From 164a08cee1358e360c47fcb26a7720461d5853a5 Mon Sep 17 00:00:00 2001 From: Lv Zheng Date: Fri, 17 Nov 2017 15:40:18 -0800 Subject: ACPICA: Dispatcher: Introduce timeout mechanism for infinite loop detection ACPICA commit 9605023e7e6d1f05581502766c8cf2905bcc03d9 This patch implements a new infinite loop detection mechanism to replace the old one, it uses acpi_os_get_timer() to limit loop execution into a determined time slice. This is useful in case some hardware/firmware operations really require the AML interpreter to wait while the old mechanism could expire too fast on recent machines. The new mechanism converts old acpi_gbl_max_loop_iterations to store the user configurable value for the new mechanism in order to allow users to be still able to configure this value for acpiexec via command line. This patch also removes wrong initilization code of acpi_gbl_max_loop_iterations accordingly (it should have been initialized by ACPI_INIT_GLOBAL, and the default value is also properly tuned for acpiexec). Reported by M. Foronda, fixed by Lv Zheng. Link: https://github.com/acpica/acpica/commit/9605023e Link: https://bugzilla.kernel.org/show_bug.cgi?id=156501 Reported-by: M. Foronda Signed-off-by: Lv Zheng Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acconfig.h | 4 ++-- include/acpi/acpixf.h | 4 ++-- include/acpi/actypes.h | 2 ++ 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h index 6db3b4668b1a..ffe364fa4040 100644 --- a/include/acpi/acconfig.h +++ b/include/acpi/acconfig.h @@ -145,9 +145,9 @@ #define ACPI_ADDRESS_RANGE_MAX 2 -/* Maximum number of While() loops before abort */ +/* Maximum time (default 30s) of While() loops before abort */ -#define ACPI_MAX_LOOP_COUNT 0x000FFFFF +#define ACPI_MAX_LOOP_TIMEOUT 30 /****************************************************************************** * diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index e1dd1a8d42b6..1a4322db0274 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -260,11 +260,11 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_osi_data, 0); ACPI_INIT_GLOBAL(u8, acpi_gbl_reduced_hardware, FALSE); /* - * Maximum number of While() loop iterations before forced method abort. + * Maximum timeout for While() loop iterations before forced method abort. * This mechanism is intended to prevent infinite loops during interpreter * execution within a host kernel. */ -ACPI_INIT_GLOBAL(u32, acpi_gbl_max_loop_iterations, ACPI_MAX_LOOP_COUNT); +ACPI_INIT_GLOBAL(u32, acpi_gbl_max_loop_iterations, ACPI_MAX_LOOP_TIMEOUT); /* * This mechanism is used to trace a specified AML method. The method is diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index 4f077edb9b81..ddde2790a54a 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -468,6 +468,8 @@ typedef void *acpi_handle; /* Actually a ptr to a NS Node */ #define ACPI_NSEC_PER_MSEC 1000000L #define ACPI_NSEC_PER_SEC 1000000000L +#define ACPI_TIME_AFTER(a, b) ((s64)((b) - (a)) < 0) + /* Owner IDs are used to track namespace nodes for selective deletion */ typedef u8 acpi_owner_id; -- cgit v1.2.3 From a26f4df913140a43cf7e3cb89b12ac27d87df984 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:40:19 -0800 Subject: ACPICA: Rename AE_AML_INFINITE_LOOP exception ACPICA commit e017213698374e01225f641ba0917516d8e91427 More appropriately renamed to AE_AML_LOOP_TIMEOUT, now that a real timer is used for the implementation. Link: https://github.com/acpica/acpica/commit/e0172136 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/dscontrol.c | 2 +- include/acpi/acexcep.h | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/acpi/acpica/dscontrol.c b/drivers/acpi/acpica/dscontrol.c index 244075dbc03a..4b6ebc2a2851 100644 --- a/drivers/acpi/acpica/dscontrol.c +++ b/drivers/acpi/acpica/dscontrol.c @@ -216,7 +216,7 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state *walk_state, if (ACPI_TIME_AFTER(acpi_os_get_timer(), control_state->control. loop_timeout)) { - status = AE_AML_INFINITE_LOOP; + status = AE_AML_LOOP_TIMEOUT; break; } diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index 17d61b1f2511..e1f9fe47f69e 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -195,7 +195,7 @@ struct acpi_exception_info { #define AE_AML_CIRCULAR_REFERENCE EXCEP_AML (0x001E) #define AE_AML_BAD_RESOURCE_LENGTH EXCEP_AML (0x001F) #define AE_AML_ILLEGAL_ADDRESS EXCEP_AML (0x0020) -#define AE_AML_INFINITE_LOOP EXCEP_AML (0x0021) +#define AE_AML_LOOP_TIMEOUT EXCEP_AML (0x0021) #define AE_AML_UNINITIALIZED_NODE EXCEP_AML (0x0022) #define AE_AML_TARGET_TYPE EXCEP_AML (0x0023) @@ -368,8 +368,8 @@ static const struct acpi_exception_info acpi_gbl_exception_names_aml[] = { "The length of a Resource Descriptor in the AML is incorrect"), EXCEP_TXT("AE_AML_ILLEGAL_ADDRESS", "A memory, I/O, or PCI configuration address is invalid"), - EXCEP_TXT("AE_AML_INFINITE_LOOP", - "An apparent infinite AML While loop, method was aborted"), + EXCEP_TXT("AE_AML_LOOP_TIMEOUT", + "An AML While loop exceeded the maximum execution time"), EXCEP_TXT("AE_AML_UNINITIALIZED_NODE", "A namespace node is uninitialized or unresolved"), EXCEP_TXT("AE_AML_TARGET_TYPE", -- cgit v1.2.3 From 4c189c9da00edcb1e5cc82b9f46a02692b465440 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:40:22 -0800 Subject: ACPICA: iASL/Tools: Add support for PDTT, SDEV, TPM2 ACPI tables ACPICA commit 028d331522f239fa615148273f6d10e9deadb1b3 Full support for PDTT and SDEV Partial support for TPM2 due to odd layout of the optional fields of the table. Link: https://github.com/acpica/acpica/commit/028d3315 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 77 ++++++++++++++++++++++++++++++++++++++++++++++----- include/acpi/actbl2.h | 14 +++++++++- 2 files changed, 83 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 7a89e6de94da..ea0c71ece407 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -69,9 +69,10 @@ #define ACPI_SIG_HEST "HEST" /* Hardware Error Source Table */ #define ACPI_SIG_MADT "APIC" /* Multiple APIC Description Table */ #define ACPI_SIG_MSCT "MSCT" /* Maximum System Characteristics Table */ -#define ACPI_SIG_PDTT "PDTT" /* Processor Debug Trigger Table */ +#define ACPI_SIG_PDTT "PDTT" /* Platform Debug Trigger Table */ #define ACPI_SIG_PPTT "PPTT" /* Processor Properties Topology Table */ #define ACPI_SIG_SBST "SBST" /* Smart Battery Specification Table */ +#define ACPI_SIG_SDEV "SDEV" /* Secure Devices table */ #define ACPI_SIG_SLIT "SLIT" /* System Locality Distance Information Table */ #define ACPI_SIG_SRAT "SRAT" /* System Resource Affinity Table */ #define ACPI_SIG_NFIT "NFIT" /* NVDIMM Firmware Interface Table */ @@ -1283,7 +1284,7 @@ struct acpi_nfit_flush_address { /******************************************************************************* * - * PDTT - Processor Debug Trigger Table (ACPI 6.2) + * PDTT - Platform Debug Trigger Table (ACPI 6.2) * Version 0 * ******************************************************************************/ @@ -1301,14 +1302,14 @@ struct acpi_table_pdtt { * starting at array_offset. */ struct acpi_pdtt_channel { - u16 sub_channel_id; + u8 subchannel_id; + u8 flags; }; -/* Mask and Flags for above */ +/* Flags for above */ -#define ACPI_PDTT_SUBCHANNEL_ID_MASK 0x00FF -#define ACPI_PDTT_RUNTIME_TRIGGER (1<<8) -#define ACPI_PPTT_WAIT_COMPLETION (1<<9) +#define ACPI_PDTT_RUNTIME_TRIGGER (1) +#define ACPI_PPTT_WAIT_COMPLETION (1<<1) /******************************************************************************* * @@ -1403,6 +1404,68 @@ struct acpi_table_sbst { u32 critical_level; }; +/******************************************************************************* + * + * SDEV - Secure Devices Table (ACPI 6.2) + * Version 1 + * + ******************************************************************************/ + +struct acpi_table_sdev { + struct acpi_table_header header; /* Common ACPI table header */ +}; + +struct acpi_sdev_header { + u8 type; + u8 flags; + u16 length; +}; + +/* Values for subtable type above */ + +enum acpi_sdev_type { + ACPI_SDEV_TYPE_NAMESPACE_DEVICE = 0, + ACPI_SDEV_TYPE_PCIE_ENDPOINT_DEVICE = 1, + ACPI_SDEV_TYPE_RESERVED = 2 /* 2 and greater are reserved */ +}; + +/* Values for flags above */ + +#define ACPI_SDEV_HANDOFF_TO_UNSECURE_OS (1) + +/* + * SDEV subtables + */ + +/* 0: Namespace Device Based Secure Device Structure */ + +struct acpi_sdev_namespace { + struct acpi_sdev_header header; + u16 device_id_offset; + u16 device_id_length; + u16 vendor_data_offset; + u16 vendor_data_length; +}; + +/* 1: PCIe Endpoint Device Based Device Structure */ + +struct acpi_sdev_pcie { + struct acpi_sdev_header header; + u16 segment; + u16 start_bus; + u16 path_offset; + u16 path_length; + u16 vendor_data_offset; + u16 vendor_data_length; +}; + +/* 1a: PCIe Endpoint path entry */ + +struct acpi_sdev_pcie_path { + u8 device; + u8 function; +}; + /******************************************************************************* * * SLIT - System Locality Distance Information Table diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 686b6f8c09dc..2623f9d72e46 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -1246,6 +1246,8 @@ enum acpi_spmi_interface_types { * TCPA - Trusted Computing Platform Alliance table * Version 2 * + * TCG Hardware Interface Table for TPM 1.2 Clients and Servers + * * Conforms to "TCG ACPI Specification, Family 1.2 and 2.0", * Version 1.2, Revision 8 * February 27, 2017 @@ -1310,6 +1312,8 @@ struct acpi_table_tcpa_server { * TPM2 - Trusted Platform Module (TPM) 2.0 Hardware Interface Table * Version 4 * + * TCG Hardware Interface Table for TPM 2.0 Clients and Servers + * * Conforms to "TCG ACPI Specification, Family 1.2 and 2.0", * Version 1.2, Revision 8 * February 27, 2017 @@ -1329,15 +1333,23 @@ struct acpi_table_tpm2 { /* Values for start_method above */ #define ACPI_TPM2_NOT_ALLOWED 0 +#define ACPI_TPM2_RESERVED1 1 #define ACPI_TPM2_START_METHOD 2 +#define ACPI_TPM2_RESERVED3 3 +#define ACPI_TPM2_RESERVED4 4 +#define ACPI_TPM2_RESERVED5 5 #define ACPI_TPM2_MEMORY_MAPPED 6 #define ACPI_TPM2_COMMAND_BUFFER 7 #define ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD 8 +#define ACPI_TPM2_RESERVED9 9 +#define ACPI_TPM2_RESERVED10 10 #define ACPI_TPM2_COMMAND_BUFFER_WITH_ARM_SMC 11 /* V1.2 Rev 8 */ +#define ACPI_TPM2_RESERVED 12 -/* Trailer appears after any start_method subtables */ +/* Optional trailer appears after any start_method subtables */ struct acpi_tpm2_trailer { + u8 method_parameters[12]; u32 minimum_log_length; /* Minimum length for the event log area */ u64 log_address; /* Address of the event log area */ }; -- cgit v1.2.3 From 8ca86e82b9f6a98d5f5606ee9cb9ed3ae08c1529 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:40:24 -0800 Subject: ACPICA: Update version to 20170929 ACPICA commit 2399a7799d6e41ec5beca77ddff3acc77e1a4e0a Version 20170929 Link: https://github.com/acpica/acpica/commit/2399a779 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index 1a4322db0274..f25668cce946 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -46,7 +46,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20170831 +#define ACPI_CA_VERSION 0x20170929 #include #include -- cgit v1.2.3 From 4c106aa411ee7c1919589f283a4f17888dfee387 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Fri, 17 Nov 2017 15:42:19 -0800 Subject: ACPICA: iasl: Add SMMUv3 device ID mapping index support ACPICA commit 5c371879e035122c5807752f42247fd091d107d6 SMMUv3 device ID mapping index is used for SMMUv3 MSI which is introduced in IORT spec revision c, add its support for iasl. Tested with iasl -t IORT then get the right SMMUv3 node in iort.asl. Link: https://github.com/acpica/acpica/commit/5c371879 Signed-off-by: Hanjun Guo Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index 2623f9d72e46..0d60d5df14f8 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -810,6 +810,7 @@ struct acpi_iort_smmu_v3 { u8 pxm; u8 reserved1; u16 reserved2; + u32 id_mapping_index; }; /* Values for Model field above */ -- cgit v1.2.3 From 4b9b1de798b668c02942792e2b3be8587c04c030 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 17 Nov 2017 15:42:21 -0800 Subject: ACPICA: Trivial fix to spelling mistake in comment ACPICA commit 62c3ff46de977456155fdedbd9f294f2ff700520 Fix spelling mistake, "Reseved" -> "Reserved" Link: https://github.com/acpica/acpica/commit/62c3ff46 Signed-off-by: Colin Ian King Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index ea0c71ece407..5ef905626c6d 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1163,7 +1163,7 @@ struct acpi_nfit_system_address { struct acpi_nfit_header header; u16 range_index; u16 flags; - u32 reserved; /* Reseved, must be zero */ + u32 reserved; /* Reserved, must be zero */ u32 proximity_domain; u8 range_guid[16]; u64 address; -- cgit v1.2.3 From 5ed4e5ca51cad5ddae09f59a95626731d1546244 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:42:24 -0800 Subject: ACPICA: ACPI 6.0A: Changes to the NFIT ACPI table ACPICA commit a42a086b8d682ab8dfbc4666cf6b9c8a5ee23a77 Adds a new subtable. Link: https://github.com/acpica/acpica/commit/a42a086b Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 65 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 5ef905626c6d..867f4136dbac 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1150,7 +1150,8 @@ enum acpi_nfit_type { ACPI_NFIT_TYPE_CONTROL_REGION = 4, ACPI_NFIT_TYPE_DATA_REGION = 5, ACPI_NFIT_TYPE_FLUSH_ADDRESS = 6, - ACPI_NFIT_TYPE_RESERVED = 7 /* 7 and greater are reserved */ + ACPI_NFIT_TYPE_CAPABILITIES = 7, + ACPI_NFIT_TYPE_RESERVED = 8 /* 8 and greater are reserved */ }; /* @@ -1282,6 +1283,69 @@ struct acpi_nfit_flush_address { u64 hint_address[1]; /* Variable length */ }; +/* 7: Platform Capabilities Structure */ + +struct acpi_nfit_capabilities { + struct acpi_nfit_header header; + u8 highest_capability; + u8 reserved[3]; /* Reserved, must be zero */ + u32 capabilities; + u32 reserved2; +}; + +/* Capabilities Flags */ + +#define ACPI_NFIT_CAPABILITY_CACHE_FLUSH (1) /* 00: Cache Flush to NVDIMM capable */ +#define ACPI_NFIT_CAPABILITY_MEM_FLUSH (1<<1) /* 01: Memory Flush to NVDIMM capable */ +#define ACPI_NFIT_CAPABILITY_MEM_MIRRORING (1<<2) /* 02: Memory Mirroring capable */ + +/* + * NFIT/DVDIMM device handle support - used as the _ADR for each NVDIMM + */ +struct nfit_device_handle { + u32 handle; +}; + +/* Device handle construction and extraction macros */ + +#define ACPI_NFIT_DIMM_NUMBER_MASK 0x0000000F +#define ACPI_NFIT_CHANNEL_NUMBER_MASK 0x000000F0 +#define ACPI_NFIT_MEMORY_ID_MASK 0x00000F00 +#define ACPI_NFIT_SOCKET_ID_MASK 0x0000F000 +#define ACPI_NFIT_NODE_ID_MASK 0x0FFF0000 + +#define ACPI_NFIT_DIMM_NUMBER_OFFSET 0 +#define ACPI_NFIT_CHANNEL_NUMBER_OFFSET 4 +#define ACPI_NFIT_MEMORY_ID_OFFSET 8 +#define ACPI_NFIT_SOCKET_ID_OFFSET 12 +#define ACPI_NFIT_NODE_ID_OFFSET 16 + +/* Macro to construct a NFIT/NVDIMM device handle */ + +#define ACPI_NFIT_BUILD_DEVICE_HANDLE(dimm, channel, memory, socket, node) \ + ((dimm) | \ + ((channel) << ACPI_NFIT_CHANNEL_NUMBER_OFFSET) | \ + ((memory) << ACPI_NFIT_MEMORY_ID_OFFSET) | \ + ((socket) << ACPI_NFIT_SOCKET_ID_OFFSET) | \ + ((node) << ACPI_NFIT_NODE_ID_OFFSET)) + +/* Macros to extract individual fields from a NFIT/NVDIMM device handle */ + +#define ACPI_NFIT_GET_DIMM_NUMBER(handle) \ + ((handle) & ACPI_NFIT_DIMM_NUMBER_MASK) + +#define ACPI_NFIT_GET_CHANNEL_NUMBER(handle) \ + (((handle) & ACPI_NFIT_CHANNEL_NUMBER_MASK) >> ACPI_NFIT_CHANNEL_NUMBER_OFFSET) + +#define ACPI_NFIT_GET_MEMORY_ID(handle) \ + (((handle) & ACPI_NFIT_MEMORY_ID_MASK) >> ACPI_NFIT_MEMORY_ID_OFFSET) + +#define ACPI_NFIT_GET_SOCKET_ID(handle) \ + (((handle) & ACPI_NFIT_SOCKET_ID_MASK) >> ACPI_NFIT_SOCKET_ID_OFFSET) + +#define ACPI_NFIT_GET_NODE_ID(handle) \ + (((handle) & ACPI_NFIT_NODE_ID_MASK) >> ACPI_NFIT_NODE_ID_OFFSET) + /******************************************************************************* * * PDTT - Platform Debug Trigger Table (ACPI 6.2) -- cgit v1.2.3 From d41bf52e38e47ce4990857a5ffdfd7910307619a Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:42:25 -0800 Subject: ACPICA: Small typo fix, no functional change ACPICA commit 9b03c05305d856274c39f3adbddd8a98ef5d018e ACPI table header. Link: https://github.com/acpica/acpica/commit/9b03c053 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 867f4136dbac..178661f1b896 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1373,7 +1373,7 @@ struct acpi_pdtt_channel { /* Flags for above */ #define ACPI_PDTT_RUNTIME_TRIGGER (1) -#define ACPI_PPTT_WAIT_COMPLETION (1<<1) +#define ACPI_PDTT_WAIT_COMPLETION (1<<1) /******************************************************************************* * -- cgit v1.2.3 From e3860b5ecff12770a45bd11c8d4fb8ac0fffcce1 Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Fri, 17 Nov 2017 15:42:29 -0800 Subject: ACPICA: ACPI 6.2: Additional PPTT flags ACPICA commit fba3ae99b2bc514ca34f0d7b2609c2a043582784 The ACPI 6.2 spec has flags to describe cache allocation, write back, and whether it is an instruction, data or unified cache. Link: https://github.com/acpica/acpica/commit/fba3ae99 Signed-off-by: Jeremy Linton Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/actbl1.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include') diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h index 178661f1b896..4c304bf4d591 100644 --- a/include/acpi/actbl1.h +++ b/include/acpi/actbl1.h @@ -1441,6 +1441,20 @@ struct acpi_pptt_cache { #define ACPI_PPTT_MASK_CACHE_TYPE (0x0C) /* Cache type */ #define ACPI_PPTT_MASK_WRITE_POLICY (0x10) /* Write policy */ +/* Attributes describing cache */ +#define ACPI_PPTT_CACHE_READ_ALLOCATE (0x0) /* Cache line is allocated on read */ +#define ACPI_PPTT_CACHE_WRITE_ALLOCATE (0x01) /* Cache line is allocated on write */ +#define ACPI_PPTT_CACHE_RW_ALLOCATE (0x02) /* Cache line is allocated on read and write */ +#define ACPI_PPTT_CACHE_RW_ALLOCATE_ALT (0x03) /* Alternate representation of above */ + +#define ACPI_PPTT_CACHE_TYPE_DATA (0x0) /* Data cache */ +#define ACPI_PPTT_CACHE_TYPE_INSTR (1<<2) /* Instruction cache */ +#define ACPI_PPTT_CACHE_TYPE_UNIFIED (2<<2) /* Unified I & D cache */ +#define ACPI_PPTT_CACHE_TYPE_UNIFIED_ALT (3<<2) /* Alternate representation of above */ + +#define ACPI_PPTT_CACHE_POLICY_WB (0x0) /* Cache is write back */ +#define ACPI_PPTT_CACHE_POLICY_WT (1<<4) /* Cache is write through */ + /* 2: ID Structure */ struct acpi_pptt_id { -- cgit v1.2.3 From fb969d160cac2074f8eeefdc073e4797885839e7 Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Fri, 17 Nov 2017 15:42:30 -0800 Subject: ACPICA: Update version to 20171110 ACPICA commit d0ef5a72ca7c01acbf590e4556d19edf69a5b5c4 Version 20171110. Link: https://github.com/acpica/acpica/commit/d0ef5a72 Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index f25668cce946..e02610adc07d 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -46,7 +46,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20170929 +#define ACPI_CA_VERSION 0x20171110 #include #include -- cgit v1.2.3 From 4c82fd0abb87e20d0d68ef5237e74732352806c8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Dec 2017 12:08:33 +0100 Subject: netfilter: uapi: correct UNTRACKED conntrack state bit number nft_ct exposes this bit to userspace. This used to be #define NF_CT_STATE_UNTRACKED_BIT (1 << (IP_CT_NUMBER + 1)) (IP_CT_NUMBER is 5, so this was 0x40) .. but this got changed to 8 (0x100) when the untracked object got removed. Replace this with a literal 6 to prevent further incompatible changes in case IP_CT_NUMBER ever increases. Fixes: cc41c84b7e7f2 ("netfilter: kill the fake untracked conntrack objects") Reported-by: Li Shuang Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 3fea7709a441..57ccfb32e87f 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -36,7 +36,7 @@ enum ip_conntrack_info { #define NF_CT_STATE_INVALID_BIT (1 << 0) #define NF_CT_STATE_BIT(ctinfo) (1 << ((ctinfo) % IP_CT_IS_REPLY + 1)) -#define NF_CT_STATE_UNTRACKED_BIT (1 << (IP_CT_UNTRACKED + 1)) +#define NF_CT_STATE_UNTRACKED_BIT (1 << 6) /* Bitset representing status of connection. */ enum ip_conntrack_status { -- cgit v1.2.3 From af955bf15d2c27496b0269b1f05c26f758c68314 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Tue, 19 Dec 2017 10:27:24 +0000 Subject: crypto: af_alg - Fix race around ctx->rcvused by making it atomic_t This variable was increased and decreased without any protection. Result was an occasional misscount and negative wrap around resulting in false resource allocation failures. Fixes: 7d2c3f54e6f6 ("crypto: af_alg - remove locking in async callback") Signed-off-by: Jonathan Cameron Reviewed-by: Stephan Mueller Signed-off-by: Herbert Xu --- crypto/af_alg.c | 4 ++-- crypto/algif_aead.c | 2 +- crypto/algif_skcipher.c | 2 +- include/crypto/if_alg.h | 5 +++-- 4 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/crypto/af_alg.c b/crypto/af_alg.c index f1a2caf1b59b..d3f1c431724b 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -664,7 +664,7 @@ void af_alg_free_areq_sgls(struct af_alg_async_req *areq) unsigned int i; list_for_each_entry_safe(rsgl, tmp, &areq->rsgl_list, list) { - ctx->rcvused -= rsgl->sg_num_bytes; + atomic_sub(rsgl->sg_num_bytes, &ctx->rcvused); af_alg_free_sg(&rsgl->sgl); list_del(&rsgl->list); if (rsgl != &areq->first_rsgl) @@ -1162,7 +1162,7 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, areq->last_rsgl = rsgl; len += err; - ctx->rcvused += err; + atomic_add(err, &ctx->rcvused); rsgl->sg_num_bytes = err; iov_iter_advance(&msg->msg_iter, err); } diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index b73db2b27656..20df8c1b6851 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -571,7 +571,7 @@ static int aead_accept_parent_nokey(void *private, struct sock *sk) INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; ctx->used = 0; - ctx->rcvused = 0; + atomic_set(&ctx->rcvused, 0); ctx->more = 0; ctx->merge = 0; ctx->enc = 0; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index baef9bfccdda..c5c47b680152 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -390,7 +390,7 @@ static int skcipher_accept_parent_nokey(void *private, struct sock *sk) INIT_LIST_HEAD(&ctx->tsgl_list); ctx->len = len; ctx->used = 0; - ctx->rcvused = 0; + atomic_set(&ctx->rcvused, 0); ctx->more = 0; ctx->merge = 0; ctx->enc = 0; diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 38d9c5861ed8..f38227a78eae 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -150,7 +151,7 @@ struct af_alg_ctx { struct crypto_wait wait; size_t used; - size_t rcvused; + atomic_t rcvused; bool more; bool merge; @@ -215,7 +216,7 @@ static inline int af_alg_rcvbuf(struct sock *sk) struct af_alg_ctx *ctx = ask->private; return max_t(int, max_t(int, sk->sk_rcvbuf & PAGE_MASK, PAGE_SIZE) - - ctx->rcvused, 0); + atomic_read(&ctx->rcvused), 0); } /** -- cgit v1.2.3 From 98801506552593c9b8ac11021b0cdad12cab4f6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 2 Jan 2018 10:02:19 +0000 Subject: fscache: Fix the default for fscache_maybe_release_page() Fix the default for fscache_maybe_release_page() for when the cookie isn't valid or the page isn't cached. It mustn't return false as that indicates the page cannot yet be freed. The problem with the default is that if, say, there's no cache, but a network filesystem's pages are using up almost all the available memory, a system can OOM because the filesystem ->releasepage() op will not allow them to be released as fscache_maybe_release_page() incorrectly prevents it. This can be tested by writing a sequence of 512MiB files to an AFS mount. It does not affect NFS or CIFS because both of those wrap the call in a check of PG_fscache and it shouldn't bother Ceph as that only has PG_private set whilst writeback is in progress. This might be an issue for 9P, however. Note that the pages aren't entirely stuck. Removing a file or unmounting will clear things because that uses ->invalidatepage() instead. Fixes: 201a15428bd5 ("FS-Cache: Handle pages pending storage that get evicted under OOM conditions") Reported-by: Marc Dionne Signed-off-by: David Howells Reviewed-by: Jeff Layton Acked-by: Al Viro Tested-by: Marc Dionne cc: stable@vger.kernel.org # 2.6.32+ --- include/linux/fscache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index f4ff47d4a893..fe0c349684fa 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -755,7 +755,7 @@ bool fscache_maybe_release_page(struct fscache_cookie *cookie, { if (fscache_cookie_valid(cookie) && PageFsCache(page)) return __fscache_maybe_release_page(cookie, page, gfp); - return false; + return true; } /** -- cgit v1.2.3 From f24c4d478013d82bd1b943df566fff3561d52864 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 2 Jan 2018 17:21:10 +0000 Subject: efi/capsule-loader: Reinstate virtual capsule mapping Commit: 82c3768b8d68 ("efi/capsule-loader: Use a cached copy of the capsule header") ... refactored the capsule loading code that maps the capsule header, to avoid having to map it several times. However, as it turns out, the vmap() call we ended up removing did not just map the header, but the entire capsule image, and dropping this virtual mapping breaks capsules that are processed by the firmware immediately (i.e., without a reboot). Unfortunately, that change was part of a larger refactor that allowed a quirk to be implemented for Quark, which has a non-standard memory layout for capsules, and we have slightly painted ourselves into a corner by allowing quirk code to mangle the capsule header and memory layout. So we need to fix this without breaking Quark. Fortunately, Quark does not appear to care about the virtual mapping, and so we can simply do a partial revert of commit: 2a457fb31df6 ("efi/capsule-loader: Use page addresses rather than struct page pointers") ... and create a vmap() mapping of the entire capsule (including header) based on the reinstated struct page array, unless running on Quark, in which case we pass the capsule header copy as before. Reported-by: Ge Song Tested-by: Bryan O'Donoghue Tested-by: Ge Song Signed-off-by: Ard Biesheuvel Cc: Cc: Dave Young Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Fixes: 82c3768b8d68 ("efi/capsule-loader: Use a cached copy of the capsule header") Link: http://lkml.kernel.org/r/20180102172110.17018-3-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- arch/x86/platform/efi/quirks.c | 13 +++++++++- drivers/firmware/efi/capsule-loader.c | 45 ++++++++++++++++++++++++++++------- include/linux/efi.h | 4 +++- 3 files changed, 52 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 8a99a2e96537..5b513ccffde4 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -592,7 +592,18 @@ static int qrk_capsule_setup_info(struct capsule_info *cap_info, void **pkbuff, /* * Update the first page pointer to skip over the CSH header. */ - cap_info->pages[0] += csh->headersize; + cap_info->phys[0] += csh->headersize; + + /* + * cap_info->capsule should point at a virtual mapping of the entire + * capsule, starting at the capsule header. Our image has the Quark + * security header prepended, so we cannot rely on the default vmap() + * mapping created by the generic capsule code. + * Given that the Quark firmware does not appear to care about the + * virtual mapping, let's just point cap_info->capsule at our copy + * of the capsule header. + */ + cap_info->capsule = &cap_info->header; return 1; } diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index ec8ac5c4dd84..055e2e8f985a 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -20,10 +20,6 @@ #define NO_FURTHER_WRITE_ACTION -1 -#ifndef phys_to_page -#define phys_to_page(x) pfn_to_page((x) >> PAGE_SHIFT) -#endif - /** * efi_free_all_buff_pages - free all previous allocated buffer pages * @cap_info: pointer to current instance of capsule_info structure @@ -35,7 +31,7 @@ static void efi_free_all_buff_pages(struct capsule_info *cap_info) { while (cap_info->index > 0) - __free_page(phys_to_page(cap_info->pages[--cap_info->index])); + __free_page(cap_info->pages[--cap_info->index]); cap_info->index = NO_FURTHER_WRITE_ACTION; } @@ -71,6 +67,14 @@ int __efi_capsule_setup_info(struct capsule_info *cap_info) cap_info->pages = temp_page; + temp_page = krealloc(cap_info->phys, + pages_needed * sizeof(phys_addr_t *), + GFP_KERNEL | __GFP_ZERO); + if (!temp_page) + return -ENOMEM; + + cap_info->phys = temp_page; + return 0; } @@ -105,9 +109,24 @@ int __weak efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, **/ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) { + bool do_vunmap = false; int ret; - ret = efi_capsule_update(&cap_info->header, cap_info->pages); + /* + * cap_info->capsule may have been assigned already by a quirk + * handler, so only overwrite it if it is NULL + */ + if (!cap_info->capsule) { + cap_info->capsule = vmap(cap_info->pages, cap_info->index, + VM_MAP, PAGE_KERNEL); + if (!cap_info->capsule) + return -ENOMEM; + do_vunmap = true; + } + + ret = efi_capsule_update(cap_info->capsule, cap_info->phys); + if (do_vunmap) + vunmap(cap_info->capsule); if (ret) { pr_err("capsule update failed\n"); return ret; @@ -165,10 +184,12 @@ static ssize_t efi_capsule_write(struct file *file, const char __user *buff, goto failed; } - cap_info->pages[cap_info->index++] = page_to_phys(page); + cap_info->pages[cap_info->index] = page; + cap_info->phys[cap_info->index] = page_to_phys(page); cap_info->page_bytes_remain = PAGE_SIZE; + cap_info->index++; } else { - page = phys_to_page(cap_info->pages[cap_info->index - 1]); + page = cap_info->pages[cap_info->index - 1]; } kbuff = kmap(page); @@ -252,6 +273,7 @@ static int efi_capsule_release(struct inode *inode, struct file *file) struct capsule_info *cap_info = file->private_data; kfree(cap_info->pages); + kfree(cap_info->phys); kfree(file->private_data); file->private_data = NULL; return 0; @@ -281,6 +303,13 @@ static int efi_capsule_open(struct inode *inode, struct file *file) return -ENOMEM; } + cap_info->phys = kzalloc(sizeof(void *), GFP_KERNEL); + if (!cap_info->phys) { + kfree(cap_info->pages); + kfree(cap_info); + return -ENOMEM; + } + file->private_data = cap_info; return 0; diff --git a/include/linux/efi.h b/include/linux/efi.h index d813f7b04da7..29fdf8029cf6 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -140,11 +140,13 @@ struct efi_boot_memmap { struct capsule_info { efi_capsule_header_t header; + efi_capsule_header_t *capsule; int reset_type; long index; size_t count; size_t total_size; - phys_addr_t *pages; + struct page **pages; + phys_addr_t *phys; size_t page_bytes_remain; }; -- cgit v1.2.3 From c0bace798436bca0fdc221ff61143f1376a9c3de Mon Sep 17 00:00:00 2001 From: Felix Janda Date: Mon, 1 Jan 2018 19:33:20 +0100 Subject: uapi libc compat: add fallback for unsupported libcs libc-compat.h aims to prevent symbol collisions between uapi and libc headers for each supported libc. This requires continuous coordination between them. The goal of this commit is to improve the situation for libcs (such as musl) which are not yet supported and/or do not wish to be explicitly supported, while not affecting supported libcs. More precisely, with this commit, unsupported libcs can request the suppression of any specific uapi definition by defining the correspondings _UAPI_DEF_* macro as 0. This can fix symbol collisions for them, as long as the libc headers are included before the uapi headers. Inclusion in the other order is outside the scope of this commit. All infrastructure in order to enable this fallback for unsupported libcs is already in place, except that libc-compat.h unconditionally defines all _UAPI_DEF_* macros to 1 for all unsupported libcs so that any previous definitions are ignored. In order to fix this, this commit merely makes these definitions conditional. This commit together with the musl libc commit http://git.musl-libc.org/cgit/musl/commit/?id=04983f2272382af92eb8f8838964ff944fbb8258 fixes for example the following compiler errors when is included after musl's : ./linux/in6.h:32:8: error: redefinition of 'struct in6_addr' ./linux/in6.h:49:8: error: redefinition of 'struct sockaddr_in6' ./linux/in6.h:59:8: error: redefinition of 'struct ipv6_mreq' The comments referencing glibc are still correct, but this file is not only used for glibc any more. Signed-off-by: Felix Janda Reviewed-by: Hauke Mehrtens Signed-off-by: David S. Miller --- include/uapi/linux/libc-compat.h | 55 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 54 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index 282875cf8056..8254c937c9f4 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -168,46 +168,99 @@ /* If we did not see any headers from any supported C libraries, * or we are being included in the kernel, then define everything - * that we need. */ + * that we need. Check for previous __UAPI_* definitions to give + * unsupported C libraries a way to opt out of any kernel definition. */ #else /* !defined(__GLIBC__) */ /* Definitions for if.h */ +#ifndef __UAPI_DEF_IF_IFCONF #define __UAPI_DEF_IF_IFCONF 1 +#endif +#ifndef __UAPI_DEF_IF_IFMAP #define __UAPI_DEF_IF_IFMAP 1 +#endif +#ifndef __UAPI_DEF_IF_IFNAMSIZ #define __UAPI_DEF_IF_IFNAMSIZ 1 +#endif +#ifndef __UAPI_DEF_IF_IFREQ #define __UAPI_DEF_IF_IFREQ 1 +#endif /* Everything up to IFF_DYNAMIC, matches net/if.h until glibc 2.23 */ +#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS #define __UAPI_DEF_IF_NET_DEVICE_FLAGS 1 +#endif /* For the future if glibc adds IFF_LOWER_UP, IFF_DORMANT and IFF_ECHO */ +#ifndef __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO #define __UAPI_DEF_IF_NET_DEVICE_FLAGS_LOWER_UP_DORMANT_ECHO 1 +#endif /* Definitions for in.h */ +#ifndef __UAPI_DEF_IN_ADDR #define __UAPI_DEF_IN_ADDR 1 +#endif +#ifndef __UAPI_DEF_IN_IPPROTO #define __UAPI_DEF_IN_IPPROTO 1 +#endif +#ifndef __UAPI_DEF_IN_PKTINFO #define __UAPI_DEF_IN_PKTINFO 1 +#endif +#ifndef __UAPI_DEF_IP_MREQ #define __UAPI_DEF_IP_MREQ 1 +#endif +#ifndef __UAPI_DEF_SOCKADDR_IN #define __UAPI_DEF_SOCKADDR_IN 1 +#endif +#ifndef __UAPI_DEF_IN_CLASS #define __UAPI_DEF_IN_CLASS 1 +#endif /* Definitions for in6.h */ +#ifndef __UAPI_DEF_IN6_ADDR #define __UAPI_DEF_IN6_ADDR 1 +#endif +#ifndef __UAPI_DEF_IN6_ADDR_ALT #define __UAPI_DEF_IN6_ADDR_ALT 1 +#endif +#ifndef __UAPI_DEF_SOCKADDR_IN6 #define __UAPI_DEF_SOCKADDR_IN6 1 +#endif +#ifndef __UAPI_DEF_IPV6_MREQ #define __UAPI_DEF_IPV6_MREQ 1 +#endif +#ifndef __UAPI_DEF_IPPROTO_V6 #define __UAPI_DEF_IPPROTO_V6 1 +#endif +#ifndef __UAPI_DEF_IPV6_OPTIONS #define __UAPI_DEF_IPV6_OPTIONS 1 +#endif +#ifndef __UAPI_DEF_IN6_PKTINFO #define __UAPI_DEF_IN6_PKTINFO 1 +#endif +#ifndef __UAPI_DEF_IP6_MTUINFO #define __UAPI_DEF_IP6_MTUINFO 1 +#endif /* Definitions for ipx.h */ +#ifndef __UAPI_DEF_SOCKADDR_IPX #define __UAPI_DEF_SOCKADDR_IPX 1 +#endif +#ifndef __UAPI_DEF_IPX_ROUTE_DEFINITION #define __UAPI_DEF_IPX_ROUTE_DEFINITION 1 +#endif +#ifndef __UAPI_DEF_IPX_INTERFACE_DEFINITION #define __UAPI_DEF_IPX_INTERFACE_DEFINITION 1 +#endif +#ifndef __UAPI_DEF_IPX_CONFIG_DATA #define __UAPI_DEF_IPX_CONFIG_DATA 1 +#endif +#ifndef __UAPI_DEF_IPX_ROUTE_DEF #define __UAPI_DEF_IPX_ROUTE_DEF 1 +#endif /* Definitions for xattr.h */ +#ifndef __UAPI_DEF_XATTR #define __UAPI_DEF_XATTR 1 +#endif #endif /* __GLIBC__ */ -- cgit v1.2.3 From f1c8d3720f2e6c8c2b209120678236debd0360e5 Mon Sep 17 00:00:00 2001 From: William Tu Date: Tue, 2 Jan 2018 14:05:19 -0800 Subject: vxlan: trivial indenting fix. Fix indentation of reserved_flags2 field in vxlanhdr_gpe. Fixes: e1e5314de08b ("vxlan: implement GPE") Signed-off-by: William Tu Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/vxlan.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 13223396dc64..f96391e84a8a 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -146,7 +146,7 @@ struct vxlanhdr_gpe { np_applied:1, instance_applied:1, version:2, -reserved_flags2:2; + reserved_flags2:2; #elif defined(__BIG_ENDIAN_BITFIELD) u8 reserved_flags2:2, version:2, -- cgit v1.2.3 From 6926e041a8920c8ec27e4e155efa760aa01551fd Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Wed, 3 Jan 2018 23:14:21 +0100 Subject: uapi/if_ether.h: prevent redefinition of struct ethhdr Musl provides its own ethhdr struct definition. Add a guard to prevent its definition of the appropriate musl header has already been included. glibc does not implement this header, but when glibc will implement this they can just define __UAPI_DEF_ETHHDR 0 to make it work with the kernel. Signed-off-by: Hauke Mehrtens Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 3 +++ include/uapi/linux/libc-compat.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 3ee3bf7c8526..144de4d2f385 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -23,6 +23,7 @@ #define _UAPI_LINUX_IF_ETHER_H #include +#include /* * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble @@ -149,11 +150,13 @@ * This is an Ethernet frame header. */ +#if __UAPI_DEF_ETHHDR struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ unsigned char h_source[ETH_ALEN]; /* source ether addr */ __be16 h_proto; /* packet type ID field */ } __attribute__((packed)); +#endif #endif /* _UAPI_LINUX_IF_ETHER_H */ diff --git a/include/uapi/linux/libc-compat.h b/include/uapi/linux/libc-compat.h index 8254c937c9f4..fc29efaa918c 100644 --- a/include/uapi/linux/libc-compat.h +++ b/include/uapi/linux/libc-compat.h @@ -264,4 +264,10 @@ #endif /* __GLIBC__ */ +/* Definitions for if_ether.h */ +/* allow libcs like musl to deactivate this, glibc does not implement this. */ +#ifndef __UAPI_DEF_ETHHDR +#define __UAPI_DEF_ETHHDR 1 +#endif + #endif /* _UAPI_LIBC_COMPAT_H */ -- cgit v1.2.3 From 87cdece169db3b839316bd8a39e438c8730d657c Mon Sep 17 00:00:00 2001 From: Erik Schmauss Date: Wed, 3 Jan 2018 15:06:27 -0800 Subject: ACPICA: DT compiler: prevent error if optional field at the end of table is not present ACPICA commit a7f73af9003bf4e730db5a133300c01ba7992a01 The data table compiler throws under the following conditions: 1.) there is a table with a last field that is optional 2.) if the optional field is not present 3.) the optional field is the last line of the data table A change was made to dt_compile_table to return an AE_EOF under these conditions. This AE_EOF means that we are at the end of the file. The caller to dt_compile_table() is responsible for handling this case. For DBG2 table, we will complete the compilation of this subtable. For other tables, this could be different. Link: https://github.com/acpica/acpica/commit/a7f73af9 Signed-off-by: Erik Schmauss Signed-off-by: Bob Moore Signed-off-by: Rafael J. Wysocki --- include/acpi/acexcep.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h index e1f9fe47f69e..3c46f0ef5f7a 100644 --- a/include/acpi/acexcep.h +++ b/include/acpi/acexcep.h @@ -130,8 +130,9 @@ struct acpi_exception_info { #define AE_HEX_OVERFLOW EXCEP_ENV (0x0020) #define AE_DECIMAL_OVERFLOW EXCEP_ENV (0x0021) #define AE_OCTAL_OVERFLOW EXCEP_ENV (0x0022) +#define AE_END_OF_TABLE EXCEP_ENV (0x0023) -#define AE_CODE_ENV_MAX 0x0022 +#define AE_CODE_ENV_MAX 0x0023 /* * Programmer exceptions @@ -275,7 +276,8 @@ static const struct acpi_exception_info acpi_gbl_exception_names_env[] = { EXCEP_TXT("AE_DECIMAL_OVERFLOW", "Overflow during ASCII decimal-to-binary conversion"), EXCEP_TXT("AE_OCTAL_OVERFLOW", - "Overflow during ASCII octal-to-binary conversion") + "Overflow during ASCII octal-to-binary conversion"), + EXCEP_TXT("AE_END_OF_TABLE", "Reached the end of table") }; static const struct acpi_exception_info acpi_gbl_exception_names_pgm[] = { -- cgit v1.2.3 From bc4d413a819f9d0764a80a55875a5d7e1f4efed4 Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Wed, 3 Jan 2018 15:06:28 -0800 Subject: ACPICA: Recognize the Windows 10 version 1607 and 1703 OSI strings ACPICA commit 35a4a3ea723b3066f575e63e5f0116f7ce65e713 The public Microsoft document listing recognized OSI strings [1] shows that these two strings were introduced. version 1607 / Anniversary Update / "Redstone 1" version 1703 / Creators Update / "Redstone 2" [1] http://download.microsoft.com/download/7/e/7/7e7662cf-cbea-470b-a97e-ce7ce0d98dc2/winacpi_osi.docx Link: https://github.com/acpica/acpica/commit/35a4a3ea Signed-off-by: Mario Limonciello Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- drivers/acpi/acpica/utosi.c | 2 ++ include/acpi/actypes.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include') diff --git a/drivers/acpi/acpica/utosi.c b/drivers/acpi/acpica/utosi.c index 3175b133c0e4..f6b8dd24b006 100644 --- a/drivers/acpi/acpica/utosi.c +++ b/drivers/acpi/acpica/utosi.c @@ -101,6 +101,8 @@ static struct acpi_interface_info acpi_default_supported_interfaces[] = { {"Windows 2012", NULL, 0, ACPI_OSI_WIN_8}, /* Windows 8 and Server 2012 - Added 08/2012 */ {"Windows 2013", NULL, 0, ACPI_OSI_WIN_8}, /* Windows 8.1 and Server 2012 R2 - Added 01/2014 */ {"Windows 2015", NULL, 0, ACPI_OSI_WIN_10}, /* Windows 10 - Added 03/2015 */ + {"Windows 2016", NULL, 0, ACPI_OSI_WIN_10_RS1}, /* Windows 10 version 1607 - Added 12/2017 */ + {"Windows 2017", NULL, 0, ACPI_OSI_WIN_10_RS2}, /* Windows 10 version 1703 - Added 12/2017 */ /* Feature Group Strings */ diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h index ddde2790a54a..31f1be74dd16 100644 --- a/include/acpi/actypes.h +++ b/include/acpi/actypes.h @@ -1301,6 +1301,8 @@ typedef enum { #define ACPI_OSI_WIN_7 0x0B #define ACPI_OSI_WIN_8 0x0C #define ACPI_OSI_WIN_10 0x0D +#define ACPI_OSI_WIN_10_RS1 0x0E +#define ACPI_OSI_WIN_10_RS2 0x0F /* Definitions of getopt */ -- cgit v1.2.3 From 3bd93bd76ba6b5588a1b2b9f4f451952c7d8994d Mon Sep 17 00:00:00 2001 From: Bob Moore Date: Wed, 3 Jan 2018 15:06:31 -0800 Subject: ACPICA: Update version to 20171215 ACPICA commit 8b38d88e4a7151a7fc9451ac2e51c945c60b913b Version 20171215. Link: https://github.com/acpica/acpica/commit/8b38d88e Signed-off-by: Bob Moore Signed-off-by: Erik Schmauss Signed-off-by: Rafael J. Wysocki --- include/acpi/acpixf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h index e02610adc07d..c589c3e12d90 100644 --- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -46,7 +46,7 @@ /* Current ACPICA subsystem version in YYYYMMDD format */ -#define ACPI_CA_VERSION 0x20171110 +#define ACPI_CA_VERSION 0x20171215 #include #include -- cgit v1.2.3 From 040ee69226f8a96b7943645d68f41d5d44b5ff7d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 2 Dec 2017 20:20:38 -0500 Subject: fix "netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'" Descriptor table is a shared object; it's not a place where you can stick temporary references to files, especially when we don't need an opened file at all. Cc: stable@vger.kernel.org # v4.14 Fixes: 98589a0998b8 ("netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'") Signed-off-by: Al Viro --- include/linux/bpf.h | 10 ++++++++++ kernel/bpf/inode.c | 40 +++++++++++++++++++++++++++++++++++++++- kernel/bpf/syscall.c | 2 +- net/netfilter/xt_bpf.c | 14 ++------------ 4 files changed, 52 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e55e4255a210..b63a592ad29d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -419,6 +419,8 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) attr->numa_node : NUMA_NO_NODE; } +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -506,6 +508,12 @@ static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, { return 0; } + +static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, + enum bpf_prog_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -514,6 +522,8 @@ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, return bpf_prog_get_type_dev(ufd, type, false); } +bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); + int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 01aaef1a77c5..5bb5e49ef4c3 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -368,7 +368,45 @@ out: putname(pname); return ret; } -EXPORT_SYMBOL_GPL(bpf_obj_get_user); + +static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + int ret = inode_permission(inode, MAY_READ | MAY_WRITE); + if (ret) + return ERR_PTR(ret); + + if (inode->i_op == &bpf_map_iops) + return ERR_PTR(-EINVAL); + if (inode->i_op != &bpf_prog_iops) + return ERR_PTR(-EACCES); + + prog = inode->i_private; + + ret = security_bpf_prog(prog); + if (ret < 0) + return ERR_PTR(ret); + + if (!bpf_prog_get_ok(prog, &type, false)) + return ERR_PTR(-EINVAL); + + return bpf_prog_inc(prog); +} + +struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) +{ + struct bpf_prog *prog; + struct path path; + int ret = kern_path(name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); + prog = __get_prog_inode(d_backing_inode(path.dentry), type); + if (!IS_ERR(prog)) + touch_atime(&path); + path_put(&path); + return prog; +} +EXPORT_SYMBOL(bpf_prog_get_type_path); static void bpf_evict_inode(struct inode *inode) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2c4cfeaa8d5e..5cb783fc8224 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1057,7 +1057,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); -static bool bpf_prog_get_ok(struct bpf_prog *prog, +bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 041da0d9c06f..fa2ca0a13619 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -52,18 +52,8 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) { - mm_segment_t oldfs = get_fs(); - int retval, fd; - - set_fs(KERNEL_DS); - fd = bpf_obj_get_user(path, 0); - set_fs(oldfs); - if (fd < 0) - return fd; - - retval = __bpf_mt_check_fd(fd, ret); - sys_close(fd); - return retval; + *ret = bpf_prog_get_type_path(path, BPF_PROG_TYPE_SOCKET_FILTER); + return PTR_ERR_OR_ZERO(*ret); } static int bpf_mt_check(const struct xt_mtchk_param *par) -- cgit v1.2.3 From 5133550296d43236439494aa955bfb765a89f615 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Thu, 4 Jan 2018 21:06:49 +0300 Subject: sh_eth: fix SH7757 GEther initialization Renesas SH7757 has 2 Fast and 2 Gigabit Ether controllers, while the 'sh_eth' driver can only reset and initialize TSU of the first controller pair. Shimoda-san tried to solve that adding the 'needs_init' member to the 'struct sh_eth_plat_data', however the platform code still never sets this flag. I think that we can infer this information from the 'devno' variable (set to 'platform_device::id') and reset/init the Ether controller pair only for an even 'devno'; therefore 'sh_eth_plat_data::needs_init' can be removed... Fixes: 150647fb2c31 ("net: sh_eth: change the condition of initialization") Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/sh_eth.c | 4 ++-- include/linux/sh_eth.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 1bdd67a8a869..f21c1db91c3f 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3254,8 +3254,8 @@ static int sh_eth_drv_probe(struct platform_device *pdev) ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER; } - /* initialize first or needed device */ - if (!devno || pd->needs_init) { + /* Need to init only the first port of the two sharing a TSU */ + if (devno % 2 == 0) { if (mdp->cd->chip_reset) mdp->cd->chip_reset(ndev); diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index ff3642d267f7..94081e9a5010 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -17,7 +17,6 @@ struct sh_eth_plat_data { unsigned char mac_addr[ETH_ALEN]; unsigned no_ether_link:1; unsigned ether_link_active_low:1; - unsigned needs_init:1; }; #endif -- cgit v1.2.3 From 87590ce6e373d1a5401f6539f0c59ef92dd924a9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 7 Jan 2018 22:48:00 +0100 Subject: sysfs/cpu: Add vulnerability folder As the meltdown/spectre problem affects several CPU architectures, it makes sense to have common way to express whether a system is affected by a particular vulnerability or not. If affected the way to express the mitigation should be common as well. Create /sys/devices/system/cpu/vulnerabilities folder and files for meltdown, spectre_v1 and spectre_v2. Allow architectures to override the show function. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Konrad Rzeszutek Wilk Cc: Peter Zijlstra Cc: Will Deacon Cc: Dave Hansen Cc: Linus Torvalds Cc: Borislav Petkov Cc: David Woodhouse Link: https://lkml.kernel.org/r/20180107214913.096657732@linutronix.de --- Documentation/ABI/testing/sysfs-devices-system-cpu | 16 ++++++++ drivers/base/Kconfig | 3 ++ drivers/base/cpu.c | 48 ++++++++++++++++++++++ include/linux/cpu.h | 7 ++++ 4 files changed, 74 insertions(+) (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index f3d5817c4ef0..bd3a88e16d8b 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -373,3 +373,19 @@ Contact: Linux kernel mailing list Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpu#. + +What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 +Date: Januar 2018 +Contact: Linux kernel mailing list +Description: Information about CPU vulnerabilities + + The files are named after the code names of CPU + vulnerabilities. The output of those files reflects the + state of the CPUs in the system. Possible output values: + + "Not affected" CPU is not affected by the vulnerability + "Vulnerable" CPU is affected and no mitigation in effect + "Mitigation: $M" CPU is affetcted and mitigation $M is in effect diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 2f6614c9a229..37a71fd9043f 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -235,6 +235,9 @@ config GENERIC_CPU_DEVICES config GENERIC_CPU_AUTOPROBE bool +config GENERIC_CPU_VULNERABILITIES + bool + config SOC_BUS bool select GLOB diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 321cd7b4d817..825964efda1d 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -501,10 +501,58 @@ static void __init cpu_dev_register_generic(void) #endif } +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES + +ssize_t __weak cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); +static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); +static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); + +static struct attribute *cpu_root_vulnerabilities_attrs[] = { + &dev_attr_meltdown.attr, + &dev_attr_spectre_v1.attr, + &dev_attr_spectre_v2.attr, + NULL +}; + +static const struct attribute_group cpu_root_vulnerabilities_group = { + .name = "vulnerabilities", + .attrs = cpu_root_vulnerabilities_attrs, +}; + +static void __init cpu_register_vulnerabilities(void) +{ + if (sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_vulnerabilities_group)) + pr_err("Unable to register CPU vulnerabilities\n"); +} + +#else +static inline void cpu_register_vulnerabilities(void) { } +#endif + void __init cpu_dev_init(void) { if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups)) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); + cpu_register_vulnerabilities(); } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 938ea8ae0ba4..c816e6f2730c 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -47,6 +47,13 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); +extern ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf); + extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, -- cgit v1.2.3 From 527187d28569e39c5d489d6306d3b79605cf85a6 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 8 Jan 2018 17:27:19 +0100 Subject: locking/lockdep: Remove cross-release leftovers There's two cross-release leftover facilities: - the crossrelease_hist_*() irq-tracing callbacks (NOPs currently) - the complete_release_commit() callback (NOP as well) Remove them. Cc: David Sterba Cc: Byungchul Park Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- include/linux/completion.h | 1 - include/linux/irqflags.h | 4 ---- include/linux/lockdep.h | 2 -- kernel/sched/completion.c | 5 ----- 4 files changed, 12 deletions(-) (limited to 'include') diff --git a/include/linux/completion.h b/include/linux/completion.h index 94a59ba7d422..519e94915d18 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -32,7 +32,6 @@ struct completion { #define init_completion(x) __init_completion(x) static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} -static inline void complete_release_commit(struct completion *x) {} #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 46cb57d5eb13..1b3996ff3f16 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -27,22 +27,18 @@ # define trace_hardirq_enter() \ do { \ current->hardirq_context++; \ - crossrelease_hist_start(XHLOCK_HARD); \ } while (0) # define trace_hardirq_exit() \ do { \ current->hardirq_context--; \ - crossrelease_hist_end(XHLOCK_HARD); \ } while (0) # define lockdep_softirq_enter() \ do { \ current->softirq_context++; \ - crossrelease_hist_start(XHLOCK_SOFT); \ } while (0) # define lockdep_softirq_exit() \ do { \ current->softirq_context--; \ - crossrelease_hist_end(XHLOCK_SOFT); \ } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2e75dc34bff5..3251d9c0d313 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -475,8 +475,6 @@ enum xhlock_context_t { #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } -static inline void crossrelease_hist_start(enum xhlock_context_t c) {} -static inline void crossrelease_hist_end(enum xhlock_context_t c) {} static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 2ddaec40956f..0926aef10dad 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -34,11 +34,6 @@ void complete(struct completion *x) spin_lock_irqsave(&x->wait.lock, flags); - /* - * Perform commit of crossrelease here. - */ - complete_release_commit(x); - if (x->done != UINT_MAX) x->done++; __wake_up_locked(&x->wait, TASK_NORMAL, 1); -- cgit v1.2.3 From b6c5734db07079c9410147b32407f2366d584e6c Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Fri, 5 Jan 2018 11:17:18 -0200 Subject: sctp: fix the handling of ICMP Frag Needed for too small MTUs syzbot reported a hang involving SCTP, on which it kept flooding dmesg with the message: [ 246.742374] sctp: sctp_transport_update_pmtu: Reported pmtu 508 too low, using default minimum of 512 That happened because whenever SCTP hits an ICMP Frag Needed, it tries to adjust to the new MTU and triggers an immediate retransmission. But it didn't consider the fact that MTUs smaller than the SCTP minimum MTU allowed (512) would not cause the PMTU to change, and issued the retransmission anyway (thus leading to another ICMP Frag Needed, and so on). As IPv4 (ip_rt_min_pmtu=556) and IPv6 (IPV6_MIN_MTU=1280) minimum MTU are higher than that, sctp_transport_update_pmtu() is changed to re-fetch the PMTU that got set after our request, and with that, detect if there was an actual change or not. The fix, thus, skips the immediate retransmission if the received ICMP resulted in no change, in the hope that SCTP will select another path. Note: The value being used for the minimum MTU (512, SCTP_DEFAULT_MINSEGMENT) is not right and instead it should be (576, SCTP_MIN_PMTU), but such change belongs to another patch. Changes from v1: - do not disable PMTU discovery, in the light of commit 06ad391919b2 ("[SCTP] Don't disable PMTU discovery when mtu is small") and as suggested by Xin Long. - changed the way to break the rtx loop by detecting if the icmp resulted in a change or not Changes from v2: none See-also: https://lkml.org/lkml/2017/12/22/811 Reported-by: syzbot Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 2 +- net/sctp/input.c | 8 ++++++-- net/sctp/transport.c | 29 +++++++++++++++++++---------- 3 files changed, 26 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2f8f93da5dc2..9a5ccf03a59b 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -966,7 +966,7 @@ void sctp_transport_burst_limited(struct sctp_transport *); void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *t); -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); +bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); diff --git a/net/sctp/input.c b/net/sctp/input.c index 9320661cc41d..141c9c466ec1 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -406,8 +406,12 @@ void sctp_icmp_frag_needed(struct sock *sk, struct sctp_association *asoc, */ return; - /* Update transports view of the MTU */ - sctp_transport_update_pmtu(t, pmtu); + /* Update transports view of the MTU. Return if no update was needed. + * If an update wasn't needed/possible, it also doesn't make sense to + * try to retransmit now. + */ + if (!sctp_transport_update_pmtu(t, pmtu)) + return; /* Update association pmtu. */ sctp_assoc_sync_pmtu(asoc); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 1e5a22430cf5..47f82bd794d9 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -248,28 +248,37 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) +bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) { struct dst_entry *dst = sctp_transport_dst_check(t); + bool change = true; if (unlikely(pmtu < SCTP_DEFAULT_MINSEGMENT)) { - pr_warn("%s: Reported pmtu %d too low, using default minimum of %d\n", - __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); - /* Use default minimum segment size and disable - * pmtu discovery on this transport. - */ - t->pathmtu = SCTP_DEFAULT_MINSEGMENT; - } else { - t->pathmtu = pmtu; + pr_warn_ratelimited("%s: Reported pmtu %d too low, using default minimum of %d\n", + __func__, pmtu, SCTP_DEFAULT_MINSEGMENT); + /* Use default minimum segment instead */ + pmtu = SCTP_DEFAULT_MINSEGMENT; } + pmtu = SCTP_TRUNC4(pmtu); if (dst) { dst->ops->update_pmtu(dst, t->asoc->base.sk, NULL, pmtu); dst = sctp_transport_dst_check(t); } - if (!dst) + if (!dst) { t->af_specific->get_dst(t, &t->saddr, &t->fl, t->asoc->base.sk); + dst = t->dst; + } + + if (dst) { + /* Re-fetch, as under layers may have a higher minimum size */ + pmtu = SCTP_TRUNC4(dst_mtu(dst)); + change = t->pathmtu != pmtu; + } + t->pathmtu = pmtu; + + return change; } /* Caches the dst entry and source address for a transport's destination -- cgit v1.2.3 From b2157399cc9898260d6031c5bfe45fe137c1fbe7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Sun, 7 Jan 2018 17:33:02 -0800 Subject: bpf: prevent out-of-bounds speculation Under speculation, CPUs may mis-predict branches in bounds checks. Thus, memory accesses under a bounds check may be speculated even if the bounds check fails, providing a primitive for building a side channel. To avoid leaking kernel data round up array-based maps and mask the index after bounds check, so speculated load with out of bounds index will load either valid value from the array or zero from the padded area. Unconditionally mask index for all array types even when max_entries are not rounded to power of 2 for root user. When map is created by unpriv user generate a sequence of bpf insns that includes AND operation to make sure that JITed code includes the same 'index & index_mask' operation. If prog_array map is created by unpriv user replace bpf_tail_call(ctx, map, index); with if (index >= max_entries) { index &= map->index_mask; bpf_tail_call(ctx, map, index); } (along with roundup to power 2) to prevent out-of-bounds speculation. There is secondary redundant 'if (index >= max_entries)' in the interpreter and in all JITs, but they can be optimized later if necessary. Other array-like maps (cpumap, devmap, sockmap, perf_event_array, cgroup_array) cannot be used by unpriv, so no changes there. That fixes bpf side of "Variant 1: bounds check bypass (CVE-2017-5753)" on all architectures with and without JIT. v2->v3: Daniel noticed that attack potentially can be crafted via syscall commands without loading the program, so add masking to those paths as well. Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Signed-off-by: Daniel Borkmann --- include/linux/bpf.h | 2 ++ kernel/bpf/arraymap.c | 47 ++++++++++++++++++++++++++++++++++++----------- kernel/bpf/verifier.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 74 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e55e4255a210..1b985ca4ffbe 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -52,6 +52,7 @@ struct bpf_map { u32 pages; u32 id; int numa_node; + bool unpriv_array; struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; @@ -221,6 +222,7 @@ struct bpf_prog_aux { struct bpf_array { struct bpf_map map; u32 elem_size; + u32 index_mask; /* 'ownership' of prog_array is claimed by the first program that * is going to use this map or by the first program which FD is stored * in the map to make sure that all callers and callees have the same diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 7c25426d3cf5..aaa319848e7d 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -53,9 +53,10 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); + u32 elem_size, index_mask, max_entries; + bool unpriv = !capable(CAP_SYS_ADMIN); struct bpf_array *array; u64 array_size; - u32 elem_size; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -72,11 +73,20 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); + max_entries = attr->max_entries; + index_mask = roundup_pow_of_two(max_entries) - 1; + + if (unpriv) + /* round up array size to nearest power of 2, + * since cpu will speculate within index_mask limits + */ + max_entries = index_mask + 1; + array_size = sizeof(*array); if (percpu) - array_size += (u64) attr->max_entries * sizeof(void *); + array_size += (u64) max_entries * sizeof(void *); else - array_size += (u64) attr->max_entries * elem_size; + array_size += (u64) max_entries * elem_size; /* make sure there is no u32 overflow later in round_up() */ if (array_size >= U32_MAX - PAGE_SIZE) @@ -86,6 +96,8 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) array = bpf_map_area_alloc(array_size, numa_node); if (!array) return ERR_PTR(-ENOMEM); + array->index_mask = index_mask; + array->map.unpriv_array = unpriv; /* copy mandatory map attributes */ array->map.map_type = attr->map_type; @@ -121,12 +133,13 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL; - return array->value + array->elem_size * index; + return array->value + array->elem_size * (index & array->index_mask); } /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { + struct bpf_array *array = container_of(map, struct bpf_array, map); struct bpf_insn *insn = insn_buf; u32 elem_size = round_up(map->value_size, 8); const int ret = BPF_REG_0; @@ -135,7 +148,12 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); + if (map->unpriv_array) { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4); + *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); + } else { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 3); + } if (is_power_of_2(elem_size)) { *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); @@ -157,7 +175,7 @@ static void *percpu_array_map_lookup_elem(struct bpf_map *map, void *key) if (unlikely(index >= array->map.max_entries)) return NULL; - return this_cpu_ptr(array->pptrs[index]); + return this_cpu_ptr(array->pptrs[index & array->index_mask]); } int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) @@ -177,7 +195,7 @@ int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value) */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); off += size; @@ -225,10 +243,11 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, return -EEXIST; if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) - memcpy(this_cpu_ptr(array->pptrs[index]), + memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); else - memcpy(array->value + array->elem_size * index, + memcpy(array->value + + array->elem_size * (index & array->index_mask), value, map->value_size); return 0; } @@ -262,7 +281,7 @@ int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, */ size = round_up(map->value_size, 8); rcu_read_lock(); - pptr = array->pptrs[index]; + pptr = array->pptrs[index & array->index_mask]; for_each_possible_cpu(cpu) { bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); off += size; @@ -613,6 +632,7 @@ static void *array_of_map_lookup_elem(struct bpf_map *map, void *key) static u32 array_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { + struct bpf_array *array = container_of(map, struct bpf_array, map); u32 elem_size = round_up(map->value_size, 8); struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; @@ -621,7 +641,12 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map, *insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value)); *insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0); - *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + if (map->unpriv_array) { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6); + *insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask); + } else { + *insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 5); + } if (is_power_of_2(elem_size)) *insn++ = BPF_ALU64_IMM(BPF_LSH, ret, ilog2(elem_size)); else diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 04b24876cd23..b414d6b2d470 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1729,6 +1729,13 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta); if (err) return err; + if (func_id == BPF_FUNC_tail_call) { + if (meta.map_ptr == NULL) { + verbose(env, "verifier bug\n"); + return -EINVAL; + } + env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr; + } err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta); if (err) return err; @@ -4456,6 +4463,35 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ insn->imm = 0; insn->code = BPF_JMP | BPF_TAIL_CALL; + + /* instead of changing every JIT dealing with tail_call + * emit two extra insns: + * if (index >= max_entries) goto out; + * index &= array->index_mask; + * to avoid out-of-bounds cpu speculation + */ + map_ptr = env->insn_aux_data[i + delta].map_ptr; + if (map_ptr == BPF_MAP_PTR_POISON) { + verbose(env, "tail_call obusing map_ptr\n"); + return -EINVAL; + } + if (!map_ptr->unpriv_array) + continue; + insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3, + map_ptr->max_entries, 2); + insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3, + container_of(map_ptr, + struct bpf_array, + map)->index_mask); + insn_buf[2] = *insn; + cnt = 3; + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; continue; } -- cgit v1.2.3 From be95a845cc4402272994ce290e3ad928aff06cb9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Jan 2018 13:17:44 +0100 Subject: bpf: avoid false sharing of map refcount with max_entries In addition to commit b2157399cc98 ("bpf: prevent out-of-bounds speculation") also change the layout of struct bpf_map such that false sharing of fast-path members like max_entries is avoided when the maps reference counter is altered. Therefore enforce them to be placed into separate cachelines. pahole dump after change: struct bpf_map { const struct bpf_map_ops * ops; /* 0 8 */ struct bpf_map * inner_map_meta; /* 8 8 */ void * security; /* 16 8 */ enum bpf_map_type map_type; /* 24 4 */ u32 key_size; /* 28 4 */ u32 value_size; /* 32 4 */ u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ u32 pages; /* 44 4 */ u32 id; /* 48 4 */ int numa_node; /* 52 4 */ bool unpriv_array; /* 56 1 */ /* XXX 7 bytes hole, try to pack */ /* --- cacheline 1 boundary (64 bytes) --- */ struct user_struct * user; /* 64 8 */ atomic_t refcnt; /* 72 4 */ atomic_t usercnt; /* 76 4 */ struct work_struct work; /* 80 32 */ char name[16]; /* 112 16 */ /* --- cacheline 2 boundary (128 bytes) --- */ /* size: 128, cachelines: 2, members: 17 */ /* sum members: 121, holes: 1, sum holes: 7 */ }; Now all entries in the first cacheline are read only throughout the life time of the map, set up once during map creation. Overall struct size and number of cachelines doesn't change from the reordering. struct bpf_map is usually first member and embedded in map structs in specific map implementations, so also avoid those members to sit at the end where it could potentially share the cacheline with first map values e.g. in the array since remote CPUs could trigger map updates just as well for those (easily dirtying members like max_entries intentionally as well) while having subsequent values in cache. Quoting from Google's Project Zero blog [1]: Additionally, at least on the Intel machine on which this was tested, bouncing modified cache lines between cores is slow, apparently because the MESI protocol is used for cache coherence [8]. Changing the reference counter of an eBPF array on one physical CPU core causes the cache line containing the reference counter to be bounced over to that CPU core, making reads of the reference counter on all other CPU cores slow until the changed reference counter has been written back to memory. Because the length and the reference counter of an eBPF array are stored in the same cache line, this also means that changing the reference counter on one physical CPU core causes reads of the eBPF array's length to be slow on other physical CPU cores (intentional false sharing). While this doesn't 'control' the out-of-bounds speculation through masking the index as in commit b2157399cc98, triggering a manipulation of the map's reference counter is really trivial, so lets not allow to easily affect max_entries from it. Splitting to separate cachelines also generally makes sense from a performance perspective anyway in that fast-path won't have a cache miss if the map gets pinned, reused in other progs, etc out of control path, thus also avoids unintentional false sharing. [1] https://googleprojectzero.blogspot.ch/2018/01/reading-privileged-memory-with-side.html Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1b985ca4ffbe..fe2cb7c398e3 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -43,7 +43,14 @@ struct bpf_map_ops { }; struct bpf_map { - atomic_t refcnt; + /* 1st cacheline with read-mostly members of which some + * are also accessed in fast-path (e.g. ops, max_entries). + */ + const struct bpf_map_ops *ops ____cacheline_aligned; + struct bpf_map *inner_map_meta; +#ifdef CONFIG_SECURITY + void *security; +#endif enum bpf_map_type map_type; u32 key_size; u32 value_size; @@ -53,15 +60,16 @@ struct bpf_map { u32 id; int numa_node; bool unpriv_array; - struct user_struct *user; - const struct bpf_map_ops *ops; - struct work_struct work; + /* 7 bytes hole */ + + /* 2nd cacheline with misc members to avoid false sharing + * particularly with refcounting. + */ + struct user_struct *user ____cacheline_aligned; + atomic_t refcnt; atomic_t usercnt; - struct bpf_map *inner_map_meta; + struct work_struct work; char name[BPF_OBJ_NAME_LEN]; -#ifdef CONFIG_SECURITY - void *security; -#endif }; /* function argument constraints */ -- cgit v1.2.3 From 67dcf8a3e06582cb6b02952335b5612beb97889f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 5 Jan 2018 18:09:33 +0200 Subject: ACPI: utils: Introduce acpi_dev_get_first_match_name() Sometimes the user wants to have device name of the match rather than just checking if device present or not. To make life easier for such users introduce acpi_dev_get_first_match_name() helper based on code for acpi_dev_present(). For example, GPIO driver for Intel Merrifield needs to know the device name of pin control to be able to apply GPIO mapping table to the proper device. To be more consistent with the purpose rename struct acpi_dev_present_info -> struct acpi_dev_match_info acpi_dev_present_cb() -> acpi_dev_match_cb() in the utils.c file. Tested-by: Pierre-Louis Bossart Signed-off-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 41 ++++++++++++++++++++++++++++++++++------- include/acpi/acpi_bus.h | 3 +++ include/linux/acpi.h | 6 ++++++ 3 files changed, 43 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 9d49a1acebe3..78db97687f26 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -737,16 +737,17 @@ bool acpi_dev_found(const char *hid) } EXPORT_SYMBOL(acpi_dev_found); -struct acpi_dev_present_info { +struct acpi_dev_match_info { + const char *dev_name; struct acpi_device_id hid[2]; const char *uid; s64 hrv; }; -static int acpi_dev_present_cb(struct device *dev, void *data) +static int acpi_dev_match_cb(struct device *dev, void *data) { struct acpi_device *adev = to_acpi_device(dev); - struct acpi_dev_present_info *match = data; + struct acpi_dev_match_info *match = data; unsigned long long hrv; acpi_status status; @@ -757,6 +758,8 @@ static int acpi_dev_present_cb(struct device *dev, void *data) strcmp(adev->pnp.unique_id, match->uid))) return 0; + match->dev_name = acpi_dev_name(adev); + if (match->hrv == -1) return 1; @@ -789,20 +792,44 @@ static int acpi_dev_present_cb(struct device *dev, void *data) */ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { - struct acpi_dev_present_info match = {}; + struct acpi_dev_match_info match = {}; struct device *dev; strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id)); match.uid = uid; match.hrv = hrv; - dev = bus_find_device(&acpi_bus_type, NULL, &match, - acpi_dev_present_cb); - + dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb); return !!dev; } EXPORT_SYMBOL(acpi_dev_present); +/** + * acpi_dev_get_first_match_name - Return name of first match of ACPI device + * @hid: Hardware ID of the device. + * @uid: Unique ID of the device, pass NULL to not check _UID + * @hrv: Hardware Revision of the device, pass -1 to not check _HRV + * + * Return device name if a matching device was present + * at the moment of invocation, or NULL otherwise. + * + * See additional information in acpi_dev_present() as well. + */ +const char * +acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) +{ + struct acpi_dev_match_info match = {}; + struct device *dev; + + strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id)); + match.uid = uid; + match.hrv = hrv; + + dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb); + return dev ? match.dev_name : NULL; +} +EXPORT_SYMBOL(acpi_dev_get_first_match_name); + /* * acpi_backlight= handling, this is done here rather then in video_detect.c * because __setup cannot be used in modules. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 79287629c888..c9608b0b80c6 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -91,6 +91,9 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, bool acpi_dev_found(const char *hid); bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); +const char * +acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv); + #ifdef CONFIG_ACPI #include diff --git a/include/linux/acpi.h b/include/linux/acpi.h index dc1ebfeeb5ec..d918f1ea84e6 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -640,6 +640,12 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) return false; } +static inline const char * +acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) +{ + return NULL; +} + static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return false; -- cgit v1.2.3 From a0b1280368d1e91ab72f849ef095b4f07a39bbf1 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 12 Jan 2018 16:53:14 -0800 Subject: kdump: write correct address of mem_section into vmcoreinfo Depending on configuration mem_section can now be an array or a pointer to an array allocated dynamically. In most cases, we can continue to refer to it as 'mem_section' regardless of what it is. But there's one exception: '&mem_section' means "address of the array" if mem_section is an array, but if mem_section is a pointer, it would mean "address of the pointer". We've stepped onto this in kdump code. VMCOREINFO_SYMBOL(mem_section) writes down address of pointer into vmcoreinfo, not array as we wanted. Let's introduce VMCOREINFO_SYMBOL_ARRAY() that would handle the situation correctly for both cases. Link: http://lkml.kernel.org/r/20180112162532.35896-1-kirill.shutemov@linux.intel.com Signed-off-by: Kirill A. Shutemov Fixes: 83e3c48729d9 ("mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y") Acked-by: Baoquan He Acked-by: Dave Young Cc: Ingo Molnar Cc: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: Dave Young Cc: Baoquan He Cc: Vivek Goyal Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_core.h | 2 ++ kernel/crash_core.c | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 06097ef30449..b511f6d24b42 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -42,6 +42,8 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SYMBOL_ARRAY(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) #define VMCOREINFO_SIZE(name) \ vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ (unsigned long)sizeof(name)) diff --git a/kernel/crash_core.c b/kernel/crash_core.c index b3663896278e..4f63597c824d 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -410,7 +410,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(contig_page_data); #endif #ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_SYMBOL_ARRAY(mem_section); VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); -- cgit v1.2.3 From 06e8ccdab15f46dfd31292e2b75d744bc5fc2a7c Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 31 Jan 2018 12:45:38 -0700 Subject: acpi: nfit: Add support for detect platform CPU cache flush on power loss In ACPI 6.2a the platform capability structure has been added to the NFIT tables. That provides software the ability to determine whether a system supports the auto flushing of CPU caches on power loss. If the capability is supported, we do not need to do dax_flush(). Plumbing the path to set the property on per region from the NFIT tables. This patch depends on the ACPI NFIT 6.2a platform capabilities support code in include/acpi/actbl1.h. Signed-off-by: Dave Jiang Reviewed-by: Ross Zwisler Signed-off-by: Ross Zwisler --- drivers/acpi/nfit/core.c | 20 ++++++++++++++++++++ drivers/acpi/nfit/nfit.h | 1 + drivers/nvdimm/pmem.c | 4 +++- include/linux/libnvdimm.h | 5 +++++ 4 files changed, 29 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index abeb4df4f22e..dc775823aea0 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -838,6 +838,18 @@ static bool add_flush(struct acpi_nfit_desc *acpi_desc, return true; } +static bool add_platform_cap(struct acpi_nfit_desc *acpi_desc, + struct acpi_nfit_capabilities *pcap) +{ + struct device *dev = acpi_desc->dev; + u32 mask; + + mask = (1 << (pcap->highest_capability + 1)) - 1; + acpi_desc->platform_cap = pcap->capabilities & mask; + dev_dbg(dev, "%s: cap: %#x\n", __func__, acpi_desc->platform_cap); + return true; +} + static void *add_table(struct acpi_nfit_desc *acpi_desc, struct nfit_table_prev *prev, void *table, const void *end) { @@ -883,6 +895,10 @@ static void *add_table(struct acpi_nfit_desc *acpi_desc, case ACPI_NFIT_TYPE_SMBIOS: dev_dbg(dev, "%s: smbios\n", __func__); break; + case ACPI_NFIT_TYPE_CAPABILITIES: + if (!add_platform_cap(acpi_desc, table)) + return err; + break; default: dev_err(dev, "unknown table '%d' parsing nfit\n", hdr->type); break; @@ -2656,6 +2672,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, else ndr_desc->numa_node = NUMA_NO_NODE; + if(acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_CACHE_FLUSH) + set_bit(ND_REGION_PERSIST_CACHE, &ndr_desc->flags); + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping_desc *mapping; @@ -3464,6 +3483,7 @@ static __init int nfit_init(void) BUILD_BUG_ON(sizeof(struct acpi_nfit_smbios) != 9); BUILD_BUG_ON(sizeof(struct acpi_nfit_control_region) != 80); BUILD_BUG_ON(sizeof(struct acpi_nfit_data_region) != 40); + BUILD_BUG_ON(sizeof(struct acpi_nfit_capabilities) != 16); guid_parse(UUID_VOLATILE_MEMORY, &nfit_uuid[NFIT_SPA_VOLATILE]); guid_parse(UUID_PERSISTENT_MEMORY, &nfit_uuid[NFIT_SPA_PM]); diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h index f0cf18b2da8b..50d36e166d70 100644 --- a/drivers/acpi/nfit/nfit.h +++ b/drivers/acpi/nfit/nfit.h @@ -202,6 +202,7 @@ struct acpi_nfit_desc { unsigned long dimm_cmd_force_en; unsigned long bus_cmd_force_en; unsigned long bus_nfit_cmd_force_en; + unsigned int platform_cap; int (*blk_do_io)(struct nd_blk_region *ndbr, resource_size_t dpa, void *iobuf, u64 len, int rw); }; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7fbc5c5dc8e1..8aa542398db4 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -35,6 +35,7 @@ #include "pmem.h" #include "pfn.h" #include "nd.h" +#include "nd-core.h" static struct device *to_dev(struct pmem_device *pmem) { @@ -334,7 +335,8 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "unable to guarantee persistence of writes\n"); fua = 0; } - wbc = nvdimm_has_cache(nd_region); + wbc = nvdimm_has_cache(nd_region) && + !test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags); if (!devm_request_mem_region(dev, res->start, resource_size(res), dev_name(&ndns->dev))) { diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f8109ddb5ef1..f2fc0da4da04 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -47,6 +47,11 @@ enum { /* region flag indicating to direct-map persistent memory by default */ ND_REGION_PAGEMAP = 0, + /* + * Platform ensures entire CPU store data path is flushed to pmem on + * system power loss. + */ + ND_REGION_PERSIST_CACHE = 1, /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, -- cgit v1.2.3 From 30e6d7bf29daa79d80711d35211c9b60894dbc44 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 31 Jan 2018 12:45:43 -0700 Subject: acpi: nfit: add persistent memory control flag for nd_region Propagate the ADR attribute flag from the NFIT platform capabilities sub-table to nd_region. Signed-off-by: Dave Jiang Reviewed-by: Ross Zwisler Signed-off-by: Ross Zwisler --- drivers/acpi/nfit/core.c | 3 +++ include/linux/libnvdimm.h | 6 ++++++ 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index dc775823aea0..aa9d00db763a 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2675,6 +2675,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, if(acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_CACHE_FLUSH) set_bit(ND_REGION_PERSIST_CACHE, &ndr_desc->flags); + if (acpi_desc->platform_cap & ACPI_NFIT_CAPABILITY_MEM_FLUSH) + set_bit(ND_REGION_PERSIST_MEMCTRL, &ndr_desc->flags); + list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping_desc *mapping; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index f2fc0da4da04..ff855ed965fb 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -52,6 +52,12 @@ enum { * system power loss. */ ND_REGION_PERSIST_CACHE = 1, + /* + * Platform provides mechanisms to automatically flush outstanding + * write data from memory controler to pmem on system power loss. + * (ADR) + */ + ND_REGION_PERSIST_MEMCTRL = 2, /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, -- cgit v1.2.3