);
 	}
 	seq_putc(m, '\n');
 }
@@ -368,7 +356,8 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 
 static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
 {
-	seq_printf(m, "CoreDumping:\t%d\n", !!mm->core_state);
+	seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state);
+	seq_putc(m, '\n');
 }
 
 int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
@@ -504,7 +493,11 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	/* convert nsec -> ticks */
 	start_time = nsec_to_clock_t(task->real_start_time);
 
-	seq_printf(m, "%d (%s) %c", pid_nr_ns(pid, ns), tcomm, state);
+	seq_put_decimal_ull(m, "", pid_nr_ns(pid, ns));
+	seq_puts(m, " (");
+	seq_puts(m, tcomm);
+	seq_puts(m, ") ");
+	seq_putc(m, state);
 	seq_put_decimal_ll(m, " ", ppid);
 	seq_put_decimal_ll(m, " ", pgid);
 	seq_put_decimal_ll(m, " ", sid);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d53246863cfb..eafa39a3a88c 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -388,14 +388,17 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long wchan;
 	char symname[KSYM_NAME_LEN];
 
-	wchan = get_wchan(task);
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto print0;
 
-	if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
-			&& !lookup_symbol_name(wchan, symname))
-		seq_printf(m, "%s", symname);
-	else
-		seq_putc(m, '0');
+	wchan = get_wchan(task);
+	if (wchan && !lookup_symbol_name(wchan, symname)) {
+		seq_puts(m, symname);
+		return 0;
+	}
 
+print0:
+	seq_putc(m, '0');
 	return 0;
 }
 #endif /* CONFIG_KALLSYMS */
@@ -1910,6 +1913,8 @@ static int dname_to_vma_addr(struct dentry *dentry,
 	unsigned long long sval, eval;
 	unsigned int len;
 
+	if (str[0] == '0' && str[1] != '-')
+		return -EINVAL;
 	len = _parse_integer(str, 16, &sval);
 	if (len & KSTRTOX_OVERFLOW)
 		return -EINVAL;
@@ -1921,6 +1926,8 @@ static int dname_to_vma_addr(struct dentry *dentry,
 		return -EINVAL;
 	str++;
 
+	if (str[0] == '0' && str[1])
+		return -EINVAL;
 	len = _parse_integer(str, 16, &eval);
 	if (len & KSTRTOX_OVERFLOW)
 		return -EINVAL;
@@ -2204,6 +2211,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 		}
 	}
 	up_read(&mm->mmap_sem);
+	mmput(mm);
 
 	for (i = 0; i < nr_files; i++) {
 		char buf[4 * sizeof(long) + 2];	/* max: %lx-%lx\0 */
@@ -2221,7 +2229,6 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 	}
 	if (fa)
 		flex_array_free(fa);
-	mmput(mm);
 
 out_put_task:
 	put_task_struct(task);
diff --git a/fs/proc/cmdline.c b/fs/proc/cmdline.c
index 403cbb12a6e9..8233e7af9389 100644
--- a/fs/proc/cmdline.c
+++ b/fs/proc/cmdline.c
@@ -6,7 +6,8 @@
 
 static int cmdline_proc_show(struct seq_file *m, void *v)
 {
-	seq_printf(m, "%s\n", saved_command_line);
+	seq_puts(m, saved_command_line);
+	seq_putc(m, '\n');
 	return 0;
 }
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 5d709fa8f3a2..2078e70e1595 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -8,12 +8,14 @@
  * Copyright (C) 1997 Theodore Ts'o
  */
 
+#include <linux/cache.h>
 #include <linux/errno.h>
 #include <linux/time.h>
 #include <linux/proc_fs.h>
 #include <linux/stat.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/namei.h>
 #include <linux/slab.h>
 #include <linux/printk.h>
 #include <linux/mount.h>
@@ -28,6 +30,17 @@
 
 static DEFINE_RWLOCK(proc_subdir_lock);
 
+struct kmem_cache *proc_dir_entry_cache __ro_after_init;
+
+void pde_free(struct proc_dir_entry *pde)
+{
+	if (S_ISLNK(pde->mode))
+		kfree(pde->data);
+	if (pde->name != pde->inline_name)
+		kfree(pde->name);
+	kmem_cache_free(proc_dir_entry_cache, pde);
+}
+
 static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int len)
 {
 	if (len < de->namelen)
@@ -40,8 +53,8 @@ static int proc_match(const char *name, struct proc_dir_entry *de, unsigned int
 
 static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
 {
-	return rb_entry_safe(rb_first_cached(&dir->subdir),
-			     struct proc_dir_entry, subdir_node);
+	return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+			     subdir_node);
 }
 
 static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
@@ -54,7 +67,7 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
 					      const char *name,
 					      unsigned int len)
 {
-	struct rb_node *node = dir->subdir.rb_root.rb_node;
+	struct rb_node *node = dir->subdir.rb_node;
 
 	while (node) {
 		struct proc_dir_entry *de = rb_entry(node,
@@ -75,9 +88,8 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
 static bool pde_subdir_insert(struct proc_dir_entry *dir,
 			      struct proc_dir_entry *de)
 {
-	struct rb_root_cached *root = &dir->subdir;
-	struct rb_node **new = &root->rb_root.rb_node, *parent = NULL;
-	bool leftmost = true;
+	struct rb_root *root = &dir->subdir;
+	struct rb_node **new = &root->rb_node, *parent = NULL;
 
 	/* Figure out where to put new node */
 	while (*new) {
@@ -89,16 +101,15 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir,
 		parent = *new;
 		if (result < 0)
 			new = &(*new)->rb_left;
-		else if (result > 0) {
+		else if (result > 0)
 			new = &(*new)->rb_right;
-			leftmost = false;
-		} else
+		else
 			return false;
 	}
 
 	/* Add new node and rebalance tree. */
 	rb_link_node(&de->subdir_node, parent, new);
-	rb_insert_color_cached(&de->subdir_node, root, leftmost);
+	rb_insert_color(&de->subdir_node, root);
 	return true;
 }
 
@@ -207,6 +218,26 @@ void proc_free_inum(unsigned int inum)
 	ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
 }
 
+static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (atomic_read(&PDE(d_inode(dentry))->in_use) < 0)
+		return 0; /* revalidate */
+	return 1;
+}
+
+static int proc_misc_d_delete(const struct dentry *dentry)
+{
+	return atomic_read(&PDE(d_inode(dentry))->in_use) < 0;
+}
+
+static const struct dentry_operations proc_misc_dentry_ops = {
+	.d_revalidate	= proc_misc_d_revalidate,
+	.d_delete	= proc_misc_d_delete,
+};
+
 /*
  * Don't create negative dentries here, return -ENOENT by hand
  * instead.
@@ -224,7 +255,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, &simple_dentry_operations);
+		d_set_d_op(dentry, &proc_misc_dentry_ops);
 		d_add(dentry, inode);
 		return NULL;
 	}
@@ -354,6 +385,14 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 		WARN(1, "name len %u\n", qstr.len);
 		return NULL;
 	}
+	if (qstr.len == 1 && fn[0] == '.') {
+		WARN(1, "name '.'\n");
+		return NULL;
+	}
+	if (qstr.len == 2 && fn[0] == '.' && fn[1] == '.') {
+		WARN(1, "name '..'\n");
+		return NULL;
+	}
 	if (*parent == &proc_root && name_to_int(&qstr) != ~0U) {
 		WARN(1, "create '/proc/%s' by hand\n", qstr.name);
 		return NULL;
@@ -363,16 +402,26 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 		return NULL;
 	}
 
-	ent = kzalloc(sizeof(struct proc_dir_entry) + qstr.len + 1, GFP_KERNEL);
+	ent = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
 	if (!ent)
 		goto out;
 
+	if (qstr.len + 1 <= sizeof(ent->inline_name)) {
+		ent->name = ent->inline_name;
+	} else {
+		ent->name = kmalloc(qstr.len + 1, GFP_KERNEL);
+		if (!ent->name) {
+			pde_free(ent);
+			return NULL;
+		}
+	}
+
 	memcpy(ent->name, fn, qstr.len + 1);
 	ent->namelen = qstr.len;
 	ent->mode = mode;
 	ent->nlink = nlink;
-	ent->subdir = RB_ROOT_CACHED;
-	atomic_set(&ent->count, 1);
+	ent->subdir = RB_ROOT;
+	refcount_set(&ent->refcnt, 1);
 	spin_lock_init(&ent->pde_unload_lock);
 	INIT_LIST_HEAD(&ent->pde_openers);
 	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
@@ -395,12 +444,11 @@ struct proc_dir_entry *proc_symlink(const char *name,
 			strcpy((char*)ent->data,dest);
 			ent->proc_iops = &proc_link_inode_operations;
 			if (proc_register(parent, ent) < 0) {
-				kfree(ent->data);
-				kfree(ent);
+				pde_free(ent);
 				ent = NULL;
 			}
 		} else {
-			kfree(ent);
+			pde_free(ent);
 			ent = NULL;
 		}
 	}
@@ -423,7 +471,7 @@ struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode,
 		ent->proc_iops = &proc_dir_inode_operations;
 		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
-			kfree(ent);
+			pde_free(ent);
 			parent->nlink--;
 			ent = NULL;
 		}
@@ -458,7 +506,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 		ent->proc_iops = NULL;
 		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
-			kfree(ent);
+			pde_free(ent);
 			parent->nlink--;
 			ent = NULL;
 		}
@@ -495,7 +543,7 @@ struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
 		goto out_free;
 	return pde;
 out_free:
-	kfree(pde);
+	pde_free(pde);
 out:
 	return NULL;
 }
@@ -522,19 +570,12 @@ void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid)
 }
 EXPORT_SYMBOL(proc_set_user);
 
-static void free_proc_entry(struct proc_dir_entry *de)
-{
-	proc_free_inum(de->low_ino);
-
-	if (S_ISLNK(de->mode))
-		kfree(de->data);
-	kfree(de);
-}
-
 void pde_put(struct proc_dir_entry *pde)
 {
-	if (atomic_dec_and_test(&pde->count))
-		free_proc_entry(pde);
+	if (refcount_dec_and_test(&pde->refcnt)) {
+		proc_free_inum(pde->low_ino);
+		pde_free(pde);
+	}
 }
 
 /*
@@ -555,7 +596,7 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 
 	de = pde_subdir_find(parent, fn, len);
 	if (de)
-		rb_erase_cached(&de->subdir_node, &parent->subdir);
+		rb_erase(&de->subdir_node, &parent->subdir);
 	write_unlock(&proc_subdir_lock);
 	if (!de) {
 		WARN(1, "name '%s'\n", name);
@@ -592,13 +633,13 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 		write_unlock(&proc_subdir_lock);
 		return -ENOENT;
 	}
-	rb_erase_cached(&root->subdir_node, &parent->subdir);
+	rb_erase(&root->subdir_node, &parent->subdir);
 
 	de = root;
 	while (1) {
 		next = pde_subdir_first(de);
 		if (next) {
-			rb_erase_cached(&next->subdir_node, &de->subdir);
+			rb_erase(&next->subdir_node, &de->subdir);
 			de = next;
 			continue;
 		}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6e8724958116..2cf3b74391ca 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -54,6 +54,7 @@ static void proc_evict_inode(struct inode *inode)
 }
 
 static struct kmem_cache *proc_inode_cachep __ro_after_init;
+static struct kmem_cache *pde_opener_cache __ro_after_init;
 
 static struct inode *proc_alloc_inode(struct super_block *sb)
 {
@@ -92,7 +93,7 @@ static void init_once(void *foo)
 	inode_init_once(&ei->vfs_inode);
 }
 
-void __init proc_init_inodecache(void)
+void __init proc_init_kmemcache(void)
 {
 	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
 					     sizeof(struct proc_inode),
@@ -100,6 +101,13 @@ void __init proc_init_inodecache(void)
 						SLAB_MEM_SPREAD|SLAB_ACCOUNT|
 						SLAB_PANIC),
 					     init_once);
+	pde_opener_cache =
+		kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0,
+				  SLAB_ACCOUNT|SLAB_PANIC, NULL);
+	proc_dir_entry_cache = kmem_cache_create_usercopy(
+		"proc_dir_entry", sizeof(struct proc_dir_entry), 0, SLAB_PANIC,
+		offsetof(struct proc_dir_entry, inline_name),
+		sizeof_field(struct proc_dir_entry, inline_name), NULL);
 }
 
 static int proc_show_options(struct seq_file *seq, struct dentry *root)
@@ -138,7 +146,7 @@ static void unuse_pde(struct proc_dir_entry *pde)
 		complete(pde->pde_unload_completion);
 }
 
-/* pde is locked */
+/* pde is locked on entry, unlocked on exit */
 static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 {
 	/*
@@ -157,9 +165,10 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 		pdeo->c = &c;
 		spin_unlock(&pde->pde_unload_lock);
 		wait_for_completion(&c);
-		spin_lock(&pde->pde_unload_lock);
 	} else {
 		struct file *file;
+		struct completion *c;
+
 		pdeo->closing = true;
 		spin_unlock(&pde->pde_unload_lock);
 		file = pdeo->file;
@@ -167,9 +176,11 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 		spin_lock(&pde->pde_unload_lock);
 		/* After ->release. */
 		list_del(&pdeo->lh);
-		if (unlikely(pdeo->c))
-			complete(pdeo->c);
-		kfree(pdeo);
+		c = pdeo->c;
+		spin_unlock(&pde->pde_unload_lock);
+		if (unlikely(c))
+			complete(c);
+		kmem_cache_free(pde_opener_cache, pdeo);
 	}
 }
 
@@ -188,6 +199,7 @@ void proc_entry_rundown(struct proc_dir_entry *de)
 		struct pde_opener *pdeo;
 		pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
 		close_pdeo(de, pdeo);
+		spin_lock(&de->pde_unload_lock);
 	}
 	spin_unlock(&de->pde_unload_lock);
 }
@@ -338,31 +350,36 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 	 *
 	 * Save every "struct file" with custom ->release hook.
 	 */
-	pdeo = kmalloc(sizeof(struct pde_opener), GFP_KERNEL);
-	if (!pdeo)
-		return -ENOMEM;
-
-	if (!use_pde(pde)) {
-		kfree(pdeo);
+	if (!use_pde(pde))
 		return -ENOENT;
-	}
-	open = pde->proc_fops->open;
+
 	release = pde->proc_fops->release;
+	if (release) {
+		pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
+		if (!pdeo) {
+			rv = -ENOMEM;
+			goto out_unuse;
+		}
+	}
 
+	open = pde->proc_fops->open;
 	if (open)
 		rv = open(inode, file);
 
-	if (rv == 0 && release) {
-		/* To know what to release. */
-		pdeo->file = file;
-		pdeo->closing = false;
-		pdeo->c = NULL;
-		spin_lock(&pde->pde_unload_lock);
-		list_add(&pdeo->lh, &pde->pde_openers);
-		spin_unlock(&pde->pde_unload_lock);
-	} else
-		kfree(pdeo);
+	if (release) {
+		if (rv == 0) {
+			/* To know what to release. */
+			pdeo->file = file;
+			pdeo->closing = false;
+			pdeo->c = NULL;
+			spin_lock(&pde->pde_unload_lock);
+			list_add(&pdeo->lh, &pde->pde_openers);
+			spin_unlock(&pde->pde_unload_lock);
+		} else
+			kmem_cache_free(pde_opener_cache, pdeo);
+	}
 
+out_unuse:
 	unuse_pde(pde);
 	return rv;
 }
@@ -375,7 +392,7 @@ static int proc_reg_release(struct inode *inode, struct file *file)
 	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
 		if (pdeo->file == file) {
 			close_pdeo(pde, pdeo);
-			break;
+			return 0;
 		}
 	}
 	spin_unlock(&pde->pde_unload_lock);
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index d697c8ab0a14..0f1692e63cb6 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -11,6 +11,7 @@
 
 #include <linux/proc_fs.h>
 #include <linux/proc_ns.h>
+#include <linux/refcount.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/binfmts.h>
@@ -36,7 +37,7 @@ struct proc_dir_entry {
 	 * negative -> it's going away RSN
 	 */
 	atomic_t in_use;
-	atomic_t count;		/* use count */
+	refcount_t refcnt;
 	struct list_head pde_openers;	/* who did ->open, but not ->release */
 	/* protects ->pde_openers and all struct pde_opener instances */
 	spinlock_t pde_unload_lock;
@@ -50,13 +51,22 @@ struct proc_dir_entry {
 	kgid_t gid;
 	loff_t size;
 	struct proc_dir_entry *parent;
-	struct rb_root_cached subdir;
+	struct rb_root subdir;
 	struct rb_node subdir_node;
+	char *name;
 	umode_t mode;
 	u8 namelen;
-	char name[];
+#ifdef CONFIG_64BIT
+#define SIZEOF_PDE_INLINE_NAME	(192-139)
+#else
+#define SIZEOF_PDE_INLINE_NAME	(128-87)
+#endif
+	char inline_name[SIZEOF_PDE_INLINE_NAME];
 } __randomize_layout;
 
+extern struct kmem_cache *proc_dir_entry_cache;
+void pde_free(struct proc_dir_entry *pde);
+
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
 	int (*proc_show)(struct seq_file *m,
@@ -159,7 +169,7 @@ int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *
 
 static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
 {
-	atomic_inc(&pde->count);
+	refcount_inc(&pde->refcnt);
 	return pde;
 }
 extern void pde_put(struct proc_dir_entry *);
@@ -177,12 +187,12 @@ struct pde_opener {
 	struct list_head lh;
 	bool closing;
 	struct completion *c;
-};
+} __randomize_layout;
 extern const struct inode_operations proc_link_inode_operations;
 
 extern const struct inode_operations proc_pid_link_inode_operations;
 
-extern void proc_init_inodecache(void);
+void proc_init_kmemcache(void);
 void set_proc_pid_nlink(void);
 extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *);
 extern int proc_fill_super(struct super_block *, void *data, int flags);
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 6bb20f864259..65a72ab57471 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -26,20 +26,7 @@ void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
 
 static void show_val_kb(struct seq_file *m, const char *s, unsigned long num)
 {
-	char v[32];
-	static const char blanks[7] = {' ', ' ', ' ', ' ',' ', ' ', ' '};
-	int len;
-
-	len = num_to_str(v, sizeof(v), num << (PAGE_SHIFT - 10));
-
-	seq_write(m, s, 16);
-
-	if (len > 0) {
-		if (len < 8)
-			seq_write(m, blanks, 8 - len);
-
-		seq_write(m, v, len);
-	}
+	seq_put_decimal_ull_width(m, s, num << (PAGE_SHIFT - 10), 8);
 	seq_write(m, " kB\n", 4);
 }
 
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 68c06ae7888c..1763f370489d 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -192,15 +192,16 @@ static __net_init int proc_net_ns_init(struct net *net)
 	int err;
 
 	err = -ENOMEM;
-	netd = kzalloc(sizeof(*netd) + 4, GFP_KERNEL);
+	netd = kmem_cache_zalloc(proc_dir_entry_cache, GFP_KERNEL);
 	if (!netd)
 		goto out;
 
-	netd->subdir = RB_ROOT_CACHED;
+	netd->subdir = RB_ROOT;
 	netd->data = net;
 	netd->nlink = 2;
 	netd->namelen = 3;
 	netd->parent = &proc_root;
+	netd->name = netd->inline_name;
 	memcpy(netd->name, "net", 4);
 
 	uid = make_kuid(net->user_ns, 0);
@@ -223,7 +224,7 @@ static __net_init int proc_net_ns_init(struct net *net)
 	return 0;
 
 free_net:
-	kfree(netd);
+	pde_free(netd);
 out:
 	return err;
 }
@@ -231,7 +232,7 @@ out:
 static __net_exit void proc_net_ns_exit(struct net *net)
 {
 	remove_proc_entry("stat", net->proc_net);
-	kfree(net->proc_net);
+	pde_free(net->proc_net);
 }
 
 static struct pernet_operations __net_initdata proc_net_ns_ops = {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index c41ab261397d..8989936f2995 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -707,14 +707,14 @@ static bool proc_sys_link_fill_cache(struct file *file,
 				    struct ctl_table *table)
 {
 	bool ret = true;
+
 	head = sysctl_head_grab(head);
+	if (IS_ERR(head))
+		return false;
 
-	if (S_ISLNK(table->mode)) {
-		/* It is not an error if we can not follow the link ignore it */
-		int err = sysctl_follow_link(&head, &table);
-		if (err)
-			goto out;
-	}
+	/* It is not an error if we can not follow the link ignore it */
+	if (sysctl_follow_link(&head, &table))
+		goto out;
 
 	ret = proc_sys_fill_cache(file, ctx, head, table);
 out:
@@ -1086,7 +1086,7 @@ static int sysctl_check_table_array(const char *path, struct ctl_table *table)
 	if ((table->proc_handler == proc_douintvec) ||
 	    (table->proc_handler == proc_douintvec_minmax)) {
 		if (table->maxlen != sizeof(unsigned int))
-			err |= sysctl_err(path, table, "array now allowed");
+			err |= sysctl_err(path, table, "array not allowed");
 	}
 
 	return err;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ede8e64974be..61b7340b357a 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -123,23 +123,13 @@ static struct file_system_type proc_fs_type = {
 
 void __init proc_root_init(void)
 {
-	int err;
-
-	proc_init_inodecache();
+	proc_init_kmemcache();
 	set_proc_pid_nlink();
-	err = register_filesystem(&proc_fs_type);
-	if (err)
-		return;
-
 	proc_self_init();
 	proc_thread_self_init();
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	proc_net_init();
-
-#ifdef CONFIG_SYSVIPC
-	proc_mkdir("sysvipc", NULL);
-#endif
 	proc_mkdir("fs", NULL);
 	proc_mkdir("driver", NULL);
 	proc_create_mount_point("fs/nfsd"); /* somewhere for the nfsd filesystem to be mounted */
@@ -150,6 +140,8 @@ void __init proc_root_init(void)
 	proc_tty_init();
 	proc_mkdir("bus", NULL);
 	proc_sys_init();
+
+	register_filesystem(&proc_fs_type);
 }
 
 static int proc_root_getattr(const struct path *path, struct kstat *stat,
@@ -207,12 +199,13 @@ struct proc_dir_entry proc_root = {
 	.namelen	= 5, 
 	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
 	.nlink		= 2, 
-	.count		= ATOMIC_INIT(1),
+	.refcnt		= REFCOUNT_INIT(1),
 	.proc_iops	= &proc_root_inode_operations, 
 	.proc_fops	= &proc_root_operations,
 	.parent		= &proc_root,
-	.subdir		= RB_ROOT_CACHED,
-	.name		= "/proc",
+	.subdir		= RB_ROOT,
+	.name		= proc_root.inline_name,
+	.inline_name	= "/proc",
 };
 
 int pid_ns_prepare_proc(struct pid_namespace *ns)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ec6d2983a5cb..65ae54659833 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -24,6 +24,8 @@
 #include <asm/tlbflush.h>
 #include "internal.h"
 
+#define SEQ_PUT_DEC(str, val) \
+		seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8)
 void task_mem(struct seq_file *m, struct mm_struct *mm)
 {
 	unsigned long text, lib, swap, anon, file, shmem;
@@ -53,39 +55,28 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	lib = (mm->exec_vm << PAGE_SHIFT) - text;
 
 	swap = get_mm_counter(mm, MM_SWAPENTS);
-	seq_printf(m,
-		"VmPeak:\t%8lu kB\n"
-		"VmSize:\t%8lu kB\n"
-		"VmLck:\t%8lu kB\n"
-		"VmPin:\t%8lu kB\n"
-		"VmHWM:\t%8lu kB\n"
-		"VmRSS:\t%8lu kB\n"
-		"RssAnon:\t%8lu kB\n"
-		"RssFile:\t%8lu kB\n"
-		"RssShmem:\t%8lu kB\n"
-		"VmData:\t%8lu kB\n"
-		"VmStk:\t%8lu kB\n"
-		"VmExe:\t%8lu kB\n"
-		"VmLib:\t%8lu kB\n"
-		"VmPTE:\t%8lu kB\n"
-		"VmSwap:\t%8lu kB\n",
-		hiwater_vm << (PAGE_SHIFT-10),
-		total_vm << (PAGE_SHIFT-10),
-		mm->locked_vm << (PAGE_SHIFT-10),
-		mm->pinned_vm << (PAGE_SHIFT-10),
-		hiwater_rss << (PAGE_SHIFT-10),
-		total_rss << (PAGE_SHIFT-10),
-		anon << (PAGE_SHIFT-10),
-		file << (PAGE_SHIFT-10),
-		shmem << (PAGE_SHIFT-10),
-		mm->data_vm << (PAGE_SHIFT-10),
-		mm->stack_vm << (PAGE_SHIFT-10),
-		text >> 10,
-		lib >> 10,
-		mm_pgtables_bytes(mm) >> 10,
-		swap << (PAGE_SHIFT-10));
+	SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
+	SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
+	SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
+	SEQ_PUT_DEC(" kB\nVmPin:\t", mm->pinned_vm);
+	SEQ_PUT_DEC(" kB\nVmHWM:\t", hiwater_rss);
+	SEQ_PUT_DEC(" kB\nVmRSS:\t", total_rss);
+	SEQ_PUT_DEC(" kB\nRssAnon:\t", anon);
+	SEQ_PUT_DEC(" kB\nRssFile:\t", file);
+	SEQ_PUT_DEC(" kB\nRssShmem:\t", shmem);
+	SEQ_PUT_DEC(" kB\nVmData:\t", mm->data_vm);
+	SEQ_PUT_DEC(" kB\nVmStk:\t", mm->stack_vm);
+	seq_put_decimal_ull_width(m,
+		    " kB\nVmExe:\t", text >> 10, 8);
+	seq_put_decimal_ull_width(m,
+		    " kB\nVmLib:\t", lib >> 10, 8);
+	seq_put_decimal_ull_width(m,
+		    " kB\nVmPTE:\t", mm_pgtables_bytes(mm) >> 10, 8);
+	SEQ_PUT_DEC(" kB\nVmSwap:\t", swap);
+	seq_puts(m, " kB\n");
 	hugetlb_report_usage(m, mm);
 }
+#undef SEQ_PUT_DEC
 
 unsigned long task_vsize(struct mm_struct *mm)
 {
@@ -287,15 +278,18 @@ static void show_vma_header_prefix(struct seq_file *m,
 				   dev_t dev, unsigned long ino)
 {
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
-	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
-		   start,
-		   end,
-		   flags & VM_READ ? 'r' : '-',
-		   flags & VM_WRITE ? 'w' : '-',
-		   flags & VM_EXEC ? 'x' : '-',
-		   flags & VM_MAYSHARE ? 's' : 'p',
-		   pgoff,
-		   MAJOR(dev), MINOR(dev), ino);
+	seq_put_hex_ll(m, NULL, start, 8);
+	seq_put_hex_ll(m, "-", end, 8);
+	seq_putc(m, ' ');
+	seq_putc(m, flags & VM_READ ? 'r' : '-');
+	seq_putc(m, flags & VM_WRITE ? 'w' : '-');
+	seq_putc(m, flags & VM_EXEC ? 'x' : '-');
+	seq_putc(m, flags & VM_MAYSHARE ? 's' : 'p');
+	seq_put_hex_ll(m, " ", pgoff, 8);
+	seq_put_hex_ll(m, " ", MAJOR(dev), 2);
+	seq_put_hex_ll(m, ":", MINOR(dev), 2);
+	seq_put_decimal_ull(m, " ", ino);
+	seq_putc(m, ' ');
 }
 
 static void
@@ -694,8 +688,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
 		if (!mnemonics[i][0])
 			continue;
 		if (vma->vm_flags & (1UL << i)) {
-			seq_printf(m, "%c%c ",
-				   mnemonics[i][0], mnemonics[i][1]);
+			seq_putc(m, mnemonics[i][0]);
+			seq_putc(m, mnemonics[i][1]);
+			seq_putc(m, ' ');
 		}
 	}
 	seq_putc(m, '\n');
@@ -736,6 +731,8 @@ void __weak arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
 {
 }
 
+#define SEQ_PUT_DEC(str, val) \
+		seq_put_decimal_ull_width(m, str, (val) >> 10, 8)
 static int show_smap(struct seq_file *m, void *v, int is_pid)
 {
 	struct proc_maps_private *priv = m->private;
@@ -809,51 +806,34 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		ret = SEQ_SKIP;
 	}
 
-	if (!rollup_mode)
-		seq_printf(m,
-			   "Size:           %8lu kB\n"
-			   "KernelPageSize: %8lu kB\n"
-			   "MMUPageSize:    %8lu kB\n",
-			   (vma->vm_end - vma->vm_start) >> 10,
-			   vma_kernel_pagesize(vma) >> 10,
-			   vma_mmu_pagesize(vma) >> 10);
-
-
-	if (!rollup_mode || last_vma)
-		seq_printf(m,
-			   "Rss:            %8lu kB\n"
-			   "Pss:            %8lu kB\n"
-			   "Shared_Clean:   %8lu kB\n"
-			   "Shared_Dirty:   %8lu kB\n"
-			   "Private_Clean:  %8lu kB\n"
-			   "Private_Dirty:  %8lu kB\n"
-			   "Referenced:     %8lu kB\n"
-			   "Anonymous:      %8lu kB\n"
-			   "LazyFree:       %8lu kB\n"
-			   "AnonHugePages:  %8lu kB\n"
-			   "ShmemPmdMapped: %8lu kB\n"
-			   "Shared_Hugetlb: %8lu kB\n"
-			   "Private_Hugetlb: %7lu kB\n"
-			   "Swap:           %8lu kB\n"
-			   "SwapPss:        %8lu kB\n"
-			   "Locked:         %8lu kB\n",
-			   mss->resident >> 10,
-			   (unsigned long)(mss->pss >> (10 + PSS_SHIFT)),
-			   mss->shared_clean  >> 10,
-			   mss->shared_dirty  >> 10,
-			   mss->private_clean >> 10,
-			   mss->private_dirty >> 10,
-			   mss->referenced >> 10,
-			   mss->anonymous >> 10,
-			   mss->lazyfree >> 10,
-			   mss->anonymous_thp >> 10,
-			   mss->shmem_thp >> 10,
-			   mss->shared_hugetlb >> 10,
-			   mss->private_hugetlb >> 10,
-			   mss->swap >> 10,
-			   (unsigned long)(mss->swap_pss >> (10 + PSS_SHIFT)),
-			   (unsigned long)(mss->pss >> (10 + PSS_SHIFT)));
+	if (!rollup_mode) {
+		SEQ_PUT_DEC("Size:           ", vma->vm_end - vma->vm_start);
+		SEQ_PUT_DEC(" kB\nKernelPageSize: ", vma_kernel_pagesize(vma));
+		SEQ_PUT_DEC(" kB\nMMUPageSize:    ", vma_mmu_pagesize(vma));
+		seq_puts(m, " kB\n");
+	}
 
+	if (!rollup_mode || last_vma) {
+		SEQ_PUT_DEC("Rss:            ", mss->resident);
+		SEQ_PUT_DEC(" kB\nPss:            ", mss->pss >> PSS_SHIFT);
+		SEQ_PUT_DEC(" kB\nShared_Clean:   ", mss->shared_clean);
+		SEQ_PUT_DEC(" kB\nShared_Dirty:   ", mss->shared_dirty);
+		SEQ_PUT_DEC(" kB\nPrivate_Clean:  ", mss->private_clean);
+		SEQ_PUT_DEC(" kB\nPrivate_Dirty:  ", mss->private_dirty);
+		SEQ_PUT_DEC(" kB\nReferenced:     ", mss->referenced);
+		SEQ_PUT_DEC(" kB\nAnonymous:      ", mss->anonymous);
+		SEQ_PUT_DEC(" kB\nLazyFree:       ", mss->lazyfree);
+		SEQ_PUT_DEC(" kB\nAnonHugePages:  ", mss->anonymous_thp);
+		SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp);
+		SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb);
+		seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ",
+					  mss->private_hugetlb >> 10, 7);
+		SEQ_PUT_DEC(" kB\nSwap:           ", mss->swap);
+		SEQ_PUT_DEC(" kB\nSwapPss:        ",
+						mss->swap_pss >> PSS_SHIFT);
+		SEQ_PUT_DEC(" kB\nLocked:         ", mss->pss >> PSS_SHIFT);
+		seq_puts(m, " kB\n");
+	}
 	if (!rollup_mode) {
 		arch_show_smap(m, vma);
 		show_smap_vma_flags(m, vma);
@@ -861,6 +841,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 	m_cache_vma(m, vma);
 	return ret;
 }
+#undef SEQ_PUT_DEC
 
 static int show_pid_smap(struct seq_file *m, void *v)
 {
diff --git a/fs/seq_file.c b/fs/seq_file.c
index eea09f6d8830..8389da9d0eb8 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -6,6 +6,7 @@
  * initial implementation -- AV, Oct 2001.
  */
 
+#include <linux/cache.h>
 #include <linux/fs.h>
 #include <linux/export.h>
 #include <linux/seq_file.h>
@@ -19,6 +20,8 @@
 #include <linux/uaccess.h>
 #include <asm/page.h>
 
+static struct kmem_cache *seq_file_cache __ro_after_init;
+
 static void seq_set_overflow(struct seq_file *m)
 {
 	m->count = m->size;
@@ -26,7 +29,7 @@ static void seq_set_overflow(struct seq_file *m)
 
 static void *seq_buf_alloc(unsigned long size)
 {
-	return kvmalloc(size, GFP_KERNEL);
+	return kvmalloc(size, GFP_KERNEL_ACCOUNT);
 }
 
 /**
@@ -51,7 +54,7 @@ int seq_open(struct file *file, const struct seq_operations *op)
 
 	WARN_ON(file->private_data);
 
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	p = kmem_cache_zalloc(seq_file_cache, GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
@@ -366,7 +369,7 @@ int seq_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *m = file->private_data;
 	kvfree(m->buf);
-	kfree(m);
+	kmem_cache_free(seq_file_cache, m);
 	return 0;
 }
 EXPORT_SYMBOL(seq_release);
@@ -563,7 +566,7 @@ static void single_stop(struct seq_file *p, void *v)
 int single_open(struct file *file, int (*show)(struct seq_file *, void *),
 		void *data)
 {
-	struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL);
+	struct seq_operations *op = kmalloc(sizeof(*op), GFP_KERNEL_ACCOUNT);
 	int res = -ENOMEM;
 
 	if (op) {
@@ -625,7 +628,7 @@ void *__seq_open_private(struct file *f, const struct seq_operations *ops,
 	void *private;
 	struct seq_file *seq;
 
-	private = kzalloc(psize, GFP_KERNEL);
+	private = kzalloc(psize, GFP_KERNEL_ACCOUNT);
 	if (private == NULL)
 		goto out;
 
@@ -673,37 +676,40 @@ void seq_puts(struct seq_file *m, const char *s)
 }
 EXPORT_SYMBOL(seq_puts);
 
-/*
+/**
  * A helper routine for putting decimal numbers without rich format of printf().
  * only 'unsigned long long' is supported.
- * This routine will put strlen(delimiter) + number into seq_file.
+ * @m: seq_file identifying the buffer to which data should be written
+ * @delimiter: a string which is printed before the number
+ * @num: the number
+ * @width: a minimum field width
+ *
+ * This routine will put strlen(delimiter) + number into seq_filed.
  * This routine is very quick when you show lots of numbers.
  * In usual cases, it will be better to use seq_printf(). It's easier to read.
  */
-void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
-			 unsigned long long num)
+void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
+			 unsigned long long num, unsigned int width)
 {
 	int len;
 
 	if (m->count + 2 >= m->size) /* we'll write 2 bytes at least */
 		goto overflow;
 
-	len = strlen(delimiter);
-	if (m->count + len >= m->size)
-		goto overflow;
+	if (delimiter && delimiter[0]) {
+		if (delimiter[1] == 0)
+			seq_putc(m, delimiter[0]);
+		else
+			seq_puts(m, delimiter);
+	}
 
-	memcpy(m->buf + m->count, delimiter, len);
-	m->count += len;
+	if (!width)
+		width = 1;
 
-	if (m->count + 1 >= m->size)
+	if (m->count + width >= m->size)
 		goto overflow;
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
-	len = num_to_str(m->buf + m->count, m->size - m->count, num);
+	len = num_to_str(m->buf + m->count, m->size - m->count, num, width);
 	if (!len)
 		goto overflow;
 
@@ -713,8 +719,60 @@ void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
 overflow:
 	seq_set_overflow(m);
 }
+
+void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
+			 unsigned long long num)
+{
+	return seq_put_decimal_ull_width(m, delimiter, num, 0);
+}
 EXPORT_SYMBOL(seq_put_decimal_ull);
 
+/**
+ * seq_put_hex_ll - put a number in hexadecimal notation
+ * @m: seq_file identifying the buffer to which data should be written
+ * @delimiter: a string which is printed before the number
+ * @v: the number
+ * @width: a minimum field width
+ *
+ * seq_put_hex_ll(m, "", v, 8) is equal to seq_printf(m, "%08llx", v)
+ *
+ * This routine is very quick when you show lots of numbers.
+ * In usual cases, it will be better to use seq_printf(). It's easier to read.
+ */
+void seq_put_hex_ll(struct seq_file *m, const char *delimiter,
+				unsigned long long v, unsigned int width)
+{
+	unsigned int len;
+	int i;
+
+	if (delimiter && delimiter[0]) {
+		if (delimiter[1] == 0)
+			seq_putc(m, delimiter[0]);
+		else
+			seq_puts(m, delimiter);
+	}
+
+	/* If x is 0, the result of __builtin_clzll is undefined */
+	if (v == 0)
+		len = 1;
+	else
+		len = (sizeof(v) * 8 - __builtin_clzll(v) + 3) / 4;
+
+	if (len < width)
+		len = width;
+
+	if (m->count + len > m->size) {
+		seq_set_overflow(m);
+		return;
+	}
+
+	for (i = len - 1; i >= 0; i--) {
+		m->buf[m->count + i] = hex_asc[0xf & v];
+		v = v >> 4;
+	}
+	m->count += len;
+}
+
 void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num)
 {
 	int len;
@@ -722,12 +780,12 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num
 	if (m->count + 3 >= m->size) /* we'll write 2 bytes at least */
 		goto overflow;
 
-	len = strlen(delimiter);
-	if (m->count + len >= m->size)
-		goto overflow;
-
-	memcpy(m->buf + m->count, delimiter, len);
-	m->count += len;
+	if (delimiter && delimiter[0]) {
+		if (delimiter[1] == 0)
+			seq_putc(m, delimiter[0]);
+		else
+			seq_puts(m, delimiter);
+	}
 
 	if (m->count + 2 >= m->size)
 		goto overflow;
@@ -737,12 +795,7 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num
 		num = -num;
 	}
 
-	if (num < 10) {
-		m->buf[m->count++] = num + '0';
-		return;
-	}
-
-	len = num_to_str(m->buf + m->count, m->size - m->count, num);
+	len = num_to_str(m->buf + m->count, m->size - m->count, num, 0);
 	if (!len)
 		goto overflow;
 
@@ -782,8 +835,14 @@ EXPORT_SYMBOL(seq_write);
 void seq_pad(struct seq_file *m, char c)
 {
 	int size = m->pad_until - m->count;
-	if (size > 0)
-		seq_printf(m, "%*s", size, "");
+	if (size > 0) {
+		if (size + m->count > m->size) {
+			seq_set_overflow(m);
+			return;
+		}
+		memset(m->buf + m->count, ' ', size);
+		m->count += size;
+	}
 	if (c)
 		seq_putc(m, c);
 }
@@ -1040,3 +1099,8 @@ seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head,
 	return NULL;
 }
 EXPORT_SYMBOL(seq_hlist_next_percpu);
+
+void __init seq_file_init(void)
+{
+	seq_file_cache = KMEM_CACHE(seq_file, SLAB_ACCOUNT|SLAB_PANIC);
+}
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f8894dbc0b19..539a5cf94fe2 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -175,7 +175,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 }
 
 long congestion_wait(int sync, long timeout);
-long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
+long wait_iff_congested(int sync, long timeout);
 
 static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi)
 {
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index b0abe21d6cc9..4955e0863b83 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -61,6 +61,8 @@ struct linux_binprm {
 	unsigned interp_flags;
 	unsigned interp_data;
 	unsigned long loader, exec;
+
+	struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */
 } __randomize_layout;
 
 #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0
@@ -118,6 +120,7 @@ extern int __must_check remove_arg_zero(struct linux_binprm *);
 extern int search_binary_handler(struct linux_binprm *);
 extern int flush_old_exec(struct linux_binprm * bprm);
 extern void setup_new_exec(struct linux_binprm * bprm);
+extern void finalize_exec(struct linux_binprm *bprm);
 extern void would_dump(struct linux_binprm *, struct file *);
 
 extern int suid_dumpable;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index dc5b70449dc6..9b2879bba00e 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -81,6 +81,11 @@ enum {
 	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
 	 */
 	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
+
+	/*
+	 * Enable cgroup-aware OOM killer.
+	 */
+	CGRP_GROUP_OOM = (1 << 5),
 };
 
 /* cftype->flags */
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index d3f264a5b04d..ceb96ecab96e 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -17,9 +17,6 @@
  */
 #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
 
-#define randomized_struct_fields_start	struct {
-#define randomized_struct_fields_end	};
-
 /* all clang versions usable with the kernel support KASAN ABI version 5 */
 #define KASAN_ABI_VERSION 5
 
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index e2c7f4369eff..b4bf73f5e38f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -242,6 +242,9 @@
 #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__)
 #define __randomize_layout __attribute__((randomize_layout))
 #define __no_randomize_layout __attribute__((no_randomize_layout))
+/* This anon struct can add padding, so only enable it under randstruct. */
+#define randomized_struct_fields_start	struct {
+#define randomized_struct_fields_end	} __randomize_layout;
 #endif
 
 #endif /* GCC_VERSION >= 40500 */
@@ -256,15 +259,6 @@
  */
 #define __visible	__attribute__((externally_visible))
 
-/*
- * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only
- * possible since GCC 4.6. To provide as much build testing coverage
- * as possible, this is used for all GCC 4.6+ builds, and not just on
- * RANDSTRUCT_PLUGIN builds.
- */
-#define randomized_struct_fields_start	struct {
-#define randomized_struct_fields_end	} __randomize_layout;
-
 #endif /* GCC_VERSION >= 40600 */
 
 
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index c3c95d18bf43..7e6c77740413 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -64,10 +64,11 @@ static inline struct dentry *fault_create_debugfs_attr(const char *name,
 
 struct kmem_cache;
 
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #ifdef CONFIG_FAILSLAB
-extern bool should_failslab(struct kmem_cache *s, gfp_t gfpflags);
+extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #else
-static inline bool should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
 	return false;
 }
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 325017ad9311..5d26e0a223d9 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -80,76 +80,145 @@
 struct hmm;
 
 /*
- * hmm_pfn_t - HMM uses its own pfn type to keep several flags per page
+ * hmm_pfn_flag_e - HMM flag enums
  *
  * Flags:
- * HMM_PFN_VALID: pfn is valid
- * HMM_PFN_READ:  CPU page table has read permission set
+ * HMM_PFN_VALID: pfn is valid. It has, at least, read permission.
  * HMM_PFN_WRITE: CPU page table has write permission set
+ * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE)
+ *
+ * The driver provide a flags array, if driver valid bit for an entry is bit
+ * 3 ie (entry & (1 << 3)) is true if entry is valid then driver must provide
+ * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3.
+ * Same logic apply to all flags. This is same idea as vm_page_prot in vma
+ * except that this is per device driver rather than per architecture.
+ */
+enum hmm_pfn_flag_e {
+	HMM_PFN_VALID = 0,
+	HMM_PFN_WRITE,
+	HMM_PFN_DEVICE_PRIVATE,
+	HMM_PFN_FLAG_MAX
+};
+
+/*
+ * hmm_pfn_value_e - HMM pfn special value
+ *
+ * Flags:
  * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
- * HMM_PFN_EMPTY: corresponding CPU page table entry is pte_none()
+ * HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
  * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
  *      result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not
  *      be mirrored by a device, because the entry will never have HMM_PFN_VALID
  *      set and the pfn value is undefined.
- * HMM_PFN_DEVICE_UNADDRESSABLE: unaddressable device memory (ZONE_DEVICE)
+ *
+ * Driver provide entry value for none entry, error entry and special entry,
+ * driver can alias (ie use same value for error and special for instance). It
+ * should not alias none and error or special.
+ *
+ * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be:
+ * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous,
+ * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table
+ * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one
  */
-typedef unsigned long hmm_pfn_t;
+enum hmm_pfn_value_e {
+	HMM_PFN_ERROR,
+	HMM_PFN_NONE,
+	HMM_PFN_SPECIAL,
+	HMM_PFN_VALUE_MAX
+};
 
-#define HMM_PFN_VALID (1 << 0)
-#define HMM_PFN_READ (1 << 1)
-#define HMM_PFN_WRITE (1 << 2)
-#define HMM_PFN_ERROR (1 << 3)
-#define HMM_PFN_EMPTY (1 << 4)
-#define HMM_PFN_SPECIAL (1 << 5)
-#define HMM_PFN_DEVICE_UNADDRESSABLE (1 << 6)
-#define HMM_PFN_SHIFT 7
+/*
+ * struct hmm_range - track invalidation lock on virtual address range
+ *
+ * @vma: the vm area struct for the range
+ * @list: all range lock are on a list
+ * @start: range virtual start address (inclusive)
+ * @end: range virtual end address (exclusive)
+ * @pfns: array of pfns (big enough for the range)
+ * @flags: pfn flags to match device driver page table
+ * @values: pfn value for some special case (none, special, error, ...)
+ * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT)
+ * @valid: pfns array did not change since it has been fill by an HMM function
+ */
+struct hmm_range {
+	struct vm_area_struct	*vma;
+	struct list_head	list;
+	unsigned long		start;
+	unsigned long		end;
+	uint64_t		*pfns;
+	const uint64_t		*flags;
+	const uint64_t		*values;
+	uint8_t			pfn_shift;
+	bool			valid;
+};
 
 /*
- * hmm_pfn_t_to_page() - return struct page pointed to by a valid hmm_pfn_t
- * @pfn: hmm_pfn_t to convert to struct page
- * Returns: struct page pointer if pfn is a valid hmm_pfn_t, NULL otherwise
+ * hmm_pfn_to_page() - return struct page pointed to by a valid HMM pfn
+ * @range: range use to decode HMM pfn value
+ * @pfn: HMM pfn value to get corresponding struct page from
+ * Returns: struct page pointer if pfn is a valid HMM pfn, NULL otherwise
  *
- * If the hmm_pfn_t is valid (ie valid flag set) then return the struct page
- * matching the pfn value stored in the hmm_pfn_t. Otherwise return NULL.
+ * If the HMM pfn is valid (ie valid flag set) then return the struct page
+ * matching the pfn value stored in the HMM pfn. Otherwise return NULL.
  */
-static inline struct page *hmm_pfn_t_to_page(hmm_pfn_t pfn)
+static inline struct page *hmm_pfn_to_page(const struct hmm_range *range,
+					   uint64_t pfn)
 {
-	if (!(pfn & HMM_PFN_VALID))
+	if (pfn == range->values[HMM_PFN_NONE])
+		return NULL;
+	if (pfn == range->values[HMM_PFN_ERROR])
+		return NULL;
+	if (pfn == range->values[HMM_PFN_SPECIAL])
 		return NULL;
-	return pfn_to_page(pfn >> HMM_PFN_SHIFT);
+	if (!(pfn & range->flags[HMM_PFN_VALID]))
+		return NULL;
+	return pfn_to_page(pfn >> range->pfn_shift);
 }
 
 /*
- * hmm_pfn_t_to_pfn() - return pfn value store in a hmm_pfn_t
- * @pfn: hmm_pfn_t to extract pfn from
- * Returns: pfn value if hmm_pfn_t is valid, -1UL otherwise
+ * hmm_pfn_to_pfn() - return pfn value store in a HMM pfn
+ * @range: range use to decode HMM pfn value
+ * @pfn: HMM pfn value to extract pfn from
+ * Returns: pfn value if HMM pfn is valid, -1UL otherwise
  */
-static inline unsigned long hmm_pfn_t_to_pfn(hmm_pfn_t pfn)
+static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range,
+					   uint64_t pfn)
 {
-	if (!(pfn & HMM_PFN_VALID))
+	if (pfn == range->values[HMM_PFN_NONE])
+		return -1UL;
+	if (pfn == range->values[HMM_PFN_ERROR])
+		return -1UL;
+	if (pfn == range->values[HMM_PFN_SPECIAL])
 		return -1UL;
-	return (pfn >> HMM_PFN_SHIFT);
+	if (!(pfn & range->flags[HMM_PFN_VALID]))
+		return -1UL;
+	return (pfn >> range->pfn_shift);
 }
 
 /*
- * hmm_pfn_t_from_page() - create a valid hmm_pfn_t value from struct page
- * @page: struct page pointer for which to create the hmm_pfn_t
- * Returns: valid hmm_pfn_t for the page
+ * hmm_pfn_from_page() - create a valid HMM pfn value from struct page
+ * @range: range use to encode HMM pfn value
+ * @page: struct page pointer for which to create the HMM pfn
+ * Returns: valid HMM pfn for the page
  */
-static inline hmm_pfn_t hmm_pfn_t_from_page(struct page *page)
+static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range,
+					 struct page *page)
 {
-	return (page_to_pfn(page) << HMM_PFN_SHIFT) | HMM_PFN_VALID;
+	return (page_to_pfn(page) << range->pfn_shift) |
+		range->flags[HMM_PFN_VALID];
 }
 
 /*
- * hmm_pfn_t_from_pfn() - create a valid hmm_pfn_t value from pfn
- * @pfn: pfn value for which to create the hmm_pfn_t
- * Returns: valid hmm_pfn_t for the pfn
+ * hmm_pfn_from_pfn() - create a valid HMM pfn value from pfn
+ * @range: range use to encode HMM pfn value
+ * @pfn: pfn value for which to create the HMM pfn
+ * Returns: valid HMM pfn for the pfn
  */
-static inline hmm_pfn_t hmm_pfn_t_from_pfn(unsigned long pfn)
+static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range,
+					unsigned long pfn)
 {
-	return (pfn << HMM_PFN_SHIFT) | HMM_PFN_VALID;
+	return (pfn << range->pfn_shift) |
+		range->flags[HMM_PFN_VALID];
 }
 
 
@@ -218,6 +287,16 @@ enum hmm_update_type {
  * @update: callback to update range on a device
  */
 struct hmm_mirror_ops {
+	/* release() - release hmm_mirror
+	 *
+	 * @mirror: pointer to struct hmm_mirror
+	 *
+	 * This is called when the mm_struct is being released.
+	 * The callback should make sure no references to the mirror occur
+	 * after the callback returns.
+	 */
+	void (*release)(struct hmm_mirror *mirror);
+
 	/* sync_cpu_device_pagetables() - synchronize page tables
 	 *
 	 * @mirror: pointer to struct hmm_mirror
@@ -262,23 +341,6 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror);
 
 
 /*
- * struct hmm_range - track invalidation lock on virtual address range
- *
- * @list: all range lock are on a list
- * @start: range virtual start address (inclusive)
- * @end: range virtual end address (exclusive)
- * @pfns: array of pfns (big enough for the range)
- * @valid: pfns array did not change since it has been fill by an HMM function
- */
-struct hmm_range {
-	struct list_head	list;
-	unsigned long		start;
-	unsigned long		end;
-	hmm_pfn_t		*pfns;
-	bool			valid;
-};
-
-/*
  * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device
  * driver lock that serializes device page table updates, then call
  * hmm_vma_range_done(), to check if the snapshot is still valid. The same
@@ -291,17 +353,13 @@ struct hmm_range {
  *
  * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID !
  */
-int hmm_vma_get_pfns(struct vm_area_struct *vma,
-		     struct hmm_range *range,
-		     unsigned long start,
-		     unsigned long end,
-		     hmm_pfn_t *pfns);
-bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range);
+int hmm_vma_get_pfns(struct hmm_range *range);
+bool hmm_vma_range_done(struct hmm_range *range);
 
 
 /*
  * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will
- * not migrate any device memory back to system memory. The hmm_pfn_t array will
+ * not migrate any device memory back to system memory. The HMM pfn array will
  * be updated with the fault result and current snapshot of the CPU page table
  * for the range.
  *
@@ -310,20 +368,14 @@ bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range);
  * function returns -EAGAIN.
  *
  * Return value does not reflect if the fault was successful for every single
- * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to
+ * address or not. Therefore, the caller must to inspect the HMM pfn array to
  * determine fault status for each address.
  *
  * Trying to fault inside an invalid vma will result in -EINVAL.
  *
  * See the function description in mm/hmm.c for further documentation.
  */
-int hmm_vma_fault(struct vm_area_struct *vma,
-		  struct hmm_range *range,
-		  unsigned long start,
-		  unsigned long end,
-		  hmm_pfn_t *pfns,
-		  bool write,
-		  bool block);
+int hmm_vma_fault(struct hmm_range *range, bool block);
 #endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
 
 
@@ -498,23 +550,16 @@ struct hmm_device {
 struct hmm_device *hmm_device_new(void *drvdata);
 void hmm_device_put(struct hmm_device *hmm_device);
 #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */
-#endif /* IS_ENABLED(CONFIG_HMM) */
 
 /* Below are for HMM internal use only! Not to be used by device driver! */
-#if IS_ENABLED(CONFIG_HMM_MIRROR)
 void hmm_mm_destroy(struct mm_struct *mm);
 
 static inline void hmm_mm_init(struct mm_struct *mm)
 {
 	mm->hmm = NULL;
 }
-#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-static inline void hmm_mm_destroy(struct mm_struct *mm) {}
-static inline void hmm_mm_init(struct mm_struct *mm) {}
-#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
-
-
 #else /* IS_ENABLED(CONFIG_HMM) */
 static inline void hmm_mm_destroy(struct mm_struct *mm) {}
 static inline void hmm_mm_init(struct mm_struct *mm) {}
+#endif /* IS_ENABLED(CONFIG_HMM) */
 #endif /* LINUX_HMM_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 36fa6a2a82e3..222d2a329f14 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -9,6 +9,7 @@
 #include <linux/cgroup.h>
 #include <linux/list.h>
 #include <linux/kref.h>
+#include <linux/mempolicy.h>
 #include <asm/pgtable.h>
 
 struct ctl_table;
@@ -256,6 +257,21 @@ enum {
 	HUGETLB_ANONHUGE_INODE  = 2,
 };
 
+/*
+ * HUGETLBFS_I (and hugetlbfs_inode_info) referenced but not used by code
+ * outside #ifdef CONFIG_HUGETLBFS.  Define here to prevent compiler errors.
+ */
+struct hugetlbfs_inode_info {
+	struct shared_policy policy;
+	struct inode vfs_inode;
+	unsigned int seals;
+};
+
+static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
+{
+	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
+}
+
 #ifdef CONFIG_HUGETLBFS
 struct hugetlbfs_sb_info {
 	long	max_inodes;   /* inodes allowed */
@@ -273,17 +289,6 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
-struct hugetlbfs_inode_info {
-	struct shared_policy policy;
-	struct inode vfs_inode;
-	unsigned int seals;
-};
-
-static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
-{
-	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
-}
-
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index d6459bd1376d..de784fd11d12 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -43,7 +43,7 @@ void kasan_unpoison_stack_above_sp_to(const void *watermark);
 void kasan_alloc_pages(struct page *page, unsigned int order);
 void kasan_free_pages(struct page *page, unsigned int order);
 
-void kasan_cache_create(struct kmem_cache *cache, size_t *size,
+void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 			slab_flags_t *flags);
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
@@ -92,7 +92,7 @@ static inline void kasan_alloc_pages(struct page *page, unsigned int order) {}
 static inline void kasan_free_pages(struct page *page, unsigned int order) {}
 
 static inline void kasan_cache_create(struct kmem_cache *cache,
-				      size_t *size,
+				      unsigned int *size,
 				      slab_flags_t *flags) {}
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 0db846a677e0..0f13b37ff7f0 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -456,7 +456,8 @@ extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
 extern long long simple_strtoll(const char *,char **,unsigned int);
 
-extern int num_to_str(char *buf, int size, unsigned long long num);
+extern int num_to_str(char *buf, int size,
+		      unsigned long long num, unsigned int width);
 
 /* lib/printf utilities */
 
@@ -560,6 +561,7 @@ extern enum system_states {
 	SYSTEM_RESTART,
 } system_state;
 
+/* This cannot be an enum because some may be used in assembly source. */
 #define TAINT_PROPRIETARY_MODULE	0
 #define TAINT_FORCED_MODULE		1
 #define TAINT_CPU_OUT_OF_SPEC		2
@@ -577,7 +579,8 @@ extern enum system_states {
 #define TAINT_SOFTLOCKUP		14
 #define TAINT_LIVEPATCH			15
 #define TAINT_AUX			16
-#define TAINT_FLAGS_COUNT		17
+#define TAINT_RANDSTRUCT		17
+#define TAINT_FLAGS_COUNT		18
 
 struct taint_flag {
 	char c_true;	/* character printed when tainted */
@@ -846,6 +849,25 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 	      x, y)
 
 /**
+ * const_max - return maximum of two positive compile-time constant values
+ * @x: first compile-time constant value
+ * @y: second compile-time constant value
+ *
+ * This has no type checking nor multi-evaluation defenses, and must
+ * only ever be used with positive compile-time constant values (for
+ * example when calculating a stack array size).
+ */
+size_t __error_not_const_arg(void) \
+__compiletime_error("const_max() used with non-compile-time constant arg");
+#define const_max(x, y)						\
+	__builtin_choose_expr(__builtin_constant_p(x) &&	\
+			      __builtin_constant_p(y),		\
+			      (size_t)(x) > (size_t)(y) ?	\
+					(size_t)(x) :		\
+					(size_t)(y),		\
+			      __error_not_const_arg())
+
+/**
  * min3 - return minimum of three values
  * @x: first value
  * @y: second value
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index bb8129a3474d..96def9d15b1b 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -32,6 +32,7 @@ struct list_lru_one {
 };
 
 struct list_lru_memcg {
+	struct rcu_head		rcu;
 	/* array of per cgroup lists, indexed by memcg_cache_id */
 	struct list_lru_one	*lru[0];
 };
@@ -43,7 +44,7 @@ struct list_lru_node {
 	struct list_lru_one	lru;
 #if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
-	struct list_lru_memcg	*memcg_lrus;
+	struct list_lru_memcg	__rcu *memcg_lrus;
 #endif
 	long nr_items;
 } ____cacheline_aligned_in_smp;
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index b1c53ff72e48..ca59883c8364 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -419,21 +419,11 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end)
 {
 }
 #endif
-
-extern unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-		phys_addr_t end_addr);
 #else
 static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
 	return 0;
 }
-
-static inline unsigned long memblock_reserved_memory_within(phys_addr_t start_addr,
-		phys_addr_t end_addr)
-{
-	return 0;
-}
-
 #endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c46016bb25eb..6246bb75e226 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -35,6 +35,7 @@ struct mem_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
+struct oom_control;
 
 /* Cgroup-specific page state, on top of universal node page state */
 enum memcg_stat_item {
@@ -189,6 +190,8 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
+	unsigned long flags;
+
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -202,6 +205,13 @@ struct mem_cgroup {
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
+	/*
+	 * Treat the sub-tree as an indivisible memory consumer,
+	 * kill all belonging tasks if the memory cgroup selected
+	 * as OOM victim.
+	 */
+	bool oom_group;
+
 	/* handle for "memory.events" */
 	struct cgroup_file events_file;
 
@@ -344,6 +354,11 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+	css_put(&memcg->css);
+}
+
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -482,6 +497,13 @@ static inline bool task_in_memcg_oom(struct task_struct *p)
 
 bool mem_cgroup_oom_synchronize(bool wait);
 
+bool mem_cgroup_select_oom_victim(struct oom_control *oc);
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return memcg->oom_group;
+}
+
 #ifdef CONFIG_MEMCG_SWAP
 extern int do_swap_account;
 #endif
@@ -789,6 +811,10 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
+static inline void mem_cgroup_put(struct mem_cgroup *memcg)
+{
+}
+
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -981,6 +1007,16 @@ static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
+
+static inline bool mem_cgroup_select_oom_victim(struct oom_control *oc)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_group(struct mem_cgroup *memcg)
+{
+	return false;
+}
 #endif /* CONFIG_MEMCG */
 
 /* idx can be of type enum memcg_stat_item or node_stat_item */
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
new file mode 100644
index 000000000000..4f1600413f91
--- /dev/null
+++ b/include/linux/memfd.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_MEMFD_H
+#define __LINUX_MEMFD_H
+
+#include <linux/file.h>
+
+#ifdef CONFIG_MEMFD_CREATE
+extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
+#else
+static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a)
+{
+	return -EINVAL;
+}
+#endif
+
+#endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index f71e732c77b2..31ca3e28b0eb 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -33,6 +33,7 @@ struct memory_block {
 	void *hw;			/* optional pointer to fw/hw data */
 	int (*phys_callback)(struct memory_block *);
 	struct device dev;
+	int nid;			/* NID for this memory block */
 };
 
 int arch_get_memory_phys_device(unsigned long start_pfn);
@@ -109,7 +110,7 @@ extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
-extern int register_new_memory(int, struct mem_section *);
+int hotplug_memory_register(int nid, struct mem_section *section);
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern int unregister_memory_section(struct mem_section *);
 #endif
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index aba5f86eb038..e0e49b5b1ee1 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -52,24 +52,6 @@ enum {
 };
 
 /*
- * pgdat resizing functions
- */
-static inline
-void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
-{
-	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
-}
-static inline
-void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
-{
-	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
-}
-static inline
-void pgdat_resize_init(struct pglist_data *pgdat)
-{
-	spin_lock_init(&pgdat->node_size_lock);
-}
-/*
  * Zone resizing functions
  *
  * Note: any attempt to resize a zone should has pgdat_resize_lock()
@@ -234,9 +216,6 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
 ({						\
@@ -246,13 +225,6 @@ extern void clear_zone_contiguous(struct zone *zone);
 	___page;				\
  })
 
-/*
- * Stub functions for when hotplug is off
- */
-static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
-static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
-static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
-
 static inline unsigned zone_span_seqbegin(struct zone *zone)
 {
 	return 0;
@@ -293,6 +265,34 @@ static inline bool movable_node_is_enabled(void)
 }
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
+#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
+/*
+ * pgdat resizing functions
+ */
+static inline
+void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
+{
+	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
+}
+static inline
+void pgdat_resize_init(struct pglist_data *pgdat)
+{
+	spin_lock_init(&pgdat->node_size_lock);
+}
+#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
+/*
+ * Stub functions for when hotplug is off
+ */
+static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
+static inline void pgdat_resize_init(struct pglist_data *pgdat) {}
+#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
+
 #ifdef CONFIG_MEMORY_HOTREMOVE
 
 extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index a2246cf670ba..f2b4abbca55e 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,8 +7,7 @@
 #include <linux/migrate_mode.h>
 #include <linux/hugetlb.h>
 
-typedef struct page *new_page_t(struct page *page, unsigned long private,
-				int **reason);
+typedef struct page *new_page_t(struct page *page, unsigned long private);
 typedef void free_page_t(struct page *page, unsigned long private);
 
 /*
@@ -25,7 +24,7 @@ enum migrate_reason {
 	MR_SYSCALL,		/* also applies to cpusets */
 	MR_MEMPOLICY_MBIND,
 	MR_NUMA_MISPLACED,
-	MR_CMA,
+	MR_CONTIG_RANGE,
 	MR_TYPES
 };
 
@@ -43,9 +42,9 @@ static inline struct page *new_page_nodemask(struct page *page,
 		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
 				preferred_nid, nodemask);
 
-	if (thp_migration_supported() && PageTransHuge(page)) {
-		order = HPAGE_PMD_ORDER;
+	if (PageTransHuge(page)) {
 		gfp_mask |= GFP_TRANSHUGE;
+		order = HPAGE_PMD_ORDER;
 	}
 
 	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 87f2149f0b69..cb8d2f85612a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -386,17 +386,19 @@ struct vm_operations_struct {
 	void (*close)(struct vm_area_struct * area);
 	int (*split)(struct vm_area_struct * area, unsigned long addr);
 	int (*mremap)(struct vm_area_struct * area);
-	int (*fault)(struct vm_fault *vmf);
-	int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size);
+	vm_fault_t (*fault)(struct vm_fault *vmf);
+	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
+			enum page_entry_size pe_size);
 	void (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
+	unsigned long (*pagesize)(struct vm_area_struct * area);
 
 	/* notification that a previously read-only page is about to become
 	 * writable, if an error is returned it will cause a SIGBUS */
-	int (*page_mkwrite)(struct vm_fault *vmf);
+	vm_fault_t (*page_mkwrite)(struct vm_fault *vmf);
 
 	/* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */
-	int (*pfn_mkwrite)(struct vm_fault *vmf);
+	vm_fault_t (*pfn_mkwrite)(struct vm_fault *vmf);
 
 	/* called by access_process_vm when get_user_pages() fails, typically
 	 * for use by special VMAs that can switch between memory and hardware
@@ -938,7 +940,9 @@ extern int page_to_nid(const struct page *page);
 #else
 static inline int page_to_nid(const struct page *page)
 {
-	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
+	struct page *p = (struct page *)page;
+
+	return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
 }
 #endif
 
@@ -1187,6 +1191,7 @@ static inline pgoff_t page_index(struct page *page)
 
 bool page_mapped(struct page *page);
 struct address_space *page_mapping(struct page *page);
+struct address_space *page_mapping_file(struct page *page);
 
 /*
  * Return true only if the page has been allocated with
@@ -2138,6 +2143,7 @@ extern void setup_per_cpu_pageset(void);
 
 extern void zone_pcp_update(struct zone *zone);
 extern void zone_pcp_reset(struct zone *zone);
+extern void setup_zone_pageset(struct zone *zone);
 
 /* page_alloc.c */
 extern int min_free_kbytes;
@@ -2455,6 +2461,44 @@ int vm_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
+static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
+				unsigned long addr, struct page *page)
+{
+	int err = vm_insert_page(vma, addr, page);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma,
+				unsigned long addr, pfn_t pfn)
+{
+	int err = vm_insert_mixed(vma, addr, pfn);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma,
+			unsigned long addr, unsigned long pfn)
+{
+	int err = vm_insert_pfn(vma, addr, pfn);
+
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (err < 0 && err != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
 
 struct page *follow_page_mask(struct vm_area_struct *vma,
 			      unsigned long address, unsigned int foll_flags,
@@ -2624,7 +2668,7 @@ extern int get_hwpoison_page(struct page *page);
 extern int sysctl_memory_failure_early_kill;
 extern int sysctl_memory_failure_recovery;
 extern void shake_page(struct page *p, int access);
-extern atomic_long_t num_poisoned_pages;
+extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(struct page *page, int flags);
 
 
@@ -2646,6 +2690,7 @@ enum mf_action_page_type {
 	MF_MSG_POISONED_HUGE,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
+	MF_MSG_NON_PMD_HUGE,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index fd1af6b9591d..21612347d311 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -22,6 +22,8 @@
 #endif
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
+typedef int vm_fault_t;
+
 struct address_space;
 struct mem_cgroup;
 struct hmm;
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 57b0030d3800..2ad72d2c8cc5 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -37,10 +37,10 @@ void dump_mm(const struct mm_struct *mm);
 			BUG();						\
 		}							\
 	} while (0)
-#define VM_WARN_ON(cond) WARN_ON(cond)
-#define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond)
-#define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
-#define VM_WARN(cond, format...) WARN(cond, format)
+#define VM_WARN_ON(cond) (void)WARN_ON(cond)
+#define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
+#define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format)
+#define VM_WARN(cond, format...) (void)WARN(cond, format)
 #else
 #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a2db4576e499..32699b2dc52a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -180,6 +180,7 @@ enum node_stat_item {
 	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
+	NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */
 	NR_VM_NODE_STAT_ITEMS
 };
 
@@ -633,14 +634,15 @@ typedef struct pglist_data {
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
 #endif
-#ifdef CONFIG_MEMORY_HOTPLUG
+#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
 	/*
 	 * Must be held any time you expect node_start_pfn, node_present_pages
 	 * or node_spanned_pages stay constant.  Holding this will also
 	 * guarantee that any pfn_valid() stays that way.
 	 *
 	 * pgdat_resize_lock() and pgdat_resize_unlock() are provided to
-	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG.
+	 * manipulate node_size_lock without checking for CONFIG_MEMORY_HOTPLUG
+	 * or CONFIG_DEFERRED_STRUCT_PAGE_INIT.
 	 *
 	 * Nests above zone->lock and zone->span_seqlock
 	 */
@@ -775,7 +777,8 @@ static inline bool is_dev_zone(const struct zone *zone)
 #include <linux/memory_hotplug.h>
 
 void build_all_zonelists(pg_data_t *pgdat);
-void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
+void wakeup_kswapd(struct zone *zone, gfp_t gfp_mask, int order,
+		   enum zone_type classzone_idx);
 bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 			 int classzone_idx, unsigned int alloc_flags,
 			 long free_pages);
@@ -882,7 +885,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int watermark_scale_factor_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
-extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
+extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
 int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int,
 					void __user *, size_t *, loff_t *);
 int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
diff --git a/include/linux/node.h b/include/linux/node.h
index 4ece0fee0ffc..41f171861dcc 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -67,7 +67,7 @@ extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int register_mem_sect_under_node(struct memory_block *mem_blk,
-						int nid);
+						int nid, bool check_nid);
 extern int unregister_mem_sect_under_nodes(struct memory_block *mem_blk,
 					   unsigned long phys_index);
 
@@ -97,7 +97,7 @@ static inline int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
 	return 0;
 }
 static inline int register_mem_sect_under_node(struct memory_block *mem_blk,
-							int nid)
+							int nid, bool check_nid)
 {
 	return 0;
 }
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 5bad038ac012..d4d41c01a74d 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -10,6 +10,13 @@
 #include <linux/sched/coredump.h> /* MMF_* */
 #include <linux/mm.h> /* VM_FAULT* */
 
+
+/*
+ * Special value returned by victim selection functions to indicate
+ * that are inflight OOM victims.
+ */
+#define INFLIGHT_VICTIM ((void *)-1UL)
+
 struct zonelist;
 struct notifier_block;
 struct mem_cgroup;
@@ -40,7 +47,8 @@ struct oom_control {
 
 	/* Used by oom implementation, do not set */
 	unsigned long totalpages;
-	struct task_struct *chosen;
+	struct task_struct *chosen_task;
+	struct mem_cgroup *chosen_memcg;
 	unsigned long chosen_points;
 };
 
@@ -111,6 +119,8 @@ extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
+extern int oom_evaluate_task(struct task_struct *task, void *arg);
+
 /* sysctls */
 extern int sysctl_oom_dump_tasks;
 extern int sysctl_oom_kill_allocating_task;
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 50c2b8786831..e34a27727b9a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -156,9 +156,18 @@ static __always_inline int PageCompound(struct page *page)
 	return test_bit(PG_head, &page->flags) || PageTail(page);
 }
 
+#define	PAGE_POISON_PATTERN	-1l
+static inline int PagePoisoned(const struct page *page)
+{
+	return page->flags == PAGE_POISON_PATTERN;
+}
+
 /*
  * Page flags policies wrt compound pages
  *
+ * PF_POISONED_CHECK
+ *     check if this struct page poisoned/uninitialized
+ *
  * PF_ANY:
  *     the page flag is relevant for small, head and tail pages.
  *
@@ -176,17 +185,20 @@ static __always_inline int PageCompound(struct page *page)
  * PF_NO_COMPOUND:
  *     the page flag is not relevant for compound pages.
  */
-#define PF_ANY(page, enforce)	page
-#define PF_HEAD(page, enforce)	compound_head(page)
+#define PF_POISONED_CHECK(page) ({					\
+		VM_BUG_ON_PGFLAGS(PagePoisoned(page), page);		\
+		page; })
+#define PF_ANY(page, enforce)	PF_POISONED_CHECK(page)
+#define PF_HEAD(page, enforce)	PF_POISONED_CHECK(compound_head(page))
 #define PF_ONLY_HEAD(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(PageTail(page), page);		\
-		page;})
+		PF_POISONED_CHECK(page); })
 #define PF_NO_TAIL(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page);	\
-		compound_head(page);})
+		PF_POISONED_CHECK(compound_head(page)); })
 #define PF_NO_COMPOUND(page, enforce) ({				\
 		VM_BUG_ON_PGFLAGS(enforce && PageCompound(page), page);	\
-		page;})
+		PF_POISONED_CHECK(page); })
 
 /*
  * Macros to create function definitions for page flags
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index cdad58bbfd8b..4ae347cbc36d 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -63,7 +63,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 			bool skip_hwpoisoned_pages);
 
-struct page *alloc_migrate_target(struct page *page, unsigned long private,
-				int **resultp);
+struct page *alloc_migrate_target(struct page *page, unsigned long private);
 
 #endif
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 760d74a0e9a9..14d14beb1f7f 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -175,8 +175,7 @@ static inline void page_ref_unfreeze(struct page *page, int count)
 	VM_BUG_ON_PAGE(page_count(page) != 0, page);
 	VM_BUG_ON(count == 0);
 
-	smp_mb();
-	atomic_set(&page->_refcount, count);
+	atomic_set_release(&page->_refcount, count);
 	if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze))
 		__page_ref_unfreeze(page, count);
 }
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 9806184bb3d5..2c570cd934af 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -104,7 +104,8 @@ static inline void mm_update_next_owner(struct mm_struct *mm)
 #endif /* CONFIG_MEMCG */
 
 #ifdef CONFIG_MMU
-extern void arch_pick_mmap_layout(struct mm_struct *mm);
+extern void arch_pick_mmap_layout(struct mm_struct *mm,
+				  struct rlimit *rlim_stack);
 extern unsigned long
 arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
 		       unsigned long, unsigned long);
@@ -113,7 +114,8 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 			  unsigned long len, unsigned long pgoff,
 			  unsigned long flags);
 #else
-static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
+static inline void arch_pick_mmap_layout(struct mm_struct *mm,
+					 struct rlimit *rlim_stack) {}
 #endif
 
 static inline bool in_vfork(struct task_struct *tsk)
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a7ce74c74e49..a52683a5fe90 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -104,6 +104,9 @@ struct signal_struct {
 	int			group_stop_count;
 	unsigned int		flags; /* see SIGNAL_* flags below */
 
+	/* The signal sent when the parent dies: */
+	int			pdeath_signal_proc;
+
 	/*
 	 * PR_SET_CHILD_SUBREAPER marks a process, like a service
 	 * manager, to re-parent orphan (double-forking) child processes
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index ab437dd2e3b9..a121982af0f5 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -118,9 +118,14 @@ __printf(2, 3)
 void seq_printf(struct seq_file *m, const char *fmt, ...);
 void seq_putc(struct seq_file *m, char c);
 void seq_puts(struct seq_file *m, const char *s);
+void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter,
+			       unsigned long long num, unsigned int width);
 void seq_put_decimal_ull(struct seq_file *m, const char *delimiter,
 			 unsigned long long num);
 void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num);
+void seq_put_hex_ll(struct seq_file *m, const char *delimiter,
+		    unsigned long long v, unsigned int width);
+
 void seq_escape(struct seq_file *m, const char *s, const char *esc);
 
 void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type,
@@ -235,4 +240,5 @@ extern struct hlist_node *seq_hlist_start_percpu(struct hlist_head __percpu *hea
 
 extern struct hlist_node *seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head, int *cpu, loff_t *pos);
 
+void seq_file_init(void);
 #endif
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 73b5e655a76e..f155dc607112 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -110,19 +110,6 @@ static inline bool shmem_file(struct file *file)
 extern bool shmem_charge(struct inode *inode, long pages);
 extern void shmem_uncharge(struct inode *inode, long pages);
 
-#ifdef CONFIG_TMPFS
-
-extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
-
-#else
-
-static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned long a)
-{
-	return -EINVAL;
-}
-
-#endif
-
 #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
 extern bool shmem_huge_enabled(struct vm_area_struct *vma);
 #else
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 388ff2936a87..a3894918a436 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -75,6 +75,6 @@ struct shrinker {
 #define SHRINKER_NUMA_AWARE	(1 << 0)
 #define SHRINKER_MEMCG_AWARE	(1 << 1)
 
-extern int register_shrinker(struct shrinker *);
+extern __must_check int register_shrinker(struct shrinker *);
 extern void unregister_shrinker(struct shrinker *);
 #endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 231abc8976c5..81ebd71f8c03 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -125,7 +125,6 @@
 #define ZERO_OR_NULL_PTR(x) ((unsigned long)(x) <= \
 				(unsigned long)ZERO_SIZE_PTR)
 
-#include <linux/kmemleak.h>
 #include <linux/kasan.h>
 
 struct mem_cgroup;
@@ -137,12 +136,13 @@ bool slab_is_available(void);
 
 extern bool usercopy_fallback;
 
-struct kmem_cache *kmem_cache_create(const char *name, size_t size,
-			size_t align, slab_flags_t flags,
+struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
+			unsigned int align, slab_flags_t flags,
 			void (*ctor)(void *));
 struct kmem_cache *kmem_cache_create_usercopy(const char *name,
-			size_t size, size_t align, slab_flags_t flags,
-			size_t useroffset, size_t usersize,
+			unsigned int size, unsigned int align,
+			slab_flags_t flags,
+			unsigned int useroffset, unsigned int usersize,
 			void (*ctor)(void *));
 void kmem_cache_destroy(struct kmem_cache *);
 int kmem_cache_shrink(struct kmem_cache *);
@@ -308,7 +308,7 @@ extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
  * 2 = 129 .. 192 bytes
  * n = 2^(n-1)+1 .. 2^n
  */
-static __always_inline int kmalloc_index(size_t size)
+static __always_inline unsigned int kmalloc_index(size_t size)
 {
 	if (!size)
 		return 0;
@@ -504,7 +504,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 			return kmalloc_large(size, flags);
 #ifndef CONFIG_SLOB
 		if (!(flags & GFP_DMA)) {
-			int index = kmalloc_index(size);
+			unsigned int index = kmalloc_index(size);
 
 			if (!index)
 				return ZERO_SIZE_PTR;
@@ -522,11 +522,11 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
  * return size or 0 if a kmalloc cache for that
  * size does not exist
  */
-static __always_inline int kmalloc_size(int n)
+static __always_inline unsigned int kmalloc_size(unsigned int n)
 {
 #ifndef CONFIG_SLOB
 	if (n > 2)
-		return 1 << n;
+		return 1U << n;
 
 	if (n == 1 && KMALLOC_MIN_SIZE <= 32)
 		return 96;
@@ -542,7 +542,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 #ifndef CONFIG_SLOB
 	if (__builtin_constant_p(size) &&
 		size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) {
-		int i = kmalloc_index(size);
+		unsigned int i = kmalloc_index(size);
 
 		if (!i)
 			return ZERO_SIZE_PTR;
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 7385547c04b1..d9228e4d0320 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -85,8 +85,8 @@ struct kmem_cache {
 	unsigned int *random_seq;
 #endif
 
-	size_t useroffset;		/* Usercopy region offset */
-	size_t usersize;		/* Usercopy region size */
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
 
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 8ad99c47b19c..3773e26c08c1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -73,7 +73,7 @@ struct kmem_cache_cpu {
  * given order would contain.
  */
 struct kmem_cache_order_objects {
-	unsigned long x;
+	unsigned int x;
 };
 
 /*
@@ -84,11 +84,12 @@ struct kmem_cache {
 	/* Used for retriving partial slabs etc */
 	slab_flags_t flags;
 	unsigned long min_partial;
-	int size;		/* The size of an object including meta data */
-	int object_size;	/* The size of an object without meta data */
-	int offset;		/* Free pointer offset. */
+	unsigned int size;	/* The size of an object including meta data */
+	unsigned int object_size;/* The size of an object without meta data */
+	unsigned int offset;	/* Free pointer offset. */
 #ifdef CONFIG_SLUB_CPU_PARTIAL
-	int cpu_partial;	/* Number of per cpu partial objects to keep around */
+	/* Number of per cpu partial objects to keep around */
+	unsigned int cpu_partial;
 #endif
 	struct kmem_cache_order_objects oo;
 
@@ -98,10 +99,10 @@ struct kmem_cache {
 	gfp_t allocflags;	/* gfp flags to use on each alloc */
 	int refcount;		/* Refcount for slab cache destroy */
 	void (*ctor)(void *);
-	int inuse;		/* Offset to metadata */
-	int align;		/* Alignment */
-	int reserved;		/* Reserved bytes at the end of slabs */
-	int red_left_pad;	/* Left redzone padding size */
+	unsigned int inuse;		/* Offset to metadata */
+	unsigned int align;		/* Alignment */
+	unsigned int reserved;		/* Reserved bytes at the end of slabs */
+	unsigned int red_left_pad;	/* Left redzone padding size */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
 #ifdef CONFIG_SYSFS
@@ -110,7 +111,8 @@ struct kmem_cache {
 #endif
 #ifdef CONFIG_MEMCG
 	struct memcg_cache_params memcg_params;
-	int max_attr_size; /* for propagation, maximum size of a stored attr */
+	/* for propagation, maximum size of a stored attr */
+	unsigned int max_attr_size;
 #ifdef CONFIG_SYSFS
 	struct kset *memcg_kset;
 #endif
@@ -124,7 +126,7 @@ struct kmem_cache {
 	/*
 	 * Defragmentation by allocating from a remote node.
 	 */
-	int remote_node_defrag_ratio;
+	unsigned int remote_node_defrag_ratio;
 #endif
 
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
@@ -135,8 +137,8 @@ struct kmem_cache {
 	struct kasan_cache kasan_info;
 #endif
 
-	size_t useroffset;		/* Usercopy region offset */
-	size_t usersize;		/* Usercopy region size */
+	unsigned int useroffset;	/* Usercopy region offset */
+	unsigned int usersize;		/* Usercopy region size */
 
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a1a3f4ed94ce..1985940af479 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -172,8 +172,9 @@ enum {
 	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
 	SWP_STABLE_WRITES = (1 << 10),	/* no overwrite PG_writeback pages */
 	SWP_SYNCHRONOUS_IO = (1 << 11),	/* synchronous IO is efficient */
+	SWP_VALID	= (1 << 12),	/* swap is valid to be operated on? */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 12),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 13),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
@@ -400,7 +401,6 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,
 #define SWAP_ADDRESS_SPACE_SHIFT	14
 #define SWAP_ADDRESS_SPACE_PAGES	(1 << SWAP_ADDRESS_SPACE_SHIFT)
 extern struct address_space *swapper_spaces[];
-extern bool swap_vma_readahead;
 #define swap_address_space(entry)			    \
 	(&swapper_spaces[swp_type(entry)][swp_offset(entry) \
 		>> SWAP_ADDRESS_SPACE_SHIFT])
@@ -422,14 +422,10 @@ extern struct page *read_swap_cache_async(swp_entry_t, gfp_t,
 extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated);
-extern struct page *swapin_readahead(swp_entry_t, gfp_t,
-			struct vm_area_struct *vma, unsigned long addr);
-
-extern struct page *swap_readahead_detect(struct vm_fault *vmf,
-					  struct vma_swap_readahead *swap_ra);
-extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
-					   struct vm_fault *vmf,
-					   struct vma_swap_readahead *swap_ra);
+extern struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag,
+				struct vm_fault *vmf);
+extern struct page *swapin_readahead(swp_entry_t entry, gfp_t flag,
+				struct vm_fault *vmf);
 
 /* linux/mm/swapfile.c */
 extern atomic_long_t nr_swap_pages;
@@ -437,11 +433,6 @@ extern long total_swap_pages;
 extern atomic_t nr_rotate_swap;
 extern bool has_usable_swap(void);
 
-static inline bool swap_use_vma_readahead(void)
-{
-	return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap);
-}
-
 /* Swap 50% full? Release swapcache more aggressively.. */
 static inline bool vm_swap_full(void)
 {
@@ -470,7 +461,7 @@ extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
 extern int page_swapcount(struct page *);
-extern int __swap_count(struct swap_info_struct *si, swp_entry_t entry);
+extern int __swap_count(swp_entry_t entry);
 extern int __swp_swapcount(swp_entry_t entry);
 extern int swp_swapcount(swp_entry_t entry);
 extern struct swap_info_struct *page_swap_info(struct page *);
@@ -480,6 +471,12 @@ extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 extern int init_swap_address_space(unsigned int type, unsigned long nr_pages);
 extern void exit_swap_address_space(unsigned int type);
+extern struct swap_info_struct *get_swap_device(swp_entry_t entry);
+
+static inline void put_swap_device(struct swap_info_struct *si)
+{
+	preempt_enable();
+}
 
 #else /* CONFIG_SWAP */
 
@@ -537,26 +534,14 @@ static inline void put_swap_page(struct page *page, swp_entry_t swp)
 {
 }
 
-static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
-			struct vm_area_struct *vma, unsigned long addr)
-{
-	return NULL;
-}
-
-static inline bool swap_use_vma_readahead(void)
-{
-	return false;
-}
-
-static inline struct page *swap_readahead_detect(
-	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
+static inline struct page *swap_cluster_readahead(swp_entry_t entry,
+				gfp_t gfp_mask, struct vm_fault *vmf)
 {
 	return NULL;
 }
 
-static inline struct page *do_swap_page_readahead(
-	swp_entry_t fentry, gfp_t gfp_mask,
-	struct vm_fault *vmf, struct vma_swap_readahead *swap_ra)
+static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
+			struct vm_fault *vmf)
 {
 	return NULL;
 }
@@ -597,7 +582,7 @@ static inline int page_swapcount(struct page *page)
 	return 0;
 }
 
-static inline int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+static inline int __swap_count(swp_entry_t entry)
 {
 	return 0;
 }
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 34f053a150a9..cf2862bd134a 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -43,11 +43,7 @@ enum {
 #define THREAD_ALIGN	THREAD_SIZE
 #endif
 
-#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK)
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
-#else
-# define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT)
-#endif
+#define THREADINFO_GFP		(GFP_KERNEL_ACCOUNT | __GFP_ZERO)
 
 /*
  * flag set/clear/test wrappers
diff --git a/include/linux/utsname.h b/include/linux/utsname.h
index c8060c2ecd04..44429d9142ca 100644
--- a/include/linux/utsname.h
+++ b/include/linux/utsname.h
@@ -44,6 +44,8 @@ static inline void put_uts_ns(struct uts_namespace *ns)
 {
 	kref_put(&ns->kref, free_uts_ns);
 }
+
+void uts_ns_init(void);
 #else
 static inline void get_uts_ns(struct uts_namespace *ns)
 {
@@ -61,6 +63,10 @@ static inline struct uts_namespace *copy_utsname(unsigned long flags,
 
 	return old_ns;
 }
+
+static inline void uts_ns_init(void)
+{
+}
 #endif
 
 #ifdef CONFIG_PROC_SYSCTL
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index a4c2317d8b9f..f25cef84b41d 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -20,6 +20,17 @@ extern int sysctl_vm_numa_stat_handler(struct ctl_table *table,
 		int write, void __user *buffer, size_t *length, loff_t *ppos);
 #endif
 
+struct reclaim_stat {
+	unsigned nr_dirty;
+	unsigned nr_unqueued_dirty;
+	unsigned nr_congested;
+	unsigned nr_writeback;
+	unsigned nr_immediate;
+	unsigned nr_activate;
+	unsigned nr_ref_keep;
+	unsigned nr_unmap_fail;
+};
+
 #ifdef CONFIG_VM_EVENT_COUNTERS
 /*
  * Light weight per cpu counter implementation.
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 57a8e98f2708..2219cce81ca4 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -47,6 +47,8 @@ void zs_destroy_pool(struct zs_pool *pool);
 unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t flags);
 void zs_free(struct zs_pool *pool, unsigned long obj);
 
+size_t zs_huge_class_size(struct zs_pool *pool);
+
 void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 			enum zs_mapmode mm);
 void zs_unmap_object(struct zs_pool *pool, unsigned long handle);
diff --git a/include/net/sock.h b/include/net/sock.h
index 49bd2c1796b0..74d725fdbe0f 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1114,8 +1114,8 @@ struct proto {
 	struct kmem_cache	*slab;
 	unsigned int		obj_size;
 	slab_flags_t		slab_flags;
-	size_t			useroffset;	/* Usercopy region offset */
-	size_t			usersize;	/* Usercopy region size */
+	unsigned int		useroffset;	/* Usercopy region offset */
+	unsigned int		usersize;	/* Usercopy region size */
 
 	struct percpu_counter	*orphan_count;
 
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index bcf4daccd6be..711372845945 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -20,7 +20,7 @@
 	EM( MR_SYSCALL,		"syscall_or_cpuset")		\
 	EM( MR_MEMPOLICY_MBIND,	"mempolicy_mbind")		\
 	EM( MR_NUMA_MISPLACED,	"numa_misplaced")		\
-	EMe(MR_CMA,		"cma")
+	EMe(MR_CONTIG_RANGE,	"contig_range")
 
 /*
  * First define the enums in the above macros to be exported to userspace
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index e0b8b9173e1c..a1cb91342231 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -78,26 +78,29 @@ TRACE_EVENT(mm_vmscan_kswapd_wake,
 
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
-	TP_PROTO(int nid, int zid, int order),
+	TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags),
 
-	TP_ARGS(nid, zid, order),
+	TP_ARGS(nid, zid, order, gfp_flags),
 
 	TP_STRUCT__entry(
-		__field(	int,		nid	)
-		__field(	int,		zid	)
-		__field(	int,		order	)
+		__field(	int,	nid		)
+		__field(	int,	zid		)
+		__field(	int,	order		)
+		__field(	gfp_t,	gfp_flags	)
 	),
 
 	TP_fast_assign(
 		__entry->nid		= nid;
 		__entry->zid		= zid;
 		__entry->order		= order;
+		__entry->gfp_flags	= gfp_flags;
 	),
 
-	TP_printk("nid=%d zid=%d order=%d",
+	TP_printk("nid=%d zid=%d order=%d gfp_flags=%s",
 		__entry->nid,
 		__entry->zid,
-		__entry->order)
+		__entry->order,
+		show_gfp_flags(__entry->gfp_flags))
 );
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
@@ -343,15 +346,9 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 
 	TP_PROTO(int nid,
 		unsigned long nr_scanned, unsigned long nr_reclaimed,
-		unsigned long nr_dirty, unsigned long nr_writeback,
-		unsigned long nr_congested, unsigned long nr_immediate,
-		unsigned long nr_activate, unsigned long nr_ref_keep,
-		unsigned long nr_unmap_fail,
-		int priority, int file),
+		struct reclaim_stat *stat, int priority, int file),
 
-	TP_ARGS(nid, nr_scanned, nr_reclaimed, nr_dirty, nr_writeback,
-		nr_congested, nr_immediate, nr_activate, nr_ref_keep,
-		nr_unmap_fail, priority, file),
+	TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, priority, file),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
@@ -372,13 +369,13 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		__entry->nid = nid;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_reclaimed = nr_reclaimed;
-		__entry->nr_dirty = nr_dirty;
-		__entry->nr_writeback = nr_writeback;
-		__entry->nr_congested = nr_congested;
-		__entry->nr_immediate = nr_immediate;
-		__entry->nr_activate = nr_activate;
-		__entry->nr_ref_keep = nr_ref_keep;
-		__entry->nr_unmap_fail = nr_unmap_fail;
+		__entry->nr_dirty = stat->nr_dirty;
+		__entry->nr_writeback = stat->nr_writeback;
+		__entry->nr_congested = stat->nr_congested;
+		__entry->nr_immediate = stat->nr_immediate;
+		__entry->nr_activate = stat->nr_activate;
+		__entry->nr_ref_keep = stat->nr_ref_keep;
+		__entry->nr_unmap_fail = stat->nr_unmap_fail;
 		__entry->priority = priority;
 		__entry->reclaim_flags = trace_shrink_flags(file);
 	),
diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h
index 5d5ab81dc9be..e4a0d9a9a9e8 100644
--- a/include/uapi/linux/msg.h
+++ b/include/uapi/linux/msg.h
@@ -7,6 +7,7 @@
 /* ipcs ctl commands */
 #define MSG_STAT 11
 #define MSG_INFO 12
+#define MSG_STAT_ANY 13
 
 /* msgrcv options */
 #define MSG_NOERROR     010000  /* no error if message is too big */
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index af5f8c2df87a..3165863aa187 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -207,4 +207,8 @@ struct prctl_mm_map {
 # define PR_SVE_VL_LEN_MASK		0xffff
 # define PR_SVE_VL_INHERIT		(1 << 17) /* inherit across exec */
 
+/* Process-based variant of PDEATHSIG */
+#define PR_SET_PDEATHSIG_PROC		48
+#define PR_GET_PDEATHSIG_PROC		49
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h
index 9c3e745b0656..39a1876f039e 100644
--- a/include/uapi/linux/sem.h
+++ b/include/uapi/linux/sem.h
@@ -19,6 +19,7 @@
 /* ipcs ctl cmds */
 #define SEM_STAT 18
 #define SEM_INFO 19
+#define SEM_STAT_ANY 20
 
 /* Obsolete, used only for backwards compatibility and libc5 compiles */
 struct semid_ds {
diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h
index 4de12a39b075..dde1344f047c 100644
--- a/include/uapi/linux/shm.h
+++ b/include/uapi/linux/shm.h
@@ -83,8 +83,9 @@ struct shmid_ds {
 #define SHM_UNLOCK 	12
 
 /* ipcs ctl commands */
-#define SHM_STAT 	13
-#define SHM_INFO 	14
+#define SHM_STAT	13
+#define SHM_INFO	14
+#define SHM_STAT_ANY    15
 
 /* Obsolete, used only for backwards compatibility */
 struct	shminfo {
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 12c159824c7b..035a5f0ab26b 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -255,7 +255,7 @@ int __init rd_load_image(char *from)
 		nblocks, ((nblocks-1)/devblocks)+1, nblocks>devblocks ? "s" : "");
 	for (i = 0, disk = 1; i < nblocks; i++) {
 		if (i && (i % devblocks == 0)) {
-			printk("done disk #%d.\n", disk++);
+			pr_cont("done disk #%d.\n", disk++);
 			rotate = 0;
 			if (ksys_close(in_fd)) {
 				printk("Error closing the disk.\n");
@@ -278,7 +278,7 @@ int __init rd_load_image(char *from)
 		}
 #endif
 	}
-	printk("done.\n");
+	pr_cont("done.\n");
 
 successful_load:
 	res = 1;
diff --git a/init/main.c b/init/main.c
index e4a3160991ea..67e2daa4ebc8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -51,6 +51,7 @@
 #include <linux/taskstats_kern.h>
 #include <linux/delayacct.h>
 #include <linux/unistd.h>
+#include <linux/utsname.h>
 #include <linux/rmap.h>
 #include <linux/mempolicy.h>
 #include <linux/key.h>
@@ -689,6 +690,7 @@ asmlinkage __visible void __init start_kernel(void)
 	cred_init();
 	fork_init();
 	proc_caches_init();
+	uts_ns_init();
 	buffer_init();
 	key_init();
 	security_init();
@@ -696,6 +698,7 @@ asmlinkage __visible void __init start_kernel(void)
 	vfs_caches_init();
 	pagecache_init();
 	signals_init();
+	seq_file_init();
 	proc_root_init();
 	nsfs_init();
 	cpuset_init();
diff --git a/ipc/msg.c b/ipc/msg.c
index 9de48065c1ac..599726f72706 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -488,14 +488,14 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid,
 	memset(p, 0, sizeof(*p));
 
 	rcu_read_lock();
-	if (cmd == MSG_STAT) {
+	if (cmd == MSG_STAT || cmd == MSG_STAT_ANY) {
 		msq = msq_obtain_object(ns, msqid);
 		if (IS_ERR(msq)) {
 			err = PTR_ERR(msq);
 			goto out_unlock;
 		}
 		id = msq->q_perm.id;
-	} else {
+	} else { /* IPC_STAT */
 		msq = msq_obtain_object_check(ns, msqid);
 		if (IS_ERR(msq)) {
 			err = PTR_ERR(msq);
@@ -503,9 +503,14 @@ static int msgctl_stat(struct ipc_namespace *ns, int msqid,
 		}
 	}
 
-	err = -EACCES;
-	if (ipcperms(ns, &msq->q_perm, S_IRUGO))
-		goto out_unlock;
+	/* see comment for SHM_STAT_ANY */
+	if (cmd == MSG_STAT_ANY)
+		audit_ipc_obj(&msq->q_perm);
+	else {
+		err = -EACCES;
+		if (ipcperms(ns, &msq->q_perm, S_IRUGO))
+			goto out_unlock;
+	}
 
 	err = security_msg_queue_msgctl(msq, cmd);
 	if (err)
@@ -563,6 +568,7 @@ long ksys_msgctl(int msqid, int cmd, struct msqid_ds __user *buf)
 		return err;
 	}
 	case MSG_STAT:	/* msqid is an index rather than a msg queue id */
+	case MSG_STAT_ANY:
 	case IPC_STAT:
 		err = msgctl_stat(ns, msqid, cmd, &msqid64);
 		if (err < 0)
@@ -681,6 +687,7 @@ long compat_ksys_msgctl(int msqid, int cmd, void __user *uptr)
 	}
 	case IPC_STAT:
 	case MSG_STAT:
+	case MSG_STAT_ANY:
 		err = msgctl_stat(ns, msqid, cmd, &msqid64);
 		if (err < 0)
 			return err;
diff --git a/ipc/sem.c b/ipc/sem.c
index 1cf56279a84c..b73f18f54ab5 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -1195,14 +1195,14 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
 	memset(semid64, 0, sizeof(*semid64));
 
 	rcu_read_lock();
-	if (cmd == SEM_STAT) {
+	if (cmd == SEM_STAT || cmd == SEM_STAT_ANY) {
 		sma = sem_obtain_object(ns, semid);
 		if (IS_ERR(sma)) {
 			err = PTR_ERR(sma);
 			goto out_unlock;
 		}
 		id = sma->sem_perm.id;
-	} else {
+	} else { /* IPC_STAT */
 		sma = sem_obtain_object_check(ns, semid);
 		if (IS_ERR(sma)) {
 			err = PTR_ERR(sma);
@@ -1210,9 +1210,14 @@ static int semctl_stat(struct ipc_namespace *ns, int semid,
 		}
 	}
 
-	err = -EACCES;
-	if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
-		goto out_unlock;
+	/* see comment for SHM_STAT_ANY */
+	if (cmd == SEM_STAT_ANY)
+		audit_ipc_obj(&sma->sem_perm);
+	else {
+		err = -EACCES;
+		if (ipcperms(ns, &sma->sem_perm, S_IRUGO))
+			goto out_unlock;
+	}
 
 	err = security_sem_semctl(sma, cmd);
 	if (err)
@@ -1601,6 +1606,7 @@ long ksys_semctl(int semid, int semnum, int cmd, unsigned long arg)
 		return semctl_info(ns, semid, cmd, p);
 	case IPC_STAT:
 	case SEM_STAT:
+	case SEM_STAT_ANY:
 		err = semctl_stat(ns, semid, cmd, &semid64);
 		if (err < 0)
 			return err;
@@ -1707,6 +1713,7 @@ long compat_ksys_semctl(int semid, int semnum, int cmd, int arg)
 		return semctl_info(ns, semid, cmd, p);
 	case IPC_STAT:
 	case SEM_STAT:
+	case SEM_STAT_ANY:
 		err = semctl_stat(ns, semid, cmd, &semid64);
 		if (err < 0)
 			return err;
diff --git a/ipc/shm.c b/ipc/shm.c
index c38c8425a89e..181df4a2fccf 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -391,7 +391,7 @@ static int shm_split(struct vm_area_struct *vma, unsigned long addr)
 	struct file *file = vma->vm_file;
 	struct shm_file_data *sfd = shm_file_data(file);
 
-	if (sfd->vm_ops && sfd->vm_ops->split)
+	if (sfd->vm_ops->split)
 		return sfd->vm_ops->split(vma, addr);
 
 	return 0;
@@ -932,14 +932,14 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid,
 	memset(tbuf, 0, sizeof(*tbuf));
 
 	rcu_read_lock();
-	if (cmd == SHM_STAT) {
+	if (cmd == SHM_STAT || cmd == SHM_STAT_ANY) {
 		shp = shm_obtain_object(ns, shmid);
 		if (IS_ERR(shp)) {
 			err = PTR_ERR(shp);
 			goto out_unlock;
 		}
 		id = shp->shm_perm.id;
-	} else {
+	} else { /* IPC_STAT */
 		shp = shm_obtain_object_check(ns, shmid);
 		if (IS_ERR(shp)) {
 			err = PTR_ERR(shp);
@@ -947,9 +947,20 @@ static int shmctl_stat(struct ipc_namespace *ns, int shmid,
 		}
 	}
 
-	err = -EACCES;
-	if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
-		goto out_unlock;
+	/*
+	 * Semantically SHM_STAT_ANY ought to be identical to
+	 * that functionality provided by the /proc/sysvipc/
+	 * interface. As such, only audit these calls and
+	 * do not do traditional S_IRUGO permission checks on
+	 * the ipc object.
+	 */
+	if (cmd == SHM_STAT_ANY)
+		audit_ipc_obj(&shp->shm_perm);
+	else {
+		err = -EACCES;
+		if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
+			goto out_unlock;
+	}
 
 	err = security_shm_shmctl(shp, cmd);
 	if (err)
@@ -1089,6 +1100,7 @@ long ksys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
 		return err;
 	}
 	case SHM_STAT:
+	case SHM_STAT_ANY:
 	case IPC_STAT: {
 		err = shmctl_stat(ns, shmid, cmd, &sem64);
 		if (err < 0)
@@ -1267,6 +1279,7 @@ long compat_ksys_shmctl(int shmid, int cmd, void __user *uptr)
 		return err;
 	}
 	case IPC_STAT:
+	case SHM_STAT_ANY:
 	case SHM_STAT:
 		err = shmctl_stat(ns, shmid, cmd, &sem64);
 		if (err < 0)
diff --git a/ipc/util.c b/ipc/util.c
index 4ed5a17dd06f..7ab5c5a1a62b 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -89,6 +89,7 @@ static int __init ipc_init(void)
 {
 	int err_sem, err_msg;
 
+	proc_mkdir("sysvipc", NULL);
 	err_sem = sem_init();
 	WARN(err_sem, "ipc: sysv sem_init failed: %d\n", err_sem);
 	err_msg = msg_init();
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b07335be7164..b3232bda8f19 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1732,6 +1732,9 @@ static int parse_cgroup_root_flags(char *data, unsigned int *root_flags)
 		if (!strcmp(token, "nsdelegate")) {
 			*root_flags |= CGRP_ROOT_NS_DELEGATE;
 			continue;
+		} else if (!strcmp(token, "groupoom")) {
+			*root_flags |= CGRP_GROUP_OOM;
+			continue;
 		}
 
 		pr_err("cgroup2: unknown option \"%s\"\n", token);
@@ -1748,6 +1751,11 @@ static void apply_cgroup_root_flags(unsigned int root_flags)
 			cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE;
 		else
 			cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE;
+
+		if (root_flags & CGRP_GROUP_OOM)
+			cgrp_dfl_root.flags |= CGRP_GROUP_OOM;
+		else
+			cgrp_dfl_root.flags &= ~CGRP_GROUP_OOM;
 	}
 }
 
@@ -1755,6 +1763,8 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root
 {
 	if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE)
 		seq_puts(seq, ",nsdelegate");
+	if (cgrp_dfl_root.flags & CGRP_GROUP_OOM)
+		seq_puts(seq, ",groupoom");
 	return 0;
 }
 
@@ -5915,7 +5925,8 @@ static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate);
 static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr,
 			     char *buf)
 {
-	return snprintf(buf, PAGE_SIZE, "nsdelegate\n");
+	return snprintf(buf, PAGE_SIZE, "nsdelegate\n"
+					"groupoom\n");
 }
 static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features);
 
diff --git a/kernel/cred.c b/kernel/cred.c
index ecf03657e71c..0192a94670e1 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -448,6 +448,7 @@ int commit_creds(struct cred *new)
 		if (task->mm)
 			set_dumpable(task->mm, suid_dumpable);
 		task->pdeath_signal = 0;
+		task->signal->pdeath_signal_proc = 0;
 		smp_wmb();
 	}
 
diff --git a/kernel/exit.c b/kernel/exit.c
index c3c7ac560114..63f7cea6456e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -635,6 +635,10 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
+	if (p->signal->pdeath_signal_proc)
+		group_send_sig_info(p->signal->pdeath_signal_proc,
+				    SEND_SIG_NOINFO, p);
+
 	/* We don't want people slaying init. */
 	p->exit_signal = SIGCHLD;
 
diff --git a/kernel/fork.c b/kernel/fork.c
index f71b67dc156d..3398037de1cb 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -216,10 +216,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
 		if (!s)
 			continue;
 
-#ifdef CONFIG_DEBUG_KMEMLEAK
 		/* Clear stale pointers from reused stack. */
 		memset(s->addr, 0, THREAD_SIZE);
-#endif
+
 		tsk->stack_vm_area = s;
 		return s->addr;
 	}
@@ -595,6 +594,8 @@ static void check_mm(struct mm_struct *mm)
 void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
+	WARN_ON_ONCE(mm == current->mm);
+	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	hmm_mm_destroy(mm);
@@ -1469,6 +1470,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 	mutex_init(&sig->cred_guard_mutex);
 
+	sig->pdeath_signal_proc = current->signal->pdeath_signal_proc;
+
 	return 0;
 }
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 9d833d913c84..bdcffaef15a3 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -34,7 +34,8 @@
 #define PANIC_BLINK_SPD 18
 
 int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
-static unsigned long tainted_mask;
+static unsigned long tainted_mask =
+	IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
 static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
@@ -308,52 +309,40 @@ EXPORT_SYMBOL(panic);
  * is being removed anyway.
  */
 const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
-	{ 'P', 'G', true },	/* TAINT_PROPRIETARY_MODULE */
-	{ 'F', ' ', true },	/* TAINT_FORCED_MODULE */
-	{ 'S', ' ', false },	/* TAINT_CPU_OUT_OF_SPEC */
-	{ 'R', ' ', false },	/* TAINT_FORCED_RMMOD */
-	{ 'M', ' ', false },	/* TAINT_MACHINE_CHECK */
-	{ 'B', ' ', false },	/* TAINT_BAD_PAGE */
-	{ 'U', ' ', false },	/* TAINT_USER */
-	{ 'D', ' ', false },	/* TAINT_DIE */
-	{ 'A', ' ', false },	/* TAINT_OVERRIDDEN_ACPI_TABLE */
-	{ 'W', ' ', false },	/* TAINT_WARN */
-	{ 'C', ' ', true },	/* TAINT_CRAP */
-	{ 'I', ' ', false },	/* TAINT_FIRMWARE_WORKAROUND */
-	{ 'O', ' ', true },	/* TAINT_OOT_MODULE */
-	{ 'E', ' ', true },	/* TAINT_UNSIGNED_MODULE */
-	{ 'L', ' ', false },	/* TAINT_SOFTLOCKUP */
-	{ 'K', ' ', true },	/* TAINT_LIVEPATCH */
-	{ 'X', ' ', true },	/* TAINT_AUX */
+	[ TAINT_PROPRIETARY_MODULE ]	= { 'P', 'G', true },
+	[ TAINT_FORCED_MODULE ]		= { 'F', ' ', true },
+	[ TAINT_CPU_OUT_OF_SPEC ]	= { 'S', ' ', false },
+	[ TAINT_FORCED_RMMOD ]		= { 'R', ' ', false },
+	[ TAINT_MACHINE_CHECK ]		= { 'M', ' ', false },
+	[ TAINT_BAD_PAGE ]		= { 'B', ' ', false },
+	[ TAINT_USER ]			= { 'U', ' ', false },
+	[ TAINT_DIE ]			= { 'D', ' ', false },
+	[ TAINT_OVERRIDDEN_ACPI_TABLE ]	= { 'A', ' ', false },
+	[ TAINT_WARN ]			= { 'W', ' ', false },
+	[ TAINT_CRAP ]			= { 'C', ' ', true },
+	[ TAINT_FIRMWARE_WORKAROUND ]	= { 'I', ' ', false },
+	[ TAINT_OOT_MODULE ]		= { 'O', ' ', true },
+	[ TAINT_UNSIGNED_MODULE ]	= { 'E', ' ', true },
+	[ TAINT_SOFTLOCKUP ]		= { 'L', ' ', false },
+	[ TAINT_LIVEPATCH ]		= { 'K', ' ', true },
+	[ TAINT_AUX ]			= { 'X', ' ', true },
+	[ TAINT_RANDSTRUCT ]		= { 'T', ' ', true },
 };
 
 /**
- *	print_tainted - return a string to represent the kernel taint state.
+ * print_tainted - return a string to represent the kernel taint state.
  *
- *  'P' - Proprietary module has been loaded.
- *  'F' - Module has been forcibly loaded.
- *  'S' - SMP with CPUs not designed for SMP.
- *  'R' - User forced a module unload.
- *  'M' - System experienced a machine check exception.
- *  'B' - System has hit bad_page.
- *  'U' - Userspace-defined naughtiness.
- *  'D' - Kernel has oopsed before
- *  'A' - ACPI table overridden.
- *  'W' - Taint on warning.
- *  'C' - modules from drivers/staging are loaded.
- *  'I' - Working around severe firmware bug.
- *  'O' - Out-of-tree module has been loaded.
- *  'E' - Unsigned module has been loaded.
- *  'L' - A soft lockup has previously occurred.
- *  'K' - Kernel has been live patched.
- *  'X' - Auxiliary taint, for distros' use.
+ * For individual taint flag meanings, see Documentation/sysctl/kernel.txt
  *
- *	The string is overwritten by the next call to print_tainted().
+ * The string is overwritten by the next call to print_tainted(),
+ * but is always NULL terminated.
  */
 const char *print_tainted(void)
 {
 	static char buf[TAINT_FLAGS_COUNT + sizeof("Tainted: ")];
 
+	BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT);
+
 	if (tainted_mask) {
 		char *s;
 		int i;
diff --git a/kernel/params.c b/kernel/params.c
index 2c08c4aa376b..8ac751c938f8 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -112,8 +112,8 @@ static bool param_check_unsafe(const struct kernel_param *kp,
 			       const char *doing)
 {
 	if (kp->flags & KERNEL_PARAM_FL_UNSAFE) {
-		pr_warn("Setting dangerous option %s - tainting kernel\n",
-			kp->name);
+		pr_notice("Setting dangerous option %s - tainting kernel\n",
+			  kp->name);
 		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
 	}
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 28b68995a417..e8afd6086f23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5560,6 +5560,7 @@ void idle_task_exit(void)
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
+		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
 	mmdrop(mm);
diff --git a/kernel/sys.c b/kernel/sys.c
index ad692183dfe9..f1b4c598f810 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2265,6 +2265,17 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 	case PR_GET_PDEATHSIG:
 		error = put_user(me->pdeath_signal, (int __user *)arg2);
 		break;
+	case PR_SET_PDEATHSIG_PROC:
+		if (!valid_signal(arg2)) {
+			error = -EINVAL;
+			break;
+		}
+		me->signal->pdeath_signal_proc = arg2;
+		break;
+	case PR_GET_PDEATHSIG_PROC:
+		error = put_user(me->signal->pdeath_signal_proc,
+				 (int __user *)arg2);
+		break;
 	case PR_GET_DUMPABLE:
 		error = get_dumpable(me->mm);
 		break;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bdf7090b106d..6a78cf70761d 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1340,7 +1340,7 @@ static struct ctl_table vm_table[] = {
 	{
 		.procname	= "dirtytime_expire_seconds",
 		.data		= &dirtytime_expire_interval,
-		.maxlen		= sizeof(dirty_expire_interval),
+		.maxlen		= sizeof(dirtytime_expire_interval),
 		.mode		= 0644,
 		.proc_handler	= dirtytime_interval_handler,
 		.extra1		= &zero,
@@ -2511,6 +2511,15 @@ static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write,
 }
 #endif
 
+/**
+ * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure
+ * @min: pointer to minimum allowable value
+ * @max: pointer to maximum allowable value
+ *
+ * The do_proc_dointvec_minmax_conv_param structure provides the
+ * minimum and maximum values for doing range checking for those sysctl
+ * parameters that use the proc_dointvec_minmax() handler.
+ */
 struct do_proc_dointvec_minmax_conv_param {
 	int *min;
 	int *max;
@@ -2554,7 +2563,7 @@ static int do_proc_dointvec_minmax_conv(bool *negp, unsigned long *lvalp,
  * This routine will ensure the values are within the range specified by
  * table->extra1 (min) and table->extra2 (max).
  *
- * Returns 0 on success.
+ * Returns 0 on success or -EINVAL on write when the range check fails.
  */
 int proc_dointvec_minmax(struct ctl_table *table, int write,
 		  void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -2567,6 +2576,15 @@ int proc_dointvec_minmax(struct ctl_table *table, int write,
 				do_proc_dointvec_minmax_conv, &param);
 }
 
+/**
+ * struct do_proc_douintvec_minmax_conv_param - proc_douintvec_minmax() range checking structure
+ * @min: pointer to minimum allowable value
+ * @max: pointer to maximum allowable value
+ *
+ * The do_proc_douintvec_minmax_conv_param structure provides the
+ * minimum and maximum values for doing range checking for those sysctl
+ * parameters that use the proc_douintvec_minmax() handler.
+ */
 struct do_proc_douintvec_minmax_conv_param {
 	unsigned int *min;
 	unsigned int *max;
@@ -2614,7 +2632,7 @@ static int do_proc_douintvec_minmax_conv(unsigned long *lvalp,
  * check for UINT_MAX to avoid having to support wrap around uses from
  * userspace.
  *
- * Returns 0 on success.
+ * Returns 0 on success or -ERANGE on write when the range check fails.
  */
 int proc_douintvec_minmax(struct ctl_table *table, int write,
 			  void __user *buffer, size_t *lenp, loff_t *ppos)
diff --git a/kernel/ucount.c b/kernel/ucount.c
index b4eeee03934f..f48d1b6376a4 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/cred.h>
 #include <linux/hash.h>
+#include <linux/kmemleak.h>
 #include <linux/user_namespace.h>
 
 #define UCOUNTS_HASHTABLE_BITS 10
diff --git a/kernel/utsname.c b/kernel/utsname.c
index 913fe4336d2b..dcd6be1996fe 100644
--- a/kernel/utsname.c
+++ b/kernel/utsname.c
@@ -19,6 +19,8 @@
 #include <linux/proc_ns.h>
 #include <linux/sched/task.h>
 
+static struct kmem_cache *uts_ns_cache __ro_after_init;
+
 static struct ucounts *inc_uts_namespaces(struct user_namespace *ns)
 {
 	return inc_ucount(ns, current_euid(), UCOUNT_UTS_NAMESPACES);
@@ -33,7 +35,7 @@ static struct uts_namespace *create_uts_ns(void)
 {
 	struct uts_namespace *uts_ns;
 
-	uts_ns = kmalloc(sizeof(struct uts_namespace), GFP_KERNEL);
+	uts_ns = kmem_cache_alloc(uts_ns_cache, GFP_KERNEL);
 	if (uts_ns)
 		kref_init(&uts_ns->kref);
 	return uts_ns;
@@ -42,7 +44,7 @@ static struct uts_namespace *create_uts_ns(void)
 /*
  * Clone a new ns copying an original utsname, setting refcount to 1
  * @old_ns: namespace to clone
- * Return ERR_PTR(-ENOMEM) on error (failure to kmalloc), new ns otherwise
+ * Return ERR_PTR(-ENOMEM) on error (failure to allocate), new ns otherwise
  */
 static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 					  struct uts_namespace *old_ns)
@@ -75,7 +77,7 @@ static struct uts_namespace *clone_uts_ns(struct user_namespace *user_ns,
 	return ns;
 
 fail_free:
-	kfree(ns);
+	kmem_cache_free(uts_ns_cache, ns);
 fail_dec:
 	dec_uts_namespaces(ucounts);
 fail:
@@ -113,7 +115,7 @@ void free_uts_ns(struct kref *kref)
 	dec_uts_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	ns_free_inum(&ns->ns);
-	kfree(ns);
+	kmem_cache_free(uts_ns_cache, ns);
 }
 
 static inline struct uts_namespace *to_uts_ns(struct ns_common *ns)
@@ -169,3 +171,13 @@ const struct proc_ns_operations utsns_operations = {
 	.install	= utsns_install,
 	.owner		= utsns_owner,
 };
+
+void __init uts_ns_init(void)
+{
+	uts_ns_cache = kmem_cache_create_usercopy(
+			"uts_namespace", sizeof(struct uts_namespace), 0,
+			SLAB_PANIC|SLAB_ACCOUNT,
+			offsetof(struct uts_namespace, name),
+			sizeof_field(struct uts_namespace, name),
+			NULL);
+}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 51c6bf0d93c6..c40c7b734cd1 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -800,6 +800,30 @@ config SOFTLOCKUP_DETECTOR
 	  chance to run.  The current stack trace is displayed upon
 	  detection and the system will stay locked up.
 
+config BOOTPARAM_SOFTLOCKUP_PANIC
+	bool "Panic (Reboot) On Soft Lockups"
+	depends on SOFTLOCKUP_DETECTOR
+	help
+	  Say Y here to enable the kernel to panic on "soft lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode for more than 20 seconds (configurable using the watchdog_thresh
+	  sysctl), without giving other tasks a chance to run.
+
+	  The panic can be used in combination with panic_timeout,
+	  to cause the system to reboot automatically after a
+	  lockup has been detected. This feature is useful for
+	  high-availability systems that have uptime guarantees and
+	  where a lockup must be resolved ASAP.
+
+	  Say N if unsure.
+
+config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
+	int
+	depends on SOFTLOCKUP_DETECTOR
+	range 0 1
+	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
+	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
+
 config HARDLOCKUP_DETECTOR_PERF
 	bool
 	select SOFTLOCKUP_DETECTOR
@@ -849,30 +873,6 @@ config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
 	default 0 if !BOOTPARAM_HARDLOCKUP_PANIC
 	default 1 if BOOTPARAM_HARDLOCKUP_PANIC
 
-config BOOTPARAM_SOFTLOCKUP_PANIC
-	bool "Panic (Reboot) On Soft Lockups"
-	depends on SOFTLOCKUP_DETECTOR
-	help
-	  Say Y here to enable the kernel to panic on "soft lockups",
-	  which are bugs that cause the kernel to loop in kernel
-	  mode for more than 20 seconds (configurable using the watchdog_thresh
-	  sysctl), without giving other tasks a chance to run.
-
-	  The panic can be used in combination with panic_timeout,
-	  to cause the system to reboot automatically after a
-	  lockup has been detected. This feature is useful for
-	  high-availability systems that have uptime guarantees and
-	  where a lockup must be resolved ASAP.
-
-	  Say N if unsure.
-
-config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
-	int
-	depends on SOFTLOCKUP_DETECTOR
-	range 0 1
-	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
-	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
-
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan
index a669c193b878..19d42ea75ec2 100644
--- a/lib/Kconfig.ubsan
+++ b/lib/Kconfig.ubsan
@@ -46,3 +46,10 @@ config UBSAN_NULL
 	help
 	  This option enables detection of memory accesses via a
 	  null pointer.
+
+config TEST_UBSAN
+	tristate "Module for testing for undefined behavior detection"
+	depends on m && UBSAN
+	help
+	  This is a test module for UBSAN.
+	  It triggers various undefined behavior, and detect it.
diff --git a/lib/Makefile b/lib/Makefile
index 8c143732efd0..384713ff70d3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -53,6 +53,9 @@ obj-$(CONFIG_TEST_FIRMWARE) += test_firmware.o
 obj-$(CONFIG_TEST_SYSCTL) += test_sysctl.o
 obj-$(CONFIG_TEST_HASH) += test_hash.o test_siphash.o
 obj-$(CONFIG_TEST_KASAN) += test_kasan.o
+CFLAGS_test_kasan.o += -fno-builtin
+obj-$(CONFIG_TEST_UBSAN) += test_ubsan.o
+UBSAN_SANITIZE_test_ubsan.o := y
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 obj-$(CONFIG_TEST_LIST_SORT) += test_list_sort.o
 obj-$(CONFIG_TEST_LKM) += test_module.o
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 0ec3f257ffdf..3e3becb836a6 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -31,9 +31,10 @@
 	 * of nroots is 8. So the necessary stack size will be about
 	 * 220 bytes max.
 	 */
-	uint16_t lambda[nroots + 1], syn[nroots];
-	uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1];
-	uint16_t root[nroots], reg[nroots + 1], loc[nroots];
+	uint16_t lambda[RS_MAX_ROOTS + 1], syn[RS_MAX_ROOTS];
+	uint16_t b[RS_MAX_ROOTS + 1], t[RS_MAX_ROOTS + 1];
+	uint16_t omega[RS_MAX_ROOTS + 1], root[RS_MAX_ROOTS];
+	uint16_t reg[RS_MAX_ROOTS + 1], loc[RS_MAX_ROOTS];
 	int count = 0;
 	uint16_t msk = (uint16_t) rs->nn;
 
diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index 06d04cfa9339..3e218e70ac2e 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -51,6 +51,9 @@ static LIST_HEAD (rslist);
 /* Protection for the list */
 static DEFINE_MUTEX(rslistlock);
 
+/* Ultimately controls the upper bounds of the on-stack buffers. */
+#define RS_MAX_ROOTS	24
+
 /**
  * rs_init - Initialize a Reed-Solomon codec
  * @symsize:	symbol size, bits (1-8)
@@ -210,7 +213,7 @@ static struct rs_control *init_rs_internal(int symsize, int gfpoly,
     		return NULL;
 	if (prim <= 0 || prim >= (1<<symsize))
     		return NULL;
-	if (nroots < 0 || nroots >= (1<<symsize))
+	if (nroots < 0 || nroots >= (1<<symsize) || nroots > RS_MAX_ROOTS)
 		return NULL;
 
 	mutex_lock(&rslistlock);
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index b3f235baa05d..756f20ad03db 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -292,15 +292,17 @@ static void __init test_bitmap_parselist(void)
 	}
 }
 
+#define EXP_BYTES	(sizeof(exp) * 8)
+
 static void __init test_bitmap_arr32(void)
 {
-	unsigned int nbits, next_bit, len = sizeof(exp) * 8;
+	unsigned int nbits, next_bit;
 	u32 arr[sizeof(exp) / 4];
-	DECLARE_BITMAP(bmap2, len);
+	DECLARE_BITMAP(bmap2, EXP_BYTES);
 
 	memset(arr, 0xa5, sizeof(arr));
 
-	for (nbits = 0; nbits < len; ++nbits) {
+	for (nbits = 0; nbits < EXP_BYTES; ++nbits) {
 		bitmap_to_arr32(arr, exp, nbits);
 		bitmap_from_arr32(bmap2, arr, nbits);
 		expect_eq_bitmap(bmap2, exp, nbits);
@@ -312,7 +314,7 @@ static void __init test_bitmap_arr32(void)
 				" tail is not safely cleared: %d\n",
 				nbits, next_bit);
 
-		if (nbits < len - 32)
+		if (nbits < EXP_BYTES - 32)
 			expect_eq_uint(arr[DIV_ROUND_UP(nbits, 32)],
 								0xa5a5a5a5);
 	}
diff --git a/lib/test_firmware.c b/lib/test_firmware.c
index 078a61480573..cee000ac54d8 100644
--- a/lib/test_firmware.c
+++ b/lib/test_firmware.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/vmalloc.h>
 
 #define TEST_FIRMWARE_NAME	"test-firmware.bin"
 #define TEST_FIRMWARE_NUM_REQS	4
diff --git a/lib/test_kasan.c b/lib/test_kasan.c
index 98854a64b014..ec657105edbf 100644
--- a/lib/test_kasan.c
+++ b/lib/test_kasan.c
@@ -567,7 +567,15 @@ static noinline void __init kmem_cache_invalid_free(void)
 		return;
 	}
 
+	/* Trigger invalid free, the object doesn't get freed */
 	kmem_cache_free(cache, p + 1);
+
+	/*
+	 * Properly free the object to prevent the "Objects remaining in
+	 * test_cache on __kmem_cache_shutdown" BUG failure.
+	 */
+	kmem_cache_free(cache, p);
+
 	kmem_cache_destroy(cache);
 }
 
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
new file mode 100644
index 000000000000..280f4979d00e
--- /dev/null
+++ b/lib/test_ubsan.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+typedef void(*test_ubsan_fp)(void);
+
+static void test_ubsan_add_overflow(void)
+{
+	volatile int val = INT_MAX;
+
+	val += 2;
+}
+
+static void test_ubsan_sub_overflow(void)
+{
+	volatile int val = INT_MIN;
+	volatile int val2 = 2;
+
+	val -= val2;
+}
+
+static void test_ubsan_mul_overflow(void)
+{
+	volatile int val = INT_MAX / 2;
+
+	val *= 3;
+}
+
+static void test_ubsan_negate_overflow(void)
+{
+	volatile int val = INT_MIN;
+
+	val = -val;
+}
+
+static void test_ubsan_divrem_overflow(void)
+{
+	volatile int val = 16;
+	volatile int val2 = 0;
+
+	val /= val2;
+}
+
+static void test_ubsan_vla_bound_not_positive(void)
+{
+	volatile int size = -1;
+	char buf[size];
+
+	(void)buf;
+}
+
+static void test_ubsan_shift_out_of_bounds(void)
+{
+	volatile int val = -1;
+	int val2 = 10;
+
+	val2 <<= val;
+}
+
+static void test_ubsan_out_of_bounds(void)
+{
+	volatile int i = 4, j = 5;
+	volatile int arr[i];
+
+	arr[j] = i;
+}
+
+static void test_ubsan_load_invalid_value(void)
+{
+	volatile char *dst, *src;
+	bool val, val2, *ptr;
+	char c = 4;
+
+	dst = (char *)&val;
+	src = &c;
+	*dst = *src;
+
+	ptr = &val2;
+	val2 = val;
+}
+
+static void test_ubsan_null_ptr_deref(void)
+{
+	volatile int *ptr = NULL;
+	int val;
+
+	val = *ptr;
+}
+
+static void test_ubsan_misaligned_access(void)
+{
+	volatile char arr[5] __aligned(4) = {1, 2, 3, 4, 5};
+	volatile int *ptr, val = 6;
+
+	ptr = (int *)(arr + 1);
+	*ptr = val;
+}
+
+static void test_ubsan_object_size_mismatch(void)
+{
+	/* "((aligned(8)))" helps this not into be misaligned for ptr-access. */
+	volatile int val __aligned(8) = 4;
+	volatile long long *ptr, val2;
+
+	ptr = (long long *)&val;
+	val2 = *ptr;
+}
+
+static const test_ubsan_fp test_ubsan_array[] = {
+	test_ubsan_add_overflow,
+	test_ubsan_sub_overflow,
+	test_ubsan_mul_overflow,
+	test_ubsan_negate_overflow,
+	test_ubsan_divrem_overflow,
+	test_ubsan_vla_bound_not_positive,
+	test_ubsan_shift_out_of_bounds,
+	test_ubsan_out_of_bounds,
+	test_ubsan_load_invalid_value,
+	//test_ubsan_null_ptr_deref, /* exclude it because there is a crash */
+	test_ubsan_misaligned_access,
+	test_ubsan_object_size_mismatch,
+};
+
+static int __init test_ubsan_init(void)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(test_ubsan_array); i++)
+		test_ubsan_array[i]();
+
+	(void)test_ubsan_null_ptr_deref; /* to avoid unsed-function warning */
+	return 0;
+}
+module_init(test_ubsan_init);
+
+static void __exit test_ubsan_exit(void)
+{
+	/* do nothing */
+}
+module_exit(test_ubsan_exit);
+
+MODULE_AUTHOR("Jinbum Park <jinb.park7@gmail.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index d7a708f82559..3d83d8a5061f 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -336,7 +336,7 @@ char *put_dec(char *buf, unsigned long long n)
  *
  * If speed is not important, use snprintf(). It's easy to read the code.
  */
-int num_to_str(char *buf, int size, unsigned long long num)
+int num_to_str(char *buf, int size, unsigned long long num, unsigned int width)
 {
 	/* put_dec requires 2-byte alignment of the buffer. */
 	char tmp[sizeof(num) * 3] __aligned(2);
@@ -350,11 +350,21 @@ int num_to_str(char *buf, int size, unsigned long long num)
 		len = put_dec(tmp, num) - tmp;
 	}
 
-	if (len > size)
+	if (len > size || width > size)
 		return 0;
+
+	if (width > len) {
+		width = width - len;
+		for (idx = 0; idx < width; idx++)
+			buf[idx] = ' ';
+	} else {
+		width = 0;
+	}
+
 	for (idx = 0; idx < len; ++idx)
-		buf[idx] = tmp[len - idx - 1];
-	return len;
+		buf[idx + width] = tmp[len - idx - 1];
+
+	return len + width;
 }
 
 #define SIGN	1		/* unsigned/signed, must be 1 */
@@ -744,8 +754,8 @@ char *resource_string(char *buf, char *end, struct resource *res,
 #define FLAG_BUF_SIZE		(2 * sizeof(res->flags))
 #define DECODED_BUF_SIZE	sizeof("[mem - 64bit pref window disabled]")
 #define RAW_BUF_SIZE		sizeof("[mem - flags 0x]")
-	char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE,
-		     2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)];
+	char sym[const_max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE,
+			   2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)];
 
 	char *p = sym, *pend = sym + sizeof(sym);
 	int decode = (fmt[0] == 'R') ? 1 : 0;
diff --git a/mm/Makefile b/mm/Makefile
index e669f02c5a54..8716bdabe1e6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -37,7 +37,7 @@ obj-y			:= filemap.o mempool.o oom_kill.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o vmacache.o swap_slots.o \
+			   compaction.o vmacache.o \
 			   interval_tree.o list_lru.o workingset.o \
 			   debug.o $(mmu-y)
 
@@ -55,7 +55,7 @@ ifdef CONFIG_MMU
 endif
 obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 
-obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o swap_slots.o
 obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
@@ -105,3 +105,4 @@ obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o
 obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o
 obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o
 obj-$(CONFIG_HMM) += hmm.o
+obj-$(CONFIG_MEMFD_CREATE) += memfd.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d2984e9fcf08..2fc3f38e4c4f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -100,18 +100,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-
-static int bdi_debug_stats_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, bdi_debug_stats_show, inode->i_private);
-}
-
-static const struct file_operations bdi_debug_stats_fops = {
-	.open		= bdi_debug_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats);
 
 static int bdi_debug_register(struct backing_dev_info *bdi, const char *name)
 {
@@ -231,11 +220,46 @@ static ssize_t stable_pages_required_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
+static ssize_t strictlimit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int val;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &val);
+	if (ret < 0)
+		return ret;
+
+	switch (val) {
+	case 0:
+		bdi->capabilities &= ~BDI_CAP_STRICTLIMIT;
+		break;
+	case 1:
+		bdi->capabilities |= BDI_CAP_STRICTLIMIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return count;
+}
+static ssize_t strictlimit_show(struct device *dev,
+		struct device_attribute *attr, char *page)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return snprintf(page, PAGE_SIZE-1, "%d\n",
+			!!(bdi->capabilities & BDI_CAP_STRICTLIMIT));
+}
+static DEVICE_ATTR_RW(strictlimit);
+
 static struct attribute *bdi_dev_attrs[] = {
 	&dev_attr_read_ahead_kb.attr,
 	&dev_attr_min_ratio.attr,
 	&dev_attr_max_ratio.attr,
 	&dev_attr_stable_pages_required.attr,
+	&dev_attr_strictlimit.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(bdi_dev);
@@ -1031,23 +1055,18 @@ EXPORT_SYMBOL(congestion_wait);
 
 /**
  * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
- * @pgdat: A pgdat to check if it is heavily congested
  * @sync: SYNC or ASYNC IO
  * @timeout: timeout in jiffies
  *
- * In the event of a congested backing_dev (any backing_dev) and the given
- * @pgdat has experienced recent congestion, this waits for up to @timeout
- * jiffies for either a BDI to exit congestion of the given @sync queue
- * or a write to complete.
- *
- * In the absence of pgdat congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the event of a congested backing_dev (any backing_dev) this waits
+ * for up to @timeout jiffies for either a BDI to exit congestion of the
+ * given @sync queue or a write to complete.
  *
  * The return value is 0 if the sleep is for the full timeout. Otherwise,
  * it is the number of jiffies that were still remaining when the function
  * returned. return_value == timeout implies the function did not sleep.
  */
-long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
+long wait_iff_congested(int sync, long timeout)
 {
 	long ret;
 	unsigned long start = jiffies;
@@ -1055,12 +1074,10 @@ long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout)
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	/*
-	 * If there is no congestion, or heavy congestion is not being
-	 * encountered in the current pgdat, yield if necessary instead
+	 * If there is no congestion, yield if necessary instead
 	 * of sleeping on the congestion queue
 	 */
-	if (atomic_read(&nr_wb_congested[sync]) == 0 ||
-	    !test_bit(PGDAT_CONGESTED, &pgdat->flags)) {
+	if (atomic_read(&nr_wb_congested[sync]) == 0) {
 		cond_resched();
 
 		/* In case we scheduled, work out time remaining */
diff --git a/mm/cma.c b/mm/cma.c
index 0607729abf3b..aa40e6c7b042 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -35,9 +35,11 @@
 #include <linux/cma.h>
 #include <linux/highmem.h>
 #include <linux/io.h>
+#include <linux/kmemleak.h>
 #include <trace/events/cma.h>
 
 #include "cma.h"
+#include "internal.h"
 
 struct cma cma_areas[MAX_CMA_AREAS];
 unsigned cma_area_count;
@@ -108,23 +110,25 @@ static int __init cma_activate_area(struct cma *cma)
 	if (!cma->bitmap)
 		return -ENOMEM;
 
-	WARN_ON_ONCE(!pfn_valid(pfn));
-	zone = page_zone(pfn_to_page(pfn));
-
 	do {
 		unsigned j;
 
 		base_pfn = pfn;
+		if (!pfn_valid(base_pfn))
+			goto err;
+
+		zone = page_zone(pfn_to_page(base_pfn));
 		for (j = pageblock_nr_pages; j; --j, pfn++) {
-			WARN_ON_ONCE(!pfn_valid(pfn));
+			if (!pfn_valid(pfn))
+				goto err;
+
 			/*
-			 * 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.
+			 * In init_cma_reserved_pageblock(), present_pages
+			 * is adjusted with assumption that all pages in
+			 * the pageblock come from a single zone.
 			 */
 			if (page_zone(pfn_to_page(pfn)) != zone)
-				goto not_in_zone;
+				goto err;
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
@@ -138,7 +142,7 @@ static int __init cma_activate_area(struct cma *cma)
 
 	return 0;
 
-not_in_zone:
+err:
 	pr_err("CMA area %s could not be activated\n", cma->name);
 	kfree(cma->bitmap);
 	cma->count = 0;
@@ -148,6 +152,41 @@ not_in_zone:
 static int __init cma_init_reserved_areas(void)
 {
 	int i;
+	struct zone *zone;
+	pg_data_t *pgdat;
+
+	if (!cma_area_count)
+		return 0;
+
+	for_each_online_pgdat(pgdat) {
+		unsigned long start_pfn = UINT_MAX, end_pfn = 0;
+
+		zone = &pgdat->node_zones[ZONE_MOVABLE];
+
+		/*
+		 * In this case, we cannot adjust the zone range
+		 * since it is now maximum node span and we don't
+		 * know original zone range.
+		 */
+		if (populated_zone(zone))
+			continue;
+
+		for (i = 0; i < cma_area_count; i++) {
+			if (pfn_to_nid(cma_areas[i].base_pfn) !=
+				pgdat->node_id)
+				continue;
+
+			start_pfn = min(start_pfn, cma_areas[i].base_pfn);
+			end_pfn = max(end_pfn, cma_areas[i].base_pfn +
+						cma_areas[i].count);
+		}
+
+		if (!end_pfn)
+			continue;
+
+		zone->zone_start_pfn = start_pfn;
+		zone->spanned_pages = end_pfn - start_pfn;
+	}
 
 	for (i = 0; i < cma_area_count; i++) {
 		int ret = cma_activate_area(&cma_areas[i]);
@@ -156,15 +195,41 @@ static int __init cma_init_reserved_areas(void)
 			return ret;
 	}
 
+	/*
+	 * Reserved pages for ZONE_MOVABLE are now activated and
+	 * this would change ZONE_MOVABLE's managed page counter and
+	 * the other zones' present counter. We need to re-calculate
+	 * various zone information that depends on this initialization.
+	 */
+	build_all_zonelists(NULL);
+	for_each_populated_zone(zone) {
+		if (zone_idx(zone) == ZONE_MOVABLE) {
+			zone_pcp_reset(zone);
+			setup_zone_pageset(zone);
+		} else
+			zone_pcp_update(zone);
+
+		set_zone_contiguous(zone);
+	}
+
+	/*
+	 * We need to re-init per zone wmark by calling
+	 * init_per_zone_wmark_min() but doesn't call here because it is
+	 * registered on core_initcall and it will be called later than us.
+	 */
+
 	return 0;
 }
-core_initcall(cma_init_reserved_areas);
+pure_initcall(cma_init_reserved_areas);
 
 /**
  * cma_init_reserved_mem() - create custom contiguous area from reserved memory
  * @base: Base address of the reserved area
  * @size: Size of the reserved area (in bytes),
  * @order_per_bit: Order of pages represented by one bit on bitmap.
+ * @name: The name of the area. If this parameter is NULL, the name of
+ *        the area will be set to "cmaN", where N is a running counter of
+ *        used areas.
  * @res_cma: Pointer to store the created cma region.
  *
  * This function creates custom contiguous area from already reserved memory.
@@ -227,6 +292,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
  * @alignment: Alignment for the CMA area, should be power of 2 or zero
  * @order_per_bit: Order of pages represented by one bit on bitmap.
  * @fixed: hint about where to place the reserved area
+ * @name: The name of the area. See function cma_init_reserved_mem()
  * @res_cma: Pointer to store the created cma region.
  *
  * This function reserves memory from early allocator. It should be
@@ -390,6 +456,7 @@ static inline void cma_debug_show_areas(struct cma *cma) { }
  * @cma:   Contiguous memory region for which the allocation is performed.
  * @count: Requested number of pages.
  * @align: Requested alignment of pages (in PAGE_SIZE order).
+ * @gfp_mask:  GFP mask to use during compaction
  *
  * This function allocates part of contiguous memory on specific
  * contiguous memory area.
diff --git a/mm/compaction.c b/mm/compaction.c
index 2c8999d027ab..028b7210a669 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -576,6 +576,7 @@ isolate_fail:
 
 /**
  * isolate_freepages_range() - isolate free pages.
+ * @cc:        Compaction control structure.
  * @start_pfn: The first PFN to start isolating.
  * @end_pfn:   The one-past-last PFN.
  *
@@ -1165,8 +1166,7 @@ static void isolate_freepages(struct compact_control *cc)
  * from the isolated freelists in the block we are migrating to.
  */
 static struct page *compaction_alloc(struct page *migratepage,
-					unsigned long data,
-					int **result)
+					unsigned long data)
 {
 	struct compact_control *cc = (struct compact_control *)data;
 	struct page *freepage;
@@ -1450,14 +1450,12 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
 	 * if compaction succeeds.
 	 * For costly orders, we require low watermark instead of min for
 	 * compaction to proceed to increase its chances.
-	 * ALLOC_CMA is used, as pages in CMA pageblocks are considered
-	 * suitable migration targets
 	 */
 	watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
 				low_wmark_pages(zone) : min_wmark_pages(zone);
 	watermark += compact_gap(order);
 	if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
-						ALLOC_CMA, wmark_target))
+						0, wmark_target))
 		return COMPACT_SKIPPED;
 
 	return COMPACT_CONTINUE;
@@ -1988,6 +1986,14 @@ static void kcompactd_do_work(pg_data_t *pgdat)
 			compaction_defer_reset(zone, cc.order, false);
 		} else if (status == COMPACT_PARTIAL_SKIPPED || status == COMPACT_COMPLETE) {
 			/*
+			 * Buddy pages may become stranded on pcps that could
+			 * otherwise coalesce on the zone's free area for
+			 * order >= cc.order.  This is ratelimited by the
+			 * upcoming deferral.
+			 */
+			drain_all_pages(zone);
+
+			/*
 			 * We use sync migration mode here, so we defer like
 			 * sync direct compaction does.
 			 */
diff --git a/mm/failslab.c b/mm/failslab.c
index 8087d976a809..1f2f248e3601 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -14,7 +14,7 @@ static struct {
 	.cache_filter = false,
 };
 
-bool should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
 	/* No fault-injection for bootstrap cache */
 	if (unlikely(s == kmem_cache))
diff --git a/mm/gup.c b/mm/gup.c
index 751c7b5dbc36..2e2df7f3e92d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -532,7 +532,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma,
 	 * reCOWed by userspace write).
 	 */
 	if ((ret & VM_FAULT_WRITE) && !(vma->vm_flags & VM_WRITE))
-	        *flags |= FOLL_COW;
+		*flags |= FOLL_COW;
 	return 0;
 }
 
@@ -1641,7 +1641,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 					 PMD_SHIFT, next, write, pages, nr))
 				return 0;
 		} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
-				return 0;
+			return 0;
 	} while (pmdp++, addr = next, addr != end);
 
 	return 1;
diff --git a/mm/hmm.c b/mm/hmm.c
index 4aa554e76d06..de7b6bf77201 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -151,6 +151,32 @@ static void hmm_invalidate_range(struct hmm *hmm,
 	up_read(&hmm->mirrors_sem);
 }
 
+static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
+{
+	struct hmm_mirror *mirror;
+	struct hmm *hmm = mm->hmm;
+
+	down_write(&hmm->mirrors_sem);
+	mirror = list_first_entry_or_null(&hmm->mirrors, struct hmm_mirror,
+					  list);
+	while (mirror) {
+		list_del_init(&mirror->list);
+		if (mirror->ops->release) {
+			/*
+			 * Drop mirrors_sem so callback can wait on any pending
+			 * work that might itself trigger mmu_notifier callback
+			 * and thus would deadlock with us.
+			 */
+			up_write(&hmm->mirrors_sem);
+			mirror->ops->release(mirror);
+			down_write(&hmm->mirrors_sem);
+		}
+		mirror = list_first_entry_or_null(&hmm->mirrors,
+						  struct hmm_mirror, list);
+	}
+	up_write(&hmm->mirrors_sem);
+}
+
 static void hmm_invalidate_range_start(struct mmu_notifier *mn,
 				       struct mm_struct *mm,
 				       unsigned long start,
@@ -176,6 +202,7 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn,
 }
 
 static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
+	.release		= hmm_release,
 	.invalidate_range_start	= hmm_invalidate_range_start,
 	.invalidate_range_end	= hmm_invalidate_range_end,
 };
@@ -197,13 +224,24 @@ int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
 	if (!mm || !mirror || !mirror->ops)
 		return -EINVAL;
 
+again:
 	mirror->hmm = hmm_register(mm);
 	if (!mirror->hmm)
 		return -ENOMEM;
 
 	down_write(&mirror->hmm->mirrors_sem);
-	list_add(&mirror->list, &mirror->hmm->mirrors);
-	up_write(&mirror->hmm->mirrors_sem);
+	if (mirror->hmm->mm == NULL) {
+		/*
+		 * A racing hmm_mirror_unregister() is about to destroy the hmm
+		 * struct. Try again to allocate a new one.
+		 */
+		up_write(&mirror->hmm->mirrors_sem);
+		mirror->hmm = NULL;
+		goto again;
+	} else {
+		list_add(&mirror->list, &mirror->hmm->mirrors);
+		up_write(&mirror->hmm->mirrors_sem);
+	}
 
 	return 0;
 }
@@ -218,11 +256,32 @@ EXPORT_SYMBOL(hmm_mirror_register);
  */
 void hmm_mirror_unregister(struct hmm_mirror *mirror)
 {
-	struct hmm *hmm = mirror->hmm;
+	bool should_unregister = false;
+	struct mm_struct *mm;
+	struct hmm *hmm;
 
+	if (mirror->hmm == NULL)
+		return;
+
+	hmm = mirror->hmm;
 	down_write(&hmm->mirrors_sem);
-	list_del(&mirror->list);
+	list_del_init(&mirror->list);
+	should_unregister = list_empty(&hmm->mirrors);
+	mirror->hmm = NULL;
+	mm = hmm->mm;
+	hmm->mm = NULL;
 	up_write(&hmm->mirrors_sem);
+
+	if (!should_unregister || mm == NULL)
+		return;
+
+	spin_lock(&mm->page_table_lock);
+	if (mm->hmm == hmm)
+		mm->hmm = NULL;
+	spin_unlock(&mm->page_table_lock);
+
+	mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm);
+	kfree(hmm);
 }
 EXPORT_SYMBOL(hmm_mirror_unregister);
 
@@ -231,110 +290,275 @@ struct hmm_vma_walk {
 	unsigned long		last;
 	bool			fault;
 	bool			block;
-	bool			write;
 };
 
-static int hmm_vma_do_fault(struct mm_walk *walk,
-			    unsigned long addr,
-			    hmm_pfn_t *pfn)
+static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
+			    bool write_fault, uint64_t *pfn)
 {
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_REMOTE;
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
 	struct vm_area_struct *vma = walk->vma;
 	int r;
 
 	flags |= hmm_vma_walk->block ? 0 : FAULT_FLAG_ALLOW_RETRY;
-	flags |= hmm_vma_walk->write ? FAULT_FLAG_WRITE : 0;
+	flags |= write_fault ? FAULT_FLAG_WRITE : 0;
 	r = handle_mm_fault(vma, addr, flags);
 	if (r & VM_FAULT_RETRY)
 		return -EBUSY;
 	if (r & VM_FAULT_ERROR) {
-		*pfn = HMM_PFN_ERROR;
+		*pfn = range->values[HMM_PFN_ERROR];
 		return -EFAULT;
 	}
 
 	return -EAGAIN;
 }
 
-static void hmm_pfns_special(hmm_pfn_t *pfns,
-			     unsigned long addr,
-			     unsigned long end)
-{
-	for (; addr < end; addr += PAGE_SIZE, pfns++)
-		*pfns = HMM_PFN_SPECIAL;
-}
-
 static int hmm_pfns_bad(unsigned long addr,
 			unsigned long end,
 			struct mm_walk *walk)
 {
-	struct hmm_range *range = walk->private;
-	hmm_pfn_t *pfns = range->pfns;
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+	uint64_t *pfns = range->pfns;
 	unsigned long i;
 
 	i = (addr - range->start) >> PAGE_SHIFT;
 	for (; addr < end; addr += PAGE_SIZE, i++)
-		pfns[i] = HMM_PFN_ERROR;
+		pfns[i] = range->values[HMM_PFN_ERROR];
 
 	return 0;
 }
 
-static void hmm_pfns_clear(hmm_pfn_t *pfns,
-			   unsigned long addr,
-			   unsigned long end)
-{
-	for (; addr < end; addr += PAGE_SIZE, pfns++)
-		*pfns = 0;
-}
-
-static int hmm_vma_walk_hole(unsigned long addr,
-			     unsigned long end,
-			     struct mm_walk *walk)
+/*
+ * hmm_vma_walk_hole() - handle a range lacking valid pmd or pte(s)
+ * @start: range virtual start address (inclusive)
+ * @end: range virtual end address (exclusive)
+ * @fault: should we fault or not ?
+ * @write_fault: write fault ?
+ * @walk: mm_walk structure
+ * Returns: 0 on success, -EAGAIN after page fault, or page fault error
+ *
+ * This function will be called whenever pmd_none() or pte_none() returns true,
+ * or whenever there is no page directory covering the virtual address range.
+ */
+static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
+			      bool fault, bool write_fault,
+			      struct mm_walk *walk)
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	hmm_pfn_t *pfns = range->pfns;
+	uint64_t *pfns = range->pfns;
 	unsigned long i;
 
 	hmm_vma_walk->last = addr;
 	i = (addr - range->start) >> PAGE_SHIFT;
 	for (; addr < end; addr += PAGE_SIZE, i++) {
-		pfns[i] = HMM_PFN_EMPTY;
-		if (hmm_vma_walk->fault) {
+		pfns[i] = range->values[HMM_PFN_NONE];
+		if (fault || write_fault) {
 			int ret;
 
-			ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
+			ret = hmm_vma_do_fault(walk, addr, write_fault,
+					       &pfns[i]);
 			if (ret != -EAGAIN)
 				return ret;
 		}
 	}
 
-	return hmm_vma_walk->fault ? -EAGAIN : 0;
+	return (fault || write_fault) ? -EAGAIN : 0;
 }
 
-static int hmm_vma_walk_clear(unsigned long addr,
-			      unsigned long end,
-			      struct mm_walk *walk)
+static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
+				      uint64_t pfns, uint64_t cpu_flags,
+				      bool *fault, bool *write_fault)
 {
-	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	hmm_pfn_t *pfns = range->pfns;
+
+	*fault = *write_fault = false;
+	if (!hmm_vma_walk->fault)
+		return;
+
+	/* We aren't ask to do anything ... */
+	if (!(pfns & range->flags[HMM_PFN_VALID]))
+		return;
+	/* If this is device memory than only fault if explicitly requested */
+	if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) {
+		/* Do we fault on device memory ? */
+		if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) {
+			*write_fault = pfns & range->flags[HMM_PFN_WRITE];
+			*fault = true;
+		}
+		return;
+	}
+
+	/* If CPU page table is not valid then we need to fault */
+	*fault = !(cpu_flags & range->flags[HMM_PFN_VALID]);
+	/* Need to write fault ? */
+	if ((pfns & range->flags[HMM_PFN_WRITE]) &&
+	    !(cpu_flags & range->flags[HMM_PFN_WRITE])) {
+		*write_fault = true;
+		*fault = true;
+	}
+}
+
+static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
+				 const uint64_t *pfns, unsigned long npages,
+				 uint64_t cpu_flags, bool *fault,
+				 bool *write_fault)
+{
 	unsigned long i;
 
-	hmm_vma_walk->last = addr;
+	if (!hmm_vma_walk->fault) {
+		*fault = *write_fault = false;
+		return;
+	}
+
+	for (i = 0; i < npages; ++i) {
+		hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags,
+				   fault, write_fault);
+		if ((*fault) || (*write_fault))
+			return;
+	}
+}
+
+static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
+			     struct mm_walk *walk)
+{
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+	bool fault, write_fault;
+	unsigned long i, npages;
+	uint64_t *pfns;
+
 	i = (addr - range->start) >> PAGE_SHIFT;
-	for (; addr < end; addr += PAGE_SIZE, i++) {
-		pfns[i] = 0;
-		if (hmm_vma_walk->fault) {
-			int ret;
+	npages = (end - addr) >> PAGE_SHIFT;
+	pfns = &range->pfns[i];
+	hmm_range_need_fault(hmm_vma_walk, pfns, npages,
+			     0, &fault, &write_fault);
+	return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
+}
 
-			ret = hmm_vma_do_fault(walk, addr, &pfns[i]);
-			if (ret != -EAGAIN)
-				return ret;
+static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
+{
+	if (pmd_protnone(pmd))
+		return 0;
+	return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
+				range->flags[HMM_PFN_WRITE] :
+				range->flags[HMM_PFN_VALID];
+}
+
+static int hmm_vma_handle_pmd(struct mm_walk *walk,
+			      unsigned long addr,
+			      unsigned long end,
+			      uint64_t *pfns,
+			      pmd_t pmd)
+{
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+	unsigned long pfn, npages, i;
+	bool fault, write_fault;
+	uint64_t cpu_flags;
+
+	npages = (end - addr) >> PAGE_SHIFT;
+	cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
+	hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags,
+			     &fault, &write_fault);
+
+	if (pmd_protnone(pmd) || fault || write_fault)
+		return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
+
+	pfn = pmd_pfn(pmd) + pte_index(addr);
+	for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
+		pfns[i] = hmm_pfn_from_pfn(range, pfn) | cpu_flags;
+	hmm_vma_walk->last = end;
+	return 0;
+}
+
+static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
+{
+	if (pte_none(pte) || !pte_present(pte))
+		return 0;
+	return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
+				range->flags[HMM_PFN_WRITE] :
+				range->flags[HMM_PFN_VALID];
+}
+
+static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
+			      unsigned long end, pmd_t *pmdp, pte_t *ptep,
+			      uint64_t *pfn)
+{
+	struct hmm_vma_walk *hmm_vma_walk = walk->private;
+	struct hmm_range *range = hmm_vma_walk->range;
+	struct vm_area_struct *vma = walk->vma;
+	bool fault, write_fault;
+	uint64_t cpu_flags;
+	pte_t pte = *ptep;
+	uint64_t orig_pfn = *pfn;
+
+	*pfn = range->values[HMM_PFN_NONE];
+	cpu_flags = pte_to_hmm_pfn_flags(range, pte);
+	hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+			   &fault, &write_fault);
+
+	if (pte_none(pte)) {
+		if (fault || write_fault)
+			goto fault;
+		return 0;
+	}
+
+	if (!pte_present(pte)) {
+		swp_entry_t entry = pte_to_swp_entry(pte);
+
+		if (!non_swap_entry(entry)) {
+			if (fault || write_fault)
+				goto fault;
+			return 0;
 		}
+
+		/*
+		 * This is a special swap entry, ignore migration, use
+		 * device and report anything else as error.
+		 */
+		if (is_device_private_entry(entry)) {
+			cpu_flags = range->flags[HMM_PFN_VALID] |
+				range->flags[HMM_PFN_DEVICE_PRIVATE];
+			cpu_flags |= is_write_device_private_entry(entry) ?
+				range->flags[HMM_PFN_WRITE] : 0;
+			hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
+					   &fault, &write_fault);
+			if (fault || write_fault)
+				goto fault;
+			*pfn = hmm_pfn_from_pfn(range, swp_offset(entry));
+			*pfn |= cpu_flags;
+			return 0;
+		}
+
+		if (is_migration_entry(entry)) {
+			if (fault || write_fault) {
+				pte_unmap(ptep);
+				hmm_vma_walk->last = addr;
+				migration_entry_wait(vma->vm_mm,
+						     pmdp, addr);
+				return -EAGAIN;
+			}
+			return 0;
+		}
+
+		/* Report error for everything else */
+		*pfn = range->values[HMM_PFN_ERROR];
+		return -EFAULT;
 	}
 
-	return hmm_vma_walk->fault ? -EAGAIN : 0;
+	if (fault || write_fault)
+		goto fault;
+
+	*pfn = hmm_pfn_from_pfn(range, pte_pfn(pte)) | cpu_flags;
+	return 0;
+
+fault:
+	pte_unmap(ptep);
+	/* Fault any virtual address we were asked to fault */
+	return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
 }
 
 static int hmm_vma_walk_pmd(pmd_t *pmdp,
@@ -344,26 +568,20 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp,
 {
 	struct hmm_vma_walk *hmm_vma_walk = walk->private;
 	struct hmm_range *range = hmm_vma_walk->range;
-	struct vm_area_struct *vma = walk->vma;
-	hmm_pfn_t *pfns = range->pfns;
+	uint64_t *pfns = range->pfns;
 	unsigned long addr = start, i;
-	bool write_fault;
-	hmm_pfn_t flag;
 	pte_t *ptep;
 
 	i = (addr - range->start) >> PAGE_SHIFT;
-	flag = vma->vm_flags & VM_READ ? HMM_PFN_READ : 0;
-	write_fault = hmm_vma_walk->fault & hmm_vma_walk->write;
 
 again:
 	if (pmd_none(*pmdp))
 		return hmm_vma_walk_hole(start, end, walk);
 
-	if (pmd_huge(*pmdp) && vma->vm_flags & VM_HUGETLB)
+	if (pmd_huge(*pmdp) && (range->vma->vm_flags & VM_HUGETLB))
 		return hmm_pfns_bad(start, end, walk);
 
 	if (pmd_devmap(*pmdp) || pmd_trans_huge(*pmdp)) {
-		unsigned long pfn;
 		pmd_t pmd;
 
 		/*
@@ -379,17 +597,8 @@ again:
 		barrier();
 		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
 			goto again;
-		if (pmd_protnone(pmd))
-			return hmm_vma_walk_clear(start, end, walk);
 
-		if (write_fault && !pmd_write(pmd))
-			return hmm_vma_walk_clear(start, end, walk);
-
-		pfn = pmd_pfn(pmd) + pte_index(addr);
-		flag |= pmd_write(pmd) ? HMM_PFN_WRITE : 0;
-		for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
-			pfns[i] = hmm_pfn_t_from_pfn(pfn) | flag;
-		return 0;
+		return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd);
 	}
 
 	if (pmd_bad(*pmdp))
@@ -397,79 +606,43 @@ again:
 
 	ptep = pte_offset_map(pmdp, addr);
 	for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
-		pte_t pte = *ptep;
-
-		pfns[i] = 0;
+		int r;
 
-		if (pte_none(pte)) {
-			pfns[i] = HMM_PFN_EMPTY;
-			if (hmm_vma_walk->fault)
-				goto fault;
-			continue;
+		r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, &pfns[i]);
+		if (r) {
+			/* hmm_vma_handle_pte() did unmap pte directory */
+			hmm_vma_walk->last = addr;
+			return r;
 		}
-
-		if (!pte_present(pte)) {
-			swp_entry_t entry = pte_to_swp_entry(pte);
-
-			if (!non_swap_entry(entry)) {
-				if (hmm_vma_walk->fault)
-					goto fault;
-				continue;
-			}
-
-			/*
-			 * This is a special swap entry, ignore migration, use
-			 * device and report anything else as error.
-			 */
-			if (is_device_private_entry(entry)) {
-				pfns[i] = hmm_pfn_t_from_pfn(swp_offset(entry));
-				if (is_write_device_private_entry(entry)) {
-					pfns[i] |= HMM_PFN_WRITE;
-				} else if (write_fault)
-					goto fault;
-				pfns[i] |= HMM_PFN_DEVICE_UNADDRESSABLE;
-				pfns[i] |= flag;
-			} else if (is_migration_entry(entry)) {
-				if (hmm_vma_walk->fault) {
-					pte_unmap(ptep);
-					hmm_vma_walk->last = addr;
-					migration_entry_wait(vma->vm_mm,
-							     pmdp, addr);
-					return -EAGAIN;
-				}
-				continue;
-			} else {
-				/* Report error for everything else */
-				pfns[i] = HMM_PFN_ERROR;
-			}
-			continue;
-		}
-
-		if (write_fault && !pte_write(pte))
-			goto fault;
-
-		pfns[i] = hmm_pfn_t_from_pfn(pte_pfn(pte)) | flag;
-		pfns[i] |= pte_write(pte) ? HMM_PFN_WRITE : 0;
-		continue;
-
-fault:
-		pte_unmap(ptep);
-		/* Fault all pages in range */
-		return hmm_vma_walk_clear(start, end, walk);
 	}
 	pte_unmap(ptep - 1);
 
+	hmm_vma_walk->last = addr;
 	return 0;
 }
 
+static void hmm_pfns_clear(struct hmm_range *range,
+			   uint64_t *pfns,
+			   unsigned long addr,
+			   unsigned long end)
+{
+	for (; addr < end; addr += PAGE_SIZE, pfns++)
+		*pfns = range->values[HMM_PFN_NONE];
+}
+
+static void hmm_pfns_special(struct hmm_range *range)
+{
+	unsigned long addr = range->start, i = 0;
+
+	for (; addr < range->end; addr += PAGE_SIZE, i++)
+		range->pfns[i] = range->values[HMM_PFN_SPECIAL];
+}
+
 /*
  * hmm_vma_get_pfns() - snapshot CPU page table for a range of virtual addresses
- * @vma: virtual memory area containing the virtual address range
- * @range: used to track snapshot validity
- * @start: range virtual start address (inclusive)
- * @end: range virtual end address (exclusive)
- * @entries: array of hmm_pfn_t: provided by the caller, filled in by function
- * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, 0 success
+ * @range: range being snapshotted
+ * Returns: -EINVAL if invalid argument, -ENOMEM out of memory, -EPERM invalid
+ *          vma permission, 0 success
  *
  * This snapshots the CPU page table for a range of virtual addresses. Snapshot
  * validity is tracked by range struct. See hmm_vma_range_done() for further
@@ -482,26 +655,17 @@ fault:
  * NOT CALLING hmm_vma_range_done() IF FUNCTION RETURNS 0 WILL LEAD TO SERIOUS
  * MEMORY CORRUPTION ! YOU HAVE BEEN WARNED !
  */
-int hmm_vma_get_pfns(struct vm_area_struct *vma,
-		     struct hmm_range *range,
-		     unsigned long start,
-		     unsigned long end,
-		     hmm_pfn_t *pfns)
+int hmm_vma_get_pfns(struct hmm_range *range)
 {
+	struct vm_area_struct *vma = range->vma;
 	struct hmm_vma_walk hmm_vma_walk;
 	struct mm_walk mm_walk;
 	struct hmm *hmm;
 
-	/* FIXME support hugetlb fs */
-	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
-		hmm_pfns_special(pfns, start, end);
-		return -EINVAL;
-	}
-
 	/* Sanity check, this really should not happen ! */
-	if (start < vma->vm_start || start >= vma->vm_end)
+	if (range->start < vma->vm_start || range->start >= vma->vm_end)
 		return -EINVAL;
-	if (end < vma->vm_start || end > vma->vm_end)
+	if (range->end < vma->vm_start || range->end > vma->vm_end)
 		return -EINVAL;
 
 	hmm = hmm_register(vma->vm_mm);
@@ -511,10 +675,24 @@ int hmm_vma_get_pfns(struct vm_area_struct *vma,
 	if (!hmm->mmu_notifier.ops)
 		return -EINVAL;
 
+	/* FIXME support hugetlb fs */
+	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+		hmm_pfns_special(range);
+		return -EINVAL;
+	}
+
+	if (!(vma->vm_flags & VM_READ)) {
+		/*
+		 * If vma do not allow read access, then assume that it does
+		 * not allow write access, either. Architecture that allow
+		 * write without read access are not supported by HMM, because
+		 * operations such has atomic access would not work.
+		 */
+		hmm_pfns_clear(range, range->pfns, range->start, range->end);
+		return -EPERM;
+	}
+
 	/* Initialize range to track CPU page table update */
-	range->start = start;
-	range->pfns = pfns;
-	range->end = end;
 	spin_lock(&hmm->lock);
 	range->valid = true;
 	list_add_rcu(&range->list, &hmm->ranges);
@@ -532,14 +710,13 @@ int hmm_vma_get_pfns(struct vm_area_struct *vma,
 	mm_walk.pmd_entry = hmm_vma_walk_pmd;
 	mm_walk.pte_hole = hmm_vma_walk_hole;
 
-	walk_page_range(start, end, &mm_walk);
+	walk_page_range(range->start, range->end, &mm_walk);
 	return 0;
 }
 EXPORT_SYMBOL(hmm_vma_get_pfns);
 
 /*
  * hmm_vma_range_done() - stop tracking change to CPU page table over a range
- * @vma: virtual memory area containing the virtual address range
  * @range: range being tracked
  * Returns: false if range data has been invalidated, true otherwise
  *
@@ -559,10 +736,10 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
  *
  * There are two ways to use this :
  * again:
- *   hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
+ *   hmm_vma_get_pfns(range); or hmm_vma_fault(...);
  *   trans = device_build_page_table_update_transaction(pfns);
  *   device_page_table_lock();
- *   if (!hmm_vma_range_done(vma, range)) {
+ *   if (!hmm_vma_range_done(range)) {
  *     device_page_table_unlock();
  *     goto again;
  *   }
@@ -570,13 +747,13 @@ EXPORT_SYMBOL(hmm_vma_get_pfns);
  *   device_page_table_unlock();
  *
  * Or:
- *   hmm_vma_get_pfns(vma, range, start, end, pfns); or hmm_vma_fault(...);
+ *   hmm_vma_get_pfns(range); or hmm_vma_fault(...);
  *   device_page_table_lock();
- *   hmm_vma_range_done(vma, range);
- *   device_update_page_table(pfns);
+ *   hmm_vma_range_done(range);
+ *   device_update_page_table(range->pfns);
  *   device_page_table_unlock();
  */
-bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range)
+bool hmm_vma_range_done(struct hmm_range *range)
 {
 	unsigned long npages = (range->end - range->start) >> PAGE_SHIFT;
 	struct hmm *hmm;
@@ -586,7 +763,7 @@ bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range)
 		return false;
 	}
 
-	hmm = hmm_register(vma->vm_mm);
+	hmm = hmm_register(range->vma->vm_mm);
 	if (!hmm) {
 		memset(range->pfns, 0, sizeof(*range->pfns) * npages);
 		return false;
@@ -602,36 +779,34 @@ EXPORT_SYMBOL(hmm_vma_range_done);
 
 /*
  * hmm_vma_fault() - try to fault some address in a virtual address range
- * @vma: virtual memory area containing the virtual address range
- * @range: use to track pfns array content validity
- * @start: fault range virtual start address (inclusive)
- * @end: fault range virtual end address (exclusive)
- * @pfns: array of hmm_pfn_t, only entry with fault flag set will be faulted
- * @write: is it a write fault
+ * @range: range being faulted
  * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
  * Returns: 0 success, error otherwise (-EAGAIN means mmap_sem have been drop)
  *
  * This is similar to a regular CPU page fault except that it will not trigger
  * any memory migration if the memory being faulted is not accessible by CPUs.
  *
- * On error, for one virtual address in the range, the function will set the
- * hmm_pfn_t error flag for the corresponding pfn entry.
+ * On error, for one virtual address in the range, the function will mark the
+ * corresponding HMM pfn entry with an error flag.
  *
  * Expected use pattern:
  * retry:
  *   down_read(&mm->mmap_sem);
  *   // Find vma and address device wants to fault, initialize hmm_pfn_t
  *   // array accordingly
- *   ret = hmm_vma_fault(vma, start, end, pfns, allow_retry);
+ *   ret = hmm_vma_fault(range, write, block);
  *   switch (ret) {
  *   case -EAGAIN:
- *     hmm_vma_range_done(vma, range);
+ *     hmm_vma_range_done(range);
  *     // You might want to rate limit or yield to play nicely, you may
  *     // also commit any valid pfn in the array assuming that you are
  *     // getting true from hmm_vma_range_monitor_end()
  *     goto retry;
  *   case 0:
  *     break;
+ *   case -ENOMEM:
+ *   case -EINVAL:
+ *   case -EPERM:
  *   default:
  *     // Handle error !
  *     up_read(&mm->mmap_sem)
@@ -639,7 +814,7 @@ EXPORT_SYMBOL(hmm_vma_range_done);
  *   }
  *   // Take device driver lock that serialize device page table update
  *   driver_lock_device_page_table_update();
- *   hmm_vma_range_done(vma, range);
+ *   hmm_vma_range_done(range);
  *   // Commit pfns we got from hmm_vma_fault()
  *   driver_unlock_device_page_table_update();
  *   up_read(&mm->mmap_sem)
@@ -649,51 +824,54 @@ EXPORT_SYMBOL(hmm_vma_range_done);
  *
  * YOU HAVE BEEN WARNED !
  */
-int hmm_vma_fault(struct vm_area_struct *vma,
-		  struct hmm_range *range,
-		  unsigned long start,
-		  unsigned long end,
-		  hmm_pfn_t *pfns,
-		  bool write,
-		  bool block)
+int hmm_vma_fault(struct hmm_range *range, bool block)
 {
+	struct vm_area_struct *vma = range->vma;
+	unsigned long start = range->start;
 	struct hmm_vma_walk hmm_vma_walk;
 	struct mm_walk mm_walk;
 	struct hmm *hmm;
 	int ret;
 
 	/* Sanity check, this really should not happen ! */
-	if (start < vma->vm_start || start >= vma->vm_end)
+	if (range->start < vma->vm_start || range->start >= vma->vm_end)
 		return -EINVAL;
-	if (end < vma->vm_start || end > vma->vm_end)
+	if (range->end < vma->vm_start || range->end > vma->vm_end)
 		return -EINVAL;
 
 	hmm = hmm_register(vma->vm_mm);
 	if (!hmm) {
-		hmm_pfns_clear(pfns, start, end);
+		hmm_pfns_clear(range, range->pfns, range->start, range->end);
 		return -ENOMEM;
 	}
 	/* Caller must have registered a mirror using hmm_mirror_register() */
 	if (!hmm->mmu_notifier.ops)
 		return -EINVAL;
 
+	/* FIXME support hugetlb fs */
+	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
+		hmm_pfns_special(range);
+		return -EINVAL;
+	}
+
+	if (!(vma->vm_flags & VM_READ)) {
+		/*
+		 * If vma do not allow read access, then assume that it does
+		 * not allow write access, either. Architecture that allow
+		 * write without read access are not supported by HMM, because
+		 * operations such has atomic access would not work.
+		 */
+		hmm_pfns_clear(range, range->pfns, range->start, range->end);
+		return -EPERM;
+	}
+
 	/* Initialize range to track CPU page table update */
-	range->start = start;
-	range->pfns = pfns;
-	range->end = end;
 	spin_lock(&hmm->lock);
 	range->valid = true;
 	list_add_rcu(&range->list, &hmm->ranges);
 	spin_unlock(&hmm->lock);
 
-	/* FIXME support hugetlb fs */
-	if (is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_SPECIAL)) {
-		hmm_pfns_special(pfns, start, end);
-		return 0;
-	}
-
 	hmm_vma_walk.fault = true;
-	hmm_vma_walk.write = write;
 	hmm_vma_walk.block = block;
 	hmm_vma_walk.range = range;
 	mm_walk.private = &hmm_vma_walk;
@@ -708,7 +886,7 @@ int hmm_vma_fault(struct vm_area_struct *vma,
 	mm_walk.pte_hole = hmm_vma_walk_hole;
 
 	do {
-		ret = walk_page_range(start, end, &mm_walk);
+		ret = walk_page_range(start, range->end, &mm_walk);
 		start = hmm_vma_walk.last;
 	} while (ret == -EAGAIN);
 
@@ -716,8 +894,9 @@ int hmm_vma_fault(struct vm_area_struct *vma,
 		unsigned long i;
 
 		i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
-		hmm_pfns_clear(&pfns[i], hmm_vma_walk.last, end);
-		hmm_vma_range_done(vma, range);
+		hmm_pfns_clear(range, &range->pfns[i], hmm_vma_walk.last,
+			       range->end);
+		hmm_vma_range_done(range);
 	}
 	return ret;
 }
@@ -836,13 +1015,6 @@ static void hmm_devmem_release(struct device *dev, void *data)
 	hmm_devmem_radix_release(resource);
 }
 
-static struct hmm_devmem *hmm_devmem_find(resource_size_t phys)
-{
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	return radix_tree_lookup(&hmm_devmem_radix, phys >> PA_SECTION_SHIFT);
-}
-
 static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
 {
 	resource_size_t key, align_start, align_size, align_end;
@@ -883,9 +1055,8 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem)
 	for (key = align_start; key <= align_end; key += PA_SECTION_SIZE) {
 		struct hmm_devmem *dup;
 
-		rcu_read_lock();
-		dup = hmm_devmem_find(key);
-		rcu_read_unlock();
+		dup = radix_tree_lookup(&hmm_devmem_radix,
+					key >> PA_SECTION_SHIFT);
 		if (dup) {
 			dev_err(device, "%s: collides with mapping for %s\n",
 				__func__, dev_name(dup->device));
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5a68730eebd6..f2eccca30535 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2356,26 +2356,13 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	struct page *page_tail = head + tail;
 
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
-	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
-	 * tail_page->_refcount is zero and not changing from under us. But
-	 * get_page_unless_zero() may be running from under us on the
-	 * tail_page. If we used atomic_set() below instead of atomic_inc() or
-	 * atomic_add(), we would then run atomic_set() concurrently with
-	 * get_page_unless_zero(), and atomic_set() is implemented in C not
-	 * using locked ops. spin_unlock on x86 sometime uses locked ops
-	 * because of PPro errata 66, 92, so unless somebody can guarantee
-	 * atomic_set() here would be safe on all archs (and not only on x86),
-	 * it's safer to use atomic_inc()/atomic_add().
+	 * Clone page flags before unfreezing refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow flags change,
+	 * for exmaple lock_page() which set PG_waiters.
 	 */
-	if (PageAnon(head) && !PageSwapCache(head)) {
-		page_ref_inc(page_tail);
-	} else {
-		/* Additional pin to radix tree */
-		page_ref_add(page_tail, 2);
-	}
-
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &
 			((1L << PG_referenced) |
@@ -2388,14 +2375,21 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_unevictable) |
 			 (1L << PG_dirty)));
 
-	/*
-	 * After clearing PageTail the gup refcount can be released.
-	 * Page flags also must be visible before we make the page non-compound.
-	 */
+	/* Page flags must be visible before we make the page non-compound. */
 	smp_wmb();
 
+	/*
+	 * Clear PageTail before unfreezing page refcount.
+	 *
+	 * After successful get_page_unless_zero() might follow put_page()
+	 * which needs correct compound_head().
+	 */
 	clear_compound_head(page_tail);
 
+	/* Finally unfreeze refcount. Additional reference from page cache. */
+	page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) ||
+					  PageSwapCache(head)));
+
 	if (page_is_young(head))
 		set_page_young(page_tail);
 	if (page_is_idle(head))
@@ -2408,6 +2402,12 @@ static void __split_huge_page_tail(struct page *head, int tail,
 
 	page_tail->index = head->index + tail;
 	page_cpupid_xchg_last(page_tail, page_cpupid_last(head));
+
+	/*
+	 * always add to the tail because some iterators expect new
+	 * pages to show after the currently processed elements - e.g.
+	 * migrate_pages
+	 */
 	lru_add_page_tail(head, page_tail, lruvec, list);
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 976bbc5646fe..218679138255 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -637,29 +637,22 @@ EXPORT_SYMBOL_GPL(linear_hugepage_index);
  */
 unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
 {
-	struct hstate *hstate;
-
-	if (!is_vm_hugetlb_page(vma))
-		return PAGE_SIZE;
-
-	hstate = hstate_vma(vma);
-
-	return 1UL << huge_page_shift(hstate);
+	if (vma->vm_ops && vma->vm_ops->pagesize)
+		return vma->vm_ops->pagesize(vma);
+	return PAGE_SIZE;
 }
 EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
 
 /*
  * Return the page size being used by the MMU to back a VMA. In the majority
  * of cases, the page size used by the kernel matches the MMU size. On
- * architectures where it differs, an architecture-specific version of this
- * function is required.
+ * architectures where it differs, an architecture-specific 'strong'
+ * version of this symbol is required.
  */
-#ifndef vma_mmu_pagesize
-unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+__weak unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
 {
 	return vma_kernel_pagesize(vma);
 }
-#endif
 
 /*
  * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
@@ -3153,6 +3146,13 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
 	return 0;
 }
 
+static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma)
+{
+	struct hstate *hstate = hstate_vma(vma);
+
+	return 1UL << huge_page_shift(hstate);
+}
+
 /*
  * We cannot handle pagefaults against hugetlb pages at all.  They cause
  * handle_mm_fault() to try to instantiate regular-sized pages in the
@@ -3170,6 +3170,7 @@ const struct vm_operations_struct hugetlb_vm_ops = {
 	.open = hugetlb_vm_op_open,
 	.close = hugetlb_vm_op_close,
 	.split = hugetlb_vm_op_split,
+	.pagesize = hugetlb_vm_op_pagesize,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
diff --git a/mm/internal.h b/mm/internal.h
index e6bd35182dae..62d8c34e63d5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -168,6 +168,9 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
 					gfp_t gfp_flags);
 extern int user_min_free_kbytes;
 
+extern void set_zone_contiguous(struct zone *zone);
+extern void clear_zone_contiguous(struct zone *zone);
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
@@ -495,7 +498,6 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 #define ALLOC_HARDER		0x10 /* try to alloc harder */
 #define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
 #define ALLOC_CPUSET		0x40 /* check for correct cpuset */
-#define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
 
 enum ttu_flags;
 struct tlbflush_unmap_batch;
@@ -538,4 +540,5 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 }
 
 void setup_zone_pageset(struct zone *zone);
+extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index e13d911251e7..135ce2838c89 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -323,9 +323,9 @@ void kasan_free_pages(struct page *page, unsigned int order)
  * Adaptive redzone policy taken from the userspace AddressSanitizer runtime.
  * For larger allocations larger redzones are used.
  */
-static size_t optimal_redzone(size_t object_size)
+static unsigned int optimal_redzone(unsigned int object_size)
 {
-	int rz =
+	return
 		object_size <= 64        - 16   ? 16 :
 		object_size <= 128       - 32   ? 32 :
 		object_size <= 512       - 64   ? 64 :
@@ -333,14 +333,13 @@ static size_t optimal_redzone(size_t object_size)
 		object_size <= (1 << 14) - 256  ? 256 :
 		object_size <= (1 << 15) - 512  ? 512 :
 		object_size <= (1 << 16) - 1024 ? 1024 : 2048;
-	return rz;
 }
 
-void kasan_cache_create(struct kmem_cache *cache, size_t *size,
+void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 			slab_flags_t *flags)
 {
+	unsigned int orig_size = *size;
 	int redzone_adjust;
-	int orig_size = *size;
 
 	/* Add alloc meta. */
 	cache->kasan_info.alloc_meta_offset = *size;
@@ -358,7 +357,8 @@ void kasan_cache_create(struct kmem_cache *cache, size_t *size,
 	if (redzone_adjust > 0)
 		*size += redzone_adjust;
 
-	*size = min(KMALLOC_MAX_SIZE, max(*size, cache->object_size +
+	*size = min_t(unsigned int, KMALLOC_MAX_SIZE,
+			max(*size, cache->object_size +
 					optimal_redzone(cache->object_size)));
 
 	/*
@@ -382,7 +382,8 @@ void kasan_cache_shrink(struct kmem_cache *cache)
 
 void kasan_cache_shutdown(struct kmem_cache *cache)
 {
-	quarantine_remove_cache(cache);
+	if (!__kmem_cache_empty(cache))
+		quarantine_remove_cache(cache);
 }
 
 size_t kasan_metadata_size(struct kmem_cache *cache)
@@ -791,6 +792,41 @@ DEFINE_ASAN_SET_SHADOW(f5);
 DEFINE_ASAN_SET_SHADOW(f8);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+	pgd_t *pgd = pgd_offset_k(addr);
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	if (pgd_none(*pgd))
+		return false;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return false;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return false;
+
+	/*
+	 * We can't use pud_large() or pud_huge(), the first one
+	 * is arch-specific, the last one depend on HUGETLB_PAGE.
+	 * So let's abuse pud_bad(), if bud is bad it's has to
+	 * because it's huge.
+	 */
+	if (pud_bad(*pud))
+		return true;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+
+	if (pmd_bad(*pmd))
+		return true;
+	pte = pte_offset_kernel(pmd, addr);
+	return !pte_none(*pte);
+}
+
 static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 			unsigned long action, void *data)
 {
@@ -812,6 +848,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 	case MEM_GOING_ONLINE: {
 		void *ret;
 
+		/*
+		 * If shadow is mapped already than it must have been mapped
+		 * during the boot. This could happen if we onlining previously
+		 * offlined memory.
+		 */
+		if (shadow_mapped(shadow_start))
+			return NOTIFY_OK;
+
 		ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
 					shadow_end, GFP_KERNEL,
 					PAGE_KERNEL, VM_NO_GUARD,
@@ -823,8 +867,18 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
 		kmemleak_ignore(ret);
 		return NOTIFY_OK;
 	}
-	case MEM_OFFLINE:
-		vfree((void *)shadow_start);
+	case MEM_OFFLINE: {
+		struct vm_struct *vm;
+
+		/*
+		 * Only hot-added memory have vm_area. Freeing shadow
+		 * mapped during boot would be tricky, so we'll just
+		 * have to keep it.
+		 */
+		vm = find_vm_area((void *)shadow_start);
+		if (vm)
+			vfree((void *)shadow_start);
+	}
 	}
 
 	return NOTIFY_OK;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 46c2290a08f1..9a085d525bbc 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1187,6 +1187,11 @@ EXPORT_SYMBOL(kmemleak_no_scan);
 /**
  * kmemleak_alloc_phys - similar to kmemleak_alloc but taking a physical
  *			 address argument
+ * @phys:	physical address of the object
+ * @size:	size of the object
+ * @min_count:	minimum number of references to this object.
+ *              See kmemleak_alloc()
+ * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
  */
 void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count,
 			       gfp_t gfp)
@@ -1199,6 +1204,9 @@ EXPORT_SYMBOL(kmemleak_alloc_phys);
 /**
  * kmemleak_free_part_phys - similar to kmemleak_free_part but taking a
  *			     physical address argument
+ * @phys:	physical address if the beginning or inside an object. This
+ *		also represents the start of the range to be freed
+ * @size:	size to be unregistered
  */
 void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size)
 {
@@ -1210,6 +1218,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys);
 /**
  * kmemleak_not_leak_phys - similar to kmemleak_not_leak but taking a physical
  *			    address argument
+ * @phys:	physical address of the object
  */
 void __ref kmemleak_not_leak_phys(phys_addr_t phys)
 {
@@ -1221,6 +1230,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys);
 /**
  * kmemleak_ignore_phys - similar to kmemleak_ignore but taking a physical
  *			  address argument
+ * @phys:	physical address of the object
  */
 void __ref kmemleak_ignore_phys(phys_addr_t phys)
 {
@@ -1963,7 +1973,7 @@ static void kmemleak_disable(void)
 /*
  * Allow boot-time kmemleak disabling (enabled by default).
  */
-static int kmemleak_boot_config(char *str)
+static int __init kmemleak_boot_config(char *str)
 {
 	if (!str)
 		return -EINVAL;
diff --git a/mm/ksm.c b/mm/ksm.c
index adb5f991da8e..e8d6c6210b80 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1318,10 +1318,10 @@ bool is_page_sharing_candidate(struct stable_node *stable_node)
 	return __is_page_sharing_candidate(stable_node, 0);
 }
 
-struct page *stable_node_dup(struct stable_node **_stable_node_dup,
-			     struct stable_node **_stable_node,
-			     struct rb_root *root,
-			     bool prune_stale_stable_nodes)
+static struct page *stable_node_dup(struct stable_node **_stable_node_dup,
+				    struct stable_node **_stable_node,
+				    struct rb_root *root,
+				    bool prune_stale_stable_nodes)
 {
 	struct stable_node *dup, *found = NULL, *stable_node = *_stable_node;
 	struct hlist_node *hlist_safe;
@@ -2082,8 +2082,22 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 	tree_rmap_item =
 		unstable_tree_search_insert(rmap_item, page, &tree_page);
 	if (tree_rmap_item) {
+		bool split;
+
 		kpage = try_to_merge_two_pages(rmap_item, page,
 						tree_rmap_item, tree_page);
+		/*
+		 * If both pages we tried to merge belong to the same compound
+		 * page, then we actually ended up increasing the reference
+		 * count of the same compound page twice, and split_huge_page
+		 * failed.
+		 * Here we set a flag if that happened, and we use it later to
+		 * try split_huge_page again. Since we call put_page right
+		 * afterwards, the reference count will be correct and
+		 * split_huge_page should succeed.
+		 */
+		split = PageTransCompound(page)
+			&& compound_head(page) == compound_head(tree_page);
 		put_page(tree_page);
 		if (kpage) {
 			/*
@@ -2110,6 +2124,20 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 				break_cow(tree_rmap_item);
 				break_cow(rmap_item);
 			}
+		} else if (split) {
+			/*
+			 * We are here if we tried to merge two pages and
+			 * failed because they both belonged to the same
+			 * compound page. We will split the page now, but no
+			 * merging will take place.
+			 * We do not want to add the cost of a full lock; if
+			 * the page is locked, it is better to skip it and
+			 * perhaps try again later.
+			 */
+			if (!trylock_page(page))
+				return;
+			split_huge_page(page);
+			unlock_page(page);
 		}
 	}
 }
diff --git a/mm/list_lru.c b/mm/list_lru.c
index fd41e969ede5..d9c84c5bda1d 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/list_lru.h>
+#include <linux/prefetch.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/memcontrol.h>
@@ -52,14 +53,15 @@ static inline bool list_lru_memcg_aware(struct list_lru *lru)
 static inline struct list_lru_one *
 list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
 {
+	struct list_lru_memcg *memcg_lrus;
 	/*
-	 * The lock protects the array of per cgroup lists from relocation
-	 * (see memcg_update_list_lru_node).
+	 * Either lock or RCU protects the array of per cgroup lists
+	 * from relocation (see memcg_update_list_lru_node).
 	 */
-	lockdep_assert_held(&nlru->lock);
-	if (nlru->memcg_lrus && idx >= 0)
-		return nlru->memcg_lrus->lru[idx];
-
+	memcg_lrus = rcu_dereference_check(nlru->memcg_lrus,
+					   lockdep_is_held(&nlru->lock));
+	if (memcg_lrus && idx >= 0)
+		return memcg_lrus->lru[idx];
 	return &nlru->lru;
 }
 
@@ -132,6 +134,12 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
 	struct list_lru_node *nlru = &lru->node[nid];
 	struct list_lru_one *l;
 
+	/*
+	 * Prefetch the neighboring list entries to reduce lock hold time.
+	 */
+	prefetchw(item->prev);
+	prefetchw(item->next);
+
 	spin_lock(&nlru->lock);
 	if (!list_empty(item)) {
 		l = list_lru_from_kmem(nlru, item);
@@ -168,10 +176,10 @@ static unsigned long __list_lru_count_one(struct list_lru *lru,
 	struct list_lru_one *l;
 	unsigned long count;
 
-	spin_lock(&nlru->lock);
+	rcu_read_lock();
 	l = list_lru_from_memcg_idx(nlru, memcg_idx);
 	count = l->nr_items;
-	spin_unlock(&nlru->lock);
+	rcu_read_unlock();
 
 	return count;
 }
@@ -324,24 +332,41 @@ fail:
 
 static int memcg_init_list_lru_node(struct list_lru_node *nlru)
 {
+	struct list_lru_memcg *memcg_lrus;
 	int size = memcg_nr_cache_ids;
 
-	nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL);
-	if (!nlru->memcg_lrus)
+	memcg_lrus = kvmalloc(sizeof(*memcg_lrus) +
+			      size * sizeof(void *), GFP_KERNEL);
+	if (!memcg_lrus)
 		return -ENOMEM;
 
-	if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
-		kvfree(nlru->memcg_lrus);
+	if (__memcg_init_list_lru_node(memcg_lrus, 0, size)) {
+		kvfree(memcg_lrus);
 		return -ENOMEM;
 	}
+	RCU_INIT_POINTER(nlru->memcg_lrus, memcg_lrus);
 
 	return 0;
 }
 
 static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
 {
-	__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
-	kvfree(nlru->memcg_lrus);
+	struct list_lru_memcg *memcg_lrus;
+	/*
+	 * This is called when shrinker has already been unregistered,
+	 * and nobody can use it. So, there is no need to use kvfree_rcu().
+	 */
+	memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true);
+	__memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids);
+	kvfree(memcg_lrus);
+}
+
+static void kvfree_rcu(struct rcu_head *head)
+{
+	struct list_lru_memcg *mlru;
+
+	mlru = container_of(head, struct list_lru_memcg, rcu);
+	kvfree(mlru);
 }
 
 static int memcg_update_list_lru_node(struct list_lru_node *nlru,
@@ -351,8 +376,9 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 
 	BUG_ON(old_size > new_size);
 
-	old = nlru->memcg_lrus;
-	new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL);
+	old = rcu_dereference_protected(nlru->memcg_lrus,
+					lockdep_is_held(&list_lrus_mutex));
+	new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -361,29 +387,33 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 		return -ENOMEM;
 	}
 
-	memcpy(new, old, old_size * sizeof(void *));
+	memcpy(&new->lru, &old->lru, old_size * sizeof(void *));
 
 	/*
-	 * The lock guarantees that we won't race with a reader
-	 * (see list_lru_from_memcg_idx).
+	 * The locking below allows readers that hold nlru->lock avoid taking
+	 * rcu_read_lock (see list_lru_from_memcg_idx).
 	 *
 	 * Since list_lru_{add,del} may be called under an IRQ-safe lock,
 	 * we have to use IRQ-safe primitives here to avoid deadlock.
 	 */
 	spin_lock_irq(&nlru->lock);
-	nlru->memcg_lrus = new;
+	rcu_assign_pointer(nlru->memcg_lrus, new);
 	spin_unlock_irq(&nlru->lock);
 
-	kvfree(old);
+	call_rcu(&old->rcu, kvfree_rcu);
 	return 0;
 }
 
 static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru,
 					      int old_size, int new_size)
 {
+	struct list_lru_memcg *memcg_lrus;
+
+	memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus,
+					       lockdep_is_held(&list_lrus_mutex));
 	/* do not bother shrinking the array back to the old size, because we
 	 * cannot handle allocation failures here */
-	__memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size);
+	__memcg_destroy_list_lru_node(memcg_lrus, old_size, new_size);
 }
 
 static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
diff --git a/mm/memblock.c b/mm/memblock.c
index 9307cbd87089..5108356ad8aa 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -17,6 +17,7 @@
 #include <linux/poison.h>
 #include <linux/pfn.h>
 #include <linux/debugfs.h>
+#include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
 
@@ -924,7 +925,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
 			r = &type_b->regions[idx_b];
 			r_start = idx_b ? r[-1].base + r[-1].size : 0;
 			r_end = idx_b < type_b->cnt ?
-				r->base : ULLONG_MAX;
+				r->base : (phys_addr_t)ULLONG_MAX;
 
 			/*
 			 * if idx_b advanced past idx_a,
@@ -1040,7 +1041,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
 			r = &type_b->regions[idx_b];
 			r_start = idx_b ? r[-1].base + r[-1].size : 0;
 			r_end = idx_b < type_b->cnt ?
-				r->base : ULLONG_MAX;
+				r->base : (phys_addr_t)ULLONG_MAX;
 			/*
 			 * if idx_b advanced past idx_a,
 			 * break out to advance idx_a
@@ -1345,7 +1346,7 @@ void * __init memblock_virt_alloc_try_nid_raw(
 					   min_addr, max_addr, nid);
 #ifdef CONFIG_DEBUG_VM
 	if (ptr && size > 0)
-		memset(ptr, 0xff, size);
+		memset(ptr, PAGE_POISON_PATTERN, size);
 #endif
 	return ptr;
 }
@@ -1750,29 +1751,6 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 	}
 }
 
-extern unsigned long __init_memblock
-memblock_reserved_memory_within(phys_addr_t start_addr, phys_addr_t end_addr)
-{
-	struct memblock_region *rgn;
-	unsigned long size = 0;
-	int idx;
-
-	for_each_memblock_type(idx, (&memblock.reserved), rgn) {
-		phys_addr_t start, end;
-
-		if (rgn->base + rgn->size < start_addr)
-			continue;
-		if (rgn->base > end_addr)
-			continue;
-
-		start = rgn->base;
-		end = start + rgn->size;
-		size += end - start;
-	}
-
-	return size;
-}
-
 void __init_memblock __memblock_dump_all(void)
 {
 	pr_info("MEMBLOCK configuration:\n");
@@ -1818,18 +1796,7 @@ static int memblock_debug_show(struct seq_file *m, void *private)
 	}
 	return 0;
 }
-
-static int memblock_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, memblock_debug_show, inode->i_private);
-}
-
-static const struct file_operations memblock_debug_fops = {
-	.open = memblock_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(memblock_debug);
 
 static int __init memblock_init_debugfs(void)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9ec024b862ac..aa1e7455e313 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -888,7 +888,8 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
  * value, the function breaks the iteration loop and returns the value.
  * Otherwise, it will iterate over all tasks and return 0.
  *
- * This function must not be called for the root memory cgroup.
+ * If memcg is the root memory cgroup, this function will iterate only
+ * over tasks belonging directly to the root memory cgroup.
  */
 int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 			  int (*fn)(struct task_struct *, void *), void *arg)
@@ -896,8 +897,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 	struct mem_cgroup *iter;
 	int ret = 0;
 
-	BUG_ON(memcg == root_mem_cgroup);
-
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
 		struct task_struct *task;
@@ -906,7 +905,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 		while (!ret && (task = css_task_iter_next(&it)))
 			ret = fn(task, arg);
 		css_task_iter_end(&it);
-		if (ret) {
+		if (ret || memcg == root_mem_cgroup) {
 			mem_cgroup_iter_break(memcg, iter);
 			break;
 		}
@@ -2592,6 +2591,224 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
 	return ret;
 }
 
+static long memcg_oom_badness(struct mem_cgroup *memcg,
+			      const nodemask_t *nodemask,
+			      unsigned long totalpages)
+{
+	long points = 0;
+	int nid;
+	pg_data_t *pgdat;
+
+	for_each_node_state(nid, N_MEMORY) {
+		if (nodemask && !node_isset(nid, *nodemask))
+			continue;
+
+		points += mem_cgroup_node_nr_lru_pages(memcg, nid,
+				LRU_ALL_ANON | BIT(LRU_UNEVICTABLE));
+
+		pgdat = NODE_DATA(nid);
+		points += lruvec_page_state(mem_cgroup_lruvec(pgdat, memcg),
+					    NR_SLAB_UNRECLAIMABLE);
+	}
+
+	points += memcg_page_state(memcg, MEMCG_KERNEL_STACK_KB) /
+		(PAGE_SIZE / 1024);
+	points += memcg_page_state(memcg, MEMCG_SOCK);
+	points += memcg_page_state(memcg, MEMCG_SWAP);
+
+	return points;
+}
+
+/*
+ * Checks if the given memcg is a valid OOM victim and returns a number,
+ * which means the folowing:
+ *   -1: there are inflight OOM victim tasks, belonging to the memcg
+ *    0: memcg is not eligible, e.g. all belonging tasks are protected
+ *       by oom_score_adj set to OOM_SCORE_ADJ_MIN
+ *   >0: memcg is eligible, and the returned value is an estimation
+ *       of the memory footprint
+ */
+static long oom_evaluate_memcg(struct mem_cgroup *memcg,
+			       const nodemask_t *nodemask,
+			       unsigned long totalpages)
+{
+	struct css_task_iter it;
+	struct task_struct *task;
+	int eligible = 0;
+
+	/*
+	 * Root memory cgroup is a special case:
+	 * we don't have necessary stats to evaluate it exactly as
+	 * leaf memory cgroups, so we approximate it's oom_score
+	 * by summing oom_score of all belonging tasks, which are
+	 * owners of their mm structs.
+	 *
+	 * If there are inflight OOM victim tasks inside
+	 * the root memcg, we return -1.
+	 */
+	if (memcg == root_mem_cgroup) {
+		struct css_task_iter it;
+		struct task_struct *task;
+		long score = 0;
+
+		css_task_iter_start(&memcg->css, 0, &it);
+		while ((task = css_task_iter_next(&it))) {
+			if (tsk_is_oom_victim(task) &&
+			    !test_bit(MMF_OOM_SKIP,
+				      &task->signal->oom_mm->flags)) {
+				score = -1;
+				break;
+			}
+
+			task_lock(task);
+			if (!task->mm || task->mm->owner != task) {
+				task_unlock(task);
+				continue;
+			}
+			task_unlock(task);
+
+			score += oom_badness(task, memcg, nodemask,
+					     totalpages);
+		}
+		css_task_iter_end(&it);
+
+		return score;
+	}
+
+	/*
+	 * Memcg is OOM eligible if there are OOM killable tasks inside.
+	 *
+	 * We treat tasks with oom_score_adj set to OOM_SCORE_ADJ_MIN
+	 * as unkillable.
+	 *
+	 * If there are inflight OOM victim tasks inside the memcg,
+	 * we return -1.
+	 */
+	css_task_iter_start(&memcg->css, 0, &it);
+	while ((task = css_task_iter_next(&it))) {
+		if (!eligible &&
+		    task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN)
+			eligible = 1;
+
+		if (tsk_is_oom_victim(task) &&
+		    !test_bit(MMF_OOM_SKIP, &task->signal->oom_mm->flags)) {
+			eligible = -1;
+			break;
+		}
+	}
+	css_task_iter_end(&it);
+
+	if (eligible <= 0)
+		return eligible;
+
+	return memcg_oom_badness(memcg, nodemask, totalpages);
+}
+
+static void select_victim_memcg(struct mem_cgroup *root, struct oom_control *oc)
+{
+	struct mem_cgroup *iter, *group = NULL;
+	long group_score = 0;
+
+	oc->chosen_memcg = NULL;
+	oc->chosen_points = 0;
+
+	/*
+	 * If OOM is memcg-wide, and the memcg has the oom_group flag set,
+	 * all tasks belonging to the memcg should be killed.
+	 * So, we mark the memcg as a victim.
+	 */
+	if (oc->memcg && mem_cgroup_oom_group(oc->memcg)) {
+		oc->chosen_memcg = oc->memcg;
+		css_get(&oc->chosen_memcg->css);
+		return;
+	}
+
+	/*
+	 * The oom_score is calculated for leaf memory cgroups (including
+	 * the root memcg).
+	 * Non-leaf oom_group cgroups accumulating score of descendant
+	 * leaf memory cgroups.
+	 */
+	rcu_read_lock();
+	for_each_mem_cgroup_tree(iter, root) {
+		long score;
+
+		/*
+		 * We don't consider non-leaf non-oom_group memory cgroups
+		 * as OOM victims.
+		 */
+		if (memcg_has_children(iter) && iter != root_mem_cgroup &&
+		    !mem_cgroup_oom_group(iter))
+			continue;
+
+		/*
+		 * If group is not set or we've ran out of the group's sub-tree,
+		 * we should set group and reset group_score.
+		 */
+		if (!group || group == root_mem_cgroup ||
+		    !mem_cgroup_is_descendant(iter, group)) {
+			group = iter;
+			group_score = 0;
+		}
+
+		if (memcg_has_children(iter) && iter != root_mem_cgroup)
+			continue;
+
+		score = oom_evaluate_memcg(iter, oc->nodemask, oc->totalpages);
+
+		/*
+		 * Ignore empty and non-eligible memory cgroups.
+		 */
+		if (score == 0)
+			continue;
+
+		/*
+		 * If there are inflight OOM victims, we don't need
+		 * to look further for new victims.
+		 */
+		if (score == -1) {
+			oc->chosen_memcg = INFLIGHT_VICTIM;
+			mem_cgroup_iter_break(root, iter);
+			break;
+		}
+
+		group_score += score;
+
+		if (group_score > oc->chosen_points) {
+			oc->chosen_points = group_score;
+			oc->chosen_memcg = group;
+		}
+	}
+
+	if (oc->chosen_memcg && oc->chosen_memcg != INFLIGHT_VICTIM)
+		css_get(&oc->chosen_memcg->css);
+
+	rcu_read_unlock();
+}
+
+bool mem_cgroup_select_oom_victim(struct oom_control *oc)
+{
+	struct mem_cgroup *root;
+
+	if (mem_cgroup_disabled())
+		return false;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return false;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return false;
+
+	if (oc->memcg)
+		root = oc->memcg;
+	else
+		root = root_mem_cgroup;
+
+	select_victim_memcg(root, oc);
+
+	return oc->chosen_memcg;
+}
+
 /*
  * Reclaims as many pages from the given memcg as possible.
  *
@@ -5187,6 +5404,39 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+static int memory_oom_group_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	bool oom_group = memcg->oom_group;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return -ENOTSUPP;
+
+	seq_printf(m, "%d\n", oom_group);
+
+	return 0;
+}
+
+static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes,
+				      loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int oom_group;
+	int err;
+
+	if (!(cgrp_dfl_root.flags & CGRP_GROUP_OOM))
+		return -ENOTSUPP;
+
+	err = kstrtoint(strstrip(buf), 0, &oom_group);
+	if (err)
+		return err;
+
+	memcg->oom_group = oom_group;
+
+	return nbytes;
+}
+
 static int memory_events_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
@@ -5307,6 +5557,12 @@ static struct cftype memory_files[] = {
 		.write = memory_max_write,
 	},
 	{
+		.name = "oom_group",
+		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
+		.seq_show = memory_oom_group_show,
+		.write = memory_oom_group_write,
+	},
+	{
 		.name = "events",
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.file_offset = offsetof(struct mem_cgroup, events_file),
diff --git a/mm/memfd.c b/mm/memfd.c
new file mode 100644
index 000000000000..c913fbfa094a
--- /dev/null
+++ b/mm/memfd.c
@@ -0,0 +1,342 @@
+/*
+ * memfd_create system call and file sealing support
+ *
+ * Code was originally included in shmem.c, and broken out to facilitate
+ * use by hugetlbfs as well as tmpfs.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/fs.h>
+#include <linux/vfs.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/khugepaged.h>
+#include <linux/syscalls.h>
+#include <linux/hugetlb.h>
+#include <linux/shmem_fs.h>
+#include <linux/memfd.h>
+#include <uapi/linux/memfd.h>
+
+/*
+ * We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
+ * so reuse a tag which we firmly believe is never set or cleared on shmem.
+ */
+#define SHMEM_TAG_PINNED        PAGECACHE_TAG_TOWRITE
+#define LAST_SCAN               4       /* about 150ms max */
+
+static void shmem_tag_pins(struct address_space *mapping)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+	pgoff_t start;
+	struct page *page;
+
+	lru_add_drain();
+	start = 0;
+	rcu_read_lock();
+
+	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+		page = radix_tree_deref_slot(slot);
+		if (!page || radix_tree_exception(page)) {
+			if (radix_tree_deref_retry(page)) {
+				slot = radix_tree_iter_retry(&iter);
+				continue;
+			}
+		} else if (page_count(page) - page_mapcount(page) > 1) {
+			spin_lock_irq(&mapping->tree_lock);
+			radix_tree_tag_set(&mapping->page_tree, iter.index,
+					   SHMEM_TAG_PINNED);
+			spin_unlock_irq(&mapping->tree_lock);
+		}
+
+		if (need_resched()) {
+			slot = radix_tree_iter_resume(slot, &iter);
+			cond_resched_rcu();
+		}
+	}
+	rcu_read_unlock();
+}
+
+/*
+ * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
+ * via get_user_pages(), drivers might have some pending I/O without any active
+ * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
+ * and see whether it has an elevated ref-count. If so, we tag them and wait for
+ * them to be dropped.
+ * The caller must guarantee that no new user will acquire writable references
+ * to those pages to avoid races.
+ */
+static int shmem_wait_for_pins(struct address_space *mapping)
+{
+	struct radix_tree_iter iter;
+	void __rcu **slot;
+	pgoff_t start;
+	struct page *page;
+	int error, scan;
+
+	shmem_tag_pins(mapping);
+
+	error = 0;
+	for (scan = 0; scan <= LAST_SCAN; scan++) {
+		if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED))
+			break;
+
+		if (!scan)
+			lru_add_drain_all();
+		else if (schedule_timeout_killable((HZ << scan) / 200))
+			scan = LAST_SCAN;
+
+		start = 0;
+		rcu_read_lock();
+		radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
+					   start, SHMEM_TAG_PINNED) {
+
+			page = radix_tree_deref_slot(slot);
+			if (radix_tree_exception(page)) {
+				if (radix_tree_deref_retry(page)) {
+					slot = radix_tree_iter_retry(&iter);
+					continue;
+				}
+
+				page = NULL;
+			}
+
+			if (page &&
+			    page_count(page) - page_mapcount(page) != 1) {
+				if (scan < LAST_SCAN)
+					goto continue_resched;
+
+				/*
+				 * On the last scan, we clean up all those tags
+				 * we inserted; but make a note that we still
+				 * found pages pinned.
+				 */
+				error = -EBUSY;
+			}
+
+			spin_lock_irq(&mapping->tree_lock);
+			radix_tree_tag_clear(&mapping->page_tree,
+					     iter.index, SHMEM_TAG_PINNED);
+			spin_unlock_irq(&mapping->tree_lock);
+continue_resched:
+			if (need_resched()) {
+				slot = radix_tree_iter_resume(slot, &iter);
+				cond_resched_rcu();
+			}
+		}
+		rcu_read_unlock();
+	}
+
+	return error;
+}
+
+static unsigned int *memfd_file_seals_ptr(struct file *file)
+{
+	if (shmem_file(file))
+		return &SHMEM_I(file_inode(file))->seals;
+
+	if (is_file_hugepages(file))
+		return &HUGETLBFS_I(file_inode(file))->seals;
+
+	return NULL;
+}
+
+#define F_ALL_SEALS (F_SEAL_SEAL | \
+		     F_SEAL_SHRINK | \
+		     F_SEAL_GROW | \
+		     F_SEAL_WRITE)
+
+static int memfd_add_seals(struct file *file, unsigned int seals)
+{
+	struct inode *inode = file_inode(file);
+	unsigned int *file_seals;
+	int error;
+
+	/*
+	 * SEALING
+	 * Sealing allows multiple parties to share a tmpfs or hugetlbfs file
+	 * but restrict access to a specific subset of file operations. Seals
+	 * can only be added, but never removed. This way, mutually untrusted
+	 * parties can share common memory regions with a well-defined policy.
+	 * A malicious peer can thus never perform unwanted operations on a
+	 * shared object.
+	 *
+	 * Seals are only supported on special tmpfs or hugetlbfs files and
+	 * always affect the whole underlying inode. Once a seal is set, it
+	 * may prevent some kinds of access to the file. Currently, the
+	 * following seals are defined:
+	 *   SEAL_SEAL: Prevent further seals from being set on this file
+	 *   SEAL_SHRINK: Prevent the file from shrinking
+	 *   SEAL_GROW: Prevent the file from growing
+	 *   SEAL_WRITE: Prevent write access to the file
+	 *
+	 * As we don't require any trust relationship between two parties, we
+	 * must prevent seals from being removed. Therefore, sealing a file
+	 * only adds a given set of seals to the file, it never touches
+	 * existing seals. Furthermore, the "setting seals"-operation can be
+	 * sealed itself, which basically prevents any further seal from being
+	 * added.
+	 *
+	 * Semantics of sealing are only defined on volatile files. Only
+	 * anonymous tmpfs and hugetlbfs files support sealing. More
+	 * importantly, seals are never written to disk. Therefore, there's
+	 * no plan to support it on other file types.
+	 */
+
+	if (!(file->f_mode & FMODE_WRITE))
+		return -EPERM;
+	if (seals & ~(unsigned int)F_ALL_SEALS)
+		return -EINVAL;
+
+	inode_lock(inode);
+
+	file_seals = memfd_file_seals_ptr(file);
+	if (!file_seals) {
+		error = -EINVAL;
+		goto unlock;
+	}
+
+	if (*file_seals & F_SEAL_SEAL) {
+		error = -EPERM;
+		goto unlock;
+	}
+
+	if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) {
+		error = mapping_deny_writable(file->f_mapping);
+		if (error)
+			goto unlock;
+
+		error = shmem_wait_for_pins(file->f_mapping);
+		if (error) {
+			mapping_allow_writable(file->f_mapping);
+			goto unlock;
+		}
+	}
+
+	*file_seals |= seals;
+	error = 0;
+
+unlock:
+	inode_unlock(inode);
+	return error;
+}
+
+static int memfd_get_seals(struct file *file)
+{
+	unsigned int *seals = memfd_file_seals_ptr(file);
+
+	return seals ? *seals : -EINVAL;
+}
+
+long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long error;
+
+	switch (cmd) {
+	case F_ADD_SEALS:
+		/* disallow upper 32bit */
+		if (arg > UINT_MAX)
+			return -EINVAL;
+
+		error = memfd_add_seals(file, arg);
+		break;
+	case F_GET_SEALS:
+		error = memfd_get_seals(file);
+		break;
+	default:
+		error = -EINVAL;
+		break;
+	}
+
+	return error;
+}
+
+#define MFD_NAME_PREFIX "memfd:"
+#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
+#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
+
+#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
+
+SYSCALL_DEFINE2(memfd_create,
+		const char __user *, uname,
+		unsigned int, flags)
+{
+	unsigned int *file_seals;
+	struct file *file;
+	int fd, error;
+	char *name;
+	long len;
+
+	if (!(flags & MFD_HUGETLB)) {
+		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
+			return -EINVAL;
+	} else {
+		/* Allow huge page size encoding in flags. */
+		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
+				(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
+			return -EINVAL;
+	}
+
+	/* length includes terminating zero */
+	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
+	if (len <= 0)
+		return -EFAULT;
+	if (len > MFD_NAME_MAX_LEN + 1)
+		return -EINVAL;
+
+	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+
+	strcpy(name, MFD_NAME_PREFIX);
+	if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
+		error = -EFAULT;
+		goto err_name;
+	}
+
+	/* terminating-zero may have changed after strnlen_user() returned */
+	if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
+		error = -EFAULT;
+		goto err_name;
+	}
+
+	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
+	if (fd < 0) {
+		error = fd;
+		goto err_name;
+	}
+
+	if (flags & MFD_HUGETLB) {
+		struct user_struct *user = NULL;
+
+		file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,
+					HUGETLB_ANONHUGE_INODE,
+					(flags >> MFD_HUGE_SHIFT) &
+					MFD_HUGE_MASK);
+	} else
+		file = shmem_file_setup(name, 0, VM_NORESERVE);
+	if (IS_ERR(file)) {
+		error = PTR_ERR(file);
+		goto err_fd;
+	}
+	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
+	file->f_flags |= O_RDWR | O_LARGEFILE;
+
+	if (flags & MFD_ALLOW_SEALING) {
+		file_seals = memfd_file_seals_ptr(file);
+		*file_seals &= ~F_SEAL_SEAL;
+	}
+
+	fd_install(fd, file);
+	kfree(name);
+	return fd;
+
+err_fd:
+	put_unused_fd(fd);
+err_name:
+	kfree(name);
+	return error;
+}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8291b75f42c8..9d142b9b86dc 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -502,6 +502,7 @@ static const char * const action_page_types[] = {
 	[MF_MSG_POISONED_HUGE]		= "huge page already hardware poisoned",
 	[MF_MSG_HUGE]			= "huge page",
 	[MF_MSG_FREE_HUGE]		= "free huge page",
+	[MF_MSG_NON_PMD_HUGE]		= "non-pmd-sized huge page",
 	[MF_MSG_UNMAP_FAILED]		= "unmapping failed page",
 	[MF_MSG_DIRTY_SWAPCACHE]	= "dirty swapcache page",
 	[MF_MSG_CLEAN_SWAPCACHE]	= "clean swapcache page",
@@ -1084,6 +1085,21 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
 		return 0;
 	}
 
+	/*
+	 * TODO: hwpoison for pud-sized hugetlb doesn't work right now, so
+	 * simply disable it. In order to make it work properly, we need
+	 * make sure that:
+	 *  - conversion of a pud that maps an error hugetlb into hwpoison
+	 *    entry properly works, and
+	 *  - other mm code walking over page table is aware of pud-aligned
+	 *    hwpoison entries.
+	 */
+	if (huge_page_size(page_hstate(head)) > PMD_SIZE) {
+		action_result(pfn, MF_MSG_NON_PMD_HUGE, MF_IGNORED);
+		res = -EBUSY;
+		goto out;
+	}
+
 	if (!hwpoison_user_mappings(p, pfn, flags, &head)) {
 		action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
 		res = -EBUSY;
@@ -1471,7 +1487,7 @@ int unpoison_memory(unsigned long pfn)
 }
 EXPORT_SYMBOL(unpoison_memory);
 
-static struct page *new_page(struct page *p, unsigned long private, int **x)
+static struct page *new_page(struct page *p, unsigned long private)
 {
 	int nid = page_to_nid(p);
 
diff --git a/mm/memory.c b/mm/memory.c
index aed37325d94e..a1f990e33e38 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2883,26 +2883,16 @@ EXPORT_SYMBOL(unmap_mapping_range);
 int do_swap_page(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct page *page = NULL, *swapcache = NULL;
+	struct page *page = NULL, *swapcache;
 	struct mem_cgroup *memcg;
-	struct vma_swap_readahead swap_ra;
 	swp_entry_t entry;
 	pte_t pte;
 	int locked;
 	int exclusive = 0;
 	int ret = 0;
-	bool vma_readahead = swap_use_vma_readahead();
 
-	if (vma_readahead) {
-		page = swap_readahead_detect(vmf, &swap_ra);
-		swapcache = page;
-	}
-
-	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte)) {
-		if (page)
-			put_page(page);
+	if (!pte_unmap_same(vma->vm_mm, vmf->pmd, vmf->pte, vmf->orig_pte))
 		goto out;
-	}
 
 	entry = pte_to_swp_entry(vmf->orig_pte);
 	if (unlikely(non_swap_entry(entry))) {
@@ -2928,19 +2918,17 @@ int do_swap_page(struct vm_fault *vmf)
 
 
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
-	if (!page) {
-		page = lookup_swap_cache(entry, vma_readahead ? vma : NULL,
-					 vmf->address);
-		swapcache = page;
-	}
+	page = lookup_swap_cache(entry, vma, vmf->address);
+	swapcache = page;
 
 	if (!page) {
 		struct swap_info_struct *si = swp_swap_info(entry);
 
 		if (si->flags & SWP_SYNCHRONOUS_IO &&
-				__swap_count(si, entry) == 1) {
+				__swap_count(entry) == 1) {
 			/* skip swapcache */
-			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address);
+			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma,
+							vmf->address);
 			if (page) {
 				__SetPageLocked(page);
 				__SetPageSwapBacked(page);
@@ -2949,12 +2937,8 @@ int do_swap_page(struct vm_fault *vmf)
 				swap_readpage(page, true);
 			}
 		} else {
-			if (vma_readahead)
-				page = do_swap_page_readahead(entry,
-					GFP_HIGHUSER_MOVABLE, vmf, &swap_ra);
-			else
-				page = swapin_readahead(entry,
-				       GFP_HIGHUSER_MOVABLE, vma, vmf->address);
+			page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE,
+						vmf);
 			swapcache = page;
 		}
 
@@ -2982,7 +2966,6 @@ int do_swap_page(struct vm_fault *vmf)
 		 */
 		ret = VM_FAULT_HWPOISON;
 		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
-		swapcache = page;
 		goto out_release;
 	}
 
@@ -3052,7 +3035,6 @@ int do_swap_page(struct vm_fault *vmf)
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 	arch_do_swap_page(vma->vm_mm, vma, vmf->address, pte, vmf->orig_pte);
 	vmf->orig_pte = pte;
 
@@ -3066,6 +3048,7 @@ int do_swap_page(struct vm_fault *vmf)
 		mem_cgroup_commit_charge(page, memcg, true, false);
 		activate_page(page);
 	}
+	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
 
 	swap_free(entry);
 	if (mem_cgroup_swap_full(page) ||
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b2bd52ff7605..f74826cdceea 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -250,7 +250,6 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
 		struct vmem_altmap *altmap, bool want_memblock)
 {
 	int ret;
-	int i;
 
 	if (pfn_valid(phys_start_pfn))
 		return -EEXIST;
@@ -259,27 +258,10 @@ static int __meminit __add_section(int nid, unsigned long phys_start_pfn,
 	if (ret < 0)
 		return ret;
 
-	/*
-	 * Make all the pages reserved so that nobody will stumble over half
-	 * initialized state.
-	 * FIXME: We also have to associate it with a node because page_to_nid
-	 * relies on having page with the proper node.
-	 */
-	for (i = 0; i < PAGES_PER_SECTION; i++) {
-		unsigned long pfn = phys_start_pfn + i;
-		struct page *page;
-		if (!pfn_valid(pfn))
-			continue;
-
-		page = pfn_to_page(pfn);
-		set_page_node(page, nid);
-		SetPageReserved(page);
-	}
-
 	if (!want_memblock)
 		return 0;
 
-	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
+	return hotplug_memory_register(nid, __pfn_to_section(phys_start_pfn));
 }
 
 /*
@@ -559,6 +541,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms,
  * @zone: zone from which pages need to be removed
  * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
  * @nr_pages: number of pages to remove (must be multiple of section size)
+ * @altmap: alternative device page map or %NULL if default memmap is used
  *
  * Generic helper function to remove section mappings and sysfs entries
  * for the section of the memory we are removing. Caller needs to make
@@ -908,8 +891,15 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	int nid;
 	int ret;
 	struct memory_notify arg;
+	struct memory_block *mem;
+
+	/*
+	 * We can't use pfn_to_nid() because nid might be stored in struct page
+	 * which is not yet initialized. Instead, we find nid from memory block.
+	 */
+	mem = find_memory_block(__pfn_to_section(pfn));
+	nid = mem->nid;
 
-	nid = pfn_to_nid(pfn);
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
 
@@ -1055,6 +1045,7 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
 
 /**
  * try_online_node - online a node if offlined
+ * @nid: the node ID
  *
  * called by cpu_up() to online a node without onlined memory.
  */
@@ -1083,15 +1074,16 @@ out:
 
 static int check_hotplug_memory_range(u64 start, u64 size)
 {
-	u64 start_pfn = PFN_DOWN(start);
+	unsigned long block_sz = memory_block_size_bytes();
+	u64 block_nr_pages = block_sz >> PAGE_SHIFT;
 	u64 nr_pages = size >> PAGE_SHIFT;
+	u64 start_pfn = PFN_DOWN(start);
 
-	/* Memory range must be aligned with section */
-	if ((start_pfn & ~PAGE_SECTION_MASK) ||
-	    (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
-		pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
-				(unsigned long long)start,
-				(unsigned long long)size);
+	/* memory range must be block size aligned */
+	if (!nr_pages || !IS_ALIGNED(start_pfn, block_nr_pages) ||
+	    !IS_ALIGNED(nr_pages, block_nr_pages)) {
+		pr_err("Block size [%#lx] unaligned hotplug range: start %#llx, size %#llx",
+		       block_sz, start, size);
 		return -EINVAL;
 	}
 
@@ -1337,8 +1329,7 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 	return 0;
 }
 
-static struct page *new_node_page(struct page *page, unsigned long private,
-		int **result)
+static struct page *new_node_page(struct page *page, unsigned long private)
 {
 	int nid = page_to_nid(page);
 	nodemask_t nmask = node_states[N_MEMORY];
@@ -1381,7 +1372,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (isolate_huge_page(page, &source))
 				move_pages -= 1 << compound_order(head);
 			continue;
-		} else if (thp_migration_supported() && PageTransHuge(page))
+		} else if (PageTransHuge(page))
 			pfn = page_to_pfn(compound_head(page))
 				+ hpage_nr_pages(page) - 1;
 
@@ -1814,6 +1805,7 @@ static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
 
 /**
  * try_offline_node
+ * @nid: the node ID
  *
  * Offline a node if all memory sections and cpus of the node are removed.
  *
@@ -1857,6 +1849,9 @@ EXPORT_SYMBOL(try_offline_node);
 
 /**
  * remove_memory
+ * @nid: the node ID
+ * @start: physical address of the region to remove
+ * @size: size of the region to remove
  *
  * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
  * and online/offline operations before this call, as required by
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 01cbb7078d6c..9ac49ef17b4e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -446,15 +446,6 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 		__split_huge_pmd(walk->vma, pmd, addr, false, NULL);
 		goto out;
 	}
-	if (!thp_migration_supported()) {
-		get_page(page);
-		spin_unlock(ptl);
-		lock_page(page);
-		ret = split_huge_page(page);
-		unlock_page(page);
-		put_page(page);
-		goto out;
-	}
 	if (!queue_pages_required(page, qp)) {
 		ret = 1;
 		goto unlock;
@@ -495,7 +486,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
-retry:
+
 	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {
 		if (!pte_present(*pte))
@@ -511,22 +502,6 @@ retry:
 			continue;
 		if (!queue_pages_required(page, qp))
 			continue;
-		if (PageTransCompound(page) && !thp_migration_supported()) {
-			get_page(page);
-			pte_unmap_unlock(pte, ptl);
-			lock_page(page);
-			ret = split_huge_page(page);
-			unlock_page(page);
-			put_page(page);
-			/* Failed to split -- skip. */
-			if (ret) {
-				pte = pte_offset_map_lock(walk->mm, pmd,
-						addr, &ptl);
-				continue;
-			}
-			goto retry;
-		}
-
 		migrate_page_add(page, qp->pagelist, flags);
 	}
 	pte_unmap_unlock(pte - 1, ptl);
@@ -942,12 +917,13 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 	}
 }
 
-static struct page *new_node_page(struct page *page, unsigned long node, int **x)
+/* page allocation callback for NUMA node migration */
+struct page *alloc_new_node_page(struct page *page, unsigned long node)
 {
 	if (PageHuge(page))
 		return alloc_huge_page_node(page_hstate(compound_head(page)),
 					node);
-	else if (thp_migration_supported() && PageTransHuge(page)) {
+	else if (PageTransHuge(page)) {
 		struct page *thp;
 
 		thp = alloc_pages_node(node,
@@ -986,7 +962,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_node_page, NULL, dest,
+		err = migrate_pages(&pagelist, alloc_new_node_page, NULL, dest,
 					MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
 			putback_movable_pages(&pagelist);
@@ -1107,7 +1083,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
  * list of pages handed to migrate_pages()--which is how we get here--
  * is in virtual address order.
  */
-static struct page *new_page(struct page *page, unsigned long start, int **x)
+static struct page *new_page(struct page *page, unsigned long start)
 {
 	struct vm_area_struct *vma;
 	unsigned long uninitialized_var(address);
@@ -1123,7 +1099,7 @@ static struct page *new_page(struct page *page, unsigned long start, int **x)
 	if (PageHuge(page)) {
 		return alloc_huge_page_vma(page_hstate(compound_head(page)),
 				vma, address);
-	} else if (thp_migration_supported() && PageTransHuge(page)) {
+	} else if (PageTransHuge(page)) {
 		struct page *thp;
 
 		thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
@@ -1152,7 +1128,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 	return -ENOSYS;
 }
 
-static struct page *new_page(struct page *page, unsigned long start, int **x)
+static struct page *new_page(struct page *page, unsigned long start)
 {
 	return NULL;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 003886606a22..f475fe9efc48 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1137,10 +1137,12 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 				   enum migrate_reason reason)
 {
 	int rc = MIGRATEPAGE_SUCCESS;
-	int *result = NULL;
 	struct page *newpage;
 
-	newpage = get_new_page(page, private, &result);
+	if (!thp_migration_supported() && PageTransHuge(page))
+		return -ENOMEM;
+
+	newpage = get_new_page(page, private);
 	if (!newpage)
 		return -ENOMEM;
 
@@ -1161,14 +1163,6 @@ static ICE_noinline int unmap_and_move(new_page_t get_new_page,
 		goto out;
 	}
 
-	if (unlikely(PageTransHuge(page) && !PageTransHuge(newpage))) {
-		lock_page(page);
-		rc = split_huge_page(page);
-		unlock_page(page);
-		if (rc)
-			goto out;
-	}
-
 	rc = __unmap_and_move(page, newpage, force, mode);
 	if (rc == MIGRATEPAGE_SUCCESS)
 		set_page_owner_migrate_reason(newpage, reason);
@@ -1231,12 +1225,6 @@ put_new:
 			put_page(newpage);
 	}
 
-	if (result) {
-		if (rc)
-			*result = rc;
-		else
-			*result = page_to_nid(newpage);
-	}
 	return rc;
 }
 
@@ -1264,7 +1252,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 				enum migrate_mode mode, int reason)
 {
 	int rc = -EAGAIN;
-	int *result = NULL;
 	int page_was_mapped = 0;
 	struct page *new_hpage;
 	struct anon_vma *anon_vma = NULL;
@@ -1281,7 +1268,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 		return -ENOSYS;
 	}
 
-	new_hpage = get_new_page(hpage, private, &result);
+	new_hpage = get_new_page(hpage, private);
 	if (!new_hpage)
 		return -ENOMEM;
 
@@ -1345,12 +1332,6 @@ out:
 	else
 		putback_active_hugepage(new_hpage);
 
-	if (result) {
-		if (rc)
-			*result = rc;
-		else
-			*result = page_to_nid(new_hpage);
-	}
 	return rc;
 }
 
@@ -1395,6 +1376,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 		retry = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
+retry:
 			cond_resched();
 
 			if (PageHuge(page))
@@ -1408,6 +1390,26 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 
 			switch(rc) {
 			case -ENOMEM:
+				/*
+				 * THP migration might be unsupported or the
+				 * allocation could've failed so we should
+				 * retry on the same page with the THP split
+				 * to base pages.
+				 *
+				 * Head page is retried immediately and tail
+				 * pages are added to the tail of the list so
+				 * we encounter them after the rest of the list
+				 * is processed.
+				 */
+				if (PageTransHuge(page)) {
+					lock_page(page);
+					rc = split_huge_page_to_list(page, from);
+					unlock_page(page);
+					if (!rc) {
+						list_safe_reset_next(page, page2, lru);
+						goto retry;
+					}
+				}
 				nr_failed++;
 				goto out;
 			case -EAGAIN:
@@ -1444,141 +1446,101 @@ out:
 }
 
 #ifdef CONFIG_NUMA
-/*
- * Move a list of individual pages
- */
-struct page_to_node {
-	unsigned long addr;
-	struct page *page;
-	int node;
-	int status;
-};
 
-static struct page *new_page_node(struct page *p, unsigned long private,
-		int **result)
+static int store_status(int __user *status, int start, int value, int nr)
 {
-	struct page_to_node *pm = (struct page_to_node *)private;
-
-	while (pm->node != MAX_NUMNODES && pm->page != p)
-		pm++;
+	while (nr-- > 0) {
+		if (put_user(value, status + start))
+			return -EFAULT;
+		start++;
+	}
 
-	if (pm->node == MAX_NUMNODES)
-		return NULL;
+	return 0;
+}
 
-	*result = &pm->status;
+static int do_move_pages_to_node(struct mm_struct *mm,
+		struct list_head *pagelist, int node)
+{
+	int err;
 
-	if (PageHuge(p))
-		return alloc_huge_page_node(page_hstate(compound_head(p)),
-					pm->node);
-	else if (thp_migration_supported() && PageTransHuge(p)) {
-		struct page *thp;
+	if (list_empty(pagelist))
+		return 0;
 
-		thp = alloc_pages_node(pm->node,
-			(GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_RECLAIM,
-			HPAGE_PMD_ORDER);
-		if (!thp)
-			return NULL;
-		prep_transhuge_page(thp);
-		return thp;
-	} else
-		return __alloc_pages_node(pm->node,
-				GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0);
+	err = migrate_pages(pagelist, alloc_new_node_page, NULL, node,
+			MIGRATE_SYNC, MR_SYSCALL);
+	if (err)
+		putback_movable_pages(pagelist);
+	return err;
 }
 
 /*
- * Move a set of pages as indicated in the pm array. The addr
- * field must be set to the virtual address of the page to be moved
- * and the node number must contain a valid target node.
- * The pm array ends with node = MAX_NUMNODES.
+ * Resolves the given address to a struct page, isolates it from the LRU and
+ * puts it to the given pagelist.
+ * Returns -errno if the page cannot be found/isolated or 0 when it has been
+ * queued or the page doesn't need to be migrated because it is already on
+ * the target node
  */
-static int do_move_page_to_node_array(struct mm_struct *mm,
-				      struct page_to_node *pm,
-				      int migrate_all)
+static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
+		int node, struct list_head *pagelist, bool migrate_all)
 {
+	struct vm_area_struct *vma;
+	struct page *page;
+	unsigned int follflags;
 	int err;
-	struct page_to_node *pp;
-	LIST_HEAD(pagelist);
 
 	down_read(&mm->mmap_sem);
+	err = -EFAULT;
+	vma = find_vma(mm, addr);
+	if (!vma || addr < vma->vm_start || !vma_migratable(vma))
+		goto out;
 
-	/*
-	 * Build a list of pages to migrate
-	 */
-	for (pp = pm; pp->node != MAX_NUMNODES; pp++) {
-		struct vm_area_struct *vma;
-		struct page *page;
-		struct page *head;
-		unsigned int follflags;
-
-		err = -EFAULT;
-		vma = find_vma(mm, pp->addr);
-		if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
-			goto set_status;
-
-		/* FOLL_DUMP to ignore special (like zero) pages */
-		follflags = FOLL_GET | FOLL_DUMP;
-		if (!thp_migration_supported())
-			follflags |= FOLL_SPLIT;
-		page = follow_page(vma, pp->addr, follflags);
+	/* FOLL_DUMP to ignore special (like zero) pages */
+	follflags = FOLL_GET | FOLL_DUMP;
+	page = follow_page(vma, addr, follflags);
 
-		err = PTR_ERR(page);
-		if (IS_ERR(page))
-			goto set_status;
+	err = PTR_ERR(page);
+	if (IS_ERR(page))
+		goto out;
 
-		err = -ENOENT;
-		if (!page)
-			goto set_status;
+	err = -ENOENT;
+	if (!page)
+		goto out;
 
-		err = page_to_nid(page);
+	err = 0;
+	if (page_to_nid(page) == node)
+		goto out_putpage;
 
-		if (err == pp->node)
-			/*
-			 * Node already in the right place
-			 */
-			goto put_and_set;
+	err = -EACCES;
+	if (page_mapcount(page) > 1 && !migrate_all)
+		goto out_putpage;
 
-		err = -EACCES;
-		if (page_mapcount(page) > 1 &&
-				!migrate_all)
-			goto put_and_set;
-
-		if (PageHuge(page)) {
-			if (PageHead(page)) {
-				isolate_huge_page(page, &pagelist);
-				err = 0;
-				pp->page = page;
-			}
-			goto put_and_set;
+	if (PageHuge(page)) {
+		if (PageHead(page)) {
+			isolate_huge_page(page, pagelist);
+			err = 0;
 		}
+	} else {
+		struct page *head;
 
-		pp->page = compound_head(page);
 		head = compound_head(page);
 		err = isolate_lru_page(head);
-		if (!err) {
-			list_add_tail(&head->lru, &pagelist);
-			mod_node_page_state(page_pgdat(head),
-				NR_ISOLATED_ANON + page_is_file_cache(head),
-				hpage_nr_pages(head));
-		}
-put_and_set:
-		/*
-		 * Either remove the duplicate refcount from
-		 * isolate_lru_page() or drop the page ref if it was
-		 * not isolated.
-		 */
-		put_page(page);
-set_status:
-		pp->status = err;
-	}
-
-	err = 0;
-	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, new_page_node, NULL,
-				(unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL);
 		if (err)
-			putback_movable_pages(&pagelist);
-	}
+			goto out_putpage;
 
+		err = 0;
+		list_add_tail(&head->lru, pagelist);
+		mod_node_page_state(page_pgdat(head),
+			NR_ISOLATED_ANON + page_is_file_cache(head),
+			hpage_nr_pages(head));
+	}
+out_putpage:
+	/*
+	 * Either remove the duplicate refcount from
+	 * isolate_lru_page() or drop the page ref if it was
+	 * not isolated.
+	 */
+	put_page(page);
+out:
 	up_read(&mm->mmap_sem);
 	return err;
 }
@@ -1593,79 +1555,79 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 			 const int __user *nodes,
 			 int __user *status, int flags)
 {
-	struct page_to_node *pm;
-	unsigned long chunk_nr_pages;
-	unsigned long chunk_start;
-	int err;
-
-	err = -ENOMEM;
-	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
-	if (!pm)
-		goto out;
+	int current_node = NUMA_NO_NODE;
+	LIST_HEAD(pagelist);
+	int start, i;
+	int err = 0, err1;
 
 	migrate_prep();
 
-	/*
-	 * Store a chunk of page_to_node array in a page,
-	 * but keep the last one as a marker
-	 */
-	chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1;
-
-	for (chunk_start = 0;
-	     chunk_start < nr_pages;
-	     chunk_start += chunk_nr_pages) {
-		int j;
+	for (i = start = 0; i < nr_pages; i++) {
+		const void __user *p;
+		unsigned long addr;
+		int node;
 
-		if (chunk_start + chunk_nr_pages > nr_pages)
-			chunk_nr_pages = nr_pages - chunk_start;
-
-		/* fill the chunk pm with addrs and nodes from user-space */
-		for (j = 0; j < chunk_nr_pages; j++) {
-			const void __user *p;
-			int node;
-
-			err = -EFAULT;
-			if (get_user(p, pages + j + chunk_start))
-				goto out_pm;
-			pm[j].addr = (unsigned long) p;
-
-			if (get_user(node, nodes + j + chunk_start))
-				goto out_pm;
-
-			err = -ENODEV;
-			if (node < 0 || node >= MAX_NUMNODES)
-				goto out_pm;
-
-			if (!node_state(node, N_MEMORY))
-				goto out_pm;
-
-			err = -EACCES;
-			if (!node_isset(node, task_nodes))
-				goto out_pm;
+		err = -EFAULT;
+		if (get_user(p, pages + i))
+			goto out_flush;
+		if (get_user(node, nodes + i))
+			goto out_flush;
+		addr = (unsigned long)p;
+
+		err = -ENODEV;
+		if (node < 0 || node >= MAX_NUMNODES)
+			goto out_flush;
+		if (!node_state(node, N_MEMORY))
+			goto out_flush;
 
-			pm[j].node = node;
+		err = -EACCES;
+		if (!node_isset(node, task_nodes))
+			goto out_flush;
+
+		if (current_node == NUMA_NO_NODE) {
+			current_node = node;
+			start = i;
+		} else if (node != current_node) {
+			err = do_move_pages_to_node(mm, &pagelist, current_node);
+			if (err)
+				goto out;
+			err = store_status(status, start, current_node, i - start);
+			if (err)
+				goto out;
+			start = i;
+			current_node = node;
 		}
 
-		/* End marker for this chunk */
-		pm[chunk_nr_pages].node = MAX_NUMNODES;
-
-		/* Migrate this chunk */
-		err = do_move_page_to_node_array(mm, pm,
-						 flags & MPOL_MF_MOVE_ALL);
-		if (err < 0)
-			goto out_pm;
+		/*
+		 * Errors in the page lookup or isolation are not fatal and we simply
+		 * report them via status
+		 */
+		err = add_page_for_migration(mm, addr, current_node,
+				&pagelist, flags & MPOL_MF_MOVE_ALL);
+		if (!err)
+			continue;
 
-		/* Return status information */
-		for (j = 0; j < chunk_nr_pages; j++)
-			if (put_user(pm[j].status, status + j + chunk_start)) {
-				err = -EFAULT;
-				goto out_pm;
-			}
-	}
-	err = 0;
+		err = store_status(status, i, err, 1);
+		if (err)
+			goto out_flush;
 
-out_pm:
-	free_page((unsigned long)pm);
+		err = do_move_pages_to_node(mm, &pagelist, current_node);
+		if (err)
+			goto out;
+		if (i > start) {
+			err = store_status(status, start, current_node, i - start);
+			if (err)
+				goto out;
+		}
+		current_node = NUMA_NO_NODE;
+	}
+out_flush:
+	/* Make sure we do not overwrite the existing error */
+	err1 = do_move_pages_to_node(mm, &pagelist, current_node);
+	if (!err1)
+		err1 = store_status(status, start, current_node, i - start);
+	if (!err)
+		err = err1;
 out:
 	return err;
 }
@@ -1866,8 +1828,7 @@ static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
 }
 
 static struct page *alloc_misplaced_dst_page(struct page *page,
-					   unsigned long data,
-					   int **result)
+					   unsigned long data)
 {
 	int nid = (int) data;
 	struct page *newpage;
@@ -1987,6 +1948,13 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 		goto out;
 
 	/*
+	 * Also do not migrate dirty pages as not all filesystems can move
+	 * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles.
+	 */
+	if (page_is_file_cache(page) && PageDirty(page))
+		goto out;
+
+	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
 	 * Optimal placement is no good if the memory bus is saturated and
 	 * all the time is being spent migrating!
diff --git a/mm/mincore.c b/mm/mincore.c
index fc37afe226e6..a66f2052c7b1 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -68,8 +68,16 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
 		 */
 		if (radix_tree_exceptional_entry(page)) {
 			swp_entry_t swp = radix_to_swp_entry(page);
-			page = find_get_page(swap_address_space(swp),
-					     swp_offset(swp));
+			struct swap_info_struct *si;
+
+			/* Prevent swap device to being swapoff under us */
+			si = get_swap_device(swp);
+			if (si) {
+				page = find_get_page(swap_address_space(swp),
+						     swp_offset(swp));
+				put_swap_device(si);
+			} else
+				page = NULL;
 		}
 	} else
 		page = find_get_page(mapping, pgoff);
diff --git a/mm/mmap.c b/mm/mmap.c
index aa0dc8231c0d..f2154fc2548b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3191,13 +3191,15 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
 		if (rlimit(RLIMIT_DATA) == 0 &&
 		    mm->data_vm + npages <= rlimit_max(RLIMIT_DATA) >> PAGE_SHIFT)
 			return true;
-		if (!ignore_rlimit_data) {
-			pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits or use boot option ignore_rlimit_data.\n",
-				     current->comm, current->pid,
-				     (mm->data_vm + npages) << PAGE_SHIFT,
-				     rlimit(RLIMIT_DATA));
+
+		pr_warn_once("%s (%d): VmData %lu exceed data ulimit %lu. Update limits%s.\n",
+			     current->comm, current->pid,
+			     (mm->data_vm + npages) << PAGE_SHIFT,
+			     rlimit(RLIMIT_DATA),
+			     ignore_rlimit_data ? "" : " or use boot option ignore_rlimit_data");
+
+		if (!ignore_rlimit_data)
 			return false;
-		}
 	}
 
 	return true;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index c1d6af7455da..625608bc8962 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -27,6 +27,7 @@
 #include <linux/pkeys.h>
 #include <linux/ksm.h>
 #include <linux/uaccess.h>
+#include <linux/mm_inline.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
@@ -89,6 +90,14 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				    page_mapcount(page) != 1)
 					continue;
 
+				/*
+				 * While migration can move some dirty pages,
+				 * it cannot move them all from MIGRATE_ASYNC
+				 * context.
+				 */
+				if (page_is_file_cache(page) && PageDirty(page))
+					continue;
+
 				/* Avoid TLB flush if possible */
 				if (pte_protnone(oldpte))
 					continue;
diff --git a/mm/nommu.c b/mm/nommu.c
index 4f8720243ae7..13723736d38f 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -457,18 +457,6 @@ void __weak vmalloc_sync_all(void)
 {
 }
 
-/**
- *	alloc_vm_area - allocate a range of kernel address space
- *	@size:		size of the area
- *
- *	Returns:	NULL on failure, vm_struct on success
- *
- *	This function reserves a range of kernel address space, and
- *	allocates pagetables to map that range.  No actual mappings
- *	are created.  If the kernel address space is not shared
- *	between processes, it syncs the pagetable across all
- *	processes.
- */
 struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	BUG();
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index f2e7dfb81eee..dfd370526909 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -185,6 +185,8 @@ static bool is_dump_unreclaim_slabs(void)
  * oom_badness - heuristic function to determine which candidate task to kill
  * @p: task struct of which task we should calculate
  * @totalpages: total present RAM allowed for page allocation
+ * @memcg: task's memory controller, if constrained
+ * @nodemask: nodemask passed to page allocator for mempolicy ooms
  *
  * The heuristic for determining which task to kill is made to be as simple and
  * predictable as possible.  The goal is to return the highest value for the
@@ -224,13 +226,6 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 		mm_pgtables_bytes(p->mm) / PAGE_SIZE;
 	task_unlock(p);
 
-	/*
-	 * Root processes get 3% bonus, just like the __vm_enough_memory()
-	 * implementation used by LSMs.
-	 */
-	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		points -= (points * 3) / 100;
-
 	/* Normalize to oom_score_adj units */
 	adj *= totalpages / 1000;
 	points += adj;
@@ -309,7 +304,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc)
 	return CONSTRAINT_NONE;
 }
 
-static int oom_evaluate_task(struct task_struct *task, void *arg)
+int oom_evaluate_task(struct task_struct *task, void *arg)
 {
 	struct oom_control *oc = arg;
 	unsigned long points;
@@ -343,26 +338,26 @@ static int oom_evaluate_task(struct task_struct *task, void *arg)
 		goto next;
 
 	/* Prefer thread group leaders for display purposes */
-	if (points == oc->chosen_points && thread_group_leader(oc->chosen))
+	if (points == oc->chosen_points && thread_group_leader(oc->chosen_task))
 		goto next;
 select:
-	if (oc->chosen)
-		put_task_struct(oc->chosen);
+	if (oc->chosen_task)
+		put_task_struct(oc->chosen_task);
 	get_task_struct(task);
-	oc->chosen = task;
+	oc->chosen_task = task;
 	oc->chosen_points = points;
 next:
 	return 0;
 abort:
-	if (oc->chosen)
-		put_task_struct(oc->chosen);
-	oc->chosen = (void *)-1UL;
+	if (oc->chosen_task)
+		put_task_struct(oc->chosen_task);
+	oc->chosen_task = INFLIGHT_VICTIM;
 	return 1;
 }
 
 /*
  * Simple selection loop. We choose the process with the highest number of
- * 'points'. In case scan was aborted, oc->chosen is set to -1.
+ * 'points'. In case scan was aborted, oc->chosen_task is set to -1.
  */
 static void select_bad_process(struct oom_control *oc)
 {
@@ -595,7 +590,8 @@ static void oom_reap_task(struct task_struct *tsk)
 	while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm))
 		schedule_timeout_idle(HZ/10);
 
-	if (attempts <= MAX_OOM_REAP_RETRIES)
+	if (attempts <= MAX_OOM_REAP_RETRIES ||
+	    test_bit(MMF_OOM_SKIP, &mm->flags))
 		goto done;
 
 
@@ -834,67 +830,22 @@ static bool task_will_free_mem(struct task_struct *task)
 	return ret;
 }
 
-static void oom_kill_process(struct oom_control *oc, const char *message)
+static void __oom_kill_process(struct task_struct *victim)
 {
-	struct task_struct *p = oc->chosen;
-	unsigned int points = oc->chosen_points;
-	struct task_struct *victim = p;
-	struct task_struct *child;
-	struct task_struct *t;
+	struct task_struct *p;
 	struct mm_struct *mm;
-	unsigned int victim_points = 0;
-	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-					      DEFAULT_RATELIMIT_BURST);
 	bool can_oom_reap = true;
 
 	/*
-	 * If the task is already exiting, don't alarm the sysadmin or kill
-	 * its children or threads, just give it access to memory reserves
-	 * so it can die quickly
+	 * __oom_kill_process() is used to kill all tasks belonging to
+	 * the selected memory cgroup, so we should check that we're not
+	 * trying to kill an unkillable task.
 	 */
-	task_lock(p);
-	if (task_will_free_mem(p)) {
-		mark_oom_victim(p);
-		wake_oom_reaper(p);
-		task_unlock(p);
-		put_task_struct(p);
+	if (is_global_init(victim) || (victim->flags & PF_KTHREAD) ||
+	    victim->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		put_task_struct(victim);
 		return;
 	}
-	task_unlock(p);
-
-	if (__ratelimit(&oom_rs))
-		dump_header(oc, p);
-
-	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
-		message, task_pid_nr(p), p->comm, points);
-
-	/*
-	 * If any of p's children has a different mm and is eligible for kill,
-	 * the one with the highest oom_badness() score is sacrificed for its
-	 * parent.  This attempts to lose the minimal amount of work done while
-	 * still freeing memory.
-	 */
-	read_lock(&tasklist_lock);
-	for_each_thread(p, t) {
-		list_for_each_entry(child, &t->children, sibling) {
-			unsigned int child_points;
-
-			if (process_shares_mm(child, p->mm))
-				continue;
-			/*
-			 * oom_badness() returns 0 if the thread is unkillable
-			 */
-			child_points = oom_badness(child,
-				oc->memcg, oc->nodemask, oc->totalpages);
-			if (child_points > victim_points) {
-				put_task_struct(victim);
-				victim = child;
-				victim_points = child_points;
-				get_task_struct(victim);
-			}
-		}
-	}
-	read_unlock(&tasklist_lock);
 
 	p = find_lock_task_mm(victim);
 	if (!p) {
@@ -969,6 +920,108 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 }
 #undef K
 
+static void oom_kill_process(struct oom_control *oc, const char *message)
+{
+	struct task_struct *p = oc->chosen_task;
+	unsigned int points = oc->chosen_points;
+	struct task_struct *victim = p;
+	struct task_struct *child;
+	struct task_struct *t;
+	unsigned int victim_points = 0;
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
+
+	/*
+	 * If the task is already exiting, don't alarm the sysadmin or kill
+	 * its children or threads, just give it access to memory reserves
+	 * so it can die quickly
+	 */
+	task_lock(p);
+	if (task_will_free_mem(p)) {
+		mark_oom_victim(p);
+		wake_oom_reaper(p);
+		task_unlock(p);
+		put_task_struct(p);
+		return;
+	}
+	task_unlock(p);
+
+	if (__ratelimit(&oom_rs))
+		dump_header(oc, p);
+
+	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points);
+
+	/*
+	 * If any of p's children has a different mm and is eligible for kill,
+	 * the one with the highest oom_badness() score is sacrificed for its
+	 * parent.  This attempts to lose the minimal amount of work done while
+	 * still freeing memory.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
+		list_for_each_entry(child, &t->children, sibling) {
+			unsigned int child_points;
+
+			if (process_shares_mm(child, p->mm))
+				continue;
+			/*
+			 * oom_badness() returns 0 if the thread is unkillable
+			 */
+			child_points = oom_badness(child,
+				oc->memcg, oc->nodemask, oc->totalpages);
+			if (child_points > victim_points) {
+				put_task_struct(victim);
+				victim = child;
+				victim_points = child_points;
+				get_task_struct(victim);
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+
+	__oom_kill_process(victim);
+}
+
+static int oom_kill_memcg_member(struct task_struct *task, void *unused)
+{
+	get_task_struct(task);
+	__oom_kill_process(task);
+	return 0;
+}
+
+static bool oom_kill_memcg_victim(struct oom_control *oc)
+{
+	if (oc->chosen_memcg == NULL || oc->chosen_memcg == INFLIGHT_VICTIM)
+		return oc->chosen_memcg;
+
+	/*
+	 * If memory.oom_group is set, kill all tasks belonging to the sub-tree
+	 * of the chosen memory cgroup, otherwise kill the task with the biggest
+	 * memory footprint.
+	 */
+	if (mem_cgroup_oom_group(oc->chosen_memcg)) {
+		mem_cgroup_scan_tasks(oc->chosen_memcg, oom_kill_memcg_member,
+				      NULL);
+		/* We have one or more terminating processes at this point. */
+		oc->chosen_task = INFLIGHT_VICTIM;
+	} else {
+		oc->chosen_points = 0;
+		oc->chosen_task = NULL;
+		mem_cgroup_scan_tasks(oc->chosen_memcg, oom_evaluate_task, oc);
+
+		if (oc->chosen_task == NULL ||
+		    oc->chosen_task == INFLIGHT_VICTIM)
+			goto out;
+
+		__oom_kill_process(oc->chosen_task);
+	}
+
+out:
+	mem_cgroup_put(oc->chosen_memcg);
+	return oc->chosen_task;
+}
+
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
@@ -1021,6 +1074,7 @@ bool out_of_memory(struct oom_control *oc)
 {
 	unsigned long freed = 0;
 	enum oom_constraint constraint = CONSTRAINT_NONE;
+	bool delay = false; /* if set, delay next allocation attempt */
 
 	if (oom_killer_disabled)
 		return false;
@@ -1065,27 +1119,37 @@ bool out_of_memory(struct oom_control *oc)
 	    current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) &&
 	    current->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
 		get_task_struct(current);
-		oc->chosen = current;
+		oc->chosen_task = current;
 		oom_kill_process(oc, "Out of memory (oom_kill_allocating_task)");
 		return true;
 	}
 
+	if (mem_cgroup_select_oom_victim(oc) && oom_kill_memcg_victim(oc)) {
+		delay = true;
+		goto out;
+	}
+
 	select_bad_process(oc);
 	/* Found nothing?!?! Either we hang forever, or we panic. */
-	if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
+	if (!oc->chosen_task && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) {
 		dump_header(oc, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
-	if (oc->chosen && oc->chosen != (void *)-1UL) {
+	if (oc->chosen_task && oc->chosen_task != INFLIGHT_VICTIM) {
 		oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" :
 				 "Memory cgroup out of memory");
-		/*
-		 * Give the killed process a good chance to exit before trying
-		 * to allocate memory again.
-		 */
-		schedule_timeout_killable(1);
+		delay = true;
 	}
-	return !!oc->chosen;
+
+out:
+	/*
+	 * Give the killed process a good chance to exit before trying
+	 * to allocate memory again.
+	 */
+	if (delay)
+		schedule_timeout_killable(1);
+
+	return !!oc->chosen_task;
 }
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4ea018263210..b4390db64da3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -205,17 +205,18 @@ static void __free_pages_ok(struct page *page, unsigned int order);
  * TBD: should special case ZONE_DMA32 machines here - in those we normally
  * don't need any ZONE_NORMAL reservation
  */
-int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
+int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES] = {
 #ifdef CONFIG_ZONE_DMA
-	 256,
+	[ZONE_DMA] = 256,
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	 256,
+	[ZONE_DMA32] = 256,
 #endif
+	[ZONE_NORMAL] = 32,
 #ifdef CONFIG_HIGHMEM
-	 32,
+	[ZONE_HIGHMEM] = 0,
 #endif
-	 32,
+	[ZONE_MOVABLE] = 0,
 };
 
 EXPORT_SYMBOL(totalram_pages);
@@ -265,17 +266,19 @@ int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
 int watermark_scale_factor = 10;
 
-static unsigned long __meminitdata nr_kernel_pages;
-static unsigned long __meminitdata nr_all_pages;
-static unsigned long __meminitdata dma_reserve;
+static unsigned long nr_kernel_pages __meminitdata;
+static unsigned long nr_all_pages __meminitdata;
+static unsigned long dma_reserve __meminitdata;
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
-static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-static unsigned long __initdata required_kernelcore;
-static unsigned long __initdata required_movablecore;
-static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
-static bool mirrored_kernelcore;
+static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long required_kernelcore __initdata;
+static unsigned long required_kernelcore_percent __initdata;
+static unsigned long required_movablecore __initdata;
+static unsigned long required_movablecore_percent __initdata;
+static unsigned long zone_movable_pfn[MAX_NUMNODES] __meminitdata;
+static bool mirrored_kernelcore __meminitdata;
 
 /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
 int movable_zone;
@@ -292,40 +295,6 @@ EXPORT_SYMBOL(nr_online_nodes);
 int page_group_by_mobility_disabled __read_mostly;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-
-/*
- * Determine how many pages need to be initialized during early boot
- * (non-deferred initialization).
- * The value of first_deferred_pfn will be set later, once non-deferred pages
- * are initialized, but for now set it ULONG_MAX.
- */
-static inline void reset_deferred_meminit(pg_data_t *pgdat)
-{
-	phys_addr_t start_addr, end_addr;
-	unsigned long max_pgcnt;
-	unsigned long reserved;
-
-	/*
-	 * Initialise at least 2G of a node but also take into account that
-	 * two large system hashes that can take up 1GB for 0.25TB/node.
-	 */
-	max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
-			(pgdat->node_spanned_pages >> 8));
-
-	/*
-	 * Compensate the all the memblock reservations (e.g. crash kernel)
-	 * from the initial estimation to make sure we will initialize enough
-	 * memory to boot.
-	 */
-	start_addr = PFN_PHYS(pgdat->node_start_pfn);
-	end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
-	reserved = memblock_reserved_memory_within(start_addr, end_addr);
-	max_pgcnt += PHYS_PFN(reserved);
-
-	pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
-	pgdat->first_deferred_pfn = ULONG_MAX;
-}
-
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
@@ -361,10 +330,6 @@ static inline bool update_defer_init(pg_data_t *pgdat,
 	return true;
 }
 #else
-static inline void reset_deferred_meminit(pg_data_t *pgdat)
-{
-}
-
 static inline bool early_page_uninitialised(unsigned long pfn)
 {
 	return false;
@@ -1099,6 +1064,15 @@ static bool bulkfree_pcp_prepare(struct page *page)
 }
 #endif /* CONFIG_DEBUG_VM */
 
+static inline void prefetch_buddy(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
+	struct page *buddy = page + (buddy_pfn - pfn);
+
+	prefetch(buddy);
+}
+
 /*
  * Frees a number of pages from the PCP lists
  * Assumes all pages on list are in same zone, and of same order.
@@ -1115,13 +1089,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 {
 	int migratetype = 0;
 	int batch_free = 0;
+	int prefetch_nr = 0;
 	bool isolated_pageblocks;
-
-	spin_lock(&zone->lock);
-	isolated_pageblocks = has_isolate_pageblock(zone);
+	struct page *page, *tmp;
+	LIST_HEAD(head);
 
 	while (count) {
-		struct page *page;
 		struct list_head *list;
 
 		/*
@@ -1143,26 +1116,48 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			batch_free = count;
 
 		do {
-			int mt;	/* migratetype of the to-be-freed page */
-
 			page = list_last_entry(list, struct page, lru);
-			/* must delete as __free_one_page list manipulates */
+			/* must delete to avoid corrupting pcp list */
 			list_del(&page->lru);
-
-			mt = get_pcppage_migratetype(page);
-			/* MIGRATE_ISOLATE page should not go to pcplists */
-			VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
-			/* Pageblock could have been isolated meanwhile */
-			if (unlikely(isolated_pageblocks))
-				mt = get_pageblock_migratetype(page);
+			pcp->count--;
 
 			if (bulkfree_pcp_prepare(page))
 				continue;
 
-			__free_one_page(page, page_to_pfn(page), zone, 0, mt);
-			trace_mm_page_pcpu_drain(page, 0, mt);
+			list_add_tail(&page->lru, &head);
+
+			/*
+			 * We are going to put the page back to the global
+			 * pool, prefetch its buddy to speed up later access
+			 * under zone->lock. It is believed the overhead of
+			 * an additional test and calculating buddy_pfn here
+			 * can be offset by reduced memory latency later. To
+			 * avoid excessive prefetching due to large count, only
+			 * prefetch buddy for the first pcp->batch nr of pages.
+			 */
+			if (prefetch_nr++ < pcp->batch)
+				prefetch_buddy(page);
 		} while (--count && --batch_free && !list_empty(list));
 	}
+
+	spin_lock(&zone->lock);
+	isolated_pageblocks = has_isolate_pageblock(zone);
+
+	/*
+	 * Use safe version since after __free_one_page(),
+	 * page->lru.next will not point to original list.
+	 */
+	list_for_each_entry_safe(page, tmp, &head, lru) {
+		int mt = get_pcppage_migratetype(page);
+		/* MIGRATE_ISOLATE page should not go to pcplists */
+		VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+		/* Pageblock could have been isolated meanwhile */
+		if (unlikely(isolated_pageblocks))
+			mt = get_pageblock_migratetype(page);
+
+		__free_one_page(page, page_to_pfn(page), zone, 0, mt);
+		trace_mm_page_pcpu_drain(page, 0, mt);
+	}
 	spin_unlock(&zone->lock);
 }
 
@@ -1181,10 +1176,9 @@ static void free_one_page(struct zone *zone,
 }
 
 static void __meminit __init_single_page(struct page *page, unsigned long pfn,
-				unsigned long zone, int nid, bool zero)
+				unsigned long zone, int nid)
 {
-	if (zero)
-		mm_zero_struct_page(page);
+	mm_zero_struct_page(page);
 	set_page_links(page, zone, nid, pfn);
 	init_page_count(page);
 	page_mapcount_reset(page);
@@ -1198,12 +1192,6 @@ static void __meminit __init_single_page(struct page *page, unsigned long pfn,
 #endif
 }
 
-static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
-					int nid, bool zero)
-{
-	return __init_single_page(pfn_to_page(pfn), pfn, zone, nid, zero);
-}
-
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 static void __meminit init_reserved_page(unsigned long pfn)
 {
@@ -1222,7 +1210,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
 		if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
 			break;
 	}
-	__init_single_pfn(pfn, zid, nid, true);
+	__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
 }
 #else
 static inline void init_reserved_page(unsigned long pfn)
@@ -1506,7 +1494,7 @@ static void __init deferred_free_pages(int nid, int zid, unsigned long pfn,
 		} else if (!(pfn & nr_pgmask)) {
 			deferred_free_range(pfn - nr_free, nr_free);
 			nr_free = 1;
-			cond_resched();
+			touch_nmi_watchdog();
 		} else {
 			nr_free++;
 		}
@@ -1535,11 +1523,11 @@ static unsigned long  __init deferred_init_pages(int nid, int zid,
 			continue;
 		} else if (!page || !(pfn & nr_pgmask)) {
 			page = pfn_to_page(pfn);
-			cond_resched();
+			touch_nmi_watchdog();
 		} else {
 			page++;
 		}
-		__init_single_page(page, pfn, zid, nid, true);
+		__init_single_page(page, pfn, zid, nid);
 		nr_pages++;
 	}
 	return (nr_pages);
@@ -1552,23 +1540,25 @@ static int __init deferred_init_memmap(void *data)
 	int nid = pgdat->node_id;
 	unsigned long start = jiffies;
 	unsigned long nr_pages = 0;
-	unsigned long spfn, epfn;
+	unsigned long spfn, epfn, first_init_pfn, flags;
 	phys_addr_t spa, epa;
 	int zid;
 	struct zone *zone;
-	unsigned long first_init_pfn = pgdat->first_deferred_pfn;
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 	u64 i;
 
+	/* Bind memory initialisation thread to a local node if possible */
+	if (!cpumask_empty(cpumask))
+		set_cpus_allowed_ptr(current, cpumask);
+
+	pgdat_resize_lock(pgdat, &flags);
+	first_init_pfn = pgdat->first_deferred_pfn;
 	if (first_init_pfn == ULONG_MAX) {
+		pgdat_resize_unlock(pgdat, &flags);
 		pgdat_init_report_one_done();
 		return 0;
 	}
 
-	/* Bind memory initialisation thread to a local node if possible */
-	if (!cpumask_empty(cpumask))
-		set_cpus_allowed_ptr(current, cpumask);
-
 	/* Sanity check boundaries */
 	BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
 	BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
@@ -1598,6 +1588,7 @@ static int __init deferred_init_memmap(void *data)
 		epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
 		deferred_free_pages(nid, zid, spfn, epfn);
 	}
+	pgdat_resize_unlock(pgdat, &flags);
 
 	/* Sanity check that the next zone really is unpopulated */
 	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
@@ -1608,6 +1599,117 @@ static int __init deferred_init_memmap(void *data)
 	pgdat_init_report_one_done();
 	return 0;
 }
+
+/*
+ * During boot we initialize deferred pages on-demand, as needed, but once
+ * page_alloc_init_late() has finished, the deferred pages are all initialized,
+ * and we can permanently disable that path.
+ */
+static DEFINE_STATIC_KEY_TRUE(deferred_pages);
+
+/*
+ * If this zone has deferred pages, try to grow it by initializing enough
+ * deferred pages to satisfy the allocation specified by order, rounded up to
+ * the nearest PAGES_PER_SECTION boundary.  So we're adding memory in increments
+ * of SECTION_SIZE bytes by initializing struct pages in increments of
+ * PAGES_PER_SECTION * sizeof(struct page) bytes.
+ *
+ * Return true when zone was grown, otherwise return false. We return true even
+ * when we grow less than requested, to let the caller decide if there are
+ * enough pages to satisfy the allocation.
+ *
+ * Note: We use noinline because this function is needed only during boot, and
+ * it is called from a __ref function _deferred_grow_zone. This way we are
+ * making sure that it is not inlined into permanent text section.
+ */
+static noinline bool __init
+deferred_grow_zone(struct zone *zone, unsigned int order)
+{
+	int zid = zone_idx(zone);
+	int nid = zone_to_nid(zone);
+	pg_data_t *pgdat = NODE_DATA(nid);
+	unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
+	unsigned long nr_pages = 0;
+	unsigned long first_init_pfn, spfn, epfn, t, flags;
+	unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
+	phys_addr_t spa, epa;
+	u64 i;
+
+	/* Only the last zone may have deferred pages */
+	if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
+		return false;
+
+	pgdat_resize_lock(pgdat, &flags);
+
+	/*
+	 * If deferred pages have been initialized while we were waiting for
+	 * the lock, return true, as the zone was grown.  The caller will retry
+	 * this zone.  We won't return to this function since the caller also
+	 * has this static branch.
+	 */
+	if (!static_branch_unlikely(&deferred_pages)) {
+		pgdat_resize_unlock(pgdat, &flags);
+		return true;
+	}
+
+	/*
+	 * If someone grew this zone while we were waiting for spinlock, return
+	 * true, as there might be enough pages already.
+	 */
+	if (first_deferred_pfn != pgdat->first_deferred_pfn) {
+		pgdat_resize_unlock(pgdat, &flags);
+		return true;
+	}
+
+	first_init_pfn = max(zone->zone_start_pfn, first_deferred_pfn);
+
+	if (first_init_pfn >= pgdat_end_pfn(pgdat)) {
+		pgdat_resize_unlock(pgdat, &flags);
+		return false;
+	}
+
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
+		spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
+		epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+
+		while (spfn < epfn && nr_pages < nr_pages_needed) {
+			t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
+			first_deferred_pfn = min(t, epfn);
+			nr_pages += deferred_init_pages(nid, zid, spfn,
+							first_deferred_pfn);
+			spfn = first_deferred_pfn;
+		}
+
+		if (nr_pages >= nr_pages_needed)
+			break;
+	}
+
+	for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
+		spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
+		epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa));
+		deferred_free_pages(nid, zid, spfn, epfn);
+
+		if (first_deferred_pfn == epfn)
+			break;
+	}
+	pgdat->first_deferred_pfn = first_deferred_pfn;
+	pgdat_resize_unlock(pgdat, &flags);
+
+	return nr_pages > 0;
+}
+
+/*
+ * deferred_grow_zone() is __init, but it is called from
+ * get_page_from_freelist() during early boot until deferred_pages permanently
+ * disables this call. This is why we have refdata wrapper to avoid warning,
+ * and to ensure that the function body gets unloaded.
+ */
+static bool __ref
+_deferred_grow_zone(struct zone *zone, unsigned int order)
+{
+	return deferred_grow_zone(zone, order);
+}
+
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 void __init page_alloc_init_late(void)
@@ -1626,6 +1728,12 @@ void __init page_alloc_init_late(void)
 	/* Block until all are initialised */
 	wait_for_completion(&pgdat_init_all_done_comp);
 
+	/*
+	 * We initialized the rest of the deferred pages.  Permanently disable
+	 * on-demand struct page initialization.
+	 */
+	static_branch_disable(&deferred_pages);
+
 	/* Reinit limits that are based on free pages after the kernel is up */
 	files_maxfiles_init();
 #endif
@@ -1639,16 +1747,38 @@ void __init page_alloc_init_late(void)
 }
 
 #ifdef CONFIG_CMA
+static void __init adjust_present_page_count(struct page *page, long count)
+{
+	struct zone *zone = page_zone(page);
+
+	/* We don't need to hold a lock since it is boot-up process */
+	zone->present_pages += count;
+}
+
 /* Free whole pageblock and set its migration type to MIGRATE_CMA. */
 void __init init_cma_reserved_pageblock(struct page *page)
 {
 	unsigned i = pageblock_nr_pages;
+	unsigned long pfn = page_to_pfn(page);
 	struct page *p = page;
+	int nid = page_to_nid(page);
+
+	/*
+	 * ZONE_MOVABLE will steal present pages from other zones by
+	 * changing page links so page_zone() is changed. Before that,
+	 * we need to adjust previous zone's page count first.
+	 */
+	adjust_present_page_count(page, -pageblock_nr_pages);
 
 	do {
 		__ClearPageReserved(p);
 		set_page_count(p, 0);
-	} while (++p, --i);
+
+		/* Steal pages from other zones */
+		set_page_links(p, ZONE_MOVABLE, nid, pfn);
+	} while (++p, ++pfn, --i);
+
+	adjust_present_page_count(page, pageblock_nr_pages);
 
 	set_pageblock_migratetype(page, MIGRATE_CMA);
 
@@ -2418,10 +2548,8 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 	local_irq_save(flags);
 	batch = READ_ONCE(pcp->batch);
 	to_drain = min(pcp->count, batch);
-	if (to_drain > 0) {
+	if (to_drain > 0)
 		free_pcppages_bulk(zone, to_drain, pcp);
-		pcp->count -= to_drain;
-	}
 	local_irq_restore(flags);
 }
 #endif
@@ -2443,10 +2571,8 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 	pset = per_cpu_ptr(zone->pageset, cpu);
 
 	pcp = &pset->pcp;
-	if (pcp->count) {
+	if (pcp->count)
 		free_pcppages_bulk(zone, pcp->count, pcp);
-		pcp->count = 0;
-	}
 	local_irq_restore(flags);
 }
 
@@ -2670,7 +2796,6 @@ static void free_unref_page_commit(struct page *page, unsigned long pfn)
 	if (pcp->count >= pcp->high) {
 		unsigned long batch = READ_ONCE(pcp->batch);
 		free_pcppages_bulk(zone, batch, pcp);
-		pcp->count -= batch;
 	}
 }
 
@@ -2768,7 +2893,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
 		 * exists.
 		 */
 		watermark = min_wmark_pages(zone) + (1UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
+		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
 			return 0;
 
 		__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3044,12 +3169,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	}
 
 
-#ifdef CONFIG_CMA
-	/* If allocation can't use CMA areas don't use free CMA pages */
-	if (!(alloc_flags & ALLOC_CMA))
-		free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
 	/*
 	 * Check watermarks for an order-0 allocation request. If these
 	 * are not met, then a high-order request also cannot go ahead
@@ -3076,10 +3195,8 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 		}
 
 #ifdef CONFIG_CMA
-		if ((alloc_flags & ALLOC_CMA) &&
-		    !list_empty(&area->free_list[MIGRATE_CMA])) {
+		if (!list_empty(&area->free_list[MIGRATE_CMA]))
 			return true;
-		}
 #endif
 		if (alloc_harder &&
 			!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3099,13 +3216,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx, unsigned int alloc_flags)
 {
 	long free_pages = zone_page_state(z, NR_FREE_PAGES);
-	long cma_pages = 0;
-
-#ifdef CONFIG_CMA
-	/* If allocation can't use CMA areas don't use free CMA pages */
-	if (!(alloc_flags & ALLOC_CMA))
-		cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
 
 	/*
 	 * Fast check for order-0 only. If this fails then the reserves
@@ -3114,7 +3224,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	 * the caller is !atomic then it'll uselessly search the free
 	 * list. That corner case is then slower but it is harmless.
 	 */
-	if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
+	if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
 		return true;
 
 	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3205,6 +3315,16 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
 				       ac_classzone_idx(ac), alloc_flags)) {
 			int ret;
 
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+			/*
+			 * Watermark failed for this zone, but see if we can
+			 * grow this zone if it contains deferred pages.
+			 */
+			if (static_branch_unlikely(&deferred_pages)) {
+				if (_deferred_grow_zone(zone, order))
+					goto try_this_zone;
+			}
+#endif
 			/* Checked here to keep the fast path fast */
 			BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 			if (alloc_flags & ALLOC_NO_WATERMARKS)
@@ -3246,6 +3366,14 @@ try_this_zone:
 				reserve_highatomic_pageblock(page, zone, order);
 
 			return page;
+		} else {
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+			/* Try again if zone has deferred pages */
+			if (static_branch_unlikely(&deferred_pages)) {
+				if (_deferred_grow_zone(zone, order))
+					goto try_this_zone;
+			}
+#endif
 		}
 	}
 
@@ -3685,16 +3813,18 @@ retry:
 	return page;
 }
 
-static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
+static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
+			     const struct alloc_context *ac)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	pg_data_t *last_pgdat = NULL;
+	enum zone_type high_zoneidx = ac->high_zoneidx;
 
-	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
-					ac->high_zoneidx, ac->nodemask) {
+	for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx,
+					ac->nodemask) {
 		if (last_pgdat != zone->zone_pgdat)
-			wakeup_kswapd(zone, order, ac->high_zoneidx);
+			wakeup_kswapd(zone, gfp_mask, order, high_zoneidx);
 		last_pgdat = zone->zone_pgdat;
 	}
 }
@@ -3730,10 +3860,6 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	return alloc_flags;
 }
 
@@ -3973,7 +4099,7 @@ retry_cpuset:
 		goto nopage;
 
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
-		wake_all_kswapds(order, ac);
+		wake_all_kswapds(order, gfp_mask, ac);
 
 	/*
 	 * The adjusted alloc_flags might result in immediate success, so try
@@ -4031,7 +4157,7 @@ retry_cpuset:
 retry:
 	/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
-		wake_all_kswapds(order, ac);
+		wake_all_kswapds(order, gfp_mask, ac);
 
 	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
 	if (reserve_flags)
@@ -4200,9 +4326,6 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 	if (should_fail_alloc_page(gfp_mask, order))
 		return false;
 
-	if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
-		*alloc_flags |= ALLOC_CMA;
-
 	return true;
 }
 
@@ -4612,6 +4735,13 @@ long si_mem_available(void)
 		     min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2,
 			 wmark_low);
 
+	/*
+	 * Part of the kernel memory, which can be released under memory
+	 * pressure.
+	 */
+	available += global_node_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >>
+		PAGE_SHIFT;
+
 	if (available < 0)
 		available = 0;
 	return available;
@@ -5334,6 +5464,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	pg_data_t *pgdat = NODE_DATA(nid);
 	unsigned long pfn;
 	unsigned long nr_initialised = 0;
+	struct page *page;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	struct memblock_region *r = NULL, *tmp;
 #endif
@@ -5386,6 +5517,11 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 #endif
 
 not_early:
+		page = pfn_to_page(pfn);
+		__init_single_page(page, pfn, zone, nid);
+		if (context == MEMMAP_HOTPLUG)
+			SetPageReserved(page);
+
 		/*
 		 * Mark the block movable so that blocks are reserved for
 		 * movable at startup. This will force kernel allocations
@@ -5402,15 +5538,8 @@ not_early:
 		 * because this is done early in sparse_add_one_section
 		 */
 		if (!(pfn & (pageblock_nr_pages - 1))) {
-			struct page *page = pfn_to_page(pfn);
-
-			__init_single_page(page, pfn, zone, nid,
-					context != MEMMAP_HOTPLUG);
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
 			cond_resched();
-		} else {
-			__init_single_pfn(pfn, zone, nid,
-					context != MEMMAP_HOTPLUG);
 		}
 	}
 }
@@ -6079,6 +6208,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 {
 	enum zone_type j;
 	int nid = pgdat->node_id;
+	unsigned long node_end_pfn = 0;
 
 	pgdat_resize_init(pgdat);
 #ifdef CONFIG_NUMA_BALANCING
@@ -6106,9 +6236,13 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;
 		unsigned long zone_start_pfn = zone->zone_start_pfn;
+		unsigned long movable_size = 0;
 
 		size = zone->spanned_pages;
 		realsize = freesize = zone->present_pages;
+		if (zone_end_pfn(zone) > node_end_pfn)
+			node_end_pfn = zone_end_pfn(zone);
+
 
 		/*
 		 * Adjust freesize so that it accounts for how much memory
@@ -6157,12 +6291,30 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 		zone_seqlock_init(zone);
 		zone_pcp_init(zone);
 
-		if (!size)
+		/*
+		 * The size of the CMA area is unknown now so we need to
+		 * prepare the memory for the usemap at maximum.
+		 */
+		if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
+			pgdat->node_spanned_pages) {
+			movable_size = node_end_pfn - pgdat->node_start_pfn;
+		}
+
+		if (!size && !movable_size)
 			continue;
 
 		set_pageblock_order();
-		setup_usemap(pgdat, zone, zone_start_pfn, size);
-		init_currently_empty_zone(zone, zone_start_pfn, size);
+		if (movable_size) {
+			zone->zone_start_pfn = pgdat->node_start_pfn;
+			zone->spanned_pages = movable_size;
+			setup_usemap(pgdat, zone,
+				pgdat->node_start_pfn, movable_size);
+			init_currently_empty_zone(zone,
+				pgdat->node_start_pfn, movable_size);
+		} else {
+			setup_usemap(pgdat, zone, zone_start_pfn, size);
+			init_currently_empty_zone(zone, zone_start_pfn, size);
+		}
 		memmap_init(size, nid, j, zone_start_pfn);
 	}
 }
@@ -6241,7 +6393,15 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 
 	alloc_node_mem_map(pgdat);
 
-	reset_deferred_meminit(pgdat);
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+	/*
+	 * We start only with one section of pages, more pages are added as
+	 * needed until the rest of deferred pages are initialized.
+	 */
+	pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
+					 pgdat->node_spanned_pages);
+	pgdat->first_deferred_pfn = ULONG_MAX;
+#endif
 	free_area_init_core(pgdat);
 }
 
@@ -6471,7 +6631,18 @@ static void __init find_zone_movable_pfns_for_nodes(void)
 	}
 
 	/*
-	 * If movablecore=nn[KMG] was specified, calculate what size of
+	 * If kernelcore=nn% or movablecore=nn% was specified, calculate the
+	 * amount of necessary memory.
+	 */
+	if (required_kernelcore_percent)
+		required_kernelcore = (totalpages * 100 * required_kernelcore_percent) /
+				       10000UL;
+	if (required_movablecore_percent)
+		required_movablecore = (totalpages * 100 * required_movablecore_percent) /
+					10000UL;
+
+	/*
+	 * If movablecore= was specified, calculate what size of
 	 * kernelcore that corresponds so that memory usable for
 	 * any allocation type is evenly spread. If both kernelcore
 	 * and movablecore are specified, then the value of kernelcore
@@ -6711,18 +6882,30 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	zero_resv_unavail();
 }
 
-static int __init cmdline_parse_core(char *p, unsigned long *core)
+static int __init cmdline_parse_core(char *p, unsigned long *core,
+				     unsigned long *percent)
 {
 	unsigned long long coremem;
+	char *endptr;
+
 	if (!p)
 		return -EINVAL;
 
-	coremem = memparse(p, &p);
-	*core = coremem >> PAGE_SHIFT;
+	/* Value may be a percentage of total memory, otherwise bytes */
+	coremem = simple_strtoull(p, &endptr, 0);
+	if (*endptr == '%') {
+		/* Paranoid check for percent values greater than 100 */
+		WARN_ON(coremem > 100);
 
-	/* Paranoid check that UL is enough for the coremem value */
-	WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
+		*percent = coremem;
+	} else {
+		coremem = memparse(p, &p);
+		/* Paranoid check that UL is enough for the coremem value */
+		WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
 
+		*core = coremem >> PAGE_SHIFT;
+		*percent = 0UL;
+	}
 	return 0;
 }
 
@@ -6738,7 +6921,8 @@ static int __init cmdline_parse_kernelcore(char *p)
 		return 0;
 	}
 
-	return cmdline_parse_core(p, &required_kernelcore);
+	return cmdline_parse_core(p, &required_kernelcore,
+				  &required_kernelcore_percent);
 }
 
 /*
@@ -6747,7 +6931,8 @@ static int __init cmdline_parse_kernelcore(char *p)
  */
 static int __init cmdline_parse_movablecore(char *p)
 {
-	return cmdline_parse_core(p, &required_movablecore);
+	return cmdline_parse_core(p, &required_movablecore,
+				  &required_movablecore_percent);
 }
 
 early_param("kernelcore", cmdline_parse_kernelcore);
@@ -6971,13 +7156,15 @@ static void setup_per_zone_lowmem_reserve(void)
 				struct zone *lower_zone;
 
 				idx--;
-
-				if (sysctl_lowmem_reserve_ratio[idx] < 1)
-					sysctl_lowmem_reserve_ratio[idx] = 1;
-
 				lower_zone = pgdat->node_zones + idx;
-				lower_zone->lowmem_reserve[j] = managed_pages /
-					sysctl_lowmem_reserve_ratio[idx];
+
+				if (sysctl_lowmem_reserve_ratio[idx] < 1) {
+					sysctl_lowmem_reserve_ratio[idx] = 0;
+					lower_zone->lowmem_reserve[j] = 0;
+				} else {
+					lower_zone->lowmem_reserve[j] =
+						managed_pages / sysctl_lowmem_reserve_ratio[idx];
+				}
 				managed_pages += lower_zone->managed_pages;
 			}
 		}
@@ -7591,7 +7778,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		cc->nr_migratepages -= nr_reclaimed;
 
 		ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
-				    NULL, 0, cc->mode, MR_CMA);
+				    NULL, 0, cc->mode, MR_CONTIG_RANGE);
 	}
 	if (ret < 0) {
 		putback_movable_pages(&cc->migratepages);
@@ -7611,11 +7798,11 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
  * @gfp_mask:	GFP mask to use during compaction
  *
  * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
- * aligned, however it's the caller's responsibility to guarantee that
- * we are the only thread that changes migrate type of pageblocks the
- * pages fall in.
+ * aligned.  The PFN range must belong to a single zone.
  *
- * The PFN range must belong to a single zone.
+ * The first thing this routine does is attempt to MIGRATE_ISOLATE all
+ * pageblocks in the range.  Once isolated, the pageblocks should not
+ * be modified by others.
  *
  * Returns zero on success or negative error code.  On success all
  * pages which PFN is in [start, end) are allocated for the caller and
@@ -7768,7 +7955,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
 }
 #endif
 
-#ifdef CONFIG_MEMORY_HOTPLUG
+#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.
diff --git a/mm/page_idle.c b/mm/page_idle.c
index 0a49374e6931..e412a63b2b74 100644
--- a/mm/page_idle.c
+++ b/mm/page_idle.c
@@ -65,11 +65,15 @@ static bool page_idle_clear_pte_refs_one(struct page *page,
 	while (page_vma_mapped_walk(&pvmw)) {
 		addr = pvmw.address;
 		if (pvmw.pte) {
-			referenced = ptep_clear_young_notify(vma, addr,
-					pvmw.pte);
+			/*
+			 * For PTE-mapped THP, one sub page is referenced,
+			 * the whole THP is referenced.
+			 */
+			if (ptep_clear_young_notify(vma, addr, pvmw.pte))
+				referenced = true;
 		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
-			referenced = pmdp_clear_young_notify(vma, addr,
-					pvmw.pmd);
+			if (pmdp_clear_young_notify(vma, addr, pvmw.pmd))
+				referenced = true;
 		} else {
 			/* unexpected pmd-mapped page? */
 			WARN_ON_ONCE(1);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 165ed8117bd1..43e085608846 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -28,6 +28,14 @@ static int set_migratetype_isolate(struct page *page, int migratetype,
 
 	spin_lock_irqsave(&zone->lock, flags);
 
+	/*
+	 * We assume the caller intended to SET migrate type to isolate.
+	 * If it is already set, then someone else must have raced and
+	 * set it before us.  Return -EBUSY
+	 */
+	if (is_migrate_isolate_page(page))
+		goto out;
+
 	pfn = page_to_pfn(page);
 	arg.start_pfn = pfn;
 	arg.nr_pages = pageblock_nr_pages;
@@ -166,7 +174,15 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * future will not be allocated again.
  *
  * start_pfn/end_pfn must be aligned to pageblock_order.
- * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
+ * Return 0 on success and -EBUSY if any part of range cannot be isolated.
+ *
+ * There is no high level synchronization mechanism that prevents two threads
+ * from trying to isolate overlapping ranges.  If this happens, one thread
+ * will notice pageblocks in the overlapping range already set to isolate.
+ * This happens in set_migratetype_isolate, and set_migratetype_isolate
+ * returns an error.  We then clean up by restoring the migration type on
+ * pageblocks we may have modified and return -EBUSY to caller.  This
+ * prevents two threads from simultaneously working on overlapping ranges.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     unsigned migratetype, bool skip_hwpoisoned_pages)
@@ -293,8 +309,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	return pfn < end_pfn ? -EBUSY : 0;
 }
 
-struct page *alloc_migrate_target(struct page *page, unsigned long private,
-				  int **resultp)
+struct page *alloc_migrate_target(struct page *page, unsigned long private)
 {
 	return new_page_nodemask(page, numa_node_id(), &node_states[N_MEMORY]);
 }
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 7172e0a80e13..77d9e791ae8a 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -35,7 +35,7 @@ static depot_stack_handle_t early_handle;
 
 static void init_early_allocated_pages(void);
 
-static int early_page_owner_param(char *buf)
+static int __init early_page_owner_param(char *buf)
 {
 	if (!buf)
 		return -EINVAL;
@@ -274,7 +274,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 	 */
 	for (; pfn < end_pfn; ) {
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
@@ -541,7 +541,7 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
 		unsigned long block_end_pfn;
 
 		if (!pfn_valid(pfn)) {
-			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
+			pfn = ALIGN(pfn + 1, pageblock_nr_pages);
 			continue;
 		}
 
diff --git a/mm/page_poison.c b/mm/page_poison.c
index e83fd44867de..aa2b3d34e8ea 100644
--- a/mm/page_poison.c
+++ b/mm/page_poison.c
@@ -9,7 +9,7 @@
 
 static bool want_page_poisoning __read_mostly;
 
-static int early_page_poison_param(char *buf)
+static int __init early_page_poison_param(char *buf)
 {
 	if (!buf)
 		return -EINVAL;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 8d2da5dec1e0..c3084ff2569d 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -258,6 +258,9 @@ static int __walk_page_range(unsigned long start, unsigned long end,
 
 /**
  * walk_page_range - walk page table with caller specific callbacks
+ * @start: start address of the virtual address range
+ * @end: end address of the virtual address range
+ * @walk: mm_walk structure defining the callbacks and the target address space
  *
  * Recursively walk the page table tree of the process represented by @walk->mm
  * within the virtual address range [@start, @end). During walking, we can do
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 7a58460bfd27..063ff60ecd90 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -223,18 +223,7 @@ alloc_buffer:
 
 	return 0;
 }
-
-static int percpu_stats_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, percpu_stats_show, NULL);
-}
-
-static const struct file_operations percpu_stats_fops = {
-	.open		= percpu_stats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(percpu_stats);
 
 static int __init init_percpu_stats_debugfs(void)
 {
diff --git a/mm/rmap.c b/mm/rmap.c
index 144c66e688a9..9122787c4947 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1171,6 +1171,7 @@ void page_add_new_anon_rmap(struct page *page,
 /**
  * page_add_file_rmap - add pte mapping to a file page
  * @page: the page to add the mapping to
+ * @compound: charge the page as compound or small page
  *
  * The caller needs to hold the pte lock.
  */
diff --git a/mm/shmem.c b/mm/shmem.c
index b85919243399..a9b6d536b6f1 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1422,9 +1422,12 @@ static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
 {
 	struct vm_area_struct pvma;
 	struct page *page;
+	struct vm_fault vmf;
 
 	shmem_pseudo_vma_init(&pvma, info, index);
-	page = swapin_readahead(swap, gfp, &pvma, 0);
+	vmf.vma = &pvma;
+	vmf.address = 0;
+	page = swap_cluster_readahead(swap, gfp, &vmf);
 	shmem_pseudo_vma_destroy(&pvma);
 
 	return page;
@@ -2613,241 +2616,6 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
 	return offset;
 }
 
-/*
- * We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
- * so reuse a tag which we firmly believe is never set or cleared on shmem.
- */
-#define SHMEM_TAG_PINNED        PAGECACHE_TAG_TOWRITE
-#define LAST_SCAN               4       /* about 150ms max */
-
-static void shmem_tag_pins(struct address_space *mapping)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	pgoff_t start;
-	struct page *page;
-
-	lru_add_drain();
-	start = 0;
-	rcu_read_lock();
-
-	radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
-		page = radix_tree_deref_slot(slot);
-		if (!page || radix_tree_exception(page)) {
-			if (radix_tree_deref_retry(page)) {
-				slot = radix_tree_iter_retry(&iter);
-				continue;
-			}
-		} else if (page_count(page) - page_mapcount(page) > 1) {
-			spin_lock_irq(&mapping->tree_lock);
-			radix_tree_tag_set(&mapping->page_tree, iter.index,
-					   SHMEM_TAG_PINNED);
-			spin_unlock_irq(&mapping->tree_lock);
-		}
-
-		if (need_resched()) {
-			slot = radix_tree_iter_resume(slot, &iter);
-			cond_resched_rcu();
-		}
-	}
-	rcu_read_unlock();
-}
-
-/*
- * Setting SEAL_WRITE requires us to verify there's no pending writer. However,
- * via get_user_pages(), drivers might have some pending I/O without any active
- * user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
- * and see whether it has an elevated ref-count. If so, we tag them and wait for
- * them to be dropped.
- * The caller must guarantee that no new user will acquire writable references
- * to those pages to avoid races.
- */
-static int shmem_wait_for_pins(struct address_space *mapping)
-{
-	struct radix_tree_iter iter;
-	void **slot;
-	pgoff_t start;
-	struct page *page;
-	int error, scan;
-
-	shmem_tag_pins(mapping);
-
-	error = 0;
-	for (scan = 0; scan <= LAST_SCAN; scan++) {
-		if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED))
-			break;
-
-		if (!scan)
-			lru_add_drain_all();
-		else if (schedule_timeout_killable((HZ << scan) / 200))
-			scan = LAST_SCAN;
-
-		start = 0;
-		rcu_read_lock();
-		radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
-					   start, SHMEM_TAG_PINNED) {
-
-			page = radix_tree_deref_slot(slot);
-			if (radix_tree_exception(page)) {
-				if (radix_tree_deref_retry(page)) {
-					slot = radix_tree_iter_retry(&iter);
-					continue;
-				}
-
-				page = NULL;
-			}
-
-			if (page &&
-			    page_count(page) - page_mapcount(page) != 1) {
-				if (scan < LAST_SCAN)
-					goto continue_resched;
-
-				/*
-				 * On the last scan, we clean up all those tags
-				 * we inserted; but make a note that we still
-				 * found pages pinned.
-				 */
-				error = -EBUSY;
-			}
-
-			spin_lock_irq(&mapping->tree_lock);
-			radix_tree_tag_clear(&mapping->page_tree,
-					     iter.index, SHMEM_TAG_PINNED);
-			spin_unlock_irq(&mapping->tree_lock);
-continue_resched:
-			if (need_resched()) {
-				slot = radix_tree_iter_resume(slot, &iter);
-				cond_resched_rcu();
-			}
-		}
-		rcu_read_unlock();
-	}
-
-	return error;
-}
-
-static unsigned int *memfd_file_seals_ptr(struct file *file)
-{
-	if (file->f_op == &shmem_file_operations)
-		return &SHMEM_I(file_inode(file))->seals;
-
-#ifdef CONFIG_HUGETLBFS
-	if (file->f_op == &hugetlbfs_file_operations)
-		return &HUGETLBFS_I(file_inode(file))->seals;
-#endif
-
-	return NULL;
-}
-
-#define F_ALL_SEALS (F_SEAL_SEAL | \
-		     F_SEAL_SHRINK | \
-		     F_SEAL_GROW | \
-		     F_SEAL_WRITE)
-
-static int memfd_add_seals(struct file *file, unsigned int seals)
-{
-	struct inode *inode = file_inode(file);
-	unsigned int *file_seals;
-	int error;
-
-	/*
-	 * SEALING
-	 * Sealing allows multiple parties to share a shmem-file but restrict
-	 * access to a specific subset of file operations. Seals can only be
-	 * added, but never removed. This way, mutually untrusted parties can
-	 * share common memory regions with a well-defined policy. A malicious
-	 * peer can thus never perform unwanted operations on a shared object.
-	 *
-	 * Seals are only supported on special shmem-files and always affect
-	 * the whole underlying inode. Once a seal is set, it may prevent some
-	 * kinds of access to the file. Currently, the following seals are
-	 * defined:
-	 *   SEAL_SEAL: Prevent further seals from being set on this file
-	 *   SEAL_SHRINK: Prevent the file from shrinking
-	 *   SEAL_GROW: Prevent the file from growing
-	 *   SEAL_WRITE: Prevent write access to the file
-	 *
-	 * As we don't require any trust relationship between two parties, we
-	 * must prevent seals from being removed. Therefore, sealing a file
-	 * only adds a given set of seals to the file, it never touches
-	 * existing seals. Furthermore, the "setting seals"-operation can be
-	 * sealed itself, which basically prevents any further seal from being
-	 * added.
-	 *
-	 * Semantics of sealing are only defined on volatile files. Only
-	 * anonymous shmem files support sealing. More importantly, seals are
-	 * never written to disk. Therefore, there's no plan to support it on
-	 * other file types.
-	 */
-
-	if (!(file->f_mode & FMODE_WRITE))
-		return -EPERM;
-	if (seals & ~(unsigned int)F_ALL_SEALS)
-		return -EINVAL;
-
-	inode_lock(inode);
-
-	file_seals = memfd_file_seals_ptr(file);
-	if (!file_seals) {
-		error = -EINVAL;
-		goto unlock;
-	}
-
-	if (*file_seals & F_SEAL_SEAL) {
-		error = -EPERM;
-		goto unlock;
-	}
-
-	if ((seals & F_SEAL_WRITE) && !(*file_seals & F_SEAL_WRITE)) {
-		error = mapping_deny_writable(file->f_mapping);
-		if (error)
-			goto unlock;
-
-		error = shmem_wait_for_pins(file->f_mapping);
-		if (error) {
-			mapping_allow_writable(file->f_mapping);
-			goto unlock;
-		}
-	}
-
-	*file_seals |= seals;
-	error = 0;
-
-unlock:
-	inode_unlock(inode);
-	return error;
-}
-
-static int memfd_get_seals(struct file *file)
-{
-	unsigned int *seals = memfd_file_seals_ptr(file);
-
-	return seals ? *seals : -EINVAL;
-}
-
-long memfd_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	long error;
-
-	switch (cmd) {
-	case F_ADD_SEALS:
-		/* disallow upper 32bit */
-		if (arg > UINT_MAX)
-			return -EINVAL;
-
-		error = memfd_add_seals(file, arg);
-		break;
-	case F_GET_SEALS:
-		error = memfd_get_seals(file);
-		break;
-	default:
-		error = -EINVAL;
-		break;
-	}
-
-	return error;
-}
-
 static long shmem_fallocate(struct file *file, int mode, loff_t offset,
 							 loff_t len)
 {
@@ -3669,94 +3437,6 @@ static int shmem_show_options(struct seq_file *seq, struct dentry *root)
 	shmem_show_mpol(seq, sbinfo->mpol);
 	return 0;
 }
-
-#define MFD_NAME_PREFIX "memfd:"
-#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
-#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
-
-#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING | MFD_HUGETLB)
-
-SYSCALL_DEFINE2(memfd_create,
-		const char __user *, uname,
-		unsigned int, flags)
-{
-	unsigned int *file_seals;
-	struct file *file;
-	int fd, error;
-	char *name;
-	long len;
-
-	if (!(flags & MFD_HUGETLB)) {
-		if (flags & ~(unsigned int)MFD_ALL_FLAGS)
-			return -EINVAL;
-	} else {
-		/* Allow huge page size encoding in flags. */
-		if (flags & ~(unsigned int)(MFD_ALL_FLAGS |
-				(MFD_HUGE_MASK << MFD_HUGE_SHIFT)))
-			return -EINVAL;
-	}
-
-	/* length includes terminating zero */
-	len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
-	if (len <= 0)
-		return -EFAULT;
-	if (len > MFD_NAME_MAX_LEN + 1)
-		return -EINVAL;
-
-	name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_KERNEL);
-	if (!name)
-		return -ENOMEM;
-
-	strcpy(name, MFD_NAME_PREFIX);
-	if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
-		error = -EFAULT;
-		goto err_name;
-	}
-
-	/* terminating-zero may have changed after strnlen_user() returned */
-	if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
-		error = -EFAULT;
-		goto err_name;
-	}
-
-	fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
-	if (fd < 0) {
-		error = fd;
-		goto err_name;
-	}
-
-	if (flags & MFD_HUGETLB) {
-		struct user_struct *user = NULL;
-
-		file = hugetlb_file_setup(name, 0, VM_NORESERVE, &user,
-					HUGETLB_ANONHUGE_INODE,
-					(flags >> MFD_HUGE_SHIFT) &
-					MFD_HUGE_MASK);
-	} else
-		file = shmem_file_setup(name, 0, VM_NORESERVE);
-	if (IS_ERR(file)) {
-		error = PTR_ERR(file);
-		goto err_fd;
-	}
-	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
-	file->f_flags |= O_RDWR | O_LARGEFILE;
-
-	if (flags & MFD_ALLOW_SEALING) {
-		file_seals = memfd_file_seals_ptr(file);
-		*file_seals &= ~F_SEAL_SEAL;
-	}
-
-	fd_install(fd, file);
-	kfree(name);
-	return fd;
-
-err_fd:
-	put_unused_fd(fd);
-err_name:
-	kfree(name);
-	return error;
-}
-
 #endif /* CONFIG_TMPFS */
 
 static void shmem_put_super(struct super_block *sb)
diff --git a/mm/slab.c b/mm/slab.c
index 9095c3945425..b59f2cdf28d1 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1869,7 +1869,7 @@ static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 	return 0;
 }
 
-slab_flags_t kmem_cache_flags(unsigned long object_size,
+slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1877,7 +1877,7 @@ slab_flags_t kmem_cache_flags(unsigned long object_size,
 }
 
 struct kmem_cache *
-__kmem_cache_alias(const char *name, size_t size, size_t align,
+__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *))
 {
 	struct kmem_cache *cachep;
@@ -1994,7 +1994,7 @@ int __kmem_cache_create(struct kmem_cache *cachep, slab_flags_t flags)
 	size_t ralign = BYTES_PER_WORD;
 	gfp_t gfp;
 	int err;
-	size_t size = cachep->size;
+	unsigned int size = cachep->size;
 
 #if DEBUG
 #if FORCED_DEBUG
@@ -2291,6 +2291,18 @@ out:
 	return nr_freed;
 }
 
+bool __kmem_cache_empty(struct kmem_cache *s)
+{
+	int node;
+	struct kmem_cache_node *n;
+
+	for_each_kmem_cache_node(s, node, n)
+		if (!list_empty(&n->slabs_full) ||
+		    !list_empty(&n->slabs_partial))
+			return false;
+	return true;
+}
+
 int __kmem_cache_shrink(struct kmem_cache *cachep)
 {
 	int ret = 0;
@@ -2675,11 +2687,7 @@ static struct page *cache_grow_begin(struct kmem_cache *cachep,
 	if (n->colour_next >= cachep->colour)
 		n->colour_next = 0;
 
-	offset = n->colour_next;
-	if (offset >= cachep->colour)
-		offset = 0;
-
-	offset *= cachep->colour_off;
+	offset = n->colour_next * cachep->colour_off;
 
 	/* Get slab management. */
 	freelist = alloc_slabmgmt(cachep, page, offset,
diff --git a/mm/slab.h b/mm/slab.h
index 51813236e773..68bdf498da3b 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -22,8 +22,8 @@ struct kmem_cache {
 	unsigned int size;	/* The aligned/padded/added on size  */
 	unsigned int align;	/* Alignment as calculated */
 	slab_flags_t flags;	/* Active flags on the slab */
-	size_t useroffset;	/* Usercopy region offset */
-	size_t usersize;	/* Usercopy region size */
+	unsigned int useroffset;/* Usercopy region offset */
+	unsigned int usersize;	/* Usercopy region size */
 	const char *name;	/* Slab name for sysfs */
 	int refcount;		/* Use counter */
 	void (*ctor)(void *);	/* Called on object slot creation */
@@ -77,7 +77,7 @@ extern struct kmem_cache *kmem_cache;
 /* A table of kmalloc cache names and sizes */
 extern const struct kmalloc_info_struct {
 	const char *name;
-	unsigned long size;
+	unsigned int size;
 } kmalloc_info[];
 
 #ifndef CONFIG_SLOB
@@ -93,31 +93,31 @@ struct kmem_cache *kmalloc_slab(size_t, gfp_t);
 /* Functions provided by the slab allocators */
 int __kmem_cache_create(struct kmem_cache *, slab_flags_t flags);
 
-extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size,
-			slab_flags_t flags, size_t useroffset,
-			size_t usersize);
+struct kmem_cache *create_kmalloc_cache(const char *name, unsigned int size,
+			slab_flags_t flags, unsigned int useroffset,
+			unsigned int usersize);
 extern void create_boot_cache(struct kmem_cache *, const char *name,
-			size_t size, slab_flags_t flags, size_t useroffset,
-			size_t usersize);
+			unsigned int size, slab_flags_t flags,
+			unsigned int useroffset, unsigned int usersize);
 
 int slab_unmergeable(struct kmem_cache *s);
-struct kmem_cache *find_mergeable(size_t size, size_t align,
+struct kmem_cache *find_mergeable(unsigned size, unsigned align,
 		slab_flags_t flags, const char *name, void (*ctor)(void *));
 #ifndef CONFIG_SLOB
 struct kmem_cache *
-__kmem_cache_alias(const char *name, size_t size, size_t align,
+__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *));
 
-slab_flags_t kmem_cache_flags(unsigned long object_size,
+slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t flags, const char *name,
 	void (*ctor)(void *));
 #else
 static inline struct kmem_cache *
-__kmem_cache_alias(const char *name, size_t size, size_t align,
+__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *))
 { return NULL; }
 
-static inline slab_flags_t kmem_cache_flags(unsigned long object_size,
+static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -166,6 +166,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned long object_size,
 			      SLAB_TEMPORARY | \
 			      SLAB_ACCOUNT)
 
+bool __kmem_cache_empty(struct kmem_cache *);
 int __kmem_cache_shutdown(struct kmem_cache *);
 void __kmem_cache_release(struct kmem_cache *);
 int __kmem_cache_shrink(struct kmem_cache *);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 10f127b2de7c..98dcdc352062 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -10,6 +10,7 @@
 #include <linux/poison.h>
 #include <linux/interrupt.h>
 #include <linux/memory.h>
+#include <linux/cache.h>
 #include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/cpu.h>
@@ -81,38 +82,19 @@ unsigned int kmem_cache_size(struct kmem_cache *s)
 EXPORT_SYMBOL(kmem_cache_size);
 
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(const char *name, size_t size)
+static int kmem_cache_sanity_check(const char *name, unsigned int size)
 {
-	struct kmem_cache *s = NULL;
-
 	if (!name || in_interrupt() || size < sizeof(void *) ||
 		size > KMALLOC_MAX_SIZE) {
 		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
 		return -EINVAL;
 	}
 
-	list_for_each_entry(s, &slab_caches, list) {
-		char tmp;
-		int res;
-
-		/*
-		 * This happens when the module gets unloaded and doesn't
-		 * destroy its slab cache and no-one else reuses the vmalloc
-		 * area of the module.  Print a warning.
-		 */
-		res = probe_kernel_address(s->name, tmp);
-		if (res) {
-			pr_err("Slab cache with size %d has lost its name\n",
-			       s->object_size);
-			continue;
-		}
-	}
-
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(const char *name, size_t size)
+static inline int kmem_cache_sanity_check(const char *name, unsigned int size)
 {
 	return 0;
 }
@@ -279,8 +261,8 @@ static inline void memcg_unlink_cache(struct kmem_cache *s)
  * Figure out what the alignment of the objects will be given a set of
  * flags, a user specified alignment and the size of the objects.
  */
-static unsigned long calculate_alignment(unsigned long flags,
-		unsigned long align, unsigned long size)
+static unsigned int calculate_alignment(slab_flags_t flags,
+		unsigned int align, unsigned int size)
 {
 	/*
 	 * If the user wants hardware cache aligned objects then follow that
@@ -290,7 +272,7 @@ static unsigned long calculate_alignment(unsigned long flags,
 	 * alignment though. If that is greater then use it.
 	 */
 	if (flags & SLAB_HWCACHE_ALIGN) {
-		unsigned long ralign;
+		unsigned int ralign;
 
 		ralign = cache_line_size();
 		while (size <= ralign / 2)
@@ -330,7 +312,7 @@ int slab_unmergeable(struct kmem_cache *s)
 	return 0;
 }
 
-struct kmem_cache *find_mergeable(size_t size, size_t align,
+struct kmem_cache *find_mergeable(unsigned int size, unsigned int align,
 		slab_flags_t flags, const char *name, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
@@ -378,9 +360,9 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 }
 
 static struct kmem_cache *create_cache(const char *name,
-		size_t object_size, size_t size, size_t align,
-		slab_flags_t flags, size_t useroffset,
-		size_t usersize, void (*ctor)(void *),
+		unsigned int object_size, unsigned int align,
+		slab_flags_t flags, unsigned int useroffset,
+		unsigned int usersize, void (*ctor)(void *),
 		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
 {
 	struct kmem_cache *s;
@@ -395,8 +377,7 @@ static struct kmem_cache *create_cache(const char *name,
 		goto out;
 
 	s->name = name;
-	s->object_size = object_size;
-	s->size = size;
+	s->size = s->object_size = object_size;
 	s->align = align;
 	s->ctor = ctor;
 	s->useroffset = useroffset;
@@ -451,8 +432,10 @@ out_free_cache:
  * as davem.
  */
 struct kmem_cache *
-kmem_cache_create_usercopy(const char *name, size_t size, size_t align,
-		  slab_flags_t flags, size_t useroffset, size_t usersize,
+kmem_cache_create_usercopy(const char *name,
+		  unsigned int size, unsigned int align,
+		  slab_flags_t flags,
+		  unsigned int useroffset, unsigned int usersize,
 		  void (*ctor)(void *))
 {
 	struct kmem_cache *s = NULL;
@@ -500,7 +483,7 @@ kmem_cache_create_usercopy(const char *name, size_t size, size_t align,
 		goto out_unlock;
 	}
 
-	s = create_cache(cache_name, size, size,
+	s = create_cache(cache_name, size,
 			 calculate_alignment(flags, align, size),
 			 flags, useroffset, usersize, ctor, NULL, NULL);
 	if (IS_ERR(s)) {
@@ -531,7 +514,7 @@ out_unlock:
 EXPORT_SYMBOL(kmem_cache_create_usercopy);
 
 struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
+kmem_cache_create(const char *name, unsigned int size, unsigned int align,
 		slab_flags_t flags, void (*ctor)(void *))
 {
 	return kmem_cache_create_usercopy(name, size, align, flags, 0, 0,
@@ -647,7 +630,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 		goto out_unlock;
 
 	s = create_cache(cache_name, root_cache->object_size,
-			 root_cache->size, root_cache->align,
+			 root_cache->align,
 			 root_cache->flags & CACHE_CREATE_MASK,
 			 root_cache->useroffset, root_cache->usersize,
 			 root_cache->ctor, memcg, root_cache);
@@ -916,8 +899,9 @@ bool slab_is_available(void)
 
 #ifndef CONFIG_SLOB
 /* Create a cache during boot when no slab services are available yet */
-void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
-		slab_flags_t flags, size_t useroffset, size_t usersize)
+void __init create_boot_cache(struct kmem_cache *s, const char *name,
+		unsigned int size, slab_flags_t flags,
+		unsigned int useroffset, unsigned int usersize)
 {
 	int err;
 
@@ -932,15 +916,15 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
-		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
+		panic("Creation of kmalloc slab %s size=%u failed. Reason %d\n",
 					name, size, err);
 
 	s->refcount = -1;	/* Exempt from merging for now */
 }
 
-struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
-				slab_flags_t flags, size_t useroffset,
-				size_t usersize)
+struct kmem_cache *__init create_kmalloc_cache(const char *name,
+		unsigned int size, slab_flags_t flags,
+		unsigned int useroffset, unsigned int usersize)
 {
 	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
 
@@ -954,11 +938,11 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
 	return s;
 }
 
-struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init;
 EXPORT_SYMBOL(kmalloc_caches);
 
 #ifdef CONFIG_ZONE_DMA
-struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init;
 EXPORT_SYMBOL(kmalloc_dma_caches);
 #endif
 
@@ -968,7 +952,7 @@ EXPORT_SYMBOL(kmalloc_dma_caches);
  * of two cache sizes there. The size of larger slabs can be determined using
  * fls.
  */
-static s8 size_index[24] = {
+static u8 size_index[24] __ro_after_init = {
 	3,	/* 8 */
 	4,	/* 16 */
 	5,	/* 24 */
@@ -995,7 +979,7 @@ static s8 size_index[24] = {
 	2	/* 192 */
 };
 
-static inline int size_index_elem(size_t bytes)
+static inline unsigned int size_index_elem(unsigned int bytes)
 {
 	return (bytes - 1) / 8;
 }
@@ -1006,7 +990,7 @@ static inline int size_index_elem(size_t bytes)
  */
 struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags)
 {
-	int index;
+	unsigned int index;
 
 	if (unlikely(size > KMALLOC_MAX_SIZE)) {
 		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
@@ -1064,13 +1048,13 @@ const struct kmalloc_info_struct kmalloc_info[] __initconst = {
  */
 void __init setup_kmalloc_cache_index_table(void)
 {
-	int i;
+	unsigned int i;
 
 	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
 		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
 
 	for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) {
-		int elem = size_index_elem(i);
+		unsigned int elem = size_index_elem(i);
 
 		if (elem >= ARRAY_SIZE(size_index))
 			break;
@@ -1137,9 +1121,9 @@ void __init create_kmalloc_caches(slab_flags_t flags)
 		struct kmem_cache *s = kmalloc_caches[i];
 
 		if (s) {
-			int size = kmalloc_size(i);
+			unsigned int size = kmalloc_size(i);
 			char *n = kasprintf(GFP_NOWAIT,
-				 "dma-kmalloc-%d", size);
+				 "dma-kmalloc-%u", size);
 
 			BUG_ON(!n);
 			kmalloc_dma_caches[i] = create_kmalloc_cache(n,
@@ -1182,10 +1166,10 @@ EXPORT_SYMBOL(kmalloc_order_trace);
 #ifdef CONFIG_SLAB_FREELIST_RANDOM
 /* Randomize a generic freelist */
 static void freelist_randomize(struct rnd_state *state, unsigned int *list,
-			size_t count)
+			       unsigned int count)
 {
-	size_t i;
 	unsigned int rand;
+	unsigned int i;
 
 	for (i = 0; i < count; i++)
 		list[i] = i;
@@ -1532,3 +1516,11 @@ EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
 EXPORT_TRACEPOINT_SYMBOL(kfree);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
+
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+{
+	if (__should_failslab(s, gfpflags))
+		return -ENOMEM;
+	return 0;
+}
+ALLOW_ERROR_INJECTION(should_failslab, ERRNO);
diff --git a/mm/slub.c b/mm/slub.c
index e381728a3751..44aa7847324a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -311,18 +311,18 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp)
 		__p += (__s)->size, __idx++)
 
 /* Determine object index from a given position */
-static inline int slab_index(void *p, struct kmem_cache *s, void *addr)
+static inline unsigned int slab_index(void *p, struct kmem_cache *s, void *addr)
 {
 	return (p - addr) / s->size;
 }
 
-static inline int order_objects(int order, unsigned long size, int reserved)
+static inline unsigned int order_objects(unsigned int order, unsigned int size, unsigned int reserved)
 {
-	return ((PAGE_SIZE << order) - reserved) / size;
+	return (((unsigned int)PAGE_SIZE << order) - reserved) / size;
 }
 
-static inline struct kmem_cache_order_objects oo_make(int order,
-		unsigned long size, int reserved)
+static inline struct kmem_cache_order_objects oo_make(unsigned int order,
+		unsigned int size, unsigned int reserved)
 {
 	struct kmem_cache_order_objects x = {
 		(order << OO_SHIFT) + order_objects(order, size, reserved)
@@ -331,12 +331,12 @@ static inline struct kmem_cache_order_objects oo_make(int order,
 	return x;
 }
 
-static inline int oo_order(struct kmem_cache_order_objects x)
+static inline unsigned int oo_order(struct kmem_cache_order_objects x)
 {
 	return x.x >> OO_SHIFT;
 }
 
-static inline int oo_objects(struct kmem_cache_order_objects x)
+static inline unsigned int oo_objects(struct kmem_cache_order_objects x)
 {
 	return x.x & OO_MASK;
 }
@@ -466,7 +466,7 @@ static void get_map(struct kmem_cache *s, struct page *page, unsigned long *map)
 		set_bit(slab_index(p, s, addr), map);
 }
 
-static inline int size_from_object(struct kmem_cache *s)
+static inline unsigned int size_from_object(struct kmem_cache *s)
 {
 	if (s->flags & SLAB_RED_ZONE)
 		return s->size - s->red_left_pad;
@@ -598,13 +598,13 @@ static void init_tracking(struct kmem_cache *s, void *object)
 	set_track(s, object, TRACK_ALLOC, 0UL);
 }
 
-static void print_track(const char *s, struct track *t)
+static void print_track(const char *s, struct track *t, unsigned long pr_time)
 {
 	if (!t->addr)
 		return;
 
 	pr_err("INFO: %s in %pS age=%lu cpu=%u pid=%d\n",
-	       s, (void *)t->addr, jiffies - t->when, t->cpu, t->pid);
+	       s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
 #ifdef CONFIG_STACKTRACE
 	{
 		int i;
@@ -619,11 +619,12 @@ static void print_track(const char *s, struct track *t)
 
 static void print_tracking(struct kmem_cache *s, void *object)
 {
+	unsigned long pr_time = jiffies;
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
-	print_track("Allocated", get_track(s, object, TRACK_ALLOC));
-	print_track("Freed", get_track(s, object, TRACK_FREE));
+	print_track("Allocated", get_track(s, object, TRACK_ALLOC), pr_time);
+	print_track("Freed", get_track(s, object, TRACK_FREE), pr_time);
 }
 
 static void print_page_info(struct page *page)
@@ -680,7 +681,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 		print_section(KERN_ERR, "Bytes b4 ", p - 16, 16);
 
 	print_section(KERN_ERR, "Object ", p,
-		      min_t(unsigned long, s->object_size, PAGE_SIZE));
+		      min_t(unsigned int, s->object_size, PAGE_SIZE));
 	if (s->flags & SLAB_RED_ZONE)
 		print_section(KERN_ERR, "Redzone ", p + s->object_size,
 			s->inuse - s->object_size);
@@ -1292,7 +1293,7 @@ out:
 
 __setup("slub_debug", setup_slub_debug);
 
-slab_flags_t kmem_cache_flags(unsigned long object_size,
+slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1325,7 +1326,7 @@ static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
 static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
 					struct page *page) {}
-slab_flags_t kmem_cache_flags(unsigned long object_size,
+slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t flags, const char *name,
 	void (*ctor)(void *))
 {
@@ -1362,10 +1363,8 @@ static __always_inline void kfree_hook(void *x)
 	kasan_kfree_large(x, _RET_IP_);
 }
 
-static __always_inline void *slab_free_hook(struct kmem_cache *s, void *x)
+static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x)
 {
-	void *freeptr;
-
 	kmemleak_free_recursive(x, s->flags);
 
 	/*
@@ -1385,17 +1384,12 @@ static __always_inline void *slab_free_hook(struct kmem_cache *s, void *x)
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(x, s->object_size);
 
-	freeptr = get_freepointer(s, x);
-	/*
-	 * kasan_slab_free() may put x into memory quarantine, delaying its
-	 * reuse. In this case the object's freelist pointer is changed.
-	 */
-	kasan_slab_free(s, x, _RET_IP_);
-	return freeptr;
+	/* KASAN might put x into memory quarantine, delaying its reuse */
+	return kasan_slab_free(s, x, _RET_IP_);
 }
 
-static inline void slab_free_freelist_hook(struct kmem_cache *s,
-					   void *head, void *tail)
+static inline bool slab_free_freelist_hook(struct kmem_cache *s,
+					   void **head, void **tail)
 {
 /*
  * Compiler cannot detect this function can be removed if slab_free_hook()
@@ -1406,13 +1400,33 @@ static inline void slab_free_freelist_hook(struct kmem_cache *s,
 	defined(CONFIG_DEBUG_OBJECTS_FREE) ||	\
 	defined(CONFIG_KASAN)
 
-	void *object = head;
-	void *tail_obj = tail ? : head;
-	void *freeptr;
+	void *object;
+	void *next = *head;
+	void *old_tail = *tail ? *tail : *head;
+
+	/* Head and tail of the reconstructed freelist */
+	*head = NULL;
+	*tail = NULL;
 
 	do {
-		freeptr = slab_free_hook(s, object);
-	} while ((object != tail_obj) && (object = freeptr));
+		object = next;
+		next = get_freepointer(s, object);
+		/* If object's reuse doesn't have to be delayed */
+		if (!slab_free_hook(s, object)) {
+			/* Move object to the new freelist */
+			set_freepointer(s, object, *head);
+			*head = object;
+			if (!*tail)
+				*tail = object;
+		}
+	} while (object != old_tail);
+
+	if (*head == *tail)
+		*tail = NULL;
+
+	return *head != NULL;
+#else
+	return true;
 #endif
 }
 
@@ -1435,7 +1449,7 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 		gfp_t flags, int node, struct kmem_cache_order_objects oo)
 {
 	struct page *page;
-	int order = oo_order(oo);
+	unsigned int order = oo_order(oo);
 
 	if (node == NUMA_NO_NODE)
 		page = alloc_pages(flags, order);
@@ -1454,8 +1468,8 @@ static inline struct page *alloc_slab_page(struct kmem_cache *s,
 /* Pre-initialize the random sequence cache */
 static int init_cache_random_seq(struct kmem_cache *s)
 {
+	unsigned int count = oo_objects(s->oo);
 	int err;
-	unsigned long i, count = oo_objects(s->oo);
 
 	/* Bailout if already initialised */
 	if (s->random_seq)
@@ -1470,6 +1484,8 @@ static int init_cache_random_seq(struct kmem_cache *s)
 
 	/* Transform to an offset on the set of pages */
 	if (s->random_seq) {
+		unsigned int i;
+
 		for (i = 0; i < count; i++)
 			s->random_seq[i] *= s->size;
 	}
@@ -1811,7 +1827,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 {
 	struct page *page, *page2;
 	void *object = NULL;
-	int available = 0;
+	unsigned int available = 0;
 	int objects;
 
 	/*
@@ -2398,7 +2414,7 @@ slab_out_of_memory(struct kmem_cache *s, gfp_t gfpflags, int nid)
 
 	pr_warn("SLUB: Unable to allocate memory on node %d, gfp=%#x(%pGg)\n",
 		nid, gfpflags, &gfpflags);
-	pr_warn("  cache: %s, object size: %d, buffer size: %d, default order: %d, min order: %d\n",
+	pr_warn("  cache: %s, object size: %u, buffer size: %u, default order: %u, min order: %u\n",
 		s->name, s->object_size, s->size, oo_order(s->oo),
 		oo_order(s->min));
 
@@ -2965,14 +2981,12 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
 				      void *head, void *tail, int cnt,
 				      unsigned long addr)
 {
-	slab_free_freelist_hook(s, head, tail);
 	/*
-	 * slab_free_freelist_hook() could have put the items into quarantine.
-	 * If so, no need to free them.
+	 * With KASAN enabled slab_free_freelist_hook modifies the freelist
+	 * to remove objects, whose reuse must be delayed.
 	 */
-	if (s->flags & SLAB_KASAN && !(s->flags & SLAB_TYPESAFE_BY_RCU))
-		return;
-	do_slab_free(s, page, head, tail, cnt, addr);
+	if (slab_free_freelist_hook(s, &head, &tail))
+		do_slab_free(s, page, head, tail, cnt, addr);
 }
 
 #ifdef CONFIG_KASAN
@@ -3181,9 +3195,9 @@ EXPORT_SYMBOL(kmem_cache_alloc_bulk);
  * and increases the number of allocations possible without having to
  * take the list_lock.
  */
-static int slub_min_order;
-static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
-static int slub_min_objects;
+static unsigned int slub_min_order;
+static unsigned int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static unsigned int slub_min_objects;
 
 /*
  * Calculate the order of allocation given an slab object size.
@@ -3210,20 +3224,21 @@ static int slub_min_objects;
  * requested a higher mininum order then we start with that one instead of
  * the smallest order which will fit the object.
  */
-static inline int slab_order(int size, int min_objects,
-				int max_order, int fract_leftover, int reserved)
+static inline unsigned int slab_order(unsigned int size,
+		unsigned int min_objects, unsigned int max_order,
+		unsigned int fract_leftover, unsigned int reserved)
 {
-	int order;
-	int rem;
-	int min_order = slub_min_order;
+	unsigned int min_order = slub_min_order;
+	unsigned int order;
 
 	if (order_objects(min_order, size, reserved) > MAX_OBJS_PER_PAGE)
 		return get_order(size * MAX_OBJS_PER_PAGE) - 1;
 
-	for (order = max(min_order, get_order(min_objects * size + reserved));
+	for (order = max(min_order, (unsigned int)get_order(min_objects * size + reserved));
 			order <= max_order; order++) {
 
-		unsigned long slab_size = PAGE_SIZE << order;
+		unsigned int slab_size = (unsigned int)PAGE_SIZE << order;
+		unsigned int rem;
 
 		rem = (slab_size - reserved) % size;
 
@@ -3234,12 +3249,11 @@ static inline int slab_order(int size, int min_objects,
 	return order;
 }
 
-static inline int calculate_order(int size, int reserved)
+static inline int calculate_order(unsigned int size, unsigned int reserved)
 {
-	int order;
-	int min_objects;
-	int fraction;
-	int max_objects;
+	unsigned int order;
+	unsigned int min_objects;
+	unsigned int max_objects;
 
 	/*
 	 * Attempt to find best configuration for a slab. This
@@ -3256,6 +3270,8 @@ static inline int calculate_order(int size, int reserved)
 	min_objects = min(min_objects, max_objects);
 
 	while (min_objects > 1) {
+		unsigned int fraction;
+
 		fraction = 16;
 		while (fraction >= 4) {
 			order = slab_order(size, min_objects,
@@ -3457,8 +3473,8 @@ static void set_cpu_partial(struct kmem_cache *s)
 static int calculate_sizes(struct kmem_cache *s, int forced_order)
 {
 	slab_flags_t flags = s->flags;
-	size_t size = s->object_size;
-	int order;
+	unsigned int size = s->object_size;
+	unsigned int order;
 
 	/*
 	 * Round up object size to the next word boundary. We can only
@@ -3548,7 +3564,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	else
 		order = calculate_order(size, s->reserved);
 
-	if (order < 0)
+	if ((int)order < 0)
 		return 0;
 
 	s->allocflags = 0;
@@ -3632,8 +3648,8 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 	free_kmem_cache_nodes(s);
 error:
 	if (flags & SLAB_PANIC)
-		panic("Cannot create slab %s size=%lu realsize=%u order=%u offset=%u flags=%lx\n",
-		      s->name, (unsigned long)s->size, s->size,
+		panic("Cannot create slab %s size=%u realsize=%u order=%u offset=%u flags=%lx\n",
+		      s->name, s->size, s->size,
 		      oo_order(s->oo), s->offset, (unsigned long)flags);
 	return -EINVAL;
 }
@@ -3691,6 +3707,17 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 		discard_slab(s, page);
 }
 
+bool __kmem_cache_empty(struct kmem_cache *s)
+{
+	int node;
+	struct kmem_cache_node *n;
+
+	for_each_kmem_cache_node(s, node, n)
+		if (n->nr_partial || slabs_node(s, node))
+			return false;
+	return true;
+}
+
 /*
  * Release all resources used by a slab cache.
  */
@@ -3716,7 +3743,7 @@ int __kmem_cache_shutdown(struct kmem_cache *s)
 
 static int __init setup_slub_min_order(char *str)
 {
-	get_option(&str, &slub_min_order);
+	get_option(&str, (int *)&slub_min_order);
 
 	return 1;
 }
@@ -3725,8 +3752,8 @@ __setup("slub_min_order=", setup_slub_min_order);
 
 static int __init setup_slub_max_order(char *str)
 {
-	get_option(&str, &slub_max_order);
-	slub_max_order = min(slub_max_order, MAX_ORDER - 1);
+	get_option(&str, (int *)&slub_max_order);
+	slub_max_order = min(slub_max_order, (unsigned int)MAX_ORDER - 1);
 
 	return 1;
 }
@@ -3735,7 +3762,7 @@ __setup("slub_max_order=", setup_slub_max_order);
 
 static int __init setup_slub_min_objects(char *str)
 {
-	get_option(&str, &slub_min_objects);
+	get_option(&str, (int *)&slub_min_objects);
 
 	return 1;
 }
@@ -3824,7 +3851,7 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
 			 bool to_user)
 {
 	struct kmem_cache *s;
-	unsigned long offset;
+	unsigned int offset;
 	size_t object_size;
 
 	/* Find object and usable object size. */
@@ -4230,7 +4257,7 @@ void __init kmem_cache_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_SLUB_DEAD, "slub:dead", NULL,
 				  slub_cpu_dead);
 
-	pr_info("SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d, CPUs=%u, Nodes=%d\n",
+	pr_info("SLUB: HWalign=%d, Order=%u-%u, MinObjects=%u, CPUs=%u, Nodes=%d\n",
 		cache_line_size(),
 		slub_min_order, slub_max_order, slub_min_objects,
 		nr_cpu_ids, nr_node_ids);
@@ -4241,7 +4268,7 @@ void __init kmem_cache_init_late(void)
 }
 
 struct kmem_cache *
-__kmem_cache_alias(const char *name, size_t size, size_t align,
+__kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		   slab_flags_t flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s, *c;
@@ -4254,13 +4281,12 @@ __kmem_cache_alias(const char *name, size_t size, size_t align,
 		 * Adjust the object sizes so that we clear
 		 * the complete object on kzalloc.
 		 */
-		s->object_size = max(s->object_size, (int)size);
-		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
+		s->object_size = max(s->object_size, size);
+		s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
 
 		for_each_memcg_cache(c, s) {
 			c->object_size = s->object_size;
-			c->inuse = max_t(int, c->inuse,
-					 ALIGN(size, sizeof(void *)));
+			c->inuse = max(c->inuse, ALIGN(size, sizeof(void *)));
 		}
 
 		if (sysfs_slab_alias(s, name)) {
@@ -4889,35 +4915,35 @@ struct slab_attribute {
 
 static ssize_t slab_size_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->size);
+	return sprintf(buf, "%u\n", s->size);
 }
 SLAB_ATTR_RO(slab_size);
 
 static ssize_t align_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->align);
+	return sprintf(buf, "%u\n", s->align);
 }
 SLAB_ATTR_RO(align);
 
 static ssize_t object_size_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->object_size);
+	return sprintf(buf, "%u\n", s->object_size);
 }
 SLAB_ATTR_RO(object_size);
 
 static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", oo_objects(s->oo));
+	return sprintf(buf, "%u\n", oo_objects(s->oo));
 }
 SLAB_ATTR_RO(objs_per_slab);
 
 static ssize_t order_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
-	unsigned long order;
+	unsigned int order;
 	int err;
 
-	err = kstrtoul(buf, 10, &order);
+	err = kstrtouint(buf, 10, &order);
 	if (err)
 		return err;
 
@@ -4930,7 +4956,7 @@ static ssize_t order_store(struct kmem_cache *s,
 
 static ssize_t order_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", oo_order(s->oo));
+	return sprintf(buf, "%u\n", oo_order(s->oo));
 }
 SLAB_ATTR(order);
 
@@ -4962,10 +4988,10 @@ static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf)
 static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
 				 size_t length)
 {
-	unsigned long objects;
+	unsigned int objects;
 	int err;
 
-	err = kstrtoul(buf, 10, &objects);
+	err = kstrtouint(buf, 10, &objects);
 	if (err)
 		return err;
 	if (objects && !kmem_cache_has_cpu_partial(s))
@@ -5081,7 +5107,7 @@ SLAB_ATTR_RO(cache_dma);
 
 static ssize_t usersize_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%zu\n", s->usersize);
+	return sprintf(buf, "%u\n", s->usersize);
 }
 SLAB_ATTR_RO(usersize);
 
@@ -5093,7 +5119,7 @@ SLAB_ATTR_RO(destroy_by_rcu);
 
 static ssize_t reserved_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->reserved);
+	return sprintf(buf, "%u\n", s->reserved);
 }
 SLAB_ATTR_RO(reserved);
 
@@ -5288,21 +5314,22 @@ SLAB_ATTR(shrink);
 #ifdef CONFIG_NUMA
 static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", s->remote_node_defrag_ratio / 10);
+	return sprintf(buf, "%u\n", s->remote_node_defrag_ratio / 10);
 }
 
 static ssize_t remote_node_defrag_ratio_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
-	unsigned long ratio;
+	unsigned int ratio;
 	int err;
 
-	err = kstrtoul(buf, 10, &ratio);
+	err = kstrtouint(buf, 10, &ratio);
 	if (err)
 		return err;
+	if (ratio > 100)
+		return -ERANGE;
 
-	if (ratio <= 100)
-		s->remote_node_defrag_ratio = ratio * 10;
+	s->remote_node_defrag_ratio = ratio * 10;
 
 	return length;
 }
@@ -5663,7 +5690,7 @@ static char *create_unique_id(struct kmem_cache *s)
 		*p++ = 'A';
 	if (p != name + 1)
 		*p++ = '-';
-	p += sprintf(p, "%07d", s->size);
+	p += sprintf(p, "%07u", s->size);
 
 	BUG_ON(p > name + ID_STR_LENGTH - 1);
 	return name;
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index bd0276d5f66b..640e68f8324b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -303,7 +303,6 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 		ms = __nr_to_section(pnum);
 		pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 		       __func__);
-		ms->section_mem_map = 0;
 	}
 
 	if (vmemmap_buf_start) {
diff --git a/mm/sparse.c b/mm/sparse.c
index 58cab483e81b..4a58f8809542 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -202,6 +202,12 @@ static inline int next_present_section_nr(int section_nr)
 	      (section_nr <= __highest_present_section_nr));	\
 	     section_nr = next_present_section_nr(section_nr))
 
+/*
+ * Record how many memory sections are marked as present
+ * during system bootup.
+ */
+static int __initdata nr_present_sections;
+
 /* Record a memory area against a node. */
 void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -231,6 +237,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end)
 			ms->section_mem_map = sparse_encode_early_nid(nid) |
 							SECTION_IS_ONLINE;
 			section_mark_present(ms);
+			nr_present_sections++;
 		}
 	}
 }
@@ -446,7 +453,6 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 		ms = __nr_to_section(pnum);
 		pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 		       __func__);
-		ms->section_mem_map = 0;
 	}
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
@@ -474,7 +480,6 @@ static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
 
 	pr_err("%s: sparsemem memory map backing failed some memory will not be available\n",
 	       __func__);
-	ms->section_mem_map = 0;
 	return NULL;
 }
 #endif
@@ -486,10 +491,12 @@ void __weak __meminit vmemmap_populate_print_last(void)
 /**
  *  alloc_usemap_and_memmap - memory alloction for pageblock flags and vmemmap
  *  @map: usemap_map for pageblock flags or mmap_map for vmemmap
+ *  @unit_size: size of map unit
  */
 static void __init alloc_usemap_and_memmap(void (*alloc_func)
 					(void *, unsigned long, unsigned long,
-					unsigned long, int), void *data)
+					unsigned long, int), void *data,
+					int data_unit_size)
 {
 	unsigned long pnum;
 	unsigned long map_count;
@@ -566,7 +573,8 @@ void __init sparse_init(void)
 	if (!usemap_map)
 		panic("can not allocate usemap_map\n");
 	alloc_usemap_and_memmap(sparse_early_usemaps_alloc_node,
-							(void *)usemap_map);
+				(void *)usemap_map,
+				sizeof(usemap_map[0]));
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 	size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
@@ -574,21 +582,28 @@ void __init sparse_init(void)
 	if (!map_map)
 		panic("can not allocate map_map\n");
 	alloc_usemap_and_memmap(sparse_early_mem_maps_alloc_node,
-							(void *)map_map);
+				(void *)map_map,
+				sizeof(map_map[0]));
 #endif
 
 	for_each_present_section_nr(0, pnum) {
+		struct mem_section *ms;
+		ms = __nr_to_section(pnum);
 		usemap = usemap_map[pnum];
-		if (!usemap)
+		if (!usemap) {
+			ms->section_mem_map = 0;
 			continue;
+		}
 
 #ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
 		map = map_map[pnum];
 #else
 		map = sparse_early_mem_map_alloc(pnum);
 #endif
-		if (!map)
+		if (!map) {
+			ms->section_mem_map = 0;
 			continue;
+		}
 
 		sparse_init_one_section(__nr_to_section(pnum), pnum, map,
 								usemap);
@@ -779,7 +794,13 @@ int __meminit sparse_add_one_section(struct pglist_data *pgdat,
 		goto out;
 	}
 
-	memset(memmap, 0, sizeof(struct page) * PAGES_PER_SECTION);
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * Poison uninitialized struct pages in order to catch invalid flags
+	 * combinations.
+	 */
+	memset(memmap, PAGE_POISON_PATTERN, sizeof(struct page) * PAGES_PER_SECTION);
+#endif
 
 	section_mark_present(ms);
 
diff --git a/mm/swap.c b/mm/swap.c
index eed846cfc8b8..26fc9b5f1b6c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -708,7 +708,6 @@ void lru_add_drain_all(void)
  * release_pages - batched put_page()
  * @pages: array of pages to release
  * @nr: number of pages
- * @cold: whether the pages are cache cold
  *
  * Decrement the reference count on all the pages in @pages.  If it
  * fell to zero, remove the page from the LRU and free it.
diff --git a/mm/swap_slots.c b/mm/swap_slots.c
index bebc19292018..f2641894f440 100644
--- a/mm/swap_slots.c
+++ b/mm/swap_slots.c
@@ -34,8 +34,6 @@
 #include <linux/mutex.h>
 #include <linux/mm.h>
 
-#ifdef CONFIG_SWAP
-
 static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots);
 static bool	swap_slot_cache_active;
 bool	swap_slot_cache_enabled;
@@ -356,5 +354,3 @@ repeat:
 
 	return entry;
 }
-
-#endif /* CONFIG_SWAP */
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 39ae7cfad90f..486f7c26386e 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -38,7 +38,7 @@ static const struct address_space_operations swap_aops = {
 
 struct address_space *swapper_spaces[MAX_SWAPFILES] __read_mostly;
 static unsigned int nr_swapper_spaces[MAX_SWAPFILES] __read_mostly;
-bool swap_vma_readahead __read_mostly = true;
+static bool enable_vma_readahead __read_mostly = true;
 
 #define SWAP_RA_WIN_SHIFT	(PAGE_SHIFT / 2)
 #define SWAP_RA_HITS_MASK	((1UL << SWAP_RA_WIN_SHIFT) - 1)
@@ -322,6 +322,11 @@ void free_pages_and_swap_cache(struct page **pages, int nr)
 	release_pages(pagep, nr);
 }
 
+static inline bool swap_use_vma_readahead(void)
+{
+	return READ_ONCE(enable_vma_readahead) && !atomic_read(&nr_rotate_swap);
+}
+
 /*
  * Lookup a swap entry in the swap cache. A found page will be returned
  * unlocked and with its refcount incremented - we rely on the kernel
@@ -332,32 +337,48 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,
 			       unsigned long addr)
 {
 	struct page *page;
-	unsigned long ra_info;
-	int win, hits, readahead;
+	struct swap_info_struct *si;
 
+	si = get_swap_device(entry);
+	if (!si)
+		return NULL;
 	page = find_get_page(swap_address_space(entry), swp_offset(entry));
+	put_swap_device(si);
 
 	INC_CACHE_INFO(find_total);
 	if (page) {
+		bool vma_ra = swap_use_vma_readahead();
+		bool readahead;
+
 		INC_CACHE_INFO(find_success);
+		/*
+		 * At the moment, we don't support PG_readahead for anon THP
+		 * so let's bail out rather than confusing the readahead stat.
+		 */
 		if (unlikely(PageTransCompound(page)))
 			return page;
+
 		readahead = TestClearPageReadahead(page);
-		if (vma) {
-			ra_info = GET_SWAP_RA_VAL(vma);
-			win = SWAP_RA_WIN(ra_info);
-			hits = SWAP_RA_HITS(ra_info);
+		if (vma && vma_ra) {
+			unsigned long ra_val;
+			int win, hits;
+
+			ra_val = GET_SWAP_RA_VAL(vma);
+			win = SWAP_RA_WIN(ra_val);
+			hits = SWAP_RA_HITS(ra_val);
 			if (readahead)
 				hits = min_t(int, hits + 1, SWAP_RA_HITS_MAX);
 			atomic_long_set(&vma->swap_readahead_info,
 					SWAP_RA_VAL(addr, win, hits));
 		}
+
 		if (readahead) {
 			count_vm_event(SWAP_RA_HIT);
-			if (!vma)
+			if (!vma || !vma_ra)
 				atomic_inc(&swapin_readahead_hits);
 		}
 	}
+
 	return page;
 }
 
@@ -365,8 +386,8 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			struct vm_area_struct *vma, unsigned long addr,
 			bool *new_page_allocated)
 {
-	struct page *found_page, *new_page = NULL;
-	struct address_space *swapper_space = swap_address_space(entry);
+	struct page *found_page = NULL, *new_page = NULL;
+	struct swap_info_struct *si;
 	int err;
 	*new_page_allocated = false;
 
@@ -376,7 +397,12 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * called after lookup_swap_cache() failed, re-calling
 		 * that would confuse statistics.
 		 */
-		found_page = find_get_page(swapper_space, swp_offset(entry));
+		si = get_swap_device(entry);
+		if (!si)
+			break;
+		found_page = find_get_page(swap_address_space(entry),
+					   swp_offset(entry));
+		put_swap_device(si);
 		if (found_page)
 			break;
 
@@ -533,11 +559,10 @@ static unsigned long swapin_nr_pages(unsigned long offset)
 }
 
 /**
- * swapin_readahead - swap in pages in hope we need them soon
+ * swap_cluster_readahead - swap in pages in hope we need them soon
  * @entry: swap entry of this memory
  * @gfp_mask: memory allocation flags
- * @vma: user vma this address belongs to
- * @addr: target address for mempolicy
+ * @vmf: fault information
  *
  * Returns the struct page for entry and addr, after queueing swapin.
  *
@@ -549,10 +574,10 @@ static unsigned long swapin_nr_pages(unsigned long offset)
  * This has been extended to use the NUMA policies from the mm triggering
  * the readahead.
  *
- * Caller must hold down_read on the vma->vm_mm if vma is not NULL.
+ * Caller must hold down_read on the vma->vm_mm if vmf->vma is not NULL.
  */
-struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
-			struct vm_area_struct *vma, unsigned long addr)
+struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask,
+				struct vm_fault *vmf)
 {
 	struct page *page;
 	unsigned long entry_offset = swp_offset(entry);
@@ -562,6 +587,8 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 	struct swap_info_struct *si = swp_swap_info(entry);
 	struct blk_plug plug;
 	bool do_poll = true, page_allocated;
+	struct vm_area_struct *vma = vmf->vma;
+	unsigned long addr = vmf->address;
 
 	mask = swapin_nr_pages(offset) - 1;
 	if (!mask)
@@ -586,8 +613,7 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
 			continue;
 		if (page_allocated) {
 			swap_readpage(page, false);
-			if (offset != entry_offset &&
-			    likely(!PageTransCompound(page))) {
+			if (offset != entry_offset) {
 				SetPageReadahead(page);
 				count_vm_event(SWAP_RA);
 			}
@@ -649,16 +675,15 @@ static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma,
 		    PFN_DOWN((faddr & PMD_MASK) + PMD_SIZE));
 }
 
-struct page *swap_readahead_detect(struct vm_fault *vmf,
-				   struct vma_swap_readahead *swap_ra)
+static void swap_ra_info(struct vm_fault *vmf,
+			struct vma_swap_readahead *ra_info)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	unsigned long swap_ra_info;
-	struct page *page;
+	unsigned long ra_val;
 	swp_entry_t entry;
 	unsigned long faddr, pfn, fpfn;
 	unsigned long start, end;
-	pte_t *pte;
+	pte_t *pte, *orig_pte;
 	unsigned int max_win, hits, prev_win, win, left;
 #ifndef CONFIG_64BIT
 	pte_t *tpte;
@@ -667,30 +692,32 @@ struct page *swap_readahead_detect(struct vm_fault *vmf,
 	max_win = 1 << min_t(unsigned int, READ_ONCE(page_cluster),
 			     SWAP_RA_ORDER_CEILING);
 	if (max_win == 1) {
-		swap_ra->win = 1;
-		return NULL;
+		ra_info->win = 1;
+		return;
 	}
 
 	faddr = vmf->address;
-	entry = pte_to_swp_entry(vmf->orig_pte);
-	if ((unlikely(non_swap_entry(entry))))
-		return NULL;
-	page = lookup_swap_cache(entry, vma, faddr);
-	if (page)
-		return page;
+	orig_pte = pte = pte_offset_map(vmf->pmd, faddr);
+	entry = pte_to_swp_entry(*pte);
+	if ((unlikely(non_swap_entry(entry)))) {
+		pte_unmap(orig_pte);
+		return;
+	}
 
 	fpfn = PFN_DOWN(faddr);
-	swap_ra_info = GET_SWAP_RA_VAL(vma);
-	pfn = PFN_DOWN(SWAP_RA_ADDR(swap_ra_info));
-	prev_win = SWAP_RA_WIN(swap_ra_info);
-	hits = SWAP_RA_HITS(swap_ra_info);
-	swap_ra->win = win = __swapin_nr_pages(pfn, fpfn, hits,
+	ra_val = GET_SWAP_RA_VAL(vma);
+	pfn = PFN_DOWN(SWAP_RA_ADDR(ra_val));
+	prev_win = SWAP_RA_WIN(ra_val);
+	hits = SWAP_RA_HITS(ra_val);
+	ra_info->win = win = __swapin_nr_pages(pfn, fpfn, hits,
 					       max_win, prev_win);
 	atomic_long_set(&vma->swap_readahead_info,
 			SWAP_RA_VAL(faddr, win, 0));
 
-	if (win == 1)
-		return NULL;
+	if (win == 1) {
+		pte_unmap(orig_pte);
+		return;
+	}
 
 	/* Copy the PTEs because the page table may be unmapped */
 	if (fpfn == pfn + 1)
@@ -703,23 +730,21 @@ struct page *swap_readahead_detect(struct vm_fault *vmf,
 		swap_ra_clamp_pfn(vma, faddr, fpfn - left, fpfn + win - left,
 				  &start, &end);
 	}
-	swap_ra->nr_pte = end - start;
-	swap_ra->offset = fpfn - start;
-	pte = vmf->pte - swap_ra->offset;
+	ra_info->nr_pte = end - start;
+	ra_info->offset = fpfn - start;
+	pte -= ra_info->offset;
 #ifdef CONFIG_64BIT
-	swap_ra->ptes = pte;
+	ra_info->ptes = pte;
 #else
-	tpte = swap_ra->ptes;
+	tpte = ra_info->ptes;
 	for (pfn = start; pfn != end; pfn++)
 		*tpte++ = *pte++;
 #endif
-
-	return NULL;
+	pte_unmap(orig_pte);
 }
 
-struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
-				    struct vm_fault *vmf,
-				    struct vma_swap_readahead *swap_ra)
+static struct page *swap_vma_readahead(swp_entry_t fentry, gfp_t gfp_mask,
+				       struct vm_fault *vmf)
 {
 	struct blk_plug plug;
 	struct vm_area_struct *vma = vmf->vma;
@@ -728,12 +753,14 @@ struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 	swp_entry_t entry;
 	unsigned int i;
 	bool page_allocated;
+	struct vma_swap_readahead ra_info = {0,};
 
-	if (swap_ra->win == 1)
+	swap_ra_info(vmf, &ra_info);
+	if (ra_info.win == 1)
 		goto skip;
 
 	blk_start_plug(&plug);
-	for (i = 0, pte = swap_ra->ptes; i < swap_ra->nr_pte;
+	for (i = 0, pte = ra_info.ptes; i < ra_info.nr_pte;
 	     i++, pte++) {
 		pentry = *pte;
 		if (pte_none(pentry))
@@ -749,8 +776,7 @@ struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 			continue;
 		if (page_allocated) {
 			swap_readpage(page, false);
-			if (i != swap_ra->offset &&
-			    likely(!PageTransCompound(page))) {
+			if (i != ra_info.offset) {
 				SetPageReadahead(page);
 				count_vm_event(SWAP_RA);
 			}
@@ -761,23 +787,43 @@ struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,
 	lru_add_drain();
 skip:
 	return read_swap_cache_async(fentry, gfp_mask, vma, vmf->address,
-				     swap_ra->win == 1);
+				     ra_info.win == 1);
+}
+
+/**
+ * swapin_readahead - swap in pages in hope we need them soon
+ * @entry: swap entry of this memory
+ * @gfp_mask: memory allocation flags
+ * @vmf: fault information
+ *
+ * Returns the struct page for entry and addr, after queueing swapin.
+ *
+ * It's a main entry function for swap readahead. By the configuration,
+ * it will read ahead blocks by cluster-based(ie, physical disk based)
+ * or vma-based(ie, virtual address based on faulty address) readahead.
+ */
+struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
+				struct vm_fault *vmf)
+{
+	return swap_use_vma_readahead() ?
+			swap_vma_readahead(entry, gfp_mask, vmf) :
+			swap_cluster_readahead(entry, gfp_mask, vmf);
 }
 
 #ifdef CONFIG_SYSFS
 static ssize_t vma_ra_enabled_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *buf)
 {
-	return sprintf(buf, "%s\n", swap_vma_readahead ? "true" : "false");
+	return sprintf(buf, "%s\n", enable_vma_readahead ? "true" : "false");
 }
 static ssize_t vma_ra_enabled_store(struct kobject *kobj,
 				      struct kobj_attribute *attr,
 				      const char *buf, size_t count)
 {
 	if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1))
-		swap_vma_readahead = true;
+		enable_vma_readahead = true;
 	else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1))
-		swap_vma_readahead = false;
+		enable_vma_readahead = false;
 	else
 		return -EINVAL;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index c7a33717d079..0b3674b1409a 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -38,6 +38,7 @@
 #include <linux/export.h>
 #include <linux/swap_slots.h>
 #include <linux/sort.h>
+#include <linux/stop_machine.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -85,7 +86,7 @@ PLIST_HEAD(swap_active_head);
  * is held and the locking order requires swap_lock to be taken
  * before any swap_info_struct->lock.
  */
-struct plist_head *swap_avail_heads;
+static struct plist_head *swap_avail_heads;
 static DEFINE_SPINLOCK(swap_avail_lock);
 
 struct swap_info_struct *swap_info[MAX_SWAPFILES];
@@ -1107,6 +1108,64 @@ static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
 	return p;
 }
 
+/*
+ * Check whether swap entry is valid in the swap device.  If so,
+ * return pointer to swap_info_struct, and keep the swap entry valid
+ * via preventing the swap device from being swapoff, until
+ * put_swap_device() is called.  Otherwise return NULL.
+ *
+ * Notice that swapoff or swapoff+swapon can still happen before the
+ * preempt_disable() in get_swap_device() or after the
+ * preempt_enable() in put_swap_device() if there isn't any other way
+ * to prevent swapoff, such as page lock, page table lock, etc.  The
+ * caller must be prepared for that.  For example, the following
+ * situation is possible.
+ *
+ *   CPU1				CPU2
+ *   do_swap_page()
+ *     ...				swapoff+swapon
+ *     __read_swap_cache_async()
+ *       swapcache_prepare()
+ *         __swap_duplicate()
+ *           // check swap_map
+ *     // verify PTE not changed
+ *
+ * In __swap_duplicate(), the swap_map need to be checked before
+ * changing partly because the specified swap entry may be for another
+ * swap device which has been swapoff.  And in do_swap_page(), after
+ * the page is read from the swap device, the PTE is verified not
+ * changed with the page table locked to check whether the swap device
+ * has been swapoff or swapoff+swapon.
+ */
+struct swap_info_struct *get_swap_device(swp_entry_t entry)
+{
+	struct swap_info_struct *si;
+	unsigned long type, offset;
+
+	if (!entry.val)
+		goto out;
+	type = swp_type(entry);
+	if (type >= nr_swapfiles)
+		goto bad_nofile;
+	si = swap_info[type];
+
+	preempt_disable();
+	if (!(si->flags & SWP_VALID))
+		goto unlock_out;
+	offset = swp_offset(entry);
+	if (offset >= si->max)
+		goto unlock_out;
+
+	return si;
+bad_nofile:
+	pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val);
+out:
+	return NULL;
+unlock_out:
+	preempt_enable();
+	return NULL;
+}
+
 static unsigned char __swap_entry_free(struct swap_info_struct *p,
 				       swp_entry_t entry, unsigned char usage)
 {
@@ -1328,11 +1387,18 @@ int page_swapcount(struct page *page)
 	return count;
 }
 
-int __swap_count(struct swap_info_struct *si, swp_entry_t entry)
+int __swap_count(swp_entry_t entry)
 {
+	struct swap_info_struct *si;
 	pgoff_t offset = swp_offset(entry);
+	int count = 0;
 
-	return swap_count(si->swap_map[offset]);
+	si = get_swap_device(entry);
+	if (si) {
+		count = swap_count(si->swap_map[offset]);
+		put_swap_device(si);
+	}
+	return count;
 }
 
 static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry)
@@ -1357,9 +1423,11 @@ int __swp_swapcount(swp_entry_t entry)
 	int count = 0;
 	struct swap_info_struct *si;
 
-	si = __swap_info_get(entry);
-	if (si)
+	si = get_swap_device(entry);
+	if (si) {
 		count = swap_swapcount(si, entry);
+		put_swap_device(si);
+	}
 	return count;
 }
 
@@ -1800,8 +1868,6 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
 	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
 	get_page(page);
-	set_pte_at(vma->vm_mm, addr, pte,
-		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	if (page == swapcache) {
 		page_add_anon_rmap(page, vma, addr, false);
 		mem_cgroup_commit_charge(page, memcg, true, false);
@@ -1810,6 +1876,8 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
+	set_pte_at(vma->vm_mm, addr, pte,
+		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
@@ -2451,9 +2519,9 @@ static int swap_node(struct swap_info_struct *p)
 	return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE;
 }
 
-static void _enable_swap_info(struct swap_info_struct *p, int prio,
-				unsigned char *swap_map,
-				struct swap_cluster_info *cluster_info)
+static void setup_swap_info(struct swap_info_struct *p, int prio,
+			    unsigned char *swap_map,
+			    struct swap_cluster_info *cluster_info)
 {
 	int i;
 
@@ -2478,7 +2546,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	}
 	p->swap_map = swap_map;
 	p->cluster_info = cluster_info;
-	p->flags |= SWP_WRITEOK;
+}
+
+static void _enable_swap_info(struct swap_info_struct *p)
+{
+	p->flags |= SWP_WRITEOK | SWP_VALID;
 	atomic_long_add(p->pages, &nr_swap_pages);
 	total_swap_pages += p->pages;
 
@@ -2497,6 +2569,11 @@ static void _enable_swap_info(struct swap_info_struct *p, int prio,
 	add_to_avail_list(p);
 }
 
+static int swap_onoff_stop(void *arg)
+{
+	return 0;
+}
+
 static void enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				struct swap_cluster_info *cluster_info,
@@ -2505,7 +2582,17 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
 	frontswap_init(p->type, frontswap_map);
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	 _enable_swap_info(p, prio, swap_map, cluster_info);
+	setup_swap_info(p, prio, swap_map, cluster_info);
+	spin_unlock(&p->lock);
+	spin_unlock(&swap_lock);
+	/*
+	 * Guarantee swap_map, cluster_info, etc. fields are used
+	 * between get/put_swap_device() only if SWP_VALID bit is set
+	 */
+	stop_machine(swap_onoff_stop, NULL, cpu_online_mask);
+	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
+	_enable_swap_info(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -2514,7 +2601,8 @@ static void reinsert_swap_info(struct swap_info_struct *p)
 {
 	spin_lock(&swap_lock);
 	spin_lock(&p->lock);
-	_enable_swap_info(p, p->prio, p->swap_map, p->cluster_info);
+	setup_swap_info(p, p->prio, p->swap_map, p->cluster_info);
+	_enable_swap_info(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
 }
@@ -2617,6 +2705,17 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 
 	reenable_swap_slots_cache_unlock();
 
+	spin_lock(&swap_lock);
+	spin_lock(&p->lock);
+	p->flags &= ~SWP_VALID;		/* mark swap device as invalid */
+	spin_unlock(&p->lock);
+	spin_unlock(&swap_lock);
+	/*
+	 * wait for swap operations protected by get/put_swap_device()
+	 * to complete
+	 */
+	stop_machine(swap_onoff_stop, NULL, cpu_online_mask);
+
 	flush_work(&p->discard_work);
 
 	destroy_swap_extents(p);
@@ -3356,22 +3455,16 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 {
 	struct swap_info_struct *p;
 	struct swap_cluster_info *ci;
-	unsigned long offset, type;
+	unsigned long offset;
 	unsigned char count;
 	unsigned char has_cache;
 	int err = -EINVAL;
 
-	if (non_swap_entry(entry))
+	p = get_swap_device(entry);
+	if (!p)
 		goto out;
 
-	type = swp_type(entry);
-	if (type >= nr_swapfiles)
-		goto bad_file;
-	p = swap_info[type];
 	offset = swp_offset(entry);
-	if (unlikely(offset >= p->max))
-		goto out;
-
 	ci = lock_cluster_or_swap_info(p, offset);
 
 	count = p->swap_map[offset];
@@ -3417,11 +3510,9 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
 unlock_out:
 	unlock_cluster_or_swap_info(p, ci);
 out:
+	if (p)
+		put_swap_device(p);
 	return err;
-
-bad_file:
-	pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val);
-	goto out;
 }
 
 /*
@@ -3513,6 +3604,7 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	struct page *list_page;
 	pgoff_t offset;
 	unsigned char count;
+	int ret = 0;
 
 	/*
 	 * When debugging, it's easier to use __GFP_ZERO here; but it's better
@@ -3520,15 +3612,15 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	 */
 	page = alloc_page(gfp_mask | __GFP_HIGHMEM);
 
-	si = swap_info_get(entry);
+	si = get_swap_device(entry);
 	if (!si) {
 		/*
 		 * An acceptable race has occurred since the failing
-		 * __swap_duplicate(): the swap entry has been freed,
-		 * perhaps even the whole swap_map cleared for swapoff.
+		 * __swap_duplicate(): the swap device may be swapoff
 		 */
 		goto outer;
 	}
+	spin_lock(&si->lock);
 
 	offset = swp_offset(entry);
 
@@ -3546,9 +3638,8 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask)
 	}
 
 	if (!page) {
-		unlock_cluster(ci);
-		spin_unlock(&si->lock);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	/*
@@ -3600,10 +3691,11 @@ out_unlock_cont:
 out:
 	unlock_cluster(ci);
 	spin_unlock(&si->lock);
+	put_swap_device(si);
 outer:
 	if (page)
 		__free_page(page);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/mm/util.c b/mm/util.c
index c1250501364f..1fc4fa7576f7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -287,7 +287,7 @@ int vma_is_stack_for_current(struct vm_area_struct *vma)
 }
 
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
-void arch_pick_mmap_layout(struct mm_struct *mm)
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
 {
 	mm->mmap_base = TASK_UNMAPPED_BASE;
 	mm->get_unmapped_area = arch_get_unmapped_area;
@@ -515,6 +515,16 @@ struct address_space *page_mapping(struct page *page)
 }
 EXPORT_SYMBOL(page_mapping);
 
+/*
+ * For file cache pages, return the address_space, otherwise return NULL
+ */
+struct address_space *page_mapping_file(struct page *page)
+{
+	if (unlikely(PageSwapCache(page)))
+		return NULL;
+	return page_mapping(page);
+}
+
 /* Slow path of page_mapcount() for compound pages */
 int __page_mapcount(struct page *page)
 {
@@ -658,6 +668,13 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		free += global_node_page_state(NR_SLAB_RECLAIMABLE);
 
 		/*
+		 * Part of the kernel memory, which can be released
+		 * under memory pressure.
+		 */
+		free += global_node_page_state(
+			NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT;
+
+		/*
 		 * Leave reserved pages. The pages are not for anonymous pages.
 		 */
 		if (free <= totalreserve_pages)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index cd5dc3faaa57..7bf65da22ff0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -116,6 +116,15 @@ struct scan_control {
 
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;
+
+	struct {
+		unsigned int dirty;
+		unsigned int unqueued_dirty;
+		unsigned int congested;
+		unsigned int writeback;
+		unsigned int immediate;
+		unsigned int file_taken;
+	} nr;
 };
 
 #ifdef ARCH_HAS_PREFETCH
@@ -190,6 +199,18 @@ static bool sane_reclaim(struct scan_control *sc)
 #endif
 	return false;
 }
+
+static void set_memcg_bit(enum pgdat_flags flag,
+			struct mem_cgroup *memcg)
+{
+	set_bit(flag, &memcg->flags);
+}
+
+static int test_memcg_bit(enum pgdat_flags flag,
+			struct mem_cgroup *memcg)
+{
+	return test_bit(flag, &memcg->flags);
+}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
@@ -200,6 +221,17 @@ static bool sane_reclaim(struct scan_control *sc)
 {
 	return true;
 }
+
+static inline void set_memcg_bit(enum pgdat_flags flag,
+				struct mem_cgroup *memcg)
+{
+}
+
+static inline int test_memcg_bit(enum pgdat_flags flag,
+				struct mem_cgroup *memcg)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -442,16 +474,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
 		return 0;
 
-	if (!down_read_trylock(&shrinker_rwsem)) {
-		/*
-		 * If we would return 0, our callers would understand that we
-		 * have nothing else to shrink and give up trying. By returning
-		 * 1 we keep it going and assume we'll be able to shrink next
-		 * time.
-		 */
-		freed = 1;
+	if (!down_read_trylock(&shrinker_rwsem))
 		goto out;
-	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		struct shrink_control sc = {
@@ -865,17 +889,6 @@ static void page_check_dirty_writeback(struct page *page,
 		mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
 }
 
-struct reclaim_stat {
-	unsigned nr_dirty;
-	unsigned nr_unqueued_dirty;
-	unsigned nr_congested;
-	unsigned nr_writeback;
-	unsigned nr_immediate;
-	unsigned nr_activate;
-	unsigned nr_ref_keep;
-	unsigned nr_unmap_fail;
-};
-
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -934,7 +947,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
 
 		/*
-		 * The number of dirty pages determines if a zone is marked
+		 * The number of dirty pages determines if a node is marked
 		 * reclaim_congested which affects wait_iff_congested. kswapd
 		 * will stall and start writing pages if the tail of the LRU
 		 * is all dirty unqueued pages.
@@ -1763,23 +1776,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	free_unref_page_list(&page_list);
 
 	/*
-	 * If reclaim is isolating dirty pages under writeback, it implies
-	 * that the long-lived page allocation rate is exceeding the page
-	 * laundering rate. Either the global limits are not being effective
-	 * at throttling processes due to the page distribution throughout
-	 * zones or there is heavy usage of a slow backing device. The
-	 * only option is to throttle from reclaim context which is not ideal
-	 * as there is no guarantee the dirtying process is throttled in the
-	 * same way balance_dirty_pages() manages.
-	 *
-	 * Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number
-	 * of pages under pages flagged for immediate reclaim and stall if any
-	 * are encountered in the nr_immediate check below.
-	 */
-	if (stat.nr_writeback && stat.nr_writeback == nr_taken)
-		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
-
-	/*
 	 * If dirty pages are scanned that are not queued for IO, it
 	 * implies that flushers are not doing their job. This can
 	 * happen when memory pressure pushes dirty pages to the end of
@@ -1793,48 +1789,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (stat.nr_unqueued_dirty == nr_taken)
 		wakeup_flusher_threads(WB_REASON_VMSCAN);
 
-	/*
-	 * Legacy memcg will stall in page writeback so avoid forcibly
-	 * stalling here.
-	 */
-	if (sane_reclaim(sc)) {
-		/*
-		 * Tag a zone as congested if all the dirty pages scanned were
-		 * backed by a congested BDI and wait_iff_congested will stall.
-		 */
-		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
-			set_bit(PGDAT_CONGESTED, &pgdat->flags);
-
-		/* Allow kswapd to start writing pages during reclaim. */
-		if (stat.nr_unqueued_dirty == nr_taken)
-			set_bit(PGDAT_DIRTY, &pgdat->flags);
-
-		/*
-		 * If kswapd scans pages marked marked for immediate
-		 * reclaim and under writeback (nr_immediate), it implies
-		 * that pages are cycling through the LRU faster than
-		 * they are written so also forcibly stall.
-		 */
-		if (stat.nr_immediate && current_may_throttle())
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
-	}
-
-	/*
-	 * Stall direct reclaim for IO completions if underlying BDIs or zone
-	 * is congested. Allow kswapd to continue until it starts encountering
-	 * unqueued dirty pages or cycling through the LRU too quickly.
-	 */
-	if (!sc->hibernation_mode && !current_is_kswapd() &&
-	    current_may_throttle())
-		wait_iff_congested(pgdat, BLK_RW_ASYNC, HZ/10);
+	sc->nr.dirty += stat.nr_dirty;
+	sc->nr.congested += stat.nr_congested;
+	sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
+	sc->nr.writeback += stat.nr_writeback;
+	sc->nr.immediate += stat.nr_immediate;
+	if (file)
+		sc->nr.file_taken += nr_taken;
 
 	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
-			nr_scanned, nr_reclaimed,
-			stat.nr_dirty,  stat.nr_writeback,
-			stat.nr_congested, stat.nr_immediate,
-			stat.nr_activate, stat.nr_ref_keep,
-			stat.nr_unmap_fail,
-			sc->priority, file);
+			nr_scanned, nr_reclaimed, &stat, sc->priority, file);
 	return nr_reclaimed;
 }
 
@@ -2515,6 +2479,12 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat,
 	return true;
 }
 
+static bool pgdat_memcg_congested(pg_data_t *pgdat, struct mem_cgroup *memcg)
+{
+	return test_bit(PGDAT_CONGESTED, &pgdat->flags) ||
+		(memcg && test_memcg_bit(PGDAT_CONGESTED, memcg));
+}
+
 static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 {
 	struct reclaim_state *reclaim_state = current->reclaim_state;
@@ -2530,6 +2500,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 		unsigned long node_lru_pages = 0;
 		struct mem_cgroup *memcg;
 
+		memset(&sc->nr, 0, sizeof(sc->nr));
+
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
@@ -2595,6 +2567,68 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 		if (sc->nr_reclaimed - nr_reclaimed)
 			reclaimable = true;
 
+		if (current_is_kswapd()) {
+			/*
+			 * If reclaim is isolating dirty pages under writeback,
+			 * it implies that the long-lived page allocation rate
+			 * is exceeding the page laundering rate. Either the
+			 * global limits are not being effective at throttling
+			 * processes due to the page distribution throughout
+			 * zones or there is heavy usage of a slow backing
+			 * device. The only option is to throttle from reclaim
+			 * context which is not ideal as there is no guarantee
+			 * the dirtying process is throttled in the same way
+			 * balance_dirty_pages() manages.
+			 *
+			 * Once a node is flagged PGDAT_WRITEBACK, kswapd will
+			 * count the number of pages under pages flagged for
+			 * immediate reclaim and stall if any are encountered
+			 * in the nr_immediate check below.
+			 */
+			if (sc->nr.writeback &&
+			    sc->nr.writeback == sc->nr.file_taken)
+				set_bit(PGDAT_WRITEBACK, &pgdat->flags);
+
+			/*
+			 * Tag a node as congested if all the dirty pages
+			 * scanned were backed by a congested BDI and
+			 * wait_iff_congested will stall.
+			 */
+			if (sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+				set_bit(PGDAT_CONGESTED, &pgdat->flags);
+
+			/* Allow kswapd to start writing pages during reclaim.*/
+			if (sc->nr.unqueued_dirty == sc->nr.file_taken)
+				set_bit(PGDAT_DIRTY, &pgdat->flags);
+
+			/*
+			 * If kswapd scans pages marked marked for immediate
+			 * reclaim and under writeback (nr_immediate), it
+			 * implies that pages are cycling through the LRU
+			 * faster than they are written so also forcibly stall.
+			 */
+			if (sc->nr.immediate)
+				congestion_wait(BLK_RW_ASYNC, HZ/10);
+		}
+
+		/*
+		 * Legacy memcg will stall in page writeback so avoid forcibly
+		 * stalling in wait_iff_congested().
+		 */
+		if (!global_reclaim(sc) && sane_reclaim(sc) &&
+		    sc->nr.dirty && sc->nr.dirty == sc->nr.congested)
+			set_memcg_bit(PGDAT_CONGESTED, root);
+
+		/*
+		 * Stall direct reclaim for IO completions if underlying BDIs
+		 * and node is congested. Allow kswapd to continue until it
+		 * starts encountering unqueued dirty pages or cycling through
+		 * the LRU too quickly.
+		 */
+		if (!sc->hibernation_mode && !current_is_kswapd() &&
+		   current_may_throttle() && pgdat_memcg_congested(pgdat, root))
+			wait_iff_congested(BLK_RW_ASYNC, HZ/10);
+
 	} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
 
@@ -3033,6 +3067,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 	 * the priority and make it zero.
 	 */
 	shrink_node_memcg(pgdat, memcg, &sc, &lru_pages);
+	clear_bit(PGDAT_CONGESTED, &memcg->flags);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
@@ -3078,6 +3113,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	noreclaim_flag = memalloc_noreclaim_save();
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 	memalloc_noreclaim_restore(noreclaim_flag);
+	clear_bit(PGDAT_CONGESTED, &memcg->flags);
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
 
@@ -3547,16 +3583,21 @@ kswapd_try_sleep:
 }
 
 /*
- * A zone is low on free memory, so wake its kswapd task to service it.
+ * A zone is low on free memory or too fragmented for high-order memory.  If
+ * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's
+ * pgdat.  It will wake up kcompactd after reclaiming memory.  If kswapd reclaim
+ * has failed or is not needed, still wake up kcompactd if only compaction is
+ * needed.
  */
-void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
+void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
+		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
 
 	if (!managed_zone(zone))
 		return;
 
-	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
+	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
 	pgdat = zone->zone_pgdat;
 	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
@@ -3565,14 +3606,23 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
-	/* Hopeless node, leave it to direct reclaim */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
-		return;
-
-	if (pgdat_balanced(pgdat, order, classzone_idx))
+	/* Hopeless node, leave it to direct reclaim if possible */
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
+	    pgdat_balanced(pgdat, order, classzone_idx)) {
+		/*
+		 * There may be plenty of free memory available, but it's too
+		 * fragmented for high-order allocations.  Wake up kcompactd
+		 * and rely on compaction_suitable() to determine if it's
+		 * needed.  If it fails, it will defer subsequent attempts to
+		 * ratelimit its work.
+		 */
+		if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
+			wakeup_kcompactd(pgdat, order, classzone_idx);
 		return;
+	}
 
-	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order);
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order,
+				      gfp_flags);
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
@@ -3802,7 +3852,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 
 	if (node_pagecache_reclaimable(pgdat) > pgdat->min_unmapped_pages) {
 		/*
-		 * Free memory by calling shrink zone with increasing
+		 * Free memory by calling shrink node with increasing
 		 * priorities until we have enough memory freed.
 		 */
 		do {
@@ -3877,7 +3927,13 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
  */
 int page_evictable(struct page *page)
 {
-	return !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+	int ret;
+
+	/* Prevent address_space of inode and swap cache from being freed */
+	rcu_read_lock();
+	ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+	rcu_read_unlock();
+	return ret;
 }
 
 #ifdef CONFIG_SHMEM
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 33581be705f0..536332e988b8 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1161,6 +1161,7 @@ const char * const vmstat_text[] = {
 	"nr_vmscan_immediate_reclaim",
 	"nr_dirtied",
 	"nr_written",
+	"nr_indirectly_reclaimable",
 
 	/* enum writeback_stat_item counters */
 	"nr_dirty_threshold",
diff --git a/mm/z3fold.c b/mm/z3fold.c
index d589d318727f..f579ad4a8100 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -620,24 +620,27 @@ lookup:
 		bud = FIRST;
 	}
 
-	spin_lock(&pool->stale_lock);
-	zhdr = list_first_entry_or_null(&pool->stale,
-					struct z3fold_header, buddy);
-	/*
-	 * Before allocating a page, let's see if we can take one from the
-	 * stale pages list. cancel_work_sync() can sleep so we must make
-	 * sure it won't be called in case we're in atomic context.
-	 */
-	if (zhdr && (can_sleep || !work_pending(&zhdr->work))) {
-		list_del(&zhdr->buddy);
-		spin_unlock(&pool->stale_lock);
-		if (can_sleep)
+	page = NULL;
+	if (can_sleep) {
+		spin_lock(&pool->stale_lock);
+		zhdr = list_first_entry_or_null(&pool->stale,
+						struct z3fold_header, buddy);
+		/*
+		 * Before allocating a page, let's see if we can take one from
+		 * the stale pages list. cancel_work_sync() can sleep so we
+		 * limit this case to the contexts where we can sleep
+		 */
+		if (zhdr) {
+			list_del(&zhdr->buddy);
+			spin_unlock(&pool->stale_lock);
 			cancel_work_sync(&zhdr->work);
-		page = virt_to_page(zhdr);
-	} else {
-		spin_unlock(&pool->stale_lock);
-		page = alloc_page(gfp);
+			page = virt_to_page(zhdr);
+		} else {
+			spin_unlock(&pool->stale_lock);
+		}
 	}
+	if (!page)
+		page = alloc_page(gfp);
 
 	if (!page)
 		return -ENOMEM;
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b7f61cd1c709..61cb05dc950c 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -193,6 +193,7 @@ static struct vfsmount *zsmalloc_mnt;
  * (see: fix_fullness_group())
  */
 static const int fullness_threshold_frac = 4;
+static size_t huge_class_size;
 
 struct size_class {
 	spinlock_t lock;
@@ -642,18 +643,7 @@ static int zs_stats_size_show(struct seq_file *s, void *v)
 
 	return 0;
 }
-
-static int zs_stats_size_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, zs_stats_size_show, inode->i_private);
-}
-
-static const struct file_operations zs_stat_size_ops = {
-	.open           = zs_stats_size_open,
-	.read           = seq_read,
-	.llseek         = seq_lseek,
-	.release        = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(zs_stats_size);
 
 static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
 {
@@ -672,7 +662,7 @@ static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
 	pool->stat_dentry = entry;
 
 	entry = debugfs_create_file("classes", S_IFREG | S_IRUGO,
-			pool->stat_dentry, pool, &zs_stat_size_ops);
+			pool->stat_dentry, pool, &zs_stats_size_fops);
 	if (!entry) {
 		pr_warn("%s: debugfs file entry <%s> creation failed\n",
 				name, "classes");
@@ -861,6 +851,7 @@ static struct page *get_next_page(struct page *page)
 
 /**
  * obj_to_location - get (<page>, <obj_idx>) from encoded object value
+ * @obj: the encoded object value
  * @page: page object resides in zspage
  * @obj_idx: object index
  */
@@ -1311,6 +1302,7 @@ EXPORT_SYMBOL_GPL(zs_get_total_pages);
  * zs_map_object - get address of allocated object from handle.
  * @pool: pool from which the object was allocated
  * @handle: handle returned from zs_malloc
+ * @mm: maping mode to use
  *
  * Before using an object allocated from zs_malloc, it must be mapped using
  * this function. When done with the object, it must be unmapped using
@@ -1418,6 +1410,25 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 }
 EXPORT_SYMBOL_GPL(zs_unmap_object);
 
+/**
+ * zs_huge_class_size() - Returns the size (in bytes) of the first huge
+ *                        zsmalloc &size_class.
+ * @pool: zsmalloc pool to use
+ *
+ * The function returns the size of the first huge class - any object of equal
+ * or bigger size will be stored in zspage consisting of a single physical
+ * page.
+ *
+ * Context: Any context.
+ *
+ * Return: the size (in bytes) of the first huge zsmalloc &size_class.
+ */
+size_t zs_huge_class_size(struct zs_pool *pool)
+{
+	return huge_class_size;
+}
+EXPORT_SYMBOL_GPL(zs_huge_class_size);
+
 static unsigned long obj_malloc(struct size_class *class,
 				struct zspage *zspage, unsigned long handle)
 {
@@ -2375,6 +2386,27 @@ struct zs_pool *zs_create_pool(const char *name)
 		objs_per_zspage = pages_per_zspage * PAGE_SIZE / size;
 
 		/*
+		 * We iterate from biggest down to smallest classes,
+		 * so huge_class_size holds the size of the first huge
+		 * class. Any object bigger than or equal to that will
+		 * endup in the huge class.
+		 */
+		if (pages_per_zspage != 1 && objs_per_zspage != 1 &&
+				!huge_class_size) {
+			huge_class_size = size;
+			/*
+			 * The object uses ZS_HANDLE_SIZE bytes to store the
+			 * handle. We need to subtract it, because zs_malloc()
+			 * unconditionally adds handle size before it performs
+			 * size class search - so object may be smaller than
+			 * huge class size, yet it still can end up in the huge
+			 * class because it grows by ZS_HANDLE_SIZE extra bytes
+			 * right before class lookup.
+			 */
+			huge_class_size -= (ZS_HANDLE_SIZE - 1);
+		}
+
+		/*
 		 * size_class is used for normal zsmalloc operation such
 		 * as alloc/free for that size. Although it is natural that we
 		 * have one size_class for each size, there is a chance that we
diff --git a/net/9p/client.c b/net/9p/client.c
index b433aff5ff13..21e6df1cc70f 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -190,7 +190,9 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 				p9_debug(P9_DEBUG_ERROR,
 					 "problem allocating copy of trans arg\n");
 				goto free_and_return;
-			 }
+			}
+
+			v9fs_put_trans(clnt->trans_mod);
 			clnt->trans_mod = v9fs_get_trans_by_name(s);
 			if (clnt->trans_mod == NULL) {
 				pr_info("Could not find request transport: %s\n",
@@ -226,6 +228,7 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	}
 
 free_and_return:
+	v9fs_put_trans(clnt->trans_mod);
 	kfree(tmp_options);
 	return ret;
 }
@@ -769,7 +772,7 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 	if (err < 0) {
 		if (err != -ERESTARTSYS && err != -EFAULT)
 			c->status = Disconnected;
-		goto reterr;
+		goto recalc_sigpending;
 	}
 again:
 	/* Wait for the response */
@@ -804,6 +807,7 @@ again:
 		if (req->status == REQ_STATUS_RCVD)
 			err = 0;
 	}
+recalc_sigpending:
 	if (sigpending) {
 		spin_lock_irqsave(&current->sighand->siglock, flags);
 		recalc_sigpending();
@@ -867,7 +871,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 		if (err == -EIO)
 			c->status = Disconnected;
 		if (err != -ERESTARTSYS)
-			goto reterr;
+			goto recalc_sigpending;
 	}
 	if (req->status == REQ_STATUS_ERROR) {
 		p9_debug(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
@@ -885,6 +889,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 		if (req->status == REQ_STATUS_RCVD)
 			err = 0;
 	}
+recalc_sigpending:
 	if (sigpending) {
 		spin_lock_irqsave(&current->sighand->siglock, flags);
 		recalc_sigpending();
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index b3b609f0eeb5..b1a2c5e38530 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -15,7 +15,6 @@
 #include <linux/vmalloc.h>
 #include <linux/init.h>
 #include <linux/slab.h>
-#include <linux/kmemleak.h>
 
 #include <net/ip.h>
 #include <net/sock.h>
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index a058de677e94..6247850a22f7 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -46,7 +46,7 @@
 #include <net/sock.h>
 #include <net/raw.h>
 
-#define TCPUDP_MIB_MAX max_t(u32, UDP_MIB_MAX, TCP_MIB_MAX)
+#define TCPUDP_MIB_MAX const_max(UDP_MIB_MAX, TCP_MIB_MAX)
 
 /*
  *	Report socket allocation statistics [mea@utu.fi]
@@ -404,7 +404,7 @@ static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v)
 	struct net *net = seq->private;
 	int i;
 
-	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
+	memset(buff, 0, sizeof(buff));
 
 	seq_puts(seq, "\nTcp:");
 	for (i = 0; snmp4_tcp_list[i].name; i++)
@@ -421,7 +421,7 @@ static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v)
 			seq_printf(seq, " %lu", buff[i]);
 	}
 
-	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
+	memset(buff, 0, sizeof(buff));
 
 	snmp_get_cpu_field_batch(buff, snmp4_udp_list,
 				 net->mib.udp_statistics);
@@ -432,7 +432,7 @@ static int snmp_seq_show_tcp_udp(struct seq_file *seq, void *v)
 	for (i = 0; snmp4_udp_list[i].name; i++)
 		seq_printf(seq, " %lu", buff[i]);
 
-	memset(buff, 0, TCPUDP_MIB_MAX * sizeof(unsigned long));
+	memset(buff, 0, sizeof(buff));
 
 	/* the UDP and UDP-Lite MIBs are the same */
 	seq_puts(seq, "\nUdpLite:");
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8322e479f299..594a1c605c92 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -108,7 +108,6 @@
 #include <net/rtnetlink.h>
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
-#include <linux/kmemleak.h>
 #endif
 #include <net/secure_seq.h>
 #include <net/ip_tunnels.h>
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index a85f7e0b14b1..36e8d4212fea 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -30,10 +30,8 @@
 #include <net/transp_v6.h>
 #include <net/ipv6.h>
 
-#define MAX4(a, b, c, d) \
-	max_t(u32, max_t(u32, a, b), max_t(u32, c, d))
-#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \
-			IPSTATS_MIB_MAX, ICMP_MIB_MAX)
+#define SNMP_MIB_MAX const_max(const_max(UDP_MIB_MAX, TCP_MIB_MAX), \
+			       const_max(IPSTATS_MIB_MAX, ICMP_MIB_MAX))
 
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
@@ -200,7 +198,7 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib,
 	int i;
 
 	if (pcpumib) {
-		memset(buff, 0, sizeof(unsigned long) * SNMP_MIB_MAX);
+		memset(buff, 0, sizeof(buff));
 
 		snmp_get_cpu_field_batch(buff, itemlist, pcpumib);
 		for (i = 0; itemlist[i].name; i++)
@@ -219,7 +217,7 @@ static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
 	u64 buff64[SNMP_MIB_MAX];
 	int i;
 
-	memset(buff64, 0, sizeof(u64) * SNMP_MIB_MAX);
+	memset(buff64, 0, sizeof(buff64));
 
 	snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff);
 	for (i = 0; itemlist[i].name; i++)
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 764ffd1bb1c5..d2464002bb40 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -791,7 +791,8 @@ our $FuncArg = qr{$Typecast{0,1}($LvalOrFunc|$Constant|$String)};
 our $declaration_macros = qr{(?x:
 	(?:$Storage\s+)?(?:[A-Z_][A-Z0-9]*_){0,2}(?:DEFINE|DECLARE)(?:_[A-Z0-9]+){1,6}\s*\(|
 	(?:$Storage\s+)?[HLP]?LIST_HEAD\s*\(|
-	(?:$Storage\s+)?${Type}\s+uninitialized_var\s*\(
+	(?:$Storage\s+)?${Type}\s+uninitialized_var\s*\(|
+	(?:SKCIPHER_REQUEST|SHASH_DESC|AHASH_REQUEST)_ON_STACK\s*\(
 )};
 
 sub deparenthesize {
@@ -1075,7 +1076,7 @@ sub parse_email {
 	} elsif ($formatted_email =~ /(\S+\@\S+)(.*)$/) {
 		$address = $1;
 		$comment = $2 if defined $2;
-		$formatted_email =~ s/$address.*$//;
+		$formatted_email =~ s/\Q$address\E.*$//;
 		$name = $formatted_email;
 		$name = trim($name);
 		$name =~ s/^\"|\"$//g;
@@ -1217,7 +1218,7 @@ sub sanitise_line {
 	for ($off = 1; $off < length($line); $off++) {
 		$c = substr($line, $off, 1);
 
-		# Comments we are wacking completly including the begin
+		# Comments we are whacking completely including the begin
 		# and end, all to $;.
 		if ($sanitise_quote eq '' && substr($line, $off, 2) eq '/*') {
 			$sanitise_quote = '*/';
@@ -1297,6 +1298,7 @@ sub sanitise_line {
 sub get_quoted_string {
 	my ($line, $rawline) = @_;
 
+	return "" if (!defined($line) || !defined($rawline));
 	return "" if ($line !~ m/($String)/g);
 	return substr($rawline, $-[0], $+[0] - $-[0]);
 }
@@ -1644,6 +1646,28 @@ sub raw_line {
 	return $line;
 }
 
+sub get_stat_real {
+	my ($linenr, $lc) = @_;
+
+	my $stat_real = raw_line($linenr, 0);
+	for (my $count = $linenr + 1; $count <= $lc; $count++) {
+		$stat_real = $stat_real . "\n" . raw_line($count, 0);
+	}
+
+	return $stat_real;
+}
+
+sub get_stat_here {
+	my ($linenr, $cnt, $here) = @_;
+
+	my $herectx = $here . "\n";
+	for (my $n = 0; $n < $cnt; $n++) {
+		$herectx .= raw_line($linenr, $n) . "\n";
+	}
+
+	return $herectx;
+}
+
 sub cat_vet {
 	my ($vet) = @_;
 	my ($res, $coded);
@@ -2257,6 +2281,8 @@ sub process {
 
 	my $camelcase_file_seeded = 0;
 
+	my $checklicenseline = 1;
+
 	sanitise_line_reset();
 	my $line;
 	foreach my $rawline (@rawlines) {
@@ -2448,6 +2474,7 @@ sub process {
 			} else {
 				$check = $check_orig;
 			}
+			$checklicenseline = 1;
 			next;
 		}
 
@@ -2911,6 +2938,30 @@ sub process {
 			}
 		}
 
+# check for using SPDX license tag at beginning of files
+		if ($realline == $checklicenseline) {
+			if ($rawline =~ /^[ \+]\s*\#\!\s*\//) {
+				$checklicenseline = 2;
+			} elsif ($rawline =~ /^\+/) {
+				my $comment = "";
+				if ($realfile =~ /\.(h|s|S)$/) {
+					$comment = '/*';
+				} elsif ($realfile =~ /\.(c|dts|dtsi)$/) {
+					$comment = '//';
+				} elsif (($checklicenseline == 2) || $realfile =~ /\.(sh|pl|py|awk|tc)$/) {
+					$comment = '#';
+				} elsif ($realfile =~ /\.rst$/) {
+					$comment = '..';
+				}
+
+				if ($comment !~ /^$/ &&
+				    $rawline !~ /^\+\Q$comment\E SPDX-License-Identifier: /) {
+					WARN("SPDX_LICENSE_TAG",
+					     "Missing or malformed SPDX-License-Identifier tag in line $checklicenseline\n" . $herecurr);
+				}
+			}
+		}
+
 # check we are in a valid source file if not then ignore this hunk
 		next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/);
 
@@ -4928,12 +4979,8 @@ sub process {
 			#print "REST<$rest> dstat<$dstat> ctx<$ctx>\n";
 
 			$ctx =~ s/\n*$//;
-			my $herectx = $here . "\n";
 			my $stmt_cnt = statement_rawlines($ctx);
-
-			for (my $n = 0; $n < $stmt_cnt; $n++) {
-				$herectx .= raw_line($linenr, $n) . "\n";
-			}
+			my $herectx = get_stat_here($linenr, $stmt_cnt, $here);
 
 			if ($dstat ne '' &&
 			    $dstat !~ /^(?:$Ident|-?$Constant),$/ &&			# 10, // foo(),
@@ -5005,12 +5052,9 @@ sub process {
 # check for macros with flow control, but without ## concatenation
 # ## concatenation is commonly a macro that defines a function so ignore those
 			if ($has_flow_statement && !$has_arg_concat) {
-				my $herectx = $here . "\n";
 				my $cnt = statement_rawlines($ctx);
+				my $herectx = get_stat_here($linenr, $cnt, $here);
 
-				for (my $n = 0; $n < $cnt; $n++) {
-					$herectx .= raw_line($linenr, $n) . "\n";
-				}
 				WARN("MACRO_WITH_FLOW_CONTROL",
 				     "Macros with flow control statements should be avoided\n" . "$herectx");
 			}
@@ -5050,11 +5094,7 @@ sub process {
 
 				$ctx =~ s/\n*$//;
 				my $cnt = statement_rawlines($ctx);
-				my $herectx = $here . "\n";
-
-				for (my $n = 0; $n < $cnt; $n++) {
-					$herectx .= raw_line($linenr, $n) . "\n";
-				}
+				my $herectx = get_stat_here($linenr, $cnt, $here);
 
 				if (($stmts =~ tr/;/;/) == 1 &&
 				    $stmts !~ /^\s*(if|while|for|switch)\b/) {
@@ -5068,11 +5108,7 @@ sub process {
 			} elsif ($dstat =~ /^\+\s*#\s*define\s+$Ident.*;\s*$/) {
 				$ctx =~ s/\n*$//;
 				my $cnt = statement_rawlines($ctx);
-				my $herectx = $here . "\n";
-
-				for (my $n = 0; $n < $cnt; $n++) {
-					$herectx .= raw_line($linenr, $n) . "\n";
-				}
+				my $herectx = get_stat_here($linenr, $cnt, $here);
 
 				WARN("TRAILING_SEMICOLON",
 				     "macros should not use a trailing semicolon\n" . "$herectx");
@@ -5195,12 +5231,8 @@ sub process {
 				}
 			}
 			if ($level == 0 && $block =~ /^\s*\{/ && !$allowed) {
-				my $herectx = $here . "\n";
 				my $cnt = statement_rawlines($block);
-
-				for (my $n = 0; $n < $cnt; $n++) {
-					$herectx .= raw_line($linenr, $n) . "\n";
-				}
+				my $herectx = get_stat_here($linenr, $cnt, $here);
 
 				WARN("BRACES",
 				     "braces {} are not necessary for single statement blocks\n" . $herectx);
@@ -5776,36 +5808,50 @@ sub process {
 			}
 		}
 
-		# check for vsprintf extension %p<foo> misuses
+# check for vsprintf extension %p<foo> misuses
 		if ($^V && $^V ge 5.10.0 &&
 		    defined $stat &&
 		    $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s &&
 		    $1 !~ /^_*volatile_*$/) {
-			my $bad_extension = "";
+			my $specifier;
+			my $extension;
+			my $bad_specifier = "";
+			my $stat_real;
+
 			my $lc = $stat =~ tr@\n@@;
 			$lc = $lc + $linenr;
 		        for (my $count = $linenr; $count <= $lc; $count++) {
 				my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
 				$fmt =~ s/%%//g;
-				if ($fmt =~ /(\%[\*\d\.]*p(?![\WSsBKRraEhMmIiUDdgVCbGNOx]).)/) {
-					$bad_extension = $1;
-					last;
-				}
-			}
-			if ($bad_extension ne "") {
-				my $stat_real = raw_line($linenr, 0);
-				my $ext_type = "Invalid";
-				my $use = "";
-				for (my $count = $linenr + 1; $count <= $lc; $count++) {
-					$stat_real = $stat_real . "\n" . raw_line($count, 0);
+
+				while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) {
+					$specifier = $1;
+					$extension = $2;
+					if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOx]/) {
+						$bad_specifier = $specifier;
+						last;
+					}
+					if ($extension eq "x" && !defined($stat_real)) {
+						if (!defined($stat_real)) {
+							$stat_real = get_stat_real($linenr, $lc);
+						}
+						WARN("VSPRINTF_SPECIFIER_PX",
+						     "Using vsprintf specifier '\%px' potentially exposes the kernel memory layout, if you don't really need the address please consider using '\%p'.\n" . "$here\n$stat_real\n");
+					}
 				}
-				if ($bad_extension =~ /p[Ff]/) {
-					$ext_type = "Deprecated";
-					$use = " - use %pS instead";
-					$use =~ s/pS/ps/ if ($bad_extension =~ /pf/);
+				if ($bad_specifier ne "") {
+					my $stat_real = get_stat_real($linenr, $lc);
+					my $ext_type = "Invalid";
+					my $use = "";
+					if ($bad_specifier =~ /p[Ff]/) {
+						$ext_type = "Deprecated";
+						$use = " - use %pS instead";
+						$use =~ s/pS/ps/ if ($bad_specifier =~ /pf/);
+					}
+
+					WARN("VSPRINTF_POINTER_EXTENSION",
+					     "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n");
 				}
-				WARN("VSPRINTF_POINTER_EXTENSION",
-				     "$ext_type vsprintf pointer extension '$bad_extension'$use\n" . "$here\n$stat_real\n");
 			}
 		}
 
@@ -5918,10 +5964,7 @@ sub process {
 		     $stat !~ /(?:$Compare)\s*\bsscanf\s*$balanced_parens/)) {
 			my $lc = $stat =~ tr@\n@@;
 			$lc = $lc + $linenr;
-			my $stat_real = raw_line($linenr, 0);
-		        for (my $count = $linenr + 1; $count <= $lc; $count++) {
-				$stat_real = $stat_real . "\n" . raw_line($count, 0);
-			}
+			my $stat_real = get_stat_real($linenr, $lc);
 			WARN("NAKED_SSCANF",
 			     "unchecked sscanf return value\n" . "$here\n$stat_real\n");
 		}
@@ -5932,10 +5975,7 @@ sub process {
 		    $line =~ /\bsscanf\b/) {
 			my $lc = $stat =~ tr@\n@@;
 			$lc = $lc + $linenr;
-			my $stat_real = raw_line($linenr, 0);
-		        for (my $count = $linenr + 1; $count <= $lc; $count++) {
-				$stat_real = $stat_real . "\n" . raw_line($count, 0);
-			}
+			my $stat_real = get_stat_real($linenr, $lc);
 			if ($stat_real =~ /\bsscanf\b\s*\(\s*$FuncArg\s*,\s*("[^"]+")/) {
 				my $format = $6;
 				my $count = $format =~ tr@%@%@;
@@ -6065,12 +6105,9 @@ sub process {
 			}
 			if ($r1 !~ /^sizeof\b/ && $r2 =~ /^sizeof\s*\S/ &&
 			    !($r1 =~ /^$Constant$/ || $r1 =~ /^[A-Z_][A-Z0-9_]*$/)) {
-				my $ctx = '';
-				my $herectx = $here . "\n";
 				my $cnt = statement_rawlines($stat);
-				for (my $n = 0; $n < $cnt; $n++) {
-					$herectx .= raw_line($linenr, $n) . "\n";
-				}
+				my $herectx = get_stat_here($linenr, $cnt, $here);
+
 				if (WARN("ALLOC_WITH_MULTIPLY",
 					 "Prefer $newfunc over $oldfunc with multiply\n" . $herectx) &&
 				    $cnt == 1 &&
@@ -6153,12 +6190,9 @@ sub process {
 		if ($^V && $^V ge 5.10.0 &&
 		    defined $stat &&
 		    $stat =~ /^\+[$;\s]*(?:case[$;\s]+\w+[$;\s]*:[$;\s]*|)*[$;\s]*\bdefault[$;\s]*:[$;\s]*;/g) {
-			my $ctx = '';
-			my $herectx = $here . "\n";
 			my $cnt = statement_rawlines($stat);
-			for (my $n = 0; $n < $cnt; $n++) {
-				$herectx .= raw_line($linenr, $n) . "\n";
-			}
+			my $herectx = get_stat_here($linenr, $cnt, $here);
+
 			WARN("DEFAULT_NO_BREAK",
 			     "switch default: should use break\n" . $herectx);
 		}
@@ -6369,10 +6403,7 @@ sub process {
 
 				my $lc = $stat =~ tr@\n@@;
 				$lc = $lc + $linenr;
-				my $stat_real = raw_line($linenr, 0);
-				for (my $count = $linenr + 1; $count <= $lc; $count++) {
-					$stat_real = $stat_real . "\n" . raw_line($count, 0);
-				}
+				my $stat_real = get_stat_real($linenr, $lc);
 
 				my $skip_args = "";
 				if ($arg_pos > 1) {
@@ -6398,7 +6429,7 @@ sub process {
 		}
 
 # check for uses of S_<PERMS> that could be octal for readability
-		if ($line =~ /\b($multi_mode_perms_string_search)\b/) {
+		while ($line =~ m{\b($multi_mode_perms_string_search)\b}g) {
 			my $oval = $1;
 			my $octal = perms_to_octal($oval);
 			if (WARN("SYMBOLIC_PERMS",
diff --git a/scripts/faddr2line b/scripts/faddr2line
index 7721d5b2b0c0..9e5735a4d3a5 100755
--- a/scripts/faddr2line
+++ b/scripts/faddr2line
@@ -163,7 +163,17 @@ __faddr2line() {
 
 		# pass real address to addr2line
 		echo "$func+$offset/$sym_size:"
-		${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;"
+		local file_lines=$(${ADDR2LINE} -fpie $objfile $addr | sed "s; $dir_prefix\(\./\)*; ;")
+		[[ -z $file_lines ]] && return
+
+		# show each line with context
+		echo "$file_lines" | while read -r line
+		do
+			echo $line
+			eval $(echo $line | awk -F "[ :]" '{printf("n1=%d;n2=%d;f=%s",$NF-5, $NF+5, $(NF-1))}')
+			awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") {printf("%d\t%s\n", NR, $0)}' $f
+		done
+
 		DONE=1
 
 	done < <(${NM} -n $objfile | awk -v fn=$func -v end=$file_end '$3 == fn { found=1; line=$0; start=$1; next } found == 1 { found=0; print line, "0x"$1 } END {if (found == 1) print line, end; }')
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 687f6043af58..cf00c8520d30 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -23,7 +23,6 @@
 #include <linux/sysctl.h>
 #include <linux/audit.h>
 #include <linux/user_namespace.h>
-#include <linux/kmemleak.h>
 #include <net/sock.h>
 
 #include "include/apparmor.h"
@@ -694,6 +693,7 @@ static void apparmor_bprm_committing_creds(struct linux_binprm *bprm)
 	aa_inherit_files(bprm->cred, current->files);
 
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* reset soft limits and set hard limits for the new label */
 	__aa_transition_rlimits(label, new_label);
diff --git a/security/keys/big_key.c b/security/keys/big_key.c
index fa728f662a6f..933623784ccd 100644
--- a/security/keys/big_key.c
+++ b/security/keys/big_key.c
@@ -18,6 +18,7 @@
 #include <linux/err.h>
 #include <linux/scatterlist.h>
 #include <linux/random.h>
+#include <linux/vmalloc.h>
 #include <keys/user-type.h>
 #include <keys/big_key-type.h>
 #include <crypto/aead.h>
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index b10f965d5ca8..14fcee01ec31 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -2641,6 +2641,7 @@ static void selinux_bprm_committing_creds(struct linux_binprm *bprm)
 
 	/* Always clear parent death signal on SID transitions. */
 	current->pdeath_signal = 0;
+	current->signal->pdeath_signal_proc = 0;
 
 	/* Check whether the new SID can inherit resource limits from the old
 	 * SID.  If not, reset all soft limits to the lower of the current
@@ -6006,6 +6007,7 @@ static int selinux_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 				    SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL);
 	case IPC_STAT:
 	case MSG_STAT:
+	case MSG_STAT_ANY:
 		perms = MSGQ__GETATTR | MSGQ__ASSOCIATE;
 		break;
 	case IPC_SET:
@@ -6157,6 +6159,7 @@ static int selinux_shm_shmctl(struct shmid_kernel *shp, int cmd)
 				    SECCLASS_SYSTEM, SYSTEM__IPC_INFO, NULL);
 	case IPC_STAT:
 	case SHM_STAT:
+	case SHM_STAT_ANY:
 		perms = SHM__GETATTR | SHM__ASSOCIATE;
 		break;
 	case IPC_SET:
@@ -6272,6 +6275,7 @@ static int selinux_sem_semctl(struct sem_array *sma, int cmd)
 		break;
 	case IPC_STAT:
 	case SEM_STAT:
+	case SEM_STAT_ANY:
 		perms = SEM__GETATTR | SEM__ASSOCIATE;
 		break;
 	default:
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index db02ddceacdd..c15fd665469e 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3049,6 +3049,7 @@ static int smack_shm_shmctl(struct shmid_kernel *shp, int cmd)
 	switch (cmd) {
 	case IPC_STAT:
 	case SHM_STAT:
+	case SHM_STAT_ANY:
 		may = MAY_READ;
 		break;
 	case IPC_SET:
@@ -3181,6 +3182,7 @@ static int smack_sem_semctl(struct sem_array *sma, int cmd)
 	case GETALL:
 	case IPC_STAT:
 	case SEM_STAT:
+	case SEM_STAT_ANY:
 		may = MAY_READ;
 		break;
 	case SETVAL:
@@ -3309,6 +3311,7 @@ static int smack_msg_queue_msgctl(struct msg_queue *msq, int cmd)
 	switch (cmd) {
 	case IPC_STAT:
 	case MSG_STAT:
+	case MSG_STAT_ANY:
 		may = MAY_READ;
 		break;
 	case IPC_SET:
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index bae6a4e9f2ee..d8010a135ed2 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -24,6 +24,7 @@ TARGETS += mqueue
 TARGETS += net
 TARGETS += nsfs
 TARGETS += powerpc
+TARGETS += proc
 TARGETS += pstore
 TARGETS += ptrace
 TARGETS += seccomp
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
new file mode 100644
index 000000000000..6c16f77c722c
--- /dev/null
+++ b/tools/testing/selftests/proc/.gitignore
@@ -0,0 +1,8 @@
+/proc-loadavg-001
+/proc-self-map-files-001
+/proc-self-map-files-002
+/proc-self-syscall
+/proc-self-wchan
+/proc-uptime-001
+/proc-uptime-002
+/read
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
new file mode 100644
index 000000000000..dbb87e56264c
--- /dev/null
+++ b/tools/testing/selftests/proc/Makefile
@@ -0,0 +1,13 @@
+CFLAGS += -Wall -O2
+
+TEST_GEN_PROGS :=
+TEST_GEN_PROGS += proc-loadavg-001
+TEST_GEN_PROGS += proc-self-map-files-001
+TEST_GEN_PROGS += proc-self-map-files-002
+TEST_GEN_PROGS += proc-self-syscall
+TEST_GEN_PROGS += proc-self-wchan
+TEST_GEN_PROGS += proc-uptime-001
+TEST_GEN_PROGS += proc-uptime-002
+TEST_GEN_PROGS += read
+
+include ../lib.mk
diff --git a/tools/testing/selftests/proc/config b/tools/testing/selftests/proc/config
new file mode 100644
index 000000000000..68fbd2b35884
--- /dev/null
+++ b/tools/testing/selftests/proc/config
@@ -0,0 +1 @@
+CONFIG_PROC_FS=y
diff --git a/tools/testing/selftests/proc/proc-loadavg-001.c b/tools/testing/selftests/proc/proc-loadavg-001.c
new file mode 100644
index 000000000000..56b0da660513
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-loadavg-001.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test that /proc/loadavg correctly reports last pid in pid namespace. */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+int main(void)
+{
+	pid_t pid;
+	int wstatus;
+
+	if (unshare(CLONE_NEWPID) == -1) {
+		if (errno == ENOSYS || errno == EPERM)
+			return 2;
+		return 1;
+	}
+
+	pid = fork();
+	if (pid == -1)
+		return 1;
+	if (pid == 0) {
+		char buf[128], *p;
+		int fd;
+		ssize_t rv;
+
+		fd = open("/proc/loadavg" , O_RDONLY);
+		if (fd == -1)
+			return 1;
+		rv = read(fd, buf, sizeof(buf));
+		if (rv < 3)
+			return 1;
+		p = buf + rv;
+
+		/* pid 1 */
+		if (!(p[-3] == ' ' && p[-2] == '1' && p[-1] == '\n'))
+			return 1;
+
+		pid = fork();
+		if (pid == -1)
+			return 1;
+		if (pid == 0)
+			return 0;
+		if (waitpid(pid, NULL, 0) == -1)
+			return 1;
+
+		lseek(fd, 0, SEEK_SET);
+		rv = read(fd, buf, sizeof(buf));
+		if (rv < 3)
+			return 1;
+		p = buf + rv;
+
+		/* pid 2 */
+		if (!(p[-3] == ' ' && p[-2] == '2' && p[-1] == '\n'))
+			return 1;
+
+		return 0;
+	}
+
+	if (waitpid(pid, &wstatus, 0) == -1)
+		return 1;
+	if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0)
+		return 0;
+	return 1;
+}
diff --git a/tools/testing/selftests/proc/proc-self-map-files-001.c b/tools/testing/selftests/proc/proc-self-map-files-001.c
new file mode 100644
index 000000000000..4abb83663195
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-map-files-001.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test readlink /proc/self/map_files/... */
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <stdlib.h>
+
+static void pass(const char *fmt, unsigned long a, unsigned long b)
+{
+	char name[64];
+	char buf[64];
+
+	snprintf(name, sizeof(name), fmt, a, b);
+	if (readlink(name, buf, sizeof(buf)) == -1)
+		exit(1);
+}
+
+static void fail(const char *fmt, unsigned long a, unsigned long b)
+{
+	char name[64];
+	char buf[64];
+
+	snprintf(name, sizeof(name), fmt, a, b);
+	if (readlink(name, buf, sizeof(buf)) == -1 && errno == ENOENT)
+		return;
+	exit(1);
+}
+
+int main(void)
+{
+	const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+	void *p;
+	int fd;
+	unsigned long a, b;
+
+	fd = open("/dev/zero", O_RDONLY);
+	if (fd == -1)
+		return 1;
+
+	p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE, fd, 0);
+	if (p == MAP_FAILED)
+		return 1;
+
+	a = (unsigned long)p;
+	b = (unsigned long)p + PAGE_SIZE;
+
+	pass("/proc/self/map_files/%lx-%lx", a, b);
+	fail("/proc/self/map_files/ %lx-%lx", a, b);
+	fail("/proc/self/map_files/%lx -%lx", a, b);
+	fail("/proc/self/map_files/%lx- %lx", a, b);
+	fail("/proc/self/map_files/%lx-%lx ", a, b);
+	fail("/proc/self/map_files/0%lx-%lx", a, b);
+	fail("/proc/self/map_files/%lx-0%lx", a, b);
+	if (sizeof(long) == 4) {
+		fail("/proc/self/map_files/100000000%lx-%lx", a, b);
+		fail("/proc/self/map_files/%lx-100000000%lx", a, b);
+	} else if (sizeof(long) == 8) {
+		fail("/proc/self/map_files/10000000000000000%lx-%lx", a, b);
+		fail("/proc/self/map_files/%lx-10000000000000000%lx", a, b);
+	} else
+		return 1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
new file mode 100644
index 000000000000..7aee67393a27
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-map-files-002.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test readlink /proc/self/map_files/... with address 0. */
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <stdlib.h>
+
+static void pass(const char *fmt, unsigned long a, unsigned long b)
+{
+	char name[64];
+	char buf[64];
+
+	snprintf(name, sizeof(name), fmt, a, b);
+	if (readlink(name, buf, sizeof(buf)) == -1)
+		exit(1);
+}
+
+static void fail(const char *fmt, unsigned long a, unsigned long b)
+{
+	char name[64];
+	char buf[64];
+
+	snprintf(name, sizeof(name), fmt, a, b);
+	if (readlink(name, buf, sizeof(buf)) == -1 && errno == ENOENT)
+		return;
+	exit(1);
+}
+
+int main(void)
+{
+	const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+	void *p;
+	int fd;
+	unsigned long a, b;
+
+	fd = open("/dev/zero", O_RDONLY);
+	if (fd == -1)
+		return 1;
+
+	p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+	if (p == MAP_FAILED) {
+		if (errno == EPERM)
+			return 2;
+		return 1;
+	}
+
+	a = (unsigned long)p;
+	b = (unsigned long)p + PAGE_SIZE;
+
+	pass("/proc/self/map_files/%lx-%lx", a, b);
+	fail("/proc/self/map_files/ %lx-%lx", a, b);
+	fail("/proc/self/map_files/%lx -%lx", a, b);
+	fail("/proc/self/map_files/%lx- %lx", a, b);
+	fail("/proc/self/map_files/%lx-%lx ", a, b);
+	fail("/proc/self/map_files/0%lx-%lx", a, b);
+	fail("/proc/self/map_files/%lx-0%lx", a, b);
+	if (sizeof(long) == 4) {
+		fail("/proc/self/map_files/100000000%lx-%lx", a, b);
+		fail("/proc/self/map_files/%lx-100000000%lx", a, b);
+	} else if (sizeof(long) == 8) {
+		fail("/proc/self/map_files/10000000000000000%lx-%lx", a, b);
+		fail("/proc/self/map_files/%lx-10000000000000000%lx", a, b);
+	} else
+		return 1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-syscall.c b/tools/testing/selftests/proc/proc-self-syscall.c
new file mode 100644
index 000000000000..05eb6f91f1e9
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-syscall.c
@@ -0,0 +1,45 @@
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdio.h>
+
+static inline ssize_t sys_read(int fd, void *buf, size_t len)
+{
+	return syscall(SYS_read, fd, buf, len);
+}
+
+int main(void)
+{
+	char buf1[64];
+	char buf2[64];
+	int fd;
+	ssize_t rv;
+
+	fd = open("/proc/self/syscall", O_RDONLY);
+	if (fd == -1) {
+		if (errno == ENOENT)
+			return 2;
+		return 1;
+	}
+
+	/* Do direct system call as libc can wrap anything. */
+	snprintf(buf1, sizeof(buf1), "%ld 0x%lx 0x%lx 0x%lx",
+		 (long)SYS_read, (long)fd, (long)buf2, (long)sizeof(buf2));
+
+	memset(buf2, 0, sizeof(buf2));
+	rv = sys_read(fd, buf2, sizeof(buf2));
+	if (rv < 0)
+		return 1;
+	if (rv < strlen(buf1))
+		return 1;
+	if (strncmp(buf1, buf2, strlen(buf1)) != 0)
+		return 1;
+
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-wchan.c b/tools/testing/selftests/proc/proc-self-wchan.c
new file mode 100644
index 000000000000..b8d8728a6869
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-wchan.c
@@ -0,0 +1,25 @@
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+
+int main(void)
+{
+	char buf[64];
+	int fd;
+
+	fd = open("/proc/self/wchan", O_RDONLY);
+	if (fd == -1) {
+		if (errno == ENOENT)
+			return 2;
+		return 1;
+	}
+
+	buf[0] = '\0';
+	if (read(fd, buf, sizeof(buf)) != 1)
+		return 1;
+	if (buf[0] != '0')
+		return 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime-001.c b/tools/testing/selftests/proc/proc-uptime-001.c
new file mode 100644
index 000000000000..702bb9b23edc
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime-001.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test that values in /proc/uptime increment monotonically.
+#undef NDEBUG
+#include <assert.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "proc-uptime.h"
+
+int main(void)
+{
+	uint64_t start, u0, u1, i0, i1;
+	int fd;
+
+	fd = open("/proc/uptime", O_RDONLY);
+	assert(fd >= 0);
+
+	proc_uptime(fd, &u0, &i0);
+	start = u0;
+	do {
+		proc_uptime(fd, &u1, &i1);
+		assert(u1 >= u0);
+		assert(i1 >= i0);
+		u0 = u1;
+		i0 = i1;
+	} while (u1 - start < 100);
+
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c
new file mode 100644
index 000000000000..5ad0023f417a
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime-002.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test that values in /proc/uptime increment monotonically
+// while shifting across CPUs.
+#define _GNU_SOURCE
+#undef NDEBUG
+#include <assert.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "proc-uptime.h"
+
+static inline int sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long *m)
+{
+	return syscall(SYS_sched_getaffinity, pid, len, m);
+}
+
+static inline int sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned long *m)
+{
+	return syscall(SYS_sched_setaffinity, pid, len, m);
+}
+
+int main(void)
+{
+	unsigned int len;
+	unsigned long *m;
+	unsigned int cpu;
+	uint64_t u0, u1, i0, i1;
+	int fd;
+
+	/* find out "nr_cpu_ids" */
+	m = NULL;
+	len = 0;
+	do {
+		len += sizeof(unsigned long);
+		free(m);
+		m = malloc(len);
+	} while (sys_sched_getaffinity(0, len, m) == -EINVAL);
+
+	fd = open("/proc/uptime", O_RDONLY);
+	assert(fd >= 0);
+
+	proc_uptime(fd, &u0, &i0);
+	for (cpu = 0; cpu < len * 8; cpu++) {
+		memset(m, 0, len);
+		m[cpu / (8 * sizeof(unsigned long))] |= 1UL << (cpu % (8 * sizeof(unsigned long)));
+
+		/* CPU might not exist, ignore error */
+		sys_sched_setaffinity(0, len, m);
+
+		proc_uptime(fd, &u1, &i1);
+		assert(u1 >= u0);
+		assert(i1 >= i0);
+		u0 = u1;
+		i0 = i1;
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime.h b/tools/testing/selftests/proc/proc-uptime.h
new file mode 100644
index 000000000000..34961e40993d
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static unsigned long long xstrtoull(const char *p, char **end)
+{
+	if (*p == '0') {
+		*end = (char *)p + 1;
+		return 0;
+	} else if ('1' <= *p && *p <= '9') {
+		unsigned long long val;
+
+		errno = 0;
+		val = strtoull(p, end, 10);
+		assert(errno == 0);
+		return val;
+	} else
+		assert(0);
+}
+
+static void proc_uptime(int fd, uint64_t *uptime, uint64_t *idle)
+{
+	uint64_t val1, val2;
+	char buf[64], *p;
+	ssize_t rv;
+
+	/* save "p < end" checks */
+	memset(buf, 0, sizeof(buf));
+	rv = pread(fd, buf, sizeof(buf), 0);
+	assert(0 <= rv && rv <= sizeof(buf));
+	buf[sizeof(buf) - 1] = '\0';
+
+	p = buf;
+
+	val1 = xstrtoull(p, &p);
+	assert(p[0] == '.');
+	assert('0' <= p[1] && p[1] <= '9');
+	assert('0' <= p[2] && p[2] <= '9');
+	assert(p[3] == ' ');
+
+	val2 = (p[1] - '0') * 10 + p[2] - '0';
+	*uptime = val1 * 100 + val2;
+
+	p += 4;
+
+	val1 = xstrtoull(p, &p);
+	assert(p[0] == '.');
+	assert('0' <= p[1] && p[1] <= '9');
+	assert('0' <= p[2] && p[2] <= '9');
+	assert(p[3] == '\n');
+
+	val2 = (p[1] - '0') * 10 + p[2] - '0';
+	*idle = val1 * 100 + val2;
+
+	assert(p + 4 == buf + rv);
+}
diff --git a/tools/testing/selftests/proc/read.c b/tools/testing/selftests/proc/read.c
new file mode 100644
index 000000000000..5238e4ba4976
--- /dev/null
+++ b/tools/testing/selftests/proc/read.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test
+// 1) read of every file in /proc
+// 2) readlink of every symlink in /proc
+// 3) recursively (1) + (2) for every directory in /proc
+// 4) write to /proc/*/clear_refs and /proc/*/task/*/clear_refs
+// 5) write to /proc/sysrq-trigger
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static inline bool streq(const char *s1, const char *s2)
+{
+	return strcmp(s1, s2) == 0;
+}
+
+static struct dirent *xreaddir(DIR *d)
+{
+	struct dirent *de;
+
+	errno = 0;
+	de = readdir(d);
+	if (!de && errno != 0) {
+		exit(1);
+	}
+	return de;
+}
+
+static void f_reg(DIR *d, const char *filename)
+{
+	char buf[4096];
+	int fd;
+	ssize_t rv;
+
+	/* read from /proc/kmsg can block */
+	fd = openat(dirfd(d), filename, O_RDONLY|O_NONBLOCK);
+	if (fd == -1)
+		return;
+	rv = read(fd, buf, sizeof(buf));
+	assert((0 <= rv && rv <= sizeof(buf)) || rv == -1);
+	close(fd);
+}
+
+static void f_reg_write(DIR *d, const char *filename, const char *buf, size_t len)
+{
+	int fd;
+	ssize_t rv;
+
+	fd = openat(dirfd(d), filename, O_WRONLY);
+	if (fd == -1)
+		return;
+	rv = write(fd, buf, len);
+	assert((0 <= rv && rv <= len) || rv == -1);
+	close(fd);
+}
+
+static void f_lnk(DIR *d, const char *filename)
+{
+	char buf[4096];
+	ssize_t rv;
+
+	rv = readlinkat(dirfd(d), filename, buf, sizeof(buf));
+	assert((0 <= rv && rv <= sizeof(buf)) || rv == -1);
+}
+
+static void f(DIR *d, unsigned int level)
+{
+	struct dirent *de;
+
+	de = xreaddir(d);
+	assert(de->d_type == DT_DIR);
+	assert(streq(de->d_name, "."));
+
+	de = xreaddir(d);
+	assert(de->d_type == DT_DIR);
+	assert(streq(de->d_name, ".."));
+
+	while ((de = xreaddir(d))) {
+		assert(!streq(de->d_name, "."));
+		assert(!streq(de->d_name, ".."));
+
+		switch (de->d_type) {
+			DIR *dd;
+			int fd;
+
+		case DT_REG:
+			if (level == 0 && streq(de->d_name, "sysrq-trigger")) {
+				f_reg_write(d, de->d_name, "h", 1);
+			} else if (level == 1 && streq(de->d_name, "clear_refs")) {
+				f_reg_write(d, de->d_name, "1", 1);
+			} else if (level == 3 && streq(de->d_name, "clear_refs")) {
+				f_reg_write(d, de->d_name, "1", 1);
+			} else {
+				f_reg(d, de->d_name);
+			}
+			break;
+		case DT_DIR:
+			fd = openat(dirfd(d), de->d_name, O_DIRECTORY|O_RDONLY);
+			if (fd == -1)
+				continue;
+			dd = fdopendir(fd);
+			if (!dd)
+				continue;
+			f(dd, level + 1);
+			closedir(dd);
+			break;
+		case DT_LNK:
+			f_lnk(d, de->d_name);
+			break;
+		default:
+			assert(0);
+		}
+	}
+}
+
+int main(void)
+{
+	DIR *d;
+
+	d = opendir("/proc");
+	if (!d)
+		return 2;
+	f(d, 0);
+	return 0;
+}