diff options
284 files changed, 10348 insertions, 3895 deletions
diff --git a/.clang-format b/.clang-format new file mode 100644 index 000000000000..faffc0d5af4e --- /dev/null +++ b/.clang-format @@ -0,0 +1,428 @@ +# 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 85bcc2696442..a1dfd2acd9c3 100644 --- a/.gitignore +++ b/.gitignore @@ -81,6 +81,7 @@ modules.builtin !.gitignore !.mailmap !.cocciconfig +!.clang-format # # Generated include files diff --git a/Documentation/cgroup-v1/memory.txt b/Documentation/cgroup-v1/memory.txt index a4af2e124e24..3682e99234c2 100644 --- a/Documentation/cgroup-v1/memory.txt +++ b/Documentation/cgroup-v1/memory.txt @@ -262,7 +262,7 @@ When oom event notifier is registered, event will be delivered. 2.6 Locking lock_page_cgroup()/unlock_page_cgroup() should not be called under - mapping->tree_lock. + the i_pages lock. Other lock order is following: PG_locked. diff --git a/Documentation/cpu-freq/core.txt b/Documentation/cpu-freq/core.txt index 978463a7c81e..073f128af5a7 100644 --- a/Documentation/cpu-freq/core.txt +++ b/Documentation/cpu-freq/core.txt @@ -97,12 +97,10 @@ flags - flags of the cpufreq driver ================================================================== For details about OPP, see Documentation/power/opp.txt -dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with - cpufreq_table_validate_and_show() which is provided with the list of - frequencies that are available for operation. This function provides - a ready to use conversion routine to translate the OPP layer's internal - information about the available frequencies into a format readily - providable to cpufreq. +dev_pm_opp_init_cpufreq_table - + This function provides a ready to use conversion routine to translate + the OPP layer's internal information about the available frequencies + into a format readily providable to cpufreq. WARNING: Do not use this function in interrupt context. @@ -112,7 +110,7 @@ dev_pm_opp_init_cpufreq_table - cpufreq framework typically is initialized with /* Do things */ r = dev_pm_opp_init_cpufreq_table(dev, &freq_table); if (!r) - cpufreq_table_validate_and_show(policy, freq_table); + policy->freq_table = freq_table; /* Do other things */ } diff --git a/Documentation/cpu-freq/cpu-drivers.txt b/Documentation/cpu-freq/cpu-drivers.txt index 61546ac578d6..6e353d00cdc6 100644 --- a/Documentation/cpu-freq/cpu-drivers.txt +++ b/Documentation/cpu-freq/cpu-drivers.txt @@ -259,10 +259,8 @@ CPUFREQ_ENTRY_INVALID. The entries don't need to be in sorted in any particular order, but if they are cpufreq core will do DVFS a bit quickly for them as search for best match is faster. -By calling cpufreq_table_validate_and_show(), the cpuinfo.min_freq and -cpuinfo.max_freq values are detected, and policy->min and policy->max -are set to the same values. This is helpful for the per-CPU -initialization stage. +The cpufreq table is verified automatically by the core if the policy contains a +valid pointer in its policy->freq_table field. cpufreq_frequency_table_verify() assures that at least one valid frequency is within policy->min and policy->max, and all other criteria diff --git a/Documentation/cpuidle/sysfs.txt b/Documentation/cpuidle/sysfs.txt index b6f44f490ed7..d1587f434e7b 100644 --- a/Documentation/cpuidle/sysfs.txt +++ b/Documentation/cpuidle/sysfs.txt @@ -40,6 +40,7 @@ total 0 -r--r--r-- 1 root root 4096 Feb 8 10:42 latency -r--r--r-- 1 root root 4096 Feb 8 10:42 name -r--r--r-- 1 root root 4096 Feb 8 10:42 power +-r--r--r-- 1 root root 4096 Feb 8 10:42 residency -r--r--r-- 1 root root 4096 Feb 8 10:42 time -r--r--r-- 1 root root 4096 Feb 8 10:42 usage @@ -50,6 +51,7 @@ total 0 -r--r--r-- 1 root root 4096 Feb 8 10:42 latency -r--r--r-- 1 root root 4096 Feb 8 10:42 name -r--r--r-- 1 root root 4096 Feb 8 10:42 power +-r--r--r-- 1 root root 4096 Feb 8 10:42 residency -r--r--r-- 1 root root 4096 Feb 8 10:42 time -r--r--r-- 1 root root 4096 Feb 8 10:42 usage @@ -60,6 +62,7 @@ total 0 -r--r--r-- 1 root root 4096 Feb 8 10:42 latency -r--r--r-- 1 root root 4096 Feb 8 10:42 name -r--r--r-- 1 root root 4096 Feb 8 10:42 power +-r--r--r-- 1 root root 4096 Feb 8 10:42 residency -r--r--r-- 1 root root 4096 Feb 8 10:42 time -r--r--r-- 1 root root 4096 Feb 8 10:42 usage @@ -70,6 +73,7 @@ total 0 -r--r--r-- 1 root root 4096 Feb 8 10:42 latency -r--r--r-- 1 root root 4096 Feb 8 10:42 name -r--r--r-- 1 root root 4096 Feb 8 10:42 power +-r--r--r-- 1 root root 4096 Feb 8 10:42 residency -r--r--r-- 1 root root 4096 Feb 8 10:42 time -r--r--r-- 1 root root 4096 Feb 8 10:42 usage -------------------------------------------------------------------------------- @@ -78,6 +82,8 @@ total 0 * desc : Small description about the idle state (string) * disable : Option to disable this idle state (bool) -> see note below * latency : Latency to exit out of this idle state (in microseconds) +* residency : Time after which a state becomes more effecient than any + shallower state (in microseconds) * name : Name of the idle state (string) * power : Power consumed while in this idle state (in milliwatts) * time : Total time spent in this idle state (in microseconds) diff --git a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt index 1fd5d69647ca..ffadb7c6f1f3 100644 --- a/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt +++ b/Documentation/devicetree/bindings/iommu/renesas,ipmmu-vmsa.txt @@ -11,6 +11,8 @@ Required Properties: the device is compatible with the R-Car Gen2 VMSA-compatible IPMMU. - "renesas,ipmmu-r8a73a4" for the R8A73A4 (R-Mobile APE6) IPMMU. + - "renesas,ipmmu-r8a7743" for the R8A7743 (RZ/G1M) IPMMU. + - "renesas,ipmmu-r8a7745" for the R8A7745 (RZ/G1E) IPMMU. - "renesas,ipmmu-r8a7790" for the R8A7790 (R-Car H2) IPMMU. - "renesas,ipmmu-r8a7791" for the R8A7791 (R-Car M2-W) IPMMU. - "renesas,ipmmu-r8a7793" for the R8A7793 (R-Car M2-N) IPMMU. @@ -19,7 +21,8 @@ Required Properties: - "renesas,ipmmu-r8a7796" for the R8A7796 (R-Car M3-W) IPMMU. - "renesas,ipmmu-r8a77970" for the R8A77970 (R-Car V3M) IPMMU. - "renesas,ipmmu-r8a77995" for the R8A77995 (R-Car D3) IPMMU. - - "renesas,ipmmu-vmsa" for generic R-Car Gen2 VMSA-compatible IPMMU. + - "renesas,ipmmu-vmsa" for generic R-Car Gen2 or RZ/G1 VMSA-compatible + IPMMU. - reg: Base address and size of the IPMMU registers. - interrupts: Specifiers for the MMU fault interrupts. For instances that diff --git a/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt b/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt index 2098f7732264..6ecefea1c6f9 100644 --- a/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt +++ b/Documentation/devicetree/bindings/iommu/rockchip,iommu.txt @@ -14,6 +14,11 @@ Required properties: "single-master" device, and needs no additional information to associate with its master device. See: Documentation/devicetree/bindings/iommu/iommu.txt +- clocks : A list of clocks required for the IOMMU to be accessible by + the host CPU. +- clock-names : Should contain the following: + "iface" - Main peripheral bus clock (PCLK/HCL) (required) + "aclk" - AXI bus clock (required) Optional properties: - rockchip,disable-mmu-reset : Don't use the mmu reset operation. @@ -27,5 +32,7 @@ Example: reg = <0xff940300 0x100>; interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "vopl_mmu"; + clocks = <&cru ACLK_VOP1>, <&cru HCLK_VOP1>; + clock-names = "aclk", "iface"; #iommu-cells = <0>; }; 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..6710c0707721 --- /dev/null +++ b/Documentation/process/clang-format.rst @@ -0,0 +1,184 @@ +.. _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/vm/hmm.txt b/Documentation/vm/hmm.txt index 4d3aac9f4a5d..2d1d6f69e91b 100644 --- a/Documentation/vm/hmm.txt +++ b/Documentation/vm/hmm.txt @@ -1,152 +1,160 @@ 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 path, with the cornerstone +of this being specialized struct page for such memory (see sections 5 to 7 of +this document). + +HMM also provides optional helpers for SVM (Share Virtual Memory), i.e., +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 mandatory to simplify the use of advanced hetero- +geneous 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 the purpose of HMM 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: - -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. - -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. - -Concretly this means that code that wants to leverage device like GPU 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. - -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. - -Duplicating each library API to accept as input or output memory allocted by +1) Problems of using a device specific memory allocator: + +Devices with a large amount of on board memory (several gigabytes) 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 happens because device can only access memory allocated +through 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. + +Concretely this means that code that wants to leverage devices like GPUs needs +to copy object between generically allocated memory (malloc, mmap private, mmap +share) and memory allocated through the device driver API (this still ends up +with an mmap but of the device file). + +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 libraries cannot 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 allocated 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 -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. +I/O buses cripple shared address spaces due to a 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. 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 -memory and can not perform atomic operations on it. Thus device memory can not -be consider like regular memory from kernel point of view. +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 cannot perform atomic operations on it. Thus device memory cannot +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. Sadly, 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 -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). +So for shared address space to make sense, not only must we allow devices to +access any 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 cannot 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 cannot 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 -device driver that want to mirror a process address space must start with the +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 wants to mirror a process address space must start with the registration of an hmm_mirror struct: int hmm_mirror_register(struct hmm_mirror *mirror, @@ -154,9 +162,9 @@ registration of an hmm_mirror struct: int hmm_mirror_register_locked(struct hmm_mirror *mirror, 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: +The locked variant is to be used when the driver is already holding mmap_sem +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 impedance 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 written 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 cannot 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 cannot 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 exercise 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 +back from device memory to regular memory cannot 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/Documentation/vm/page_migration b/Documentation/vm/page_migration index 0478ae2ad44a..496868072e24 100644 --- a/Documentation/vm/page_migration +++ b/Documentation/vm/page_migration @@ -90,7 +90,7 @@ Steps: 1. Lock the page to be migrated -2. Insure that writeback is complete. +2. Ensure that writeback is complete. 3. Lock the new page that we want to move to. It is locked so that accesses to this (not yet uptodate) page immediately lock while the move is in progress. @@ -100,8 +100,8 @@ Steps: mapcount is not zero then we do not migrate the page. All user space processes that attempt to access the page will now wait on the page lock. -5. The radix tree lock is taken. This will cause all processes trying - to access the page via the mapping to block on the radix tree spinlock. +5. The i_pages lock is taken. This will cause all processes trying + to access the page via the mapping to block on the spinlock. 6. The refcount of the page is examined and we back out if references remain otherwise we know that we are the only one referencing this page. @@ -114,12 +114,12 @@ Steps: 9. The radix tree is changed to point to the new page. -10. The reference count of the old page is dropped because the radix tree +10. The reference count of the old page is dropped because the address space reference is gone. A reference to the new page is established because - the new page is referenced to by the radix tree. + the new page is referenced by the address space. -11. The radix tree lock is dropped. With that lookups in the mapping - become possible again. Processes will move from spinning on the tree_lock +11. The i_pages lock is dropped. With that lookups in the mapping + become possible again. Processes will move from spinning on the lock to sleeping on the locked new page. 12. The page contents are copied to the new page. diff --git a/MAINTAINERS b/MAINTAINERS index 7bb2e9595f14..b60179d948bb 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1232,10 +1232,15 @@ F: Documentation/devicetree/bindings/i2c/i2c-aspeed.txt ARM/ASPEED MACHINE SUPPORT M: Joel Stanley <joel@jms.id.au> -S: Maintained +R: Andrew Jeffery <andrew@aj.id.au> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) +Q: https://patchwork.ozlabs.org/project/linux-aspeed/list/ +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/joel/aspeed.git F: arch/arm/mach-aspeed/ F: arch/arm/boot/dts/aspeed-* -F: drivers/*/*aspeed* +N: aspeed ARM/ATMEL AT91 Clock Support M: Boris Brezillon <boris.brezillon@bootlin.com> @@ -1743,7 +1748,7 @@ F: arch/arm/mach-orion5x/ts78xx-* ARM/OXNAS platform support M: Neil Armstrong <narmstrong@baylibre.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -L: linux-oxnas@lists.tuxfamily.org (moderated for non-subscribers) +L: linux-oxnas@groups.io (moderated for non-subscribers) S: Maintained F: arch/arm/mach-oxnas/ F: arch/arm/boot/dts/ox8*.dts* @@ -4392,7 +4397,7 @@ S: Maintained F: drivers/staging/fsl-dpaa2/ethsw DPT_I2O SCSI RAID DRIVER -M: Adaptec OEM Raid Solutions <aacraid@adaptec.com> +M: Adaptec OEM Raid Solutions <aacraid@microsemi.com> L: linux-scsi@vger.kernel.org W: http://www.adaptec.com/ S: Maintained @@ -6410,6 +6415,7 @@ 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> @@ -7344,7 +7350,7 @@ F: include/linux/ipmi* F: include/uapi/linux/ipmi* IPS SCSI RAID DRIVER -M: Adaptec OEM Raid Solutions <aacraid@adaptec.com> +M: Adaptec OEM Raid Solutions <aacraid@microsemi.com> L: linux-scsi@vger.kernel.org W: http://www.adaptec.com/ S: Maintained @@ -11762,7 +11768,7 @@ F: drivers/char/random.c RAPIDIO SUBSYSTEM M: Matt Porter <mporter@kernel.crashing.org> -M: Alexandre Bounine <alexandre.bounine@idt.com> +M: Alexandre Bounine <alex.bou9@gmail.com> S: Maintained F: drivers/rapidio/ diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 2dbdf59258d9..f9d4e6b6d4bd 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -32,6 +32,7 @@ #define MAP_NONBLOCK 0x40000 /* do not block on IO */ #define MAP_STACK 0x80000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x100000 /* create a huge page mapping */ +#define MAP_FIXED_NOREPLACE 0x200000/* MAP_FIXED which doesn't unmap underlying mapping */ #define MS_ASYNC 1 /* sync memory asynchronously */ #define MS_SYNC 2 /* synchronous memory sync */ diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index 74504b154256..869080bedb89 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -318,10 +318,8 @@ static inline void flush_anon_page(struct vm_area_struct *vma, #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE extern void flush_kernel_dcache_page(struct page *); -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) +#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) #define flush_icache_user_range(vma,page,addr,len) \ flush_dcache_page(page) diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h index 496667703693..ed8fd0d19a3e 100644 --- a/arch/arm/include/asm/memory.h +++ b/arch/arm/include/asm/memory.h @@ -22,12 +22,6 @@ #include <mach/memory.h> #endif -/* - * Allow for constants defined here to be used from assembly code - * by prepending the UL suffix only with actual C code compilation. - */ -#define UL(x) _AC(x, UL) - /* PAGE_OFFSET - the virtual address of the start of the kernel image */ #define PAGE_OFFSET UL(CONFIG_PAGE_OFFSET) diff --git a/arch/arm/mach-npcm/npcm7xx.c b/arch/arm/mach-npcm/npcm7xx.c index 5f7cd88103ef..c5f77d854c4f 100644 --- a/arch/arm/mach-npcm/npcm7xx.c +++ b/arch/arm/mach-npcm/npcm7xx.c @@ -17,4 +17,6 @@ static const char *const npcm7xx_dt_match[] = { DT_MACHINE_START(NPCM7XX_DT, "NPCM7XX Chip family") .atag_offset = 0x100, .dt_compat = npcm7xx_dt_match, + .l2c_aux_val = 0x0, + .l2c_aux_mask = ~0x0, MACHINE_END 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/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/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 7dfcec4700fe..0094c6653b06 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -140,10 +140,8 @@ static inline void __flush_icache_all(void) dsb(ish); } -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) do { } while (0) +#define flush_dcache_mmap_unlock(mapping) do { } while (0) /* * We don't appear to need to do anything here. In fact, if we did, we'd diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 50fa96a49792..49d99214f43c 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -29,12 +29,6 @@ #include <asm/sizes.h> /* - * Allow for constants defined here to be used from assembly code - * by prepending the UL suffix only with actual C code compilation. - */ -#define UL(x) _AC(x, UL) - -/* * Size of the PCI I/O space. This must remain a power of two so that * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses. */ 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/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h index 114b93488193..5de871eb4a59 100644 --- a/arch/microblaze/include/asm/pci.h +++ b/arch/microblaze/include/asm/pci.h @@ -47,9 +47,10 @@ extern int pci_proc_domain(struct pci_bus *bus); struct vm_area_struct; -/* Tell drivers/pci/proc.c that we have pci_mmap_page_range() */ -#define HAVE_PCI_MMAP 1 -#define arch_can_pci_mmap_io() 1 +/* Tell PCI code what kind of PCI resource mappings we support */ +#define HAVE_PCI_MMAP 1 +#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1 +#define arch_can_pci_mmap_io() 1 extern int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t count); diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index e53b8532353c..db8b1fa83452 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -33,6 +33,8 @@ extern int mem_init_done; #define PAGE_KERNEL __pgprot(0) /* these mean nothing to non MMU */ #define pgprot_noncached(x) (x) +#define pgprot_writecombine pgprot_noncached +#define pgprot_device pgprot_noncached #define __swp_type(x) (0) #define __swp_offset(x) (0) diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index ae79e8638d50..161f9758c631 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -151,72 +151,22 @@ void pcibios_set_master(struct pci_dev *dev) } /* - * Platform support for /proc/bus/pci/X/Y mmap()s, - * modelled on the sparc64 implementation by Dave Miller. - * -- paulus. + * Platform support for /proc/bus/pci/X/Y mmap()s. */ -/* - * Adjust vm_pgoff of VMA such that it is the physical page offset - * corresponding to the 32-bit pci bus offset for DEV requested by the user. - * - * Basically, the user finds the base address for his device which he wishes - * to mmap. They read the 32-bit value from the config space base register, - * add whatever PAGE_SIZE multiple offset they wish, and feed this into the - * offset parameter of mmap on /proc/bus/pci/XXX for that device. - * - * Returns negative error code on failure, zero on success. - */ -static struct resource *__pci_mmap_make_offset(struct pci_dev *dev, - resource_size_t *offset, - enum pci_mmap_state mmap_state) +int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma) { - struct pci_controller *hose = pci_bus_to_host(dev->bus); - unsigned long io_offset = 0; - int i, res_bit; + struct pci_controller *hose = pci_bus_to_host(pdev->bus); + resource_size_t ioaddr = pci_resource_start(pdev, bar); if (!hose) - return NULL; /* should never happen */ - - /* If memory, add on the PCI bridge address offset */ - if (mmap_state == pci_mmap_mem) { -#if 0 /* See comment in pci_resource_to_user() for why this is disabled */ - *offset += hose->pci_mem_offset; -#endif - res_bit = IORESOURCE_MEM; - } else { - io_offset = (unsigned long)hose->io_base_virt - _IO_BASE; - *offset += io_offset; - res_bit = IORESOURCE_IO; - } - - /* - * Check that the offset requested corresponds to one of the - * resources of the device. - */ - for (i = 0; i <= PCI_ROM_RESOURCE; i++) { - struct resource *rp = &dev->resource[i]; - int flags = rp->flags; + return -EINVAL; /* should never happen */ - /* treat ROM as memory (should be already) */ - if (i == PCI_ROM_RESOURCE) - flags |= IORESOURCE_MEM; - - /* Active and same type? */ - if ((flags & res_bit) == 0) - continue; - - /* In the range of this resource? */ - if (*offset < (rp->start & PAGE_MASK) || *offset > rp->end) - continue; - - /* found it! construct the final physical address */ - if (mmap_state == pci_mmap_io) - *offset += hose->io_base_phys - io_offset; - return rp; - } + /* Convert to an offset within this PCI controller */ + ioaddr -= (unsigned long)hose->io_base_virt - _IO_BASE; - return NULL; + vma->vm_pgoff += (ioaddr + hose->io_base_phys) >> PAGE_SHIFT; + return 0; } /* @@ -268,37 +218,6 @@ pgprot_t pci_phys_mem_access_prot(struct file *file, return prot; } -/* - * Perform the actual remap of the pages for a PCI device mapping, as - * appropriate for this architecture. The region in the process to map - * is described by vm_start and vm_end members of VMA, the base physical - * address is found in vm_pgoff. - * The pci device structure is provided so that architectures may make mapping - * decisions on a per-device or per-bus basis. - * - * Returns a negative error code on failure, zero on success. - */ -int pci_mmap_page_range(struct pci_dev *dev, int bar, struct vm_area_struct *vma, - enum pci_mmap_state mmap_state, int write_combine) -{ - resource_size_t offset = - ((resource_size_t)vma->vm_pgoff) << PAGE_SHIFT; - struct resource *rp; - int ret; - - rp = __pci_mmap_make_offset(dev, &offset, mmap_state); - if (rp == NULL) - return -EINVAL; - - vma->vm_pgoff = offset >> PAGE_SHIFT; - vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); - - ret = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, - vma->vm_end - vma->vm_start, vma->vm_page_prot); - - return ret; -} - /* This provides legacy IO read access on a bus */ int pci_legacy_read(struct pci_bus *bus, loff_t port, u32 *val, size_t size) { diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index 606e02ca4b6c..3035ca499cd8 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -50,6 +50,7 @@ #define MAP_NONBLOCK 0x20000 /* do not block on IO */ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ +#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ /* * Flags for msync 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/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 7b9b20a381cb..1240f148ec0f 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -34,8 +34,8 @@ void flush_anon_page(struct vm_area_struct *vma, void flush_kernel_dcache_page(struct page *page); void flush_icache_range(unsigned long start, unsigned long end); void flush_icache_page(struct vm_area_struct *vma, struct page *page); -#define flush_dcache_mmap_lock(mapping) spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&(mapping)->i_pages) +#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages) #else #include <asm-generic/cacheflush.h> diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 55e383c173f7..18eb9f69f806 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -46,9 +46,7 @@ extern void copy_from_user_page(struct vm_area_struct *vma, struct page *page, extern void flush_dcache_range(unsigned long start, unsigned long end); extern void invalidate_dcache_range(unsigned long start, unsigned long end); -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) +#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) #endif /* _ASM_NIOS2_CACHEFLUSH_H */ diff --git a/arch/nios2/kernel/time.c b/arch/nios2/kernel/time.c index 20e86209ef2e..ab88b6dd4679 100644 --- a/arch/nios2/kernel/time.c +++ b/arch/nios2/kernel/time.c @@ -336,9 +336,9 @@ static int __init nios2_time_init(struct device_node *timer) return ret; } -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { - ts->tv_sec = mktime(2007, 1, 1, 0, 0, 0); + ts->tv_sec = mktime64(2007, 1, 1, 0, 0, 0); ts->tv_nsec = 0; } diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index bd5ce31936f5..0c83644bfa5c 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -55,10 +55,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *page); -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) +#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) #define flush_icache_page(vma,page) do { \ flush_kernel_dcache_page(page); \ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index a056a642bb31..870fbf8c7088 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -26,6 +26,7 @@ #define MAP_NONBLOCK 0x20000 /* do not block on IO */ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ +#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ #define MS_SYNC 1 /* synchronous memory sync */ #define MS_ASYNC 2 /* sync memory asynchronously */ 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/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 9a8a084e4aba..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; 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/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/um/Kconfig.net b/arch/um/Kconfig.net index e871af24d9cd..c390f3deb0dc 100644 --- a/arch/um/Kconfig.net +++ b/arch/um/Kconfig.net @@ -109,6 +109,17 @@ config UML_NET_DAEMON more than one without conflict. If you don't need UML networking, say N. +config UML_NET_VECTOR + bool "Vector I/O high performance network devices" + depends on UML_NET + help + This User-Mode Linux network driver uses multi-message send + and receive functions. The host running the UML guest must have + a linux kernel version above 3.0 and a libc version > 2.13. + This driver provides tap, raw, gre and l2tpv3 network transports + with up to 4 times higher network throughput than the UML network + drivers. + config UML_NET_VDE bool "VDE transport" depends on UML_NET diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile index e7582e1d248c..16b3cebddafb 100644 --- a/arch/um/drivers/Makefile +++ b/arch/um/drivers/Makefile @@ -9,6 +9,7 @@ slip-objs := slip_kern.o slip_user.o slirp-objs := slirp_kern.o slirp_user.o daemon-objs := daemon_kern.o daemon_user.o +vector-objs := vector_kern.o vector_user.o vector_transports.o umcast-objs := umcast_kern.o umcast_user.o net-objs := net_kern.o net_user.o mconsole-objs := mconsole_kern.o mconsole_user.o @@ -43,6 +44,7 @@ obj-$(CONFIG_STDERR_CONSOLE) += stderr_console.o obj-$(CONFIG_UML_NET_SLIP) += slip.o slip_common.o obj-$(CONFIG_UML_NET_SLIRP) += slirp.o slip_common.o obj-$(CONFIG_UML_NET_DAEMON) += daemon.o +obj-$(CONFIG_UML_NET_VECTOR) += vector.o obj-$(CONFIG_UML_NET_VDE) += vde.o obj-$(CONFIG_UML_NET_MCAST) += umcast.o obj-$(CONFIG_UML_NET_PCAP) += pcap.o @@ -61,7 +63,7 @@ obj-$(CONFIG_BLK_DEV_COW_COMMON) += cow_user.o obj-$(CONFIG_UML_RANDOM) += random.o # pcap_user.o must be added explicitly. -USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o +USER_OBJS := fd.o null.o pty.o tty.o xterm.o slip_common.o pcap_user.o vde_user.o vector_user.o CFLAGS_null.o = -DDEV_NULL=$(DEV_NULL_PATH) include arch/um/scripts/Makefile.rules diff --git a/arch/um/drivers/chan_kern.c b/arch/um/drivers/chan_kern.c index acbe6c67afba..05588f9466c7 100644 --- a/arch/um/drivers/chan_kern.c +++ b/arch/um/drivers/chan_kern.c @@ -171,56 +171,19 @@ int enable_chan(struct line *line) return err; } -/* Items are added in IRQ context, when free_irq can't be called, and - * removed in process context, when it can. - * This handles interrupt sources which disappear, and which need to - * be permanently disabled. This is discovered in IRQ context, but - * the freeing of the IRQ must be done later. - */ -static DEFINE_SPINLOCK(irqs_to_free_lock); -static LIST_HEAD(irqs_to_free); - -void free_irqs(void) -{ - struct chan *chan; - LIST_HEAD(list); - struct list_head *ele; - unsigned long flags; - - spin_lock_irqsave(&irqs_to_free_lock, flags); - list_splice_init(&irqs_to_free, &list); - spin_unlock_irqrestore(&irqs_to_free_lock, flags); - - list_for_each(ele, &list) { - chan = list_entry(ele, struct chan, free_list); - - if (chan->input && chan->enabled) - um_free_irq(chan->line->driver->read_irq, chan); - if (chan->output && chan->enabled) - um_free_irq(chan->line->driver->write_irq, chan); - chan->enabled = 0; - } -} - static void close_one_chan(struct chan *chan, int delay_free_irq) { - unsigned long flags; - if (!chan->opened) return; - if (delay_free_irq) { - spin_lock_irqsave(&irqs_to_free_lock, flags); - list_add(&chan->free_list, &irqs_to_free); - spin_unlock_irqrestore(&irqs_to_free_lock, flags); - } - else { - if (chan->input && chan->enabled) - um_free_irq(chan->line->driver->read_irq, chan); - if (chan->output && chan->enabled) - um_free_irq(chan->line->driver->write_irq, chan); - chan->enabled = 0; - } + /* we can safely call free now - it will be marked + * as free and freed once the IRQ stopped processing + */ + if (chan->input && chan->enabled) + um_free_irq(chan->line->driver->read_irq, chan); + if (chan->output && chan->enabled) + um_free_irq(chan->line->driver->write_irq, chan); + chan->enabled = 0; if (chan->ops->close != NULL) (*chan->ops->close)(chan->fd, chan->data); diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 366e57f5e8d6..8d80b27502e6 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -284,7 +284,7 @@ int line_setup_irq(int fd, int input, int output, struct line *line, void *data) if (err) return err; if (output) - err = um_request_irq(driver->write_irq, fd, IRQ_WRITE, + err = um_request_irq(driver->write_irq, fd, IRQ_NONE, line_write_interrupt, IRQF_SHARED, driver->write_irq_name, data); return err; diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index b305f8247909..3ef1b48e064a 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -288,7 +288,7 @@ static void uml_net_user_timer_expire(struct timer_list *t) #endif } -static void setup_etheraddr(struct net_device *dev, char *str) +void uml_net_setup_etheraddr(struct net_device *dev, char *str) { unsigned char *addr = dev->dev_addr; char *end; @@ -412,7 +412,7 @@ static void eth_configure(int n, void *init, char *mac, */ snprintf(dev->name, sizeof(dev->name), "eth%d", n); - setup_etheraddr(dev, mac); + uml_net_setup_etheraddr(dev, mac); printk(KERN_INFO "Netdevice %d (%pM) : ", n, dev->dev_addr); diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c index 37c51a6be690..778a0e52d5a5 100644 --- a/arch/um/drivers/random.c +++ b/arch/um/drivers/random.c @@ -13,6 +13,7 @@ #include <linux/miscdevice.h> #include <linux/delay.h> #include <linux/uaccess.h> +#include <init.h> #include <irq_kern.h> #include <os.h> @@ -154,7 +155,14 @@ err_out_cleanup_hw: /* * rng_cleanup - shutdown RNG module */ -static void __exit rng_cleanup (void) + +static void cleanup(void) +{ + free_irq_by_fd(random_fd); + os_close_file(random_fd); +} + +static void __exit rng_cleanup(void) { os_close_file(random_fd); misc_deregister (&rng_miscdev); @@ -162,6 +170,7 @@ static void __exit rng_cleanup (void) module_init (rng_init); module_exit (rng_cleanup); +__uml_exitcall(cleanup); MODULE_DESCRIPTION("UML Host Random Number Generator (RNG) driver"); MODULE_LICENSE("GPL"); diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index b55fe9bf5d3e..d4e8c497ae86 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1587,11 +1587,11 @@ int io_thread(void *arg) do { res = os_write_file(kernel_fd, ((char *) io_req_buffer) + written, n); - if (res > 0) { + if (res >= 0) { written += res; } else { if (res != -EAGAIN) { - printk("io_thread - read failed, fd = %d, " + printk("io_thread - write failed, fd = %d, " "err = %d\n", kernel_fd, -n); } } diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c new file mode 100644 index 000000000000..02168fe25105 --- /dev/null +++ b/arch/um/drivers/vector_kern.c @@ -0,0 +1,1633 @@ +/* + * Copyright (C) 2017 - Cambridge Greys Limited + * Copyright (C) 2011 - 2014 Cisco Systems Inc + * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Copyright (C) 2001 Lennert Buytenhek (buytenh@gnu.org) and + * James Leu (jleu@mindspring.net). + * Copyright (C) 2001 by various other people who didn't put their name here. + * Licensed under the GPL. + */ + +#include <linux/version.h> +#include <linux/bootmem.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/inetdevice.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/netdevice.h> +#include <linux/platform_device.h> +#include <linux/rtnetlink.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <init.h> +#include <irq_kern.h> +#include <irq_user.h> +#include <net_kern.h> +#include <os.h> +#include "mconsole_kern.h" +#include "vector_user.h" +#include "vector_kern.h" + +/* + * Adapted from network devices with the following major changes: + * All transports are static - simplifies the code significantly + * Multiple FDs/IRQs per device + * Vector IO optionally used for read/write, falling back to legacy + * based on configuration and/or availability + * Configuration is no longer positional - L2TPv3 and GRE require up to + * 10 parameters, passing this as positional is not fit for purpose. + * Only socket transports are supported + */ + + +#define DRIVER_NAME "uml-vector" +#define DRIVER_VERSION "01" +struct vector_cmd_line_arg { + struct list_head list; + int unit; + char *arguments; +}; + +struct vector_device { + struct list_head list; + struct net_device *dev; + struct platform_device pdev; + int unit; + int opened; +}; + +static LIST_HEAD(vec_cmd_line); + +static DEFINE_SPINLOCK(vector_devices_lock); +static LIST_HEAD(vector_devices); + +static int driver_registered; + +static void vector_eth_configure(int n, struct arglist *def); + +/* Argument accessors to set variables (and/or set default values) + * mtu, buffer sizing, default headroom, etc + */ + +#define DEFAULT_HEADROOM 2 +#define SAFETY_MARGIN 32 +#define DEFAULT_VECTOR_SIZE 64 +#define TX_SMALL_PACKET 128 +#define MAX_IOV_SIZE (MAX_SKB_FRAGS + 1) + +static const struct { + const char string[ETH_GSTRING_LEN]; +} ethtool_stats_keys[] = { + { "rx_queue_max" }, + { "rx_queue_running_average" }, + { "tx_queue_max" }, + { "tx_queue_running_average" }, + { "rx_encaps_errors" }, + { "tx_timeout_count" }, + { "tx_restart_queue" }, + { "tx_kicks" }, + { "tx_flow_control_xon" }, + { "tx_flow_control_xoff" }, + { "rx_csum_offload_good" }, + { "rx_csum_offload_errors"}, + { "sg_ok"}, + { "sg_linearized"}, +}; + +#define VECTOR_NUM_STATS ARRAY_SIZE(ethtool_stats_keys) + +static void vector_reset_stats(struct vector_private *vp) +{ + vp->estats.rx_queue_max = 0; + vp->estats.rx_queue_running_average = 0; + vp->estats.tx_queue_max = 0; + vp->estats.tx_queue_running_average = 0; + vp->estats.rx_encaps_errors = 0; + vp->estats.tx_timeout_count = 0; + vp->estats.tx_restart_queue = 0; + vp->estats.tx_kicks = 0; + vp->estats.tx_flow_control_xon = 0; + vp->estats.tx_flow_control_xoff = 0; + vp->estats.sg_ok = 0; + vp->estats.sg_linearized = 0; +} + +static int get_mtu(struct arglist *def) +{ + char *mtu = uml_vector_fetch_arg(def, "mtu"); + long result; + + if (mtu != NULL) { + if (kstrtoul(mtu, 10, &result) == 0) + return result; + } + return ETH_MAX_PACKET; +} + +static int get_depth(struct arglist *def) +{ + char *mtu = uml_vector_fetch_arg(def, "depth"); + long result; + + if (mtu != NULL) { + if (kstrtoul(mtu, 10, &result) == 0) + return result; + } + return DEFAULT_VECTOR_SIZE; +} + +static int get_headroom(struct arglist *def) +{ + char *mtu = uml_vector_fetch_arg(def, "headroom"); + long result; + + if (mtu != NULL) { + if (kstrtoul(mtu, 10, &result) == 0) + return result; + } + return DEFAULT_HEADROOM; +} + +static int get_req_size(struct arglist *def) +{ + char *gro = uml_vector_fetch_arg(def, "gro"); + long result; + + if (gro != NULL) { + if (kstrtoul(gro, 10, &result) == 0) { + if (result > 0) + return 65536; + } + } + return get_mtu(def) + ETH_HEADER_OTHER + + get_headroom(def) + SAFETY_MARGIN; +} + + +static int get_transport_options(struct arglist *def) +{ + char *transport = uml_vector_fetch_arg(def, "transport"); + char *vector = uml_vector_fetch_arg(def, "vec"); + + int vec_rx = VECTOR_RX; + int vec_tx = VECTOR_TX; + long parsed; + + if (vector != NULL) { + if (kstrtoul(vector, 10, &parsed) == 0) { + if (parsed == 0) { + vec_rx = 0; + vec_tx = 0; + } + } + } + + + if (strncmp(transport, TRANS_TAP, TRANS_TAP_LEN) == 0) + return (vec_rx | VECTOR_BPF); + if (strncmp(transport, TRANS_RAW, TRANS_RAW_LEN) == 0) + return (vec_rx | vec_tx); + return (vec_rx | vec_tx); +} + + +/* A mini-buffer for packet drop read + * All of our supported transports are datagram oriented and we always + * read using recvmsg or recvmmsg. If we pass a buffer which is smaller + * than the packet size it still counts as full packet read and will + * clean the incoming stream to keep sigio/epoll happy + */ + +#define DROP_BUFFER_SIZE 32 + +static char *drop_buffer; + +/* Array backed queues optimized for bulk enqueue/dequeue and + * 1:N (small values of N) or 1:1 enqueuer/dequeuer ratios. + * For more details and full design rationale see + * http://foswiki.cambridgegreys.com/Main/EatYourTailAndEnjoyIt + */ + + +/* + * Advance the mmsg queue head by n = advance. Resets the queue to + * maximum enqueue/dequeue-at-once capacity if possible. Called by + * dequeuers. Caller must hold the head_lock! + */ + +static int vector_advancehead(struct vector_queue *qi, int advance) +{ + int queue_depth; + + qi->head = + (qi->head + advance) + % qi->max_depth; + + + spin_lock(&qi->tail_lock); + qi->queue_depth -= advance; + + /* we are at 0, use this to + * reset head and tail so we can use max size vectors + */ + + if (qi->queue_depth == 0) { + qi->head = 0; + qi->tail = 0; + } + queue_depth = qi->queue_depth; + spin_unlock(&qi->tail_lock); + return queue_depth; +} + +/* Advance the queue tail by n = advance. + * This is called by enqueuers which should hold the + * head lock already + */ + +static int vector_advancetail(struct vector_queue *qi, int advance) +{ + int queue_depth; + + qi->tail = + (qi->tail + advance) + % qi->max_depth; + spin_lock(&qi->head_lock); + qi->queue_depth += advance; + queue_depth = qi->queue_depth; + spin_unlock(&qi->head_lock); + return queue_depth; +} + +static int prep_msg(struct vector_private *vp, + struct sk_buff *skb, + struct iovec *iov) +{ + int iov_index = 0; + int nr_frags, frag; + skb_frag_t *skb_frag; + + nr_frags = skb_shinfo(skb)->nr_frags; + if (nr_frags > MAX_IOV_SIZE) { + if (skb_linearize(skb) != 0) + goto drop; + } + if (vp->header_size > 0) { + iov[iov_index].iov_len = vp->header_size; + vp->form_header(iov[iov_index].iov_base, skb, vp); + iov_index++; + } + iov[iov_index].iov_base = skb->data; + if (nr_frags > 0) { + iov[iov_index].iov_len = skb->len - skb->data_len; + vp->estats.sg_ok++; + } else + iov[iov_index].iov_len = skb->len; + iov_index++; + for (frag = 0; frag < nr_frags; frag++) { + skb_frag = &skb_shinfo(skb)->frags[frag]; + iov[iov_index].iov_base = skb_frag_address_safe(skb_frag); + iov[iov_index].iov_len = skb_frag_size(skb_frag); + iov_index++; + } + return iov_index; +drop: + return -1; +} +/* + * Generic vector enqueue with support for forming headers using transport + * specific callback. Allows GRE, L2TPv3, RAW and other transports + * to use a common enqueue procedure in vector mode + */ + +static int vector_enqueue(struct vector_queue *qi, struct sk_buff *skb) +{ + struct vector_private *vp = netdev_priv(qi->dev); + int queue_depth; + int packet_len; + struct mmsghdr *mmsg_vector = qi->mmsg_vector; + int iov_count; + + spin_lock(&qi->tail_lock); + spin_lock(&qi->head_lock); + queue_depth = qi->queue_depth; + spin_unlock(&qi->head_lock); + + if (skb) + packet_len = skb->len; + + if (queue_depth < qi->max_depth) { + + *(qi->skbuff_vector + qi->tail) = skb; + mmsg_vector += qi->tail; + iov_count = prep_msg( + vp, + skb, + mmsg_vector->msg_hdr.msg_iov + ); + if (iov_count < 1) + goto drop; + mmsg_vector->msg_hdr.msg_iovlen = iov_count; + mmsg_vector->msg_hdr.msg_name = vp->fds->remote_addr; + mmsg_vector->msg_hdr.msg_namelen = vp->fds->remote_addr_size; + queue_depth = vector_advancetail(qi, 1); + } else + goto drop; + spin_unlock(&qi->tail_lock); + return queue_depth; +drop: + qi->dev->stats.tx_dropped++; + if (skb != NULL) { + packet_len = skb->len; + dev_consume_skb_any(skb); + netdev_completed_queue(qi->dev, 1, packet_len); + } + spin_unlock(&qi->tail_lock); + return queue_depth; +} + +static int consume_vector_skbs(struct vector_queue *qi, int count) +{ + struct sk_buff *skb; + int skb_index; + int bytes_compl = 0; + + for (skb_index = qi->head; skb_index < qi->head + count; skb_index++) { + skb = *(qi->skbuff_vector + skb_index); + /* mark as empty to ensure correct destruction if + * needed + */ + bytes_compl += skb->len; + *(qi->skbuff_vector + skb_index) = NULL; + dev_consume_skb_any(skb); + } + qi->dev->stats.tx_bytes += bytes_compl; + qi->dev->stats.tx_packets += count; + netdev_completed_queue(qi->dev, count, bytes_compl); + return vector_advancehead(qi, count); +} + +/* + * Generic vector deque via sendmmsg with support for forming headers + * using transport specific callback. Allows GRE, L2TPv3, RAW and + * other transports to use a common dequeue procedure in vector mode + */ + + +static int vector_send(struct vector_queue *qi) +{ + struct vector_private *vp = netdev_priv(qi->dev); + struct mmsghdr *send_from; + int result = 0, send_len, queue_depth = qi->max_depth; + + if (spin_trylock(&qi->head_lock)) { + if (spin_trylock(&qi->tail_lock)) { + /* update queue_depth to current value */ + queue_depth = qi->queue_depth; + spin_unlock(&qi->tail_lock); + while (queue_depth > 0) { + /* Calculate the start of the vector */ + send_len = queue_depth; + send_from = qi->mmsg_vector; + send_from += qi->head; + /* Adjust vector size if wraparound */ + if (send_len + qi->head > qi->max_depth) + send_len = qi->max_depth - qi->head; + /* Try to TX as many packets as possible */ + if (send_len > 0) { + result = uml_vector_sendmmsg( + vp->fds->tx_fd, + send_from, + send_len, + 0 + ); + vp->in_write_poll = + (result != send_len); + } + /* For some of the sendmmsg error scenarios + * we may end being unsure in the TX success + * for all packets. It is safer to declare + * them all TX-ed and blame the network. + */ + if (result < 0) { + if (net_ratelimit()) + netdev_err(vp->dev, "sendmmsg err=%i\n", + result); + result = send_len; + } + if (result > 0) { + queue_depth = + consume_vector_skbs(qi, result); + /* This is equivalent to an TX IRQ. + * Restart the upper layers to feed us + * more packets. + */ + if (result > vp->estats.tx_queue_max) + vp->estats.tx_queue_max = result; + vp->estats.tx_queue_running_average = + (vp->estats.tx_queue_running_average + result) >> 1; + } + netif_trans_update(qi->dev); + netif_wake_queue(qi->dev); + /* if TX is busy, break out of the send loop, + * poll write IRQ will reschedule xmit for us + */ + if (result != send_len) { + vp->estats.tx_restart_queue++; + break; + } + } + } + spin_unlock(&qi->head_lock); + } else { + tasklet_schedule(&vp->tx_poll); + } + return queue_depth; +} + +/* Queue destructor. Deliberately stateless so we can use + * it in queue cleanup if initialization fails. + */ + +static void destroy_queue(struct vector_queue *qi) +{ + int i; + struct iovec *iov; + struct vector_private *vp = netdev_priv(qi->dev); + struct mmsghdr *mmsg_vector; + + if (qi == NULL) + return; + /* deallocate any skbuffs - we rely on any unused to be + * set to NULL. + */ + if (qi->skbuff_vector != NULL) { + for (i = 0; i < qi->max_depth; i++) { + if (*(qi->skbuff_vector + i) != NULL) + dev_kfree_skb_any(*(qi->skbuff_vector + i)); + } + kfree(qi->skbuff_vector); + } + /* deallocate matching IOV structures including header buffs */ + if (qi->mmsg_vector != NULL) { + mmsg_vector = qi->mmsg_vector; + for (i = 0; i < qi->max_depth; i++) { + iov = mmsg_vector->msg_hdr.msg_iov; + if (iov != NULL) { + if ((vp->header_size > 0) && + (iov->iov_base != NULL)) + kfree(iov->iov_base); + kfree(iov); + } + mmsg_vector++; + } + kfree(qi->mmsg_vector); + } + kfree(qi); +} + +/* + * Queue constructor. Create a queue with a given side. + */ +static struct vector_queue *create_queue( + struct vector_private *vp, + int max_size, + int header_size, + int num_extra_frags) +{ + struct vector_queue *result; + int i; + struct iovec *iov; + struct mmsghdr *mmsg_vector; + + result = kmalloc(sizeof(struct vector_queue), GFP_KERNEL); + if (result == NULL) + goto out_fail; + result->max_depth = max_size; + result->dev = vp->dev; + result->mmsg_vector = kmalloc( + (sizeof(struct mmsghdr) * max_size), GFP_KERNEL); + result->skbuff_vector = kmalloc( + (sizeof(void *) * max_size), GFP_KERNEL); + if (result->mmsg_vector == NULL || result->skbuff_vector == NULL) + goto out_fail; + + mmsg_vector = result->mmsg_vector; + for (i = 0; i < max_size; i++) { + /* Clear all pointers - we use non-NULL as marking on + * what to free on destruction + */ + *(result->skbuff_vector + i) = NULL; + mmsg_vector->msg_hdr.msg_iov = NULL; + mmsg_vector++; + } + mmsg_vector = result->mmsg_vector; + result->max_iov_frags = num_extra_frags; + for (i = 0; i < max_size; i++) { + if (vp->header_size > 0) + iov = kmalloc( + sizeof(struct iovec) * (3 + num_extra_frags), + GFP_KERNEL + ); + else + iov = kmalloc( + sizeof(struct iovec) * (2 + num_extra_frags), + GFP_KERNEL + ); + if (iov == NULL) + goto out_fail; + mmsg_vector->msg_hdr.msg_iov = iov; + mmsg_vector->msg_hdr.msg_iovlen = 1; + mmsg_vector->msg_hdr.msg_control = NULL; + mmsg_vector->msg_hdr.msg_controllen = 0; + mmsg_vector->msg_hdr.msg_flags = MSG_DONTWAIT; + mmsg_vector->msg_hdr.msg_name = NULL; + mmsg_vector->msg_hdr.msg_namelen = 0; + if (vp->header_size > 0) { + iov->iov_base = kmalloc(header_size, GFP_KERNEL); + if (iov->iov_base == NULL) + goto out_fail; + iov->iov_len = header_size; + mmsg_vector->msg_hdr.msg_iovlen = 2; + iov++; + } + iov->iov_base = NULL; + iov->iov_len = 0; + mmsg_vector++; + } + spin_lock_init(&result->head_lock); + spin_lock_init(&result->tail_lock); + result->queue_depth = 0; + result->head = 0; + result->tail = 0; + return result; +out_fail: + destroy_queue(result); + return NULL; +} + +/* + * We do not use the RX queue as a proper wraparound queue for now + * This is not necessary because the consumption via netif_rx() + * happens in-line. While we can try using the return code of + * netif_rx() for flow control there are no drivers doing this today. + * For this RX specific use we ignore the tail/head locks and + * just read into a prepared queue filled with skbuffs. + */ + +static struct sk_buff *prep_skb( + struct vector_private *vp, + struct user_msghdr *msg) +{ + int linear = vp->max_packet + vp->headroom + SAFETY_MARGIN; + struct sk_buff *result; + int iov_index = 0, len; + struct iovec *iov = msg->msg_iov; + int err, nr_frags, frag; + skb_frag_t *skb_frag; + + if (vp->req_size <= linear) + len = linear; + else + len = vp->req_size; + result = alloc_skb_with_frags( + linear, + len - vp->max_packet, + 3, + &err, + GFP_ATOMIC + ); + if (vp->header_size > 0) + iov_index++; + if (result == NULL) { + iov[iov_index].iov_base = NULL; + iov[iov_index].iov_len = 0; + goto done; + } + skb_reserve(result, vp->headroom); + result->dev = vp->dev; + skb_put(result, vp->max_packet); + result->data_len = len - vp->max_packet; + result->len += len - vp->max_packet; + skb_reset_mac_header(result); + result->ip_summed = CHECKSUM_NONE; + iov[iov_index].iov_base = result->data; + iov[iov_index].iov_len = vp->max_packet; + iov_index++; + + nr_frags = skb_shinfo(result)->nr_frags; + for (frag = 0; frag < nr_frags; frag++) { + skb_frag = &skb_shinfo(result)->frags[frag]; + iov[iov_index].iov_base = skb_frag_address_safe(skb_frag); + if (iov[iov_index].iov_base != NULL) + iov[iov_index].iov_len = skb_frag_size(skb_frag); + else + iov[iov_index].iov_len = 0; + iov_index++; + } +done: + msg->msg_iovlen = iov_index; + return result; +} + + +/* Prepare queue for recvmmsg one-shot rx - fill with fresh sk_buffs*/ + +static void prep_queue_for_rx(struct vector_queue *qi) +{ + struct vector_private *vp = netdev_priv(qi->dev); + struct mmsghdr *mmsg_vector = qi->mmsg_vector; + void **skbuff_vector = qi->skbuff_vector; + int i; + + if (qi->queue_depth == 0) + return; + for (i = 0; i < qi->queue_depth; i++) { + /* it is OK if allocation fails - recvmmsg with NULL data in + * iov argument still performs an RX, just drops the packet + * This allows us stop faffing around with a "drop buffer" + */ + + *skbuff_vector = prep_skb(vp, &mmsg_vector->msg_hdr); + skbuff_vector++; + mmsg_vector++; + } + qi->queue_depth = 0; +} + +static struct vector_device *find_device(int n) +{ + struct vector_device *device; + struct list_head *ele; + + spin_lock(&vector_devices_lock); + list_for_each(ele, &vector_devices) { + device = list_entry(ele, struct vector_device, list); + if (device->unit == n) + goto out; + } + device = NULL; + out: + spin_unlock(&vector_devices_lock); + return device; +} + +static int vector_parse(char *str, int *index_out, char **str_out, + char **error_out) +{ + int n, len, err; + char *start = str; + + len = strlen(str); + + while ((*str != ':') && (strlen(str) > 1)) + str++; + if (*str != ':') { + *error_out = "Expected ':' after device number"; + return -EINVAL; + } + *str = '\0'; + + err = kstrtouint(start, 0, &n); + if (err < 0) { + *error_out = "Bad device number"; + return err; + } + + str++; + if (find_device(n)) { + *error_out = "Device already configured"; + return -EINVAL; + } + + *index_out = n; + *str_out = str; + return 0; +} + +static int vector_config(char *str, char **error_out) +{ + int err, n; + char *params; + struct arglist *parsed; + + err = vector_parse(str, &n, ¶ms, error_out); + if (err != 0) + return err; + + /* This string is broken up and the pieces used by the underlying + * driver. We should copy it to make sure things do not go wrong + * later. + */ + + params = kstrdup(params, GFP_KERNEL); + if (params == NULL) { + *error_out = "vector_config failed to strdup string"; + return -ENOMEM; + } + + parsed = uml_parse_vector_ifspec(params); + + if (parsed == NULL) { + *error_out = "vector_config failed to parse parameters"; + return -EINVAL; + } + + vector_eth_configure(n, parsed); + return 0; +} + +static int vector_id(char **str, int *start_out, int *end_out) +{ + char *end; + int n; + + n = simple_strtoul(*str, &end, 0); + if ((*end != '\0') || (end == *str)) + return -1; + + *start_out = n; + *end_out = n; + *str = end; + return n; +} + +static int vector_remove(int n, char **error_out) +{ + struct vector_device *vec_d; + struct net_device *dev; + struct vector_private *vp; + + vec_d = find_device(n); + if (vec_d == NULL) + return -ENODEV; + dev = vec_d->dev; + vp = netdev_priv(dev); + if (vp->fds != NULL) + return -EBUSY; + unregister_netdev(dev); + platform_device_unregister(&vec_d->pdev); + return 0; +} + +/* + * There is no shared per-transport initialization code, so + * we will just initialize each interface one by one and + * add them to a list + */ + +static struct platform_driver uml_net_driver = { + .driver = { + .name = DRIVER_NAME, + }, +}; + + +static void vector_device_release(struct device *dev) +{ + struct vector_device *device = dev_get_drvdata(dev); + struct net_device *netdev = device->dev; + + list_del(&device->list); + kfree(device); + free_netdev(netdev); +} + +/* Bog standard recv using recvmsg - not used normally unless the user + * explicitly specifies not to use recvmmsg vector RX. + */ + +static int vector_legacy_rx(struct vector_private *vp) +{ + int pkt_len; + struct user_msghdr hdr; + struct iovec iov[2 + MAX_IOV_SIZE]; /* header + data use case only */ + int iovpos = 0; + struct sk_buff *skb; + int header_check; + + hdr.msg_name = NULL; + hdr.msg_namelen = 0; + hdr.msg_iov = (struct iovec *) &iov; + hdr.msg_control = NULL; + hdr.msg_controllen = 0; + hdr.msg_flags = 0; + + if (vp->header_size > 0) { + iov[0].iov_base = vp->header_rxbuffer; + iov[0].iov_len = vp->header_size; + } + + skb = prep_skb(vp, &hdr); + + if (skb == NULL) { + /* Read a packet into drop_buffer and don't do + * anything with it. + */ + iov[iovpos].iov_base = drop_buffer; + iov[iovpos].iov_len = DROP_BUFFER_SIZE; + hdr.msg_iovlen = 1; + vp->dev->stats.rx_dropped++; + } + + pkt_len = uml_vector_recvmsg(vp->fds->rx_fd, &hdr, 0); + + if (skb != NULL) { + if (pkt_len > vp->header_size) { + if (vp->header_size > 0) { + header_check = vp->verify_header( + vp->header_rxbuffer, skb, vp); + if (header_check < 0) { + dev_kfree_skb_irq(skb); + vp->dev->stats.rx_dropped++; + vp->estats.rx_encaps_errors++; + return 0; + } + if (header_check > 0) { + vp->estats.rx_csum_offload_good++; + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + } + pskb_trim(skb, pkt_len - vp->rx_header_size); + skb->protocol = eth_type_trans(skb, skb->dev); + vp->dev->stats.rx_bytes += skb->len; + vp->dev->stats.rx_packets++; + netif_rx(skb); + } else { + dev_kfree_skb_irq(skb); + } + } + return pkt_len; +} + +/* + * Packet at a time TX which falls back to vector TX if the + * underlying transport is busy. + */ + + + +static int writev_tx(struct vector_private *vp, struct sk_buff *skb) +{ + struct iovec iov[3 + MAX_IOV_SIZE]; + int iov_count, pkt_len = 0; + + iov[0].iov_base = vp->header_txbuffer; + iov_count = prep_msg(vp, skb, (struct iovec *) &iov); + + if (iov_count < 1) + goto drop; + pkt_len = uml_vector_writev( + vp->fds->tx_fd, + (struct iovec *) &iov, + iov_count + ); + + netif_trans_update(vp->dev); + netif_wake_queue(vp->dev); + + if (pkt_len > 0) { + vp->dev->stats.tx_bytes += skb->len; + vp->dev->stats.tx_packets++; + } else { + vp->dev->stats.tx_dropped++; + } + consume_skb(skb); + return pkt_len; +drop: + vp->dev->stats.tx_dropped++; + consume_skb(skb); + return pkt_len; +} + +/* + * Receive as many messages as we can in one call using the special + * mmsg vector matched to an skb vector which we prepared earlier. + */ + +static int vector_mmsg_rx(struct vector_private *vp) +{ + int packet_count, i; + struct vector_queue *qi = vp->rx_queue; + struct sk_buff *skb; + struct mmsghdr *mmsg_vector = qi->mmsg_vector; + void **skbuff_vector = qi->skbuff_vector; + int header_check; + + /* Refresh the vector and make sure it is with new skbs and the + * iovs are updated to point to them. + */ + + prep_queue_for_rx(qi); + + /* Fire the Lazy Gun - get as many packets as we can in one go. */ + + packet_count = uml_vector_recvmmsg( + vp->fds->rx_fd, qi->mmsg_vector, qi->max_depth, 0); + + if (packet_count <= 0) + return packet_count; + + /* We treat packet processing as enqueue, buffer refresh as dequeue + * The queue_depth tells us how many buffers have been used and how + * many do we need to prep the next time prep_queue_for_rx() is called. + */ + + qi->queue_depth = packet_count; + + for (i = 0; i < packet_count; i++) { + skb = (*skbuff_vector); + if (mmsg_vector->msg_len > vp->header_size) { + if (vp->header_size > 0) { + header_check = vp->verify_header( + mmsg_vector->msg_hdr.msg_iov->iov_base, + skb, + vp + ); + if (header_check < 0) { + /* Overlay header failed to verify - discard. + * We can actually keep this skb and reuse it, + * but that will make the prep logic too + * complex. + */ + dev_kfree_skb_irq(skb); + vp->estats.rx_encaps_errors++; + continue; + } + if (header_check > 0) { + vp->estats.rx_csum_offload_good++; + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + } + pskb_trim(skb, + mmsg_vector->msg_len - vp->rx_header_size); + skb->protocol = eth_type_trans(skb, skb->dev); + /* + * We do not need to lock on updating stats here + * The interrupt loop is non-reentrant. + */ + vp->dev->stats.rx_bytes += skb->len; + vp->dev->stats.rx_packets++; + netif_rx(skb); + } else { + /* Overlay header too short to do anything - discard. + * We can actually keep this skb and reuse it, + * but that will make the prep logic too complex. + */ + if (skb != NULL) + dev_kfree_skb_irq(skb); + } + (*skbuff_vector) = NULL; + /* Move to the next buffer element */ + mmsg_vector++; + skbuff_vector++; + } + if (packet_count > 0) { + if (vp->estats.rx_queue_max < packet_count) + vp->estats.rx_queue_max = packet_count; + vp->estats.rx_queue_running_average = + (vp->estats.rx_queue_running_average + packet_count) >> 1; + } + return packet_count; +} + +static void vector_rx(struct vector_private *vp) +{ + int err; + + if ((vp->options & VECTOR_RX) > 0) + while ((err = vector_mmsg_rx(vp)) > 0) + ; + else + while ((err = vector_legacy_rx(vp)) > 0) + ; + if ((err != 0) && net_ratelimit()) + netdev_err(vp->dev, "vector_rx: error(%d)\n", err); +} + +static int vector_net_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct vector_private *vp = netdev_priv(dev); + int queue_depth = 0; + + if ((vp->options & VECTOR_TX) == 0) { + writev_tx(vp, skb); + return NETDEV_TX_OK; + } + + /* We do BQL only in the vector path, no point doing it in + * packet at a time mode as there is no device queue + */ + + netdev_sent_queue(vp->dev, skb->len); + queue_depth = vector_enqueue(vp->tx_queue, skb); + + /* if the device queue is full, stop the upper layers and + * flush it. + */ + + if (queue_depth >= vp->tx_queue->max_depth - 1) { + vp->estats.tx_kicks++; + netif_stop_queue(dev); + vector_send(vp->tx_queue); + return NETDEV_TX_OK; + } + if (skb->xmit_more) { + mod_timer(&vp->tl, vp->coalesce); + return NETDEV_TX_OK; + } + if (skb->len < TX_SMALL_PACKET) { + vp->estats.tx_kicks++; + vector_send(vp->tx_queue); + } else + tasklet_schedule(&vp->tx_poll); + return NETDEV_TX_OK; +} + +static irqreturn_t vector_rx_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct vector_private *vp = netdev_priv(dev); + + if (!netif_running(dev)) + return IRQ_NONE; + vector_rx(vp); + return IRQ_HANDLED; + +} + +static irqreturn_t vector_tx_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct vector_private *vp = netdev_priv(dev); + + if (!netif_running(dev)) + return IRQ_NONE; + /* We need to pay attention to it only if we got + * -EAGAIN or -ENOBUFFS from sendmmsg. Otherwise + * we ignore it. In the future, it may be worth + * it to improve the IRQ controller a bit to make + * tweaking the IRQ mask less costly + */ + + if (vp->in_write_poll) + tasklet_schedule(&vp->tx_poll); + return IRQ_HANDLED; + +} + +static int irq_rr; + +static int vector_net_close(struct net_device *dev) +{ + struct vector_private *vp = netdev_priv(dev); + unsigned long flags; + + netif_stop_queue(dev); + del_timer(&vp->tl); + + if (vp->fds == NULL) + return 0; + + /* Disable and free all IRQS */ + if (vp->rx_irq > 0) { + um_free_irq(vp->rx_irq, dev); + vp->rx_irq = 0; + } + if (vp->tx_irq > 0) { + um_free_irq(vp->tx_irq, dev); + vp->tx_irq = 0; + } + tasklet_kill(&vp->tx_poll); + if (vp->fds->rx_fd > 0) { + os_close_file(vp->fds->rx_fd); + vp->fds->rx_fd = -1; + } + if (vp->fds->tx_fd > 0) { + os_close_file(vp->fds->tx_fd); + vp->fds->tx_fd = -1; + } + if (vp->bpf != NULL) + kfree(vp->bpf); + if (vp->fds->remote_addr != NULL) + kfree(vp->fds->remote_addr); + if (vp->transport_data != NULL) + kfree(vp->transport_data); + if (vp->header_rxbuffer != NULL) + kfree(vp->header_rxbuffer); + if (vp->header_txbuffer != NULL) + kfree(vp->header_txbuffer); + if (vp->rx_queue != NULL) + destroy_queue(vp->rx_queue); + if (vp->tx_queue != NULL) + destroy_queue(vp->tx_queue); + kfree(vp->fds); + vp->fds = NULL; + spin_lock_irqsave(&vp->lock, flags); + vp->opened = false; + spin_unlock_irqrestore(&vp->lock, flags); + return 0; +} + +/* TX tasklet */ + +static void vector_tx_poll(unsigned long data) +{ + struct vector_private *vp = (struct vector_private *)data; + + vp->estats.tx_kicks++; + vector_send(vp->tx_queue); +} +static void vector_reset_tx(struct work_struct *work) +{ + struct vector_private *vp = + container_of(work, struct vector_private, reset_tx); + netdev_reset_queue(vp->dev); + netif_start_queue(vp->dev); + netif_wake_queue(vp->dev); +} +static int vector_net_open(struct net_device *dev) +{ + struct vector_private *vp = netdev_priv(dev); + unsigned long flags; + int err = -EINVAL; + struct vector_device *vdevice; + + spin_lock_irqsave(&vp->lock, flags); + if (vp->opened) { + spin_unlock_irqrestore(&vp->lock, flags); + return -ENXIO; + } + vp->opened = true; + spin_unlock_irqrestore(&vp->lock, flags); + + vp->fds = uml_vector_user_open(vp->unit, vp->parsed); + + if (vp->fds == NULL) + goto out_close; + + if (build_transport_data(vp) < 0) + goto out_close; + + if ((vp->options & VECTOR_RX) > 0) { + vp->rx_queue = create_queue( + vp, + get_depth(vp->parsed), + vp->rx_header_size, + MAX_IOV_SIZE + ); + vp->rx_queue->queue_depth = get_depth(vp->parsed); + } else { + vp->header_rxbuffer = kmalloc( + vp->rx_header_size, + GFP_KERNEL + ); + if (vp->header_rxbuffer == NULL) + goto out_close; + } + if ((vp->options & VECTOR_TX) > 0) { + vp->tx_queue = create_queue( + vp, + get_depth(vp->parsed), + vp->header_size, + MAX_IOV_SIZE + ); + } else { + vp->header_txbuffer = kmalloc(vp->header_size, GFP_KERNEL); + if (vp->header_txbuffer == NULL) + goto out_close; + } + + /* READ IRQ */ + err = um_request_irq( + irq_rr + VECTOR_BASE_IRQ, vp->fds->rx_fd, + IRQ_READ, vector_rx_interrupt, + IRQF_SHARED, dev->name, dev); + if (err != 0) { + netdev_err(dev, "vector_open: failed to get rx irq(%d)\n", err); + err = -ENETUNREACH; + goto out_close; + } + vp->rx_irq = irq_rr + VECTOR_BASE_IRQ; + dev->irq = irq_rr + VECTOR_BASE_IRQ; + irq_rr = (irq_rr + 1) % VECTOR_IRQ_SPACE; + + /* WRITE IRQ - we need it only if we have vector TX */ + if ((vp->options & VECTOR_TX) > 0) { + err = um_request_irq( + irq_rr + VECTOR_BASE_IRQ, vp->fds->tx_fd, + IRQ_WRITE, vector_tx_interrupt, + IRQF_SHARED, dev->name, dev); + if (err != 0) { + netdev_err(dev, + "vector_open: failed to get tx irq(%d)\n", err); + err = -ENETUNREACH; + goto out_close; + } + vp->tx_irq = irq_rr + VECTOR_BASE_IRQ; + irq_rr = (irq_rr + 1) % VECTOR_IRQ_SPACE; + } + + if ((vp->options & VECTOR_QDISC_BYPASS) != 0) { + if (!uml_raw_enable_qdisc_bypass(vp->fds->rx_fd)) + vp->options = vp->options | VECTOR_BPF; + } + + if ((vp->options & VECTOR_BPF) != 0) + vp->bpf = uml_vector_default_bpf(vp->fds->rx_fd, dev->dev_addr); + + netif_start_queue(dev); + + /* clear buffer - it can happen that the host side of the interface + * is full when we get here. In this case, new data is never queued, + * SIGIOs never arrive, and the net never works. + */ + + vector_rx(vp); + + vector_reset_stats(vp); + vdevice = find_device(vp->unit); + vdevice->opened = 1; + + if ((vp->options & VECTOR_TX) != 0) + add_timer(&vp->tl); + return 0; +out_close: + vector_net_close(dev); + return err; +} + + +static void vector_net_set_multicast_list(struct net_device *dev) +{ + /* TODO: - we can do some BPF games here */ + return; +} + +static void vector_net_tx_timeout(struct net_device *dev) +{ + struct vector_private *vp = netdev_priv(dev); + + vp->estats.tx_timeout_count++; + netif_trans_update(dev); + schedule_work(&vp->reset_tx); +} + +static netdev_features_t vector_fix_features(struct net_device *dev, + netdev_features_t features) +{ + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); + return features; +} + +static int vector_set_features(struct net_device *dev, + netdev_features_t features) +{ + struct vector_private *vp = netdev_priv(dev); + /* Adjust buffer sizes for GSO/GRO. Unfortunately, there is + * no way to negotiate it on raw sockets, so we can change + * only our side. + */ + if (features & NETIF_F_GRO) + /* All new frame buffers will be GRO-sized */ + vp->req_size = 65536; + else + /* All new frame buffers will be normal sized */ + vp->req_size = vp->max_packet + vp->headroom + SAFETY_MARGIN; + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void vector_net_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + vector_rx_interrupt(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + +static void vector_net_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver)); + strlcpy(info->version, DRIVER_VERSION, sizeof(info->version)); +} + +static void vector_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct vector_private *vp = netdev_priv(netdev); + + ring->rx_max_pending = vp->rx_queue->max_depth; + ring->tx_max_pending = vp->tx_queue->max_depth; + ring->rx_pending = vp->rx_queue->max_depth; + ring->tx_pending = vp->tx_queue->max_depth; +} + +static void vector_get_strings(struct net_device *dev, u32 stringset, u8 *buf) +{ + switch (stringset) { + case ETH_SS_TEST: + *buf = '\0'; + break; + case ETH_SS_STATS: + memcpy(buf, ðtool_stats_keys, sizeof(ethtool_stats_keys)); + break; + default: + WARN_ON(1); + break; + } +} + +static int vector_get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_TEST: + return 0; + case ETH_SS_STATS: + return VECTOR_NUM_STATS; + default: + return -EOPNOTSUPP; + } +} + +static void vector_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *estats, + u64 *tmp_stats) +{ + struct vector_private *vp = netdev_priv(dev); + + memcpy(tmp_stats, &vp->estats, sizeof(struct vector_estats)); +} + +static int vector_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct vector_private *vp = netdev_priv(netdev); + + ec->tx_coalesce_usecs = (vp->coalesce * 1000000) / HZ; + return 0; +} + +static int vector_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct vector_private *vp = netdev_priv(netdev); + + vp->coalesce = (ec->tx_coalesce_usecs * HZ) / 1000000; + if (vp->coalesce == 0) + vp->coalesce = 1; + return 0; +} + +static const struct ethtool_ops vector_net_ethtool_ops = { + .get_drvinfo = vector_net_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ts_info = ethtool_op_get_ts_info, + .get_ringparam = vector_get_ringparam, + .get_strings = vector_get_strings, + .get_sset_count = vector_get_sset_count, + .get_ethtool_stats = vector_get_ethtool_stats, + .get_coalesce = vector_get_coalesce, + .set_coalesce = vector_set_coalesce, +}; + + +static const struct net_device_ops vector_netdev_ops = { + .ndo_open = vector_net_open, + .ndo_stop = vector_net_close, + .ndo_start_xmit = vector_net_start_xmit, + .ndo_set_rx_mode = vector_net_set_multicast_list, + .ndo_tx_timeout = vector_net_tx_timeout, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_fix_features = vector_fix_features, + .ndo_set_features = vector_set_features, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = vector_net_poll_controller, +#endif +}; + + +static void vector_timer_expire(struct timer_list *t) +{ + struct vector_private *vp = from_timer(vp, t, tl); + + vp->estats.tx_kicks++; + vector_send(vp->tx_queue); +} + +static void vector_eth_configure( + int n, + struct arglist *def + ) +{ + struct vector_device *device; + struct net_device *dev; + struct vector_private *vp; + int err; + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (device == NULL) { + printk(KERN_ERR "eth_configure failed to allocate struct " + "vector_device\n"); + return; + } + dev = alloc_etherdev(sizeof(struct vector_private)); + if (dev == NULL) { + printk(KERN_ERR "eth_configure: failed to allocate struct " + "net_device for vec%d\n", n); + goto out_free_device; + } + + dev->mtu = get_mtu(def); + + INIT_LIST_HEAD(&device->list); + device->unit = n; + + /* If this name ends up conflicting with an existing registered + * netdevice, that is OK, register_netdev{,ice}() will notice this + * and fail. + */ + snprintf(dev->name, sizeof(dev->name), "vec%d", n); + uml_net_setup_etheraddr(dev, uml_vector_fetch_arg(def, "mac")); + vp = netdev_priv(dev); + + /* sysfs register */ + if (!driver_registered) { + platform_driver_register(¨_net_driver); + driver_registered = 1; + } + device->pdev.id = n; + device->pdev.name = DRIVER_NAME; + device->pdev.dev.release = vector_device_release; + dev_set_drvdata(&device->pdev.dev, device); + if (platform_device_register(&device->pdev)) + goto out_free_netdev; + SET_NETDEV_DEV(dev, &device->pdev.dev); + + device->dev = dev; + + *vp = ((struct vector_private) + { + .list = LIST_HEAD_INIT(vp->list), + .dev = dev, + .unit = n, + .options = get_transport_options(def), + .rx_irq = 0, + .tx_irq = 0, + .parsed = def, + .max_packet = get_mtu(def) + ETH_HEADER_OTHER, + /* TODO - we need to calculate headroom so that ip header + * is 16 byte aligned all the time + */ + .headroom = get_headroom(def), + .form_header = NULL, + .verify_header = NULL, + .header_rxbuffer = NULL, + .header_txbuffer = NULL, + .header_size = 0, + .rx_header_size = 0, + .rexmit_scheduled = false, + .opened = false, + .transport_data = NULL, + .in_write_poll = false, + .coalesce = 2, + .req_size = get_req_size(def) + }); + + dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST); + tasklet_init(&vp->tx_poll, vector_tx_poll, (unsigned long)vp); + INIT_WORK(&vp->reset_tx, vector_reset_tx); + + timer_setup(&vp->tl, vector_timer_expire, 0); + spin_lock_init(&vp->lock); + + /* FIXME */ + dev->netdev_ops = &vector_netdev_ops; + dev->ethtool_ops = &vector_net_ethtool_ops; + dev->watchdog_timeo = (HZ >> 1); + /* primary IRQ - fixme */ + dev->irq = 0; /* we will adjust this once opened */ + + rtnl_lock(); + err = register_netdevice(dev); + rtnl_unlock(); + if (err) + goto out_undo_user_init; + + spin_lock(&vector_devices_lock); + list_add(&device->list, &vector_devices); + spin_unlock(&vector_devices_lock); + + return; + +out_undo_user_init: + return; +out_free_netdev: + free_netdev(dev); +out_free_device: + kfree(device); +} + + + + +/* + * Invoked late in the init + */ + +static int __init vector_init(void) +{ + struct list_head *ele; + struct vector_cmd_line_arg *def; + struct arglist *parsed; + + list_for_each(ele, &vec_cmd_line) { + def = list_entry(ele, struct vector_cmd_line_arg, list); + parsed = uml_parse_vector_ifspec(def->arguments); + if (parsed != NULL) + vector_eth_configure(def->unit, parsed); + } + return 0; +} + + +/* Invoked at initial argument parsing, only stores + * arguments until a proper vector_init is called + * later + */ + +static int __init vector_setup(char *str) +{ + char *error; + int n, err; + struct vector_cmd_line_arg *new; + + err = vector_parse(str, &n, &str, &error); + if (err) { + printk(KERN_ERR "vector_setup - Couldn't parse '%s' : %s\n", + str, error); + return 1; + } + new = alloc_bootmem(sizeof(*new)); + INIT_LIST_HEAD(&new->list); + new->unit = n; + new->arguments = str; + list_add_tail(&new->list, &vec_cmd_line); + return 1; +} + +__setup("vec", vector_setup); +__uml_help(vector_setup, +"vec[0-9]+:<option>=<value>,<option>=<value>\n" +" Configure a vector io network device.\n\n" +); + +late_initcall(vector_init); + +static struct mc_device vector_mc = { + .list = LIST_HEAD_INIT(vector_mc.list), + .name = "vec", + .config = vector_config, + .get_config = NULL, + .id = vector_id, + .remove = vector_remove, +}; + +#ifdef CONFIG_INET +static int vector_inetaddr_event( + struct notifier_block *this, + unsigned long event, + void *ptr) +{ + return NOTIFY_DONE; +} + +static struct notifier_block vector_inetaddr_notifier = { + .notifier_call = vector_inetaddr_event, +}; + +static void inet_register(void) +{ + register_inetaddr_notifier(&vector_inetaddr_notifier); +} +#else +static inline void inet_register(void) +{ +} +#endif + +static int vector_net_init(void) +{ + mconsole_register_dev(&vector_mc); + inet_register(); + return 0; +} + +__initcall(vector_net_init); + + + diff --git a/arch/um/drivers/vector_kern.h b/arch/um/drivers/vector_kern.h new file mode 100644 index 000000000000..0b0a767b9076 --- /dev/null +++ b/arch/um/drivers/vector_kern.h @@ -0,0 +1,130 @@ +/* + * Copyright (C) 2002 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Licensed under the GPL + */ + +#ifndef __UM_VECTOR_KERN_H +#define __UM_VECTOR_KERN_H + +#include <linux/netdevice.h> +#include <linux/platform_device.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/list.h> +#include <linux/ctype.h> +#include <linux/workqueue.h> +#include <linux/interrupt.h> +#include "vector_user.h" + +/* Queue structure specially adapted for multiple enqueue/dequeue + * in a mmsgrecv/mmsgsend context + */ + +/* Dequeue method */ + +#define QUEUE_SENDMSG 0 +#define QUEUE_SENDMMSG 1 + +#define VECTOR_RX 1 +#define VECTOR_TX (1 << 1) +#define VECTOR_BPF (1 << 2) +#define VECTOR_QDISC_BYPASS (1 << 3) + +#define ETH_MAX_PACKET 1500 +#define ETH_HEADER_OTHER 32 /* just in case someone decides to go mad on QnQ */ + +struct vector_queue { + struct mmsghdr *mmsg_vector; + void **skbuff_vector; + /* backlink to device which owns us */ + struct net_device *dev; + spinlock_t head_lock; + spinlock_t tail_lock; + int queue_depth, head, tail, max_depth, max_iov_frags; + short options; +}; + +struct vector_estats { + uint64_t rx_queue_max; + uint64_t rx_queue_running_average; + uint64_t tx_queue_max; + uint64_t tx_queue_running_average; + uint64_t rx_encaps_errors; + uint64_t tx_timeout_count; + uint64_t tx_restart_queue; + uint64_t tx_kicks; + uint64_t tx_flow_control_xon; + uint64_t tx_flow_control_xoff; + uint64_t rx_csum_offload_good; + uint64_t rx_csum_offload_errors; + uint64_t sg_ok; + uint64_t sg_linearized; +}; + +#define VERIFY_HEADER_NOK -1 +#define VERIFY_HEADER_OK 0 +#define VERIFY_CSUM_OK 1 + +struct vector_private { + struct list_head list; + spinlock_t lock; + struct net_device *dev; + + int unit; + + /* Timeout timer in TX */ + + struct timer_list tl; + + /* Scheduled "remove device" work */ + struct work_struct reset_tx; + struct vector_fds *fds; + + struct vector_queue *rx_queue; + struct vector_queue *tx_queue; + + int rx_irq; + int tx_irq; + + struct arglist *parsed; + + void *transport_data; /* transport specific params if needed */ + + int max_packet; + int req_size; /* different from max packet - used for TSO */ + int headroom; + + int options; + + /* remote address if any - some transports will leave this as null */ + + int header_size; + int rx_header_size; + int coalesce; + + void *header_rxbuffer; + void *header_txbuffer; + + int (*form_header)(uint8_t *header, + struct sk_buff *skb, struct vector_private *vp); + int (*verify_header)(uint8_t *header, + struct sk_buff *skb, struct vector_private *vp); + + spinlock_t stats_lock; + + struct tasklet_struct tx_poll; + bool rexmit_scheduled; + bool opened; + bool in_write_poll; + + /* ethtool stats */ + + struct vector_estats estats; + void *bpf; + + char user[0]; +}; + +extern int build_transport_data(struct vector_private *vp); + +#endif diff --git a/arch/um/drivers/vector_transports.c b/arch/um/drivers/vector_transports.c new file mode 100644 index 000000000000..9065047f844b --- /dev/null +++ b/arch/um/drivers/vector_transports.c @@ -0,0 +1,458 @@ +/* + * Copyright (C) 2017 - Cambridge Greys Limited + * Copyright (C) 2011 - 2014 Cisco Systems Inc + * Licensed under the GPL. + */ + +#include <linux/etherdevice.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <asm/byteorder.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/virtio_net.h> +#include <linux/virtio_net.h> +#include <linux/virtio_byteorder.h> +#include <linux/netdev_features.h> +#include "vector_user.h" +#include "vector_kern.h" + +#define GOOD_LINEAR 512 +#define GSO_ERROR "Incoming GSO frames and GRO disabled on the interface" + +struct gre_minimal_header { + uint16_t header; + uint16_t arptype; +}; + + +struct uml_gre_data { + uint32_t rx_key; + uint32_t tx_key; + uint32_t sequence; + + bool ipv6; + bool has_sequence; + bool pin_sequence; + bool checksum; + bool key; + struct gre_minimal_header expected_header; + + uint32_t checksum_offset; + uint32_t key_offset; + uint32_t sequence_offset; + +}; + +struct uml_l2tpv3_data { + uint64_t rx_cookie; + uint64_t tx_cookie; + uint64_t rx_session; + uint64_t tx_session; + uint32_t counter; + + bool udp; + bool ipv6; + bool has_counter; + bool pin_counter; + bool cookie; + bool cookie_is_64; + + uint32_t cookie_offset; + uint32_t session_offset; + uint32_t counter_offset; +}; + +static int l2tpv3_form_header(uint8_t *header, + struct sk_buff *skb, struct vector_private *vp) +{ + struct uml_l2tpv3_data *td = vp->transport_data; + uint32_t *counter; + + if (td->udp) + *(uint32_t *) header = cpu_to_be32(L2TPV3_DATA_PACKET); + (*(uint32_t *) (header + td->session_offset)) = td->tx_session; + + if (td->cookie) { + if (td->cookie_is_64) + (*(uint64_t *)(header + td->cookie_offset)) = + td->tx_cookie; + else + (*(uint32_t *)(header + td->cookie_offset)) = + td->tx_cookie; + } + if (td->has_counter) { + counter = (uint32_t *)(header + td->counter_offset); + if (td->pin_counter) { + *counter = 0; + } else { + td->counter++; + *counter = cpu_to_be32(td->counter); + } + } + return 0; +} + +static int gre_form_header(uint8_t *header, + struct sk_buff *skb, struct vector_private *vp) +{ + struct uml_gre_data *td = vp->transport_data; + uint32_t *sequence; + *((uint32_t *) header) = *((uint32_t *) &td->expected_header); + if (td->key) + (*(uint32_t *) (header + td->key_offset)) = td->tx_key; + if (td->has_sequence) { + sequence = (uint32_t *)(header + td->sequence_offset); + if (td->pin_sequence) + *sequence = 0; + else + *sequence = cpu_to_be32(++td->sequence); + } + return 0; +} + +static int raw_form_header(uint8_t *header, + struct sk_buff *skb, struct vector_private *vp) +{ + struct virtio_net_hdr *vheader = (struct virtio_net_hdr *) header; + + virtio_net_hdr_from_skb( + skb, + vheader, + virtio_legacy_is_little_endian(), + false + ); + + return 0; +} + +static int l2tpv3_verify_header( + uint8_t *header, struct sk_buff *skb, struct vector_private *vp) +{ + struct uml_l2tpv3_data *td = vp->transport_data; + uint32_t *session; + uint64_t cookie; + + if ((!td->udp) && (!td->ipv6)) + header += sizeof(struct iphdr) /* fix for ipv4 raw */; + + /* we do not do a strict check for "data" packets as per + * the RFC spec because the pure IP spec does not have + * that anyway. + */ + + if (td->cookie) { + if (td->cookie_is_64) + cookie = *(uint64_t *)(header + td->cookie_offset); + else + cookie = *(uint32_t *)(header + td->cookie_offset); + if (cookie != td->rx_cookie) { + if (net_ratelimit()) + netdev_err(vp->dev, "uml_l2tpv3: unknown cookie id"); + return -1; + } + } + session = (uint32_t *) (header + td->session_offset); + if (*session != td->rx_session) { + if (net_ratelimit()) + netdev_err(vp->dev, "uml_l2tpv3: session mismatch"); + return -1; + } + return 0; +} + +static int gre_verify_header( + uint8_t *header, struct sk_buff *skb, struct vector_private *vp) +{ + + uint32_t key; + struct uml_gre_data *td = vp->transport_data; + + if (!td->ipv6) + header += sizeof(struct iphdr) /* fix for ipv4 raw */; + + if (*((uint32_t *) header) != *((uint32_t *) &td->expected_header)) { + if (net_ratelimit()) + netdev_err(vp->dev, "header type disagreement, expecting %0x, got %0x", + *((uint32_t *) &td->expected_header), + *((uint32_t *) header) + ); + return -1; + } + + if (td->key) { + key = (*(uint32_t *)(header + td->key_offset)); + if (key != td->rx_key) { + if (net_ratelimit()) + netdev_err(vp->dev, "unknown key id %0x, expecting %0x", + key, td->rx_key); + return -1; + } + } + return 0; +} + +static int raw_verify_header( + uint8_t *header, struct sk_buff *skb, struct vector_private *vp) +{ + struct virtio_net_hdr *vheader = (struct virtio_net_hdr *) header; + + if ((vheader->gso_type != VIRTIO_NET_HDR_GSO_NONE) && + (vp->req_size != 65536)) { + if (net_ratelimit()) + netdev_err( + vp->dev, + GSO_ERROR + ); + } + if ((vheader->flags & VIRTIO_NET_HDR_F_DATA_VALID) > 0) + return 1; + + virtio_net_hdr_to_skb(skb, vheader, virtio_legacy_is_little_endian()); + return 0; +} + +static bool get_uint_param( + struct arglist *def, char *param, unsigned int *result) +{ + char *arg = uml_vector_fetch_arg(def, param); + + if (arg != NULL) { + if (kstrtoint(arg, 0, result) == 0) + return true; + } + return false; +} + +static bool get_ulong_param( + struct arglist *def, char *param, unsigned long *result) +{ + char *arg = uml_vector_fetch_arg(def, param); + + if (arg != NULL) { + if (kstrtoul(arg, 0, result) == 0) + return true; + return true; + } + return false; +} + +static int build_gre_transport_data(struct vector_private *vp) +{ + struct uml_gre_data *td; + int temp_int; + int temp_rx; + int temp_tx; + + vp->transport_data = kmalloc(sizeof(struct uml_gre_data), GFP_KERNEL); + if (vp->transport_data == NULL) + return -ENOMEM; + td = vp->transport_data; + td->sequence = 0; + + td->expected_header.arptype = GRE_IRB; + td->expected_header.header = 0; + + vp->form_header = &gre_form_header; + vp->verify_header = &gre_verify_header; + vp->header_size = 4; + td->key_offset = 4; + td->sequence_offset = 4; + td->checksum_offset = 4; + + td->ipv6 = false; + if (get_uint_param(vp->parsed, "v6", &temp_int)) { + if (temp_int > 0) + td->ipv6 = true; + } + td->key = false; + if (get_uint_param(vp->parsed, "rx_key", &temp_rx)) { + if (get_uint_param(vp->parsed, "tx_key", &temp_tx)) { + td->key = true; + td->expected_header.header |= GRE_MODE_KEY; + td->rx_key = cpu_to_be32(temp_rx); + td->tx_key = cpu_to_be32(temp_tx); + vp->header_size += 4; + td->sequence_offset += 4; + } else { + return -EINVAL; + } + } + + td->sequence = false; + if (get_uint_param(vp->parsed, "sequence", &temp_int)) { + if (temp_int > 0) { + vp->header_size += 4; + td->has_sequence = true; + td->expected_header.header |= GRE_MODE_SEQUENCE; + if (get_uint_param( + vp->parsed, "pin_sequence", &temp_int)) { + if (temp_int > 0) + td->pin_sequence = true; + } + } + } + vp->rx_header_size = vp->header_size; + if (!td->ipv6) + vp->rx_header_size += sizeof(struct iphdr); + return 0; +} + +static int build_l2tpv3_transport_data(struct vector_private *vp) +{ + + struct uml_l2tpv3_data *td; + int temp_int, temp_rxs, temp_txs; + unsigned long temp_rx; + unsigned long temp_tx; + + vp->transport_data = kmalloc( + sizeof(struct uml_l2tpv3_data), GFP_KERNEL); + + if (vp->transport_data == NULL) + return -ENOMEM; + + td = vp->transport_data; + + vp->form_header = &l2tpv3_form_header; + vp->verify_header = &l2tpv3_verify_header; + td->counter = 0; + + vp->header_size = 4; + td->session_offset = 0; + td->cookie_offset = 4; + td->counter_offset = 4; + + + td->ipv6 = false; + if (get_uint_param(vp->parsed, "v6", &temp_int)) { + if (temp_int > 0) + td->ipv6 = true; + } + + if (get_uint_param(vp->parsed, "rx_session", &temp_rxs)) { + if (get_uint_param(vp->parsed, "tx_session", &temp_txs)) { + td->tx_session = cpu_to_be32(temp_txs); + td->rx_session = cpu_to_be32(temp_rxs); + } else { + return -EINVAL; + } + } else { + return -EINVAL; + } + + td->cookie_is_64 = false; + if (get_uint_param(vp->parsed, "cookie64", &temp_int)) { + if (temp_int > 0) + td->cookie_is_64 = true; + } + td->cookie = false; + if (get_ulong_param(vp->parsed, "rx_cookie", &temp_rx)) { + if (get_ulong_param(vp->parsed, "tx_cookie", &temp_tx)) { + td->cookie = true; + if (td->cookie_is_64) { + td->rx_cookie = cpu_to_be64(temp_rx); + td->tx_cookie = cpu_to_be64(temp_tx); + vp->header_size += 8; + td->counter_offset += 8; + } else { + td->rx_cookie = cpu_to_be32(temp_rx); + td->tx_cookie = cpu_to_be32(temp_tx); + vp->header_size += 4; + td->counter_offset += 4; + } + } else { + return -EINVAL; + } + } + + td->has_counter = false; + if (get_uint_param(vp->parsed, "counter", &temp_int)) { + if (temp_int > 0) { + td->has_counter = true; + vp->header_size += 4; + if (get_uint_param( + vp->parsed, "pin_counter", &temp_int)) { + if (temp_int > 0) + td->pin_counter = true; + } + } + } + + if (get_uint_param(vp->parsed, "udp", &temp_int)) { + if (temp_int > 0) { + td->udp = true; + vp->header_size += 4; + td->counter_offset += 4; + td->session_offset += 4; + td->cookie_offset += 4; + } + } + + vp->rx_header_size = vp->header_size; + if ((!td->ipv6) && (!td->udp)) + vp->rx_header_size += sizeof(struct iphdr); + + return 0; +} + +static int build_raw_transport_data(struct vector_private *vp) +{ + if (uml_raw_enable_vnet_headers(vp->fds->rx_fd)) { + if (!uml_raw_enable_vnet_headers(vp->fds->tx_fd)) + return -1; + vp->form_header = &raw_form_header; + vp->verify_header = &raw_verify_header; + vp->header_size = sizeof(struct virtio_net_hdr); + vp->rx_header_size = sizeof(struct virtio_net_hdr); + vp->dev->hw_features |= (NETIF_F_TSO | NETIF_F_GRO); + vp->dev->features |= + (NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + NETIF_F_TSO | NETIF_F_GRO); + netdev_info( + vp->dev, + "raw: using vnet headers for tso and tx/rx checksum" + ); + } + return 0; +} + +static int build_tap_transport_data(struct vector_private *vp) +{ + if (uml_raw_enable_vnet_headers(vp->fds->rx_fd)) { + vp->form_header = &raw_form_header; + vp->verify_header = &raw_verify_header; + vp->header_size = sizeof(struct virtio_net_hdr); + vp->rx_header_size = sizeof(struct virtio_net_hdr); + vp->dev->hw_features |= + (NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GRO); + vp->dev->features |= + (NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + NETIF_F_TSO | NETIF_F_GSO | NETIF_F_GRO); + netdev_info( + vp->dev, + "tap/raw: using vnet headers for tso and tx/rx checksum" + ); + } else { + return 0; /* do not try to enable tap too if raw failed */ + } + if (uml_tap_enable_vnet_headers(vp->fds->tx_fd)) + return 0; + return -1; +} + +int build_transport_data(struct vector_private *vp) +{ + char *transport = uml_vector_fetch_arg(vp->parsed, "transport"); + + if (strncmp(transport, TRANS_GRE, TRANS_GRE_LEN) == 0) + return build_gre_transport_data(vp); + if (strncmp(transport, TRANS_L2TPV3, TRANS_L2TPV3_LEN) == 0) + return build_l2tpv3_transport_data(vp); + if (strncmp(transport, TRANS_RAW, TRANS_RAW_LEN) == 0) + return build_raw_transport_data(vp); + if (strncmp(transport, TRANS_TAP, TRANS_TAP_LEN) == 0) + return build_tap_transport_data(vp); + return 0; +} + diff --git a/arch/um/drivers/vector_user.c b/arch/um/drivers/vector_user.c new file mode 100644 index 000000000000..4d6a78e31089 --- /dev/null +++ b/arch/um/drivers/vector_user.c @@ -0,0 +1,590 @@ +/* + * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Licensed under the GPL + */ + +#include <stdio.h> +#include <unistd.h> +#include <stdarg.h> +#include <errno.h> +#include <stddef.h> +#include <string.h> +#include <sys/ioctl.h> +#include <net/if.h> +#include <linux/if_tun.h> +#include <arpa/inet.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <net/ethernet.h> +#include <netinet/ip.h> +#include <netinet/ether.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <sys/socket.h> +#include <sys/wait.h> +#include <linux/virtio_net.h> +#include <netdb.h> +#include <stdlib.h> +#include <os.h> +#include <um_malloc.h> +#include "vector_user.h" + +#define ID_GRE 0 +#define ID_L2TPV3 1 +#define ID_MAX 1 + +#define TOKEN_IFNAME "ifname" + +#define TRANS_RAW "raw" +#define TRANS_RAW_LEN strlen(TRANS_RAW) + +#define VNET_HDR_FAIL "could not enable vnet headers on fd %d" +#define TUN_GET_F_FAIL "tapraw: TUNGETFEATURES failed: %s" +#define L2TPV3_BIND_FAIL "l2tpv3_open : could not bind socket err=%i" +#define BPF_ATTACH_FAIL "Failed to attach filter size %d to %d, err %d\n" + +/* This is very ugly and brute force lookup, but it is done + * only once at initialization so not worth doing hashes or + * anything more intelligent + */ + +char *uml_vector_fetch_arg(struct arglist *ifspec, char *token) +{ + int i; + + for (i = 0; i < ifspec->numargs; i++) { + if (strcmp(ifspec->tokens[i], token) == 0) + return ifspec->values[i]; + } + return NULL; + +} + +struct arglist *uml_parse_vector_ifspec(char *arg) +{ + struct arglist *result; + int pos, len; + bool parsing_token = true, next_starts = true; + + if (arg == NULL) + return NULL; + result = uml_kmalloc(sizeof(struct arglist), UM_GFP_KERNEL); + if (result == NULL) + return NULL; + result->numargs = 0; + len = strlen(arg); + for (pos = 0; pos < len; pos++) { + if (next_starts) { + if (parsing_token) { + result->tokens[result->numargs] = arg + pos; + } else { + result->values[result->numargs] = arg + pos; + result->numargs++; + } + next_starts = false; + } + if (*(arg + pos) == '=') { + if (parsing_token) + parsing_token = false; + else + goto cleanup; + next_starts = true; + (*(arg + pos)) = '\0'; + } + if (*(arg + pos) == ',') { + parsing_token = true; + next_starts = true; + (*(arg + pos)) = '\0'; + } + } + return result; +cleanup: + printk(UM_KERN_ERR "vector_setup - Couldn't parse '%s'\n", arg); + kfree(result); + return NULL; +} + +/* + * Socket/FD configuration functions. These return an structure + * of rx and tx descriptors to cover cases where these are not + * the same (f.e. read via raw socket and write via tap). + */ + +#define PATH_NET_TUN "/dev/net/tun" + +static struct vector_fds *user_init_tap_fds(struct arglist *ifspec) +{ + struct ifreq ifr; + int fd = -1; + struct sockaddr_ll sock; + int err = -ENOMEM, offload; + char *iface; + struct vector_fds *result = NULL; + + iface = uml_vector_fetch_arg(ifspec, TOKEN_IFNAME); + if (iface == NULL) { + printk(UM_KERN_ERR "uml_tap: failed to parse interface spec\n"); + goto tap_cleanup; + } + + result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL); + if (result == NULL) { + printk(UM_KERN_ERR "uml_tap: failed to allocate file descriptors\n"); + goto tap_cleanup; + } + result->rx_fd = -1; + result->tx_fd = -1; + result->remote_addr = NULL; + result->remote_addr_size = 0; + + /* TAP */ + + fd = open(PATH_NET_TUN, O_RDWR); + if (fd < 0) { + printk(UM_KERN_ERR "uml_tap: failed to open tun device\n"); + goto tap_cleanup; + } + result->tx_fd = fd; + memset(&ifr, 0, sizeof(ifr)); + ifr.ifr_flags = IFF_TAP | IFF_NO_PI | IFF_VNET_HDR; + strncpy((char *)&ifr.ifr_name, iface, sizeof(ifr.ifr_name) - 1); + + err = ioctl(fd, TUNSETIFF, (void *) &ifr); + if (err != 0) { + printk(UM_KERN_ERR "uml_tap: failed to select tap interface\n"); + goto tap_cleanup; + } + + offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6; + ioctl(fd, TUNSETOFFLOAD, offload); + + /* RAW */ + + fd = socket(AF_PACKET, SOCK_RAW, htons(ETH_P_ALL)); + if (fd == -1) { + printk(UM_KERN_ERR + "uml_tap: failed to create socket: %i\n", -errno); + goto tap_cleanup; + } + result->rx_fd = fd; + memset(&ifr, 0, sizeof(ifr)); + strncpy((char *)&ifr.ifr_name, iface, sizeof(ifr.ifr_name) - 1); + if (ioctl(fd, SIOCGIFINDEX, (void *) &ifr) < 0) { + printk(UM_KERN_ERR + "uml_tap: failed to set interface: %i\n", -errno); + goto tap_cleanup; + } + + sock.sll_family = AF_PACKET; + sock.sll_protocol = htons(ETH_P_ALL); + sock.sll_ifindex = ifr.ifr_ifindex; + + if (bind(fd, + (struct sockaddr *) &sock, sizeof(struct sockaddr_ll)) < 0) { + printk(UM_KERN_ERR + "user_init_tap: failed to bind raw pair, err %d\n", + -errno); + goto tap_cleanup; + } + return result; +tap_cleanup: + printk(UM_KERN_ERR "user_init_tap: init failed, error %d", err); + if (result != NULL) { + if (result->rx_fd >= 0) + os_close_file(result->rx_fd); + if (result->tx_fd >= 0) + os_close_file(result->tx_fd); + kfree(result); + } + return NULL; +} + + +static struct vector_fds *user_init_raw_fds(struct arglist *ifspec) +{ + struct ifreq ifr; + int rxfd = -1, txfd = -1; + struct sockaddr_ll sock; + int err = -ENOMEM; + char *iface; + struct vector_fds *result = NULL; + + iface = uml_vector_fetch_arg(ifspec, TOKEN_IFNAME); + if (iface == NULL) + goto cleanup; + + rxfd = socket(AF_PACKET, SOCK_RAW, ETH_P_ALL); + if (rxfd == -1) { + err = -errno; + goto cleanup; + } + txfd = socket(AF_PACKET, SOCK_RAW, 0); /* Turn off RX on this fd */ + if (txfd == -1) { + err = -errno; + goto cleanup; + } + memset(&ifr, 0, sizeof(ifr)); + strncpy((char *)&ifr.ifr_name, iface, sizeof(ifr.ifr_name) - 1); + if (ioctl(rxfd, SIOCGIFINDEX, (void *) &ifr) < 0) { + err = -errno; + goto cleanup; + } + + sock.sll_family = AF_PACKET; + sock.sll_protocol = htons(ETH_P_ALL); + sock.sll_ifindex = ifr.ifr_ifindex; + + if (bind(rxfd, + (struct sockaddr *) &sock, sizeof(struct sockaddr_ll)) < 0) { + err = -errno; + goto cleanup; + } + + sock.sll_family = AF_PACKET; + sock.sll_protocol = htons(ETH_P_IP); + sock.sll_ifindex = ifr.ifr_ifindex; + + if (bind(txfd, + (struct sockaddr *) &sock, sizeof(struct sockaddr_ll)) < 0) { + err = -errno; + goto cleanup; + } + + result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL); + if (result != NULL) { + result->rx_fd = rxfd; + result->tx_fd = txfd; + result->remote_addr = NULL; + result->remote_addr_size = 0; + } + return result; +cleanup: + printk(UM_KERN_ERR "user_init_raw: init failed, error %d", err); + if (rxfd >= 0) + os_close_file(rxfd); + if (txfd >= 0) + os_close_file(txfd); + if (result != NULL) + kfree(result); + return NULL; +} + + +bool uml_raw_enable_qdisc_bypass(int fd) +{ + int optval = 1; + + if (setsockopt(fd, + SOL_PACKET, PACKET_QDISC_BYPASS, + &optval, sizeof(optval)) != 0) { + return false; + } + return true; +} + +bool uml_raw_enable_vnet_headers(int fd) +{ + int optval = 1; + + if (setsockopt(fd, + SOL_PACKET, PACKET_VNET_HDR, + &optval, sizeof(optval)) != 0) { + printk(UM_KERN_INFO VNET_HDR_FAIL, fd); + return false; + } + return true; +} +bool uml_tap_enable_vnet_headers(int fd) +{ + unsigned int features; + int len = sizeof(struct virtio_net_hdr); + + if (ioctl(fd, TUNGETFEATURES, &features) == -1) { + printk(UM_KERN_INFO TUN_GET_F_FAIL, strerror(errno)); + return false; + } + if ((features & IFF_VNET_HDR) == 0) { + printk(UM_KERN_INFO "tapraw: No VNET HEADER support"); + return false; + } + ioctl(fd, TUNSETVNETHDRSZ, &len); + return true; +} + +static struct vector_fds *user_init_socket_fds(struct arglist *ifspec, int id) +{ + int err = -ENOMEM; + int fd = -1, gairet; + struct addrinfo srchints; + struct addrinfo dsthints; + bool v6, udp; + char *value; + char *src, *dst, *srcport, *dstport; + struct addrinfo *gairesult = NULL; + struct vector_fds *result = NULL; + + + value = uml_vector_fetch_arg(ifspec, "v6"); + v6 = false; + udp = false; + if (value != NULL) { + if (strtol((const char *) value, NULL, 10) > 0) + v6 = true; + } + + value = uml_vector_fetch_arg(ifspec, "udp"); + if (value != NULL) { + if (strtol((const char *) value, NULL, 10) > 0) + udp = true; + } + src = uml_vector_fetch_arg(ifspec, "src"); + dst = uml_vector_fetch_arg(ifspec, "dst"); + srcport = uml_vector_fetch_arg(ifspec, "srcport"); + dstport = uml_vector_fetch_arg(ifspec, "dstport"); + + memset(&dsthints, 0, sizeof(dsthints)); + + if (v6) + dsthints.ai_family = AF_INET6; + else + dsthints.ai_family = AF_INET; + + switch (id) { + case ID_GRE: + dsthints.ai_socktype = SOCK_RAW; + dsthints.ai_protocol = IPPROTO_GRE; + break; + case ID_L2TPV3: + if (udp) { + dsthints.ai_socktype = SOCK_DGRAM; + dsthints.ai_protocol = 0; + } else { + dsthints.ai_socktype = SOCK_RAW; + dsthints.ai_protocol = IPPROTO_L2TP; + } + break; + default: + printk(KERN_ERR "Unsupported socket type\n"); + return NULL; + } + memcpy(&srchints, &dsthints, sizeof(struct addrinfo)); + + gairet = getaddrinfo(src, srcport, &dsthints, &gairesult); + if ((gairet != 0) || (gairesult == NULL)) { + printk(UM_KERN_ERR + "socket_open : could not resolve src, error = %s", + gai_strerror(gairet) + ); + return NULL; + } + fd = socket(gairesult->ai_family, + gairesult->ai_socktype, gairesult->ai_protocol); + if (fd == -1) { + printk(UM_KERN_ERR + "socket_open : could not open socket, error = %d", + -errno + ); + goto cleanup; + } + if (bind(fd, + (struct sockaddr *) gairesult->ai_addr, + gairesult->ai_addrlen)) { + printk(UM_KERN_ERR L2TPV3_BIND_FAIL, errno); + goto cleanup; + } + + if (gairesult != NULL) + freeaddrinfo(gairesult); + + gairesult = NULL; + + gairet = getaddrinfo(dst, dstport, &dsthints, &gairesult); + if ((gairet != 0) || (gairesult == NULL)) { + printk(UM_KERN_ERR + "socket_open : could not resolve dst, error = %s", + gai_strerror(gairet) + ); + return NULL; + } + + result = uml_kmalloc(sizeof(struct vector_fds), UM_GFP_KERNEL); + if (result != NULL) { + result->rx_fd = fd; + result->tx_fd = fd; + result->remote_addr = uml_kmalloc( + gairesult->ai_addrlen, UM_GFP_KERNEL); + if (result->remote_addr == NULL) + goto cleanup; + result->remote_addr_size = gairesult->ai_addrlen; + memcpy( + result->remote_addr, + gairesult->ai_addr, + gairesult->ai_addrlen + ); + } + freeaddrinfo(gairesult); + return result; +cleanup: + if (gairesult != NULL) + freeaddrinfo(gairesult); + printk(UM_KERN_ERR "user_init_socket: init failed, error %d", err); + if (fd >= 0) + os_close_file(fd); + if (result != NULL) { + if (result->remote_addr != NULL) + kfree(result->remote_addr); + kfree(result); + } + return NULL; +} + +struct vector_fds *uml_vector_user_open( + int unit, + struct arglist *parsed +) +{ + char *transport; + + if (parsed == NULL) { + printk(UM_KERN_ERR "no parsed config for unit %d\n", unit); + return NULL; + } + transport = uml_vector_fetch_arg(parsed, "transport"); + if (transport == NULL) { + printk(UM_KERN_ERR "missing transport for unit %d\n", unit); + return NULL; + } + if (strncmp(transport, TRANS_RAW, TRANS_RAW_LEN) == 0) + return user_init_raw_fds(parsed); + if (strncmp(transport, TRANS_TAP, TRANS_TAP_LEN) == 0) + return user_init_tap_fds(parsed); + if (strncmp(transport, TRANS_GRE, TRANS_GRE_LEN) == 0) + return user_init_socket_fds(parsed, ID_GRE); + if (strncmp(transport, TRANS_L2TPV3, TRANS_L2TPV3_LEN) == 0) + return user_init_socket_fds(parsed, ID_L2TPV3); + return NULL; +} + + +int uml_vector_sendmsg(int fd, void *hdr, int flags) +{ + int n; + + CATCH_EINTR(n = sendmsg(fd, (struct msghdr *) hdr, flags)); + if ((n < 0) && (errno == EAGAIN)) + return 0; + if (n >= 0) + return n; + else + return -errno; +} + +int uml_vector_recvmsg(int fd, void *hdr, int flags) +{ + int n; + + CATCH_EINTR(n = recvmsg(fd, (struct msghdr *) hdr, flags)); + if ((n < 0) && (errno == EAGAIN)) + return 0; + if (n >= 0) + return n; + else + return -errno; +} + +int uml_vector_writev(int fd, void *hdr, int iovcount) +{ + int n; + + CATCH_EINTR(n = writev(fd, (struct iovec *) hdr, iovcount)); + if ((n < 0) && (errno == EAGAIN)) + return 0; + if (n >= 0) + return n; + else + return -errno; +} + +int uml_vector_sendmmsg( + int fd, + void *msgvec, + unsigned int vlen, + unsigned int flags) +{ + int n; + + CATCH_EINTR(n = sendmmsg(fd, (struct mmsghdr *) msgvec, vlen, flags)); + if ((n < 0) && (errno == EAGAIN)) + return 0; + if (n >= 0) + return n; + else + return -errno; +} + +int uml_vector_recvmmsg( + int fd, + void *msgvec, + unsigned int vlen, + unsigned int flags) +{ + int n; + + CATCH_EINTR( + n = recvmmsg(fd, (struct mmsghdr *) msgvec, vlen, flags, 0)); + if ((n < 0) && (errno == EAGAIN)) + return 0; + if (n >= 0) + return n; + else + return -errno; +} +int uml_vector_attach_bpf(int fd, void *bpf, int bpf_len) +{ + int err = setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, bpf, bpf_len); + + if (err < 0) + printk(KERN_ERR BPF_ATTACH_FAIL, bpf_len, fd, -errno); + return err; +} + +#define DEFAULT_BPF_LEN 6 + +void *uml_vector_default_bpf(int fd, void *mac) +{ + struct sock_filter *bpf; + uint32_t *mac1 = (uint32_t *)(mac + 2); + uint16_t *mac2 = (uint16_t *) mac; + struct sock_fprog bpf_prog = { + .len = 6, + .filter = NULL, + }; + + bpf = uml_kmalloc( + sizeof(struct sock_filter) * DEFAULT_BPF_LEN, UM_GFP_KERNEL); + if (bpf != NULL) { + bpf_prog.filter = bpf; + /* ld [8] */ + bpf[0] = (struct sock_filter){ 0x20, 0, 0, 0x00000008 }; + /* jeq #0xMAC[2-6] jt 2 jf 5*/ + bpf[1] = (struct sock_filter){ 0x15, 0, 3, ntohl(*mac1)}; + /* ldh [6] */ + bpf[2] = (struct sock_filter){ 0x28, 0, 0, 0x00000006 }; + /* jeq #0xMAC[0-1] jt 4 jf 5 */ + bpf[3] = (struct sock_filter){ 0x15, 0, 1, ntohs(*mac2)}; + /* ret #0 */ + bpf[4] = (struct sock_filter){ 0x6, 0, 0, 0x00000000 }; + /* ret #0x40000 */ + bpf[5] = (struct sock_filter){ 0x6, 0, 0, 0x00040000 }; + if (uml_vector_attach_bpf( + fd, &bpf_prog, sizeof(struct sock_fprog)) < 0) { + kfree(bpf); + bpf = NULL; + } + } + return bpf; +} + diff --git a/arch/um/drivers/vector_user.h b/arch/um/drivers/vector_user.h new file mode 100644 index 000000000000..d7cbff73b7ff --- /dev/null +++ b/arch/um/drivers/vector_user.h @@ -0,0 +1,100 @@ +/* + * Copyright (C) 2002 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Licensed under the GPL + */ + +#ifndef __UM_VECTOR_USER_H +#define __UM_VECTOR_USER_H + +#define MAXVARGS 20 + +#define TOKEN_IFNAME "ifname" + +#define TRANS_RAW "raw" +#define TRANS_RAW_LEN strlen(TRANS_RAW) + +#define TRANS_TAP "tap" +#define TRANS_TAP_LEN strlen(TRANS_TAP) + + +#define TRANS_GRE "gre" +#define TRANS_GRE_LEN strlen(TRANS_RAW) + +#define TRANS_L2TPV3 "l2tpv3" +#define TRANS_L2TPV3_LEN strlen(TRANS_L2TPV3) + +#ifndef IPPROTO_GRE +#define IPPROTO_GRE 0x2F +#endif + +#define GRE_MODE_CHECKSUM cpu_to_be16(8 << 12) /* checksum */ +#define GRE_MODE_RESERVED cpu_to_be16(4 << 12) /* unused */ +#define GRE_MODE_KEY cpu_to_be16(2 << 12) /* KEY present */ +#define GRE_MODE_SEQUENCE cpu_to_be16(1 << 12) /* sequence */ + +#define GRE_IRB cpu_to_be16(0x6558) + +#define L2TPV3_DATA_PACKET 0x30000 + +/* IANA-assigned IP protocol ID for L2TPv3 */ + +#ifndef IPPROTO_L2TP +#define IPPROTO_L2TP 0x73 +#endif + +struct arglist { + int numargs; + char *tokens[MAXVARGS]; + char *values[MAXVARGS]; +}; + +/* Separating read and write FDs allows us to have different + * rx and tx method. Example - read tap via raw socket using + * recvmmsg, write using legacy tap write calls + */ + +struct vector_fds { + int rx_fd; + int tx_fd; + void *remote_addr; + int remote_addr_size; +}; + +#define VECTOR_READ 1 +#define VECTOR_WRITE (1 < 1) +#define VECTOR_HEADERS (1 < 2) + +extern struct arglist *uml_parse_vector_ifspec(char *arg); + +extern struct vector_fds *uml_vector_user_open( + int unit, + struct arglist *parsed +); + +extern char *uml_vector_fetch_arg( + struct arglist *ifspec, + char *token +); + +extern int uml_vector_recvmsg(int fd, void *hdr, int flags); +extern int uml_vector_sendmsg(int fd, void *hdr, int flags); +extern int uml_vector_writev(int fd, void *hdr, int iovcount); +extern int uml_vector_sendmmsg( + int fd, void *msgvec, + unsigned int vlen, + unsigned int flags +); +extern int uml_vector_recvmmsg( + int fd, + void *msgvec, + unsigned int vlen, + unsigned int flags +); +extern void *uml_vector_default_bpf(int fd, void *mac); +extern int uml_vector_attach_bpf(int fd, void *bpf, int bpf_len); +extern bool uml_raw_enable_qdisc_bypass(int fd); +extern bool uml_raw_enable_vnet_headers(int fd); +extern bool uml_tap_enable_vnet_headers(int fd); + + +#endif diff --git a/arch/um/include/asm/asm-prototypes.h b/arch/um/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..5898a26daa0d --- /dev/null +++ b/arch/um/include/asm/asm-prototypes.h @@ -0,0 +1 @@ +#include <asm-generic/asm-prototypes.h> diff --git a/arch/um/include/asm/irq.h b/arch/um/include/asm/irq.h index b5cdd3f91157..49ed3e35b35a 100644 --- a/arch/um/include/asm/irq.h +++ b/arch/um/include/asm/irq.h @@ -18,7 +18,19 @@ #define XTERM_IRQ 13 #define RANDOM_IRQ 14 +#ifdef CONFIG_UML_NET_VECTOR + +#define VECTOR_BASE_IRQ 15 +#define VECTOR_IRQ_SPACE 8 + +#define LAST_IRQ (VECTOR_IRQ_SPACE + VECTOR_BASE_IRQ) + +#else + #define LAST_IRQ RANDOM_IRQ + +#endif + #define NR_IRQS (LAST_IRQ + 1) #endif diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h index df5633053957..a7a6120f19d5 100644 --- a/arch/um/include/shared/irq_user.h +++ b/arch/um/include/shared/irq_user.h @@ -7,6 +7,7 @@ #define __IRQ_USER_H__ #include <sysdep/ptrace.h> +#include <stdbool.h> struct irq_fd { struct irq_fd *next; @@ -15,10 +16,17 @@ struct irq_fd { int type; int irq; int events; - int current_events; + bool active; + bool pending; + bool purge; }; -enum { IRQ_READ, IRQ_WRITE }; +#define IRQ_READ 0 +#define IRQ_WRITE 1 +#define IRQ_NONE 2 +#define MAX_IRQ_TYPE (IRQ_NONE + 1) + + struct siginfo; extern void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs); diff --git a/arch/um/include/shared/net_kern.h b/arch/um/include/shared/net_kern.h index 012ac87d4900..40442b98b173 100644 --- a/arch/um/include/shared/net_kern.h +++ b/arch/um/include/shared/net_kern.h @@ -65,5 +65,7 @@ extern int tap_setup_common(char *str, char *type, char **dev_name, char **mac_out, char **gate_addr); extern void register_transport(struct transport *new); extern unsigned short eth_protocol(struct sk_buff *skb); +extern void uml_net_setup_etheraddr(struct net_device *dev, char *str); + #endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index d8ddaf9790d2..048ae37eb5aa 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -290,15 +290,16 @@ extern void halt_skas(void); extern void reboot_skas(void); /* irq.c */ -extern int os_waiting_for_events(struct irq_fd *active_fds); -extern int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds); -extern void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, - struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2); -extern void os_free_irq_later(struct irq_fd *active_fds, - int irq, void *dev_id); -extern int os_get_pollfd(int i); -extern void os_set_pollfd(int i, int fd); +extern int os_waiting_for_events_epoll(void); +extern void *os_epoll_get_data_pointer(int index); +extern int os_epoll_triggered(int index, int events); +extern int os_event_mask(int irq_type); +extern int os_setup_epoll(void); +extern int os_add_epoll_fd(int events, int fd, void *data); +extern int os_mod_epoll_fd(int events, int fd, void *data); +extern int os_del_epoll_fd(int fd); extern void os_set_ioignore(void); +extern void os_close_epoll_fd(void); /* sigio.c */ extern int add_sigio_fd(int fd); diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 23cb9350d47e..6b7f3827d6e4 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -1,4 +1,6 @@ /* + * Copyright (C) 2017 - Cambridge Greys Ltd + * Copyright (C) 2011 - 2014 Cisco Systems Inc * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL * Derived (i.e. mostly copied) from arch/i386/kernel/irq.c: @@ -16,243 +18,362 @@ #include <as-layout.h> #include <kern_util.h> #include <os.h> +#include <irq_user.h> -/* - * This list is accessed under irq_lock, except in sigio_handler, - * where it is safe from being modified. IRQ handlers won't change it - - * if an IRQ source has vanished, it will be freed by free_irqs just - * before returning from sigio_handler. That will process a separate - * list of irqs to free, with its own locking, coming back here to - * remove list elements, taking the irq_lock to do so. + +/* When epoll triggers we do not know why it did so + * we can also have different IRQs for read and write. + * This is why we keep a small irq_fd array for each fd - + * one entry per IRQ type */ -static struct irq_fd *active_fds = NULL; -static struct irq_fd **last_irq_ptr = &active_fds; -extern void free_irqs(void); +struct irq_entry { + struct irq_entry *next; + int fd; + struct irq_fd *irq_array[MAX_IRQ_TYPE + 1]; +}; + +static struct irq_entry *active_fds; + +static DEFINE_SPINLOCK(irq_lock); + +static void irq_io_loop(struct irq_fd *irq, struct uml_pt_regs *regs) +{ +/* + * irq->active guards against reentry + * irq->pending accumulates pending requests + * if pending is raised the irq_handler is re-run + * until pending is cleared + */ + if (irq->active) { + irq->active = false; + do { + irq->pending = false; + do_IRQ(irq->irq, regs); + } while (irq->pending && (!irq->purge)); + if (!irq->purge) + irq->active = true; + } else { + irq->pending = true; + } +} void sigio_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs) { - struct irq_fd *irq_fd; - int n; + struct irq_entry *irq_entry; + struct irq_fd *irq; + + int n, i, j; while (1) { - n = os_waiting_for_events(active_fds); + /* This is now lockless - epoll keeps back-referencesto the irqs + * which have trigger it so there is no need to walk the irq + * list and lock it every time. We avoid locking by turning off + * IO for a specific fd by executing os_del_epoll_fd(fd) before + * we do any changes to the actual data structures + */ + n = os_waiting_for_events_epoll(); + if (n <= 0) { if (n == -EINTR) continue; - else break; + else + break; } - for (irq_fd = active_fds; irq_fd != NULL; - irq_fd = irq_fd->next) { - if (irq_fd->current_events != 0) { - irq_fd->current_events = 0; - do_IRQ(irq_fd->irq, regs); + for (i = 0; i < n ; i++) { + /* Epoll back reference is the entry with 3 irq_fd + * leaves - one for each irq type. + */ + irq_entry = (struct irq_entry *) + os_epoll_get_data_pointer(i); + for (j = 0; j < MAX_IRQ_TYPE ; j++) { + irq = irq_entry->irq_array[j]; + if (irq == NULL) + continue; + if (os_epoll_triggered(i, irq->events) > 0) + irq_io_loop(irq, regs); + if (irq->purge) { + irq_entry->irq_array[j] = NULL; + kfree(irq); + } } } } +} + +static int assign_epoll_events_to_irq(struct irq_entry *irq_entry) +{ + int i; + int events = 0; + struct irq_fd *irq; - free_irqs(); + for (i = 0; i < MAX_IRQ_TYPE ; i++) { + irq = irq_entry->irq_array[i]; + if (irq != NULL) + events = irq->events | events; + } + if (events > 0) { + /* os_add_epoll will call os_mod_epoll if this already exists */ + return os_add_epoll_fd(events, irq_entry->fd, irq_entry); + } + /* No events - delete */ + return os_del_epoll_fd(irq_entry->fd); } -static DEFINE_SPINLOCK(irq_lock); + static int activate_fd(int irq, int fd, int type, void *dev_id) { - struct pollfd *tmp_pfd; - struct irq_fd *new_fd, *irq_fd; + struct irq_fd *new_fd; + struct irq_entry *irq_entry; + int i, err, events; unsigned long flags; - int events, err, n; err = os_set_fd_async(fd); if (err < 0) goto out; - err = -ENOMEM; - new_fd = kmalloc(sizeof(struct irq_fd), GFP_KERNEL); - if (new_fd == NULL) - goto out; + spin_lock_irqsave(&irq_lock, flags); - if (type == IRQ_READ) - events = UM_POLLIN | UM_POLLPRI; - else events = UM_POLLOUT; - *new_fd = ((struct irq_fd) { .next = NULL, - .id = dev_id, - .fd = fd, - .type = type, - .irq = irq, - .events = events, - .current_events = 0 } ); + /* Check if we have an entry for this fd */ err = -EBUSY; - spin_lock_irqsave(&irq_lock, flags); - for (irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next) { - if ((irq_fd->fd == fd) && (irq_fd->type == type)) { - printk(KERN_ERR "Registering fd %d twice\n", fd); - printk(KERN_ERR "Irqs : %d, %d\n", irq_fd->irq, irq); - printk(KERN_ERR "Ids : 0x%p, 0x%p\n", irq_fd->id, - dev_id); + for (irq_entry = active_fds; + irq_entry != NULL; irq_entry = irq_entry->next) { + if (irq_entry->fd == fd) + break; + } + + if (irq_entry == NULL) { + /* This needs to be atomic as it may be called from an + * IRQ context. + */ + irq_entry = kmalloc(sizeof(struct irq_entry), GFP_ATOMIC); + if (irq_entry == NULL) { + printk(KERN_ERR + "Failed to allocate new IRQ entry\n"); goto out_unlock; } + irq_entry->fd = fd; + for (i = 0; i < MAX_IRQ_TYPE; i++) + irq_entry->irq_array[i] = NULL; + irq_entry->next = active_fds; + active_fds = irq_entry; } - if (type == IRQ_WRITE) - fd = -1; - - tmp_pfd = NULL; - n = 0; + /* Check if we are trying to re-register an interrupt for a + * particular fd + */ - while (1) { - n = os_create_pollfd(fd, events, tmp_pfd, n); - if (n == 0) - break; + if (irq_entry->irq_array[type] != NULL) { + printk(KERN_ERR + "Trying to reregister IRQ %d FD %d TYPE %d ID %p\n", + irq, fd, type, dev_id + ); + goto out_unlock; + } else { + /* New entry for this fd */ + + err = -ENOMEM; + new_fd = kmalloc(sizeof(struct irq_fd), GFP_ATOMIC); + if (new_fd == NULL) + goto out_unlock; - /* - * n > 0 - * It means we couldn't put new pollfd to current pollfds - * and tmp_fds is NULL or too small for new pollfds array. - * Needed size is equal to n as minimum. - * - * Here we have to drop the lock in order to call - * kmalloc, which might sleep. - * If something else came in and changed the pollfds array - * so we will not be able to put new pollfd struct to pollfds - * then we free the buffer tmp_fds and try again. + events = os_event_mask(type); + + *new_fd = ((struct irq_fd) { + .id = dev_id, + .irq = irq, + .type = type, + .events = events, + .active = true, + .pending = false, + .purge = false + }); + /* Turn off any IO on this fd - allows us to + * avoid locking the IRQ loop */ - spin_unlock_irqrestore(&irq_lock, flags); - kfree(tmp_pfd); - - tmp_pfd = kmalloc(n, GFP_KERNEL); - if (tmp_pfd == NULL) - goto out_kfree; - - spin_lock_irqsave(&irq_lock, flags); + os_del_epoll_fd(irq_entry->fd); + irq_entry->irq_array[type] = new_fd; } - *last_irq_ptr = new_fd; - last_irq_ptr = &new_fd->next; - + /* Turn back IO on with the correct (new) IO event mask */ + assign_epoll_events_to_irq(irq_entry); spin_unlock_irqrestore(&irq_lock, flags); - - /* - * This calls activate_fd, so it has to be outside the critical - * section. - */ - maybe_sigio_broken(fd, (type == IRQ_READ)); + maybe_sigio_broken(fd, (type != IRQ_NONE)); return 0; - - out_unlock: +out_unlock: spin_unlock_irqrestore(&irq_lock, flags); - out_kfree: - kfree(new_fd); - out: +out: return err; } -static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) +/* + * Walk the IRQ list and dispose of any unused entries. + * Should be done under irq_lock. + */ + +static void garbage_collect_irq_entries(void) { - unsigned long flags; + int i; + bool reap; + struct irq_entry *walk; + struct irq_entry *previous = NULL; + struct irq_entry *to_free; - spin_lock_irqsave(&irq_lock, flags); - os_free_irq_by_cb(test, arg, active_fds, &last_irq_ptr); - spin_unlock_irqrestore(&irq_lock, flags); + if (active_fds == NULL) + return; + walk = active_fds; + while (walk != NULL) { + reap = true; + for (i = 0; i < MAX_IRQ_TYPE ; i++) { + if (walk->irq_array[i] != NULL) { + reap = false; + break; + } + } + if (reap) { + if (previous == NULL) + active_fds = walk->next; + else + previous->next = walk->next; + to_free = walk; + } else { + to_free = NULL; + } + walk = walk->next; + if (to_free != NULL) + kfree(to_free); + } } -struct irq_and_dev { - int irq; - void *dev; -}; +/* + * Walk the IRQ list and get the descriptor for our FD + */ -static int same_irq_and_dev(struct irq_fd *irq, void *d) +static struct irq_entry *get_irq_entry_by_fd(int fd) { - struct irq_and_dev *data = d; + struct irq_entry *walk = active_fds; - return ((irq->irq == data->irq) && (irq->id == data->dev)); + while (walk != NULL) { + if (walk->fd == fd) + return walk; + walk = walk->next; + } + return NULL; } -static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) -{ - struct irq_and_dev data = ((struct irq_and_dev) { .irq = irq, - .dev = dev }); - free_irq_by_cb(same_irq_and_dev, &data); -} +/* + * Walk the IRQ list and dispose of an entry for a specific + * device, fd and number. Note - if sharing an IRQ for read + * and writefor the same FD it will be disposed in either case. + * If this behaviour is undesirable use different IRQ ids. + */ -static int same_fd(struct irq_fd *irq, void *fd) -{ - return (irq->fd == *((int *)fd)); -} +#define IGNORE_IRQ 1 +#define IGNORE_DEV (1<<1) -void free_irq_by_fd(int fd) +static void do_free_by_irq_and_dev( + struct irq_entry *irq_entry, + unsigned int irq, + void *dev, + int flags +) { - free_irq_by_cb(same_fd, &fd); + int i; + struct irq_fd *to_free; + + for (i = 0; i < MAX_IRQ_TYPE ; i++) { + if (irq_entry->irq_array[i] != NULL) { + if ( + ((flags & IGNORE_IRQ) || + (irq_entry->irq_array[i]->irq == irq)) && + ((flags & IGNORE_DEV) || + (irq_entry->irq_array[i]->id == dev)) + ) { + /* Turn off any IO on this fd - allows us to + * avoid locking the IRQ loop + */ + os_del_epoll_fd(irq_entry->fd); + to_free = irq_entry->irq_array[i]; + irq_entry->irq_array[i] = NULL; + assign_epoll_events_to_irq(irq_entry); + if (to_free->active) + to_free->purge = true; + else + kfree(to_free); + } + } + } } -/* Must be called with irq_lock held */ -static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) +void free_irq_by_fd(int fd) { - struct irq_fd *irq; - int i = 0; - int fdi; + struct irq_entry *to_free; + unsigned long flags; - for (irq = active_fds; irq != NULL; irq = irq->next) { - if ((irq->fd == fd) && (irq->irq == irqnum)) - break; - i++; - } - if (irq == NULL) { - printk(KERN_ERR "find_irq_by_fd doesn't have descriptor %d\n", - fd); - goto out; - } - fdi = os_get_pollfd(i); - if ((fdi != -1) && (fdi != fd)) { - printk(KERN_ERR "find_irq_by_fd - mismatch between active_fds " - "and pollfds, fd %d vs %d, need %d\n", irq->fd, - fdi, fd); - irq = NULL; - goto out; + spin_lock_irqsave(&irq_lock, flags); + to_free = get_irq_entry_by_fd(fd); + if (to_free != NULL) { + do_free_by_irq_and_dev( + to_free, + -1, + NULL, + IGNORE_IRQ | IGNORE_DEV + ); } - *index_out = i; - out: - return irq; + garbage_collect_irq_entries(); + spin_unlock_irqrestore(&irq_lock, flags); } +EXPORT_SYMBOL(free_irq_by_fd); -void reactivate_fd(int fd, int irqnum) +static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) { - struct irq_fd *irq; + struct irq_entry *to_free; unsigned long flags; - int i; spin_lock_irqsave(&irq_lock, flags); - irq = find_irq_by_fd(fd, irqnum, &i); - if (irq == NULL) { - spin_unlock_irqrestore(&irq_lock, flags); - return; + to_free = active_fds; + while (to_free != NULL) { + do_free_by_irq_and_dev( + to_free, + irq, + dev, + 0 + ); + to_free = to_free->next; } - os_set_pollfd(i, irq->fd); + garbage_collect_irq_entries(); spin_unlock_irqrestore(&irq_lock, flags); +} - add_sigio_fd(fd); + +void reactivate_fd(int fd, int irqnum) +{ + /** NOP - we do auto-EOI now **/ } void deactivate_fd(int fd, int irqnum) { - struct irq_fd *irq; + struct irq_entry *to_free; unsigned long flags; - int i; + os_del_epoll_fd(fd); spin_lock_irqsave(&irq_lock, flags); - irq = find_irq_by_fd(fd, irqnum, &i); - if (irq == NULL) { - spin_unlock_irqrestore(&irq_lock, flags); - return; + to_free = get_irq_entry_by_fd(fd); + if (to_free != NULL) { + do_free_by_irq_and_dev( + to_free, + irqnum, + NULL, + IGNORE_DEV + ); } - - os_set_pollfd(i, -1); + garbage_collect_irq_entries(); spin_unlock_irqrestore(&irq_lock, flags); - ignore_sigio_fd(fd); } EXPORT_SYMBOL(deactivate_fd); @@ -265,17 +386,28 @@ EXPORT_SYMBOL(deactivate_fd); */ int deactivate_all_fds(void) { - struct irq_fd *irq; - int err; + unsigned long flags; + struct irq_entry *to_free; - for (irq = active_fds; irq != NULL; irq = irq->next) { - err = os_clear_fd_async(irq->fd); - if (err) - return err; - } - /* If there is a signal already queued, after unblocking ignore it */ + spin_lock_irqsave(&irq_lock, flags); + /* Stop IO. The IRQ loop has no lock so this is our + * only way of making sure we are safe to dispose + * of all IRQ handlers + */ os_set_ioignore(); - + to_free = active_fds; + while (to_free != NULL) { + do_free_by_irq_and_dev( + to_free, + -1, + NULL, + IGNORE_IRQ | IGNORE_DEV + ); + to_free = to_free->next; + } + garbage_collect_irq_entries(); + spin_unlock_irqrestore(&irq_lock, flags); + os_close_epoll_fd(); return 0; } @@ -353,8 +485,11 @@ void __init init_IRQ(void) irq_set_chip_and_handler(TIMER_IRQ, &SIGVTALRM_irq_type, handle_edge_irq); + for (i = 1; i < NR_IRQS; i++) irq_set_chip_and_handler(i, &normal_irq_type, handle_edge_irq); + /* Initialize EPOLL Loop */ + os_setup_epoll(); } /* diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 7f69d17de354..052de4c8acb2 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -121,12 +121,12 @@ static void __init um_timer_setup(void) clockevents_register_device(&timer_clockevent); } -void read_persistent_clock(struct timespec *ts) +void read_persistent_clock64(struct timespec64 *ts) { long long nsecs = os_persistent_clock_emulation(); - set_normalized_timespec(ts, nsecs / NSEC_PER_SEC, - nsecs % NSEC_PER_SEC); + set_normalized_timespec64(ts, nsecs / NSEC_PER_SEC, + nsecs % NSEC_PER_SEC); } void __init time_init(void) diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 2db18cbbb0ea..c0197097c86e 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -12,6 +12,7 @@ #include <sys/mount.h> #include <sys/socket.h> #include <sys/stat.h> +#include <sys/sysmacros.h> #include <sys/un.h> #include <sys/types.h> #include <os.h> diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c index b9afb74b79ad..365823010346 100644 --- a/arch/um/os-Linux/irq.c +++ b/arch/um/os-Linux/irq.c @@ -1,135 +1,147 @@ /* + * Copyright (C) 2017 - Cambridge Greys Ltd + * Copyright (C) 2011 - 2014 Cisco Systems Inc * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) * Licensed under the GPL */ #include <stdlib.h> #include <errno.h> -#include <poll.h> +#include <sys/epoll.h> #include <signal.h> #include <string.h> #include <irq_user.h> #include <os.h> #include <um_malloc.h> +/* Epoll support */ + +static int epollfd = -1; + +#define MAX_EPOLL_EVENTS 64 + +static struct epoll_event epoll_events[MAX_EPOLL_EVENTS]; + +/* Helper to return an Epoll data pointer from an epoll event structure. + * We need to keep this one on the userspace side to keep includes separate + */ + +void *os_epoll_get_data_pointer(int index) +{ + return epoll_events[index].data.ptr; +} + +/* Helper to compare events versus the events in the epoll structure. + * Same as above - needs to be on the userspace side + */ + + +int os_epoll_triggered(int index, int events) +{ + return epoll_events[index].events & events; +} +/* Helper to set the event mask. + * The event mask is opaque to the kernel side, because it does not have + * access to the right includes/defines for EPOLL constants. + */ + +int os_event_mask(int irq_type) +{ + if (irq_type == IRQ_READ) + return EPOLLIN | EPOLLPRI; + if (irq_type == IRQ_WRITE) + return EPOLLOUT; + return 0; +} + /* - * Locked by irq_lock in arch/um/kernel/irq.c. Changed by os_create_pollfd - * and os_free_irq_by_cb, which are called under irq_lock. + * Initial Epoll Setup */ -static struct pollfd *pollfds = NULL; -static int pollfds_num = 0; -static int pollfds_size = 0; +int os_setup_epoll(void) +{ + epollfd = epoll_create(MAX_EPOLL_EVENTS); + return epollfd; +} -int os_waiting_for_events(struct irq_fd *active_fds) +/* + * Helper to run the actual epoll_wait + */ +int os_waiting_for_events_epoll(void) { - struct irq_fd *irq_fd; - int i, n, err; + int n, err; - n = poll(pollfds, pollfds_num, 0); + n = epoll_wait(epollfd, + (struct epoll_event *) &epoll_events, MAX_EPOLL_EVENTS, 0); if (n < 0) { err = -errno; if (errno != EINTR) - printk(UM_KERN_ERR "os_waiting_for_events:" - " poll returned %d, errno = %d\n", n, errno); + printk( + UM_KERN_ERR "os_waiting_for_events:" + " epoll returned %d, error = %s\n", n, + strerror(errno) + ); return err; } - - if (n == 0) - return 0; - - irq_fd = active_fds; - - for (i = 0; i < pollfds_num; i++) { - if (pollfds[i].revents != 0) { - irq_fd->current_events = pollfds[i].revents; - pollfds[i].fd = -1; - } - irq_fd = irq_fd->next; - } return n; } -int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds) -{ - if (pollfds_num == pollfds_size) { - if (size_tmpfds <= pollfds_size * sizeof(pollfds[0])) { - /* return min size needed for new pollfds area */ - return (pollfds_size + 1) * sizeof(pollfds[0]); - } - - if (pollfds != NULL) { - memcpy(tmp_pfd, pollfds, - sizeof(pollfds[0]) * pollfds_size); - /* remove old pollfds */ - kfree(pollfds); - } - pollfds = tmp_pfd; - pollfds_size++; - } else - kfree(tmp_pfd); /* remove not used tmp_pfd */ - - pollfds[pollfds_num] = ((struct pollfd) { .fd = fd, - .events = events, - .revents = 0 }); - pollfds_num++; - - return 0; -} -void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, - struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2) +/* + * Helper to add a fd to epoll + */ +int os_add_epoll_fd(int events, int fd, void *data) { - struct irq_fd **prev; - int i = 0; - - prev = &active_fds; - while (*prev != NULL) { - if ((*test)(*prev, arg)) { - struct irq_fd *old_fd = *prev; - if ((pollfds[i].fd != -1) && - (pollfds[i].fd != (*prev)->fd)) { - printk(UM_KERN_ERR "os_free_irq_by_cb - " - "mismatch between active_fds and " - "pollfds, fd %d vs %d\n", - (*prev)->fd, pollfds[i].fd); - goto out; - } - - pollfds_num--; - - /* - * This moves the *whole* array after pollfds[i] - * (though it doesn't spot as such)! - */ - memmove(&pollfds[i], &pollfds[i + 1], - (pollfds_num - i) * sizeof(pollfds[0])); - if (*last_irq_ptr2 == &old_fd->next) - *last_irq_ptr2 = prev; - - *prev = (*prev)->next; - if (old_fd->type == IRQ_WRITE) - ignore_sigio_fd(old_fd->fd); - kfree(old_fd); - continue; - } - prev = &(*prev)->next; - i++; - } - out: - return; + struct epoll_event event; + int result; + + event.data.ptr = data; + event.events = events | EPOLLET; + result = epoll_ctl(epollfd, EPOLL_CTL_ADD, fd, &event); + if ((result) && (errno == EEXIST)) + result = os_mod_epoll_fd(events, fd, data); + if (result) + printk("epollctl add err fd %d, %s\n", fd, strerror(errno)); + return result; } -int os_get_pollfd(int i) +/* + * Helper to mod the fd event mask and/or data backreference + */ +int os_mod_epoll_fd(int events, int fd, void *data) { - return pollfds[i].fd; + struct epoll_event event; + int result; + + event.data.ptr = data; + event.events = events; + result = epoll_ctl(epollfd, EPOLL_CTL_MOD, fd, &event); + if (result) + printk(UM_KERN_ERR + "epollctl mod err fd %d, %s\n", fd, strerror(errno)); + return result; } -void os_set_pollfd(int i, int fd) +/* + * Helper to delete the epoll fd + */ +int os_del_epoll_fd(int fd) { - pollfds[i].fd = fd; + struct epoll_event event; + int result; + /* This is quiet as we use this as IO ON/OFF - so it is often + * invoked on a non-existent fd + */ + result = epoll_ctl(epollfd, EPOLL_CTL_DEL, fd, &event); + return result; } void os_set_ioignore(void) { signal(SIGIO, SIG_IGN); } + +void os_close_epoll_fd(void) +{ + /* Needed so we do not leak an fd when rebooting */ + os_close_file(epollfd); +} diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index a86d7cc2c2d8..bf0acb8aad8b 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -16,6 +16,7 @@ #include <os.h> #include <sysdep/mcontext.h> #include <um_malloc.h> +#include <sys/ucontext.h> void (*sig_info[NSIG])(int, struct siginfo *, struct uml_pt_regs *) = { [SIGTRAP] = relay_signal, @@ -159,7 +160,7 @@ static void (*handlers[_NSIG])(int sig, struct siginfo *si, mcontext_t *mc) = { static void hard_handler(int sig, siginfo_t *si, void *p) { - struct ucontext *uc = p; + ucontext_t *uc = p; mcontext_t *mc = &uc->uc_mcontext; unsigned long pending = 1UL << sig; diff --git a/arch/unicore32/include/asm/cacheflush.h b/arch/unicore32/include/asm/cacheflush.h index a5e08e2d5d6d..1d9132b66039 100644 --- a/arch/unicore32/include/asm/cacheflush.h +++ b/arch/unicore32/include/asm/cacheflush.h @@ -170,10 +170,8 @@ extern void flush_cache_page(struct vm_area_struct *vma, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) do { } while (0) +#define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_user_range(vma, page, addr, len) \ flush_dcache_page(page) diff --git a/arch/unicore32/include/asm/memory.h b/arch/unicore32/include/asm/memory.h index 3bb0a29fd2d7..66bb9f6525c0 100644 --- a/arch/unicore32/include/asm/memory.h +++ b/arch/unicore32/include/asm/memory.h @@ -20,12 +20,6 @@ #include <mach/memory.h> /* - * Allow for constants defined here to be used from assembly code - * by prepending the UL suffix only with actual C code compilation. - */ -#define UL(x) _AC(x, UL) - -/* * PAGE_OFFSET - the virtual address of the start of the kernel image * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 199e15bd3ec5..ce8b4da07e35 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -122,12 +122,14 @@ struct x86_init_pci { * @guest_late_init: guest late init * @x2apic_available: X2APIC detection * @init_mem_mapping: setup early mappings during init_mem_mapping() + * @init_after_bootmem: guest init after boot allocator is finished */ struct x86_hyper_init { void (*init_platform)(void); void (*guest_late_init)(void); bool (*x2apic_available)(void); void (*init_mem_mapping)(void); + void (*init_after_bootmem)(void); }; /** diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index ebda84a91510..3ab867603e81 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -92,6 +92,7 @@ struct x86_init_ops x86_init __initdata = { .guest_late_init = x86_init_noop, .x2apic_available = bool_x86_init_noop, .init_mem_mapping = x86_init_noop, + .init_after_bootmem = x86_init_noop, }, .acpi = { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 396e1f0151ac..8008db2bddb3 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -778,6 +778,7 @@ void __init mem_init(void) free_all_bootmem(); after_bootmem = 1; + x86_init.hyper.init_after_bootmem(); mem_init_print_info(NULL); printk(KERN_INFO "virtual kernel memory layout:\n" diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index dca9abf2b85c..66de40e45f58 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1185,6 +1185,7 @@ void __init mem_init(void) /* this will put all memory onto the freelists */ free_all_bootmem(); after_bootmem = 1; + x86_init.hyper.init_after_bootmem(); /* * Must be done after boot memory is put on freelist, because here we 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/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c index 1518d2805ae8..27361cbb7ca9 100644 --- a/arch/x86/um/stub_segv.c +++ b/arch/x86/um/stub_segv.c @@ -6,11 +6,12 @@ #include <sysdep/stub.h> #include <sysdep/faultinfo.h> #include <sysdep/mcontext.h> +#include <sys/ucontext.h> void __attribute__ ((__section__ (".__syscall_stub"))) stub_segv_handler(int sig, siginfo_t *info, void *p) { - struct ucontext *uc = p; + ucontext_t *uc = p; GET_FAULTINFO_FROM_MC(*((struct faultinfo *) STUB_DATA), &uc->uc_mcontext); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index d20763472920..486c0a34d00b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -116,6 +116,8 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */ static phys_addr_t xen_pt_base, xen_pt_size __initdata; +static DEFINE_STATIC_KEY_FALSE(xen_struct_pages_ready); + /* * Just beyond the highest usermode address. STACK_TOP_MAX has a * redzone above it, so round it up to a PGD boundary. @@ -155,11 +157,18 @@ void make_lowmem_page_readwrite(void *vaddr) } +/* + * During early boot all page table pages are pinned, but we do not have struct + * pages, so return true until struct pages are ready. + */ static bool xen_page_pinned(void *ptr) { - struct page *page = virt_to_page(ptr); + if (static_branch_likely(&xen_struct_pages_ready)) { + struct page *page = virt_to_page(ptr); - return PagePinned(page); + return PagePinned(page); + } + return true; } static void xen_extend_mmu_update(const struct mmu_update *update) @@ -836,11 +845,6 @@ void xen_mm_pin_all(void) spin_unlock(&pgd_lock); } -/* - * The init_mm pagetable is really pinned as soon as its created, but - * that's before we have page structures to store the bits. So do all - * the book-keeping now. - */ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, enum pt_level level) { @@ -848,8 +852,18 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, return 0; } -static void __init xen_mark_init_mm_pinned(void) +/* + * The init_mm pagetable is really pinned as soon as its created, but + * that's before we have page structures to store the bits. So do all + * the book-keeping now once struct pages for allocated pages are + * initialized. This happens only after free_all_bootmem() is called. + */ +static void __init xen_after_bootmem(void) { + static_branch_enable(&xen_struct_pages_ready); +#ifdef CONFIG_X86_64 + SetPagePinned(virt_to_page(level3_user_vsyscall)); +#endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); } @@ -1623,14 +1637,15 @@ static inline void __set_pfn_prot(unsigned long pfn, pgprot_t prot) static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned level) { - bool pinned = PagePinned(virt_to_page(mm->pgd)); + bool pinned = xen_page_pinned(mm->pgd); trace_xen_mmu_alloc_ptpage(mm, pfn, level, pinned); if (pinned) { struct page *page = pfn_to_page(pfn); - SetPagePinned(page); + if (static_branch_likely(&xen_struct_pages_ready)) + SetPagePinned(page); if (!PageHighMem(page)) { xen_mc_batch(); @@ -2364,9 +2379,7 @@ static void __init xen_post_allocator_init(void) #ifdef CONFIG_X86_64 pv_mmu_ops.write_cr3 = &xen_write_cr3; - SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif - xen_mark_init_mm_pinned(); } static void xen_leave_lazy_mmu(void) @@ -2450,6 +2463,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { void __init xen_init_mmu_ops(void) { x86_init.paging.pagetable_init = xen_pagetable_init; + x86_init.hyper.init_after_bootmem = xen_after_bootmem; pv_mmu_ops = xen_mmu_ops; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index c0c756c76afe..2e20ae2fa2d6 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -425,6 +425,7 @@ static void xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */ * data back is to call: */ tick_nohz_idle_enter(); + tick_nohz_idle_stop_tick_protected(); cpuhp_online_idle(CPUHP_AP_ONLINE_IDLE); } diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 3e9d01ada81f..58f29a9d895d 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -57,6 +57,7 @@ #define MAP_NONBLOCK 0x20000 /* do not block on IO */ #define MAP_STACK 0x40000 /* give out an address that is best suited for process/thread stacks */ #define MAP_HUGETLB 0x80000 /* create a huge page mapping */ +#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ #ifdef CONFIG_MMAP_ALLOW_UNINITIALIZED # define MAP_UNINITIALIZED 0x4000000 /* For anonymous mmap, memory could be * uninitialized */ diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 9e702bc4960f..7a3a541046ed 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -34,6 +34,7 @@ struct iort_its_msi_chip { struct list_head list; struct fwnode_handle *fw_node; + phys_addr_t base_addr; u32 translation_id; }; @@ -156,14 +157,16 @@ static LIST_HEAD(iort_msi_chip_list); static DEFINE_SPINLOCK(iort_msi_chip_lock); /** - * iort_register_domain_token() - register domain token and related ITS ID - * to the list from where we can get it back later on. + * iort_register_domain_token() - register domain token along with related + * ITS ID and base address to the list from where we can get it back later on. * @trans_id: ITS ID. + * @base: ITS base address. * @fw_node: Domain token. * * Returns: 0 on success, -ENOMEM if no memory when allocating list element */ -int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node) +int iort_register_domain_token(int trans_id, phys_addr_t base, + struct fwnode_handle *fw_node) { struct iort_its_msi_chip *its_msi_chip; @@ -173,6 +176,7 @@ int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node) its_msi_chip->fw_node = fw_node; its_msi_chip->translation_id = trans_id; + its_msi_chip->base_addr = base; spin_lock(&iort_msi_chip_lock); list_add(&its_msi_chip->list, &iort_msi_chip_list); @@ -569,6 +573,24 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id) return -ENODEV; } +static int __maybe_unused iort_find_its_base(u32 its_id, phys_addr_t *base) +{ + struct iort_its_msi_chip *its_msi_chip; + int ret = -ENODEV; + + spin_lock(&iort_msi_chip_lock); + list_for_each_entry(its_msi_chip, &iort_msi_chip_list, list) { + if (its_msi_chip->translation_id == its_id) { + *base = its_msi_chip->base_addr; + ret = 0; + break; + } + } + spin_unlock(&iort_msi_chip_lock); + + return ret; +} + /** * iort_dev_find_its_id() - Find the ITS identifier for a device * @dev: The device. @@ -754,6 +776,24 @@ static inline bool iort_iommu_driver_enabled(u8 type) } #ifdef CONFIG_IOMMU_API +static struct acpi_iort_node *iort_get_msi_resv_iommu(struct device *dev) +{ + struct acpi_iort_node *iommu; + struct iommu_fwspec *fwspec = dev->iommu_fwspec; + + iommu = iort_get_iort_node(fwspec->iommu_fwnode); + + if (iommu && (iommu->type == ACPI_IORT_NODE_SMMU_V3)) { + struct acpi_iort_smmu_v3 *smmu; + + smmu = (struct acpi_iort_smmu_v3 *)iommu->node_data; + if (smmu->model == ACPI_IORT_SMMU_V3_HISILICON_HI161X) + return iommu; + } + + return NULL; +} + static inline const struct iommu_ops *iort_fwspec_iommu_ops( struct iommu_fwspec *fwspec) { @@ -770,6 +810,69 @@ static inline int iort_add_device_replay(const struct iommu_ops *ops, return err; } + +/** + * iort_iommu_msi_get_resv_regions - Reserved region driver helper + * @dev: Device from iommu_get_resv_regions() + * @head: Reserved region list from iommu_get_resv_regions() + * + * Returns: Number of msi reserved regions on success (0 if platform + * doesn't require the reservation or no associated msi regions), + * appropriate error value otherwise. The ITS interrupt translation + * spaces (ITS_base + SZ_64K, SZ_64K) associated with the device + * are the msi reserved regions. + */ +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) +{ + struct acpi_iort_its_group *its; + struct acpi_iort_node *iommu_node, *its_node = NULL; + int i, resv = 0; + + iommu_node = iort_get_msi_resv_iommu(dev); + if (!iommu_node) + return 0; + + /* + * Current logic to reserve ITS regions relies on HW topologies + * where a given PCI or named component maps its IDs to only one + * ITS group; if a PCI or named component can map its IDs to + * different ITS groups through IORT mappings this function has + * to be reworked to ensure we reserve regions for all ITS groups + * a given PCI or named component may map IDs to. + */ + + for (i = 0; i < dev->iommu_fwspec->num_ids; i++) { + its_node = iort_node_map_id(iommu_node, + dev->iommu_fwspec->ids[i], + NULL, IORT_MSI_TYPE); + if (its_node) + break; + } + + if (!its_node) + return 0; + + /* Move to ITS specific data */ + its = (struct acpi_iort_its_group *)its_node->node_data; + + for (i = 0; i < its->its_count; i++) { + phys_addr_t base; + + if (!iort_find_its_base(its->identifiers[i], &base)) { + int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO; + struct iommu_resv_region *region; + + region = iommu_alloc_resv_region(base + SZ_64K, SZ_64K, + prot, IOMMU_RESV_MSI); + if (region) { + list_add_tail(®ion->list, head); + resv++; + } + } + } + + return (resv == its->its_count) ? resv : -ENODEV; +} #else static inline const struct iommu_ops *iort_fwspec_iommu_ops( struct iommu_fwspec *fwspec) @@ -777,6 +880,8 @@ static inline const struct iommu_ops *iort_fwspec_iommu_ops( static inline int iort_add_device_replay(const struct iommu_ops *ops, struct device *dev) { return 0; } +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) +{ return 0; } #endif static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node, diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 79fcd2bae96b..bffe8616bd55 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -837,11 +837,8 @@ int __init memory_dev_init(void) * during boot and have been initialized */ mutex_lock(&mem_sysfs_mutex); - for (i = 0; i < NR_MEM_SECTIONS; i += sections_per_block) { - /* Don't iterate over sections we know are !present: */ - if (i > __highest_present_section_nr) - break; - + for (i = 0; i <= __highest_present_section_nr; + i += sections_per_block) { err = add_memory_block(i); if (!ret) ret = err; diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index c6ebc88a7d8d..72a2975499db 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -202,6 +202,7 @@ static int __init armada37xx_cpufreq_driver_init(void) cur_frequency = clk_get_rate(clk); if (!cur_frequency) { dev_err(cpu_dev, "Failed to get clock rate for CPU\n"); + clk_put(clk); return -EINVAL; } @@ -210,6 +211,7 @@ static int __init armada37xx_cpufreq_driver_init(void) return -EINVAL; armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider); + clk_put(clk); for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR; load_lvl++) { diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 8300a9fcb80c..bc5fc1630876 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -162,14 +162,23 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) cpu->perf_caps.highest_perf; policy->cpuinfo.max_freq = cppc_dmi_max_khz; - policy->cpuinfo.transition_latency = cppc_get_transition_latency(cpu_num); policy->transition_delay_us = cppc_get_transition_latency(cpu_num) / NSEC_PER_USEC; policy->shared_type = cpu->shared_type; - if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) + if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) { + int i; + cpumask_copy(policy->cpus, cpu->shared_cpu_map); - else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) { + + for_each_cpu(i, policy->cpus) { + if (unlikely(i == policy->cpu)) + continue; + + memcpy(&all_cpu_data[i]->perf_caps, &cpu->perf_caps, + sizeof(cpu->perf_caps)); + } + } else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) { /* Support only SW_ANY for now. */ pr_debug("Unsupported CPU co-ord type\n"); return -EFAULT; diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index 10e119ae66dd..3a8cc99e6815 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -352,20 +352,6 @@ static int set_freq_table_sorted(struct cpufreq_policy *policy) return 0; } -int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table) -{ - int ret; - - ret = cpufreq_frequency_table_cpuinfo(policy, table); - if (ret) - return ret; - - policy->freq_table = table; - return 0; -} -EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show); - int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy) { int ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 6d084c61ee25..17e566afbb41 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -26,7 +26,6 @@ #include <linux/sysfs.h> #include <linux/types.h> #include <linux/fs.h> -#include <linux/debugfs.h> #include <linux/acpi.h> #include <linux/vmalloc.h> #include <trace/events/power.h> diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 959a1dbe3835..b4dbc77459b6 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -159,13 +159,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) priv->domain_id = handle->perf_ops->device_domain_id(cpu_dev); policy->driver_data = priv; - - ret = cpufreq_table_validate_and_show(policy, freq_table); - if (ret) { - dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__, - ret); - goto out_free_cpufreq_table; - } + policy->freq_table = freq_table; /* SCMI allows DVFS request for any domain from any CPU */ policy->dvfs_possible_from_any_cpu = true; @@ -179,8 +173,6 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy) policy->fast_switch_possible = true; return 0; -out_free_cpufreq_table: - dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table); out_free_priv: kfree(priv); out_free_opp: diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index a099b7bf74cd..6ba709b6f095 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -304,7 +304,7 @@ static struct platform_driver ti_cpufreq_driver = { .name = "ti-cpufreq", }, }; -module_platform_driver(ti_cpufreq_driver); +builtin_platform_driver(ti_cpufreq_driver); MODULE_DESCRIPTION("TI CPUFreq/OPP hw-supported driver"); MODULE_AUTHOR("Dave Gerlach <d-gerlach@ti.com>"); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0003e9a02637..6df894d65d9e 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -272,12 +272,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, * * @drv: the cpuidle driver * @dev: the cpuidle device + * @stop_tick: indication on whether or not to stop the tick * * Returns the index of the idle state. The return value must not be negative. + * + * The memory location pointed to by @stop_tick is expected to be written the + * 'false' boolean value if the scheduler tick should not be stopped before + * entering the returned state. */ -int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) +int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) { - return cpuidle_curr_governor->select(drv, dev); + return cpuidle_curr_governor->select(drv, dev, stop_tick); } /** diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index 1ad8745fd6d6..b24883f85c99 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/drivers/cpuidle/governors/ladder.c @@ -63,9 +63,10 @@ static inline void ladder_do_selection(struct ladder_device *ldev, * ladder_select_state - selects the next state to enter * @drv: cpuidle driver * @dev: the CPU + * @dummy: not used */ static int ladder_select_state(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, bool *dummy) { struct ladder_device *ldev = this_cpu_ptr(&ladder_devices); struct device *device = get_cpu_device(dev->cpu); diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index aa390404e85f..1bfe03ceb236 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -123,6 +123,7 @@ struct menu_device { int last_state_idx; int needs_update; + int tick_wakeup; unsigned int next_timer_us; unsigned int predicted_us; @@ -279,8 +280,10 @@ again: * menu_select - selects the next idle state to enter * @drv: cpuidle driver containing state data * @dev: the CPU + * @stop_tick: indication on whether or not to stop the tick */ -static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) +static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) { struct menu_device *data = this_cpu_ptr(&menu_devices); struct device *device = get_cpu_device(dev->cpu); @@ -292,6 +295,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) unsigned int expected_interval; unsigned long nr_iowaiters, cpu_load; int resume_latency = dev_pm_qos_raw_read_value(device); + ktime_t delta_next; if (data->needs_update) { menu_update(drv, dev); @@ -303,11 +307,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) latency_req = resume_latency; /* Special case when user has set very strict latency requirement */ - if (unlikely(latency_req == 0)) + if (unlikely(latency_req == 0)) { + *stop_tick = false; return 0; + } /* determine the expected residency time, round up */ - data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length()); + data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); get_iowait_load(&nr_iowaiters, &cpu_load); data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); @@ -346,14 +352,30 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) */ data->predicted_us = min(data->predicted_us, expected_interval); - /* - * Use the performance multiplier and the user-configurable - * latency_req to determine the maximum exit latency. - */ - interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); - if (latency_req > interactivity_req) - latency_req = interactivity_req; + if (tick_nohz_tick_stopped()) { + /* + * If the tick is already stopped, the cost of possible short + * idle duration misprediction is much higher, because the CPU + * may be stuck in a shallow idle state for a long time as a + * result of it. In that case say we might mispredict and try + * to force the CPU into a state for which we would have stopped + * the tick, unless a timer is going to expire really soon + * anyway. + */ + if (data->predicted_us < TICK_USEC) + data->predicted_us = min_t(unsigned int, TICK_USEC, + ktime_to_us(delta_next)); + } else { + /* + * Use the performance multiplier and the user-configurable + * latency_req to determine the maximum exit latency. + */ + interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); + if (latency_req > interactivity_req) + latency_req = interactivity_req; + } + expected_interval = data->predicted_us; /* * Find the idle state with the lowest power while satisfying * our constraints. @@ -369,15 +391,52 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) idx = i; /* first enabled state */ if (s->target_residency > data->predicted_us) break; - if (s->exit_latency > latency_req) + if (s->exit_latency > latency_req) { + /* + * If we break out of the loop for latency reasons, use + * the target residency of the selected state as the + * expected idle duration so that the tick is retained + * as long as that target residency is low enough. + */ + expected_interval = drv->states[idx].target_residency; break; - + } idx = i; } if (idx == -1) idx = 0; /* No states enabled. Must use 0. */ + /* + * Don't stop the tick if the selected state is a polling one or if the + * expected idle duration is shorter than the tick period length. + */ + if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || + expected_interval < TICK_USEC) { + unsigned int delta_next_us = ktime_to_us(delta_next); + + *stop_tick = false; + + if (!tick_nohz_tick_stopped() && idx > 0 && + drv->states[idx].target_residency > delta_next_us) { + /* + * The tick is not going to be stopped and the target + * residency of the state to be returned is not within + * the time until the next timer event including the + * tick, so try to correct that. + */ + for (i = idx - 1; i >= 0; i--) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + idx = i; + if (drv->states[i].target_residency <= delta_next_us) + break; + } + } + } + data->last_state_idx = idx; return data->last_state_idx; @@ -397,6 +456,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index) data->last_state_idx = index; data->needs_update = 1; + data->tick_wakeup = tick_nohz_idle_got_tick(); } /** @@ -427,14 +487,27 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * assume the state was never reached and the exit latency is 0. */ - /* measured value */ - measured_us = cpuidle_get_last_residency(dev); - - /* Deduct exit latency */ - if (measured_us > 2 * target->exit_latency) - measured_us -= target->exit_latency; - else - measured_us /= 2; + if (data->tick_wakeup && data->next_timer_us > TICK_USEC) { + /* + * The nohz code said that there wouldn't be any events within + * the tick boundary (if the tick was stopped), but the idle + * duration predictor had a differing opinion. Since the CPU + * was woken up by a tick (that wasn't stopped after all), the + * predictor was not quite right, so assume that the CPU could + * have been idle long (but not forever) to help the idle + * duration predictor do a better job next time. + */ + measured_us = 9 * MAX_INTERESTING / 10; + } else { + /* measured value */ + measured_us = cpuidle_get_last_residency(dev); + + /* Deduct exit latency */ + if (measured_us > 2 * target->exit_latency) + measured_us -= target->exit_latency; + else + measured_us /= 2; + } /* Make sure our coefficients do not exceed unity */ if (measured_us > data->next_timer_us) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 83819d0cbf90..2a99f0f14795 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -81,11 +81,12 @@ */ #define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38)) -static DEFINE_RWLOCK(amd_iommu_devtable_lock); +static DEFINE_SPINLOCK(amd_iommu_devtable_lock); +static DEFINE_SPINLOCK(pd_bitmap_lock); +static DEFINE_SPINLOCK(iommu_table_lock); /* List of all available dev_data structures */ -static LIST_HEAD(dev_data_list); -static DEFINE_SPINLOCK(dev_data_list_lock); +static LLIST_HEAD(dev_data_list); LIST_HEAD(ioapic_map); LIST_HEAD(hpet_map); @@ -204,40 +205,33 @@ static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; - unsigned long flags; dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL); if (!dev_data) return NULL; dev_data->devid = devid; - - spin_lock_irqsave(&dev_data_list_lock, flags); - list_add_tail(&dev_data->dev_data_list, &dev_data_list); - spin_unlock_irqrestore(&dev_data_list_lock, flags); - ratelimit_default_init(&dev_data->rs); + llist_add(&dev_data->dev_data_list, &dev_data_list); return dev_data; } static struct iommu_dev_data *search_dev_data(u16 devid) { struct iommu_dev_data *dev_data; - unsigned long flags; + struct llist_node *node; - spin_lock_irqsave(&dev_data_list_lock, flags); - list_for_each_entry(dev_data, &dev_data_list, dev_data_list) { + if (llist_empty(&dev_data_list)) + return NULL; + + node = dev_data_list.first; + llist_for_each_entry(dev_data, node, dev_data_list) { if (dev_data->devid == devid) - goto out_unlock; + return dev_data; } - dev_data = NULL; - -out_unlock: - spin_unlock_irqrestore(&dev_data_list_lock, flags); - - return dev_data; + return NULL; } static int __last_alias(struct pci_dev *pdev, u16 alias, void *data) @@ -311,6 +305,8 @@ static struct iommu_dev_data *find_dev_data(u16 devid) if (dev_data == NULL) { dev_data = alloc_dev_data(devid); + if (!dev_data) + return NULL; if (translation_pre_enabled(iommu)) dev_data->defer_attach = true; @@ -548,6 +544,7 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id, static void iommu_print_event(struct amd_iommu *iommu, void *__evt) { + struct device *dev = iommu->iommu.dev; int type, devid, domid, flags; volatile u32 *event = __evt; int count = 0; @@ -574,53 +571,53 @@ retry: amd_iommu_report_page_fault(devid, domid, address, flags); return; } else { - printk(KERN_ERR "AMD-Vi: Event logged ["); + dev_err(dev, "AMD-Vi: Event logged ["); } switch (type) { case EVENT_TYPE_ILL_DEV: - printk("ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); + dev_err(dev, "ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x " + "address=0x%016llx flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address, flags); dump_dte_entry(devid); break; case EVENT_TYPE_DEV_TAB_ERR: - printk("DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); + dev_err(dev, "DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x " + "address=0x%016llx flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address, flags); break; case EVENT_TYPE_PAGE_TAB_ERR: - printk("PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x " - "domain=0x%04x address=0x%016llx flags=0x%04x]\n", - PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), - domid, address, flags); + dev_err(dev, "PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x " + "domain=0x%04x address=0x%016llx flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + domid, address, flags); break; case EVENT_TYPE_ILL_CMD: - printk("ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address); + dev_err(dev, "ILLEGAL_COMMAND_ERROR address=0x%016llx]\n", address); dump_command(address); break; case EVENT_TYPE_CMD_HARD_ERR: - printk("COMMAND_HARDWARE_ERROR address=0x%016llx " - "flags=0x%04x]\n", address, flags); + dev_err(dev, "COMMAND_HARDWARE_ERROR address=0x%016llx " + "flags=0x%04x]\n", address, flags); break; case EVENT_TYPE_IOTLB_INV_TO: - printk("IOTLB_INV_TIMEOUT device=%02x:%02x.%x " - "address=0x%016llx]\n", - PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address); + dev_err(dev, "IOTLB_INV_TIMEOUT device=%02x:%02x.%x " + "address=0x%016llx]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address); break; case EVENT_TYPE_INV_DEV_REQ: - printk("INVALID_DEVICE_REQUEST device=%02x:%02x.%x " - "address=0x%016llx flags=0x%04x]\n", - PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), - address, flags); + dev_err(dev, "INVALID_DEVICE_REQUEST device=%02x:%02x.%x " + "address=0x%016llx flags=0x%04x]\n", + PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid), + address, flags); break; default: - printk(KERN_ERR "UNKNOWN type=0x%02x event[0]=0x%08x " - "event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n", - type, event[0], event[1], event[2], event[3]); + dev_err(dev, KERN_ERR "UNKNOWN event[0]=0x%08x event[1]=0x%08x " + "event[2]=0x%08x event[3]=0x%08x\n", + event[0], event[1], event[2], event[3]); } memset(__evt, 0, 4 * sizeof(u32)); @@ -1057,9 +1054,9 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu, unsigned long flags; int ret; - spin_lock_irqsave(&iommu->lock, flags); + raw_spin_lock_irqsave(&iommu->lock, flags); ret = __iommu_queue_command_sync(iommu, cmd, sync); - spin_unlock_irqrestore(&iommu->lock, flags); + raw_spin_unlock_irqrestore(&iommu->lock, flags); return ret; } @@ -1085,7 +1082,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu) build_completion_wait(&cmd, (u64)&iommu->cmd_sem); - spin_lock_irqsave(&iommu->lock, flags); + raw_spin_lock_irqsave(&iommu->lock, flags); iommu->cmd_sem = 0; @@ -1096,7 +1093,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu) ret = wait_on_sem(&iommu->cmd_sem); out_unlock: - spin_unlock_irqrestore(&iommu->lock, flags); + raw_spin_unlock_irqrestore(&iommu->lock, flags); return ret; } @@ -1606,29 +1603,26 @@ static void del_domain_from_list(struct protection_domain *domain) static u16 domain_id_alloc(void) { - unsigned long flags; int id; - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock(&pd_bitmap_lock); id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID); BUG_ON(id == 0); if (id > 0 && id < MAX_DOMAIN_ID) __set_bit(id, amd_iommu_pd_alloc_bitmap); else id = 0; - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock(&pd_bitmap_lock); return id; } static void domain_id_free(int id) { - unsigned long flags; - - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock(&pd_bitmap_lock); if (id > 0 && id < MAX_DOMAIN_ID) __clear_bit(id, amd_iommu_pd_alloc_bitmap); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock(&pd_bitmap_lock); } #define DEFINE_FREE_PT_FN(LVL, FN) \ @@ -2104,9 +2098,9 @@ static int attach_device(struct device *dev, } skip_ats_check: - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock_irqsave(&amd_iommu_devtable_lock, flags); ret = __attach_device(dev_data, domain); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags); /* * We might boot into a crash-kernel here. The crashed kernel @@ -2156,9 +2150,9 @@ static void detach_device(struct device *dev) domain = dev_data->domain; /* lock device table */ - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock_irqsave(&amd_iommu_devtable_lock, flags); __detach_device(dev_data); - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags); if (!dev_is_pci(dev)) return; @@ -2795,7 +2789,7 @@ static void cleanup_domain(struct protection_domain *domain) struct iommu_dev_data *entry; unsigned long flags; - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock_irqsave(&amd_iommu_devtable_lock, flags); while (!list_empty(&domain->dev_list)) { entry = list_first_entry(&domain->dev_list, @@ -2803,7 +2797,7 @@ static void cleanup_domain(struct protection_domain *domain) __detach_device(entry); } - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags); } static void protection_domain_free(struct protection_domain *domain) @@ -3025,15 +3019,12 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, size_t unmap_size; if (domain->mode == PAGE_MODE_NONE) - return -EINVAL; + return 0; mutex_lock(&domain->api_lock); unmap_size = iommu_unmap_page(domain, iova, page_size); mutex_unlock(&domain->api_lock); - domain_flush_tlb_pde(domain); - domain_flush_complete(domain); - return unmap_size; } @@ -3151,6 +3142,19 @@ static bool amd_iommu_is_attach_deferred(struct iommu_domain *domain, return dev_data->defer_attach; } +static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain) +{ + struct protection_domain *dom = to_pdomain(domain); + + domain_flush_tlb_pde(dom); + domain_flush_complete(dom); +} + +static void amd_iommu_iotlb_range_add(struct iommu_domain *domain, + unsigned long iova, size_t size) +{ +} + const struct iommu_ops amd_iommu_ops = { .capable = amd_iommu_capable, .domain_alloc = amd_iommu_domain_alloc, @@ -3169,6 +3173,9 @@ const struct iommu_ops amd_iommu_ops = { .apply_resv_region = amd_iommu_apply_resv_region, .is_attach_deferred = amd_iommu_is_attach_deferred, .pgsize_bitmap = AMD_IOMMU_PGSIZES, + .flush_iotlb_all = amd_iommu_flush_iotlb_all, + .iotlb_range_add = amd_iommu_iotlb_range_add, + .iotlb_sync = amd_iommu_flush_iotlb_all, }; /***************************************************************************** @@ -3570,14 +3577,62 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table) amd_iommu_dev_table[devid].data[2] = dte; } -static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic) +static struct irq_remap_table *get_irq_table(u16 devid) +{ + struct irq_remap_table *table; + + if (WARN_ONCE(!amd_iommu_rlookup_table[devid], + "%s: no iommu for devid %x\n", __func__, devid)) + return NULL; + + table = irq_lookup_table[devid]; + if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid)) + return NULL; + + return table; +} + +static struct irq_remap_table *__alloc_irq_table(void) +{ + struct irq_remap_table *table; + + table = kzalloc(sizeof(*table), GFP_KERNEL); + if (!table) + return NULL; + + table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL); + if (!table->table) { + kfree(table); + return NULL; + } + raw_spin_lock_init(&table->lock); + + if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) + memset(table->table, 0, + MAX_IRQS_PER_TABLE * sizeof(u32)); + else + memset(table->table, 0, + (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2))); + return table; +} + +static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid, + struct irq_remap_table *table) +{ + irq_lookup_table[devid] = table; + set_dte_irq_entry(devid, table); + iommu_flush_dte(iommu, devid); +} + +static struct irq_remap_table *alloc_irq_table(u16 devid) { struct irq_remap_table *table = NULL; + struct irq_remap_table *new_table = NULL; struct amd_iommu *iommu; unsigned long flags; u16 alias; - write_lock_irqsave(&amd_iommu_devtable_lock, flags); + spin_lock_irqsave(&iommu_table_lock, flags); iommu = amd_iommu_rlookup_table[devid]; if (!iommu) @@ -3590,60 +3645,45 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic) alias = amd_iommu_alias_table[devid]; table = irq_lookup_table[alias]; if (table) { - irq_lookup_table[devid] = table; - set_dte_irq_entry(devid, table); - iommu_flush_dte(iommu, devid); - goto out; + set_remap_table_entry(iommu, devid, table); + goto out_wait; } + spin_unlock_irqrestore(&iommu_table_lock, flags); /* Nothing there yet, allocate new irq remapping table */ - table = kzalloc(sizeof(*table), GFP_ATOMIC); - if (!table) - goto out_unlock; - - /* Initialize table spin-lock */ - spin_lock_init(&table->lock); + new_table = __alloc_irq_table(); + if (!new_table) + return NULL; - if (ioapic) - /* Keep the first 32 indexes free for IOAPIC interrupts */ - table->min_index = 32; + spin_lock_irqsave(&iommu_table_lock, flags); - table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC); - if (!table->table) { - kfree(table); - table = NULL; + table = irq_lookup_table[devid]; + if (table) goto out_unlock; - } - if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir)) - memset(table->table, 0, - MAX_IRQS_PER_TABLE * sizeof(u32)); - else - memset(table->table, 0, - (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2))); - - if (ioapic) { - int i; - - for (i = 0; i < 32; ++i) - iommu->irte_ops->set_allocated(table, i); + table = irq_lookup_table[alias]; + if (table) { + set_remap_table_entry(iommu, devid, table); + goto out_wait; } - irq_lookup_table[devid] = table; - set_dte_irq_entry(devid, table); - iommu_flush_dte(iommu, devid); - if (devid != alias) { - irq_lookup_table[alias] = table; - set_dte_irq_entry(alias, table); - iommu_flush_dte(iommu, alias); - } + table = new_table; + new_table = NULL; -out: + set_remap_table_entry(iommu, devid, table); + if (devid != alias) + set_remap_table_entry(iommu, alias, table); + +out_wait: iommu_completion_wait(iommu); out_unlock: - write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); + spin_unlock_irqrestore(&iommu_table_lock, flags); + if (new_table) { + kmem_cache_free(amd_iommu_irq_cache, new_table->table); + kfree(new_table); + } return table; } @@ -3657,14 +3697,14 @@ static int alloc_irq_index(u16 devid, int count, bool align) if (!iommu) return -ENODEV; - table = get_irq_table(devid, false); + table = alloc_irq_table(devid); if (!table) return -ENODEV; if (align) alignment = roundup_pow_of_two(count); - spin_lock_irqsave(&table->lock, flags); + raw_spin_lock_irqsave(&table->lock, flags); /* Scan table for free entries */ for (index = ALIGN(table->min_index, alignment), c = 0; @@ -3691,7 +3731,7 @@ static int alloc_irq_index(u16 devid, int count, bool align) index = -ENOSPC; out: - spin_unlock_irqrestore(&table->lock, flags); + raw_spin_unlock_irqrestore(&table->lock, flags); return index; } @@ -3708,11 +3748,11 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte, if (iommu == NULL) return -EINVAL; - table = get_irq_table(devid, false); + table = get_irq_table(devid); if (!table) return -ENOMEM; - spin_lock_irqsave(&table->lock, flags); + raw_spin_lock_irqsave(&table->lock, flags); entry = (struct irte_ga *)table->table; entry = &entry[index]; @@ -3723,7 +3763,7 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte, if (data) data->ref = entry; - spin_unlock_irqrestore(&table->lock, flags); + raw_spin_unlock_irqrestore(&table->lock, flags); iommu_flush_irt(iommu, devid); iommu_completion_wait(iommu); @@ -3741,13 +3781,13 @@ static int modify_irte(u16 devid, int index, union irte *irte) if (iommu == NULL) return -EINVAL; - table = get_irq_table(devid, false); + table = get_irq_table(devid); if (!table) return -ENOMEM; - spin_lock_irqsave(&table->lock, flags); + raw_spin_lock_irqsave(&table->lock, flags); table->table[index] = irte->val; - spin_unlock_irqrestore(&table->lock, flags); + raw_spin_unlock_irqrestore(&table->lock, flags); iommu_flush_irt(iommu, devid); iommu_completion_wait(iommu); @@ -3765,13 +3805,13 @@ static void free_irte(u16 devid, int index) if (iommu == NULL) return; - table = get_irq_table(devid, false); + table = get_irq_table(devid); if (!table) return; - spin_lock_irqsave(&table->lock, flags); + raw_spin_lock_irqsave(&table->lock, flags); iommu->irte_ops->clear_allocated(table, index); - spin_unlock_irqrestore(&table->lock, flags); + raw_spin_unlock_irqrestore(&table->lock, flags); iommu_flush_irt(iommu, devid); iommu_completion_wait(iommu); @@ -3852,10 +3892,8 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index, u8 vector, u32 dest_apicid) { struct irte_ga *irte = (struct irte_ga *) entry; - struct iommu_dev_data *dev_data = search_dev_data(devid); - if (!dev_data || !dev_data->use_vapic || - !irte->lo.fields_remap.guest_mode) { + if (!irte->lo.fields_remap.guest_mode) { irte->hi.fields.vector = vector; irte->lo.fields_remap.destination = dest_apicid; modify_irte_ga(devid, index, irte, NULL); @@ -4061,7 +4099,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, struct amd_ir_data *data = NULL; struct irq_cfg *cfg; int i, ret, devid; - int index = -1; + int index; if (!info) return -EINVAL; @@ -4085,10 +4123,26 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq, return ret; if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) { - if (get_irq_table(devid, true)) + struct irq_remap_table *table; + struct amd_iommu *iommu; + + table = alloc_irq_table(devid); + if (table) { + if (!table->min_index) { + /* + * Keep the first 32 indexes free for IOAPIC + * interrupts. + */ + table->min_index = 32; + iommu = amd_iommu_rlookup_table[devid]; + for (i = 0; i < 32; ++i) + iommu->irte_ops->set_allocated(table, i); + } + WARN_ON(table->min_index != 32); index = info->ioapic_pin; - else - ret = -ENOMEM; + } else { + index = -ENOMEM; + } } else { bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI); @@ -4354,7 +4408,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data) { unsigned long flags; struct amd_iommu *iommu; - struct irq_remap_table *irt; + struct irq_remap_table *table; struct amd_ir_data *ir_data = (struct amd_ir_data *)data; int devid = ir_data->irq_2_irte.devid; struct irte_ga *entry = (struct irte_ga *) ir_data->entry; @@ -4368,11 +4422,11 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data) if (!iommu) return -ENODEV; - irt = get_irq_table(devid, false); - if (!irt) + table = get_irq_table(devid); + if (!table) return -ENODEV; - spin_lock_irqsave(&irt->lock, flags); + raw_spin_lock_irqsave(&table->lock, flags); if (ref->lo.fields_vapic.guest_mode) { if (cpu >= 0) @@ -4381,7 +4435,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data) barrier(); } - spin_unlock_irqrestore(&irt->lock, flags); + raw_spin_unlock_irqrestore(&table->lock, flags); iommu_flush_irt(iommu, devid); iommu_completion_wait(iommu); diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c index 4e4a615bf13f..904c575d1677 100644 --- a/drivers/iommu/amd_iommu_init.c +++ b/drivers/iommu/amd_iommu_init.c @@ -1474,7 +1474,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h) { int ret; - spin_lock_init(&iommu->lock); + raw_spin_lock_init(&iommu->lock); /* Add IOMMU to internal data structures */ list_add_tail(&iommu->list, &amd_iommu_list); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 6a877ebd058b..1c9b080276c9 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -408,7 +408,7 @@ extern bool amd_iommu_iotlb_sup; #define IRQ_TABLE_ALIGNMENT 128 struct irq_remap_table { - spinlock_t lock; + raw_spinlock_t lock; unsigned min_index; u32 *table; }; @@ -490,7 +490,7 @@ struct amd_iommu { int index; /* locks the accesses to the hardware */ - spinlock_t lock; + raw_spinlock_t lock; /* Pointer to PCI device of this IOMMU */ struct pci_dev *dev; @@ -627,7 +627,7 @@ struct devid_map { */ struct iommu_dev_data { struct list_head list; /* For domain->dev_list */ - struct list_head dev_data_list; /* For global dev_data_list */ + struct llist_node dev_data_list; /* For global dev_data_list */ struct protection_domain *domain; /* Domain the device is bound to */ u16 devid; /* PCI Device ID */ u16 alias; /* Alias Device ID */ diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 3f2f1fc68b52..1d647104bccc 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -22,6 +22,8 @@ #include <linux/acpi.h> #include <linux/acpi_iort.h> +#include <linux/bitfield.h> +#include <linux/bitops.h> #include <linux/delay.h> #include <linux/dma-iommu.h> #include <linux/err.h> @@ -43,18 +45,15 @@ /* MMIO registers */ #define ARM_SMMU_IDR0 0x0 -#define IDR0_ST_LVL_SHIFT 27 -#define IDR0_ST_LVL_MASK 0x3 -#define IDR0_ST_LVL_2LVL (1 << IDR0_ST_LVL_SHIFT) -#define IDR0_STALL_MODEL_SHIFT 24 -#define IDR0_STALL_MODEL_MASK 0x3 -#define IDR0_STALL_MODEL_STALL (0 << IDR0_STALL_MODEL_SHIFT) -#define IDR0_STALL_MODEL_FORCE (2 << IDR0_STALL_MODEL_SHIFT) -#define IDR0_TTENDIAN_SHIFT 21 -#define IDR0_TTENDIAN_MASK 0x3 -#define IDR0_TTENDIAN_LE (2 << IDR0_TTENDIAN_SHIFT) -#define IDR0_TTENDIAN_BE (3 << IDR0_TTENDIAN_SHIFT) -#define IDR0_TTENDIAN_MIXED (0 << IDR0_TTENDIAN_SHIFT) +#define IDR0_ST_LVL GENMASK(28, 27) +#define IDR0_ST_LVL_2LVL 1 +#define IDR0_STALL_MODEL GENMASK(25, 24) +#define IDR0_STALL_MODEL_STALL 0 +#define IDR0_STALL_MODEL_FORCE 2 +#define IDR0_TTENDIAN GENMASK(22, 21) +#define IDR0_TTENDIAN_MIXED 0 +#define IDR0_TTENDIAN_LE 2 +#define IDR0_TTENDIAN_BE 3 #define IDR0_CD2L (1 << 19) #define IDR0_VMID16 (1 << 18) #define IDR0_PRI (1 << 16) @@ -64,10 +63,9 @@ #define IDR0_ATS (1 << 10) #define IDR0_HYP (1 << 9) #define IDR0_COHACC (1 << 4) -#define IDR0_TTF_SHIFT 2 -#define IDR0_TTF_MASK 0x3 -#define IDR0_TTF_AARCH64 (2 << IDR0_TTF_SHIFT) -#define IDR0_TTF_AARCH32_64 (3 << IDR0_TTF_SHIFT) +#define IDR0_TTF GENMASK(3, 2) +#define IDR0_TTF_AARCH64 2 +#define IDR0_TTF_AARCH32_64 3 #define IDR0_S1P (1 << 1) #define IDR0_S2P (1 << 0) @@ -75,31 +73,27 @@ #define IDR1_TABLES_PRESET (1 << 30) #define IDR1_QUEUES_PRESET (1 << 29) #define IDR1_REL (1 << 28) -#define IDR1_CMDQ_SHIFT 21 -#define IDR1_CMDQ_MASK 0x1f -#define IDR1_EVTQ_SHIFT 16 -#define IDR1_EVTQ_MASK 0x1f -#define IDR1_PRIQ_SHIFT 11 -#define IDR1_PRIQ_MASK 0x1f -#define IDR1_SSID_SHIFT 6 -#define IDR1_SSID_MASK 0x1f -#define IDR1_SID_SHIFT 0 -#define IDR1_SID_MASK 0x3f +#define IDR1_CMDQS GENMASK(25, 21) +#define IDR1_EVTQS GENMASK(20, 16) +#define IDR1_PRIQS GENMASK(15, 11) +#define IDR1_SSIDSIZE GENMASK(10, 6) +#define IDR1_SIDSIZE GENMASK(5, 0) #define ARM_SMMU_IDR5 0x14 -#define IDR5_STALL_MAX_SHIFT 16 -#define IDR5_STALL_MAX_MASK 0xffff +#define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) #define IDR5_GRAN16K (1 << 5) #define IDR5_GRAN4K (1 << 4) -#define IDR5_OAS_SHIFT 0 -#define IDR5_OAS_MASK 0x7 -#define IDR5_OAS_32_BIT (0 << IDR5_OAS_SHIFT) -#define IDR5_OAS_36_BIT (1 << IDR5_OAS_SHIFT) -#define IDR5_OAS_40_BIT (2 << IDR5_OAS_SHIFT) -#define IDR5_OAS_42_BIT (3 << IDR5_OAS_SHIFT) -#define IDR5_OAS_44_BIT (4 << IDR5_OAS_SHIFT) -#define IDR5_OAS_48_BIT (5 << IDR5_OAS_SHIFT) +#define IDR5_OAS GENMASK(2, 0) +#define IDR5_OAS_32_BIT 0 +#define IDR5_OAS_36_BIT 1 +#define IDR5_OAS_40_BIT 2 +#define IDR5_OAS_42_BIT 3 +#define IDR5_OAS_44_BIT 4 +#define IDR5_OAS_48_BIT 5 +#define IDR5_OAS_52_BIT 6 +#define IDR5_VAX GENMASK(11, 10) +#define IDR5_VAX_52_BIT 1 #define ARM_SMMU_CR0 0x20 #define CR0_CMDQEN (1 << 3) @@ -110,18 +104,16 @@ #define ARM_SMMU_CR0ACK 0x24 #define ARM_SMMU_CR1 0x28 -#define CR1_SH_NSH 0 -#define CR1_SH_OSH 2 -#define CR1_SH_ISH 3 +#define CR1_TABLE_SH GENMASK(11, 10) +#define CR1_TABLE_OC GENMASK(9, 8) +#define CR1_TABLE_IC GENMASK(7, 6) +#define CR1_QUEUE_SH GENMASK(5, 4) +#define CR1_QUEUE_OC GENMASK(3, 2) +#define CR1_QUEUE_IC GENMASK(1, 0) +/* CR1 cacheability fields don't quite follow the usual TCR-style encoding */ #define CR1_CACHE_NC 0 #define CR1_CACHE_WB 1 #define CR1_CACHE_WT 2 -#define CR1_TABLE_SH_SHIFT 10 -#define CR1_TABLE_OC_SHIFT 8 -#define CR1_TABLE_IC_SHIFT 6 -#define CR1_QUEUE_SH_SHIFT 4 -#define CR1_QUEUE_OC_SHIFT 2 -#define CR1_QUEUE_IC_SHIFT 0 #define ARM_SMMU_CR2 0x2c #define CR2_PTM (1 << 2) @@ -129,8 +121,8 @@ #define CR2_E2H (1 << 0) #define ARM_SMMU_GBPA 0x44 -#define GBPA_ABORT (1 << 20) #define GBPA_UPDATE (1 << 31) +#define GBPA_ABORT (1 << 20) #define ARM_SMMU_IRQ_CTRL 0x50 #define IRQ_CTRL_EVTQ_IRQEN (1 << 2) @@ -158,18 +150,14 @@ #define ARM_SMMU_STRTAB_BASE 0x80 #define STRTAB_BASE_RA (1UL << 62) -#define STRTAB_BASE_ADDR_SHIFT 6 -#define STRTAB_BASE_ADDR_MASK 0x3ffffffffffUL +#define STRTAB_BASE_ADDR_MASK GENMASK_ULL(51, 6) #define ARM_SMMU_STRTAB_BASE_CFG 0x88 -#define STRTAB_BASE_CFG_LOG2SIZE_SHIFT 0 -#define STRTAB_BASE_CFG_LOG2SIZE_MASK 0x3f -#define STRTAB_BASE_CFG_SPLIT_SHIFT 6 -#define STRTAB_BASE_CFG_SPLIT_MASK 0x1f -#define STRTAB_BASE_CFG_FMT_SHIFT 16 -#define STRTAB_BASE_CFG_FMT_MASK 0x3 -#define STRTAB_BASE_CFG_FMT_LINEAR (0 << STRTAB_BASE_CFG_FMT_SHIFT) -#define STRTAB_BASE_CFG_FMT_2LVL (1 << STRTAB_BASE_CFG_FMT_SHIFT) +#define STRTAB_BASE_CFG_FMT GENMASK(17, 16) +#define STRTAB_BASE_CFG_FMT_LINEAR 0 +#define STRTAB_BASE_CFG_FMT_2LVL 1 +#define STRTAB_BASE_CFG_SPLIT GENMASK(10, 6) +#define STRTAB_BASE_CFG_LOG2SIZE GENMASK(5, 0) #define ARM_SMMU_CMDQ_BASE 0x90 #define ARM_SMMU_CMDQ_PROD 0x98 @@ -190,14 +178,16 @@ #define ARM_SMMU_PRIQ_IRQ_CFG2 0xdc /* Common MSI config fields */ -#define MSI_CFG0_ADDR_SHIFT 2 -#define MSI_CFG0_ADDR_MASK 0x3fffffffffffUL -#define MSI_CFG2_SH_SHIFT 4 -#define MSI_CFG2_SH_NSH (0UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_SH_OSH (2UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_SH_ISH (3UL << MSI_CFG2_SH_SHIFT) -#define MSI_CFG2_MEMATTR_SHIFT 0 -#define MSI_CFG2_MEMATTR_DEVICE_nGnRE (0x1 << MSI_CFG2_MEMATTR_SHIFT) +#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2) +#define MSI_CFG2_SH GENMASK(5, 4) +#define MSI_CFG2_MEMATTR GENMASK(3, 0) + +/* Common memory attribute values */ +#define ARM_SMMU_SH_NSH 0 +#define ARM_SMMU_SH_OSH 2 +#define ARM_SMMU_SH_ISH 3 +#define ARM_SMMU_MEMATTR_DEVICE_nGnRE 0x1 +#define ARM_SMMU_MEMATTR_OIWB 0xf #define Q_IDX(q, p) ((p) & ((1 << (q)->max_n_shift) - 1)) #define Q_WRP(q, p) ((p) & (1 << (q)->max_n_shift)) @@ -207,10 +197,8 @@ Q_IDX(q, p) * (q)->ent_dwords) #define Q_BASE_RWA (1UL << 62) -#define Q_BASE_ADDR_SHIFT 5 -#define Q_BASE_ADDR_MASK 0xfffffffffffUL -#define Q_BASE_LOG2SIZE_SHIFT 0 -#define Q_BASE_LOG2SIZE_MASK 0x1fUL +#define Q_BASE_ADDR_MASK GENMASK_ULL(51, 5) +#define Q_BASE_LOG2SIZE GENMASK(4, 0) /* * Stream table. @@ -223,187 +211,143 @@ #define STRTAB_SPLIT 8 #define STRTAB_L1_DESC_DWORDS 1 -#define STRTAB_L1_DESC_SPAN_SHIFT 0 -#define STRTAB_L1_DESC_SPAN_MASK 0x1fUL -#define STRTAB_L1_DESC_L2PTR_SHIFT 6 -#define STRTAB_L1_DESC_L2PTR_MASK 0x3ffffffffffUL +#define STRTAB_L1_DESC_SPAN GENMASK_ULL(4, 0) +#define STRTAB_L1_DESC_L2PTR_MASK GENMASK_ULL(51, 6) #define STRTAB_STE_DWORDS 8 #define STRTAB_STE_0_V (1UL << 0) -#define STRTAB_STE_0_CFG_SHIFT 1 -#define STRTAB_STE_0_CFG_MASK 0x7UL -#define STRTAB_STE_0_CFG_ABORT (0UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_BYPASS (4UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_S1_TRANS (5UL << STRTAB_STE_0_CFG_SHIFT) -#define STRTAB_STE_0_CFG_S2_TRANS (6UL << STRTAB_STE_0_CFG_SHIFT) - -#define STRTAB_STE_0_S1FMT_SHIFT 4 -#define STRTAB_STE_0_S1FMT_LINEAR (0UL << STRTAB_STE_0_S1FMT_SHIFT) -#define STRTAB_STE_0_S1CTXPTR_SHIFT 6 -#define STRTAB_STE_0_S1CTXPTR_MASK 0x3ffffffffffUL -#define STRTAB_STE_0_S1CDMAX_SHIFT 59 -#define STRTAB_STE_0_S1CDMAX_MASK 0x1fUL +#define STRTAB_STE_0_CFG GENMASK_ULL(3, 1) +#define STRTAB_STE_0_CFG_ABORT 0 +#define STRTAB_STE_0_CFG_BYPASS 4 +#define STRTAB_STE_0_CFG_S1_TRANS 5 +#define STRTAB_STE_0_CFG_S2_TRANS 6 + +#define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) +#define STRTAB_STE_0_S1FMT_LINEAR 0 +#define STRTAB_STE_0_S1CTXPTR_MASK GENMASK_ULL(51, 6) +#define STRTAB_STE_0_S1CDMAX GENMASK_ULL(63, 59) #define STRTAB_STE_1_S1C_CACHE_NC 0UL #define STRTAB_STE_1_S1C_CACHE_WBRA 1UL #define STRTAB_STE_1_S1C_CACHE_WT 2UL #define STRTAB_STE_1_S1C_CACHE_WB 3UL -#define STRTAB_STE_1_S1C_SH_NSH 0UL -#define STRTAB_STE_1_S1C_SH_OSH 2UL -#define STRTAB_STE_1_S1C_SH_ISH 3UL -#define STRTAB_STE_1_S1CIR_SHIFT 2 -#define STRTAB_STE_1_S1COR_SHIFT 4 -#define STRTAB_STE_1_S1CSH_SHIFT 6 +#define STRTAB_STE_1_S1CIR GENMASK_ULL(3, 2) +#define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) +#define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) #define STRTAB_STE_1_S1STALLD (1UL << 27) +#define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) #define STRTAB_STE_1_EATS_ABT 0UL #define STRTAB_STE_1_EATS_TRANS 1UL #define STRTAB_STE_1_EATS_S1CHK 2UL -#define STRTAB_STE_1_EATS_SHIFT 28 +#define STRTAB_STE_1_STRW GENMASK_ULL(31, 30) #define STRTAB_STE_1_STRW_NSEL1 0UL #define STRTAB_STE_1_STRW_EL2 2UL -#define STRTAB_STE_1_STRW_SHIFT 30 +#define STRTAB_STE_1_SHCFG GENMASK_ULL(45, 44) #define STRTAB_STE_1_SHCFG_INCOMING 1UL -#define STRTAB_STE_1_SHCFG_SHIFT 44 -#define STRTAB_STE_2_S2VMID_SHIFT 0 -#define STRTAB_STE_2_S2VMID_MASK 0xffffUL -#define STRTAB_STE_2_VTCR_SHIFT 32 -#define STRTAB_STE_2_VTCR_MASK 0x7ffffUL +#define STRTAB_STE_2_S2VMID GENMASK_ULL(15, 0) +#define STRTAB_STE_2_VTCR GENMASK_ULL(50, 32) #define STRTAB_STE_2_S2AA64 (1UL << 51) #define STRTAB_STE_2_S2ENDI (1UL << 52) #define STRTAB_STE_2_S2PTW (1UL << 54) #define STRTAB_STE_2_S2R (1UL << 58) -#define STRTAB_STE_3_S2TTB_SHIFT 4 -#define STRTAB_STE_3_S2TTB_MASK 0xfffffffffffUL +#define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) /* Context descriptor (stage-1 only) */ #define CTXDESC_CD_DWORDS 8 -#define CTXDESC_CD_0_TCR_T0SZ_SHIFT 0 -#define ARM64_TCR_T0SZ_SHIFT 0 -#define ARM64_TCR_T0SZ_MASK 0x1fUL -#define CTXDESC_CD_0_TCR_TG0_SHIFT 6 -#define ARM64_TCR_TG0_SHIFT 14 -#define ARM64_TCR_TG0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_IRGN0_SHIFT 8 -#define ARM64_TCR_IRGN0_SHIFT 8 -#define ARM64_TCR_IRGN0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_ORGN0_SHIFT 10 -#define ARM64_TCR_ORGN0_SHIFT 10 -#define ARM64_TCR_ORGN0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_SH0_SHIFT 12 -#define ARM64_TCR_SH0_SHIFT 12 -#define ARM64_TCR_SH0_MASK 0x3UL -#define CTXDESC_CD_0_TCR_EPD0_SHIFT 14 -#define ARM64_TCR_EPD0_SHIFT 7 -#define ARM64_TCR_EPD0_MASK 0x1UL -#define CTXDESC_CD_0_TCR_EPD1_SHIFT 30 -#define ARM64_TCR_EPD1_SHIFT 23 -#define ARM64_TCR_EPD1_MASK 0x1UL +#define CTXDESC_CD_0_TCR_T0SZ GENMASK_ULL(5, 0) +#define ARM64_TCR_T0SZ GENMASK_ULL(5, 0) +#define CTXDESC_CD_0_TCR_TG0 GENMASK_ULL(7, 6) +#define ARM64_TCR_TG0 GENMASK_ULL(15, 14) +#define CTXDESC_CD_0_TCR_IRGN0 GENMASK_ULL(9, 8) +#define ARM64_TCR_IRGN0 GENMASK_ULL(9, 8) +#define CTXDESC_CD_0_TCR_ORGN0 GENMASK_ULL(11, 10) +#define ARM64_TCR_ORGN0 GENMASK_ULL(11, 10) +#define CTXDESC_CD_0_TCR_SH0 GENMASK_ULL(13, 12) +#define ARM64_TCR_SH0 GENMASK_ULL(13, 12) +#define CTXDESC_CD_0_TCR_EPD0 (1ULL << 14) +#define ARM64_TCR_EPD0 (1ULL << 7) +#define CTXDESC_CD_0_TCR_EPD1 (1ULL << 30) +#define ARM64_TCR_EPD1 (1ULL << 23) #define CTXDESC_CD_0_ENDI (1UL << 15) #define CTXDESC_CD_0_V (1UL << 31) -#define CTXDESC_CD_0_TCR_IPS_SHIFT 32 -#define ARM64_TCR_IPS_SHIFT 32 -#define ARM64_TCR_IPS_MASK 0x7UL -#define CTXDESC_CD_0_TCR_TBI0_SHIFT 38 -#define ARM64_TCR_TBI0_SHIFT 37 -#define ARM64_TCR_TBI0_MASK 0x1UL +#define CTXDESC_CD_0_TCR_IPS GENMASK_ULL(34, 32) +#define ARM64_TCR_IPS GENMASK_ULL(34, 32) +#define CTXDESC_CD_0_TCR_TBI0 (1ULL << 38) +#define ARM64_TCR_TBI0 (1ULL << 37) #define CTXDESC_CD_0_AA64 (1UL << 41) #define CTXDESC_CD_0_S (1UL << 44) #define CTXDESC_CD_0_R (1UL << 45) #define CTXDESC_CD_0_A (1UL << 46) -#define CTXDESC_CD_0_ASET_SHIFT 47 -#define CTXDESC_CD_0_ASET_SHARED (0UL << CTXDESC_CD_0_ASET_SHIFT) -#define CTXDESC_CD_0_ASET_PRIVATE (1UL << CTXDESC_CD_0_ASET_SHIFT) -#define CTXDESC_CD_0_ASID_SHIFT 48 -#define CTXDESC_CD_0_ASID_MASK 0xffffUL - -#define CTXDESC_CD_1_TTB0_SHIFT 4 -#define CTXDESC_CD_1_TTB0_MASK 0xfffffffffffUL +#define CTXDESC_CD_0_ASET (1UL << 47) +#define CTXDESC_CD_0_ASID GENMASK_ULL(63, 48) -#define CTXDESC_CD_3_MAIR_SHIFT 0 +#define CTXDESC_CD_1_TTB0_MASK GENMASK_ULL(51, 4) /* Convert between AArch64 (CPU) TCR format and SMMU CD format */ -#define ARM_SMMU_TCR2CD(tcr, fld) \ - (((tcr) >> ARM64_TCR_##fld##_SHIFT & ARM64_TCR_##fld##_MASK) \ - << CTXDESC_CD_0_TCR_##fld##_SHIFT) +#define ARM_SMMU_TCR2CD(tcr, fld) FIELD_PREP(CTXDESC_CD_0_TCR_##fld, \ + FIELD_GET(ARM64_TCR_##fld, tcr)) /* Command queue */ #define CMDQ_ENT_DWORDS 2 #define CMDQ_MAX_SZ_SHIFT 8 -#define CMDQ_ERR_SHIFT 24 -#define CMDQ_ERR_MASK 0x7f +#define CMDQ_CONS_ERR GENMASK(30, 24) #define CMDQ_ERR_CERROR_NONE_IDX 0 #define CMDQ_ERR_CERROR_ILL_IDX 1 #define CMDQ_ERR_CERROR_ABT_IDX 2 -#define CMDQ_0_OP_SHIFT 0 -#define CMDQ_0_OP_MASK 0xffUL +#define CMDQ_0_OP GENMASK_ULL(7, 0) #define CMDQ_0_SSV (1UL << 11) -#define CMDQ_PREFETCH_0_SID_SHIFT 32 -#define CMDQ_PREFETCH_1_SIZE_SHIFT 0 -#define CMDQ_PREFETCH_1_ADDR_MASK ~0xfffUL +#define CMDQ_PREFETCH_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PREFETCH_1_SIZE GENMASK_ULL(4, 0) +#define CMDQ_PREFETCH_1_ADDR_MASK GENMASK_ULL(63, 12) -#define CMDQ_CFGI_0_SID_SHIFT 32 -#define CMDQ_CFGI_0_SID_MASK 0xffffffffUL +#define CMDQ_CFGI_0_SID GENMASK_ULL(63, 32) #define CMDQ_CFGI_1_LEAF (1UL << 0) -#define CMDQ_CFGI_1_RANGE_SHIFT 0 -#define CMDQ_CFGI_1_RANGE_MASK 0x1fUL +#define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) -#define CMDQ_TLBI_0_VMID_SHIFT 32 -#define CMDQ_TLBI_0_ASID_SHIFT 48 +#define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) +#define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) #define CMDQ_TLBI_1_LEAF (1UL << 0) -#define CMDQ_TLBI_1_VA_MASK ~0xfffUL -#define CMDQ_TLBI_1_IPA_MASK 0xfffffffff000UL - -#define CMDQ_PRI_0_SSID_SHIFT 12 -#define CMDQ_PRI_0_SSID_MASK 0xfffffUL -#define CMDQ_PRI_0_SID_SHIFT 32 -#define CMDQ_PRI_0_SID_MASK 0xffffffffUL -#define CMDQ_PRI_1_GRPID_SHIFT 0 -#define CMDQ_PRI_1_GRPID_MASK 0x1ffUL -#define CMDQ_PRI_1_RESP_SHIFT 12 -#define CMDQ_PRI_1_RESP_DENY (0UL << CMDQ_PRI_1_RESP_SHIFT) -#define CMDQ_PRI_1_RESP_FAIL (1UL << CMDQ_PRI_1_RESP_SHIFT) -#define CMDQ_PRI_1_RESP_SUCC (2UL << CMDQ_PRI_1_RESP_SHIFT) - -#define CMDQ_SYNC_0_CS_SHIFT 12 -#define CMDQ_SYNC_0_CS_NONE (0UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_CS_IRQ (1UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_CS_SEV (2UL << CMDQ_SYNC_0_CS_SHIFT) -#define CMDQ_SYNC_0_MSH_SHIFT 22 -#define CMDQ_SYNC_0_MSH_ISH (3UL << CMDQ_SYNC_0_MSH_SHIFT) -#define CMDQ_SYNC_0_MSIATTR_SHIFT 24 -#define CMDQ_SYNC_0_MSIATTR_OIWB (0xfUL << CMDQ_SYNC_0_MSIATTR_SHIFT) -#define CMDQ_SYNC_0_MSIDATA_SHIFT 32 -#define CMDQ_SYNC_0_MSIDATA_MASK 0xffffffffUL -#define CMDQ_SYNC_1_MSIADDR_SHIFT 0 -#define CMDQ_SYNC_1_MSIADDR_MASK 0xffffffffffffcUL +#define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) +#define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) + +#define CMDQ_PRI_0_SSID GENMASK_ULL(31, 12) +#define CMDQ_PRI_0_SID GENMASK_ULL(63, 32) +#define CMDQ_PRI_1_GRPID GENMASK_ULL(8, 0) +#define CMDQ_PRI_1_RESP GENMASK_ULL(13, 12) + +#define CMDQ_SYNC_0_CS GENMASK_ULL(13, 12) +#define CMDQ_SYNC_0_CS_NONE 0 +#define CMDQ_SYNC_0_CS_IRQ 1 +#define CMDQ_SYNC_0_CS_SEV 2 +#define CMDQ_SYNC_0_MSH GENMASK_ULL(23, 22) +#define CMDQ_SYNC_0_MSIATTR GENMASK_ULL(27, 24) +#define CMDQ_SYNC_0_MSIDATA GENMASK_ULL(63, 32) +#define CMDQ_SYNC_1_MSIADDR_MASK GENMASK_ULL(51, 2) /* Event queue */ #define EVTQ_ENT_DWORDS 4 #define EVTQ_MAX_SZ_SHIFT 7 -#define EVTQ_0_ID_SHIFT 0 -#define EVTQ_0_ID_MASK 0xffUL +#define EVTQ_0_ID GENMASK_ULL(7, 0) /* PRI queue */ #define PRIQ_ENT_DWORDS 2 #define PRIQ_MAX_SZ_SHIFT 8 -#define PRIQ_0_SID_SHIFT 0 -#define PRIQ_0_SID_MASK 0xffffffffUL -#define PRIQ_0_SSID_SHIFT 32 -#define PRIQ_0_SSID_MASK 0xfffffUL +#define PRIQ_0_SID GENMASK_ULL(31, 0) +#define PRIQ_0_SSID GENMASK_ULL(51, 32) #define PRIQ_0_PERM_PRIV (1UL << 58) #define PRIQ_0_PERM_EXEC (1UL << 59) #define PRIQ_0_PERM_READ (1UL << 60) @@ -411,10 +355,8 @@ #define PRIQ_0_PRG_LAST (1UL << 62) #define PRIQ_0_SSID_V (1UL << 63) -#define PRIQ_1_PRG_IDX_SHIFT 0 -#define PRIQ_1_PRG_IDX_MASK 0x1ffUL -#define PRIQ_1_ADDR_SHIFT 12 -#define PRIQ_1_ADDR_MASK 0xfffffffffffffUL +#define PRIQ_1_PRG_IDX GENMASK_ULL(8, 0) +#define PRIQ_1_ADDR_MASK GENMASK_ULL(63, 12) /* High-level queue structures */ #define ARM_SMMU_POLL_TIMEOUT_US 100 @@ -430,9 +372,9 @@ MODULE_PARM_DESC(disable_bypass, "Disable bypass streams such that incoming transactions from devices that are not attached to an iommu domain will report an abort back to the device and will not be allowed to pass through the SMMU."); enum pri_resp { - PRI_RESP_DENY, - PRI_RESP_FAIL, - PRI_RESP_SUCC, + PRI_RESP_DENY = 0, + PRI_RESP_FAIL = 1, + PRI_RESP_SUCC = 2, }; enum arm_smmu_msi_index { @@ -611,6 +553,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_STALLS (1 << 11) #define ARM_SMMU_FEAT_HYP (1 << 12) #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) +#define ARM_SMMU_FEAT_VAX (1 << 14) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -836,67 +779,64 @@ static int queue_remove_raw(struct arm_smmu_queue *q, u64 *ent) static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) { memset(cmd, 0, CMDQ_ENT_DWORDS << 3); - cmd[0] |= (ent->opcode & CMDQ_0_OP_MASK) << CMDQ_0_OP_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_0_OP, ent->opcode); switch (ent->opcode) { case CMDQ_OP_TLBI_EL2_ALL: case CMDQ_OP_TLBI_NSNH_ALL: break; case CMDQ_OP_PREFETCH_CFG: - cmd[0] |= (u64)ent->prefetch.sid << CMDQ_PREFETCH_0_SID_SHIFT; - cmd[1] |= ent->prefetch.size << CMDQ_PREFETCH_1_SIZE_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_PREFETCH_0_SID, ent->prefetch.sid); + cmd[1] |= FIELD_PREP(CMDQ_PREFETCH_1_SIZE, ent->prefetch.size); cmd[1] |= ent->prefetch.addr & CMDQ_PREFETCH_1_ADDR_MASK; break; case CMDQ_OP_CFGI_STE: - cmd[0] |= (u64)ent->cfgi.sid << CMDQ_CFGI_0_SID_SHIFT; - cmd[1] |= ent->cfgi.leaf ? CMDQ_CFGI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, ent->cfgi.sid); + cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_LEAF, ent->cfgi.leaf); break; case CMDQ_OP_CFGI_ALL: /* Cover the entire SID range */ - cmd[1] |= CMDQ_CFGI_1_RANGE_MASK << CMDQ_CFGI_1_RANGE_SHIFT; + cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); break; case CMDQ_OP_TLBI_NH_VA: - cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; - cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; break; case CMDQ_OP_TLBI_S2_IPA: - cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; - cmd[1] |= ent->tlbi.leaf ? CMDQ_TLBI_1_LEAF : 0; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: - cmd[0] |= (u64)ent->tlbi.asid << CMDQ_TLBI_0_ASID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); /* Fallthrough */ case CMDQ_OP_TLBI_S12_VMALL: - cmd[0] |= (u64)ent->tlbi.vmid << CMDQ_TLBI_0_VMID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; case CMDQ_OP_PRI_RESP: - cmd[0] |= ent->substream_valid ? CMDQ_0_SSV : 0; - cmd[0] |= ent->pri.ssid << CMDQ_PRI_0_SSID_SHIFT; - cmd[0] |= (u64)ent->pri.sid << CMDQ_PRI_0_SID_SHIFT; - cmd[1] |= ent->pri.grpid << CMDQ_PRI_1_GRPID_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_0_SSV, ent->substream_valid); + cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SSID, ent->pri.ssid); + cmd[0] |= FIELD_PREP(CMDQ_PRI_0_SID, ent->pri.sid); + cmd[1] |= FIELD_PREP(CMDQ_PRI_1_GRPID, ent->pri.grpid); switch (ent->pri.resp) { case PRI_RESP_DENY: - cmd[1] |= CMDQ_PRI_1_RESP_DENY; - break; case PRI_RESP_FAIL: - cmd[1] |= CMDQ_PRI_1_RESP_FAIL; - break; case PRI_RESP_SUCC: - cmd[1] |= CMDQ_PRI_1_RESP_SUCC; break; default: return -EINVAL; } + cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp); break; case CMDQ_OP_CMD_SYNC: if (ent->sync.msiaddr) - cmd[0] |= CMDQ_SYNC_0_CS_IRQ; + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ); else - cmd[0] |= CMDQ_SYNC_0_CS_SEV; - cmd[0] |= CMDQ_SYNC_0_MSH_ISH | CMDQ_SYNC_0_MSIATTR_OIWB; - cmd[0] |= (u64)ent->sync.msidata << CMDQ_SYNC_0_MSIDATA_SHIFT; + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_SEV); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSH, ARM_SMMU_SH_ISH); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIATTR, ARM_SMMU_MEMATTR_OIWB); + cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_MSIDATA, ent->sync.msidata); cmd[1] |= ent->sync.msiaddr & CMDQ_SYNC_1_MSIADDR_MASK; break; default: @@ -918,7 +858,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) u64 cmd[CMDQ_ENT_DWORDS]; struct arm_smmu_queue *q = &smmu->cmdq.q; u32 cons = readl_relaxed(q->cons_reg); - u32 idx = cons >> CMDQ_ERR_SHIFT & CMDQ_ERR_MASK; + u32 idx = FIELD_GET(CMDQ_CONS_ERR, cons); struct arm_smmu_cmdq_ent cmd_sync = { .opcode = CMDQ_OP_CMD_SYNC, }; @@ -1083,8 +1023,8 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu, #ifdef __BIG_ENDIAN CTXDESC_CD_0_ENDI | #endif - CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET_PRIVATE | - CTXDESC_CD_0_AA64 | (u64)cfg->cd.asid << CTXDESC_CD_0_ASID_SHIFT | + CTXDESC_CD_0_R | CTXDESC_CD_0_A | CTXDESC_CD_0_ASET | + CTXDESC_CD_0_AA64 | FIELD_PREP(CTXDESC_CD_0_ASID, cfg->cd.asid) | CTXDESC_CD_0_V; /* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */ @@ -1093,10 +1033,10 @@ static void arm_smmu_write_ctx_desc(struct arm_smmu_device *smmu, cfg->cdptr[0] = cpu_to_le64(val); - val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK << CTXDESC_CD_1_TTB0_SHIFT; + val = cfg->cd.ttbr & CTXDESC_CD_1_TTB0_MASK; cfg->cdptr[1] = cpu_to_le64(val); - cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair << CTXDESC_CD_3_MAIR_SHIFT); + cfg->cdptr[3] = cpu_to_le64(cfg->cd.mair); } /* Stream table manipulation functions */ @@ -1105,10 +1045,8 @@ arm_smmu_write_strtab_l1_desc(__le64 *dst, struct arm_smmu_strtab_l1_desc *desc) { u64 val = 0; - val |= (desc->span & STRTAB_L1_DESC_SPAN_MASK) - << STRTAB_L1_DESC_SPAN_SHIFT; - val |= desc->l2ptr_dma & - STRTAB_L1_DESC_L2PTR_MASK << STRTAB_L1_DESC_L2PTR_SHIFT; + val |= FIELD_PREP(STRTAB_L1_DESC_SPAN, desc->span); + val |= desc->l2ptr_dma & STRTAB_L1_DESC_L2PTR_MASK; *dst = cpu_to_le64(val); } @@ -1156,10 +1094,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, }; if (val & STRTAB_STE_0_V) { - u64 cfg; - - cfg = val & STRTAB_STE_0_CFG_MASK << STRTAB_STE_0_CFG_SHIFT; - switch (cfg) { + switch (FIELD_GET(STRTAB_STE_0_CFG, val)) { case STRTAB_STE_0_CFG_BYPASS: break; case STRTAB_STE_0_CFG_S1_TRANS: @@ -1180,13 +1115,13 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, /* Bypass/fault */ if (!ste->assigned || !(ste->s1_cfg || ste->s2_cfg)) { if (!ste->assigned && disable_bypass) - val |= STRTAB_STE_0_CFG_ABORT; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_ABORT); else - val |= STRTAB_STE_0_CFG_BYPASS; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_BYPASS); dst[0] = cpu_to_le64(val); - dst[1] = cpu_to_le64(STRTAB_STE_1_SHCFG_INCOMING - << STRTAB_STE_1_SHCFG_SHIFT); + dst[1] = cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, + STRTAB_STE_1_SHCFG_INCOMING)); dst[2] = 0; /* Nuke the VMID */ /* * The SMMU can perform negative caching, so we must sync @@ -1200,41 +1135,36 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, if (ste->s1_cfg) { BUG_ON(ste_live); dst[1] = cpu_to_le64( - STRTAB_STE_1_S1C_CACHE_WBRA - << STRTAB_STE_1_S1CIR_SHIFT | - STRTAB_STE_1_S1C_CACHE_WBRA - << STRTAB_STE_1_S1COR_SHIFT | - STRTAB_STE_1_S1C_SH_ISH << STRTAB_STE_1_S1CSH_SHIFT | + FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | + FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | + FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) | #ifdef CONFIG_PCI_ATS - STRTAB_STE_1_EATS_TRANS << STRTAB_STE_1_EATS_SHIFT | + FIELD_PREP(STRTAB_STE_1_EATS, STRTAB_STE_1_EATS_TRANS) | #endif - STRTAB_STE_1_STRW_NSEL1 << STRTAB_STE_1_STRW_SHIFT); + FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1)); if (smmu->features & ARM_SMMU_FEAT_STALLS && !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE)) dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD); - val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK - << STRTAB_STE_0_S1CTXPTR_SHIFT) | - STRTAB_STE_0_CFG_S1_TRANS; + val |= (ste->s1_cfg->cdptr_dma & STRTAB_STE_0_S1CTXPTR_MASK) | + FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S1_TRANS); } if (ste->s2_cfg) { BUG_ON(ste_live); dst[2] = cpu_to_le64( - ste->s2_cfg->vmid << STRTAB_STE_2_S2VMID_SHIFT | - (ste->s2_cfg->vtcr & STRTAB_STE_2_VTCR_MASK) - << STRTAB_STE_2_VTCR_SHIFT | + FIELD_PREP(STRTAB_STE_2_S2VMID, ste->s2_cfg->vmid) | + FIELD_PREP(STRTAB_STE_2_VTCR, ste->s2_cfg->vtcr) | #ifdef __BIG_ENDIAN STRTAB_STE_2_S2ENDI | #endif STRTAB_STE_2_S2PTW | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2R); - dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & - STRTAB_STE_3_S2TTB_MASK << STRTAB_STE_3_S2TTB_SHIFT); + dst[3] = cpu_to_le64(ste->s2_cfg->vttbr & STRTAB_STE_3_S2TTB_MASK); - val |= STRTAB_STE_0_CFG_S2_TRANS; + val |= FIELD_PREP(STRTAB_STE_0_CFG, STRTAB_STE_0_CFG_S2_TRANS); } arm_smmu_sync_ste_for_sid(smmu, sid); @@ -1295,7 +1225,7 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev) do { while (!queue_remove_raw(q, evt)) { - u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK; + u8 id = FIELD_GET(EVTQ_0_ID, evt[0]); dev_info(smmu->dev, "event 0x%02x received:\n", id); for (i = 0; i < ARRAY_SIZE(evt); ++i) @@ -1323,11 +1253,11 @@ static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt) u16 grpid; bool ssv, last; - sid = evt[0] >> PRIQ_0_SID_SHIFT & PRIQ_0_SID_MASK; - ssv = evt[0] & PRIQ_0_SSID_V; - ssid = ssv ? evt[0] >> PRIQ_0_SSID_SHIFT & PRIQ_0_SSID_MASK : 0; - last = evt[0] & PRIQ_0_PRG_LAST; - grpid = evt[1] >> PRIQ_1_PRG_IDX_SHIFT & PRIQ_1_PRG_IDX_MASK; + sid = FIELD_GET(PRIQ_0_SID, evt[0]); + ssv = FIELD_GET(PRIQ_0_SSID_V, evt[0]); + ssid = ssv ? FIELD_GET(PRIQ_0_SSID, evt[0]) : 0; + last = FIELD_GET(PRIQ_0_PRG_LAST, evt[0]); + grpid = FIELD_GET(PRIQ_1_PRG_IDX, evt[1]); dev_info(smmu->dev, "unexpected PRI request received:\n"); dev_info(smmu->dev, @@ -1337,7 +1267,7 @@ static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt) evt[0] & PRIQ_0_PERM_READ ? "R" : "", evt[0] & PRIQ_0_PERM_WRITE ? "W" : "", evt[0] & PRIQ_0_PERM_EXEC ? "X" : "", - evt[1] & PRIQ_1_ADDR_MASK << PRIQ_1_ADDR_SHIFT); + evt[1] & PRIQ_1_ADDR_MASK); if (last) { struct arm_smmu_cmdq_ent cmd = { @@ -1664,7 +1594,8 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) switch (smmu_domain->stage) { case ARM_SMMU_DOMAIN_S1: - ias = VA_BITS; + ias = (smmu->features & ARM_SMMU_FEAT_VAX) ? 52 : 48; + ias = min_t(unsigned long, ias, VA_BITS); oas = smmu->ias; fmt = ARM_64_LPAE_S1; finalise_stage_fn = arm_smmu_domain_finalise_s1; @@ -1696,7 +1627,7 @@ static int arm_smmu_domain_finalise(struct iommu_domain *domain) return -ENOMEM; domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap; - domain->geometry.aperture_end = (1UL << ias) - 1; + domain->geometry.aperture_end = (1UL << pgtbl_cfg.ias) - 1; domain->geometry.force_aperture = true; ret = finalise_stage_fn(smmu_domain, &pgtbl_cfg); @@ -2102,9 +2033,8 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu, q->ent_dwords = dwords; q->q_base = Q_BASE_RWA; - q->q_base |= q->base_dma & Q_BASE_ADDR_MASK << Q_BASE_ADDR_SHIFT; - q->q_base |= (q->max_n_shift & Q_BASE_LOG2SIZE_MASK) - << Q_BASE_LOG2SIZE_SHIFT; + q->q_base |= q->base_dma & Q_BASE_ADDR_MASK; + q->q_base |= FIELD_PREP(Q_BASE_LOG2SIZE, q->max_n_shift); q->prod = q->cons = 0; return 0; @@ -2186,11 +2116,9 @@ static int arm_smmu_init_strtab_2lvl(struct arm_smmu_device *smmu) cfg->strtab = strtab; /* Configure strtab_base_cfg for 2 levels */ - reg = STRTAB_BASE_CFG_FMT_2LVL; - reg |= (size & STRTAB_BASE_CFG_LOG2SIZE_MASK) - << STRTAB_BASE_CFG_LOG2SIZE_SHIFT; - reg |= (STRTAB_SPLIT & STRTAB_BASE_CFG_SPLIT_MASK) - << STRTAB_BASE_CFG_SPLIT_SHIFT; + reg = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_2LVL); + reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, size); + reg |= FIELD_PREP(STRTAB_BASE_CFG_SPLIT, STRTAB_SPLIT); cfg->strtab_base_cfg = reg; return arm_smmu_init_l1_strtab(smmu); @@ -2216,9 +2144,8 @@ static int arm_smmu_init_strtab_linear(struct arm_smmu_device *smmu) cfg->num_l1_ents = 1 << smmu->sid_bits; /* Configure strtab_base_cfg for a linear table covering all SIDs */ - reg = STRTAB_BASE_CFG_FMT_LINEAR; - reg |= (smmu->sid_bits & STRTAB_BASE_CFG_LOG2SIZE_MASK) - << STRTAB_BASE_CFG_LOG2SIZE_SHIFT; + reg = FIELD_PREP(STRTAB_BASE_CFG_FMT, STRTAB_BASE_CFG_FMT_LINEAR); + reg |= FIELD_PREP(STRTAB_BASE_CFG_LOG2SIZE, smmu->sid_bits); cfg->strtab_base_cfg = reg; arm_smmu_init_bypass_stes(strtab, cfg->num_l1_ents); @@ -2239,8 +2166,7 @@ static int arm_smmu_init_strtab(struct arm_smmu_device *smmu) return ret; /* Set the strtab base address */ - reg = smmu->strtab_cfg.strtab_dma & - STRTAB_BASE_ADDR_MASK << STRTAB_BASE_ADDR_SHIFT; + reg = smmu->strtab_cfg.strtab_dma & STRTAB_BASE_ADDR_MASK; reg |= STRTAB_BASE_RA; smmu->strtab_cfg.strtab_base = reg; @@ -2303,11 +2229,11 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index]; doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; - doorbell &= MSI_CFG0_ADDR_MASK << MSI_CFG0_ADDR_SHIFT; + doorbell &= MSI_CFG0_ADDR_MASK; writeq_relaxed(doorbell, smmu->base + cfg[0]); writel_relaxed(msg->data, smmu->base + cfg[1]); - writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); + writel_relaxed(ARM_SMMU_MEMATTR_DEVICE_nGnRE, smmu->base + cfg[2]); } static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) @@ -2328,10 +2254,15 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) if (!(smmu->features & ARM_SMMU_FEAT_MSI)) return; + if (!dev->msi_domain) { + dev_info(smmu->dev, "msi_domain absent - falling back to wired irqs\n"); + return; + } + /* Allocate MSIs for evtq, gerror and priq. Ignore cmdq */ ret = platform_msi_domain_alloc_irqs(dev, nvec, arm_smmu_write_msi_msg); if (ret) { - dev_warn(dev, "failed to allocate MSIs\n"); + dev_warn(dev, "failed to allocate MSIs - falling back to wired irqs\n"); return; } @@ -2370,6 +2301,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) "arm-smmu-v3-evtq", smmu); if (ret < 0) dev_warn(smmu->dev, "failed to enable evtq irq\n"); + } else { + dev_warn(smmu->dev, "no evtq irq - events will not be reported!\n"); } irq = smmu->gerr_irq; @@ -2378,6 +2311,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) 0, "arm-smmu-v3-gerror", smmu); if (ret < 0) dev_warn(smmu->dev, "failed to enable gerror irq\n"); + } else { + dev_warn(smmu->dev, "no gerr irq - errors will not be reported!\n"); } if (smmu->features & ARM_SMMU_FEAT_PRI) { @@ -2391,6 +2326,8 @@ static void arm_smmu_setup_unique_irqs(struct arm_smmu_device *smmu) if (ret < 0) dev_warn(smmu->dev, "failed to enable priq irq\n"); + } else { + dev_warn(smmu->dev, "no priq irq - PRI will be broken\n"); } } } @@ -2463,12 +2400,12 @@ static int arm_smmu_device_reset(struct arm_smmu_device *smmu, bool bypass) return ret; /* CR1 (table and queue memory attributes) */ - reg = (CR1_SH_ISH << CR1_TABLE_SH_SHIFT) | - (CR1_CACHE_WB << CR1_TABLE_OC_SHIFT) | - (CR1_CACHE_WB << CR1_TABLE_IC_SHIFT) | - (CR1_SH_ISH << CR1_QUEUE_SH_SHIFT) | - (CR1_CACHE_WB << CR1_QUEUE_OC_SHIFT) | - (CR1_CACHE_WB << CR1_QUEUE_IC_SHIFT); + reg = FIELD_PREP(CR1_TABLE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_TABLE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_TABLE_IC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_SH, ARM_SMMU_SH_ISH) | + FIELD_PREP(CR1_QUEUE_OC, CR1_CACHE_WB) | + FIELD_PREP(CR1_QUEUE_IC, CR1_CACHE_WB); writel_relaxed(reg, smmu->base + ARM_SMMU_CR1); /* CR2 (random crap) */ @@ -2578,7 +2515,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) reg = readl_relaxed(smmu->base + ARM_SMMU_IDR0); /* 2-level structures */ - if ((reg & IDR0_ST_LVL_MASK << IDR0_ST_LVL_SHIFT) == IDR0_ST_LVL_2LVL) + if (FIELD_GET(IDR0_ST_LVL, reg) == IDR0_ST_LVL_2LVL) smmu->features |= ARM_SMMU_FEAT_2_LVL_STRTAB; if (reg & IDR0_CD2L) @@ -2589,7 +2526,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) * We currently require the same endianness as the CPU, but this * could be changed later by adding a new IO_PGTABLE_QUIRK. */ - switch (reg & IDR0_TTENDIAN_MASK << IDR0_TTENDIAN_SHIFT) { + switch (FIELD_GET(IDR0_TTENDIAN, reg)) { case IDR0_TTENDIAN_MIXED: smmu->features |= ARM_SMMU_FEAT_TT_LE | ARM_SMMU_FEAT_TT_BE; break; @@ -2631,7 +2568,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) dev_warn(smmu->dev, "IDR0.COHACC overridden by FW configuration (%s)\n", coherent ? "true" : "false"); - switch (reg & IDR0_STALL_MODEL_MASK << IDR0_STALL_MODEL_SHIFT) { + switch (FIELD_GET(IDR0_STALL_MODEL, reg)) { case IDR0_STALL_MODEL_FORCE: smmu->features |= ARM_SMMU_FEAT_STALL_FORCE; /* Fallthrough */ @@ -2651,7 +2588,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) } /* We only support the AArch64 table format at present */ - switch (reg & IDR0_TTF_MASK << IDR0_TTF_SHIFT) { + switch (FIELD_GET(IDR0_TTF, reg)) { case IDR0_TTF_AARCH32_64: smmu->ias = 40; /* Fallthrough */ @@ -2674,22 +2611,22 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) } /* Queue sizes, capped at 4k */ - smmu->cmdq.q.max_n_shift = min((u32)CMDQ_MAX_SZ_SHIFT, - reg >> IDR1_CMDQ_SHIFT & IDR1_CMDQ_MASK); + smmu->cmdq.q.max_n_shift = min_t(u32, CMDQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_CMDQS, reg)); if (!smmu->cmdq.q.max_n_shift) { /* Odd alignment restrictions on the base, so ignore for now */ dev_err(smmu->dev, "unit-length command queue not supported\n"); return -ENXIO; } - smmu->evtq.q.max_n_shift = min((u32)EVTQ_MAX_SZ_SHIFT, - reg >> IDR1_EVTQ_SHIFT & IDR1_EVTQ_MASK); - smmu->priq.q.max_n_shift = min((u32)PRIQ_MAX_SZ_SHIFT, - reg >> IDR1_PRIQ_SHIFT & IDR1_PRIQ_MASK); + smmu->evtq.q.max_n_shift = min_t(u32, EVTQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_EVTQS, reg)); + smmu->priq.q.max_n_shift = min_t(u32, PRIQ_MAX_SZ_SHIFT, + FIELD_GET(IDR1_PRIQS, reg)); /* SID/SSID sizes */ - smmu->ssid_bits = reg >> IDR1_SSID_SHIFT & IDR1_SSID_MASK; - smmu->sid_bits = reg >> IDR1_SID_SHIFT & IDR1_SID_MASK; + smmu->ssid_bits = FIELD_GET(IDR1_SSIDSIZE, reg); + smmu->sid_bits = FIELD_GET(IDR1_SIDSIZE, reg); /* * If the SMMU supports fewer bits than would fill a single L2 stream @@ -2702,8 +2639,7 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); /* Maximum number of outstanding stalls */ - smmu->evtq.max_stalls = reg >> IDR5_STALL_MAX_SHIFT - & IDR5_STALL_MAX_MASK; + smmu->evtq.max_stalls = FIELD_GET(IDR5_STALL_MAX, reg); /* Page sizes */ if (reg & IDR5_GRAN64K) @@ -2713,13 +2649,12 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (reg & IDR5_GRAN4K) smmu->pgsize_bitmap |= SZ_4K | SZ_2M | SZ_1G; - if (arm_smmu_ops.pgsize_bitmap == -1UL) - arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap; - else - arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap; + /* Input address size */ + if (FIELD_GET(IDR5_VAX, reg) == IDR5_VAX_52_BIT) + smmu->features |= ARM_SMMU_FEAT_VAX; /* Output address size */ - switch (reg & IDR5_OAS_MASK << IDR5_OAS_SHIFT) { + switch (FIELD_GET(IDR5_OAS, reg)) { case IDR5_OAS_32_BIT: smmu->oas = 32; break; @@ -2735,6 +2670,10 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) case IDR5_OAS_44_BIT: smmu->oas = 44; break; + case IDR5_OAS_52_BIT: + smmu->oas = 52; + smmu->pgsize_bitmap |= 1ULL << 42; /* 4TB */ + break; default: dev_info(smmu->dev, "unknown output address size. Truncating to 48-bit\n"); @@ -2743,6 +2682,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) smmu->oas = 48; } + if (arm_smmu_ops.pgsize_bitmap == -1UL) + arm_smmu_ops.pgsize_bitmap = smmu->pgsize_bitmap; + else + arm_smmu_ops.pgsize_bitmap |= smmu->pgsize_bitmap; + /* Set the DMA mask for our table walker */ if (dma_set_mask_and_coherent(smmu->dev, DMA_BIT_MASK(smmu->oas))) dev_warn(smmu->dev, diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 25914d36c5ac..f05f3cf90756 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -19,6 +19,7 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/acpi_iort.h> #include <linux/device.h> #include <linux/dma-iommu.h> #include <linux/gfp.h> @@ -167,13 +168,18 @@ EXPORT_SYMBOL(iommu_put_dma_cookie); * * IOMMU drivers can use this to implement their .get_resv_regions callback * for general non-IOMMU-specific reservations. Currently, this covers host - * bridge windows for PCI devices. + * bridge windows for PCI devices and GICv3 ITS region reservation on ACPI + * based ARM platforms that may require HW MSI reservation. */ void iommu_dma_get_resv_regions(struct device *dev, struct list_head *list) { struct pci_host_bridge *bridge; struct resource_entry *window; + if (!is_of_node(dev->iommu_fwspec->iommu_fwnode) && + iort_iommu_msi_get_resv_regions(dev, list) < 0) + return; + if (!dev_is_pci(dev)) return; diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index 9a7ffd13c7f0..accf58388bdb 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -806,7 +806,7 @@ int __init dmar_dev_scope_init(void) return dmar_dev_scope_status; } -void dmar_register_bus_notifier(void) +void __init dmar_register_bus_notifier(void) { bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb); } diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index c5f4f7691b57..85879cfec52f 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1239,17 +1239,6 @@ static phys_addr_t exynos_iommu_iova_to_phys(struct iommu_domain *iommu_domain, return phys; } -static struct iommu_group *get_device_iommu_group(struct device *dev) -{ - struct iommu_group *group; - - group = iommu_group_get(dev); - if (!group) - group = iommu_group_alloc(); - - return group; -} - static int exynos_iommu_add_device(struct device *dev) { struct exynos_iommu_owner *owner = dev->archdata.iommu; @@ -1345,7 +1334,7 @@ static const struct iommu_ops exynos_iommu_ops = { .unmap = exynos_iommu_unmap, .map_sg = default_iommu_map_sg, .iova_to_phys = exynos_iommu_iova_to_phys, - .device_group = get_device_iommu_group, + .device_group = generic_device_group, .add_device = exynos_iommu_add_device, .remove_device = exynos_iommu_remove_device, .pgsize_bitmap = SECT_SIZE | LPAGE_SIZE | SPAGE_SIZE, diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 24d1b1b42013..749d8f235346 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -5043,7 +5043,6 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, { struct dmar_domain *dmar_domain = to_dmar_domain(domain); struct page *freelist = NULL; - struct intel_iommu *iommu; unsigned long start_pfn, last_pfn; unsigned int npages; int iommu_id, level = 0; @@ -5062,12 +5061,9 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, npages = last_pfn - start_pfn + 1; - for_each_domain_iommu(iommu_id, dmar_domain) { - iommu = g_iommus[iommu_id]; - + for_each_domain_iommu(iommu_id, dmar_domain) iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain, start_pfn, npages, !freelist, 0); - } dma_free_pagelist(freelist); diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 99bc9bd64b9e..e8cd984cf9c8 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -396,6 +396,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ pasid_max - 1, GFP_KERNEL); if (ret < 0) { kfree(svm); + kfree(sdev); goto out; } svm->pasid = ret; @@ -422,17 +423,13 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_ iommu->pasid_table[svm->pasid].val = pasid_entry_val; wmb(); - /* In caching mode, we still have to flush with PASID 0 when - * a PASID table entry becomes present. Not entirely clear - * *why* that would be the case — surely we could just issue - * a flush with the PASID value that we've changed? The PASID - * is the index into the table, after all. It's not like domain - * IDs in the case of the equivalent context-entry change in - * caching mode. And for that matter it's not entirely clear why - * a VMM would be in the business of caching the PASID table - * anyway. Surely that can be left entirely to the guest? */ + + /* + * Flush PASID cache when a PASID table entry becomes + * present. + */ if (cap_caching_mode(iommu->cap)) - intel_flush_pasid_dev(svm, sdev, 0); + intel_flush_pasid_dev(svm, sdev, svm->pasid); } list_add_rcu(&sdev->list, &svm->devs); diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 2ca08dc9331c..10e4a3d11c02 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -357,8 +357,8 @@ static bool arm_v7s_pte_is_cont(arm_v7s_iopte pte, int lvl) return false; } -static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long, - size_t, int, arm_v7s_iopte *); +static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *, unsigned long, + size_t, int, arm_v7s_iopte *); static int arm_v7s_init_pte(struct arm_v7s_io_pgtable *data, unsigned long iova, phys_addr_t paddr, int prot, @@ -541,9 +541,10 @@ static arm_v7s_iopte arm_v7s_split_cont(struct arm_v7s_io_pgtable *data, return pte; } -static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, - unsigned long iova, size_t size, - arm_v7s_iopte blk_pte, arm_v7s_iopte *ptep) +static size_t arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, + unsigned long iova, size_t size, + arm_v7s_iopte blk_pte, + arm_v7s_iopte *ptep) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_v7s_iopte pte, *tablep; @@ -584,9 +585,9 @@ static int arm_v7s_split_blk_unmap(struct arm_v7s_io_pgtable *data, return size; } -static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_v7s_iopte *ptep) +static size_t __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_v7s_iopte *ptep) { arm_v7s_iopte pte[ARM_V7S_CONT_PAGES]; struct io_pgtable *iop = &data->iop; @@ -656,8 +657,8 @@ static int __arm_v7s_unmap(struct arm_v7s_io_pgtable *data, return __arm_v7s_unmap(data, iova, size, lvl + 1, ptep); } -static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) +static size_t arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size) { struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops); diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 51e5c43caed1..39c2a056da21 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -21,6 +21,7 @@ #define pr_fmt(fmt) "arm-lpae io-pgtable: " fmt #include <linux/atomic.h> +#include <linux/bitops.h> #include <linux/iommu.h> #include <linux/kernel.h> #include <linux/sizes.h> @@ -32,7 +33,7 @@ #include "io-pgtable.h" -#define ARM_LPAE_MAX_ADDR_BITS 48 +#define ARM_LPAE_MAX_ADDR_BITS 52 #define ARM_LPAE_S2_MAX_CONCAT_PAGES 16 #define ARM_LPAE_MAX_LEVELS 4 @@ -86,6 +87,8 @@ #define ARM_LPAE_PTE_TYPE_TABLE 3 #define ARM_LPAE_PTE_TYPE_PAGE 3 +#define ARM_LPAE_PTE_ADDR_MASK GENMASK_ULL(47,12) + #define ARM_LPAE_PTE_NSTABLE (((arm_lpae_iopte)1) << 63) #define ARM_LPAE_PTE_XN (((arm_lpae_iopte)3) << 53) #define ARM_LPAE_PTE_AF (((arm_lpae_iopte)1) << 10) @@ -159,6 +162,7 @@ #define ARM_LPAE_TCR_PS_42_BIT 0x3ULL #define ARM_LPAE_TCR_PS_44_BIT 0x4ULL #define ARM_LPAE_TCR_PS_48_BIT 0x5ULL +#define ARM_LPAE_TCR_PS_52_BIT 0x6ULL #define ARM_LPAE_MAIR_ATTR_SHIFT(n) ((n) << 3) #define ARM_LPAE_MAIR_ATTR_MASK 0xff @@ -170,9 +174,7 @@ #define ARM_LPAE_MAIR_ATTR_IDX_DEV 2 /* IOPTE accessors */ -#define iopte_deref(pte,d) \ - (__va((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1) \ - & ~(ARM_LPAE_GRANULE(d) - 1ULL))) +#define iopte_deref(pte,d) __va(iopte_to_paddr(pte, d)) #define iopte_type(pte,l) \ (((pte) >> ARM_LPAE_PTE_TYPE_SHIFT) & ARM_LPAE_PTE_TYPE_MASK) @@ -184,12 +186,6 @@ (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_PAGE) : \ (iopte_type(pte,l) == ARM_LPAE_PTE_TYPE_BLOCK)) -#define iopte_to_pfn(pte,d) \ - (((pte) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) >> (d)->pg_shift) - -#define pfn_to_iopte(pfn,d) \ - (((pfn) << (d)->pg_shift) & ((1ULL << ARM_LPAE_MAX_ADDR_BITS) - 1)) - struct arm_lpae_io_pgtable { struct io_pgtable iop; @@ -203,6 +199,27 @@ struct arm_lpae_io_pgtable { typedef u64 arm_lpae_iopte; +static arm_lpae_iopte paddr_to_iopte(phys_addr_t paddr, + struct arm_lpae_io_pgtable *data) +{ + arm_lpae_iopte pte = paddr; + + /* Of the bits which overlap, either 51:48 or 15:12 are always RES0 */ + return (pte | (pte >> (48 - 12))) & ARM_LPAE_PTE_ADDR_MASK; +} + +static phys_addr_t iopte_to_paddr(arm_lpae_iopte pte, + struct arm_lpae_io_pgtable *data) +{ + u64 paddr = pte & ARM_LPAE_PTE_ADDR_MASK; + + if (data->pg_shift < 16) + return paddr; + + /* Rotate the packed high-order bits back to the top */ + return (paddr | (paddr << (48 - 12))) & (ARM_LPAE_PTE_ADDR_MASK << 4); +} + static bool selftest_running = false; static dma_addr_t __arm_lpae_dma_addr(void *pages) @@ -268,9 +285,9 @@ static void __arm_lpae_set_pte(arm_lpae_iopte *ptep, arm_lpae_iopte pte, __arm_lpae_sync_pte(ptep, cfg); } -static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep); +static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep); static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, phys_addr_t paddr, arm_lpae_iopte prot, @@ -287,7 +304,7 @@ static void __arm_lpae_init_pte(struct arm_lpae_io_pgtable *data, pte |= ARM_LPAE_PTE_TYPE_BLOCK; pte |= ARM_LPAE_PTE_AF | ARM_LPAE_PTE_SH_IS; - pte |= pfn_to_iopte(paddr >> data->pg_shift, data); + pte |= paddr_to_iopte(paddr, data); __arm_lpae_set_pte(ptep, pte, &data->iop.cfg); } @@ -506,10 +523,10 @@ static void arm_lpae_free_pgtable(struct io_pgtable *iop) kfree(data); } -static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, - arm_lpae_iopte blk_pte, int lvl, - arm_lpae_iopte *ptep) +static size_t arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, + arm_lpae_iopte blk_pte, int lvl, + arm_lpae_iopte *ptep) { struct io_pgtable_cfg *cfg = &data->iop.cfg; arm_lpae_iopte pte, *tablep; @@ -528,7 +545,7 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, if (size == split_sz) unmap_idx = ARM_LPAE_LVL_IDX(iova, lvl, data); - blk_paddr = iopte_to_pfn(blk_pte, data) << data->pg_shift; + blk_paddr = iopte_to_paddr(blk_pte, data); pte = iopte_prot(blk_pte); for (i = 0; i < tablesz / sizeof(pte); i++, blk_paddr += split_sz) { @@ -560,9 +577,9 @@ static int arm_lpae_split_blk_unmap(struct arm_lpae_io_pgtable *data, return size; } -static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, - unsigned long iova, size_t size, int lvl, - arm_lpae_iopte *ptep) +static size_t __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, + unsigned long iova, size_t size, int lvl, + arm_lpae_iopte *ptep) { arm_lpae_iopte pte; struct io_pgtable *iop = &data->iop; @@ -606,8 +623,8 @@ static int __arm_lpae_unmap(struct arm_lpae_io_pgtable *data, return __arm_lpae_unmap(data, iova, size, lvl + 1, ptep); } -static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, - size_t size) +static size_t arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova, + size_t size) { struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops); arm_lpae_iopte *ptep = data->pgd; @@ -652,12 +669,13 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops, found_translation: iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1); - return ((phys_addr_t)iopte_to_pfn(pte,data) << data->pg_shift) | iova; + return iopte_to_paddr(pte, data) | iova; } static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) { - unsigned long granule; + unsigned long granule, page_sizes; + unsigned int max_addr_bits = 48; /* * We need to restrict the supported page sizes to match the @@ -677,17 +695,24 @@ static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg) switch (granule) { case SZ_4K: - cfg->pgsize_bitmap &= (SZ_4K | SZ_2M | SZ_1G); + page_sizes = (SZ_4K | SZ_2M | SZ_1G); break; case SZ_16K: - cfg->pgsize_bitmap &= (SZ_16K | SZ_32M); + page_sizes = (SZ_16K | SZ_32M); break; case SZ_64K: - cfg->pgsize_bitmap &= (SZ_64K | SZ_512M); + max_addr_bits = 52; + page_sizes = (SZ_64K | SZ_512M); + if (cfg->oas > 48) + page_sizes |= 1ULL << 42; /* 4TB */ break; default: - cfg->pgsize_bitmap = 0; + page_sizes = 0; } + + cfg->pgsize_bitmap &= page_sizes; + cfg->ias = min(cfg->ias, max_addr_bits); + cfg->oas = min(cfg->oas, max_addr_bits); } static struct arm_lpae_io_pgtable * @@ -784,6 +809,9 @@ arm_64_lpae_alloc_pgtable_s1(struct io_pgtable_cfg *cfg, void *cookie) case 48: reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_IPS_SHIFT); break; + case 52: + reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_IPS_SHIFT); + break; default: goto out_free_data; } @@ -891,6 +919,9 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) case 48: reg |= (ARM_LPAE_TCR_PS_48_BIT << ARM_LPAE_TCR_PS_SHIFT); break; + case 52: + reg |= (ARM_LPAE_TCR_PS_52_BIT << ARM_LPAE_TCR_PS_SHIFT); + break; default: goto out_free_data; } diff --git a/drivers/iommu/io-pgtable.h b/drivers/iommu/io-pgtable.h index cd2e1eafffe6..2df79093cad9 100644 --- a/drivers/iommu/io-pgtable.h +++ b/drivers/iommu/io-pgtable.h @@ -119,8 +119,8 @@ struct io_pgtable_cfg { struct io_pgtable_ops { int (*map)(struct io_pgtable_ops *ops, unsigned long iova, phys_addr_t paddr, size_t size, int prot); - int (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, - size_t size); + size_t (*unmap)(struct io_pgtable_ops *ops, unsigned long iova, + size_t size); phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops, unsigned long iova); }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 69fef991c651..d2aa23202bb9 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1573,10 +1573,10 @@ static size_t __iommu_unmap(struct iommu_domain *domain, if (unlikely(ops->unmap == NULL || domain->pgsize_bitmap == 0UL)) - return -ENODEV; + return 0; if (unlikely(!(domain->type & __IOMMU_DOMAIN_PAGING))) - return -EINVAL; + return 0; /* find out the minimum page size supported */ min_pagesz = 1 << __ffs(domain->pgsize_bitmap); @@ -1589,7 +1589,7 @@ static size_t __iommu_unmap(struct iommu_domain *domain, if (!IS_ALIGNED(iova | size, min_pagesz)) { pr_err("unaligned: iova 0x%lx size 0x%zx min_pagesz 0x%x\n", iova, size, min_pagesz); - return -EINVAL; + return 0; } pr_debug("unmap this: iova 0x%lx size 0x%zx\n", iova, size); diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f227d73e7bf6..f2832a10fcea 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -60,7 +60,7 @@ (((prot) & 0x3) << F_MMU_TF_PROTECT_SEL_SHIFT(data)) #define REG_MMU_IVRP_PADDR 0x114 -#define F_MMU_IVRP_PA_SET(pa, ext) (((pa) >> 1) | ((!!(ext)) << 31)) + #define REG_MMU_VLD_PA_RNG 0x118 #define F_MMU_VLD_PA_RNG(EA, SA) (((EA) << 8) | (SA)) @@ -539,8 +539,13 @@ static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) F_INT_PRETETCH_TRANSATION_FIFO_FAULT; writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL); - writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB), - data->base + REG_MMU_IVRP_PADDR); + if (data->m4u_plat == M4U_MT8173) + regval = (data->protect_base >> 1) | (data->enable_4GB << 31); + else + regval = lower_32_bits(data->protect_base) | + upper_32_bits(data->protect_base); + writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR); + if (data->enable_4GB && data->m4u_plat != M4U_MT8173) { /* * If 4GB mode is enabled, the validate PA range is from @@ -695,6 +700,7 @@ static int __maybe_unused mtk_iommu_suspend(struct device *dev) reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG); reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0); reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL); + reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR); clk_disable_unprepare(data->bclk); return 0; } @@ -717,8 +723,7 @@ static int __maybe_unused mtk_iommu_resume(struct device *dev) writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG); writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0); writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL); - writel_relaxed(F_MMU_IVRP_PA_SET(data->protect_base, data->enable_4GB), - base + REG_MMU_IVRP_PADDR); + writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR); if (data->m4u_dom) writel(data->m4u_dom->cfg.arm_v7s_cfg.ttbr[0], base + REG_MMU_PT_BASE_ADDR); diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index b4451a1c7c2f..778498b8633f 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -32,6 +32,7 @@ struct mtk_iommu_suspend_reg { u32 ctrl_reg; u32 int_control0; u32 int_main_control; + u32 ivrp_paddr; }; enum mtk_iommu_plat { diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 5a96fd14ac22..a7c2a973784f 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -417,20 +417,12 @@ static int mtk_iommu_create_mapping(struct device *dev, m4udev->archdata.iommu = mtk_mapping; } - ret = arm_iommu_attach_device(dev, mtk_mapping); - if (ret) - goto err_release_mapping; - return 0; - -err_release_mapping: - arm_iommu_release_mapping(mtk_mapping); - m4udev->archdata.iommu = NULL; - return ret; } static int mtk_iommu_add_device(struct device *dev) { + struct dma_iommu_mapping *mtk_mapping; struct of_phandle_args iommu_spec; struct of_phandle_iterator it; struct mtk_iommu_data *data; @@ -451,15 +443,30 @@ static int mtk_iommu_add_device(struct device *dev) if (!dev->iommu_fwspec || dev->iommu_fwspec->ops != &mtk_iommu_ops) return -ENODEV; /* Not a iommu client device */ - data = dev->iommu_fwspec->iommu_priv; - iommu_device_link(&data->iommu, dev); - - group = iommu_group_get_for_dev(dev); + /* + * This is a short-term bodge because the ARM DMA code doesn't + * understand multi-device groups, but we have to call into it + * successfully (and not just rely on a normal IOMMU API attach + * here) in order to set the correct DMA API ops on @dev. + */ + group = iommu_group_alloc(); if (IS_ERR(group)) return PTR_ERR(group); + err = iommu_group_add_device(group, dev); iommu_group_put(group); - return 0; + if (err) + return err; + + data = dev->iommu_fwspec->iommu_priv; + mtk_mapping = data->dev->archdata.iommu; + err = arm_iommu_attach_device(dev, mtk_mapping); + if (err) { + iommu_group_remove_device(dev); + return err; + } + + return iommu_device_link(&data->iommu, dev);; } static void mtk_iommu_remove_device(struct device *dev) @@ -476,24 +483,6 @@ static void mtk_iommu_remove_device(struct device *dev) iommu_fwspec_free(dev); } -static struct iommu_group *mtk_iommu_device_group(struct device *dev) -{ - struct mtk_iommu_data *data = dev->iommu_fwspec->iommu_priv; - - if (!data) - return ERR_PTR(-ENODEV); - - /* All the client devices are in the same m4u iommu-group */ - if (!data->m4u_group) { - data->m4u_group = iommu_group_alloc(); - if (IS_ERR(data->m4u_group)) - dev_err(dev, "Failed to allocate M4U IOMMU group\n"); - } else { - iommu_group_ref_get(data->m4u_group); - } - return data->m4u_group; -} - static int mtk_iommu_hw_init(const struct mtk_iommu_data *data) { u32 regval; @@ -546,7 +535,6 @@ static struct iommu_ops mtk_iommu_ops = { .iova_to_phys = mtk_iommu_iova_to_phys, .add_device = mtk_iommu_add_device, .remove_device = mtk_iommu_remove_device, - .device_group = mtk_iommu_device_group, .pgsize_bitmap = ~0UL << MT2701_IOMMU_PAGE_SHIFT, }; diff --git a/drivers/iommu/omap-iommu.c b/drivers/iommu/omap-iommu.c index e135ab830ebf..c33b7b104e72 100644 --- a/drivers/iommu/omap-iommu.c +++ b/drivers/iommu/omap-iommu.c @@ -1536,7 +1536,7 @@ static struct iommu_group *omap_iommu_device_group(struct device *dev) struct iommu_group *group = ERR_PTR(-EINVAL); if (arch_data->iommu_dev) - group = arch_data->iommu_dev->group; + group = iommu_group_ref_get(arch_data->iommu_dev->group); return group; } diff --git a/drivers/iommu/rockchip-iommu.c b/drivers/iommu/rockchip-iommu.c index 9d991c2d8767..5fc8656c60f9 100644 --- a/drivers/iommu/rockchip-iommu.c +++ b/drivers/iommu/rockchip-iommu.c @@ -4,6 +4,7 @@ * published by the Free Software Foundation. */ +#include <linux/clk.h> #include <linux/compiler.h> #include <linux/delay.h> #include <linux/device.h> @@ -13,13 +14,15 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iommu.h> -#include <linux/jiffies.h> +#include <linux/iopoll.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_iommu.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -36,7 +39,10 @@ #define RK_MMU_AUTO_GATING 0x24 #define DTE_ADDR_DUMMY 0xCAFEBABE -#define FORCE_RESET_TIMEOUT 100 /* ms */ + +#define RK_MMU_POLL_PERIOD_US 100 +#define RK_MMU_FORCE_RESET_TIMEOUT_US 100000 +#define RK_MMU_POLL_TIMEOUT_US 1000 /* RK_MMU_STATUS fields */ #define RK_MMU_STATUS_PAGING_ENABLED BIT(0) @@ -73,11 +79,8 @@ */ #define RK_IOMMU_PGSIZE_BITMAP 0x007ff000 -#define IOMMU_REG_POLL_COUNT_FAST 1000 - struct rk_iommu_domain { struct list_head iommus; - struct platform_device *pdev; u32 *dt; /* page directory table */ dma_addr_t dt_dma; spinlock_t iommus_lock; /* lock for iommus list */ @@ -86,24 +89,37 @@ struct rk_iommu_domain { struct iommu_domain domain; }; +/* list of clocks required by IOMMU */ +static const char * const rk_iommu_clocks[] = { + "aclk", "iface", +}; + struct rk_iommu { struct device *dev; void __iomem **bases; int num_mmu; - int *irq; - int num_irq; + struct clk_bulk_data *clocks; + int num_clocks; bool reset_disabled; struct iommu_device iommu; struct list_head node; /* entry in rk_iommu_domain.iommus */ struct iommu_domain *domain; /* domain to which iommu is attached */ + struct iommu_group *group; +}; + +struct rk_iommudata { + struct device_link *link; /* runtime PM link from IOMMU to master */ + struct rk_iommu *iommu; }; +static struct device *dma_dev; + static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma, unsigned int count) { size_t size = count * sizeof(u32); /* count of u32 entry */ - dma_sync_single_for_device(&dom->pdev->dev, dma, size, DMA_TO_DEVICE); + dma_sync_single_for_device(dma_dev, dma, size, DMA_TO_DEVICE); } static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom) @@ -111,27 +127,6 @@ static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom) return container_of(dom, struct rk_iommu_domain, domain); } -/** - * Inspired by _wait_for in intel_drv.h - * This is NOT safe for use in interrupt context. - * - * Note that it's important that we check the condition again after having - * timed out, since the timeout could be due to preemption or similar and - * we've never had a chance to check the condition before the timeout. - */ -#define rk_wait_for(COND, MS) ({ \ - unsigned long timeout__ = jiffies + msecs_to_jiffies(MS) + 1; \ - int ret__ = 0; \ - while (!(COND)) { \ - if (time_after(jiffies, timeout__)) { \ - ret__ = (COND) ? 0 : -ETIMEDOUT; \ - break; \ - } \ - usleep_range(50, 100); \ - } \ - ret__; \ -}) - /* * The Rockchip rk3288 iommu uses a 2-level page table. * The first level is the "Directory Table" (DT). @@ -296,19 +291,21 @@ static void rk_iommu_base_command(void __iomem *base, u32 command) { writel(command, base + RK_MMU_COMMAND); } -static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova, +static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova_start, size_t size) { int i; - - dma_addr_t iova_end = iova + size; + dma_addr_t iova_end = iova_start + size; /* * TODO(djkurtz): Figure out when it is more efficient to shootdown the * entire iotlb rather than iterate over individual iovas. */ - for (i = 0; i < iommu->num_mmu; i++) - for (; iova < iova_end; iova += SPAGE_SIZE) + for (i = 0; i < iommu->num_mmu; i++) { + dma_addr_t iova; + + for (iova = iova_start; iova < iova_end; iova += SPAGE_SIZE) rk_iommu_write(iommu->bases[i], RK_MMU_ZAP_ONE_LINE, iova); + } } static bool rk_iommu_is_stall_active(struct rk_iommu *iommu) @@ -335,9 +332,21 @@ static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu) return enable; } +static bool rk_iommu_is_reset_done(struct rk_iommu *iommu) +{ + bool done = true; + int i; + + for (i = 0; i < iommu->num_mmu; i++) + done &= rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0; + + return done; +} + static int rk_iommu_enable_stall(struct rk_iommu *iommu) { int ret, i; + bool val; if (rk_iommu_is_stall_active(iommu)) return 0; @@ -348,7 +357,9 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu) rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL); - ret = rk_wait_for(rk_iommu_is_stall_active(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val, + val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n", @@ -360,13 +371,16 @@ static int rk_iommu_enable_stall(struct rk_iommu *iommu) static int rk_iommu_disable_stall(struct rk_iommu *iommu) { int ret, i; + bool val; if (!rk_iommu_is_stall_active(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL); - ret = rk_wait_for(!rk_iommu_is_stall_active(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val, + !val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n", @@ -378,13 +392,16 @@ static int rk_iommu_disable_stall(struct rk_iommu *iommu) static int rk_iommu_enable_paging(struct rk_iommu *iommu) { int ret, i; + bool val; if (rk_iommu_is_paging_enabled(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING); - ret = rk_wait_for(rk_iommu_is_paging_enabled(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val, + val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n", @@ -396,13 +413,16 @@ static int rk_iommu_enable_paging(struct rk_iommu *iommu) static int rk_iommu_disable_paging(struct rk_iommu *iommu) { int ret, i; + bool val; if (!rk_iommu_is_paging_enabled(iommu)) return 0; rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING); - ret = rk_wait_for(!rk_iommu_is_paging_enabled(iommu), 1); + ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val, + !val, RK_MMU_POLL_PERIOD_US, + RK_MMU_POLL_TIMEOUT_US); if (ret) for (i = 0; i < iommu->num_mmu; i++) dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n", @@ -415,6 +435,7 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) { int ret, i; u32 dte_addr; + bool val; if (iommu->reset_disabled) return 0; @@ -435,13 +456,12 @@ static int rk_iommu_force_reset(struct rk_iommu *iommu) rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET); - for (i = 0; i < iommu->num_mmu; i++) { - ret = rk_wait_for(rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0x00000000, - FORCE_RESET_TIMEOUT); - if (ret) { - dev_err(iommu->dev, "FORCE_RESET command timed out\n"); - return ret; - } + ret = readx_poll_timeout(rk_iommu_is_reset_done, iommu, val, + val, RK_MMU_FORCE_RESET_TIMEOUT_US, + RK_MMU_POLL_TIMEOUT_US); + if (ret) { + dev_err(iommu->dev, "FORCE_RESET command timed out\n"); + return ret; } return 0; @@ -503,6 +523,12 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) irqreturn_t ret = IRQ_NONE; int i; + if (WARN_ON(!pm_runtime_get_if_in_use(iommu->dev))) + return 0; + + if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks))) + goto out; + for (i = 0; i < iommu->num_mmu; i++) { int_status = rk_iommu_read(iommu->bases[i], RK_MMU_INT_STATUS); if (int_status == 0) @@ -549,6 +575,10 @@ static irqreturn_t rk_iommu_irq(int irq, void *dev_id) rk_iommu_write(iommu->bases[i], RK_MMU_INT_CLEAR, int_status); } + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + +out: + pm_runtime_put(iommu->dev); return ret; } @@ -590,8 +620,17 @@ static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain, spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_for_each(pos, &rk_domain->iommus) { struct rk_iommu *iommu; + iommu = list_entry(pos, struct rk_iommu, node); - rk_iommu_zap_lines(iommu, iova, size); + + /* Only zap TLBs of IOMMUs that are powered on. */ + if (pm_runtime_get_if_in_use(iommu->dev)) { + WARN_ON(clk_bulk_enable(iommu->num_clocks, + iommu->clocks)); + rk_iommu_zap_lines(iommu, iova, size); + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + pm_runtime_put(iommu->dev); + } } spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); } @@ -608,7 +647,6 @@ static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain, static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, dma_addr_t iova) { - struct device *dev = &rk_domain->pdev->dev; u32 *page_table, *dte_addr; u32 dte_index, dte; phys_addr_t pt_phys; @@ -626,9 +664,9 @@ static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain, if (!page_table) return ERR_PTR(-ENOMEM); - pt_dma = dma_map_single(dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE); - if (dma_mapping_error(dev, pt_dma)) { - dev_err(dev, "DMA mapping error while allocating page table\n"); + pt_dma = dma_map_single(dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dma_dev, pt_dma)) { + dev_err(dma_dev, "DMA mapping error while allocating page table\n"); free_page((unsigned long)page_table); return ERR_PTR(-ENOMEM); } @@ -790,52 +828,46 @@ static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova, static struct rk_iommu *rk_iommu_from_dev(struct device *dev) { - struct iommu_group *group; - struct device *iommu_dev; - struct rk_iommu *rk_iommu; + struct rk_iommudata *data = dev->archdata.iommu; - group = iommu_group_get(dev); - if (!group) - return NULL; - iommu_dev = iommu_group_get_iommudata(group); - rk_iommu = dev_get_drvdata(iommu_dev); - iommu_group_put(group); + return data ? data->iommu : NULL; +} + +/* Must be called with iommu powered on and attached */ +static void rk_iommu_disable(struct rk_iommu *iommu) +{ + int i; - return rk_iommu; + /* Ignore error while disabling, just keep going */ + WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)); + rk_iommu_enable_stall(iommu); + rk_iommu_disable_paging(iommu); + for (i = 0; i < iommu->num_mmu; i++) { + rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0); + rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0); + } + rk_iommu_disable_stall(iommu); + clk_bulk_disable(iommu->num_clocks, iommu->clocks); } -static int rk_iommu_attach_device(struct iommu_domain *domain, - struct device *dev) +/* Must be called with iommu powered on and attached */ +static int rk_iommu_enable(struct rk_iommu *iommu) { - struct rk_iommu *iommu; + struct iommu_domain *domain = iommu->domain; struct rk_iommu_domain *rk_domain = to_rk_domain(domain); - unsigned long flags; int ret, i; - /* - * Allow 'virtual devices' (e.g., drm) to attach to domain. - * Such a device does not belong to an iommu group. - */ - iommu = rk_iommu_from_dev(dev); - if (!iommu) - return 0; + ret = clk_bulk_enable(iommu->num_clocks, iommu->clocks); + if (ret) + return ret; ret = rk_iommu_enable_stall(iommu); if (ret) - return ret; + goto out_disable_clocks; ret = rk_iommu_force_reset(iommu); if (ret) - return ret; - - iommu->domain = domain; - - for (i = 0; i < iommu->num_irq; i++) { - ret = devm_request_irq(iommu->dev, iommu->irq[i], rk_iommu_irq, - IRQF_SHARED, dev_name(dev), iommu); - if (ret) - return ret; - } + goto out_disable_stall; for (i = 0; i < iommu->num_mmu; i++) { rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, @@ -845,18 +877,12 @@ static int rk_iommu_attach_device(struct iommu_domain *domain, } ret = rk_iommu_enable_paging(iommu); - if (ret) - return ret; - - spin_lock_irqsave(&rk_domain->iommus_lock, flags); - list_add_tail(&iommu->node, &rk_domain->iommus); - spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); - - dev_dbg(dev, "Attached to iommu domain\n"); +out_disable_stall: rk_iommu_disable_stall(iommu); - - return 0; +out_disable_clocks: + clk_bulk_disable(iommu->num_clocks, iommu->clocks); + return ret; } static void rk_iommu_detach_device(struct iommu_domain *domain, @@ -865,60 +891,90 @@ static void rk_iommu_detach_device(struct iommu_domain *domain, struct rk_iommu *iommu; struct rk_iommu_domain *rk_domain = to_rk_domain(domain); unsigned long flags; - int i; /* Allow 'virtual devices' (eg drm) to detach from domain */ iommu = rk_iommu_from_dev(dev); if (!iommu) return; + dev_dbg(dev, "Detaching from iommu domain\n"); + + /* iommu already detached */ + if (iommu->domain != domain) + return; + + iommu->domain = NULL; + spin_lock_irqsave(&rk_domain->iommus_lock, flags); list_del_init(&iommu->node); spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); - /* Ignore error while disabling, just keep going */ - rk_iommu_enable_stall(iommu); - rk_iommu_disable_paging(iommu); - for (i = 0; i < iommu->num_mmu; i++) { - rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0); - rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0); + if (pm_runtime_get_if_in_use(iommu->dev)) { + rk_iommu_disable(iommu); + pm_runtime_put(iommu->dev); } - rk_iommu_disable_stall(iommu); +} - for (i = 0; i < iommu->num_irq; i++) - devm_free_irq(iommu->dev, iommu->irq[i], iommu); +static int rk_iommu_attach_device(struct iommu_domain *domain, + struct device *dev) +{ + struct rk_iommu *iommu; + struct rk_iommu_domain *rk_domain = to_rk_domain(domain); + unsigned long flags; + int ret; - iommu->domain = NULL; + /* + * Allow 'virtual devices' (e.g., drm) to attach to domain. + * Such a device does not belong to an iommu group. + */ + iommu = rk_iommu_from_dev(dev); + if (!iommu) + return 0; + + dev_dbg(dev, "Attaching to iommu domain\n"); + + /* iommu already attached */ + if (iommu->domain == domain) + return 0; - dev_dbg(dev, "Detached from iommu domain\n"); + if (iommu->domain) + rk_iommu_detach_device(iommu->domain, dev); + + iommu->domain = domain; + + spin_lock_irqsave(&rk_domain->iommus_lock, flags); + list_add_tail(&iommu->node, &rk_domain->iommus); + spin_unlock_irqrestore(&rk_domain->iommus_lock, flags); + + if (!pm_runtime_get_if_in_use(iommu->dev)) + return 0; + + ret = rk_iommu_enable(iommu); + if (ret) + rk_iommu_detach_device(iommu->domain, dev); + + pm_runtime_put(iommu->dev); + + return ret; } static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) { struct rk_iommu_domain *rk_domain; - struct platform_device *pdev; - struct device *iommu_dev; if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA) return NULL; - /* Register a pdev per domain, so DMA API can base on this *dev - * even some virtual master doesn't have an iommu slave - */ - pdev = platform_device_register_simple("rk_iommu_domain", - PLATFORM_DEVID_AUTO, NULL, 0); - if (IS_ERR(pdev)) + if (!dma_dev) return NULL; - rk_domain = devm_kzalloc(&pdev->dev, sizeof(*rk_domain), GFP_KERNEL); + rk_domain = devm_kzalloc(dma_dev, sizeof(*rk_domain), GFP_KERNEL); if (!rk_domain) - goto err_unreg_pdev; - - rk_domain->pdev = pdev; + return NULL; if (type == IOMMU_DOMAIN_DMA && iommu_get_dma_cookie(&rk_domain->domain)) - goto err_unreg_pdev; + return NULL; /* * rk32xx iommus use a 2 level pagetable. @@ -929,11 +985,10 @@ static struct iommu_domain *rk_iommu_domain_alloc(unsigned type) if (!rk_domain->dt) goto err_put_cookie; - iommu_dev = &pdev->dev; - rk_domain->dt_dma = dma_map_single(iommu_dev, rk_domain->dt, + rk_domain->dt_dma = dma_map_single(dma_dev, rk_domain->dt, SPAGE_SIZE, DMA_TO_DEVICE); - if (dma_mapping_error(iommu_dev, rk_domain->dt_dma)) { - dev_err(iommu_dev, "DMA map error for DT\n"); + if (dma_mapping_error(dma_dev, rk_domain->dt_dma)) { + dev_err(dma_dev, "DMA map error for DT\n"); goto err_free_dt; } @@ -954,8 +1009,6 @@ err_free_dt: err_put_cookie: if (type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); -err_unreg_pdev: - platform_device_unregister(pdev); return NULL; } @@ -972,126 +1025,82 @@ static void rk_iommu_domain_free(struct iommu_domain *domain) if (rk_dte_is_pt_valid(dte)) { phys_addr_t pt_phys = rk_dte_pt_address(dte); u32 *page_table = phys_to_virt(pt_phys); - dma_unmap_single(&rk_domain->pdev->dev, pt_phys, + dma_unmap_single(dma_dev, pt_phys, SPAGE_SIZE, DMA_TO_DEVICE); free_page((unsigned long)page_table); } } - dma_unmap_single(&rk_domain->pdev->dev, rk_domain->dt_dma, + dma_unmap_single(dma_dev, rk_domain->dt_dma, SPAGE_SIZE, DMA_TO_DEVICE); free_page((unsigned long)rk_domain->dt); if (domain->type == IOMMU_DOMAIN_DMA) iommu_put_dma_cookie(&rk_domain->domain); - - platform_device_unregister(rk_domain->pdev); } -static bool rk_iommu_is_dev_iommu_master(struct device *dev) +static int rk_iommu_add_device(struct device *dev) { - struct device_node *np = dev->of_node; - int ret; - - /* - * An iommu master has an iommus property containing a list of phandles - * to iommu nodes, each with an #iommu-cells property with value 0. - */ - ret = of_count_phandle_with_args(np, "iommus", "#iommu-cells"); - return (ret > 0); -} + struct iommu_group *group; + struct rk_iommu *iommu; + struct rk_iommudata *data; -static int rk_iommu_group_set_iommudata(struct iommu_group *group, - struct device *dev) -{ - struct device_node *np = dev->of_node; - struct platform_device *pd; - int ret; - struct of_phandle_args args; + data = dev->archdata.iommu; + if (!data) + return -ENODEV; - /* - * An iommu master has an iommus property containing a list of phandles - * to iommu nodes, each with an #iommu-cells property with value 0. - */ - ret = of_parse_phandle_with_args(np, "iommus", "#iommu-cells", 0, - &args); - if (ret) { - dev_err(dev, "of_parse_phandle_with_args(%pOF) => %d\n", - np, ret); - return ret; - } - if (args.args_count != 0) { - dev_err(dev, "incorrect number of iommu params found for %pOF (found %d, expected 0)\n", - args.np, args.args_count); - return -EINVAL; - } + iommu = rk_iommu_from_dev(dev); - pd = of_find_device_by_node(args.np); - of_node_put(args.np); - if (!pd) { - dev_err(dev, "iommu %pOF not found\n", args.np); - return -EPROBE_DEFER; - } + group = iommu_group_get_for_dev(dev); + if (IS_ERR(group)) + return PTR_ERR(group); + iommu_group_put(group); - /* TODO(djkurtz): handle multiple slave iommus for a single master */ - iommu_group_set_iommudata(group, &pd->dev, NULL); + iommu_device_link(&iommu->iommu, dev); + data->link = device_link_add(dev, iommu->dev, DL_FLAG_PM_RUNTIME); return 0; } -static int rk_iommu_add_device(struct device *dev) +static void rk_iommu_remove_device(struct device *dev) { - struct iommu_group *group; struct rk_iommu *iommu; - int ret; - - if (!rk_iommu_is_dev_iommu_master(dev)) - return -ENODEV; + struct rk_iommudata *data = dev->archdata.iommu; - group = iommu_group_get(dev); - if (!group) { - group = iommu_group_alloc(); - if (IS_ERR(group)) { - dev_err(dev, "Failed to allocate IOMMU group\n"); - return PTR_ERR(group); - } - } + iommu = rk_iommu_from_dev(dev); - ret = iommu_group_add_device(group, dev); - if (ret) - goto err_put_group; + device_link_del(data->link); + iommu_device_unlink(&iommu->iommu, dev); + iommu_group_remove_device(dev); +} - ret = rk_iommu_group_set_iommudata(group, dev); - if (ret) - goto err_remove_device; +static struct iommu_group *rk_iommu_device_group(struct device *dev) +{ + struct rk_iommu *iommu; iommu = rk_iommu_from_dev(dev); - if (iommu) - iommu_device_link(&iommu->iommu, dev); - - iommu_group_put(group); - - return 0; -err_remove_device: - iommu_group_remove_device(dev); -err_put_group: - iommu_group_put(group); - return ret; + return iommu_group_ref_get(iommu->group); } -static void rk_iommu_remove_device(struct device *dev) +static int rk_iommu_of_xlate(struct device *dev, + struct of_phandle_args *args) { - struct rk_iommu *iommu; + struct platform_device *iommu_dev; + struct rk_iommudata *data; - if (!rk_iommu_is_dev_iommu_master(dev)) - return; + data = devm_kzalloc(dma_dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; - iommu = rk_iommu_from_dev(dev); - if (iommu) - iommu_device_unlink(&iommu->iommu, dev); + iommu_dev = of_find_device_by_node(args->np); - iommu_group_remove_device(dev); + data->iommu = platform_get_drvdata(iommu_dev); + dev->archdata.iommu = data; + + of_dev_put(iommu_dev); + + return 0; } static const struct iommu_ops rk_iommu_ops = { @@ -1105,31 +1114,9 @@ static const struct iommu_ops rk_iommu_ops = { .add_device = rk_iommu_add_device, .remove_device = rk_iommu_remove_device, .iova_to_phys = rk_iommu_iova_to_phys, + .device_group = rk_iommu_device_group, .pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP, -}; - -static int rk_iommu_domain_probe(struct platform_device *pdev) -{ - struct device *dev = &pdev->dev; - - dev->dma_parms = devm_kzalloc(dev, sizeof(*dev->dma_parms), GFP_KERNEL); - if (!dev->dma_parms) - return -ENOMEM; - - /* Set dma_ops for dev, otherwise it would be dummy_dma_ops */ - arch_setup_dma_ops(dev, 0, DMA_BIT_MASK(32), NULL, false); - - dma_set_max_seg_size(dev, DMA_BIT_MASK(32)); - dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32)); - - return 0; -} - -static struct platform_driver rk_iommu_domain_driver = { - .probe = rk_iommu_domain_probe, - .driver = { - .name = "rk_iommu_domain", - }, + .of_xlate = rk_iommu_of_xlate, }; static int rk_iommu_probe(struct platform_device *pdev) @@ -1138,7 +1125,7 @@ static int rk_iommu_probe(struct platform_device *pdev) struct rk_iommu *iommu; struct resource *res; int num_res = pdev->num_resources; - int err, i; + int err, i, irq; iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL); if (!iommu) @@ -1165,50 +1152,108 @@ static int rk_iommu_probe(struct platform_device *pdev) if (iommu->num_mmu == 0) return PTR_ERR(iommu->bases[0]); - iommu->num_irq = platform_irq_count(pdev); - if (iommu->num_irq < 0) - return iommu->num_irq; - if (iommu->num_irq == 0) - return -ENXIO; - - iommu->irq = devm_kcalloc(dev, iommu->num_irq, sizeof(*iommu->irq), - GFP_KERNEL); - if (!iommu->irq) - return -ENOMEM; + i = 0; + while ((irq = platform_get_irq(pdev, i++)) != -ENXIO) { + if (irq < 0) + return irq; - for (i = 0; i < iommu->num_irq; i++) { - iommu->irq[i] = platform_get_irq(pdev, i); - if (iommu->irq[i] < 0) { - dev_err(dev, "Failed to get IRQ, %d\n", iommu->irq[i]); - return -ENXIO; - } + err = devm_request_irq(iommu->dev, irq, rk_iommu_irq, + IRQF_SHARED, dev_name(dev), iommu); + if (err) + return err; } iommu->reset_disabled = device_property_read_bool(dev, "rockchip,disable-mmu-reset"); - err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev)); + iommu->num_clocks = ARRAY_SIZE(rk_iommu_clocks); + iommu->clocks = devm_kcalloc(iommu->dev, iommu->num_clocks, + sizeof(*iommu->clocks), GFP_KERNEL); + if (!iommu->clocks) + return -ENOMEM; + + for (i = 0; i < iommu->num_clocks; ++i) + iommu->clocks[i].id = rk_iommu_clocks[i]; + + err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks); + if (err) + return err; + + err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks); if (err) return err; + iommu->group = iommu_group_alloc(); + if (IS_ERR(iommu->group)) { + err = PTR_ERR(iommu->group); + goto err_unprepare_clocks; + } + + err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev)); + if (err) + goto err_put_group; + iommu_device_set_ops(&iommu->iommu, &rk_iommu_ops); + iommu_device_set_fwnode(&iommu->iommu, &dev->of_node->fwnode); + err = iommu_device_register(&iommu->iommu); + if (err) + goto err_remove_sysfs; + + /* + * Use the first registered IOMMU device for domain to use with DMA + * API, since a domain might not physically correspond to a single + * IOMMU device.. + */ + if (!dma_dev) + dma_dev = &pdev->dev; + + bus_set_iommu(&platform_bus_type, &rk_iommu_ops); + pm_runtime_enable(dev); + + return 0; +err_remove_sysfs: + iommu_device_sysfs_remove(&iommu->iommu); +err_put_group: + iommu_group_put(iommu->group); +err_unprepare_clocks: + clk_bulk_unprepare(iommu->num_clocks, iommu->clocks); return err; } -static int rk_iommu_remove(struct platform_device *pdev) +static void rk_iommu_shutdown(struct platform_device *pdev) { - struct rk_iommu *iommu = platform_get_drvdata(pdev); + pm_runtime_force_suspend(&pdev->dev); +} - if (iommu) { - iommu_device_sysfs_remove(&iommu->iommu); - iommu_device_unregister(&iommu->iommu); - } +static int __maybe_unused rk_iommu_suspend(struct device *dev) +{ + struct rk_iommu *iommu = dev_get_drvdata(dev); + if (!iommu->domain) + return 0; + + rk_iommu_disable(iommu); return 0; } +static int __maybe_unused rk_iommu_resume(struct device *dev) +{ + struct rk_iommu *iommu = dev_get_drvdata(dev); + + if (!iommu->domain) + return 0; + + return rk_iommu_enable(iommu); +} + +static const struct dev_pm_ops rk_iommu_pm_ops = { + SET_RUNTIME_PM_OPS(rk_iommu_suspend, rk_iommu_resume, NULL) + SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) +}; + static const struct of_device_id rk_iommu_dt_ids[] = { { .compatible = "rockchip,iommu" }, { /* sentinel */ } @@ -1217,45 +1262,22 @@ MODULE_DEVICE_TABLE(of, rk_iommu_dt_ids); static struct platform_driver rk_iommu_driver = { .probe = rk_iommu_probe, - .remove = rk_iommu_remove, + .shutdown = rk_iommu_shutdown, .driver = { .name = "rk_iommu", .of_match_table = rk_iommu_dt_ids, + .pm = &rk_iommu_pm_ops, + .suppress_bind_attrs = true, }, }; static int __init rk_iommu_init(void) { - struct device_node *np; - int ret; - - np = of_find_matching_node(NULL, rk_iommu_dt_ids); - if (!np) - return 0; - - of_node_put(np); - - ret = bus_set_iommu(&platform_bus_type, &rk_iommu_ops); - if (ret) - return ret; - - ret = platform_driver_register(&rk_iommu_domain_driver); - if (ret) - return ret; - - ret = platform_driver_register(&rk_iommu_driver); - if (ret) - platform_driver_unregister(&rk_iommu_domain_driver); - return ret; + return platform_driver_register(&rk_iommu_driver); } -static void __exit rk_iommu_exit(void) -{ - platform_driver_unregister(&rk_iommu_driver); - platform_driver_unregister(&rk_iommu_domain_driver); -} - subsys_initcall(rk_iommu_init); -module_exit(rk_iommu_exit); + +IOMMU_OF_DECLARE(rk_iommu_of, "rockchip,iommu"); MODULE_DESCRIPTION("IOMMU API for Rockchip"); MODULE_AUTHOR("Simon Xue <xxm@rock-chips.com> and Daniel Kurtz <djkurtz@chromium.org>"); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 2982e93d2369..5416f2b2ac21 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3612,7 +3612,8 @@ static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header, return -ENOMEM; } - err = iort_register_domain_token(its_entry->translation_id, dom_handle); + err = iort_register_domain_token(its_entry->translation_id, res.start, + dom_handle); if (err) { pr_err("ITS@%pa: Unable to register GICv3 ITS domain token (ITS ID %d) to IORT\n", &res.start, its_entry->translation_id); diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index 24108bfad889..6193270e7b3d 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -400,10 +400,14 @@ static void skip_back_repeat_test(char *arg) int go_back = simple_strtol(arg, NULL, 10); repeat_test--; - if (repeat_test <= 0) + if (repeat_test <= 0) { ts.idx++; - else + } else { + if (repeat_test % 100 == 0) + v1printk("kgdbts:RUN ... %d remaining\n", repeat_test); + ts.idx -= go_back; + } fill_get_buf(ts.tst[ts.idx].get); } diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 02485e310c81..9e923cd1d80e 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -3080,6 +3080,7 @@ static void __exit mmc_blk_exit(void) mmc_unregister_driver(&mmc_driver); unregister_blkdev(MMC_BLOCK_MAJOR, "mmc"); unregister_chrdev_region(mmc_rpmb_devt, MAX_DEVICES); + bus_unregister(&mmc_rpmb_bus_type); } module_init(mmc_blk_init); diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index 712e08d9a45e..a0168e9e4fce 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -362,9 +362,9 @@ static void jz4740_mmc_set_irq_enabled(struct jz4740_mmc_host *host, host->irq_mask &= ~irq; else host->irq_mask |= irq; - spin_unlock_irqrestore(&host->lock, flags); writew(host->irq_mask, host->base + JZ_REG_MMC_IMASK); + spin_unlock_irqrestore(&host->lock, flags); } static void jz4740_mmc_clock_enable(struct jz4740_mmc_host *host, diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index e30df9ad8197..308029930304 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -913,7 +913,7 @@ static void tmio_mmc_finish_request(struct tmio_mmc_host *host) host->check_scc_error(host); /* If SET_BLOCK_COUNT, continue with main command */ - if (host->mrq) { + if (host->mrq && !mrq->cmd->error) { tmio_process_mrq(host, mrq); return; } diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index b1fc28f63882..d0b63bbf46a7 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -244,7 +244,7 @@ static int ubiblock_open(struct block_device *bdev, fmode_t mode) * in any case. */ if (mode & FMODE_WRITE) { - ret = -EPERM; + ret = -EROFS; goto out_unlock; } diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index e941395de3ae..753494e042d5 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -854,6 +854,17 @@ int ubi_attach_mtd_dev(struct mtd_info *mtd, int ubi_num, return -EINVAL; } + /* + * Both UBI and UBIFS have been designed for SLC NAND and NOR flashes. + * MLC NAND is different and needs special care, otherwise UBI or UBIFS + * will die soon and you will lose all your data. + */ + if (mtd->type == MTD_MLCNANDFLASH) { + pr_err("ubi: refuse attaching mtd%d - MLC NAND is not supported\n", + mtd->index); + return -EINVAL; + } + if (ubi_num == UBI_DEV_NUM_AUTO) { /* Search for an empty slot in the @ubi_devices array */ for (ubi_num = 0; ubi_num < UBI_MAX_DEVICES; ubi_num++) diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c index 590d967011bb..98f7d6be8d1f 100644 --- a/drivers/mtd/ubi/fastmap-wl.c +++ b/drivers/mtd/ubi/fastmap-wl.c @@ -362,7 +362,6 @@ static void ubi_fastmap_close(struct ubi_device *ubi) { int i; - flush_work(&ubi->fm_work); return_unused_pool_pebs(ubi, &ubi->fm_pool); return_unused_pool_pebs(ubi, &ubi->fm_wl_pool); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 9c2567b0d93e..dfad93fca0a6 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -375,7 +375,7 @@ static int efx_mcdi_poll(struct efx_nic *efx) * because generally mcdi responses are fast. After that, back off * and poll once a jiffy (approximately) */ - spins = TICK_USEC; + spins = USER_TICK_USEC; finish = jiffies + MCDI_RPC_TIMEOUT; while (1) { diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 6afe896e5cb8..96d26cfae90b 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -253,7 +253,7 @@ static inline void hwsim_clear_chanctx_magic(struct ieee80211_chanctx_conf *c) static unsigned int hwsim_net_id; -static struct ida hwsim_netgroup_ida = IDA_INIT; +static DEFINE_IDA(hwsim_netgroup_ida); struct hwsim_net { int netgroup; 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/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c index cfb54e01d758..9d27016c899e 100644 --- a/drivers/rapidio/devices/rio_mport_cdev.c +++ b/drivers/rapidio/devices/rio_mport_cdev.c @@ -212,7 +212,6 @@ struct mport_cdev_priv { #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct dma_chan *dmach; struct list_head async_list; - struct list_head pend_list; spinlock_t req_lock; struct mutex dma_lock; struct kref dma_ref; @@ -258,8 +257,6 @@ static DECLARE_WAIT_QUEUE_HEAD(mport_cdev_wait); static struct class *dev_class; static dev_t dev_number; -static struct workqueue_struct *dma_wq; - static void mport_release_mapping(struct kref *ref); static int rio_mport_maint_rd(struct mport_cdev_priv *priv, void __user *arg, @@ -539,6 +536,7 @@ static int maint_comptag_set(struct mport_cdev_priv *priv, void __user *arg) #ifdef CONFIG_RAPIDIO_DMA_ENGINE struct mport_dma_req { + struct kref refcount; struct list_head node; struct file *filp; struct mport_cdev_priv *priv; @@ -554,11 +552,6 @@ struct mport_dma_req { struct completion req_comp; }; -struct mport_faf_work { - struct work_struct work; - struct mport_dma_req *req; -}; - static void mport_release_def_dma(struct kref *dma_ref) { struct mport_dev *md = @@ -578,8 +571,10 @@ static void mport_release_dma(struct kref *dma_ref) complete(&priv->comp); } -static void dma_req_free(struct mport_dma_req *req) +static void dma_req_free(struct kref *ref) { + struct mport_dma_req *req = container_of(ref, struct mport_dma_req, + refcount); struct mport_cdev_priv *priv = req->priv; unsigned int i; @@ -611,30 +606,7 @@ static void dma_xfer_callback(void *param) req->status = dma_async_is_tx_complete(priv->dmach, req->cookie, NULL, NULL); complete(&req->req_comp); -} - -static void dma_faf_cleanup(struct work_struct *_work) -{ - struct mport_faf_work *work = container_of(_work, - struct mport_faf_work, work); - struct mport_dma_req *req = work->req; - - dma_req_free(req); - kfree(work); -} - -static void dma_faf_callback(void *param) -{ - struct mport_dma_req *req = (struct mport_dma_req *)param; - struct mport_faf_work *work; - - work = kmalloc(sizeof(*work), GFP_ATOMIC); - if (!work) - return; - - INIT_WORK(&work->work, dma_faf_cleanup); - work->req = req; - queue_work(dma_wq, &work->work); + kref_put(&req->refcount, dma_req_free); } /* @@ -765,16 +737,14 @@ static int do_dma_request(struct mport_dma_req *req, goto err_out; } - if (sync == RIO_TRANSFER_FAF) - tx->callback = dma_faf_callback; - else - tx->callback = dma_xfer_callback; + tx->callback = dma_xfer_callback; tx->callback_param = req; req->dmach = chan; req->sync = sync; req->status = DMA_IN_PROGRESS; init_completion(&req->req_comp); + kref_get(&req->refcount); cookie = dmaengine_submit(tx); req->cookie = cookie; @@ -785,6 +755,7 @@ static int do_dma_request(struct mport_dma_req *req, if (dma_submit_error(cookie)) { rmcd_error("submit err=%d (addr:0x%llx len:0x%llx)", cookie, xfer->rio_addr, xfer->length); + kref_put(&req->refcount, dma_req_free); ret = -EIO; goto err_out; } @@ -860,6 +831,8 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, if (!req) return -ENOMEM; + kref_init(&req->refcount); + ret = get_dma_channel(priv); if (ret) { kfree(req); @@ -968,42 +941,20 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode, ret = do_dma_request(req, xfer, sync, nents); if (ret >= 0) { - if (sync == RIO_TRANSFER_SYNC) - goto sync_out; - return ret; /* return ASYNC cookie */ - } - - if (ret == -ETIMEDOUT || ret == -EINTR) { - /* - * This can happen only in case of SYNC transfer. - * Do not free unfinished request structure immediately. - * Place it into pending list and deal with it later - */ - spin_lock(&priv->req_lock); - list_add_tail(&req->node, &priv->pend_list); - spin_unlock(&priv->req_lock); - return ret; + if (sync == RIO_TRANSFER_ASYNC) + return ret; /* return ASYNC cookie */ + } else { + rmcd_debug(DMA, "do_dma_request failed with err=%d", ret); } - - rmcd_debug(DMA, "do_dma_request failed with err=%d", ret); -sync_out: - dma_unmap_sg(chan->device->dev, req->sgt.sgl, req->sgt.nents, dir); - sg_free_table(&req->sgt); err_pg: - if (page_list) { + if (!req->page_list) { for (i = 0; i < nr_pages; i++) put_page(page_list[i]); kfree(page_list); } err_req: - if (req->map) { - mutex_lock(&md->buf_mutex); - kref_put(&req->map->ref, mport_release_mapping); - mutex_unlock(&md->buf_mutex); - } - put_dma_channel(priv); - kfree(req); + kref_put(&req->refcount, dma_req_free); return ret; } @@ -1121,7 +1072,7 @@ static int rio_mport_wait_for_async_dma(struct file *filp, void __user *arg) ret = 0; if (req->status != DMA_IN_PROGRESS && req->status != DMA_PAUSED) - dma_req_free(req); + kref_put(&req->refcount, dma_req_free); return ret; @@ -1966,7 +1917,6 @@ static int mport_cdev_open(struct inode *inode, struct file *filp) #ifdef CONFIG_RAPIDIO_DMA_ENGINE INIT_LIST_HEAD(&priv->async_list); - INIT_LIST_HEAD(&priv->pend_list); spin_lock_init(&priv->req_lock); mutex_init(&priv->dma_lock); #endif @@ -2006,8 +1956,6 @@ static void mport_cdev_release_dma(struct file *filp) md = priv->md; - flush_workqueue(dma_wq); - spin_lock(&priv->req_lock); if (!list_empty(&priv->async_list)) { rmcd_debug(EXIT, "async list not empty filp=%p %s(%d)", @@ -2023,20 +1971,7 @@ static void mport_cdev_release_dma(struct file *filp) req->filp, req->cookie, completion_done(&req->req_comp)?"yes":"no"); list_del(&req->node); - dma_req_free(req); - } - } - - if (!list_empty(&priv->pend_list)) { - rmcd_debug(EXIT, "Free pending DMA requests for filp=%p %s(%d)", - filp, current->comm, task_pid_nr(current)); - list_for_each_entry_safe(req, - req_next, &priv->pend_list, node) { - rmcd_debug(EXIT, "free req->filp=%p cookie=%d compl=%s", - req->filp, req->cookie, - completion_done(&req->req_comp)?"yes":"no"); - list_del(&req->node); - dma_req_free(req); + kref_put(&req->refcount, dma_req_free); } } @@ -2048,15 +1983,6 @@ static void mport_cdev_release_dma(struct file *filp) current->comm, task_pid_nr(current), wret); } - spin_lock(&priv->req_lock); - - if (!list_empty(&priv->pend_list)) { - rmcd_debug(EXIT, "ATTN: pending DMA requests, filp=%p %s(%d)", - filp, current->comm, task_pid_nr(current)); - } - - spin_unlock(&priv->req_lock); - if (priv->dmach != priv->md->dma_chan) { rmcd_debug(EXIT, "Release DMA channel for filp=%p %s(%d)", filp, current->comm, task_pid_nr(current)); @@ -2573,8 +2499,6 @@ static void mport_cdev_remove(struct mport_dev *md) cdev_device_del(&md->cdev, &md->dev); mport_cdev_kill_fasync(md); - flush_workqueue(dma_wq); - /* TODO: do we need to give clients some time to close file * descriptors? Simple wait for XX, or kref? */ @@ -2691,17 +2615,8 @@ static int __init mport_init(void) goto err_cli; } - dma_wq = create_singlethread_workqueue("dma_wq"); - if (!dma_wq) { - rmcd_error("failed to create DMA work queue"); - ret = -ENOMEM; - goto err_wq; - } - return 0; -err_wq: - class_interface_unregister(&rio_mport_interface); err_cli: unregister_chrdev_region(dev_number, RIO_MAX_MPORTS); err_chr: @@ -2717,7 +2632,6 @@ static void __exit mport_exit(void) class_interface_unregister(&rio_mport_interface); class_destroy(dev_class); unregister_chrdev_region(dev_number, RIO_MAX_MPORTS); - destroy_workqueue(dma_wq); } module_init(mport_init); diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c index 23429bdaca84..161b927d9de1 100644 --- a/drivers/rapidio/rio-scan.c +++ b/drivers/rapidio/rio-scan.c @@ -76,7 +76,7 @@ static u16 rio_destid_alloc(struct rio_net *net) } /** - * rio_destid_reserve - Reserve the specivied destID + * rio_destid_reserve - Reserve the specified destID * @net: RIO network * @destid: destID to reserve * @@ -885,7 +885,7 @@ static struct rio_net *rio_scan_alloc_net(struct rio_mport *mport, * * For each enumerated device, ensure that each switch in a system * has correct routing entries. Add routes for devices that where - * unknown dirung the first enumeration pass through the switch. + * unknown during the first enumeration pass through the switch. */ static void rio_update_route_tables(struct rio_net *net) { @@ -983,7 +983,7 @@ static int rio_enum_mport(struct rio_mport *mport, u32 flags) /* reserve mport destID in new net */ rio_destid_reserve(net, mport->host_deviceid); - /* Enable Input Output Port (transmitter reviever) */ + /* Enable Input Output Port (transmitter receiver) */ rio_enable_rx_tx_port(mport, 1, 0, 0, 0); /* Set component tag for host */ diff --git a/drivers/staging/lustre/lustre/llite/glimpse.c b/drivers/staging/lustre/lustre/llite/glimpse.c index c43ac574274c..3075358f3f08 100644 --- a/drivers/staging/lustre/lustre/llite/glimpse.c +++ b/drivers/staging/lustre/lustre/llite/glimpse.c @@ -69,7 +69,7 @@ blkcnt_t dirty_cnt(struct inode *inode) void *results[1]; if (inode->i_mapping) - cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->page_tree, + cnt += radix_tree_gang_lookup_tag(&inode->i_mapping->i_pages, results, 0, 1, PAGECACHE_TAG_DIRTY); if (cnt == 0 && atomic_read(&vob->vob_mmap_cnt) > 0) diff --git a/drivers/staging/lustre/lustre/mdc/mdc_request.c b/drivers/staging/lustre/lustre/mdc/mdc_request.c index 3b1c8e5a3053..8ee7b4d273b2 100644 --- a/drivers/staging/lustre/lustre/mdc/mdc_request.c +++ b/drivers/staging/lustre/lustre/mdc/mdc_request.c @@ -934,14 +934,14 @@ static struct page *mdc_page_locate(struct address_space *mapping, __u64 *hash, struct page *page; int found; - spin_lock_irq(&mapping->tree_lock); - found = radix_tree_gang_lookup(&mapping->page_tree, + xa_lock_irq(&mapping->i_pages); + found = radix_tree_gang_lookup(&mapping->i_pages, (void **)&page, offset, 1); if (found > 0 && !radix_tree_exceptional_entry(page)) { struct lu_dirpage *dp; get_page(page); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); /* * In contrast to find_lock_page() we are sure that directory * page cannot be truncated (while DLM lock is held) and, @@ -989,7 +989,7 @@ static struct page *mdc_page_locate(struct address_space *mapping, __u64 *hash, page = ERR_PTR(-EIO); } } else { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); page = NULL; } return page; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index dfe5684000be..6b237e3f4983 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -272,6 +272,12 @@ static unsigned int update_balloon_stats(struct virtio_balloon *vb) pages_to_bytes(events[PSWPOUT])); update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]); update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]); +#ifdef CONFIG_HUGETLB_PAGE + update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGALLOC, + events[HTLB_BUDDY_PGALLOC]); + update_stat(vb, idx++, VIRTIO_BALLOON_S_HTLB_PGFAIL, + events[HTLB_BUDDY_PGALLOC_FAIL]); +#endif #endif update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE, pages_to_bytes(i.freeram)); diff --git a/fs/afs/write.c b/fs/afs/write.c index 9370e2feb999..dbc3c0b0142d 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -570,10 +570,11 @@ static int afs_writepages_region(struct address_space *mapping, _debug("wback %lx", page->index); - /* at this point we hold neither mapping->tree_lock nor lock on - * the page itself: the page may be truncated or invalidated - * (changing page->mapping to NULL), or even swizzled back from - * swapper_space to tmpfs file mapping + /* + * at this point we hold neither the i_pages lock nor the + * page lock: the page may be truncated or invalidated + * (changing page->mapping to NULL), or even swizzled + * back from swapper_space to tmpfs file mapping */ ret = lock_page_killable(page); if (ret < 0) { 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(¤t->sighand->siglock, irqflags); - oldset = current->blocked; - shutdown_sigs_mask = SHUTDOWN_SIGS & ~oldset.sig[0]; - siginitsetinv(¤t->blocked, shutdown_sigs_mask); - recalc_sigpending(); - spin_unlock_irqrestore(¤t->sighand->siglock, irqflags); - - wait_event_interruptible(wq->queue, wq->name.name == NULL); - - spin_lock_irqsave(¤t->sighand->siglock, irqflags); - current->blocked = oldset; - recalc_sigpending(); - spin_unlock_irqrestore(¤t->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..41e04183e4ce 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -377,6 +377,11 @@ static unsigned long elf_map(struct file *filep, unsigned long addr, } else map_addr = vm_mmap(filep, addr, size, prot, type, off); + if ((type & MAP_FIXED_NOREPLACE) && BAD_ADDR(map_addr)) + pr_info("%d (%s): Uhuuh, elf segment at %p requested but the memory is mapped already\n", + task_pid_nr(current), current->comm, + (void *)addr); + return(map_addr); } @@ -575,7 +580,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex, elf_prot |= PROT_EXEC; vaddr = eppnt->p_vaddr; if (interp_elf_ex->e_type == ET_EXEC || load_addr_set) - elf_type |= MAP_FIXED; + elf_type |= MAP_FIXED_NOREPLACE; else if (no_base && interp_elf_ex->e_type == ET_DYN) load_addr = -vaddr; @@ -890,7 +895,7 @@ static int load_elf_binary(struct linux_binprm *bprm) the correct location in memory. */ for(i = 0, elf_ppnt = elf_phdata; i < loc->elf_ex.e_phnum; i++, elf_ppnt++) { - int elf_prot = 0, elf_flags; + int elf_prot = 0, elf_flags, elf_fixed = MAP_FIXED_NOREPLACE; unsigned long k, vaddr; unsigned long total_size = 0; @@ -922,6 +927,13 @@ static int load_elf_binary(struct linux_binprm *bprm) */ } } + + /* + * Some binaries have overlapping elf segments and then + * we have to forcefully map over an existing mapping + * e.g. over this newly established brk mapping. + */ + elf_fixed = MAP_FIXED; } if (elf_ppnt->p_flags & PF_R) @@ -939,7 +951,7 @@ static int load_elf_binary(struct linux_binprm *bprm) * the ET_DYN load_addr calculations, proceed normally. */ if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) { - elf_flags |= MAP_FIXED; + elf_flags |= elf_fixed; } else if (loc->elf_ex.e_type == ET_DYN) { /* * This logic is run once for the first LOAD Program @@ -975,7 +987,7 @@ static int load_elf_binary(struct linux_binprm *bprm) load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); - elf_flags |= MAP_FIXED; + elf_flags |= elf_fixed; } else load_bias = 0; @@ -1155,6 +1167,7 @@ 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: @@ -1234,7 +1247,7 @@ static int load_elf_library(struct file *file) (eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr)), PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE, + MAP_FIXED_NOREPLACE | MAP_PRIVATE | MAP_DENYWRITE, (eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr))); if (error != ELF_PAGESTART(eppnt->p_vaddr)) 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/btrfs/compression.c b/fs/btrfs/compression.c index 562c3e633403..578181cd96b5 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -458,7 +458,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, break; rcu_read_lock(); - page = radix_tree_lookup(&mapping->page_tree, pg_index); + page = radix_tree_lookup(&mapping->i_pages, pg_index); rcu_read_unlock(); if (page && !radix_tree_exceptional_entry(page)) { misses++; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 47a8fe9d22e8..cf87976e389d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3963,11 +3963,11 @@ retry: done_index = page->index; /* - * At this point we hold neither mapping->tree_lock nor - * lock on the page itself: the page may be truncated or - * invalidated (changing page->mapping to NULL), or even - * swizzled back from swapper_space to tmpfs file - * mapping + * At this point we hold neither the i_pages lock nor + * the page lock: the page may be truncated or + * invalidated (changing page->mapping to NULL), + * or even swizzled back from swapper_space to + * tmpfs file mapping */ if (!trylock_page(page)) { flush_write_bio(epd); @@ -5174,13 +5174,13 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb) WARN_ON(!PagePrivate(page)); clear_page_dirty_for_io(page); - spin_lock_irq(&page->mapping->tree_lock); + xa_lock_irq(&page->mapping->i_pages); if (!PageDirty(page)) { - radix_tree_tag_clear(&page->mapping->page_tree, + radix_tree_tag_clear(&page->mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&page->mapping->tree_lock); + xa_unlock_irq(&page->mapping->i_pages); ClearPageError(page); unlock_page(page); } diff --git a/fs/buffer.c b/fs/buffer.c index ec5dd39071e6..f3491074b035 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -185,10 +185,9 @@ EXPORT_SYMBOL(end_buffer_write_sync); * we get exclusion from try_to_free_buffers with the blockdev mapping's * private_lock. * - * Hack idea: for the blockdev mapping, i_bufferlist_lock contention + * Hack idea: for the blockdev mapping, private_lock contention * may be quite high. This code could TryLock the page, and if that - * succeeds, there is no need to take private_lock. (But if - * private_lock is contended then so is mapping->tree_lock). + * succeeds, there is no need to take private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) @@ -594,20 +593,21 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); * * The caller must hold lock_page_memcg(). */ -static void __set_page_dirty(struct page *page, struct address_space *mapping, +void __set_page_dirty(struct page *page, struct address_space *mapping, int warn) { unsigned long flags; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); if (page->mapping) { /* Race with truncate? */ WARN_ON_ONCE(warn && !PageUptodate(page)); account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, + radix_tree_tag_set(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); } - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); } +EXPORT_SYMBOL_GPL(__set_page_dirty); /* * Add a page to the dirty page list. @@ -1095,7 +1095,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_page->mapping->private_lock, - * mapping->tree_lock and mapping->host->i_lock. + * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 7cee97b93a61..4bcd4e838b47 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1987,11 +1987,10 @@ wdata_prepare_pages(struct cifs_writedata *wdata, unsigned int found_pages, for (i = 0; i < found_pages; i++) { page = wdata->pages[i]; /* - * At this point we hold neither mapping->tree_lock nor - * lock on the page itself: the page may be truncated or - * invalidated (changing page->mapping to NULL), or even - * swizzled back from swapper_space to tmpfs file - * mapping + * At this point we hold neither the i_pages lock nor the + * page lock: the page may be truncated or invalidated + * (changing page->mapping to NULL), or even swizzled + * back from swapper_space to tmpfs file mapping */ if (nr_pages == 0) @@ -158,11 +158,9 @@ static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mo } /* - * We do not necessarily hold the mapping->tree_lock when we call this - * function so it is possible that 'entry' is no longer a valid item in the - * radix tree. This is okay because all we really need to do is to find the - * correct waitqueue where tasks might be waiting for that old 'entry' and - * wake them. + * @entry may no longer be the entry at the index in the mapping. + * The important information it's conveying is whether the entry at + * this index used to be a PMD entry. */ static void dax_wake_mapping_entry_waiter(struct address_space *mapping, pgoff_t index, void *entry, bool wake_all) @@ -174,7 +172,7 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping, /* * Checking for locked entry and prepare_to_wait_exclusive() happens - * under mapping->tree_lock, ditto for entry handling in our callers. + * under the i_pages lock, ditto for entry handling in our callers. * So at this point all tasks that could have seen our entry locked * must be in the waitqueue and the following check will see them. */ @@ -183,41 +181,39 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping, } /* - * Check whether the given slot is locked. The function must be called with - * mapping->tree_lock held + * Check whether the given slot is locked. Must be called with the i_pages + * lock held. */ static inline int slot_locked(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); return entry & RADIX_DAX_ENTRY_LOCK; } /* - * Mark the given slot is locked. The function must be called with - * mapping->tree_lock held + * Mark the given slot as locked. Must be called with the i_pages lock held. */ static inline void *lock_slot(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); entry |= RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry); + radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); return (void *)entry; } /* - * Mark the given slot is unlocked. The function must be called with - * mapping->tree_lock held + * Mark the given slot as unlocked. Must be called with the i_pages lock held. */ static inline void *unlock_slot(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry); + radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); return (void *)entry; } @@ -228,7 +224,7 @@ static inline void *unlock_slot(struct address_space *mapping, void **slot) * put_locked_mapping_entry() when he locked the entry and now wants to * unlock it. * - * The function must be called with mapping->tree_lock held. + * Must be called with the i_pages lock held. */ static void *get_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void ***slotp) @@ -241,7 +237,7 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping, ewait.wait.func = wake_exceptional_entry_func; for (;;) { - entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, + entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) || @@ -254,10 +250,10 @@ static void *get_unlocked_mapping_entry(struct address_space *mapping, wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key); prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); schedule(); finish_wait(wq, &ewait.wait); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); } } @@ -266,15 +262,15 @@ static void dax_unlock_mapping_entry(struct address_space *mapping, { void *entry, **slot; - spin_lock_irq(&mapping->tree_lock); - entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); + xa_lock_irq(&mapping->i_pages); + entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) || !slot_locked(mapping, slot))) { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return; } unlock_slot(mapping, slot); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); dax_wake_mapping_entry_waiter(mapping, index, entry, false); } @@ -388,7 +384,7 @@ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index, void *entry, **slot; restart: - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, &slot); if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) { @@ -420,12 +416,12 @@ restart: if (pmd_downgrade) { /* * Make sure 'entry' remains valid while we drop - * mapping->tree_lock. + * the i_pages lock. */ entry = lock_slot(mapping, slot); } - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); /* * Besides huge zero pages the only other thing that gets * downgraded are empty entries which don't need to be @@ -442,27 +438,27 @@ restart: put_locked_mapping_entry(mapping, index); return ERR_PTR(err); } - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); if (!entry) { /* - * We needed to drop the page_tree lock while calling + * We needed to drop the i_pages lock while calling * radix_tree_preload() and we didn't have an entry to * lock. See if another thread inserted an entry at * our index during this time. */ - entry = __radix_tree_lookup(&mapping->page_tree, index, + entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); if (entry) { radix_tree_preload_end(); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); goto restart; } } if (pmd_downgrade) { dax_disassociate_entry(entry, mapping, false); - radix_tree_delete(&mapping->page_tree, index); + radix_tree_delete(&mapping->i_pages, index); mapping->nrexceptional--; dax_wake_mapping_entry_waiter(mapping, index, entry, true); @@ -470,11 +466,11 @@ restart: entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY); - err = __radix_tree_insert(&mapping->page_tree, index, + err = __radix_tree_insert(&mapping->i_pages, index, dax_radix_order(entry), entry); radix_tree_preload_end(); if (err) { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); /* * Our insertion of a DAX entry failed, most likely * because we were inserting a PMD entry and it @@ -487,12 +483,12 @@ restart: } /* Good, we have inserted empty locked entry into the tree. */ mapping->nrexceptional++; - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return entry; } entry = lock_slot(mapping, slot); out_unlock: - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return entry; } @@ -501,23 +497,23 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping, { int ret = 0; void *entry; - struct radix_tree_root *page_tree = &mapping->page_tree; + struct radix_tree_root *pages = &mapping->i_pages; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(pages); entry = get_unlocked_mapping_entry(mapping, index, NULL); if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry))) goto out; if (!trunc && - (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) || - radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))) + (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) || + radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE))) goto out; dax_disassociate_entry(entry, mapping, trunc); - radix_tree_delete(page_tree, index); + radix_tree_delete(pages, index); mapping->nrexceptional--; ret = 1; out: put_unlocked_mapping_entry(mapping, index, entry); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(pages); return ret; } /* @@ -587,7 +583,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, void *entry, pfn_t pfn_t, unsigned long flags, bool dirty) { - struct radix_tree_root *page_tree = &mapping->page_tree; + struct radix_tree_root *pages = &mapping->i_pages; unsigned long pfn = pfn_t_to_pfn(pfn_t); pgoff_t index = vmf->pgoff; void *new_entry; @@ -604,7 +600,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, unmap_mapping_pages(mapping, vmf->pgoff, 1, false); } - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(pages); new_entry = dax_radix_locked_entry(pfn, flags); if (dax_entry_size(entry) != dax_entry_size(new_entry)) { dax_disassociate_entry(entry, mapping, false); @@ -624,17 +620,17 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, void **slot; void *ret; - ret = __radix_tree_lookup(page_tree, index, &node, &slot); + ret = __radix_tree_lookup(pages, index, &node, &slot); WARN_ON_ONCE(ret != entry); - __radix_tree_replace(page_tree, node, slot, + __radix_tree_replace(pages, node, slot, new_entry, NULL); entry = new_entry; } if (dirty) - radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY); + radix_tree_tag_set(pages, index, PAGECACHE_TAG_DIRTY); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(pages); return entry; } @@ -723,7 +719,7 @@ unlock_pte: static int dax_writeback_one(struct dax_device *dax_dev, struct address_space *mapping, pgoff_t index, void *entry) { - struct radix_tree_root *page_tree = &mapping->page_tree; + struct radix_tree_root *pages = &mapping->i_pages; void *entry2, **slot; unsigned long pfn; long ret = 0; @@ -736,7 +732,7 @@ static int dax_writeback_one(struct dax_device *dax_dev, if (WARN_ON(!radix_tree_exceptional_entry(entry))) return -EIO; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(pages); entry2 = get_unlocked_mapping_entry(mapping, index, &slot); /* Entry got punched out / reallocated? */ if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2))) @@ -755,7 +751,7 @@ static int dax_writeback_one(struct dax_device *dax_dev, } /* Another fsync thread may have already written back this entry */ - if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)) + if (!radix_tree_tag_get(pages, index, PAGECACHE_TAG_TOWRITE)) goto put_unlocked; /* Lock the entry to serialize with page faults */ entry = lock_slot(mapping, slot); @@ -763,11 +759,11 @@ static int dax_writeback_one(struct dax_device *dax_dev, * We can clear the tag now but we have to be careful so that concurrent * dax_writeback_one() calls for the same index cannot finish before we * actually flush the caches. This is achieved as the calls will look - * at the entry only under tree_lock and once they do that they will - * see the entry locked and wait for it to unlock. + * at the entry only under the i_pages lock and once they do that + * they will see the entry locked and wait for it to unlock. */ - radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE); - spin_unlock_irq(&mapping->tree_lock); + radix_tree_tag_clear(pages, index, PAGECACHE_TAG_TOWRITE); + xa_unlock_irq(pages); /* * Even if dax_writeback_mapping_range() was given a wbc->range_start @@ -787,16 +783,16 @@ static int dax_writeback_one(struct dax_device *dax_dev, * the pfn mappings are writeprotected and fault waits for mapping * entry lock. */ - spin_lock_irq(&mapping->tree_lock); - radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY); - spin_unlock_irq(&mapping->tree_lock); + xa_lock_irq(pages); + radix_tree_tag_clear(pages, index, PAGECACHE_TAG_DIRTY); + xa_unlock_irq(pages); trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT); put_locked_mapping_entry(mapping, index); return ret; put_unlocked: put_unlocked_mapping_entry(mapping, index, entry2); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(pages); return ret; } @@ -1566,21 +1562,21 @@ static int dax_insert_pfn_mkwrite(struct vm_fault *vmf, pgoff_t index = vmf->pgoff; int vmf_ret, error; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, &slot); /* Did we race with someone splitting entry or so? */ if (!entry || (pe_size == PE_SIZE_PTE && !dax_is_pte_entry(entry)) || (pe_size == PE_SIZE_PMD && !dax_is_pmd_entry(entry))) { put_unlocked_mapping_entry(mapping, index, entry); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf, VM_FAULT_NOPAGE); return VM_FAULT_NOPAGE; } - radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY); + radix_tree_tag_set(&mapping->i_pages, index, PAGECACHE_TAG_DIRTY); entry = lock_slot(mapping, slot); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); switch (pe_size) { case PE_SIZE_PTE: error = vm_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn); diff --git a/fs/dcache.c b/fs/dcache.c index 593079176123..86d2de63461e 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) @@ -291,7 +305,7 @@ 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); @@ -1038,6 +1052,8 @@ static void shrink_dentry_list(struct list_head *list) while (!list_empty(list)) { struct dentry *dentry, *parent; + cond_resched(); + dentry = list_entry(list->prev, struct dentry, d_lru); spin_lock(&dentry->d_lock); rcu_read_lock(); @@ -1191,7 +1207,6 @@ void shrink_dcache_sb(struct super_block *sb) this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); - cond_resched(); } while (list_lru_count(&sb->s_dentry_lru) > 0); } EXPORT_SYMBOL(shrink_dcache_sb); @@ -1473,7 +1488,6 @@ void shrink_dcache_parent(struct dentry *parent) break; shrink_dentry_list(&data.dispose); - cond_resched(); } } EXPORT_SYMBOL(shrink_dcache_parent); @@ -1600,7 +1614,6 @@ void d_invalidate(struct dentry *dentry) detach_mounts(data.mountpoint); dput(data.mountpoint); } - cond_resched(); } } EXPORT_SYMBOL(d_invalidate); @@ -1617,6 +1630,7 @@ 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 +1651,14 @@ 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 +1697,12 @@ 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 +2790,7 @@ 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/exec.c b/fs/exec.c index a919a827d181..183059c427b9 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; @@ -1341,11 +1346,11 @@ 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 +1383,16 @@ 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/f2fs/data.c b/fs/f2fs/data.c index db50686f5096..02237d4d91f5 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2424,12 +2424,12 @@ void f2fs_set_page_dirty_nobuffers(struct page *page) SetPageDirty(page); spin_unlock(&mapping->private_lock); - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); WARN_ON_ONCE(!PageUptodate(page)); account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, + radix_tree_tag_set(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index fe661274ff10..8c9c2f31b253 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -732,10 +732,10 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page, if (bit_pos == NR_DENTRY_IN_BLOCK && !truncate_hole(dir, page->index, page->index + 1)) { - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, page_index(page), + xa_lock_irqsave(&mapping->i_pages, flags); + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); clear_page_dirty_for_io(page); ClearPagePrivate(page); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index bfb7a4a3a929..9327411fd93b 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1015,7 +1015,7 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, unsigned int init_segno = segno; struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), - .iroot = RADIX_TREE_INIT(GFP_NOFS), + .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; trace_f2fs_gc_begin(sbi->sb, sync, background, diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c index 3b77d6421218..265da200daa8 100644 --- a/fs/f2fs/inline.c +++ b/fs/f2fs/inline.c @@ -226,10 +226,10 @@ int f2fs_write_inline_data(struct inode *inode, struct page *page) kunmap_atomic(src_addr); set_page_dirty(dn.inode_page); - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, page_index(page), + xa_lock_irqsave(&mapping->i_pages, flags); + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); set_inode_flag(inode, FI_APPEND_WRITE); set_inode_flag(inode, FI_DATA_EXIST); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 9a99243054ba..f202398e20ea 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -91,11 +91,11 @@ static void clear_node_page_dirty(struct page *page) unsigned int long flags; if (PageDirty(page)) { - spin_lock_irqsave(&mapping->tree_lock, flags); - radix_tree_tag_clear(&mapping->page_tree, + xa_lock_irqsave(&mapping->i_pages, flags); + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); clear_page_dirty_for_io(page); dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); @@ -1161,7 +1161,7 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) f2fs_bug_on(sbi, check_nid_range(sbi, nid)); rcu_read_lock(); - apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid); + apage = radix_tree_lookup(&NODE_MAPPING(sbi)->i_pages, nid); rcu_read_unlock(); if (apage) return; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 1280f915079b..4b12ba70a895 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -347,9 +347,9 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be - * synchronizing against mapping->tree_lock. + * synchronizing against the i_pages lock. * - * Grabbing old_wb->list_lock, inode->i_lock and mapping->tree_lock + * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ @@ -361,7 +361,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns @@ -373,22 +373,22 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to - * pages actually under underwriteback. + * pages actually under writeback. */ - radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0, + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, 0, PAGECACHE_TAG_DIRTY) { struct page *page = radix_tree_deref_slot_protected(slot, - &mapping->tree_lock); + &mapping->i_pages.xa_lock); if (likely(page) && PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } - radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, 0, + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, 0, PAGECACHE_TAG_WRITEBACK) { struct page *page = radix_tree_deref_slot_protected(slot, - &mapping->tree_lock); + &mapping->i_pages.xa_lock); if (likely(page)) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); @@ -430,7 +430,7 @@ skip_switch: */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); @@ -506,8 +506,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* * In addition to synchronizing among switchers, I_WB_SWITCH tells - * the RCU protected stat update paths to grab the mapping's - * tree_lock so that stat transfer can synchronize against them. + * the RCU protected stat update paths to grab the i_page + * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 7dc55b93a830..97137d7ec5ee 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -832,7 +832,7 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, /* Clear pointers back to the netfs */ cookie->netfs_data = NULL; cookie->def = NULL; - BUG_ON(cookie->stores.rnode); + BUG_ON(!radix_tree_empty(&cookie->stores)); if (cookie->parent) { ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0); diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 1085ca12e25c..20e0d0a4dc8c 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -973,7 +973,7 @@ static const struct fscache_state *_fscache_invalidate_object(struct fscache_obj * retire the object instead. */ if (!fscache_use_cookie(object)) { - ASSERT(object->cookie->stores.rnode == NULL); + ASSERT(radix_tree_empty(&object->cookie->stores)); set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); _leave(" [no cookie]"); return transit_to(KILL_OBJECT); diff --git a/fs/inode.c b/fs/inode.c index b153aeaa61ea..13ceb98c3bd3 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -348,8 +348,7 @@ EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { - INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC | __GFP_ACCOUNT); - spin_lock_init(&mapping->tree_lock); + INIT_RADIX_TREE(&mapping->i_pages, GFP_ATOMIC | __GFP_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); @@ -504,14 +503,14 @@ EXPORT_SYMBOL(__remove_inode_hash); void clear_inode(struct inode *inode) { /* - * We have to cycle tree_lock here because reclaim can be still in the + * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __delete_from_page_cache()) - * and we must not free mapping under it. + * and we must not free the mapping under it. */ - spin_lock_irq(&inode->i_data.tree_lock); + xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); BUG_ON(inode->i_data.nrexceptional); - spin_unlock_irq(&inode->i_data.tree_lock); + xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index c21e0b4454a6..dec98cab729d 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -193,9 +193,9 @@ retry: (unsigned long long)oldkey, (unsigned long long)newkey); - spin_lock_irq(&btnc->tree_lock); - err = radix_tree_insert(&btnc->page_tree, newkey, obh->b_page); - spin_unlock_irq(&btnc->tree_lock); + xa_lock_irq(&btnc->i_pages); + err = radix_tree_insert(&btnc->i_pages, newkey, obh->b_page); + xa_unlock_irq(&btnc->i_pages); /* * Note: page->index will not change to newkey until * nilfs_btnode_commit_change_key() will be called. @@ -251,11 +251,11 @@ void nilfs_btnode_commit_change_key(struct address_space *btnc, (unsigned long long)newkey); mark_buffer_dirty(obh); - spin_lock_irq(&btnc->tree_lock); - radix_tree_delete(&btnc->page_tree, oldkey); - radix_tree_tag_set(&btnc->page_tree, newkey, + xa_lock_irq(&btnc->i_pages); + radix_tree_delete(&btnc->i_pages, oldkey); + radix_tree_tag_set(&btnc->i_pages, newkey, PAGECACHE_TAG_DIRTY); - spin_unlock_irq(&btnc->tree_lock); + xa_unlock_irq(&btnc->i_pages); opage->index = obh->b_blocknr = newkey; unlock_page(opage); @@ -283,9 +283,9 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc, return; if (nbh == NULL) { /* blocksize == pagesize */ - spin_lock_irq(&btnc->tree_lock); - radix_tree_delete(&btnc->page_tree, newkey); - spin_unlock_irq(&btnc->tree_lock); + xa_lock_irq(&btnc->i_pages); + radix_tree_delete(&btnc->i_pages, newkey); + xa_unlock_irq(&btnc->i_pages); unlock_page(ctxt->bh->b_page); } else brelse(nbh); diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 68241512d7c1..4cb850a6f1c2 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -331,15 +331,15 @@ repeat: struct page *page2; /* move the page to the destination cache */ - spin_lock_irq(&smap->tree_lock); - page2 = radix_tree_delete(&smap->page_tree, offset); + xa_lock_irq(&smap->i_pages); + page2 = radix_tree_delete(&smap->i_pages, offset); WARN_ON(page2 != page); smap->nrpages--; - spin_unlock_irq(&smap->tree_lock); + xa_unlock_irq(&smap->i_pages); - spin_lock_irq(&dmap->tree_lock); - err = radix_tree_insert(&dmap->page_tree, offset, page); + xa_lock_irq(&dmap->i_pages); + err = radix_tree_insert(&dmap->i_pages, offset, page); if (unlikely(err < 0)) { WARN_ON(err == -EEXIST); page->mapping = NULL; @@ -348,11 +348,11 @@ repeat: page->mapping = dmap; dmap->nrpages++; if (PageDirty(page)) - radix_tree_tag_set(&dmap->page_tree, + radix_tree_tag_set(&dmap->i_pages, offset, PAGECACHE_TAG_DIRTY); } - spin_unlock_irq(&dmap->tree_lock); + xa_unlock_irq(&dmap->i_pages); } unlock_page(page); } @@ -474,15 +474,15 @@ int __nilfs_clear_page_dirty(struct page *page) struct address_space *mapping = page->mapping; if (mapping) { - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); if (test_bit(PG_dirty, &page->flags)) { - radix_tree_tag_clear(&mapping->page_tree, + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return clear_page_dirty_for_io(page); } - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return 0; } return TestClearPageDirty(page); 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..04c4804cbdef 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -8,6 +8,7 @@ * Copyright (C) 1997 Theodore Ts'o */ +#include <linux/cache.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/proc_fs.h> @@ -28,6 +29,17 @@ 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 +52,8 @@ 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 +66,7 @@ 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 +87,8 @@ 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 +100,15 @@ 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; } @@ -354,6 +364,14 @@ 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 +381,26 @@ 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 +423,11 @@ 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 +450,7 @@ 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 +485,7 @@ 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 +522,7 @@ 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 +549,12 @@ 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 +575,7 @@ 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 +612,13 @@ 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/reiserfs/journal.c b/fs/reiserfs/journal.c index 70057359fbaf..23148c3ed675 100644 --- a/fs/reiserfs/journal.c +++ b/fs/reiserfs/journal.c @@ -2643,7 +2643,7 @@ static int journal_init_dev(struct super_block *super, if (IS_ERR(journal->j_dev_bd)) { result = PTR_ERR(journal->j_dev_bd); journal->j_dev_bd = NULL; - reiserfs_warning(super, + reiserfs_warning(super, "sh-457", "journal_init_dev: Cannot open '%s': %i", jdev_name, result); return result; diff --git a/fs/seq_file.c b/fs/seq_file.c index eea09f6d8830..c6c27f1f9c98 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; @@ -673,29 +676,37 @@ 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) { @@ -703,7 +714,7 @@ void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, 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 +724,60 @@ 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 +785,12 @@ 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; @@ -742,7 +805,7 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num 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 +845,14 @@ 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 +1109,8 @@ 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/fs/ubifs/find.c b/fs/ubifs/find.c index 2dcf3d473fec..9571616b5dda 100644 --- a/fs/ubifs/find.c +++ b/fs/ubifs/find.c @@ -632,7 +632,7 @@ static int scan_for_idx_cb(struct ubifs_info *c, */ static const struct ubifs_lprops *scan_for_leb_for_idx(struct ubifs_info *c) { - struct ubifs_lprops *lprops; + const struct ubifs_lprops *lprops; struct scan_data data; int err; diff --git a/fs/ubifs/lprops.c b/fs/ubifs/lprops.c index 6c3a1abd0e22..f5a46844340c 100644 --- a/fs/ubifs/lprops.c +++ b/fs/ubifs/lprops.c @@ -244,7 +244,6 @@ static void remove_from_lpt_heap(struct ubifs_info *c, /** * lpt_heap_replace - replace lprops in a category heap. * @c: UBIFS file-system description object - * @old_lprops: LEB properties to replace * @new_lprops: LEB properties with which to replace * @cat: LEB category * @@ -254,7 +253,6 @@ static void remove_from_lpt_heap(struct ubifs_info *c, * lprops. This function does that. */ static void lpt_heap_replace(struct ubifs_info *c, - struct ubifs_lprops *old_lprops, struct ubifs_lprops *new_lprops, int cat) { struct ubifs_lpt_heap *heap; @@ -362,7 +360,7 @@ void ubifs_replace_cat(struct ubifs_info *c, struct ubifs_lprops *old_lprops, case LPROPS_DIRTY: case LPROPS_DIRTY_IDX: case LPROPS_FREE: - lpt_heap_replace(c, old_lprops, new_lprops, cat); + lpt_heap_replace(c, new_lprops, cat); break; case LPROPS_UNCAT: case LPROPS_EMPTY: diff --git a/fs/ubifs/scan.c b/fs/ubifs/scan.c index aab87340d3de..16f03d9929e5 100644 --- a/fs/ubifs/scan.c +++ b/fs/ubifs/scan.c @@ -175,7 +175,6 @@ struct ubifs_scan_leb *ubifs_start_scan(const struct ubifs_info *c, int lnum, void ubifs_end_scan(const struct ubifs_info *c, struct ubifs_scan_leb *sleb, int lnum, int offs) { - lnum = lnum; dbg_scan("stop scanning LEB %d at offset %d", lnum, offs); ubifs_assert(offs % c->min_io_size == 0); diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index b16ef162344a..6c397a389105 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1737,8 +1737,11 @@ static void ubifs_remount_ro(struct ubifs_info *c) dbg_save_space_info(c); - for (i = 0; i < c->jhead_cnt; i++) - ubifs_wbuf_sync(&c->jheads[i].wbuf); + for (i = 0; i < c->jhead_cnt; i++) { + err = ubifs_wbuf_sync(&c->jheads[i].wbuf); + if (err) + ubifs_ro_mode(c, err); + } c->mst_node->flags &= ~cpu_to_le32(UBIFS_MST_DIRTY); c->mst_node->flags |= cpu_to_le32(UBIFS_MST_NO_ORPHS); @@ -1804,8 +1807,11 @@ static void ubifs_put_super(struct super_block *sb) int err; /* Synchronize write-buffers */ - for (i = 0; i < c->jhead_cnt; i++) - ubifs_wbuf_sync(&c->jheads[i].wbuf); + for (i = 0; i < c->jhead_cnt; i++) { + err = ubifs_wbuf_sync(&c->jheads[i].wbuf); + if (err) + ubifs_ro_mode(c, err); + } /* * We are being cleanly unmounted which means the diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 436a1de3fcdf..0ab824f574ed 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1467,19 +1467,8 @@ xfs_vm_set_page_dirty( newly_dirty = !TestSetPageDirty(page); spin_unlock(&mapping->private_lock); - if (newly_dirty) { - /* sigh - __set_page_dirty() is static, so copy it here, too */ - unsigned long flags; - - spin_lock_irqsave(&mapping->tree_lock, flags); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(!PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } - spin_unlock_irqrestore(&mapping->tree_lock, flags); - } + if (newly_dirty) + __set_page_dirty(page, mapping, 1); unlock_page_memcg(page); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 04c4cc6fd820..66d1d45fa2e1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -25,6 +25,50 @@ #define mmiowb() do {} while (0) #endif +#ifndef __io_br +#define __io_br() barrier() +#endif + +/* prevent prefetching of coherent DMA data ahead of a dma-complete */ +#ifndef __io_ar +#ifdef rmb +#define __io_ar() rmb() +#else +#define __io_ar() barrier() +#endif +#endif + +/* flush writes to coherent DMA data before possibly triggering a DMA read */ +#ifndef __io_bw +#ifdef wmb +#define __io_bw() wmb() +#else +#define __io_bw() barrier() +#endif +#endif + +/* serialize device access against a spin_unlock, usually handled there. */ +#ifndef __io_aw +#define __io_aw() barrier() +#endif + +#ifndef __io_pbw +#define __io_pbw() __io_bw() +#endif + +#ifndef __io_paw +#define __io_paw() __io_aw() +#endif + +#ifndef __io_pbr +#define __io_pbr() __io_br() +#endif + +#ifndef __io_par +#define __io_par() __io_ar() +#endif + + /* * __raw_{read,write}{b,w,l,q}() access memory in native endianness. * @@ -110,7 +154,12 @@ static inline void __raw_writeq(u64 value, volatile void __iomem *addr) #define readb readb static inline u8 readb(const volatile void __iomem *addr) { - return __raw_readb(addr); + u8 val; + + __io_br(); + val = __raw_readb(addr); + __io_ar(); + return val; } #endif @@ -118,7 +167,12 @@ static inline u8 readb(const volatile void __iomem *addr) #define readw readw static inline u16 readw(const volatile void __iomem *addr) { - return __le16_to_cpu(__raw_readw(addr)); + u16 val; + + __io_br(); + val = __le16_to_cpu(__raw_readw(addr)); + __io_ar(); + return val; } #endif @@ -126,7 +180,12 @@ static inline u16 readw(const volatile void __iomem *addr) #define readl readl static inline u32 readl(const volatile void __iomem *addr) { - return __le32_to_cpu(__raw_readl(addr)); + u32 val; + + __io_br(); + val = __le32_to_cpu(__raw_readl(addr)); + __io_ar(); + return val; } #endif @@ -135,7 +194,12 @@ static inline u32 readl(const volatile void __iomem *addr) #define readq readq static inline u64 readq(const volatile void __iomem *addr) { - return __le64_to_cpu(__raw_readq(addr)); + u64 val; + + __io_br(); + val = __le64_to_cpu(__raw_readq(addr)); + __io_ar(); + return val; } #endif #endif /* CONFIG_64BIT */ @@ -144,7 +208,9 @@ static inline u64 readq(const volatile void __iomem *addr) #define writeb writeb static inline void writeb(u8 value, volatile void __iomem *addr) { + __io_bw(); __raw_writeb(value, addr); + __io_aw(); } #endif @@ -152,7 +218,9 @@ static inline void writeb(u8 value, volatile void __iomem *addr) #define writew writew static inline void writew(u16 value, volatile void __iomem *addr) { + __io_bw(); __raw_writew(cpu_to_le16(value), addr); + __io_aw(); } #endif @@ -160,7 +228,9 @@ static inline void writew(u16 value, volatile void __iomem *addr) #define writel writel static inline void writel(u32 value, volatile void __iomem *addr) { + __io_bw(); __raw_writel(__cpu_to_le32(value), addr); + __io_aw(); } #endif @@ -169,7 +239,9 @@ static inline void writel(u32 value, volatile void __iomem *addr) #define writeq writeq static inline void writeq(u64 value, volatile void __iomem *addr) { + __io_bw(); __raw_writeq(__cpu_to_le64(value), addr); + __io_aw(); } #endif #endif /* CONFIG_64BIT */ @@ -180,35 +252,67 @@ static inline void writeq(u64 value, volatile void __iomem *addr) * accesses. */ #ifndef readb_relaxed -#define readb_relaxed readb +#define readb_relaxed readb_relaxed +static inline u8 readb_relaxed(const volatile void __iomem *addr) +{ + return __raw_readb(addr); +} #endif #ifndef readw_relaxed -#define readw_relaxed readw +#define readw_relaxed readw_relaxed +static inline u16 readw_relaxed(const volatile void __iomem *addr) +{ + return __le16_to_cpu(__raw_readw(addr)); +} #endif #ifndef readl_relaxed -#define readl_relaxed readl +#define readl_relaxed readl_relaxed +static inline u32 readl_relaxed(const volatile void __iomem *addr) +{ + return __le32_to_cpu(__raw_readl(addr)); +} #endif #if defined(readq) && !defined(readq_relaxed) -#define readq_relaxed readq +#define readq_relaxed readq_relaxed +static inline u64 readq_relaxed(const volatile void __iomem *addr) +{ + return __le64_to_cpu(__raw_readq(addr)); +} #endif #ifndef writeb_relaxed -#define writeb_relaxed writeb +#define writeb_relaxed writeb_relaxed +static inline void writeb_relaxed(u8 value, volatile void __iomem *addr) +{ + __raw_writeb(value, addr); +} #endif #ifndef writew_relaxed -#define writew_relaxed writew +#define writew_relaxed writew_relaxed +static inline void writew_relaxed(u16 value, volatile void __iomem *addr) +{ + __raw_writew(cpu_to_le16(value), addr); +} #endif #ifndef writel_relaxed -#define writel_relaxed writel +#define writel_relaxed writel_relaxed +static inline void writel_relaxed(u32 value, volatile void __iomem *addr) +{ + __raw_writel(__cpu_to_le32(value), addr); +} #endif #if defined(writeq) && !defined(writeq_relaxed) -#define writeq_relaxed writeq +#define writeq_relaxed writeq_relaxed +static inline void writeq_relaxed(u64 value, volatile void __iomem *addr) +{ + __raw_writeq(__cpu_to_le64(value), addr); +} #endif /* @@ -363,7 +467,12 @@ static inline void writesq(volatile void __iomem *addr, const void *buffer, #define inb inb static inline u8 inb(unsigned long addr) { - return readb(PCI_IOBASE + addr); + u8 val; + + __io_pbr(); + val = __raw_readb(PCI_IOBASE + addr); + __io_par(); + return val; } #endif @@ -371,7 +480,12 @@ static inline u8 inb(unsigned long addr) #define inw inw static inline u16 inw(unsigned long addr) { - return readw(PCI_IOBASE + addr); + u16 val; + + __io_pbr(); + val = __le16_to_cpu(__raw_readw(PCI_IOBASE + addr)); + __io_par(); + return val; } #endif @@ -379,7 +493,12 @@ static inline u16 inw(unsigned long addr) #define inl inl static inline u32 inl(unsigned long addr) { - return readl(PCI_IOBASE + addr); + u32 val; + + __io_pbr(); + val = __le32_to_cpu(__raw_readl(PCI_IOBASE + addr)); + __io_par(); + return val; } #endif @@ -387,7 +506,9 @@ static inline u32 inl(unsigned long addr) #define outb outb static inline void outb(u8 value, unsigned long addr) { - writeb(value, PCI_IOBASE + addr); + __io_pbw(); + __raw_writeb(value, PCI_IOBASE + addr); + __io_paw(); } #endif @@ -395,7 +516,9 @@ static inline void outb(u8 value, unsigned long addr) #define outw outw static inline void outw(u16 value, unsigned long addr) { - writew(value, PCI_IOBASE + addr); + __io_pbw(); + __raw_writew(cpu_to_le16(value), PCI_IOBASE + addr); + __io_paw(); } #endif @@ -403,7 +526,9 @@ static inline void outw(u16 value, unsigned long addr) #define outl outl static inline void outl(u32 value, unsigned long addr) { - writel(value, PCI_IOBASE + addr); + __io_pbw(); + __raw_writel(cpu_to_le32(value), PCI_IOBASE + addr); + __io_paw(); } #endif diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 2f7a29242b87..38cd77b39a64 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,7 +26,8 @@ #define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL) #define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL) -int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node); +int iort_register_domain_token(int trans_id, phys_addr_t base, + struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT @@ -38,6 +39,7 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); const struct iommu_ops *iort_iommu_configure(struct device *dev); +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); #else static inline void acpi_iort_init(void) { } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) @@ -52,6 +54,9 @@ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, static inline const struct iommu_ops *iort_iommu_configure( struct device *dev) { return NULL; } +static inline +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) +{ return 0; } #endif #endif /* __ACPI_IORT_H__ */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3e4ce54d84ab..09da0f124699 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) { @@ -329,7 +329,7 @@ static inline bool inode_to_wb_is_valid(struct inode *inode) * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be - * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the + * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) @@ -337,7 +337,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && - !lockdep_is_held(&inode->i_mapping->tree_lock) && + !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; @@ -349,7 +349,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * @lockedp: temp bool output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't - * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This + * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). @@ -370,11 +370,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(*lockedp)) - spin_lock_irq(&inode->i_mapping->tree_lock); + xa_lock_irq(&inode->i_mapping->i_pages); /* - * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock. - * inode_to_wb() will bark. Deref directly. + * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages + * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } @@ -387,7 +387,7 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) { if (unlikely(locked)) - spin_unlock_irq(&inode->i_mapping->tree_lock); + xa_unlock_irq(&inode->i_mapping->i_pages); rcu_read_unlock(); } 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/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/const.h b/include/linux/const.h new file mode 100644 index 000000000000..7b55a55f5911 --- /dev/null +++ b/include/linux/const.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_CONST_H +#define _LINUX_CONST_H + +#include <uapi/linux/const.h> + +#define UL(x) (_UL(x)) +#define ULL(x) (_ULL(x)) + +#endif /* _LINUX_CONST_H */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1fe49724da9e..87f48dd932eb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -960,8 +960,6 @@ extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; extern struct freq_attr *cpufreq_generic_attr[]; -int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy); unsigned int cpufreq_generic_get(unsigned int cpu); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a806e94c482f..1eefabf1621f 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -135,7 +135,8 @@ extern bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); extern int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index); extern void cpuidle_reflect(struct cpuidle_device *dev, int index); @@ -167,7 +168,7 @@ static inline bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return true; } static inline int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, bool *stop_tick) {return -ENODEV; } static inline int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) @@ -250,7 +251,8 @@ struct cpuidle_governor { struct cpuidle_device *dev); int (*select) (struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); void (*reflect) (struct cpuidle_device *dev, int index); }; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2aa02cad94d4..92efaf1f8977 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -13,6 +13,7 @@ #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> @@ -390,12 +391,11 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root page_tree; /* radix tree of all pages */ - spinlock_t tree_lock; /* and lock protecting it */ + struct radix_tree_root i_pages; /* cached pages */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by tree_lock together with the radix tree */ + /* Protected by the i_pages lock */ unsigned long nrpages; /* number of total pages */ /* number of shadow or DAX exceptional entries */ unsigned long nrexceptional; @@ -1989,7 +1989,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell - * wb stat updates to grab mapping->tree_lock. See + * wb stat updates to grab the i_pages lock. See * inode_switch_wb_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 325017ad9311..39988924de3a 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; - return pfn_to_page(pfn >> HMM_PFN_SHIFT); + if (pfn == range->values[HMM_PFN_SPECIAL]) + return NULL; + 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; + if (!(pfn & range->flags[HMM_PFN_VALID])) return -1UL; - return (pfn >> HMM_PFN_SHIFT); + 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. * @@ -310,22 +368,26 @@ 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); -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +int hmm_vma_fault(struct hmm_range *range, bool block); +/* Below are for HMM internal use only! Not to be used by device driver! */ +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) */ #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) struct hmm_devmem; @@ -498,23 +560,9 @@ 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/hrtimer.h b/include/linux/hrtimer.h index 78f456fcd242..a2656c3ebe81 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -424,6 +424,7 @@ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } extern u64 hrtimer_get_next_event(void); +extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); diff --git a/include/linux/idr.h b/include/linux/idr.h index 7d6a6313f0ab..e856f4e0ab35 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -29,29 +29,31 @@ struct idr { #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ -#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) +#define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ + (1 << (ROOT_TAG_SHIFT + IDR_FREE))) -#define IDR_INIT_BASE(base) { \ - .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER), \ +#define IDR_INIT_BASE(name, base) { \ + .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. + * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ -#define IDR_INIT IDR_INIT_BASE(0) +#define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** - * DEFINE_IDR() - Define a statically-allocated IDR - * @name: Name of IDR + * DEFINE_IDR() - Define a statically-allocated IDR. + * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ -#define DEFINE_IDR(name) struct idr name = IDR_INIT +#define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator @@ -218,10 +220,10 @@ struct ida { struct radix_tree_root ida_rt; }; -#define IDA_INIT { \ - .ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT), \ +#define IDA_INIT(name) { \ + .ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT), \ } -#define DEFINE_IDA(name) struct ida name = IDA_INIT +#define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 8dad3dd26eae..ef169d67df92 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -209,12 +209,12 @@ #define DMA_FECTL_IM (((u32)1) << 31) /* FSTS_REG */ -#define DMA_FSTS_PPF ((u32)2) -#define DMA_FSTS_PFO ((u32)1) -#define DMA_FSTS_IQE (1 << 4) -#define DMA_FSTS_ICE (1 << 5) -#define DMA_FSTS_ITE (1 << 6) -#define DMA_FSTS_PRO (1 << 7) +#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */ +#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */ +#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */ +#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */ +#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */ +#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */ #define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff) /* FRCD_REG, 32 bits access */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 41b8c5757859..19938ee6eb31 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -465,23 +465,23 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } -static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) +static inline size_t iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size) { - return -ENODEV; + return 0; } -static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, - int gfp_order) +static inline size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, int gfp_order) { - return -ENODEV; + return 0; } static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { - return -ENODEV; + return 0; } static inline void iommu_flush_tlb_all(struct iommu_domain *domain) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 9385aa57497b..a27cf6652327 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -62,8 +62,11 @@ extern int register_refined_jiffies(long clock_tick_rate); /* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */ #define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ) -/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ -#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) +/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */ +#define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) + +/* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ +#define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) #ifndef __jiffy_arch_data #define __jiffy_arch_data diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 52b70894eaa5..6a1eb0b0aad9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -439,7 +439,8 @@ 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 */ @@ -543,6 +544,7 @@ 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 @@ -560,7 +562,8 @@ 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 */ diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index e251533a5939..89fc8dc7bf38 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -41,11 +41,11 @@ */ /* - * Note about locking : There is no locking required until only * one reader - * and one writer is using the fifo and no kfifo_reset() will be * called - * kfifo_reset_out() can be safely used, until it will be only called + * Note about locking: There is no locking required until only one reader + * and one writer is using the fifo and no kfifo_reset() will be called. + * kfifo_reset_out() can be safely used, until it will be only called * in the reader thread. - * For multiple writer and one reader there is only a need to lock the writer. + * For multiple writer and one reader there is only a need to lock the writer. * And vice versa for only one writer and multiple reader there is only a need * to lock the reader. */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c46016bb25eb..d99b71bc2c66 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -48,13 +48,12 @@ enum memcg_stat_item { MEMCG_NR_STAT, }; -/* Cgroup-specific events, on top of universal VM events */ -enum memcg_event_item { - MEMCG_LOW = NR_VM_EVENT_ITEMS, +enum memcg_memory_event { + MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, - MEMCG_NR_EVENTS, + MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { @@ -88,7 +87,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; - unsigned long events[MEMCG_NR_EVENTS]; + unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -120,6 +119,9 @@ struct mem_cgroup_per_node { unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; + bool congested; /* memcg has many dirty pages */ + /* backed by a congested BDI */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -202,7 +204,8 @@ struct mem_cgroup { /* OOM-Killer disable */ int oom_kill_disable; - /* handle for "memory.events" */ + /* memory.events */ + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; struct cgroup_file events_file; /* protect arrays of thresholds */ @@ -231,9 +234,10 @@ struct mem_cgroup { struct task_struct *move_lock_task; unsigned long move_lock_flags; + /* memory.stat */ struct mem_cgroup_stat_cpu __percpu *stat_cpu; atomic_long_t stat[MEMCG_NR_STAT]; - atomic_long_t events[MEMCG_NR_EVENTS]; + atomic_long_t events[NR_VM_EVENT_ITEMS]; unsigned long socket_pressure; @@ -645,9 +649,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void __count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long x; @@ -663,7 +667,8 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, } static inline void count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long flags; @@ -672,9 +677,8 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, local_irq_restore(flags); } -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void count_memcg_page_event(struct page *page, - int idx) + enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); @@ -698,10 +702,10 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { - count_memcg_events(memcg, event, 1); + atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); } @@ -721,8 +725,8 @@ static inline bool mem_cgroup_disabled(void) return true; } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2b0265265c28..e0e49b5b1ee1 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -216,9 +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) \ ({ \ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ab45f8a0d288..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); /* @@ -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 3ad632366973..1ac1f06a4be6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -747,7 +747,7 @@ int finish_mkwrite_fault(struct vm_fault *vmf); * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is - * rooted at mapping->page_tree, and indexed by offset. + * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * @@ -1466,6 +1466,7 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); +void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, @@ -2108,6 +2109,7 @@ 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; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f11ae29005f1..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 }; @@ -884,7 +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/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/pagemap.h b/include/linux/pagemap.h index 34ce3ebf97d5..b1bd2186e6d2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -144,7 +144,7 @@ void release_pages(struct page **pages, int nr); * 3. check the page is still in pagecache (if no, goto 1) * * Remove-side that cares about stability of _refcount (eg. reclaim) has the - * following (with tree_lock held for write): + * following (with the i_pages lock held): * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) * B. remove page from pagecache * C. free the page @@ -157,7 +157,7 @@ void release_pages(struct page **pages, int nr); * * It is possible that between 1 and 2, the page is removed then the exact same * page is inserted into the same position in pagecache. That's OK: the - * old find_get_page using tree_lock could equally have run before or after + * old find_get_page using a lock could equally have run before or after * such a re-insertion, depending on order that locks are granted. * * Lookups racing against pagecache insertion isn't a big problem: either 1 diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index fc55ff31eca7..34149e8b5f73 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -104,25 +104,29 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The top bits of gfp_mask are used to store the root tags and the IDR flag */ -#define ROOT_IS_IDR ((__force gfp_t)(1 << __GFP_BITS_SHIFT)) -#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT + 1) +/* The IDR tag is stored in the low bits of the GFP flags */ +#define ROOT_IS_IDR ((__force gfp_t)4) +/* The top bits of gfp_mask are used to store the root tags */ +#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) struct radix_tree_root { + spinlock_t xa_lock; gfp_t gfp_mask; struct radix_tree_node __rcu *rnode; }; -#define RADIX_TREE_INIT(mask) { \ +#define RADIX_TREE_INIT(name, mask) { \ + .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .gfp_mask = (mask), \ .rnode = NULL, \ } #define RADIX_TREE(name, mask) \ - struct radix_tree_root name = RADIX_TREE_INIT(mask) + struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) \ do { \ + spin_lock_init(&(root)->xa_lock); \ (root)->gfp_mask = (mask); \ (root)->rnode = NULL; \ } while (0) 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/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/tick.h b/include/linux/tick.h index 7f8c9a127f5a..55388ab45fd4 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -115,27 +115,46 @@ enum tick_dep_bits { extern bool tick_nohz_enabled; extern bool tick_nohz_tick_stopped(void); extern bool tick_nohz_tick_stopped_cpu(int cpu); +extern void tick_nohz_idle_stop_tick(void); +extern void tick_nohz_idle_retain_tick(void); +extern void tick_nohz_idle_restart_tick(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); -extern ktime_t tick_nohz_get_sleep_length(void); +extern bool tick_nohz_idle_got_tick(void); +extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); + +static inline void tick_nohz_idle_stop_tick_protected(void) +{ + local_irq_disable(); + tick_nohz_idle_stop_tick(); + local_irq_enable(); +} + #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; } +static inline void tick_nohz_idle_stop_tick(void) { } +static inline void tick_nohz_idle_retain_tick(void) { } +static inline void tick_nohz_idle_restart_tick(void) { } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } +static inline bool tick_nohz_idle_got_tick(void) { return false; } -static inline ktime_t tick_nohz_get_sleep_length(void) +static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { - return NSEC_PER_SEC / HZ; + *delta_next = TICK_NSEC; + return *delta_next; } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } + +static inline void tick_nohz_idle_stop_tick_protected(void) { } #endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 82c219dfd3bb..9737fbec7019 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -31,6 +31,7 @@ struct timespec64 get_monotonic_coarse64(void); extern void getrawmonotonic64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern time64_t ktime_get_seconds(void); +extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); extern void ktime_get_active_ts64(struct timespec64 *ts); 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/xarray.h b/include/linux/xarray.h new file mode 100644 index 000000000000..2dfc8006fe64 --- /dev/null +++ b/include/linux/xarray.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _LINUX_XARRAY_H +#define _LINUX_XARRAY_H +/* + * eXtensible Arrays + * Copyright (c) 2017 Microsoft Corporation + * Author: Matthew Wilcox <mawilcox@microsoft.com> + */ + +#include <linux/spinlock.h> + +#define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) +#define xa_lock(xa) spin_lock(&(xa)->xa_lock) +#define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) +#define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) +#define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) +#define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) +#define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) +#define xa_lock_irqsave(xa, flags) \ + spin_lock_irqsave(&(xa)->xa_lock, flags) +#define xa_unlock_irqrestore(xa, flags) \ + spin_unlock_irqrestore(&(xa)->xa_lock, flags) + +#endif /* _LINUX_XARRAY_H */ diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 6570c5b45ba1..a1cb91342231 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -346,15 +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) @@ -375,13 +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/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index f8b134f5608f..e7ee32861d51 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -27,6 +27,9 @@ # define MAP_UNINITIALIZED 0x0 /* Don't support this flag */ #endif +/* 0x0100 - 0x80000 flags are defined in asm-generic/mman.h */ +#define MAP_FIXED_NOREPLACE 0x100000 /* MAP_FIXED which doesn't unmap underlying mapping */ + /* * Flags for mlock */ diff --git a/include/uapi/linux/const.h b/include/uapi/linux/const.h index 92537757590a..5ed721ad5b19 100644 --- a/include/uapi/linux/const.h +++ b/include/uapi/linux/const.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* const.h: Macros for dealing with constants. */ -#ifndef _LINUX_CONST_H -#define _LINUX_CONST_H +#ifndef _UAPI_LINUX_CONST_H +#define _UAPI_LINUX_CONST_H /* Some constant macros are used in both assembler and * C code. Therefore we cannot annotate them always with @@ -22,7 +22,10 @@ #define _AT(T,X) ((T)(X)) #endif -#define _BITUL(x) (_AC(1,UL) << (x)) -#define _BITULL(x) (_AC(1,ULL) << (x)) +#define _UL(x) (_AC(x, UL)) +#define _ULL(x) (_AC(x, ULL)) -#endif /* !(_LINUX_CONST_H) */ +#define _BITUL(x) (_UL(1) << (x)) +#define _BITULL(x) (_ULL(1) << (x)) + +#endif /* _UAPI_LINUX_CONST_H */ 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/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/include/uapi/linux/virtio_balloon.h b/include/uapi/linux/virtio_balloon.h index 4e8b8304b793..40297a3181ed 100644 --- a/include/uapi/linux/virtio_balloon.h +++ b/include/uapi/linux/virtio_balloon.h @@ -53,7 +53,9 @@ struct virtio_balloon_config { #define VIRTIO_BALLOON_S_MEMTOT 5 /* Total amount of memory */ #define VIRTIO_BALLOON_S_AVAIL 6 /* Available memory as in /proc */ #define VIRTIO_BALLOON_S_CACHES 7 /* Disk caches */ -#define VIRTIO_BALLOON_S_NR 8 +#define VIRTIO_BALLOON_S_HTLB_PGALLOC 8 /* Hugetlb page allocations */ +#define VIRTIO_BALLOON_S_HTLB_PGFAIL 9 /* Hugetlb page allocation failures */ +#define VIRTIO_BALLOON_S_NR 10 /* * Memory statistics structure. 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 d499f4a80e0b..b795aa341a3a 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> @@ -706,6 +707,7 @@ asmlinkage __visible void __init start_kernel(void) cred_init(); fork_init(); proc_caches_init(); + uts_ns_init(); buffer_init(); key_init(); security_init(); @@ -713,6 +715,7 @@ 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 114a21189613..56fd1c73eedc 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -497,14 +497,14 @@ 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); @@ -512,9 +512,14 @@ 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->q_perm, cmd); if (err) @@ -572,6 +577,7 @@ 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) @@ -690,6 +696,7 @@ 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 2994da8ccc7f..06be75d9217a 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -1220,14 +1220,14 @@ 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); @@ -1235,9 +1235,14 @@ 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->sem_perm, cmd); if (err) @@ -1626,6 +1631,7 @@ 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; @@ -1732,6 +1738,7 @@ 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 acefe44fefef..5639345dbec9 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -415,7 +415,7 @@ 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; @@ -947,14 +947,14 @@ 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); @@ -962,9 +962,20 @@ 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->shm_perm, cmd); if (err) @@ -1104,6 +1115,7 @@ 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) @@ -1282,6 +1294,7 @@ 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 3783b7991cc7..4e81182fa0ac 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/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index 90ff129c88a2..62c301ad0773 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -242,11 +242,11 @@ static void kdb_printbp(kdb_bp_t *bp, int i) kdb_symbol_print(bp->bp_addr, NULL, KDB_SP_DEFAULT); if (bp->bp_enabled) - kdb_printf("\n is enabled"); + kdb_printf("\n is enabled "); else kdb_printf("\n is disabled"); - kdb_printf("\taddr at %016lx, hardtype=%d installed=%d\n", + kdb_printf(" addr at %016lx, hardtype=%d installed=%d\n", bp->bp_addr, bp->bp_type, bp->bp_installed); kdb_printf("\n"); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index dbb0781a0533..e405677ee08d 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1150,6 +1150,16 @@ void kdb_set_current_task(struct task_struct *p) kdb_current_regs = NULL; } +static void drop_newline(char *buf) +{ + size_t len = strlen(buf); + + if (len == 0) + return; + if (*(buf + len - 1) == '\n') + *(buf + len - 1) = '\0'; +} + /* * kdb_local - The main code for kdb. This routine is invoked on a * specific processor, it is not global. The main kdb() routine @@ -1327,6 +1337,7 @@ do_full_getstr: cmdptr = cmd_head; diag = kdb_parse(cmdbuf); if (diag == KDB_NOTFOUND) { + drop_newline(cmdbuf); kdb_printf("Unknown kdb command: '%s'\n", cmdbuf); diag = 0; } @@ -1566,6 +1577,7 @@ static int kdb_md(int argc, const char **argv) int symbolic = 0; int valid = 0; int phys = 0; + int raw = 0; kdbgetintenv("MDCOUNT", &mdcount); kdbgetintenv("RADIX", &radix); @@ -1575,9 +1587,10 @@ static int kdb_md(int argc, const char **argv) repeat = mdcount * 16 / bytesperword; if (strcmp(argv[0], "mdr") == 0) { - if (argc != 2) + if (argc == 2 || (argc == 0 && last_addr != 0)) + valid = raw = 1; + else return KDB_ARGCOUNT; - valid = 1; } else if (isdigit(argv[0][2])) { bytesperword = (int)(argv[0][2] - '0'); if (bytesperword == 0) { @@ -1613,7 +1626,10 @@ static int kdb_md(int argc, const char **argv) radix = last_radix; bytesperword = last_bytesperword; repeat = last_repeat; - mdcount = ((repeat * bytesperword) + 15) / 16; + if (raw) + mdcount = repeat; + else + mdcount = ((repeat * bytesperword) + 15) / 16; } if (argc) { @@ -1630,7 +1646,10 @@ static int kdb_md(int argc, const char **argv) diag = kdbgetularg(argv[nextarg], &val); if (!diag) { mdcount = (int) val; - repeat = mdcount * 16 / bytesperword; + if (raw) + repeat = mdcount; + else + repeat = mdcount * 16 / bytesperword; } } if (argc >= nextarg+1) { @@ -1640,8 +1659,15 @@ static int kdb_md(int argc, const char **argv) } } - if (strcmp(argv[0], "mdr") == 0) - return kdb_mdr(addr, mdcount); + if (strcmp(argv[0], "mdr") == 0) { + int ret; + last_addr = addr; + ret = kdb_mdr(addr, mdcount); + last_addr += mdcount; + last_repeat = mdcount; + last_bytesperword = bytesperword; // to make REPEAT happy + return ret; + } switch (radix) { case 10: @@ -2473,41 +2499,6 @@ static int kdb_kill(int argc, const char **argv) return 0; } -struct kdb_tm { - int tm_sec; /* seconds */ - int tm_min; /* minutes */ - int tm_hour; /* hours */ - int tm_mday; /* day of the month */ - int tm_mon; /* month */ - int tm_year; /* year */ -}; - -static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm) -{ - /* This will work from 1970-2099, 2100 is not a leap year */ - static int mon_day[] = { 31, 29, 31, 30, 31, 30, 31, - 31, 30, 31, 30, 31 }; - memset(tm, 0, sizeof(*tm)); - tm->tm_sec = tv->tv_sec % (24 * 60 * 60); - tm->tm_mday = tv->tv_sec / (24 * 60 * 60) + - (2 * 365 + 1); /* shift base from 1970 to 1968 */ - tm->tm_min = tm->tm_sec / 60 % 60; - tm->tm_hour = tm->tm_sec / 60 / 60; - tm->tm_sec = tm->tm_sec % 60; - tm->tm_year = 68 + 4*(tm->tm_mday / (4*365+1)); - tm->tm_mday %= (4*365+1); - mon_day[1] = 29; - while (tm->tm_mday >= mon_day[tm->tm_mon]) { - tm->tm_mday -= mon_day[tm->tm_mon]; - if (++tm->tm_mon == 12) { - tm->tm_mon = 0; - ++tm->tm_year; - mon_day[1] = 28; - } - } - ++tm->tm_mday; -} - /* * Most of this code has been lifted from kernel/timer.c::sys_sysinfo(). * I cannot call that code directly from kdb, it has an unconditional @@ -2515,10 +2506,10 @@ static void kdb_gmtime(struct timespec *tv, struct kdb_tm *tm) */ static void kdb_sysinfo(struct sysinfo *val) { - struct timespec uptime; - ktime_get_ts(&uptime); + u64 uptime = ktime_get_mono_fast_ns(); + memset(val, 0, sizeof(*val)); - val->uptime = uptime.tv_sec; + val->uptime = div_u64(uptime, NSEC_PER_SEC); val->loads[0] = avenrun[0]; val->loads[1] = avenrun[1]; val->loads[2] = avenrun[2]; @@ -2533,8 +2524,8 @@ static void kdb_sysinfo(struct sysinfo *val) */ static int kdb_summary(int argc, const char **argv) { - struct timespec now; - struct kdb_tm tm; + time64_t now; + struct tm tm; struct sysinfo val; if (argc) @@ -2548,9 +2539,9 @@ static int kdb_summary(int argc, const char **argv) kdb_printf("domainname %s\n", init_uts_ns.name.domainname); kdb_printf("ccversion %s\n", __stringify(CCVERSION)); - now = __current_kernel_time(); - kdb_gmtime(&now, &tm); - kdb_printf("date %04d-%02d-%02d %02d:%02d:%02d " + now = __ktime_get_real_seconds(); + time64_to_tm(now, 0, &tm); + kdb_printf("date %04ld-%02d-%02d %02d:%02d:%02d " "tz_minuteswest %d\n", 1900+tm.tm_year, tm.tm_mon+1, tm.tm_mday, tm.tm_hour, tm.tm_min, tm.tm_sec, diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index d35cc2d3a4cc..990b3cc526c8 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -129,13 +129,13 @@ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) } if (i >= ARRAY_SIZE(kdb_name_table)) { debug_kfree(kdb_name_table[0]); - memcpy(kdb_name_table, kdb_name_table+1, + memmove(kdb_name_table, kdb_name_table+1, sizeof(kdb_name_table[0]) * (ARRAY_SIZE(kdb_name_table)-1)); } else { debug_kfree(knt1); knt1 = kdb_name_table[i]; - memcpy(kdb_name_table+i, kdb_name_table+i+1, + memmove(kdb_name_table+i, kdb_name_table+i+1, sizeof(kdb_name_table[0]) * (ARRAY_SIZE(kdb_name_table)-i-1)); } diff --git a/kernel/panic.c b/kernel/panic.c index 6c3b08cd1139..42e487488554 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 cc9108c2a1fd..ce89f757e6da 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -111,8 +111,8 @@ bool parameq(const char *a, const char *b) static void param_check_unsafe(const struct kernel_param *kp) { 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/pid.c b/kernel/pid.c index ed6c343fe50d..157fe4b19971 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -70,7 +70,7 @@ int pid_max_max = PID_MAX_LIMIT; */ struct pid_namespace init_pid_ns = { .kref = KREF_INIT(2), - .idr = IDR_INIT, + .idr = IDR_INIT(init_pid_ns.idr), .pid_allocated = PIDNS_ADDING, .level = 0, .child_reaper = &init_task, diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 9d7503910ce2..fa39092b7aea 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -295,6 +295,7 @@ int pm_qos_update_target(struct pm_qos_constraints *c, struct plist_node *node, * changed */ plist_del(node, &c->list); + /* fall through */ case PM_QOS_ADD_REQ: plist_node_init(node, new_value); plist_add(node, &c->list); @@ -367,6 +368,7 @@ bool pm_qos_update_flags(struct pm_qos_flags *pqf, break; case PM_QOS_UPDATE_REQ: pm_qos_flags_remove_req(pqf, req); + /* fall through */ case PM_QOS_ADD_REQ: req->flags = val; INIT_LIST_HEAD(&req->node); diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 2975f195e1c4..1a3e9bddd17b 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -141,13 +141,15 @@ static void cpuidle_idle_call(void) } /* - * Tell the RCU framework we are entering an idle section, - * so no more rcu read side critical sections and one more + * The RCU framework needs to be told that we are entering an idle + * section, so no more rcu read side critical sections and one more * step to the grace period */ - rcu_idle_enter(); if (cpuidle_not_available(drv, dev)) { + tick_nohz_idle_stop_tick(); + rcu_idle_enter(); + default_idle_call(); goto exit_idle; } @@ -164,20 +166,37 @@ static void cpuidle_idle_call(void) if (idle_should_enter_s2idle() || dev->use_deepest_state) { if (idle_should_enter_s2idle()) { + rcu_idle_enter(); + entered_state = cpuidle_enter_s2idle(drv, dev); if (entered_state > 0) { local_irq_enable(); goto exit_idle; } + + rcu_idle_exit(); } + tick_nohz_idle_stop_tick(); + rcu_idle_enter(); + next_state = cpuidle_find_deepest_state(drv, dev); call_cpuidle(drv, dev, next_state); } else { + bool stop_tick = true; + /* * Ask the cpuidle framework to choose a convenient idle state. */ - next_state = cpuidle_select(drv, dev); + next_state = cpuidle_select(drv, dev, &stop_tick); + + if (stop_tick) + tick_nohz_idle_stop_tick(); + else + tick_nohz_idle_retain_tick(); + + rcu_idle_enter(); + entered_state = call_cpuidle(drv, dev, next_state); /* * Give the governor an opportunity to reflect on the outcome @@ -222,6 +241,7 @@ static void do_idle(void) rmb(); if (cpu_is_offline(cpu)) { + tick_nohz_idle_stop_tick_protected(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } @@ -235,10 +255,12 @@ static void do_idle(void) * broadcast device expired for us, we don't want to go deep * idle as we know that the IPI is going to arrive right away. */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) + if (cpu_idle_force_poll || tick_check_broadcast_expired()) { + tick_nohz_idle_restart_tick(); cpu_idle_poll(); - else + } else { cpuidle_idle_call(); + } arch_cpu_idle_exit(); } 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, ¶m); } +/** + * 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/time/hrtimer.c b/kernel/time/hrtimer.c index 9b082ce86325..eda1210ce50f 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -480,6 +480,7 @@ __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, + const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { @@ -492,9 +493,22 @@ static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); + if (timer == exclude) { + /* Get to the next timer in the queue. */ + next = timerqueue_iterate_next(next); + if (!next) + continue; + + timer = container_of(next, struct hrtimer, node); + } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; + + /* Skip cpu_base update if a timer is being excluded. */ + if (exclude) + continue; + if (timer->is_soft) cpu_base->softirq_next_timer = timer; else @@ -538,7 +552,8 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; - expires_next = __hrtimer_next_event_base(cpu_base, active, KTIME_MAX); + expires_next = __hrtimer_next_event_base(cpu_base, NULL, + active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } @@ -546,7 +561,8 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; - expires_next = __hrtimer_next_event_base(cpu_base, active, expires_next); + expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, + expires_next); } return expires_next; @@ -1190,6 +1206,39 @@ u64 hrtimer_get_next_event(void) return expires; } + +/** + * hrtimer_next_event_without - time until next expiry event w/o one timer + * @exclude: timer to exclude + * + * Returns the next expiry time over all timers except for the @exclude one or + * KTIME_MAX if none of them is pending. + */ +u64 hrtimer_next_event_without(const struct hrtimer *exclude) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + u64 expires = KTIME_MAX; + unsigned long flags; + + raw_spin_lock_irqsave(&cpu_base->lock, flags); + + if (__hrtimer_hres_active(cpu_base)) { + unsigned int active; + + if (!cpu_base->softirq_activated) { + active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; + expires = __hrtimer_next_event_base(cpu_base, exclude, + active, KTIME_MAX); + } + active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; + expires = __hrtimer_next_event_base(cpu_base, exclude, active, + expires); + } + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); + + return expires; +} #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 8d70da1b9a0d..a09ded765f6c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -31,7 +31,7 @@ /* USER_HZ period (usecs): */ -unsigned long tick_usec = TICK_USEC; +unsigned long tick_usec = USER_TICK_USEC; /* SHIFTED_HZ period (nsecs): */ unsigned long tick_nsec; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f3ab08caa2c3..646645e981f9 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -122,8 +122,7 @@ static ktime_t tick_init_jiffy_update(void) return period; } - -static void tick_sched_do_timer(ktime_t now) +static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int cpu = smp_processor_id(); @@ -143,6 +142,9 @@ static void tick_sched_do_timer(ktime_t now) /* Check, if the jiffies need an update */ if (tick_do_timer_cpu == cpu) tick_do_update_jiffies64(now); + + if (ts->inidle) + ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) @@ -474,7 +476,9 @@ __setup("nohz=", setup_tick_nohz); bool tick_nohz_tick_stopped(void) { - return __this_cpu_read(tick_cpu_sched.tick_stopped); + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + return ts->tick_stopped; } bool tick_nohz_tick_stopped_cpu(int cpu) @@ -537,14 +541,11 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) sched_clock_idle_wakeup_event(); } -static ktime_t tick_nohz_start_idle(struct tick_sched *ts) +static void tick_nohz_start_idle(struct tick_sched *ts) { - ktime_t now = ktime_get(); - - ts->idle_entrytime = now; + ts->idle_entrytime = ktime_get(); ts->idle_active = 1; sched_clock_idle_sleep_event(); - return now; } /** @@ -653,13 +654,10 @@ static inline bool local_timer_softirq_pending(void) return local_softirq_pending() & TIMER_SOFTIRQ; } -static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, - ktime_t now, int cpu) +static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { - struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; unsigned long seq, basejiff; - ktime_t tick; /* Read jiffies and the time when jiffies were updated last */ do { @@ -668,6 +666,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, basejiff = jiffies; } while (read_seqretry(&jiffies_lock, seq)); ts->last_jiffies = basejiff; + ts->timer_expires_base = basemono; /* * Keep the periodic tick, when RCU, architecture or irq_work @@ -712,47 +711,63 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * next period, so no point in stopping it either, bail. */ if (!ts->tick_stopped) { - tick = 0; + ts->timer_expires = 0; goto out; } } /* + * If this CPU is the one which had the do_timer() duty last, we limit + * the sleep time to the timekeeping max_deferment value. + * Otherwise we can sleep as long as we want. + */ + delta = timekeeping_max_deferment(); + if (cpu != tick_do_timer_cpu && + (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) + delta = KTIME_MAX; + + /* Calculate the next expiry time */ + if (delta < (KTIME_MAX - basemono)) + expires = basemono + delta; + else + expires = KTIME_MAX; + + ts->timer_expires = min_t(u64, expires, next_tick); + +out: + return ts->timer_expires; +} + +static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) +{ + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + u64 basemono = ts->timer_expires_base; + u64 expires = ts->timer_expires; + ktime_t tick = expires; + + /* Make sure we won't be trying to stop it twice in a row. */ + ts->timer_expires_base = 0; + + /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we * don't drop this here the jiffies might be stale and * do_timer() never invoked. Keep track of the fact that it - * was the one which had the do_timer() duty last. If this CPU - * is the one which had the do_timer() duty last, we limit the - * sleep time to the timekeeping max_deferment value. - * Otherwise we can sleep as long as we want. + * was the one which had the do_timer() duty last. */ - delta = timekeeping_max_deferment(); if (cpu == tick_do_timer_cpu) { tick_do_timer_cpu = TICK_DO_TIMER_NONE; ts->do_timer_last = 1; } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { - delta = KTIME_MAX; ts->do_timer_last = 0; - } else if (!ts->do_timer_last) { - delta = KTIME_MAX; } - /* Calculate the next expiry time */ - if (delta < (KTIME_MAX - basemono)) - expires = basemono + delta; - else - expires = KTIME_MAX; - - expires = min_t(u64, expires, next_tick); - tick = expires; - /* Skip reprogram of event if its not changed */ if (ts->tick_stopped && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) - goto out; + return; WARN_ON_ONCE(1); printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n", @@ -786,7 +801,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, if (unlikely(expires == KTIME_MAX)) { if (ts->nohz_mode == NOHZ_MODE_HIGHRES) hrtimer_cancel(&ts->sched_timer); - goto out; + return; } hrtimer_set_expires(&ts->sched_timer, tick); @@ -795,15 +810,23 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); else tick_program_event(tick, 1); -out: - /* - * Update the estimated sleep length until the next timer - * (not only the tick). - */ - ts->sleep_length = ktime_sub(dev->next_event, now); - return tick; } +static void tick_nohz_retain_tick(struct tick_sched *ts) +{ + ts->timer_expires_base = 0; +} + +#ifdef CONFIG_NO_HZ_FULL +static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) +{ + if (tick_nohz_next_event(ts, cpu)) + tick_nohz_stop_tick(ts, cpu); + else + tick_nohz_retain_tick(ts); +} +#endif /* CONFIG_NO_HZ_FULL */ + static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ @@ -839,7 +862,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) return; if (can_stop_full_tick(cpu, ts)) - tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); + tick_nohz_stop_sched_tick(ts, cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get()); #endif @@ -865,10 +888,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return false; } - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) { - ts->sleep_length = NSEC_PER_SEC / HZ; + if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) return false; - } if (need_resched()) return false; @@ -903,42 +924,65 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) return true; } -static void __tick_nohz_idle_enter(struct tick_sched *ts) +static void __tick_nohz_idle_stop_tick(struct tick_sched *ts) { - ktime_t now, expires; + ktime_t expires; int cpu = smp_processor_id(); - now = tick_nohz_start_idle(ts); + /* + * If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the + * tick timer expiration time is known already. + */ + if (ts->timer_expires_base) + expires = ts->timer_expires; + else if (can_stop_idle_tick(cpu, ts)) + expires = tick_nohz_next_event(ts, cpu); + else + return; + + ts->idle_calls++; - if (can_stop_idle_tick(cpu, ts)) { + if (expires > 0LL) { int was_stopped = ts->tick_stopped; - ts->idle_calls++; + tick_nohz_stop_tick(ts, cpu); - expires = tick_nohz_stop_sched_tick(ts, now, cpu); - if (expires > 0LL) { - ts->idle_sleeps++; - ts->idle_expires = expires; - } + ts->idle_sleeps++; + ts->idle_expires = expires; if (!was_stopped && ts->tick_stopped) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } + } else { + tick_nohz_retain_tick(ts); } } /** - * tick_nohz_idle_enter - stop the idle tick from the idle task + * tick_nohz_idle_stop_tick - stop the idle tick from the idle task * * When the next event is more than a tick into the future, stop the idle tick - * Called when we start the idle loop. - * - * The arch is responsible of calling: + */ +void tick_nohz_idle_stop_tick(void) +{ + __tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched)); +} + +void tick_nohz_idle_retain_tick(void) +{ + tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); + /* + * Undo the effect of get_next_timer_interrupt() called from + * tick_nohz_next_event(). + */ + timer_clear_idle(); +} + +/** + * tick_nohz_idle_enter - prepare for entering idle on the current CPU * - * - rcu_idle_enter() after its last use of RCU before the CPU is put - * to sleep. - * - rcu_idle_exit() before the first use of RCU after the CPU is woken up. + * Called when we start the idle loop. */ void tick_nohz_idle_enter(void) { @@ -949,8 +993,11 @@ void tick_nohz_idle_enter(void) local_irq_disable(); ts = this_cpu_ptr(&tick_cpu_sched); + + WARN_ON_ONCE(ts->timer_expires_base); + ts->inidle = 1; - __tick_nohz_idle_enter(ts); + tick_nohz_start_idle(ts); local_irq_enable(); } @@ -968,21 +1015,62 @@ void tick_nohz_irq_exit(void) struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); if (ts->inidle) - __tick_nohz_idle_enter(ts); + tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); } /** - * tick_nohz_get_sleep_length - return the length of the current sleep + * tick_nohz_idle_got_tick - Check whether or not the tick handler has run + */ +bool tick_nohz_idle_got_tick(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->got_idle_tick) { + ts->got_idle_tick = 0; + return true; + } + return false; +} + +/** + * tick_nohz_get_sleep_length - return the expected length of the current sleep + * @delta_next: duration until the next event if the tick cannot be stopped * * Called from power state control code with interrupts disabled */ -ktime_t tick_nohz_get_sleep_length(void) +ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { + struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + int cpu = smp_processor_id(); + /* + * The idle entry time is expected to be a sufficient approximation of + * the current time at this point. + */ + ktime_t now = ts->idle_entrytime; + ktime_t next_event; + + WARN_ON_ONCE(!ts->inidle); + + *delta_next = ktime_sub(dev->next_event, now); + + if (!can_stop_idle_tick(cpu, ts)) + return *delta_next; + + next_event = tick_nohz_next_event(ts, cpu); + if (!next_event) + return *delta_next; + + /* + * If the next highres timer to expire is earlier than next_event, the + * idle governor needs to know that. + */ + next_event = min_t(u64, next_event, + hrtimer_next_event_without(&ts->sched_timer)); - return ts->sleep_length; + return ktime_sub(next_event, now); } /** @@ -1031,6 +1119,20 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) #endif } +static void __tick_nohz_idle_restart_tick(struct tick_sched *ts, ktime_t now) +{ + tick_nohz_restart_sched_tick(ts, now); + tick_nohz_account_idle_ticks(ts); +} + +void tick_nohz_idle_restart_tick(void) +{ + struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + + if (ts->tick_stopped) + __tick_nohz_idle_restart_tick(ts, ktime_get()); +} + /** * tick_nohz_idle_exit - restart the idle tick from the idle task * @@ -1041,24 +1143,26 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts) void tick_nohz_idle_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); + bool idle_active, tick_stopped; ktime_t now; local_irq_disable(); WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(ts->timer_expires_base); ts->inidle = 0; + idle_active = ts->idle_active; + tick_stopped = ts->tick_stopped; - if (ts->idle_active || ts->tick_stopped) + if (idle_active || tick_stopped) now = ktime_get(); - if (ts->idle_active) + if (idle_active) tick_nohz_stop_idle(ts, now); - if (ts->tick_stopped) { - tick_nohz_restart_sched_tick(ts, now); - tick_nohz_account_idle_ticks(ts); - } + if (tick_stopped) + __tick_nohz_idle_restart_tick(ts, now); local_irq_enable(); } @@ -1074,7 +1178,7 @@ static void tick_nohz_handler(struct clock_event_device *dev) dev->next_event = KTIME_MAX; - tick_sched_do_timer(now); + tick_sched_do_timer(ts, now); tick_sched_handle(ts, regs); /* No need to reprogram if we are running tickless */ @@ -1169,7 +1273,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) struct pt_regs *regs = get_irq_regs(); ktime_t now = ktime_get(); - tick_sched_do_timer(now); + tick_sched_do_timer(ts, now); /* * Do not call, when we are not in irq context and have diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 954b43dbf21c..6de959a854b2 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -38,31 +38,37 @@ enum tick_nohz_mode { * @idle_exittime: Time when the idle state was left * @idle_sleeptime: Sum of the time slept in idle with sched tick stopped * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding - * @sleep_length: Duration of the current idle sleep + * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) + * @timer_expires_base: Base time clock monotonic for @timer_expires * @do_timer_lst: CPU was the last one doing do_timer before going idle + * @got_idle_tick: Tick timer function has run with @inidle set */ struct tick_sched { struct hrtimer sched_timer; unsigned long check_clocks; enum tick_nohz_mode nohz_mode; + + unsigned int inidle : 1; + unsigned int tick_stopped : 1; + unsigned int idle_active : 1; + unsigned int do_timer_last : 1; + unsigned int got_idle_tick : 1; + ktime_t last_tick; ktime_t next_tick; - int inidle; - int tick_stopped; unsigned long idle_jiffies; unsigned long idle_calls; unsigned long idle_sleeps; - int idle_active; ktime_t idle_entrytime; ktime_t idle_waketime; ktime_t idle_exittime; ktime_t idle_sleeptime; ktime_t iowait_sleeptime; - ktime_t sleep_length; unsigned long last_jiffies; + u64 timer_expires; + u64 timer_expires_base; u64 next_timer; ktime_t idle_expires; - int do_timer_last; atomic_t tick_dep_mask; }; diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index fdbeeb02dde9..cf5c0828ee31 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -31,6 +31,4 @@ static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) } #endif -extern time64_t __ktime_get_real_seconds(void); - #endif /* _TIMEKEEPING_INTERNAL_H */ 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 8fc0d3a9b34f..ce20696d5a92 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/list_debug.c b/lib/list_debug.c index a34db8d27667..5d5424b51b74 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -21,13 +21,13 @@ bool __list_add_valid(struct list_head *new, struct list_head *prev, struct list_head *next) { if (CHECK_DATA_CORRUPTION(next->prev != prev, - "list_add corruption. next->prev should be prev (%p), but was %p. (next=%p).\n", + "list_add corruption. next->prev should be prev (%px), but was %px. (next=%px).\n", prev, next->prev, next) || CHECK_DATA_CORRUPTION(prev->next != next, - "list_add corruption. prev->next should be next (%p), but was %p. (prev=%p).\n", + "list_add corruption. prev->next should be next (%px), but was %px. (prev=%px).\n", next, prev->next, prev) || CHECK_DATA_CORRUPTION(new == prev || new == next, - "list_add double add: new=%p, prev=%p, next=%p.\n", + "list_add double add: new=%px, prev=%px, next=%px.\n", new, prev, next)) return false; @@ -43,16 +43,16 @@ bool __list_del_entry_valid(struct list_head *entry) next = entry->next; if (CHECK_DATA_CORRUPTION(next == LIST_POISON1, - "list_del corruption, %p->next is LIST_POISON1 (%p)\n", + "list_del corruption, %px->next is LIST_POISON1 (%px)\n", entry, LIST_POISON1) || CHECK_DATA_CORRUPTION(prev == LIST_POISON2, - "list_del corruption, %p->prev is LIST_POISON2 (%p)\n", + "list_del corruption, %px->prev is LIST_POISON2 (%px)\n", entry, LIST_POISON2) || CHECK_DATA_CORRUPTION(prev->next != entry, - "list_del corruption. prev->next should be %p, but was %p\n", + "list_del corruption. prev->next should be %px, but was %px\n", entry, prev->next) || CHECK_DATA_CORRUPTION(next->prev != entry, - "list_del corruption. next->prev should be %p, but was %p\n", + "list_del corruption. next->prev should be %px, but was %px\n", entry, next->prev)) return false; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8e00138d593f..da9e10c827df 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -146,7 +146,7 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { - return root->gfp_mask & __GFP_BITS_MASK; + return root->gfp_mask & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, @@ -2285,6 +2285,7 @@ void __init radix_tree_init(void) int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); + BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 413367cf569e..de16f7869fb1 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -296,15 +296,17 @@ 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); @@ -316,7 +318,7 @@ 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_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 89f8a4a4b770..30c0cb8cc9bc 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 */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 08b9aab631ab..023190c69dce 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1020,23 +1020,18 @@ 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; @@ -1044,12 +1039,10 @@ 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 */ @@ -39,6 +39,7 @@ #include <trace/events/cma.h> #include "cma.h" +#include "internal.h" struct cma cma_areas[MAX_CMA_AREAS]; unsigned cma_area_count; @@ -109,23 +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); @@ -139,7 +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; @@ -149,6 +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]); @@ -157,9 +195,32 @@ 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 diff --git a/mm/compaction.c b/mm/compaction.c index 88d01a50a015..028b7210a669 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1166,8 +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; @@ -1451,14 +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; diff --git a/mm/filemap.c b/mm/filemap.c index 693f62212a59..ab77e19ab09c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -66,7 +66,7 @@ * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->__set_page_dirty_buffers) * ->swap_lock (exclusive_swap_page, others) - * ->mapping->tree_lock + * ->i_pages lock * * ->i_mutex * ->i_mmap_rwsem (truncate->unmap_mapping_range) @@ -74,7 +74,7 @@ * ->mmap_sem * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) - * ->mapping->tree_lock (arch-dependent flush_dcache_mmap_lock) + * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_sem * ->lock_page (access_process_vm) @@ -84,7 +84,7 @@ * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) - * ->mapping->tree_lock (__sync_single_inode) + * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_adjust) @@ -95,11 +95,11 @@ * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) - * ->tree_lock (try_to_unmap_one) + * ->i_pages lock (try_to_unmap_one) * ->zone_lru_lock(zone) (follow_page->mark_page_accessed) * ->zone_lru_lock(zone) (check_pte_range->isolate_lru_page) * ->private_lock (page_remove_rmap->set_page_dirty) - * ->tree_lock (page_remove_rmap->set_page_dirty) + * ->i_pages lock (page_remove_rmap->set_page_dirty) * bdi.wb->list_lock (page_remove_rmap->set_page_dirty) * ->inode->i_lock (page_remove_rmap->set_page_dirty) * ->memcg->move_lock (page_remove_rmap->lock_page_memcg) @@ -118,14 +118,15 @@ static int page_cache_tree_insert(struct address_space *mapping, void **slot; int error; - error = __radix_tree_create(&mapping->page_tree, page->index, 0, + error = __radix_tree_create(&mapping->i_pages, page->index, 0, &node, &slot); if (error) return error; if (*slot) { void *p; - p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + p = radix_tree_deref_slot_protected(slot, + &mapping->i_pages.xa_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; @@ -133,7 +134,7 @@ static int page_cache_tree_insert(struct address_space *mapping, if (shadowp) *shadowp = p; } - __radix_tree_replace(&mapping->page_tree, node, slot, page, + __radix_tree_replace(&mapping->i_pages, node, slot, page, workingset_lookup_update(mapping)); mapping->nrpages++; return 0; @@ -155,13 +156,13 @@ static void page_cache_tree_delete(struct address_space *mapping, struct radix_tree_node *node; void **slot; - __radix_tree_lookup(&mapping->page_tree, page->index + i, + __radix_tree_lookup(&mapping->i_pages, page->index + i, &node, &slot); VM_BUG_ON_PAGE(!node && nr != 1, page); - radix_tree_clear_tags(&mapping->page_tree, node, slot); - __radix_tree_replace(&mapping->page_tree, node, slot, shadow, + radix_tree_clear_tags(&mapping->i_pages, node, slot); + __radix_tree_replace(&mapping->i_pages, node, slot, shadow, workingset_lookup_update(mapping)); } @@ -253,7 +254,7 @@ static void unaccount_page_cache_page(struct address_space *mapping, /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage - * is safe. The caller must hold the mapping's tree_lock. + * is safe. The caller must hold the i_pages lock. */ void __delete_from_page_cache(struct page *page, void *shadow) { @@ -296,9 +297,9 @@ void delete_from_page_cache(struct page *page) unsigned long flags; BUG_ON(!PageLocked(page)); - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(page, NULL); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); page_cache_free_page(mapping, page); } @@ -309,14 +310,14 @@ EXPORT_SYMBOL(delete_from_page_cache); * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * - * The function walks over mapping->page_tree and removes pages passed in @pvec - * from the radix tree. The function expects @pvec to be sorted by page index. - * It tolerates holes in @pvec (radix tree entries at those indices are not + * The function walks over mapping->i_pages and removes pages passed in @pvec + * from the mapping. The function expects @pvec to be sorted by page index. + * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the - * @pvec and takes care to delete all corresponding tail pages from the radix - * tree as well. + * @pvec and takes care to delete all corresponding tail pages from the + * mapping as well. * - * The function expects mapping->tree_lock to be held. + * The function expects the i_pages lock to be held. */ static void page_cache_tree_delete_batch(struct address_space *mapping, @@ -330,11 +331,11 @@ page_cache_tree_delete_batch(struct address_space *mapping, pgoff_t start; start = pvec->pages[0]->index; - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { if (i >= pagevec_count(pvec) && !tail_pages) break; page = radix_tree_deref_slot_protected(slot, - &mapping->tree_lock); + &mapping->i_pages.xa_lock); if (radix_tree_exceptional_entry(page)) continue; if (!tail_pages) { @@ -357,8 +358,8 @@ page_cache_tree_delete_batch(struct address_space *mapping, } else { tail_pages--; } - radix_tree_clear_tags(&mapping->page_tree, iter.node, slot); - __radix_tree_replace(&mapping->page_tree, iter.node, slot, NULL, + radix_tree_clear_tags(&mapping->i_pages, iter.node, slot); + __radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL, workingset_lookup_update(mapping)); total_pages++; } @@ -374,14 +375,14 @@ void delete_from_page_cache_batch(struct address_space *mapping, if (!pagevec_count(pvec)) return; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); unaccount_page_cache_page(mapping, pvec->pages[i]); } page_cache_tree_delete_batch(mapping, pvec); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); @@ -798,7 +799,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) new->mapping = mapping; new->index = offset; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); __delete_from_page_cache(old, NULL); error = page_cache_tree_insert(mapping, new, NULL); BUG_ON(error); @@ -810,7 +811,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) __inc_node_page_state(new, NR_FILE_PAGES); if (PageSwapBacked(new)) __inc_node_page_state(new, NR_SHMEM); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); mem_cgroup_migrate(old, new); radix_tree_preload_end(); if (freepage) @@ -852,7 +853,7 @@ static int __add_to_page_cache_locked(struct page *page, page->mapping = mapping; page->index = offset; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); error = page_cache_tree_insert(mapping, page, shadowp); radix_tree_preload_end(); if (unlikely(error)) @@ -861,7 +862,7 @@ static int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting. */ if (!huge) __inc_node_page_state(page, NR_FILE_PAGES); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); @@ -869,7 +870,7 @@ static int __add_to_page_cache_locked(struct page *page, err_insert: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); put_page(page); @@ -1353,7 +1354,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, for (i = 0; i < max_scan; i++) { struct page *page; - page = radix_tree_lookup(&mapping->page_tree, index); + page = radix_tree_lookup(&mapping->i_pages, index); if (!page || radix_tree_exceptional_entry(page)) break; index++; @@ -1394,7 +1395,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, for (i = 0; i < max_scan; i++) { struct page *page; - page = radix_tree_lookup(&mapping->page_tree, index); + page = radix_tree_lookup(&mapping->i_pages, index); if (!page || radix_tree_exceptional_entry(page)) break; index--; @@ -1427,7 +1428,7 @@ struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) rcu_read_lock(); repeat: page = NULL; - pagep = radix_tree_lookup_slot(&mapping->page_tree, offset); + pagep = radix_tree_lookup_slot(&mapping->i_pages, offset); if (pagep) { page = radix_tree_deref_slot(pagep); if (unlikely(!page)) @@ -1633,7 +1634,7 @@ unsigned find_get_entries(struct address_space *mapping, return 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); @@ -1710,7 +1711,7 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, return 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, *start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) { struct page *head, *page; if (iter.index > end) @@ -1795,7 +1796,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, return 0; rcu_read_lock(); - radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) { + radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); @@ -1875,8 +1876,7 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->page_tree, - &iter, *index, tag) { + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) { struct page *head, *page; if (iter.index > end) @@ -1969,8 +1969,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->page_tree, - &iter, start, tag) { + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) { struct page *head, *page; repeat: page = radix_tree_deref_slot(slot); @@ -2624,8 +2623,7 @@ void filemap_map_pages(struct vm_fault *vmf, struct page *head, *page; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, - start_pgoff) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) { if (iter.index > end_pgoff) break; repeat: @@ -160,6 +160,32 @@ 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, @@ -185,6 +211,7 @@ 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, }; @@ -206,13 +233,24 @@ 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; } @@ -227,11 +265,32 @@ 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); @@ -240,110 +299,275 @@ 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, @@ -353,26 +577,20 @@ 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; /* @@ -388,17 +606,8 @@ 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)) @@ -406,79 +615,43 @@ 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 @@ -491,26 +664,17 @@ 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); @@ -520,10 +684,24 @@ 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); @@ -541,14 +719,13 @@ 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 * @@ -568,10 +745,10 @@ 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; * } @@ -579,13 +756,13 @@ 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; @@ -595,7 +772,7 @@ 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; @@ -611,36 +788,34 @@ 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) @@ -648,7 +823,7 @@ 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) @@ -658,51 +833,54 @@ 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; @@ -717,7 +895,7 @@ 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); @@ -725,8 +903,9 @@ 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; } @@ -845,13 +1024,6 @@ 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; @@ -892,9 +1064,8 @@ 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 f0ae8d1d4329..14ed6ee5e02f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -555,8 +555,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_try_charge(page, vma->vm_mm, gfp | __GFP_NORETRY, &memcg, - true)) { + if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1317,7 +1316,7 @@ alloc: } if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm, - huge_gfp | __GFP_NORETRY, &memcg, true))) { + huge_gfp, &memcg, true))) { put_page(new_page); split_huge_pmd(vma, vmf->pmd, vmf->address); if (page) @@ -2402,6 +2401,12 @@ 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); } @@ -2445,7 +2450,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, } else { /* Additional pin to radix tree */ page_ref_add(head, 2); - spin_unlock(&head->mapping->tree_lock); + xa_unlock(&head->mapping->i_pages); } spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); @@ -2653,15 +2658,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mapping) { void **pslot; - spin_lock(&mapping->tree_lock); - pslot = radix_tree_lookup_slot(&mapping->page_tree, + xa_lock(&mapping->i_pages); + pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(head)); /* * Check if the head page is present in radix tree. * We assume all tail are present too, if head is there. */ if (radix_tree_deref_slot_protected(pslot, - &mapping->tree_lock) != head) + &mapping->i_pages.xa_lock) != head) goto fail; } @@ -2695,7 +2700,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } spin_unlock(&pgdata->split_queue_lock); fail: if (mapping) - spin_unlock(&mapping->tree_lock); + xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); unfreeze_page(head); ret = -EBUSY; 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/khugepaged.c b/mm/khugepaged.c index e42568284e06..d7b2a4bf8671 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -965,9 +965,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - /* Do not oom kill for khugepaged charges */ - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY, - &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1326,9 +1324,7 @@ static void collapse_shmem(struct mm_struct *mm, goto out; } - /* Do not oom kill for khugepaged charges */ - if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp | __GFP_NORETRY, - &memcg, true))) { + if (unlikely(mem_cgroup_try_charge(new_page, mm, gfp, &memcg, true))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } @@ -1348,8 +1344,8 @@ static void collapse_shmem(struct mm_struct *mm, */ index = start; - spin_lock_irq(&mapping->tree_lock); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + xa_lock_irq(&mapping->i_pages); + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { int n = min(iter.index, end) - index; /* @@ -1362,7 +1358,7 @@ static void collapse_shmem(struct mm_struct *mm, } nr_none += n; for (; index < min(iter.index, end); index++) { - radix_tree_insert(&mapping->page_tree, index, + radix_tree_insert(&mapping->i_pages, index, new_page + (index % HPAGE_PMD_NR)); } @@ -1371,16 +1367,16 @@ static void collapse_shmem(struct mm_struct *mm, break; page = radix_tree_deref_slot_protected(slot, - &mapping->tree_lock); + &mapping->i_pages.xa_lock); if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, SGP_NOHUGE)) { result = SCAN_FAIL; goto tree_unlocked; } - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); } else if (trylock_page(page)) { get_page(page); } else { @@ -1389,7 +1385,7 @@ static void collapse_shmem(struct mm_struct *mm, } /* - * The page must be locked, so we can drop the tree_lock + * The page must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -1400,7 +1396,7 @@ static void collapse_shmem(struct mm_struct *mm, result = SCAN_TRUNCATED; goto out_unlock; } - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; @@ -1410,11 +1406,11 @@ static void collapse_shmem(struct mm_struct *mm, if (page_mapped(page)) unmap_mapping_pages(mapping, index, 1, false); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); - slot = radix_tree_lookup_slot(&mapping->page_tree, index); + slot = radix_tree_lookup_slot(&mapping->i_pages, index); VM_BUG_ON_PAGE(page != radix_tree_deref_slot_protected(slot, - &mapping->tree_lock), page); + &mapping->i_pages.xa_lock), page); VM_BUG_ON_PAGE(page_mapped(page), page); /* @@ -1435,14 +1431,14 @@ static void collapse_shmem(struct mm_struct *mm, list_add_tail(&page->lru, &pagelist); /* Finally, replace with the new page. */ - radix_tree_replace_slot(&mapping->page_tree, slot, + radix_tree_replace_slot(&mapping->i_pages, slot, new_page + (index % HPAGE_PMD_NR)); slot = radix_tree_iter_resume(slot, &iter); index++; continue; out_lru: - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); putback_lru_page(page); out_isolate_failed: unlock_page(page); @@ -1468,14 +1464,14 @@ out_unlock: } for (; index < end; index++) { - radix_tree_insert(&mapping->page_tree, index, + radix_tree_insert(&mapping->i_pages, index, new_page + (index % HPAGE_PMD_NR)); } nr_none += n; } tree_locked: - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); tree_unlocked: if (result == SCAN_SUCCEED) { @@ -1524,9 +1520,8 @@ tree_unlocked: } else { /* Something went wrong: rollback changes to the radix-tree */ shmem_uncharge(mapping->host, nr_none); - spin_lock_irq(&mapping->tree_lock); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, - start) { + xa_lock_irq(&mapping->i_pages); + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { if (iter.index >= end) break; page = list_first_entry_or_null(&pagelist, @@ -1536,8 +1531,7 @@ tree_unlocked: break; nr_none--; /* Put holes back where they were */ - radix_tree_delete(&mapping->page_tree, - iter.index); + radix_tree_delete(&mapping->i_pages, iter.index); continue; } @@ -1546,16 +1540,15 @@ tree_unlocked: /* Unfreeze the page. */ list_del(&page->lru); page_ref_unfreeze(page, 2); - radix_tree_replace_slot(&mapping->page_tree, - slot, page); + radix_tree_replace_slot(&mapping->i_pages, slot, page); slot = radix_tree_iter_resume(slot, &iter); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); putback_lru_page(page); unlock_page(page); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); } VM_BUG_ON(nr_none); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); /* Unfreeze new_page, caller would take care about freeing it */ page_ref_unfreeze(new_page, 1); @@ -1583,7 +1576,7 @@ static void khugepaged_scan_shmem(struct mm_struct *mm, swap = 0; memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { if (iter.index >= start + HPAGE_PMD_NR) break; @@ -1883,8 +1876,16 @@ static void set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; - for_each_populated_zone(zone) + for_each_populated_zone(zone) { + /* + * We don't need to worry about fragmentation of + * ZONE_MOVABLE since it only has movable pages. + */ + if (zone_idx(zone) > gfp_zone(GFP_USER)) + continue; + nr_zones++; + } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; @@ -1131,6 +1131,13 @@ static int replace_page(struct vm_area_struct *vma, struct page *page, } else { newpte = pte_mkspecial(pfn_pte(page_to_pfn(kpage), vma->vm_page_prot)); + /* + * We're replacing an anonymous page with a zero page, which is + * not anonymous. We need to do proper accounting otherwise we + * will get wrong values in /proc, and a BUG message in dmesg + * when tearing down the mm. + */ + dec_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(*ptep)); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9ec024b862ac..e074f7c637aa 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1485,7 +1485,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { - if (!current->memcg_may_oom) + if (!current->memcg_may_oom || order > PAGE_ALLOC_COSTLY_ORDER) return; /* * We are in the middle of the charge context here, so we @@ -1839,7 +1839,7 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) } } - for (i = 0; i < MEMCG_NR_EVENTS; i++) { + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) { long x; x = this_cpu_xchg(memcg->stat_cpu->events[i], 0); @@ -1858,7 +1858,7 @@ static void reclaim_high(struct mem_cgroup *memcg, do { if (page_counter_read(&memcg->memory) <= memcg->high) continue; - mem_cgroup_event(memcg, MEMCG_HIGH); + memcg_memory_event(memcg, MEMCG_HIGH); try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); } while ((memcg = parent_mem_cgroup(memcg))); } @@ -1949,7 +1949,7 @@ retry: if (!gfpflags_allow_blocking(gfp_mask)) goto nomem; - mem_cgroup_event(mem_over_limit, MEMCG_MAX); + memcg_memory_event(mem_over_limit, MEMCG_MAX); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -1992,7 +1992,7 @@ retry: if (fatal_signal_pending(current)) goto force; - mem_cgroup_event(mem_over_limit, MEMCG_OOM); + memcg_memory_event(mem_over_limit, MEMCG_OOM); mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages * PAGE_SIZE)); @@ -2688,10 +2688,10 @@ static void tree_events(struct mem_cgroup *memcg, unsigned long *events) struct mem_cgroup *iter; int i; - memset(events, 0, sizeof(*events) * MEMCG_NR_EVENTS); + memset(events, 0, sizeof(*events) * NR_VM_EVENT_ITEMS); for_each_mem_cgroup_tree(iter, memcg) { - for (i = 0; i < MEMCG_NR_EVENTS; i++) + for (i = 0; i < NR_VM_EVENT_ITEMS; i++) events[i] += memcg_sum_events(iter, i); } } @@ -4108,6 +4108,9 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn = memcg->nodeinfo[node]; + if (!pn) + return; + free_percpu(pn->lruvec_stat_cpu); kfree(pn); } @@ -5178,7 +5181,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, continue; } - mem_cgroup_event(memcg, MEMCG_OOM); + memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; } @@ -5191,10 +5194,14 @@ static int memory_events_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - seq_printf(m, "low %lu\n", memcg_sum_events(memcg, MEMCG_LOW)); - seq_printf(m, "high %lu\n", memcg_sum_events(memcg, MEMCG_HIGH)); - seq_printf(m, "max %lu\n", memcg_sum_events(memcg, MEMCG_MAX)); - seq_printf(m, "oom %lu\n", memcg_sum_events(memcg, MEMCG_OOM)); + seq_printf(m, "low %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_LOW])); + seq_printf(m, "high %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_HIGH])); + seq_printf(m, "max %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_MAX])); + seq_printf(m, "oom %lu\n", + atomic_long_read(&memcg->memory_events[MEMCG_OOM])); seq_printf(m, "oom_kill %lu\n", memcg_sum_events(memcg, OOM_KILL)); return 0; @@ -5204,7 +5211,7 @@ static int memory_stat_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); unsigned long stat[MEMCG_NR_STAT]; - unsigned long events[MEMCG_NR_EVENTS]; + unsigned long events[NR_VM_EVENT_ITEMS]; int i; /* @@ -5967,9 +5974,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) /* * Interrupts should be disabled here because the caller holds the - * mapping->tree_lock lock which is taken with interrupts-off. It is + * i_pages lock which is taken with interrupts-off. It is * important here to have the interrupts disabled because it is the - * only synchronisation we have for udpating the per-CPU variables. + * only synchronisation we have for updating the per-CPU variables. */ VM_BUG_ON(!irqs_disabled()); mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 2d4bf647cf01..9d142b9b86dc 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1487,7 +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_hotplug.c b/mm/memory_hotplug.c index cc6dfa5832ca..f74826cdceea 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1329,8 +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]; @@ -1373,7 +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; 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..f65dd69e1fd1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -467,20 +467,21 @@ int migrate_page_move_mapping(struct address_space *mapping, oldzone = page_zone(page); newzone = page_zone(newpage); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); - pslot = radix_tree_lookup_slot(&mapping->page_tree, + pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(page)); expected_count += 1 + page_has_private(page); if (page_count(page) != expected_count || - radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { - spin_unlock_irq(&mapping->tree_lock); + radix_tree_deref_slot_protected(pslot, + &mapping->i_pages.xa_lock) != page) { + xa_unlock_irq(&mapping->i_pages); return -EAGAIN; } if (!page_ref_freeze(page, expected_count)) { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return -EAGAIN; } @@ -494,7 +495,7 @@ int migrate_page_move_mapping(struct address_space *mapping, if (mode == MIGRATE_ASYNC && head && !buffer_migrate_lock_buffers(head, mode)) { page_ref_unfreeze(page, expected_count); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return -EAGAIN; } @@ -522,7 +523,7 @@ int migrate_page_move_mapping(struct address_space *mapping, SetPageDirty(newpage); } - radix_tree_replace_slot(&mapping->page_tree, pslot, newpage); + radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); /* * Drop cache reference from old page by unfreezing @@ -531,7 +532,7 @@ int migrate_page_move_mapping(struct address_space *mapping, */ page_ref_unfreeze(page, expected_count - 1); - spin_unlock(&mapping->tree_lock); + xa_unlock(&mapping->i_pages); /* Leave irq disabled to prevent preemption while updating stats */ /* @@ -574,20 +575,19 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, int expected_count; void **pslot; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); - pslot = radix_tree_lookup_slot(&mapping->page_tree, - page_index(page)); + pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(page)); expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || - radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { - spin_unlock_irq(&mapping->tree_lock); + radix_tree_deref_slot_protected(pslot, &mapping->i_pages.xa_lock) != page) { + xa_unlock_irq(&mapping->i_pages); return -EAGAIN; } if (!page_ref_freeze(page, expected_count)) { - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return -EAGAIN; } @@ -596,11 +596,11 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, get_page(newpage); - radix_tree_replace_slot(&mapping->page_tree, pslot, newpage); + radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); page_ref_unfreeze(page, expected_count - 1); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); return MIGRATEPAGE_SUCCESS; } @@ -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! @@ -2339,7 +2307,8 @@ again: ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ - entry = make_migration_entry(page, pte_write(pte)); + entry = make_migration_entry(page, mpfn & + MIGRATE_PFN_WRITE); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pte)) swp_pte = pte_swp_mksoft_dirty(swp_pte); diff --git a/mm/mmap.c b/mm/mmap.c index f2154fc2548b..188f195883b9 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1342,6 +1342,10 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (!(file && path_noexec(&file->f_path))) prot |= PROT_EXEC; + /* force arch specific MAP_FIXED handling in get_unmapped_area */ + if (flags & MAP_FIXED_NOREPLACE) + flags |= MAP_FIXED; + if (!(flags & MAP_FIXED)) addr = round_hint_to_min(addr); @@ -1365,6 +1369,13 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (offset_in_page(addr)) return addr; + if (flags & MAP_FIXED_NOREPLACE) { + struct vm_area_struct *vma = find_vma(mm, addr); + + if (vma && vma->vm_start <= addr) + return -EEXIST; + } + if (prot == PROT_EXEC) { pkey = execute_only_pkey(mm); if (pkey < 0) 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/page-writeback.c b/mm/page-writeback.c index 586f31261c83..5c1a3279e63f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2099,7 +2099,8 @@ void __init page_writeback_init(void) * so that it can tag pages faster than a dirtying process can create them). */ /* - * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce tree_lock latency. + * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce the i_pages lock + * latency. */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) @@ -2109,22 +2110,22 @@ void tag_pages_for_writeback(struct address_space *mapping, struct radix_tree_iter iter; void **slot; - spin_lock_irq(&mapping->tree_lock); - radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, start, + xa_lock_irq(&mapping->i_pages); + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, PAGECACHE_TAG_DIRTY) { if (iter.index > end) break; - radix_tree_iter_tag_set(&mapping->page_tree, &iter, + radix_tree_iter_tag_set(&mapping->i_pages, &iter, PAGECACHE_TAG_TOWRITE); tagged++; if ((tagged % WRITEBACK_TAG_BATCH) != 0) continue; slot = radix_tree_iter_resume(slot, &iter); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); cond_resched(); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); } - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); } EXPORT_SYMBOL(tag_pages_for_writeback); @@ -2467,13 +2468,13 @@ int __set_page_dirty_nobuffers(struct page *page) return 1; } - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, page_index(page), + radix_tree_tag_set(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); if (mapping->host) { @@ -2718,11 +2719,10 @@ int test_clear_page_writeback(struct page *page) struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) { struct bdi_writeback *wb = inode_to_wb(inode); @@ -2736,7 +2736,7 @@ int test_clear_page_writeback(struct page *page) PAGECACHE_TAG_WRITEBACK)) sb_clear_inode_writeback(mapping->host); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = TestClearPageWriteback(page); } @@ -2766,7 +2766,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; @@ -2774,8 +2774,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), + radix_tree_tag_set(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); @@ -2789,14 +2788,12 @@ int __test_set_page_writeback(struct page *page, bool keep_write) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); if (!keep_write) - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), + radix_tree_tag_clear(&mapping->i_pages, page_index(page), PAGECACHE_TAG_TOWRITE); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); } else { ret = TestSetPageWriteback(page); } @@ -2816,7 +2813,7 @@ EXPORT_SYMBOL(__test_set_page_writeback); */ int mapping_tagged(struct address_space *mapping, int tag) { - return radix_tree_tagged(&mapping->page_tree, tag); + return radix_tree_tagged(&mapping->i_pages, tag); } EXPORT_SYMBOL(mapping_tagged); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0b97b8ece4a9..905db9d7962f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -46,7 +46,6 @@ #include <linux/stop_machine.h> #include <linux/sort.h> #include <linux/pfn.h> -#include <xen/xen.h> #include <linux/backing-dev.h> #include <linux/fault-inject.h> #include <linux/page-isolation.h> @@ -205,17 +204,18 @@ 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); @@ -316,9 +316,6 @@ static inline bool update_defer_init(pg_data_t *pgdat, /* Always populate low zones for address-constrained allocations */ if (zone_end < pgdat_end_pfn(pgdat)) return true; - /* Xen PV domains need page structures early */ - if (xen_pv_domain()) - return true; (*nr_initialised)++; if ((*nr_initialised > pgdat->static_init_pgcnt) && (pfn & (PAGES_PER_SECTION - 1)) == 0) { @@ -1746,16 +1743,38 @@ 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); @@ -2870,7 +2889,7 @@ 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); @@ -3146,12 +3165,6 @@ 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 @@ -3178,10 +3191,8 @@ 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])) @@ -3201,13 +3212,6 @@ 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 @@ -3216,7 +3220,7 @@ 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, @@ -3852,10 +3856,6 @@ 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; } @@ -4322,9 +4322,6 @@ 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; } @@ -4734,6 +4731,13 @@ 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; @@ -6200,6 +6204,7 @@ 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 @@ -6227,9 +6232,13 @@ 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 @@ -6278,12 +6287,30 @@ 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); } } @@ -7125,13 +7152,15 @@ 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; } } @@ -7922,7 +7951,7 @@ 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_isolation.c b/mm/page_isolation.c index 61dee77bb211..43e085608846 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -309,8 +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/readahead.c b/mm/readahead.c index 4d57b4644f98..539bbb6c1fad 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -175,7 +175,7 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, break; rcu_read_lock(); - page = radix_tree_lookup(&mapping->page_tree, page_offset); + page = radix_tree_lookup(&mapping->i_pages, page_offset); rcu_read_unlock(); if (page && !radix_tree_exceptional_entry(page)) continue; diff --git a/mm/rmap.c b/mm/rmap.c index 9122787c4947..f0dd4e4565bc 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -32,11 +32,11 @@ * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in __set_page_dirty_buffers) * mem_cgroup_{begin,end}_page_stat (memcg->move_lock) - * mapping->tree_lock (widely used) + * i_pages lock (widely used) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) - * mapping->tree_lock (widely used, in set_page_dirty, + * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * diff --git a/mm/shmem.c b/mm/shmem.c index 4424fc0c33aa..9d6c7e595415 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -332,12 +332,12 @@ static int shmem_radix_tree_replace(struct address_space *mapping, VM_BUG_ON(!expected); VM_BUG_ON(!replacement); - item = __radix_tree_lookup(&mapping->page_tree, index, &node, &pslot); + item = __radix_tree_lookup(&mapping->i_pages, index, &node, &pslot); if (!item) return -ENOENT; if (item != expected) return -ENOENT; - __radix_tree_replace(&mapping->page_tree, node, pslot, + __radix_tree_replace(&mapping->i_pages, node, pslot, replacement, NULL); return 0; } @@ -355,7 +355,7 @@ static bool shmem_confirm_swap(struct address_space *mapping, void *item; rcu_read_lock(); - item = radix_tree_lookup(&mapping->page_tree, index); + item = radix_tree_lookup(&mapping->i_pages, index); rcu_read_unlock(); return item == swp_to_radix_entry(swap); } @@ -590,14 +590,14 @@ static int shmem_add_to_page_cache(struct page *page, page->mapping = mapping; page->index = index; - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); if (PageTransHuge(page)) { void __rcu **results; pgoff_t idx; int i; error = 0; - if (radix_tree_gang_lookup_slot(&mapping->page_tree, + if (radix_tree_gang_lookup_slot(&mapping->i_pages, &results, &idx, index, 1) && idx < index + HPAGE_PMD_NR) { error = -EEXIST; @@ -605,14 +605,14 @@ static int shmem_add_to_page_cache(struct page *page, if (!error) { for (i = 0; i < HPAGE_PMD_NR; i++) { - error = radix_tree_insert(&mapping->page_tree, + error = radix_tree_insert(&mapping->i_pages, index + i, page + i); VM_BUG_ON(error); } count_vm_event(THP_FILE_ALLOC); } } else if (!expected) { - error = radix_tree_insert(&mapping->page_tree, index, page); + error = radix_tree_insert(&mapping->i_pages, index, page); } else { error = shmem_radix_tree_replace(mapping, index, expected, page); @@ -624,10 +624,10 @@ static int shmem_add_to_page_cache(struct page *page, __inc_node_page_state(page, NR_SHMEM_THPS); __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); } else { page->mapping = NULL; - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); page_ref_sub(page, nr); } return error; @@ -643,13 +643,13 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) VM_BUG_ON_PAGE(PageCompound(page), page); - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); error = shmem_radix_tree_replace(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; __dec_node_page_state(page, NR_FILE_PAGES); __dec_node_page_state(page, NR_SHMEM); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); put_page(page); BUG_ON(error); } @@ -662,9 +662,9 @@ static int shmem_free_swap(struct address_space *mapping, { void *old; - spin_lock_irq(&mapping->tree_lock); - old = radix_tree_delete_item(&mapping->page_tree, index, radswap); - spin_unlock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); + old = radix_tree_delete_item(&mapping->i_pages, index, radswap); + xa_unlock_irq(&mapping->i_pages); if (old != radswap) return -ENOENT; free_swap_and_cache(radix_to_swp_entry(radswap)); @@ -675,7 +675,7 @@ static int shmem_free_swap(struct address_space *mapping, * Determine (in bytes) how many of the shmem object's pages mapped by the * given offsets are swapped out. * - * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_partial_swap_usage(struct address_space *mapping, @@ -688,7 +688,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { if (iter.index >= end) break; @@ -717,7 +717,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, * Determine (in bytes) how many of the shmem object's pages mapped by the * given vma is swapped out. * - * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU, + * This is safe to call without i_mutex or the i_pages lock thanks to RCU, * as long as the inode doesn't go away and racy results are not a problem. */ unsigned long shmem_swap_usage(struct vm_area_struct *vma) @@ -1132,7 +1132,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, int error = 0; radswap = swp_to_radix_entry(swap); - index = find_swap_entry(&mapping->page_tree, radswap); + index = find_swap_entry(&mapping->i_pages, radswap); if (index == -1) return -EAGAIN; /* tell shmem_unuse we found nothing */ @@ -1448,7 +1448,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, hindex = round_down(index, HPAGE_PMD_NR); rcu_read_lock(); - if (radix_tree_gang_lookup_slot(&mapping->page_tree, &results, &idx, + if (radix_tree_gang_lookup_slot(&mapping->i_pages, &results, &idx, hindex, 1) && idx < hindex + HPAGE_PMD_NR) { rcu_read_unlock(); return NULL; @@ -1561,14 +1561,14 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, * Our caller will very soon move newpage out of swapcache, but it's * a nice clean interface for us to replace oldpage by newpage there. */ - spin_lock_irq(&swap_mapping->tree_lock); + xa_lock_irq(&swap_mapping->i_pages); error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, newpage); if (!error) { __inc_node_page_state(newpage, NR_FILE_PAGES); __dec_node_page_state(oldpage, NR_FILE_PAGES); } - spin_unlock_irq(&swap_mapping->tree_lock); + xa_unlock_irq(&swap_mapping->i_pages); if (unlikely(error)) { /* @@ -2634,7 +2634,7 @@ static void shmem_tag_pins(struct address_space *mapping) start = 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { + radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { page = radix_tree_deref_slot(slot); if (!page || radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { @@ -2642,10 +2642,10 @@ static void shmem_tag_pins(struct address_space *mapping) 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, + xa_lock_irq(&mapping->i_pages); + radix_tree_tag_set(&mapping->i_pages, iter.index, SHMEM_TAG_PINNED); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); } if (need_resched()) { @@ -2677,7 +2677,7 @@ static int shmem_wait_for_pins(struct address_space *mapping) error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { - if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED)) + if (!radix_tree_tagged(&mapping->i_pages, SHMEM_TAG_PINNED)) break; if (!scan) @@ -2687,7 +2687,7 @@ static int shmem_wait_for_pins(struct address_space *mapping) start = 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter, + radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, SHMEM_TAG_PINNED) { page = radix_tree_deref_slot(slot); @@ -2713,10 +2713,10 @@ static int shmem_wait_for_pins(struct address_space *mapping) error = -EBUSY; } - spin_lock_irq(&mapping->tree_lock); - radix_tree_tag_clear(&mapping->page_tree, + xa_lock_irq(&mapping->i_pages); + radix_tree_tag_clear(&mapping->i_pages, iter.index, SHMEM_TAG_PINNED); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); continue_resched: if (need_resched()) { slot = radix_tree_iter_resume(slot, &iter); diff --git a/mm/slub.c b/mm/slub.c index 4fb037c98782..44aa7847324a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1363,10 +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); /* @@ -1386,17 +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() @@ -1407,13 +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 } @@ -2968,14 +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 diff --git a/mm/swap_state.c b/mm/swap_state.c index f233dccd3b1b..07f9aa2340c3 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -124,10 +124,10 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) SetPageSwapCache(page); address_space = swap_address_space(entry); - spin_lock_irq(&address_space->tree_lock); + xa_lock_irq(&address_space->i_pages); for (i = 0; i < nr; i++) { set_page_private(page + i, entry.val + i); - error = radix_tree_insert(&address_space->page_tree, + error = radix_tree_insert(&address_space->i_pages, idx + i, page + i); if (unlikely(error)) break; @@ -145,13 +145,13 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) VM_BUG_ON(error == -EEXIST); set_page_private(page + i, 0UL); while (i--) { - radix_tree_delete(&address_space->page_tree, idx + i); + radix_tree_delete(&address_space->i_pages, idx + i); set_page_private(page + i, 0UL); } ClearPageSwapCache(page); page_ref_sub(page, nr); } - spin_unlock_irq(&address_space->tree_lock); + xa_unlock_irq(&address_space->i_pages); return error; } @@ -188,7 +188,7 @@ void __delete_from_swap_cache(struct page *page) address_space = swap_address_space(entry); idx = swp_offset(entry); for (i = 0; i < nr; i++) { - radix_tree_delete(&address_space->page_tree, idx + i); + radix_tree_delete(&address_space->i_pages, idx + i); set_page_private(page + i, 0); } ClearPageSwapCache(page); @@ -272,9 +272,9 @@ void delete_from_swap_cache(struct page *page) entry.val = page_private(page); address_space = swap_address_space(entry); - spin_lock_irq(&address_space->tree_lock); + xa_lock_irq(&address_space->i_pages); __delete_from_swap_cache(page); - spin_unlock_irq(&address_space->tree_lock); + xa_unlock_irq(&address_space->i_pages); put_swap_page(page, entry); page_ref_sub(page, hpage_nr_pages(page)); @@ -628,12 +628,11 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) return -ENOMEM; for (i = 0; i < nr; i++) { space = spaces + i; - INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN); + INIT_RADIX_TREE(&space->i_pages, GFP_ATOMIC|__GFP_NOWARN); atomic_set(&space->i_mmap_writable, 0); space->a_ops = &swap_aops; /* swap cache doesn't use writeback related tags */ mapping_set_no_writeback_tags(space); - spin_lock_init(&space->tree_lock); } nr_swapper_spaces[type] = nr; rcu_assign_pointer(swapper_spaces[type], spaces); diff --git a/mm/swapfile.c b/mm/swapfile.c index c7a33717d079..cc2cf04d9018 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -85,7 +85,7 @@ 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]; @@ -2961,6 +2961,10 @@ static unsigned long read_swap_header(struct swap_info_struct *p, maxpages = swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; last_page = swap_header->info.last_page; + if (!last_page) { + pr_warn("Empty swap-file\n"); + return 0; + } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), diff --git a/mm/truncate.c b/mm/truncate.c index c34e2fd4f583..1d2fb2dca96f 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -36,11 +36,11 @@ static inline void __clear_shadow_entry(struct address_space *mapping, struct radix_tree_node *node; void **slot; - if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) + if (!__radix_tree_lookup(&mapping->i_pages, index, &node, &slot)) return; if (*slot != entry) return; - __radix_tree_replace(&mapping->page_tree, node, slot, NULL, + __radix_tree_replace(&mapping->i_pages, node, slot, NULL, workingset_update_node); mapping->nrexceptional--; } @@ -48,9 +48,9 @@ static inline void __clear_shadow_entry(struct address_space *mapping, static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); } /* @@ -79,7 +79,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, dax = dax_mapping(mapping); lock = !dax && indices[j] < end; if (lock) - spin_lock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; @@ -102,7 +102,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, } if (lock) - spin_unlock_irq(&mapping->tree_lock); + xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } @@ -518,8 +518,8 @@ void truncate_inode_pages_final(struct address_space *mapping) * modification that does not see AS_EXITING is * completed before starting the final truncate. */ - spin_lock_irq(&mapping->tree_lock); - spin_unlock_irq(&mapping->tree_lock); + xa_lock_irq(&mapping->i_pages); + xa_unlock_irq(&mapping->i_pages); truncate_inode_pages(mapping, 0); } @@ -627,13 +627,13 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); @@ -641,7 +641,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) put_page(page); /* pagecache ref */ return 1; failed: - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } diff --git a/mm/util.c b/mm/util.c index 029fc2f3b395..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; @@ -668,6 +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 4390a8d5be41..8b920ce3ae02 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -116,6 +116,16 @@ 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; + unsigned int taken; + } nr; }; #ifdef ARCH_HAS_PREFETCH @@ -190,6 +200,29 @@ static bool sane_reclaim(struct scan_control *sc) #endif return false; } + +static void set_memcg_congestion(pg_data_t *pgdat, + struct mem_cgroup *memcg, + bool congested) +{ + struct mem_cgroup_per_node *mn; + + if (!memcg) + return; + + mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + WRITE_ONCE(mn->congested, congested); +} + +static bool memcg_congested(pg_data_t *pgdat, + struct mem_cgroup *memcg) +{ + struct mem_cgroup_per_node *mn; + + mn = mem_cgroup_nodeinfo(memcg, pgdat->node_id); + return READ_ONCE(mn->congested); + +} #else static bool global_reclaim(struct scan_control *sc) { @@ -200,6 +233,18 @@ static bool sane_reclaim(struct scan_control *sc) { return true; } + +static inline void set_memcg_congestion(struct pglist_data *pgdat, + struct mem_cgroup *memcg, bool congested) +{ +} + +static inline bool memcg_congested(struct pglist_data *pgdat, + struct mem_cgroup *memcg) +{ + return false; + +} #endif /* @@ -648,7 +693,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); - spin_lock_irqsave(&mapping->tree_lock, flags); + xa_lock_irqsave(&mapping->i_pages, flags); /* * The non racy check for a busy page. * @@ -672,7 +717,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * load is not satisfied before that of page->_refcount. * * Note that if SetPageDirty is always performed via set_page_dirty, - * and thus under tree_lock, then this ordering is not required. + * and thus under the i_pages lock, then this ordering is not required. */ if (unlikely(PageTransHuge(page)) && PageSwapCache(page)) refcount = 1 + HPAGE_PMD_NR; @@ -690,7 +735,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); __delete_from_swap_cache(page); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { void (*freepage)(struct page *); @@ -711,13 +756,13 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * only page cache pages found in these are zero pages * covering holes, and because we don't want to mix DAX * exceptional entries and shadow exceptional entries in the - * same page_tree. + * same address_space. */ if (reclaimed && page_is_file_cache(page) && !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(mapping, page); __delete_from_page_cache(page, shadow); - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); if (freepage != NULL) freepage(page); @@ -726,7 +771,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, return 1; cannot_free: - spin_unlock_irqrestore(&mapping->tree_lock, flags); + xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } @@ -857,17 +902,6 @@ 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 */ @@ -926,7 +960,7 @@ 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. @@ -1755,23 +1789,6 @@ 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 @@ -1785,48 +1802,17 @@ 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; + sc->nr.taken += nr_taken; + 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; } @@ -2507,6 +2493,12 @@ 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 && memcg_congested(pgdat, memcg)); +} + static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) { struct reclaim_state *reclaim_state = current->reclaim_state; @@ -2522,6 +2514,8 @@ 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; @@ -2536,7 +2530,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) sc->memcg_low_skipped = 1; continue; } - mem_cgroup_event(memcg, MEMCG_LOW); + memcg_memory_event(memcg, MEMCG_LOW); } reclaimed = sc->nr_reclaimed; @@ -2587,6 +2581,67 @@ 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.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_congestion(pgdat, root, true); + + /* + * 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)); @@ -2802,6 +2857,7 @@ retry: continue; last_pgdat = zone->zone_pgdat; snapshot_refaults(sc->target_mem_cgroup, zone->zone_pgdat); + set_memcg_congestion(last_pgdat, sc->target_mem_cgroup, false); } delayacct_freepages_end(); @@ -3808,7 +3864,7 @@ 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 { 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/workingset.c b/mm/workingset.c index b7d616a3bbbe..40ee02c83978 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -202,7 +202,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, * @mapping: address space the page was backing * @page: the page being evicted * - * Returns a shadow entry to be stored in @mapping->page_tree in place + * Returns a shadow entry to be stored in @mapping->i_pages in place * of the evicted @page so that a later refault can be detected. */ void *workingset_eviction(struct address_space *mapping, struct page *page) @@ -348,7 +348,7 @@ void workingset_update_node(struct radix_tree_node *node) * * Avoid acquiring the list_lru lock when the nodes are * already where they should be. The list_empty() test is safe - * as node->private_list is protected by &mapping->tree_lock. + * as node->private_list is protected by the i_pages lock. */ if (node->count && node->count == node->exceptional) { if (list_empty(&node->private_list)) @@ -366,7 +366,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, unsigned long nodes; unsigned long cache; - /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + /* list_lru lock nests inside the IRQ-safe i_pages lock */ local_irq_disable(); nodes = list_lru_shrink_count(&shadow_nodes, sc); local_irq_enable(); @@ -419,21 +419,21 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, /* * Page cache insertions and deletions synchroneously maintain - * the shadow node LRU under the mapping->tree_lock and the + * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any * address_space that has radix tree nodes on the LRU. * - * We can then safely transition to the mapping->tree_lock to + * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ node = container_of(item, struct radix_tree_node, private_list); - mapping = container_of(node->root, struct address_space, page_tree); + mapping = container_of(node->root, struct address_space, i_pages); /* Coming from the list, invert the lock order */ - if (!spin_trylock(&mapping->tree_lock)) { + if (!xa_trylock(&mapping->i_pages)) { spin_unlock(lru_lock); ret = LRU_RETRY; goto out; @@ -468,11 +468,11 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, if (WARN_ON_ONCE(node->exceptional)) goto out_invalid; inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); - __radix_tree_delete_node(&mapping->page_tree, node, + __radix_tree_delete_node(&mapping->i_pages, node, workingset_lookup_update(mapping)); out_invalid: - spin_unlock(&mapping->tree_lock); + xa_unlock(&mapping->i_pages); ret = LRU_REMOVED_RETRY; out: local_irq_enable(); @@ -487,7 +487,7 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, { unsigned long ret; - /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + /* list_lru lock nests inside the IRQ-safe i_pages lock */ local_irq_disable(); ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL); local_irq_enable(); @@ -503,7 +503,7 @@ static struct shrinker workingset_shadow_shrinker = { /* * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe - * mapping->tree_lock. + * i_pages lock. */ static struct lock_class_key shadow_nodes_key; diff --git a/mm/z3fold.c b/mm/z3fold.c index f579ad4a8100..c0bca6153b95 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -467,6 +467,8 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, spin_lock_init(&pool->lock); spin_lock_init(&pool->stale_lock); pool->unbuddied = __alloc_percpu(sizeof(struct list_head)*NCHUNKS, 2); + if (!pool->unbuddied) + goto out_pool; for_each_possible_cpu(cpu) { struct list_head *unbuddied = per_cpu_ptr(pool->unbuddied, cpu); @@ -479,7 +481,7 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, pool->name = name; pool->compact_wq = create_singlethread_workqueue(pool->name); if (!pool->compact_wq) - goto out; + goto out_unbuddied; pool->release_wq = create_singlethread_workqueue(pool->name); if (!pool->release_wq) goto out_wq; @@ -489,8 +491,11 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp, out_wq: destroy_workqueue(pool->compact_wq); -out: +out_unbuddied: + free_percpu(pool->unbuddied); +out_pool: kfree(pool); +out: return NULL; } @@ -533,7 +538,7 @@ static int z3fold_alloc(struct z3fold_pool *pool, size_t size, gfp_t gfp, struct z3fold_header *zhdr = NULL; struct page *page = NULL; enum buddy bud; - bool can_sleep = (gfp & __GFP_RECLAIM) == __GFP_RECLAIM; + bool can_sleep = gfpflags_allow_blocking(gfp); if (!size || (gfp & __GFP_HIGHMEM)) return -EINVAL; diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 764ffd1bb1c5..e16d6713f236 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)$/); @@ -3011,6 +3062,12 @@ sub process { } } +# check for assignments on the start of a line + if ($sline =~ /^\+\s+($Assignment)[^=]/) { + CHK("ASSIGNMENT_CONTINUATIONS", + "Assignment operator '$1' should be on the previous line\n" . $hereprev); + } + # check for && or || at the start of a line if ($rawline =~ /^\+\s*(&&|\|\|)/) { CHK("LOGICAL_CONTINUATIONS", @@ -4032,7 +4089,7 @@ sub process { my ($where, $prefix) = ($-[1], $1); if ($prefix !~ /$Type\s+$/ && ($where != 0 || $prefix !~ /^.\s+$/) && - $prefix !~ /[{,]\s+$/) { + $prefix !~ /[{,:]\s+$/) { if (ERROR("BRACKET_SPACE", "space prohibited before open square bracket '['\n" . $herecurr) && $fix) { @@ -4928,12 +4985,8 @@ sub process { #print "REST<$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 +5058,9 @@ 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 +5100,7 @@ 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 && $stmts !~ /^\s*(if|while|for|switch)\b/) { @@ -5068,11 +5114,7 @@ sub process { } elsif ($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 +5237,8 @@ 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" . $herectx); @@ -5776,36 +5814,50 @@ sub process { } } - # check for vsprintf extension %p<foo> misuses +# check for vsprintf extension %p<foo> misuses if ($^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 +5970,7 @@ 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 +5981,7 @@ 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*\(\s*$FuncArg\s*,\s*("[^"]+")/) { my $format = $6; my $count = $format =~ tr@%@%@; @@ -6065,12 +6111,9 @@ sub process { } if ($r1 !~ /^sizeof\b/ && $r2 =~ /^sizeof\s*\S/ && !($r1 =~ /^$Constant$/ || $r1 =~ /^[A-Z_][A-Z0-9_]*$/)) { - my $ctx = ''; - my $herectx = $here . "\n"; my $cnt = statement_rawlines($stat); - for (my $n = 0; $n < $cnt; $n++) { - $herectx .= raw_line($linenr, $n) . "\n"; - } + my $herectx = get_stat_here($linenr, $cnt, $here); + if (WARN("ALLOC_WITH_MULTIPLY", "Prefer $newfunc over $oldfunc with multiply\n" . $herectx) && $cnt == 1 && @@ -6153,12 +6196,9 @@ sub process { if ($^V && $^V ge 5.10.0 && defined $stat && $stat =~ /^\+[$;\s]*(?:case[$;\s]+\w+[$;\s]*:[$;\s]*|)*[$;\s]*\bdefault[$;\s]*:[$;\s]*;/g) { - my $ctx = ''; - my $herectx = $here . "\n"; my $cnt = statement_rawlines($stat); - for (my $n = 0; $n < $cnt; $n++) { - $herectx .= raw_line($linenr, $n) . "\n"; - } + my $herectx = get_stat_here($linenr, $cnt, $here); + WARN("DEFAULT_NO_BREAK", "switch default: should use break\n" . $herectx); } @@ -6211,6 +6251,12 @@ sub process { } } +# check for bool bitfields + if ($sline =~ /^.\s+bool\s*$Ident\s*:\s*\d+\s*;/) { + WARN("BOOL_BITFIELD", + "Avoid using bool as bitfield. Prefer bool bitfields as unsigned int or u<8|16|32>\n" . $herecurr); + } + # check for semaphores initialized locked if ($line =~ /^.\s*sema_init.+,\W?0\W?\)/) { WARN("CONSIDER_COMPLETION", @@ -6369,10 +6415,7 @@ 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 +6441,7 @@ 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/dtc/include-prefixes/cris b/scripts/dtc/include-prefixes/cris deleted file mode 120000 index 736d998ba506..000000000000 --- a/scripts/dtc/include-prefixes/cris +++ /dev/null @@ -1 +0,0 @@ -../../../arch/cris/boot/dts
\ No newline at end of file diff --git a/scripts/dtc/include-prefixes/metag b/scripts/dtc/include-prefixes/metag deleted file mode 120000 index 87a3c847db8f..000000000000 --- a/scripts/dtc/include-prefixes/metag +++ /dev/null @@ -1 +0,0 @@ -../../../arch/metag/boot/dts
\ No newline at end of file diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 1eeb70e439d7..4cafe6a19167 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6006,6 +6006,7 @@ static int selinux_msg_queue_msgctl(struct kern_ipc_perm *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 +6158,7 @@ static int selinux_shm_shmctl(struct kern_ipc_perm *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 +6274,7 @@ static int selinux_sem_semctl(struct kern_ipc_perm *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 73549007bf9e..0b414836bebd 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -3046,6 +3046,7 @@ static int smack_shm_shmctl(struct kern_ipc_perm *isp, int cmd) switch (cmd) { case IPC_STAT: case SHM_STAT: + case SHM_STAT_ANY: may = MAY_READ; break; case IPC_SET: @@ -3139,6 +3140,7 @@ static int smack_sem_semctl(struct kern_ipc_perm *isp, int cmd) case GETALL: case IPC_STAT: case SEM_STAT: + case SEM_STAT_ANY: may = MAY_READ; break; case SETVAL: @@ -3228,6 +3230,7 @@ static int smack_msg_queue_msgctl(struct kern_ipc_perm *isp, 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/include/linux/spinlock.h b/tools/include/linux/spinlock.h index 4ed569fcb139..b21b586b9854 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -7,6 +7,7 @@ #define spinlock_t pthread_mutex_t #define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; +#define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl new file mode 100755 index 000000000000..b28feea7c363 --- /dev/null +++ b/tools/testing/ktest/config-bisect.pl @@ -0,0 +1,770 @@ +#!/usr/bin/perl -w +# +# Copyright 2015 - Steven Rostedt, Red Hat Inc. +# Copyright 2017 - Steven Rostedt, VMware, Inc. +# +# Licensed under the terms of the GNU GPL License version 2 +# + +# usage: +# config-bisect.pl [options] good-config bad-config [good|bad] +# + +# Compares a good config to a bad config, then takes half of the diffs +# and produces a config that is somewhere between the good config and +# the bad config. That is, the resulting config will start with the +# good config and will try to make half of the differences of between +# the good and bad configs match the bad config. It tries because of +# dependencies between the two configs it may not be able to change +# exactly half of the configs that are different between the two config +# files. + +# Here's a normal way to use it: +# +# $ cd /path/to/linux/kernel +# $ config-bisect.pl /path/to/good/config /path/to/bad/config + +# This will now pull in good config (blowing away .config in that directory +# so do not make that be one of the good or bad configs), and then +# build the config with "make oldconfig" to make sure it matches the +# current kernel. It will then store the configs in that result for +# the good config. It does the same for the bad config as well. +# The algorithm will run, merging half of the differences between +# the two configs and building them with "make oldconfig" to make sure +# the result changes (dependencies may reset changes the tool had made). +# It then copies the result of its good config to /path/to/good/config.tmp +# and the bad config to /path/to/bad/config.tmp (just appends ".tmp" to the +# files passed in). And the ".config" that you should test will be in +# directory + +# After the first run, determine if the result is good or bad then +# run the same command appending the result + +# For good results: +# $ config-bisect.pl /path/to/good/config /path/to/bad/config good + +# For bad results: +# $ config-bisect.pl /path/to/good/config /path/to/bad/config bad + +# Do not change the good-config or bad-config, config-bisect.pl will +# copy the good-config to a temp file with the same name as good-config +# but with a ".tmp" after it. It will do the same with the bad-config. + +# If "good" or "bad" is not stated at the end, it will copy the good and +# bad configs to the .tmp versions. If a .tmp version already exists, it will +# warn before writing over them (-r will not warn, and just write over them). +# If the last config is labeled "good", then it will copy it to the good .tmp +# version. If the last config is labeled "bad", it will copy it to the bad +# .tmp version. It will continue this until it can not merge the two any more +# without the result being equal to either the good or bad .tmp configs. + +my $start = 0; +my $val = ""; + +my $pwd = `pwd`; +chomp $pwd; +my $tree = $pwd; +my $build; + +my $output_config; +my $reset_bisect; + +sub usage { + print << "EOF" + +usage: config-bisect.pl [-l linux-tree][-b build-dir] good-config bad-config [good|bad] + -l [optional] define location of linux-tree (default is current directory) + -b [optional] define location to build (O=build-dir) (default is linux-tree) + good-config the config that is considered good + bad-config the config that does not work + "good" add this if the last run produced a good config + "bad" add this if the last run produced a bad config + If "good" or "bad" is not specified, then it is the start of a new bisect + + Note, each run will create copy of good and bad configs with ".tmp" appended. + +EOF +; + + exit(-1); +} + +sub doprint { + print @_; +} + +sub dodie { + doprint "CRITICAL FAILURE... ", @_, "\n"; + + die @_, "\n"; +} + +sub expand_path { + my ($file) = @_; + + if ($file =~ m,^/,) { + return $file; + } + return "$pwd/$file"; +} + +sub read_prompt { + my ($cancel, $prompt) = @_; + + my $ans; + + for (;;) { + if ($cancel) { + print "$prompt [y/n/C] "; + } else { + print "$prompt [y/N] "; + } + $ans = <STDIN>; + chomp $ans; + if ($ans =~ /^\s*$/) { + if ($cancel) { + $ans = "c"; + } else { + $ans = "n"; + } + } + last if ($ans =~ /^y$/i || $ans =~ /^n$/i); + if ($cancel) { + last if ($ans =~ /^c$/i); + print "Please answer either 'y', 'n' or 'c'.\n"; + } else { + print "Please answer either 'y' or 'n'.\n"; + } + } + if ($ans =~ /^c/i) { + exit; + } + if ($ans !~ /^y$/i) { + return 0; + } + return 1; +} + +sub read_yn { + my ($prompt) = @_; + + return read_prompt 0, $prompt; +} + +sub read_ync { + my ($prompt) = @_; + + return read_prompt 1, $prompt; +} + +sub run_command { + my ($command, $redirect) = @_; + my $start_time; + my $end_time; + my $dord = 0; + my $pid; + + $start_time = time; + + doprint("$command ... "); + + $pid = open(CMD, "$command 2>&1 |") or + dodie "unable to exec $command"; + + if (defined($redirect)) { + open (RD, ">$redirect") or + dodie "failed to write to redirect $redirect"; + $dord = 1; + } + + while (<CMD>) { + print RD if ($dord); + } + + waitpid($pid, 0); + my $failed = $?; + + close(CMD); + close(RD) if ($dord); + + $end_time = time; + my $delta = $end_time - $start_time; + + if ($delta == 1) { + doprint "[1 second] "; + } else { + doprint "[$delta seconds] "; + } + + if ($failed) { + doprint "FAILED!\n"; + } else { + doprint "SUCCESS\n"; + } + + return !$failed; +} + +###### CONFIG BISECT ###### + +# config_ignore holds the configs that were set (or unset) for +# a good config and we will ignore these configs for the rest +# of a config bisect. These configs stay as they were. +my %config_ignore; + +# config_set holds what all configs were set as. +my %config_set; + +# config_off holds the set of configs that the bad config had disabled. +# We need to record them and set them in the .config when running +# olddefconfig, because olddefconfig keeps the defaults. +my %config_off; + +# config_off_tmp holds a set of configs to turn off for now +my @config_off_tmp; + +# config_list is the set of configs that are being tested +my %config_list; +my %null_config; + +my %dependency; + +my $make; + +sub make_oldconfig { + + if (!run_command "$make olddefconfig") { + # Perhaps olddefconfig doesn't exist in this version of the kernel + # try oldnoconfig + doprint "olddefconfig failed, trying make oldnoconfig\n"; + if (!run_command "$make oldnoconfig") { + doprint "oldnoconfig failed, trying yes '' | make oldconfig\n"; + # try a yes '' | oldconfig + run_command "yes '' | $make oldconfig" or + dodie "failed make config oldconfig"; + } + } +} + +sub assign_configs { + my ($hash, $config) = @_; + + doprint "Reading configs from $config\n"; + + open (IN, $config) + or dodie "Failed to read $config"; + + while (<IN>) { + chomp; + if (/^((CONFIG\S*)=.*)/) { + ${$hash}{$2} = $1; + } elsif (/^(# (CONFIG\S*) is not set)/) { + ${$hash}{$2} = $1; + } + } + + close(IN); +} + +sub process_config_ignore { + my ($config) = @_; + + assign_configs \%config_ignore, $config; +} + +sub get_dependencies { + my ($config) = @_; + + my $arr = $dependency{$config}; + if (!defined($arr)) { + return (); + } + + my @deps = @{$arr}; + + foreach my $dep (@{$arr}) { + print "ADD DEP $dep\n"; + @deps = (@deps, get_dependencies $dep); + } + + return @deps; +} + +sub save_config { + my ($pc, $file) = @_; + + my %configs = %{$pc}; + + doprint "Saving configs into $file\n"; + + open(OUT, ">$file") or dodie "Can not write to $file"; + + foreach my $config (keys %configs) { + print OUT "$configs{$config}\n"; + } + close(OUT); +} + +sub create_config { + my ($name, $pc) = @_; + + doprint "Creating old config from $name configs\n"; + + save_config $pc, $output_config; + + make_oldconfig; +} + +# compare two config hashes, and return configs with different vals. +# It returns B's config values, but you can use A to see what A was. +sub diff_config_vals { + my ($pa, $pb) = @_; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + my %ret; + + foreach my $item (keys %a) { + if (defined($b{$item}) && $b{$item} ne $a{$item}) { + $ret{$item} = $b{$item}; + } + } + + return %ret; +} + +# compare two config hashes and return the configs in B but not A +sub diff_configs { + my ($pa, $pb) = @_; + + my %ret; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + foreach my $item (keys %b) { + if (!defined($a{$item})) { + $ret{$item} = $b{$item}; + } + } + + return %ret; +} + +# return if two configs are equal or not +# 0 is equal +1 b has something a does not +# +1 if a and b have a different item. +# -1 if a has something b does not +sub compare_configs { + my ($pa, $pb) = @_; + + my %ret; + + # crappy Perl way to pass in hashes. + my %a = %{$pa}; + my %b = %{$pb}; + + foreach my $item (keys %b) { + if (!defined($a{$item})) { + return 1; + } + if ($a{$item} ne $b{$item}) { + return 1; + } + } + + foreach my $item (keys %a) { + if (!defined($b{$item})) { + return -1; + } + } + + return 0; +} + +sub process_failed { + my ($config) = @_; + + doprint "\n\n***************************************\n"; + doprint "Found bad config: $config\n"; + doprint "***************************************\n\n"; +} + +sub process_new_config { + my ($tc, $nc, $gc, $bc) = @_; + + my %tmp_config = %{$tc}; + my %good_configs = %{$gc}; + my %bad_configs = %{$bc}; + + my %new_configs; + + my $runtest = 1; + my $ret; + + create_config "tmp_configs", \%tmp_config; + assign_configs \%new_configs, $output_config; + + $ret = compare_configs \%new_configs, \%bad_configs; + if (!$ret) { + doprint "New config equals bad config, try next test\n"; + $runtest = 0; + } + + if ($runtest) { + $ret = compare_configs \%new_configs, \%good_configs; + if (!$ret) { + doprint "New config equals good config, try next test\n"; + $runtest = 0; + } + } + + %{$nc} = %new_configs; + + return $runtest; +} + +sub convert_config { + my ($config) = @_; + + if ($config =~ /^# (.*) is not set/) { + $config = "$1=n"; + } + + $config =~ s/^CONFIG_//; + return $config; +} + +sub print_config { + my ($sym, $config) = @_; + + $config = convert_config $config; + doprint "$sym$config\n"; +} + +sub print_config_compare { + my ($good_config, $bad_config) = @_; + + $good_config = convert_config $good_config; + $bad_config = convert_config $bad_config; + + my $good_value = $good_config; + my $bad_value = $bad_config; + $good_value =~ s/(.*)=//; + my $config = $1; + + $bad_value =~ s/.*=//; + + doprint " $config $good_value -> $bad_value\n"; +} + +# Pass in: +# $phalf: half of the configs names you want to add +# $oconfigs: The orginial configs to start with +# $sconfigs: The source to update $oconfigs with (from $phalf) +# $which: The name of which half that is updating (top / bottom) +# $type: The name of the source type (good / bad) +sub make_half { + my ($phalf, $oconfigs, $sconfigs, $which, $type) = @_; + + my @half = @{$phalf}; + my %orig_configs = %{$oconfigs}; + my %source_configs = %{$sconfigs}; + + my %tmp_config = %orig_configs; + + doprint "Settings bisect with $which half of $type configs:\n"; + foreach my $item (@half) { + doprint "Updating $item to $source_configs{$item}\n"; + $tmp_config{$item} = $source_configs{$item}; + } + + return %tmp_config; +} + +sub run_config_bisect { + my ($pgood, $pbad) = @_; + + my %good_configs = %{$pgood}; + my %bad_configs = %{$pbad}; + + my %diff_configs = diff_config_vals \%good_configs, \%bad_configs; + my %b_configs = diff_configs \%good_configs, \%bad_configs; + my %g_configs = diff_configs \%bad_configs, \%good_configs; + + # diff_arr is what is in both good and bad but are different (y->n) + my @diff_arr = keys %diff_configs; + my $len_diff = $#diff_arr + 1; + + # b_arr is what is in bad but not in good (has depends) + my @b_arr = keys %b_configs; + my $len_b = $#b_arr + 1; + + # g_arr is what is in good but not in bad + my @g_arr = keys %g_configs; + my $len_g = $#g_arr + 1; + + my $runtest = 0; + my %new_configs; + my $ret; + + # Look at the configs that are different between good and bad. + # This does not include those that depend on other configs + # (configs depending on other configs that are not set would + # not show up even as a "# CONFIG_FOO is not set" + + + doprint "# of configs to check: $len_diff\n"; + doprint "# of configs showing only in good: $len_g\n"; + doprint "# of configs showing only in bad: $len_b\n"; + + if ($len_diff > 0) { + # Now test for different values + + doprint "Configs left to check:\n"; + doprint " Good Config\t\t\tBad Config\n"; + doprint " -----------\t\t\t----------\n"; + foreach my $item (@diff_arr) { + doprint " $good_configs{$item}\t$bad_configs{$item}\n"; + } + + my $half = int($#diff_arr / 2); + my @tophalf = @diff_arr[0 .. $half]; + + doprint "Set tmp config to be good config with some bad config values\n"; + + my %tmp_config = make_half \@tophalf, \%good_configs, + \%bad_configs, "top", "bad"; + + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; + + if (!$runtest) { + doprint "Set tmp config to be bad config with some good config values\n"; + + my %tmp_config = make_half \@tophalf, \%bad_configs, + \%good_configs, "top", "good"; + + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; + } + } + + if (!$runtest && $len_diff > 0) { + # do the same thing, but this time with bottom half + + my $half = int($#diff_arr / 2); + my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr]; + + doprint "Set tmp config to be good config with some bad config values\n"; + + my %tmp_config = make_half \@bottomhalf, \%good_configs, + \%bad_configs, "bottom", "bad"; + + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; + + if (!$runtest) { + doprint "Set tmp config to be bad config with some good config values\n"; + + my %tmp_config = make_half \@bottomhalf, \%bad_configs, + \%good_configs, "bottom", "good"; + + $runtest = process_new_config \%tmp_config, \%new_configs, + \%good_configs, \%bad_configs; + } + } + + if ($runtest) { + make_oldconfig; + doprint "READY TO TEST .config IN $build\n"; + return 0; + } + + doprint "\n%%%%%%%% FAILED TO FIND SINGLE BAD CONFIG %%%%%%%%\n"; + doprint "Hmm, can't make any more changes without making good == bad?\n"; + doprint "Difference between good (+) and bad (-)\n"; + + foreach my $item (keys %bad_configs) { + if (!defined($good_configs{$item})) { + print_config "-", $bad_configs{$item}; + } + } + + foreach my $item (keys %good_configs) { + next if (!defined($bad_configs{$item})); + if ($good_configs{$item} ne $bad_configs{$item}) { + print_config_compare $good_configs{$item}, $bad_configs{$item}; + } + } + + foreach my $item (keys %good_configs) { + if (!defined($bad_configs{$item})) { + print_config "+", $good_configs{$item}; + } + } + return -1; +} + +sub config_bisect { + my ($good_config, $bad_config) = @_; + my $ret; + + my %good_configs; + my %bad_configs; + my %tmp_configs; + + doprint "Run good configs through make oldconfig\n"; + assign_configs \%tmp_configs, $good_config; + create_config "$good_config", \%tmp_configs; + assign_configs \%good_configs, $output_config; + + doprint "Run bad configs through make oldconfig\n"; + assign_configs \%tmp_configs, $bad_config; + create_config "$bad_config", \%tmp_configs; + assign_configs \%bad_configs, $output_config; + + save_config \%good_configs, $good_config; + save_config \%bad_configs, $bad_config; + + return run_config_bisect \%good_configs, \%bad_configs; +} + +while ($#ARGV >= 0) { + if ($ARGV[0] !~ m/^-/) { + last; + } + my $opt = shift @ARGV; + + if ($opt eq "-b") { + $val = shift @ARGV; + if (!defined($val)) { + die "-b requires value\n"; + } + $build = $val; + } + + elsif ($opt eq "-l") { + $val = shift @ARGV; + if (!defined($val)) { + die "-l requires value\n"; + } + $tree = $val; + } + + elsif ($opt eq "-r") { + $reset_bisect = 1; + } + + elsif ($opt eq "-h") { + usage; + } + + else { + die "Unknow option $opt\n"; + } +} + +$build = $tree if (!defined($build)); + +$tree = expand_path $tree; +$build = expand_path $build; + +if ( ! -d $tree ) { + die "$tree not a directory\n"; +} + +if ( ! -d $build ) { + die "$build not a directory\n"; +} + +usage if $#ARGV < 1; + +if ($#ARGV == 1) { + $start = 1; +} elsif ($#ARGV == 2) { + $val = $ARGV[2]; + if ($val ne "good" && $val ne "bad") { + die "Unknown command '$val', bust be either \"good\" or \"bad\"\n"; + } +} else { + usage; +} + +my $good_start = expand_path $ARGV[0]; +my $bad_start = expand_path $ARGV[1]; + +my $good = "$good_start.tmp"; +my $bad = "$bad_start.tmp"; + +$make = "make"; + +if ($build ne $tree) { + $make = "make O=$build" +} + +$output_config = "$build/.config"; + +if ($start) { + if ( ! -f $good_start ) { + die "$good_start not found\n"; + } + if ( ! -f $bad_start ) { + die "$bad_start not found\n"; + } + if ( -f $good || -f $bad ) { + my $p = ""; + + if ( -f $good ) { + $p = "$good exists\n"; + } + + if ( -f $bad ) { + $p = "$p$bad exists\n"; + } + + if (!defined($reset_bisect)) { + if (!read_yn "${p}Overwrite and start new bisect anyway?") { + exit (-1); + } + } + } + run_command "cp $good_start $good" or die "failed to copy to $good\n"; + run_command "cp $bad_start $bad" or die "faield to copy to $bad\n"; +} else { + if ( ! -f $good ) { + die "Can not find file $good\n"; + } + if ( ! -f $bad ) { + die "Can not find file $bad\n"; + } + if ($val eq "good") { + run_command "cp $output_config $good" or die "failed to copy $config to $good\n"; + } elsif ($val eq "bad") { + run_command "cp $output_config $bad" or die "failed to copy $config to $bad\n"; + } +} + +chdir $tree || die "can't change directory to $tree"; + +my $ret = config_bisect $good, $bad; + +if (!$ret) { + exit(0); +} + +if ($ret > 0) { + doprint "Cleaning temp files\n"; + run_command "rm $good"; + run_command "rm $bad"; + exit(1); +} else { + doprint "See good and bad configs for details:\n"; + doprint "good: $good\n"; + doprint "bad: $bad\n"; + doprint "%%%%%%%% FAILED TO FIND SINGLE BAD CONFIG %%%%%%%%\n"; +} +exit(2); diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index 8809f244bb7c..87af8a68ab25 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -10,6 +10,7 @@ use Fcntl qw(F_GETFL F_SETFL O_NONBLOCK); use File::Path qw(mkpath); use File::Copy qw(cp); use FileHandle; +use FindBin; my $VERSION = "0.2"; @@ -22,6 +23,11 @@ my %evals; #default opts my %default = ( + "MAILER" => "sendmail", # default mailer + "EMAIL_ON_ERROR" => 1, + "EMAIL_WHEN_FINISHED" => 1, + "EMAIL_WHEN_CANCELED" => 0, + "EMAIL_WHEN_STARTED" => 0, "NUM_TESTS" => 1, "TEST_TYPE" => "build", "BUILD_TYPE" => "randconfig", @@ -59,6 +65,7 @@ my %default = ( "GRUB_REBOOT" => "grub2-reboot", "SYSLINUX" => "extlinux", "SYSLINUX_PATH" => "/boot/extlinux", + "CONNECT_TIMEOUT" => 25, # required, and we will ask users if they don't have them but we keep the default # value something that is common. @@ -163,6 +170,8 @@ my $store_failures; my $store_successes; my $test_name; my $timeout; +my $connect_timeout; +my $config_bisect_exec; my $booted_timeout; my $detect_triplefault; my $console; @@ -204,6 +213,20 @@ my $install_time; my $reboot_time; my $test_time; +my $pwd; +my $dirname = $FindBin::Bin; + +my $mailto; +my $mailer; +my $mail_path; +my $mail_command; +my $email_on_error; +my $email_when_finished; +my $email_when_started; +my $email_when_canceled; + +my $script_start_time = localtime(); + # set when a test is something other that just building or install # which would require more options. my $buildonly = 1; @@ -229,6 +252,14 @@ my $no_reboot = 1; my $reboot_success = 0; my %option_map = ( + "MAILTO" => \$mailto, + "MAILER" => \$mailer, + "MAIL_PATH" => \$mail_path, + "MAIL_COMMAND" => \$mail_command, + "EMAIL_ON_ERROR" => \$email_on_error, + "EMAIL_WHEN_FINISHED" => \$email_when_finished, + "EMAIL_WHEN_STARTED" => \$email_when_started, + "EMAIL_WHEN_CANCELED" => \$email_when_canceled, "MACHINE" => \$machine, "SSH_USER" => \$ssh_user, "TMP_DIR" => \$tmpdir, @@ -296,6 +327,8 @@ my %option_map = ( "STORE_SUCCESSES" => \$store_successes, "TEST_NAME" => \$test_name, "TIMEOUT" => \$timeout, + "CONNECT_TIMEOUT" => \$connect_timeout, + "CONFIG_BISECT_EXEC" => \$config_bisect_exec, "BOOTED_TIMEOUT" => \$booted_timeout, "CONSOLE" => \$console, "CLOSE_CONSOLE_SIGNAL" => \$close_console_signal, @@ -337,6 +370,7 @@ my %used_options; # default variables that can be used chomp ($variable{"PWD"} = `pwd`); +$pwd = $variable{"PWD"}; $config_help{"MACHINE"} = << "EOF" The machine hostname that you will test. @@ -718,22 +752,14 @@ sub set_value { my $prvalue = process_variables($rvalue); - if ($buildonly && $lvalue =~ /^TEST_TYPE(\[.*\])?$/ && $prvalue ne "build") { + if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ && + $prvalue !~ /^(config_|)bisect$/ && + $prvalue !~ /^build$/ && + $buildonly) { + # Note if a test is something other than build, then we # will need other mandatory options. if ($prvalue ne "install") { - # for bisect, we need to check BISECT_TYPE - if ($prvalue ne "bisect") { - $buildonly = 0; - } - } else { - # install still limits some mandatory options. - $buildonly = 2; - } - } - - if ($buildonly && $lvalue =~ /^BISECT_TYPE(\[.*\])?$/ && $prvalue ne "build") { - if ($prvalue ne "install") { $buildonly = 0; } else { # install still limits some mandatory options. @@ -1140,7 +1166,8 @@ sub __read_config { sub get_test_case { print "What test case would you like to run?\n"; print " (build, install or boot)\n"; - print " Other tests are available but require editing the config file\n"; + print " Other tests are available but require editing ktest.conf\n"; + print " (see tools/testing/ktest/sample.conf)\n"; my $ans = <STDIN>; chomp $ans; $default{"TEST_TYPE"} = $ans; @@ -1328,8 +1355,8 @@ sub reboot { my ($time) = @_; my $powercycle = 0; - # test if the machine can be connected to within 5 seconds - my $stat = run_ssh("echo check machine status", 5); + # test if the machine can be connected to within a few seconds + my $stat = run_ssh("echo check machine status", $connect_timeout); if (!$stat) { doprint("power cycle\n"); $powercycle = 1; @@ -1404,10 +1431,18 @@ sub do_not_reboot { return $test_type eq "build" || $no_reboot || ($test_type eq "patchcheck" && $opt{"PATCHCHECK_TYPE[$i]"} eq "build") || - ($test_type eq "bisect" && $opt{"BISECT_TYPE[$i]"} eq "build"); + ($test_type eq "bisect" && $opt{"BISECT_TYPE[$i]"} eq "build") || + ($test_type eq "config_bisect" && $opt{"CONFIG_BISECT_TYPE[$i]"} eq "build"); } +my $in_die = 0; + sub dodie { + + # avoid recusion + return if ($in_die); + $in_die = 1; + doprint "CRITICAL FAILURE... ", @_, "\n"; my $i = $iteration; @@ -1426,6 +1461,11 @@ sub dodie { print " See $opt{LOG_FILE} for more info.\n"; } + if ($email_on_error) { + send_email("KTEST: critical failure for your [$test_type] test", + "Your test started at $script_start_time has failed with:\n@_\n"); + } + if ($monitor_cnt) { # restore terminal settings system("stty $stty_orig"); @@ -1477,7 +1517,7 @@ sub exec_console { close($pts); exec $console or - die "Can't open console $console"; + dodie "Can't open console $console"; } sub open_console { @@ -1515,6 +1555,9 @@ sub close_console { doprint "kill child process $pid\n"; kill $close_console_signal, $pid; + doprint "wait for child process $pid to exit\n"; + waitpid($pid, 0); + print "closing!\n"; close($fp); @@ -1625,7 +1668,7 @@ sub save_logs { if (!-d $dir) { mkpath($dir) or - die "can't create $dir"; + dodie "can't create $dir"; } my %files = ( @@ -1638,7 +1681,7 @@ sub save_logs { while (my ($name, $source) = each(%files)) { if (-f "$source") { cp "$source", "$dir/$name" or - die "failed to copy $source"; + dodie "failed to copy $source"; } } @@ -1692,6 +1735,7 @@ sub run_command { my $end_time; my $dolog = 0; my $dord = 0; + my $dostdout = 0; my $pid; $command =~ s/\$SSH_USER/$ssh_user/g; @@ -1710,9 +1754,15 @@ sub run_command { } if (defined($redirect)) { - open (RD, ">$redirect") or - dodie "failed to write to redirect $redirect"; - $dord = 1; + if ($redirect eq 1) { + $dostdout = 1; + # Have the output of the command on its own line + doprint "\n"; + } else { + open (RD, ">$redirect") or + dodie "failed to write to redirect $redirect"; + $dord = 1; + } } my $hit_timeout = 0; @@ -1734,6 +1784,7 @@ sub run_command { } print LOG $line if ($dolog); print RD $line if ($dord); + print $line if ($dostdout); } waitpid($pid, 0); @@ -1812,7 +1863,7 @@ sub get_grub2_index { $ssh_grub =~ s,\$SSH_COMMAND,cat $grub_file,g; open(IN, "$ssh_grub |") - or die "unable to get $grub_file"; + or dodie "unable to get $grub_file"; my $found = 0; @@ -1821,13 +1872,13 @@ sub get_grub2_index { $grub_number++; $found = 1; last; - } elsif (/^menuentry\s/) { + } elsif (/^menuentry\s|^submenu\s/) { $grub_number++; } } close(IN); - die "Could not find '$grub_menu' in $grub_file on $machine" + dodie "Could not find '$grub_menu' in $grub_file on $machine" if (!$found); doprint "$grub_number\n"; $last_grub_menu = $grub_menu; @@ -1855,7 +1906,7 @@ sub get_grub_index { $ssh_grub =~ s,\$SSH_COMMAND,cat /boot/grub/menu.lst,g; open(IN, "$ssh_grub |") - or die "unable to get menu.lst"; + or dodie "unable to get menu.lst"; my $found = 0; @@ -1870,7 +1921,7 @@ sub get_grub_index { } close(IN); - die "Could not find '$grub_menu' in /boot/grub/menu on $machine" + dodie "Could not find '$grub_menu' in /boot/grub/menu on $machine" if (!$found); doprint "$grub_number\n"; $last_grub_menu = $grub_menu; @@ -1983,7 +2034,7 @@ sub monitor { my $full_line = ""; open(DMESG, "> $dmesg") or - die "unable to write to $dmesg"; + dodie "unable to write to $dmesg"; reboot_to; @@ -2862,7 +2913,7 @@ sub run_bisect { sub update_bisect_replay { my $tmp_log = "$tmpdir/ktest_bisect_log"; run_command "git bisect log > $tmp_log" or - die "can't create bisect log"; + dodie "can't create bisect log"; return $tmp_log; } @@ -2871,9 +2922,9 @@ sub bisect { my $result; - die "BISECT_GOOD[$i] not defined\n" if (!defined($bisect_good)); - die "BISECT_BAD[$i] not defined\n" if (!defined($bisect_bad)); - die "BISECT_TYPE[$i] not defined\n" if (!defined($bisect_type)); + dodie "BISECT_GOOD[$i] not defined\n" if (!defined($bisect_good)); + dodie "BISECT_BAD[$i] not defined\n" if (!defined($bisect_bad)); + dodie "BISECT_TYPE[$i] not defined\n" if (!defined($bisect_type)); my $good = $bisect_good; my $bad = $bisect_bad; @@ -2936,7 +2987,7 @@ sub bisect { if ($check ne "good") { doprint "TESTING BISECT BAD [$bad]\n"; run_command "git checkout $bad" or - die "Failed to checkout $bad"; + dodie "Failed to checkout $bad"; $result = run_bisect $type; @@ -2948,7 +2999,7 @@ sub bisect { if ($check ne "bad") { doprint "TESTING BISECT GOOD [$good]\n"; run_command "git checkout $good" or - die "Failed to checkout $good"; + dodie "Failed to checkout $good"; $result = run_bisect $type; @@ -2959,7 +3010,7 @@ sub bisect { # checkout where we started run_command "git checkout $head" or - die "Failed to checkout $head"; + dodie "Failed to checkout $head"; } run_command "git bisect start$start_files" or @@ -3092,76 +3143,6 @@ sub create_config { make_oldconfig; } -# compare two config hashes, and return configs with different vals. -# It returns B's config values, but you can use A to see what A was. -sub diff_config_vals { - my ($pa, $pb) = @_; - - # crappy Perl way to pass in hashes. - my %a = %{$pa}; - my %b = %{$pb}; - - my %ret; - - foreach my $item (keys %a) { - if (defined($b{$item}) && $b{$item} ne $a{$item}) { - $ret{$item} = $b{$item}; - } - } - - return %ret; -} - -# compare two config hashes and return the configs in B but not A -sub diff_configs { - my ($pa, $pb) = @_; - - my %ret; - - # crappy Perl way to pass in hashes. - my %a = %{$pa}; - my %b = %{$pb}; - - foreach my $item (keys %b) { - if (!defined($a{$item})) { - $ret{$item} = $b{$item}; - } - } - - return %ret; -} - -# return if two configs are equal or not -# 0 is equal +1 b has something a does not -# +1 if a and b have a different item. -# -1 if a has something b does not -sub compare_configs { - my ($pa, $pb) = @_; - - my %ret; - - # crappy Perl way to pass in hashes. - my %a = %{$pa}; - my %b = %{$pb}; - - foreach my $item (keys %b) { - if (!defined($a{$item})) { - return 1; - } - if ($a{$item} ne $b{$item}) { - return 1; - } - } - - foreach my $item (keys %a) { - if (!defined($b{$item})) { - return -1; - } - } - - return 0; -} - sub run_config_bisect_test { my ($type) = @_; @@ -3174,166 +3155,57 @@ sub run_config_bisect_test { return $ret; } -sub process_failed { - my ($config) = @_; +sub config_bisect_end { + my ($good, $bad) = @_; + my $diffexec = "diff -u"; + if (-f "$builddir/scripts/diffconfig") { + $diffexec = "$builddir/scripts/diffconfig"; + } doprint "\n\n***************************************\n"; - doprint "Found bad config: $config\n"; + doprint "No more config bisecting possible.\n"; + run_command "$diffexec $good $bad", 1; doprint "***************************************\n\n"; } -# used for config bisecting -my $good_config; -my $bad_config; - -sub process_new_config { - my ($tc, $nc, $gc, $bc) = @_; - - my %tmp_config = %{$tc}; - my %good_configs = %{$gc}; - my %bad_configs = %{$bc}; - - my %new_configs; - - my $runtest = 1; - my $ret; - - create_config "tmp_configs", \%tmp_config; - assign_configs \%new_configs, $output_config; - - $ret = compare_configs \%new_configs, \%bad_configs; - if (!$ret) { - doprint "New config equals bad config, try next test\n"; - $runtest = 0; - } - - if ($runtest) { - $ret = compare_configs \%new_configs, \%good_configs; - if (!$ret) { - doprint "New config equals good config, try next test\n"; - $runtest = 0; - } - } - - %{$nc} = %new_configs; - - return $runtest; -} - sub run_config_bisect { - my ($pgood, $pbad) = @_; - - my $type = $config_bisect_type; - - my %good_configs = %{$pgood}; - my %bad_configs = %{$pbad}; - - my %diff_configs = diff_config_vals \%good_configs, \%bad_configs; - my %b_configs = diff_configs \%good_configs, \%bad_configs; - my %g_configs = diff_configs \%bad_configs, \%good_configs; - - my @diff_arr = keys %diff_configs; - my $len_diff = $#diff_arr + 1; - - my @b_arr = keys %b_configs; - my $len_b = $#b_arr + 1; - - my @g_arr = keys %g_configs; - my $len_g = $#g_arr + 1; - - my $runtest = 1; - my %new_configs; + my ($good, $bad, $last_result) = @_; + my $reset = ""; + my $cmd; my $ret; - # First, lets get it down to a single subset. - # Is the problem with a difference in values? - # Is the problem with a missing config? - # Is the problem with a config that breaks things? - - # Enable all of one set and see if we get a new bad - # or good config. - - # first set the good config to the bad values. - - doprint "d=$len_diff g=$len_g b=$len_b\n"; - - # first lets enable things in bad config that are enabled in good config - - if ($len_diff > 0) { - if ($len_b > 0 || $len_g > 0) { - my %tmp_config = %bad_configs; - - doprint "Set tmp config to be bad config with good config values\n"; - foreach my $item (@diff_arr) { - $tmp_config{$item} = $good_configs{$item}; - } - - $runtest = process_new_config \%tmp_config, \%new_configs, - \%good_configs, \%bad_configs; - } + if (!length($last_result)) { + $reset = "-r"; } + run_command "$config_bisect_exec $reset -b $outputdir $good $bad $last_result", 1; - if (!$runtest && $len_diff > 0) { - - if ($len_diff == 1) { - process_failed $diff_arr[0]; - return 1; - } - my %tmp_config = %bad_configs; - - my $half = int($#diff_arr / 2); - my @tophalf = @diff_arr[0 .. $half]; - - doprint "Settings bisect with top half:\n"; - doprint "Set tmp config to be bad config with some good config values\n"; - foreach my $item (@tophalf) { - $tmp_config{$item} = $good_configs{$item}; - } - - $runtest = process_new_config \%tmp_config, \%new_configs, - \%good_configs, \%bad_configs; - - if (!$runtest) { - my %tmp_config = %bad_configs; - - doprint "Try bottom half\n"; - - my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr]; - - foreach my $item (@bottomhalf) { - $tmp_config{$item} = $good_configs{$item}; - } - - $runtest = process_new_config \%tmp_config, \%new_configs, - \%good_configs, \%bad_configs; - } + # config-bisect returns: + # 0 if there is more to bisect + # 1 for finding a good config + # 2 if it can not find any more configs + # -1 (255) on error + if ($run_command_status) { + return $run_command_status; } - if ($runtest) { - $ret = run_config_bisect_test $type; - if ($ret) { - doprint "NEW GOOD CONFIG\n"; - %good_configs = %new_configs; - run_command "mv $good_config ${good_config}.last"; - save_config \%good_configs, $good_config; - %{$pgood} = %good_configs; - } else { - doprint "NEW BAD CONFIG\n"; - %bad_configs = %new_configs; - run_command "mv $bad_config ${bad_config}.last"; - save_config \%bad_configs, $bad_config; - %{$pbad} = %bad_configs; - } - return 0; + $ret = run_config_bisect_test $config_bisect_type; + if ($ret) { + doprint "NEW GOOD CONFIG\n"; + # Return 3 for good config + return 3; + } else { + doprint "NEW BAD CONFIG\n"; + # Return 4 for bad config + return 4; } - - fail "Hmm, need to do a mix match?\n"; - return -1; } sub config_bisect { my ($i) = @_; + my $good_config; + my $bad_config; + my $type = $config_bisect_type; my $ret; @@ -3353,6 +3225,24 @@ sub config_bisect { $good_config = $output_config; } + if (!defined($config_bisect_exec)) { + # First check the location that ktest.pl ran + my @locations = ( "$pwd/config-bisect.pl", + "$dirname/config-bisect.pl", + "$builddir/tools/testing/ktest/config-bisect.pl", + undef ); + foreach my $loc (@locations) { + doprint "loc = $loc\n"; + $config_bisect_exec = $loc; + last if (defined($config_bisect_exec && -x $config_bisect_exec)); + } + if (!defined($config_bisect_exec)) { + fail "Could not find an executable config-bisect.pl\n", + " Set CONFIG_BISECT_EXEC to point to config-bisect.pl"; + return 1; + } + } + # we don't want min configs to cause issues here. doprint "Disabling 'MIN_CONFIG' for this test\n"; undef $minconfig; @@ -3361,21 +3251,31 @@ sub config_bisect { my %bad_configs; my %tmp_configs; + if (-f "$tmpdir/good_config.tmp" || -f "$tmpdir/bad_config.tmp") { + if (read_yn "Interrupted config-bisect. Continue (n - will start new)?") { + if (-f "$tmpdir/good_config.tmp") { + $good_config = "$tmpdir/good_config.tmp"; + } else { + $good_config = "$tmpdir/good_config"; + } + if (-f "$tmpdir/bad_config.tmp") { + $bad_config = "$tmpdir/bad_config.tmp"; + } else { + $bad_config = "$tmpdir/bad_config"; + } + } + } doprint "Run good configs through make oldconfig\n"; assign_configs \%tmp_configs, $good_config; create_config "$good_config", \%tmp_configs; - assign_configs \%good_configs, $output_config; + $good_config = "$tmpdir/good_config"; + system("cp $output_config $good_config") == 0 or dodie "cp good config"; doprint "Run bad configs through make oldconfig\n"; assign_configs \%tmp_configs, $bad_config; create_config "$bad_config", \%tmp_configs; - assign_configs \%bad_configs, $output_config; - - $good_config = "$tmpdir/good_config"; $bad_config = "$tmpdir/bad_config"; - - save_config \%good_configs, $good_config; - save_config \%bad_configs, $bad_config; + system("cp $output_config $bad_config") == 0 or dodie "cp bad config"; if (defined($config_bisect_check) && $config_bisect_check ne "0") { if ($config_bisect_check ne "good") { @@ -3398,10 +3298,21 @@ sub config_bisect { } } + my $last_run = ""; + do { - $ret = run_config_bisect \%good_configs, \%bad_configs; + $ret = run_config_bisect $good_config, $bad_config, $last_run; + if ($ret == 3) { + $last_run = "good"; + } elsif ($ret == 4) { + $last_run = "bad"; + } print_times; - } while (!$ret); + } while ($ret == 3 || $ret == 4); + + if ($ret == 2) { + config_bisect_end "$good_config.tmp", "$bad_config.tmp"; + } return $ret if ($ret < 0); @@ -3416,9 +3327,9 @@ sub patchcheck_reboot { sub patchcheck { my ($i) = @_; - die "PATCHCHECK_START[$i] not defined\n" + dodie "PATCHCHECK_START[$i] not defined\n" if (!defined($patchcheck_start)); - die "PATCHCHECK_TYPE[$i] not defined\n" + dodie "PATCHCHECK_TYPE[$i] not defined\n" if (!defined($patchcheck_type)); my $start = $patchcheck_start; @@ -3432,7 +3343,7 @@ sub patchcheck { if (defined($patchcheck_end)) { $end = $patchcheck_end; } elsif ($cherry) { - die "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n"; + dodie "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n"; } # Get the true sha1's since we can use things like HEAD~3 @@ -3496,7 +3407,7 @@ sub patchcheck { doprint "\nProcessing commit \"$item\"\n\n"; run_command "git checkout $sha1" or - die "Failed to checkout $sha1"; + dodie "Failed to checkout $sha1"; # only clean on the first and last patch if ($item eq $list[0] || @@ -3587,7 +3498,7 @@ sub read_kconfig { } open(KIN, "$kconfig") - or die "Can't open $kconfig"; + or dodie "Can't open $kconfig"; while (<KIN>) { chomp; @@ -3746,7 +3657,7 @@ sub get_depends { $dep =~ s/^[^$valid]*[$valid]+//; } else { - die "this should never happen"; + dodie "this should never happen"; } } @@ -4007,7 +3918,7 @@ sub make_min_config { # update new ignore configs if (defined($ignore_config)) { open (OUT, ">$temp_config") - or die "Can't write to $temp_config"; + or dodie "Can't write to $temp_config"; foreach my $config (keys %save_configs) { print OUT "$save_configs{$config}\n"; } @@ -4035,7 +3946,7 @@ sub make_min_config { # Save off all the current mandatory configs open (OUT, ">$temp_config") - or die "Can't write to $temp_config"; + or dodie "Can't write to $temp_config"; foreach my $config (keys %keep_configs) { print OUT "$keep_configs{$config}\n"; } @@ -4222,6 +4133,74 @@ sub set_test_option { return eval_option($name, $option, $i); } +sub find_mailer { + my ($mailer) = @_; + + my @paths = split /:/, $ENV{PATH}; + + # sendmail is usually in /usr/sbin + $paths[$#paths + 1] = "/usr/sbin"; + + foreach my $path (@paths) { + if (-x "$path/$mailer") { + return $path; + } + } + + return undef; +} + +sub do_send_mail { + my ($subject, $message) = @_; + + if (!defined($mail_path)) { + # find the mailer + $mail_path = find_mailer $mailer; + if (!defined($mail_path)) { + die "\nCan not find $mailer in PATH\n"; + } + } + + if (!defined($mail_command)) { + if ($mailer eq "mail" || $mailer eq "mailx") { + $mail_command = "\$MAIL_PATH/\$MAILER -s \'\$SUBJECT\' \$MAILTO <<< \'\$MESSAGE\'"; + } elsif ($mailer eq "sendmail" ) { + $mail_command = "echo \'Subject: \$SUBJECT\n\n\$MESSAGE\' | \$MAIL_PATH/\$MAILER -t \$MAILTO"; + } else { + die "\nYour mailer: $mailer is not supported.\n"; + } + } + + $mail_command =~ s/\$MAILER/$mailer/g; + $mail_command =~ s/\$MAIL_PATH/$mail_path/g; + $mail_command =~ s/\$MAILTO/$mailto/g; + $mail_command =~ s/\$SUBJECT/$subject/g; + $mail_command =~ s/\$MESSAGE/$message/g; + + run_command $mail_command; +} + +sub send_email { + + if (defined($mailto)) { + if (!defined($mailer)) { + doprint "No email sent: email or mailer not specified in config.\n"; + return; + } + do_send_mail @_; + } +} + +sub cancel_test { + if ($email_when_canceled) { + send_email("KTEST: Your [$test_type] test was cancelled", + "Your test started at $script_start_time was cancelled: sig int"); + } + die "\nCaught Sig Int, test interrupted: $!\n" +} + +$SIG{INT} = qw(cancel_test); + # First we need to do is the builds for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { @@ -4245,11 +4224,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { $outputdir = set_test_option("OUTPUT_DIR", $i); $builddir = set_test_option("BUILD_DIR", $i); - chdir $builddir || die "can't change directory to $builddir"; + chdir $builddir || dodie "can't change directory to $builddir"; if (!-d $outputdir) { mkpath($outputdir) or - die "can't create $outputdir"; + dodie "can't create $outputdir"; } $make = "$makecmd O=$outputdir"; @@ -4262,9 +4241,15 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { $start_minconfig_defined = 1; # The first test may override the PRE_KTEST option - if (defined($pre_ktest) && $i == 1) { - doprint "\n"; - run_command $pre_ktest; + if ($i == 1) { + if (defined($pre_ktest)) { + doprint "\n"; + run_command $pre_ktest; + } + if ($email_when_started) { + send_email("KTEST: Your [$test_type] test was started", + "Your test was started on $script_start_time"); + } } # Any test can override the POST_KTEST option @@ -4280,7 +4265,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { if (!-d $tmpdir) { mkpath($tmpdir) or - die "can't create $tmpdir"; + dodie "can't create $tmpdir"; } $ENV{"SSH_USER"} = $ssh_user; @@ -4353,7 +4338,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) { if (defined($checkout)) { run_command "git checkout $checkout" or - die "failed to checkout $checkout"; + dodie "failed to checkout $checkout"; } $no_reboot = 0; @@ -4428,4 +4413,8 @@ if ($opt{"POWEROFF_ON_SUCCESS"}) { doprint "\n $successes of $opt{NUM_TESTS} tests were successful\n\n"; +if ($email_when_finished) { + send_email("KTEST: Your [$test_type] test has finished!", + "$successes of $opt{NUM_TESTS} tests started at $script_start_time were successful!"); +} exit 0; diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf index 6c58cd8bbbae..6ca6ca0ce695 100644 --- a/tools/testing/ktest/sample.conf +++ b/tools/testing/ktest/sample.conf @@ -1,6 +1,11 @@ # # Config file for ktest.pl # +# Place your customized version of this, in the working directory that +# ktest.pl is run from. By default, ktest.pl will look for a file +# called "ktest.conf", but you can name it anything you like and specify +# the name of your config file as the first argument of ktest.pl. +# # Note, all paths must be absolute # @@ -396,6 +401,44 @@ #### Optional Config Options (all have defaults) #### +# Email options for receiving notifications. Users must setup +# the specified mailer prior to using this feature. +# +# (default undefined) +#MAILTO = +# +# Supported mailers: sendmail, mail, mailx +# (default sendmail) +#MAILER = sendmail +# +# The executable to run +# (default: for sendmail "/usr/sbin/sendmail", otherwise equals ${MAILER}) +#MAIL_EXEC = /usr/sbin/sendmail +# +# The command used to send mail, which uses the above options +# can be modified. By default if the mailer is "sendmail" then +# MAIL_COMMAND = echo \'Subject: $SUBJECT\n\n$MESSAGE\' | $MAIL_PATH/$MAILER -t $MAILTO +# For mail or mailx: +# MAIL_COMMAND = "$MAIL_PATH/$MAILER -s \'$SUBJECT\' $MAILTO <<< \'$MESSAGE\' +# ktest.pl will do the substitution for MAIL_PATH, MAILER, MAILTO at the time +# it sends the mail if "$FOO" format is used. If "${FOO}" format is used, +# then the substitutions will occur at the time the config file is read. +# But note, MAIL_PATH and MAILER require being set by the config file if +# ${MAIL_PATH} or ${MAILER} are used, but not if $MAIL_PATH or $MAILER are. +#MAIL_COMMAND = echo \'Subject: $SUBJECT\n\n$MESSAGE\' | $MAIL_PATH/$MAILER -t $MAILTO +# +# Errors are defined as those would terminate the script +# (default 1) +#EMAIL_ON_ERROR = 1 +# (default 1) +#EMAIL_WHEN_FINISHED = 1 +# (default 0) +#EMAIL_WHEN_STARTED = 1 +# +# Users can cancel the test by Ctrl^C +# (default 0) +#EMAIL_WHEN_CANCELED = 1 + # Start a test setup. If you leave this off, all options # will be default and the test will run once. # This is a label and not really an option (it takes no value). @@ -725,6 +768,13 @@ # (default 120) #TIMEOUT = 120 +# The timeout in seconds when to test if the box can be rebooted +# or not. Before issuing the reboot command, a ssh connection +# is attempted to see if the target machine is still active. +# If the target does not connect within this timeout, a power cycle +# is issued instead of a reboot. +# CONNECT_TIMEOUT = 25 + # In between tests, a reboot of the box may occur, and this # is the time to wait for the console after it stops producing # output. Some machines may not produce a large lag on reboot @@ -1167,6 +1217,16 @@ # Set it to "good" to test only the good config and set it # to "bad" to only test the bad config. # +# CONFIG_BISECT_EXEC (optional) +# The config bisect is a separate program that comes with ktest.pl. +# By befault, it will look for: +# `pwd`/config-bisect.pl # the location ktest.pl was executed from. +# If it does not find it there, it will look for: +# `dirname <ktest.pl>`/config-bisect.pl # The directory that holds ktest.pl +# If it does not find it there, it will look for: +# ${BUILD_DIR}/tools/testing/ktest/config-bisect.pl +# Setting CONFIG_BISECT_EXEC will override where it looks. +# # Example: # TEST_START # TEST_TYPE = config_bisect diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h index e3201ccf54c3..32159c08a52e 100644 --- a/tools/testing/radix-tree/linux/gfp.h +++ b/tools/testing/radix-tree/linux/gfp.h @@ -19,6 +19,7 @@ #define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM) +#define GFP_ZONEMASK 0x0fu #define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) #define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) #define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 2fc410bc4f33..32aafa92074c 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -25,6 +25,7 @@ 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..e38ad6d94d4b --- /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..af1d0a6af810 --- /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..aebf4be56111 --- /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..303f26092306 --- /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..0cb79e1f1674 --- /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..d584419f50a7 --- /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..12e397f78592 --- /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; +} |
