diff options
80 files changed, 3364 insertions, 588 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 16501334b99f..498741737055 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -340,3 +340,13 @@ Description: POWERNV CPUFreq driver's frequency throttle stats directory and 'policyX/throttle_stats' directory and all the attributes are same as the /sys/devices/system/cpu/cpuX/cpufreq/throttle_stats directory and attributes which give the frequency throttle information of the chip. + +What: /sys/devices/system/cpu/cpuX/regs/ + /sys/devices/system/cpu/cpuX/regs/identification/ + /sys/devices/system/cpu/cpuX/regs/identification/midr_el1 + /sys/devices/system/cpu/cpuX/regs/identification/revidr_el1 +Date: June 2016 +Contact: Linux ARM Kernel Mailing list <linux-arm-kernel@lists.infradead.org> +Description: AArch64 CPU registers + 'identification' directory exposes the CPU ID registers for + identifying model and revision of the CPU. diff --git a/Documentation/arm64/acpi_object_usage.txt b/Documentation/arm64/acpi_object_usage.txt index a6e1a1805e51..c77010c5c1f0 100644 --- a/Documentation/arm64/acpi_object_usage.txt +++ b/Documentation/arm64/acpi_object_usage.txt @@ -13,14 +13,14 @@ For ACPI on arm64, tables also fall into the following categories: -- Required: DSDT, FADT, GTDT, MADT, MCFG, RSDP, SPCR, XSDT - -- Recommended: BERT, EINJ, ERST, HEST, SSDT + -- Recommended: BERT, EINJ, ERST, HEST, PCCT, SSDT - -- Optional: BGRT, CPEP, CSRT, DRTM, ECDT, FACS, FPDT, MCHI, MPST, - MSCT, RASF, SBST, SLIT, SPMI, SRAT, TCPA, TPM2, UEFI - - -- Not supported: BOOT, DBG2, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, - LPIT, MSDM, RSDT, SLIC, WAET, WDAT, WDRT, WPBT + -- Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IORT, + MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, STAO, + TCPA, TPM2, UEFI, XENV + -- Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, LPIT, + MSDM, OEMx, PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT Table Usage for ARMv8 Linux ----- ---------------------------------------------------------------- @@ -50,7 +50,8 @@ CSRT Signature Reserved (signature == "CSRT") DBG2 Signature Reserved (signature == "DBG2") == DeBuG port table 2 == - Microsoft only table, will not be supported. + License has changed and should be usable. Optional if used instead + of earlycon=<device> on the command line. DBGP Signature Reserved (signature == "DBGP") == DeBuG Port table == @@ -133,10 +134,11 @@ GTDT Section 5.2.24 (signature == "GTDT") HEST Section 18.3.2 (signature == "HEST") == Hardware Error Source Table == - Until further error source types are defined, use only types 6 (AER - Root Port), 7 (AER Endpoint), 8 (AER Bridge), or 9 (Generic Hardware - Error Source). Firmware first error handling is possible if and only - if Trusted Firmware is being used on arm64. + ARM-specific error sources have been defined; please use those or the + PCI types such as type 6 (AER Root Port), 7 (AER Endpoint), or 8 (AER + Bridge), or use type 9 (Generic Hardware Error Source). Firmware first + error handling is possible if and only if Trusted Firmware is being + used on arm64. Must be supplied if RAS support is provided by the platform. It is recommended this table be supplied. @@ -149,20 +151,30 @@ IBFT Signature Reserved (signature == "IBFT") == iSCSI Boot Firmware Table == Microsoft defined table, support TBD. +IORT Signature Reserved (signature == "IORT") + == Input Output Remapping Table == + arm64 only table, required in order to describe IO topology, SMMUs, + and GIC ITSs, and how those various components are connected together, + such as identifying which components are behind which SMMUs/ITSs. + This table will only be required on certain SBSA platforms (e.g., + when using GICv3-ITS and an SMMU); on SBSA Level 0 platforms, it + remains optional. + IVRS Signature Reserved (signature == "IVRS") == I/O Virtualization Reporting Structure == x86_64 (AMD) only table, will not be supported. LPIT Signature Reserved (signature == "LPIT") == Low Power Idle Table == - x86 only table as of ACPI 5.1; future versions have been adapted for - use with ARM and will be recommended in order to support ACPI power - management. + x86 only table as of ACPI 5.1; starting with ACPI 6.0, processor + descriptions and power states on ARM platforms should use the DSDT + and define processor container devices (_HID ACPI0010, Section 8.4, + and more specifically 8.4.3 and and 8.4.4). MADT Section 5.2.12 (signature == "APIC") == Multiple APIC Description Table == Required for arm64. Only the GIC interrupt controller structures - should be used (types 0xA - 0xE). + should be used (types 0xA - 0xF). MCFG Signature Reserved (signature == "MCFG") == Memory-mapped ConFiGuration space == @@ -176,14 +188,38 @@ MPST Section 5.2.21 (signature == "MPST") == Memory Power State Table == Optional, not currently supported. +MSCT Section 5.2.19 (signature == "MSCT") + == Maximum System Characteristic Table == + Optional, not currently supported. + MSDM Signature Reserved (signature == "MSDM") == Microsoft Data Management table == Microsoft only table, will not be supported. -MSCT Section 5.2.19 (signature == "MSCT") - == Maximum System Characteristic Table == +NFIT Section 5.2.25 (signature == "NFIT") + == NVDIMM Firmware Interface Table == + Optional, not currently supported. + +OEMx Signature of "OEMx" only + == OEM Specific Tables == + All tables starting with a signature of "OEM" are reserved for OEM + use. Since these are not meant to be of general use but are limited + to very specific end users, they are not recommended for use and are + not supported by the kernel for arm64. + +PCCT Section 14.1 (signature == "PCCT) + == Platform Communications Channel Table == + Recommend for use on arm64; use of PCC is recommended when using CPPC + to control performance and power for platform processors. + +PMTT Section 5.2.21.12 (signature == "PMTT") + == Platform Memory Topology Table == Optional, not currently supported. +PSDT Section 5.2.11.3 (signature == "PSDT") + == Persistent System Description Table == + Obsolete table, will not be supported. + RASF Section 5.2.20 (signature == "RASF") == RAS Feature table == Optional, not currently supported. @@ -195,7 +231,7 @@ RSDP Section 5.2.5 (signature == "RSD PTR") RSDT Section 5.2.7 (signature == "RSDT") == Root System Description Table == Since this table can only provide 32-bit addresses, it is deprecated - on arm64, and will not be used. + on arm64, and will not be used. If provided, it will be ignored. SBST Section 5.2.14 (signature == "SBST") == Smart Battery Subsystem Table == @@ -220,7 +256,7 @@ SPMI Signature Reserved (signature == "SPMI") SRAT Section 5.2.16 (signature == "SRAT") == System Resource Affinity Table == Optional, but if used, only the GICC Affinity structures are read. - To support NUMA, this table is required. + To support arm64 NUMA, this table is required. SSDT Section 5.2.11.2 (signature == "SSDT") == Secondary System Description Table == @@ -235,6 +271,11 @@ SSDT Section 5.2.11.2 (signature == "SSDT") These tables are optional, however. ACPI tables should contain only one DSDT but can contain many SSDTs. +STAO Signature Reserved (signature == "STAO") + == _STA Override table == + Optional, but only necessary in virtualized environments in order to + hide devices from guest OSs. + TCPA Signature Reserved (signature == "TCPA") == Trusted Computing Platform Alliance table == Optional, not currently supported, and may need changes to fully @@ -266,6 +307,10 @@ WPBT Signature Reserved (signature == "WPBT") == Windows Platform Binary Table == Microsoft only table, will not be supported. +XENV Signature Reserved (signature == "XENV") + == Xen project table == + Optional, used only by Xen at present. + XSDT Section 5.2.8 (signature == "XSDT") == eXtended System Description Table == Required for arm64. @@ -273,44 +318,46 @@ XSDT Section 5.2.8 (signature == "XSDT") ACPI Objects ------------ -The expectations on individual ACPI objects are discussed in the list that -follows: +The expectations on individual ACPI objects that are likely to be used are +shown in the list that follows; any object not explicitly mentioned below +should be used as needed for a particular platform or particular subsystem, +such as power management or PCI. Name Section Usage for ARMv8 Linux ---- ------------ ------------------------------------------------- -_ADR 6.1.1 Use as needed. - -_BBN 6.5.5 Use as needed; PCI-specific. +_CCA 6.2.17 This method must be defined for all bus masters + on arm64 -- there are no assumptions made about + whether such devices are cache coherent or not. + The _CCA value is inherited by all descendants of + these devices so it does not need to be repeated. + Without _CCA on arm64, the kernel does not know what + to do about setting up DMA for the device. -_BDN 6.5.3 Optional; not likely to be used on arm64. + NB: this method provides default cache coherency + attributes; the presence of an SMMU can be used to + modify that, however. For example, a master could + default to non-coherent, but be made coherent with + the appropriate SMMU configuration (see Table 17 of + the IORT specification, ARM Document DEN 0049B). -_CCA 6.2.17 This method should be defined for all bus masters - on arm64. While cache coherency is assumed, making - it explicit ensures the kernel will set up DMA as - it should. +_CID 6.1.2 Use as needed, see also _HID. -_CDM 6.2.1 Optional, to be used only for processor devices. +_CLS 6.1.3 Use as needed, see also _HID. -_CID 6.1.2 Use as needed. - -_CLS 6.1.3 Use as needed. +_CPC 8.4.7.1 Use as needed, power management specific. CPPC is + recommended on arm64. _CRS 6.2.2 Required on arm64. -_DCK 6.5.2 Optional; not likely to be used on arm64. +_CSD 8.4.2.2 Use as needed, used only in conjunction with _CST. + +_CST 8.4.2.1 Low power idle states (8.4.4) are recommended instead + of C-states. _DDN 6.1.4 This field can be used for a device name. However, it is meant for DOS device names (e.g., COM1), so be careful of its use across OSes. -_DEP 6.5.8 Use as needed. - -_DIS 6.2.3 Optional, for power management use. - -_DLM 5.7.5 Optional. - -_DMA 6.2.4 Optional. - _DSD 6.2.5 To be used with caution. If this object is used, try to use it within the constraints already defined by the Device Properties UUID. Only in rare circumstances @@ -325,20 +372,10 @@ _DSD 6.2.5 To be used with caution. If this object is used, try with the UEFI Forum; this may cause some iteration as more than one OS will be registering entries. -_DSM Do not use this method. It is not standardized, the +_DSM 9.1.1 Do not use this method. It is not standardized, the return values are not well documented, and it is currently a frequent source of error. -_DSW 7.2.1 Use as needed; power management specific. - -_EDL 6.3.1 Optional. - -_EJD 6.3.2 Optional. - -_EJx 6.3.3 Optional. - -_FIX 6.2.7 x86 specific, not used on arm64. - \_GL 5.7.1 This object is not to be used in hardware reduced mode, and therefore should not be used on arm64. @@ -349,35 +386,22 @@ _GLK 6.5.7 This object requires a global lock be defined; there \_GPE 5.3.1 This namespace is for x86 use only. Do not use it on arm64. -_GSB 6.2.7 Optional. - -_HID 6.1.5 Use as needed. This is the primary object to use in - device probing, though _CID and _CLS may also be used. - -_HPP 6.2.8 Optional, PCI specific. - -_HPX 6.2.9 Optional, PCI specific. - -_HRV 6.1.6 Optional, use as needed to clarify device behavior; in - some cases, this may be easier to use than _DSD. +_HID 6.1.5 This is the primary object to use in device probing, + though _CID and _CLS may also be used. _INI 6.5.1 Not required, but can be useful in setting up devices when UEFI leaves them in a state that may not be what the driver expects before it starts probing. -_IRC 7.2.15 Use as needed; power management specific. - -_LCK 6.3.4 Optional. - -_MAT 6.2.10 Optional; see also the MADT. +_LPI 8.4.4.3 Recommended for use with processor definitions (_HID + ACPI0010) on arm64. See also _RDI. -_MLS 6.1.7 Optional, but highly recommended for use in - internationalization. +_MLS 6.1.7 Highly recommended for use in internationalization. -_OFF 7.1.2 It is recommended to define this method for any device +_OFF 7.2.2 It is recommended to define this method for any device that can be turned on or off. -_ON 7.1.3 It is recommended to define this method for any device +_ON 7.2.3 It is recommended to define this method for any device that can be turned on or off. \_OS 5.7.3 This method will return "Linux" by default (this is @@ -398,122 +422,107 @@ _OSC 6.2.11 This method can be a global method in ACPI (i.e., by the kernel community, then register it with the UEFI Forum. -\_OSI 5.7.2 Deprecated on ARM64. Any invocation of this method - will print a warning on the console and return false. - That is, as far as ACPI firmware is concerned, _OSI - cannot be used to determine what sort of system is - being used or what functionality is provided. The - _OSC method is to be used instead. - -_OST 6.3.5 Optional. +\_OSI 5.7.2 Deprecated on ARM64. As far as ACPI firmware is + concerned, _OSI is not to be used to determine what + sort of system is being used or what functionality + is provided. The _OSC method is to be used instead. _PDC 8.4.1 Deprecated, do not use on arm64. \_PIC 5.8.1 The method should not be used. On arm64, the only interrupt model available is GIC. -_PLD 6.1.8 Optional. - \_PR 5.3.1 This namespace is for x86 use only on legacy systems. Do not use it on arm64. -_PRS 6.2.12 Optional. - _PRT 6.2.13 Required as part of the definition of all PCI root devices. -_PRW 7.2.13 Use as needed; power management specific. - -_PRx 7.2.8-11 Use as needed; power management specific. If _PR0 is +_PRx 7.3.8-11 Use as needed; power management specific. If _PR0 is defined, _PR3 must also be defined. -_PSC 7.2.6 Use as needed; power management specific. - -_PSE 7.2.7 Use as needed; power management specific. - -_PSW 7.2.14 Use as needed; power management specific. - -_PSx 7.2.2-5 Use as needed; power management specific. If _PS0 is +_PSx 7.3.2-5 Use as needed; power management specific. If _PS0 is defined, _PS3 must also be defined. If clocks or regulators need adjusting to be consistent with power usage, change them in these methods. -\_PTS 7.3.1 Use as needed; power management specific. - -_PXM 6.2.14 Optional. - -_REG 6.5.4 Use as needed. +_RDI 8.4.4.4 Recommended for use with processor definitions (_HID + ACPI0010) on arm64. This should only be used in + conjunction with _LPI. \_REV 5.7.4 Always returns the latest version of ACPI supported. -_RMV 6.3.6 Optional. - \_SB 5.3.1 Required on arm64; all devices must be defined in this namespace. -_SEG 6.5.6 Use as needed; PCI-specific. - -\_SI 5.3.1, Optional. - 9.1 - -_SLI 6.2.15 Optional; recommended when SLIT table is in use. +_SLI 6.2.15 Use is recommended when SLIT table is in use. _STA 6.3.7, It is recommended to define this method for any device - 7.1.4 that can be turned on or off. + 7.2.4 that can be turned on or off. See also the STAO table + that provides overrides to hide devices in virtualized + environments. -_SRS 6.2.16 Optional; see also _PRS. +_SRS 6.2.16 Use as needed; see also _PRS. _STR 6.1.10 Recommended for conveying device names to end users; this is preferred over using _DDN. _SUB 6.1.9 Use as needed; _HID or _CID are preferred. -_SUN 6.1.11 Optional. - -\_Sx 7.3.2 Use as needed; power management specific. - -_SxD 7.2.16-19 Use as needed; power management specific. - -_SxW 7.2.20-24 Use as needed; power management specific. +_SUN 6.1.11 Use as needed, but recommended. -_SWS 7.3.3 Use as needed; power management specific; this may +_SWS 7.4.3 Use as needed; power management specific; this may require specification changes for use on arm64. -\_TTS 7.3.4 Use as needed; power management specific. - -\_TZ 5.3.1 Optional. - _UID 6.1.12 Recommended for distinguishing devices of the same class; define it if at all possible. -\_WAK 7.3.5 Use as needed; power management specific. + ACPI Event Model ---------------- Do not use GPE block devices; these are not supported in the hardware reduced profile used by arm64. Since there are no GPE blocks defined for use on ARM -platforms, GPIO-signaled interrupts should be used for creating system events. +platforms, ACPI events must be signaled differently. + +There are two options: GPIO-signaled interrupts (Section 5.6.5), and +interrupt-signaled events (Section 5.6.9). Interrupt-signaled events are a +new feature in the ACPI 6.1 specification. Either -- or both -- can be used +on a given platform, and which to use may be dependent of limitations in any +given SoC. If possible, interrupt-signaled events are recommended. ACPI Processor Control ---------------------- -Section 8 of the ACPI specification is currently undergoing change that -should be completed in the 6.0 version of the specification. Processor -performance control will be handled differently for arm64 at that point -in time. Processor aggregator devices (section 8.5) will not be used, -for example, but another similar mechanism instead. - -While UEFI constrains what we can say until the release of 6.0, it is -recommended that CPPC (8.4.5) be used as the primary model. This will -still be useful into the future. C-states and P-states will still be -provided, but most of the current design work appears to favor CPPC. +Section 8 of the ACPI specification changed significantly in version 6.0. +Processors should now be defined as Device objects with _HID ACPI0007; do +not use the deprecated Processor statement in ASL. All multiprocessor systems +should also define a hierarchy of processors, done with Processor Container +Devices (see Section 8.4.3.1, _HID ACPI0010); do not use processor aggregator +devices (Section 8.5) to describe processor topology. Section 8.4 of the +specification describes the semantics of these object definitions and how +they interrelate. + +Most importantly, the processor hierarchy defined also defines the low power +idle states that are available to the platform, along with the rules for +determining which processors can be turned on or off and the circumstances +that control that. Without this information, the processors will run in +whatever power state they were left in by UEFI. + +Note too, that the processor Device objects defined and the entries in the +MADT for GICs are expected to be in synchronization. The _UID of the Device +object must correspond to processor IDs used in the MADT. + +It is recommended that CPPC (8.4.5) be used as the primary model for processor +performance control on arm64. C-states and P-states may become available at +some point in the future, but most current design work appears to favor CPPC. Further, it is essential that the ARMv8 SoC provide a fully functional implementation of PSCI; this will be the only mechanism supported by ACPI -to control CPU power state (including secondary CPU booting). - -More details will be provided on the release of the ACPI 6.0 specification. +to control CPU power state. Booting of secondary CPUs using the ACPI +parking protocol is possible, but discouraged, since only PSCI is supported +for ARM servers. ACPI System Address Map Interfaces @@ -535,21 +544,25 @@ used to indicate fatal errors that cannot be corrected, and require immediate attention. Since there is no direct equivalent of the x86 SCI or NMI, arm64 handles -these slightly differently. The SCI is handled as a normal GPIO-signaled -interrupt; given that these are corrected (or correctable) errors being -reported, this is sufficient. The NMI is emulated as the highest priority -GPIO-signaled interrupt possible. This implies some caution must be used -since there could be interrupts at higher privilege levels or even interrupts -at the same priority as the emulated NMI. In Linux, this should not be the -case but one should be aware it could happen. +these slightly differently. The SCI is handled as a high priority interrupt; +given that these are corrected (or correctable) errors being reported, this +is sufficient. The NMI is emulated as the highest priority interrupt +possible. This implies some caution must be used since there could be +interrupts at higher privilege levels or even interrupts at the same priority +as the emulated NMI. In Linux, this should not be the case but one should +be aware it could happen. ACPI Objects Not Supported on ARM64 ----------------------------------- While this may change in the future, there are several classes of objects that can be defined, but are not currently of general interest to ARM servers. +Some of these objects have x86 equivalents, and may actually make sense in ARM +servers. However, there is either no hardware available at present, or there +may not even be a non-ARM implementation yet. Hence, they are not currently +supported. -These are not supported: +The following classes of objects are not supported: -- Section 9.2: ambient light sensor devices @@ -571,16 +584,6 @@ These are not supported: -- Section 9.18: time and alarm devices (see 9.15) - -ACPI Objects Not Yet Implemented --------------------------------- -While these objects have x86 equivalents, and they do make some sense in ARM -servers, there is either no hardware available at present, or in some cases -there may not yet be a non-ARM implementation. Hence, they are currently not -implemented though that may change in the future. - -Not yet implemented are: - -- Section 10: power source and power meter devices -- Section 11: thermal management @@ -589,5 +592,31 @@ Not yet implemented are: -- Section 13: SMBus interfaces - -- Section 17: NUMA support (prototypes have been submitted for - review) + +This also means that there is no support for the following objects: + +Name Section Name Section +---- ------------ ---- ------------ +_ALC 9.3.4 _FDM 9.10.3 +_ALI 9.3.2 _FIX 6.2.7 +_ALP 9.3.6 _GAI 10.4.5 +_ALR 9.3.5 _GHL 10.4.7 +_ALT 9.3.3 _GTM 9.9.2.1.1 +_BCT 10.2.2.10 _LID 9.5.1 +_BDN 6.5.3 _PAI 10.4.4 +_BIF 10.2.2.1 _PCL 10.3.2 +_BIX 10.2.2.1 _PIF 10.3.3 +_BLT 9.2.3 _PMC 10.4.1 +_BMA 10.2.2.4 _PMD 10.4.8 +_BMC 10.2.2.12 _PMM 10.4.3 +_BMD 10.2.2.11 _PRL 10.3.4 +_BMS 10.2.2.5 _PSR 10.3.1 +_BST 10.2.2.6 _PTP 10.4.2 +_BTH 10.2.2.7 _SBS 10.1.3 +_BTM 10.2.2.9 _SHL 10.4.6 +_BTP 10.2.2.8 _STM 9.9.2.1.1 +_DCK 6.5.2 _UPD 9.16.1 +_EC 12.12 _UPP 9.16.2 +_FDE 9.10.1 _WPC 10.5.2 +_FDI 9.10.2 _WPP 10.5.3 + diff --git a/Documentation/arm64/arm-acpi.txt b/Documentation/arm64/arm-acpi.txt index 570a4f8e1a01..1a74a041a443 100644 --- a/Documentation/arm64/arm-acpi.txt +++ b/Documentation/arm64/arm-acpi.txt @@ -34,7 +34,7 @@ of the summary text almost directly, to be honest. The short form of the rationale for ACPI on ARM is: --- ACPI’s bytecode (AML) allows the platform to encode hardware behavior, +-- ACPI’s byte code (AML) allows the platform to encode hardware behavior, while DT explicitly does not support this. For hardware vendors, being able to encode behavior is a key tool used in supporting operating system releases on new hardware. @@ -57,11 +57,11 @@ The short form of the rationale for ACPI on ARM is: -- The new ACPI governance process works well and Linux is now at the same table as hardware vendors and other OS vendors. In fact, there is no - longer any reason to feel that ACPI is only belongs to Windows or that + longer any reason to feel that ACPI only belongs to Windows or that Linux is in any way secondary to Microsoft in this arena. The move of ACPI governance into the UEFI forum has significantly opened up the specification development process, and currently, a large portion of the - changes being made to ACPI is being driven by Linux. + changes being made to ACPI are being driven by Linux. Key to the use of ACPI is the support model. For servers in general, the responsibility for hardware behaviour cannot solely be the domain of the @@ -110,7 +110,7 @@ ACPI support in drivers and subsystems for ARMv8 should never be mutually exclusive with DT support at compile time. At boot time the kernel will only use one description method depending on -parameters passed from the bootloader (including kernel bootargs). +parameters passed from the boot loader (including kernel bootargs). Regardless of whether DT or ACPI is used, the kernel must always be capable of booting with either scheme (in kernels with both schemes enabled at compile @@ -159,7 +159,7 @@ Further, the ACPI core will only use the 64-bit address fields in the FADT (Fixed ACPI Description Table). Any 32-bit address fields in the FADT will be ignored on arm64. -Hardware reduced mode (see Section 4.1 of the ACPI 5.1 specification) will +Hardware reduced mode (see Section 4.1 of the ACPI 6.1 specification) will be enforced by the ACPI core on arm64. Doing so allows the ACPI core to run less complex code since it no longer has to provide support for legacy hardware from other architectures. Any fields that are not to be used for @@ -167,7 +167,7 @@ hardware reduced mode must be set to zero. For the ACPI core to operate properly, and in turn provide the information the kernel needs to configure devices, it expects to find the following -tables (all section numbers refer to the ACPI 5.1 specfication): +tables (all section numbers refer to the ACPI 6.1 specification): -- RSDP (Root System Description Pointer), section 5.2.5 @@ -185,9 +185,23 @@ tables (all section numbers refer to the ACPI 5.1 specfication): -- If PCI is supported, the MCFG (Memory mapped ConFiGuration Table), section 5.2.6, specifically Table 5-31. + -- If booting without a console=<device> kernel parameter is + supported, the SPCR (Serial Port Console Redirection table), + section 5.2.6, specifically Table 5-31. + + -- If necessary to describe the I/O topology, SMMUs and GIC ITSs, + the IORT (Input Output Remapping Table, section 5.2.6, specifically + Table 5-31). + + -- If NUMA is supported, the SRAT (System Resource Affinity Table) + and SLIT (System Locality distance Information Table), sections + 5.2.16 and 5.2.17, respectively. + If the above tables are not all present, the kernel may or may not be able to boot properly since it may not be able to configure all of the -devices available. +devices available. This list of tables is not meant to be all inclusive; +in some environments other tables may be needed (e.g., any of the APEI +tables from section 18) to support specific functionality. ACPI Detection @@ -198,7 +212,7 @@ the device structure. This is detailed further in the "Driver Recommendations" section. In non-driver code, if the presence of ACPI needs to be detected at -runtime, then check the value of acpi_disabled. If CONFIG_ACPI is not +run time, then check the value of acpi_disabled. If CONFIG_ACPI is not set, acpi_disabled will always be 1. @@ -233,7 +247,7 @@ that looks like this: Name(KEY0, "value0"). An ACPI device driver would then retrieve the value of the property by evaluating the KEY0 object. However, using Name() this way has multiple problems: (1) ACPI limits names ("KEY0") to four characters unlike DT; (2) there is no industry -wide registry that maintains a list of names, minimzing re-use; (3) +wide registry that maintains a list of names, minimizing re-use; (3) there is also no registry for the definition of property values ("value0"), again making re-use difficult; and (4) how does one maintain backward compatibility as new hardware comes out? The _DSD method was created @@ -434,7 +448,8 @@ The ACPI specification changes regularly. During the year 2014, for instance, version 5.1 was released and version 6.0 substantially completed, with most of the changes being driven by ARM-specific requirements. Proposed changes are presented and discussed in the ASWG (ACPI Specification Working Group) which -is a part of the UEFI Forum. +is a part of the UEFI Forum. The current version of the ACPI specification +is 6.1 release in January 2016. Participation in this group is open to all UEFI members. Please see http://www.uefi.org/workinggroup for details on group membership. @@ -443,7 +458,7 @@ It is the intent of the ARMv8 ACPI kernel code to follow the ACPI specification as closely as possible, and to only implement functionality that complies with the released standards from UEFI ASWG. As a practical matter, there will be vendors that provide bad ACPI tables or violate the standards in some way. -If this is because of errors, quirks and fixups may be necessary, but will +If this is because of errors, quirks and fix-ups may be necessary, but will be avoided if possible. If there are features missing from ACPI that preclude it from being used on a platform, ECRs (Engineering Change Requests) should be submitted to ASWG and go through the normal approval process; for those that @@ -480,8 +495,7 @@ References Software on ARM Platforms", dated 16 Aug 2014 [2] http://www.secretlab.ca/archives/151, 10 Jan 2015, Copyright (c) 2015, - Linaro Ltd., written by Grant Likely. A copy of the verbatim text (apart - from formatting) is also in Documentation/arm64/why_use_acpi.txt. + Linaro Ltd., written by Grant Likely. [3] AMD ACPI for Seattle platform documentation: http://amd-dev.wpengine.netdna-cdn.com/wordpress/media/2012/10/Seattle_ACPI_Guide.pdf diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt index 74d5417d0410..61c8b4620415 100644 --- a/Documentation/devicetree/bindings/arm/pmu.txt +++ b/Documentation/devicetree/bindings/arm/pmu.txt @@ -39,7 +39,9 @@ Optional properties: When using a PPI, specifies a list of phandles to CPU nodes corresponding to the set of CPUs which have a PMU of this type signalling the PPI listed in the - interrupts property. + interrupts property, unless this is already specified + by the PPI interrupt specifier itself (in which case + the interrupt-affinity property shouldn't be present). This property should be present when there is more than a single SPI. diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 20d5a60530b1..9f8b99e20557 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -8,6 +8,7 @@ config ARM64 select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_KCOV select ARCH_HAS_SG_CHAIN select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_USE_CMPXCHG_LOCKREF @@ -86,8 +87,11 @@ config ARM64 select HAVE_PERF_EVENTS select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP + select HAVE_REGS_AND_STACK_ACCESS_API select HAVE_RCU_TABLE_FREE select HAVE_SYSCALL_TRACEPOINTS + select HAVE_KPROBES + select HAVE_KRETPROBES if HAVE_KPROBES select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING @@ -665,6 +669,16 @@ config PARAVIRT_TIME_ACCOUNTING If in doubt, say N here. +config KEXEC + depends on PM_SLEEP_SMP + select KEXEC_CORE + bool "kexec system call" + ---help--- + kexec is a system call that implements the ability to shutdown your + current kernel, and to start another kernel. It is like a reboot + but it is independent of the system firmware. And like a reboot + you can start any kernel with it, not just Linux. + config XEN_DOM0 def_bool y depends on XEN @@ -873,7 +887,7 @@ config RELOCATABLE config RANDOMIZE_BASE bool "Randomize the address of the kernel image" - select ARM64_MODULE_PLTS + select ARM64_MODULE_PLTS if MODULES select RELOCATABLE help Randomizes the virtual address at which the kernel image is diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 648a32c89541..d59b6908a21a 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -12,7 +12,6 @@ LDFLAGS_vmlinux :=-p --no-undefined -X CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET) -OBJCOPYFLAGS :=-O binary -R .note -R .note.gnu.build-id -R .comment -S GZFLAGS :=-9 ifneq ($(CONFIG_RELOCATABLE),) @@ -121,6 +120,16 @@ archclean: $(Q)$(MAKE) $(clean)=$(boot) $(Q)$(MAKE) $(clean)=$(boot)/dts +# We need to generate vdso-offsets.h before compiling certain files in kernel/. +# In order to do that, we should use the archprepare target, but we can't since +# asm-offsets.h is included in some files used to generate vdso-offsets.h, and +# asm-offsets.h is built in prepare0, for which archprepare is a dependency. +# Therefore we need to generate the header after prepare0 has been made, hence +# this hack. +prepare: vdso_prepare +vdso_prepare: prepare0 + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso include/generated/vdso-offsets.h + define archhelp echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)' echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)' diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index 305c552b5ec1..1f012c506434 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -14,6 +14,8 @@ # Based on the ia64 boot/Makefile. # +OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S + targets := Image Image.gz $(obj)/Image: vmlinux FORCE diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index fd2d74d0491e..4ed4756dfa97 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -70,6 +70,7 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y CONFIG_XEN=y +CONFIG_KEXEC=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_COMPAT=y CONFIG_CPU_IDLE=y diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index cff532a6744e..f43d2c44c765 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -1,6 +1,5 @@ generic-y += bug.h generic-y += bugs.h -generic-y += checksum.h generic-y += clkdev.h generic-y += cputime.h generic-y += current.h diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index beccbdefa106..8746ff6abd77 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -95,13 +95,11 @@ void apply_alternatives(void *start, size_t length); * The code that follows this macro will be assembled and linked as * normal. There are no restrictions on this code. */ -.macro alternative_if_not cap, enable = 1 - .if \enable +.macro alternative_if_not cap .pushsection .altinstructions, "a" altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f .popsection 661: - .endif .endm /* @@ -118,27 +116,27 @@ void apply_alternatives(void *start, size_t length); * alternative sequence it is defined in (branches into an * alternative sequence are not fixed up). */ -.macro alternative_else, enable = 1 - .if \enable +.macro alternative_else 662: .pushsection .altinstr_replacement, "ax" 663: - .endif .endm /* * Complete an alternative code sequence. */ -.macro alternative_endif, enable = 1 - .if \enable +.macro alternative_endif 664: .popsection .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) - .endif .endm #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) +.macro user_alt, label, oldinstr, newinstr, cond +9999: alternative_insn "\oldinstr", "\newinstr", \cond + _ASM_EXTABLE 9999b, \label +.endm /* * Generate the assembly for UAO alternatives with exception table entries. diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 10b017c4bdd8..d5025c69ca81 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -24,6 +24,7 @@ #define __ASM_ASSEMBLER_H #include <asm/asm-offsets.h> +#include <asm/cpufeature.h> #include <asm/page.h> #include <asm/pgtable-hwdef.h> #include <asm/ptrace.h> @@ -261,7 +262,16 @@ lr .req x30 // link register add \size, \kaddr, \size sub \tmp2, \tmp1, #1 bic \kaddr, \kaddr, \tmp2 -9998: dc \op, \kaddr +9998: + .if (\op == cvau || \op == cvac) +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc \op, \kaddr +alternative_else + dc civac, \kaddr +alternative_endif + .else + dc \op, \kaddr + .endif add \kaddr, \kaddr, \tmp1 cmp \kaddr, \size b.lo 9998b diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h new file mode 100644 index 000000000000..09f65339d66d --- /dev/null +++ b/arch/arm64/include/asm/checksum.h @@ -0,0 +1,51 @@ +/* + * Copyright (C) 2016 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_CHECKSUM_H +#define __ASM_CHECKSUM_H + +#include <linux/types.h> + +static inline __sum16 csum_fold(__wsum csum) +{ + u32 sum = (__force u32)csum; + sum += (sum >> 16) | (sum << 16); + return ~(__force __sum16)(sum >> 16); +} +#define csum_fold csum_fold + +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + __uint128_t tmp; + u64 sum; + + tmp = *(const __uint128_t *)iph; + iph += 16; + ihl -= 4; + tmp += ((tmp >> 64) | (tmp << 64)); + sum = tmp >> 64; + do { + sum += *(const u32 *)iph; + iph += 4; + } while (--ihl); + + sum += ((sum >> 32) | (sum << 32)); + return csum_fold(sum >> 32); +} +#define ip_fast_csum ip_fast_csum + +#include <asm-generic/checksum.h> + +#endif /* __ASM_CHECKSUM_H */ diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index 13a6103130cd..889226b4c6e1 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -25,10 +25,12 @@ */ struct cpuinfo_arm64 { struct cpu cpu; + struct kobject kobj; u32 reg_ctr; u32 reg_cntfrq; u32 reg_dczid; u32 reg_midr; + u32 reg_revidr; u64 reg_id_aa64dfr0; u64 reg_id_aa64dfr1; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 224efe730e46..49dd1bd3ea50 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -191,7 +191,9 @@ void __init setup_cpu_features(void); void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, const char *info); +void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps); void check_local_cpu_errata(void); +void __init enable_errata_workarounds(void); void verify_local_cpu_errata(void); void verify_local_cpu_capabilities(void); diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h index 2fcb9b7c876c..4b6b3f72a215 100644 --- a/arch/arm64/include/asm/debug-monitors.h +++ b/arch/arm64/include/asm/debug-monitors.h @@ -66,6 +66,11 @@ #define CACHE_FLUSH_IS_SAFE 1 +/* kprobes BRK opcodes with ESR encoding */ +#define BRK64_ESR_MASK 0xFFFF +#define BRK64_ESR_KPROBES 0x0004 +#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5)) + /* AArch32 */ #define DBG_ESR_EVT_BKPT 0x4 #define DBG_ESR_EVT_VECC 0x5 diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index bd887663689b..a9e54aad15ef 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,8 +14,7 @@ extern void efi_init(void); #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); - -#define efi_set_mapping_permissions efi_create_mapping +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); #define arch_efi_call_virt_setup() \ ({ \ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 77eeb2cc648f..f772e15c4766 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -74,6 +74,7 @@ #define ESR_ELx_EC_SHIFT (26) #define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT) +#define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT) #define ESR_ELx_IL (UL(1) << 25) #define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 30e50eb54a67..1dbaa901d7e5 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -120,6 +120,29 @@ enum aarch64_insn_register { AARCH64_INSN_REG_SP = 31 /* Stack pointer: as load/store base reg */ }; +enum aarch64_insn_special_register { + AARCH64_INSN_SPCLREG_SPSR_EL1 = 0xC200, + AARCH64_INSN_SPCLREG_ELR_EL1 = 0xC201, + AARCH64_INSN_SPCLREG_SP_EL0 = 0xC208, + AARCH64_INSN_SPCLREG_SPSEL = 0xC210, + AARCH64_INSN_SPCLREG_CURRENTEL = 0xC212, + AARCH64_INSN_SPCLREG_DAIF = 0xDA11, + AARCH64_INSN_SPCLREG_NZCV = 0xDA10, + AARCH64_INSN_SPCLREG_FPCR = 0xDA20, + AARCH64_INSN_SPCLREG_DSPSR_EL0 = 0xDA28, + AARCH64_INSN_SPCLREG_DLR_EL0 = 0xDA29, + AARCH64_INSN_SPCLREG_SPSR_EL2 = 0xE200, + AARCH64_INSN_SPCLREG_ELR_EL2 = 0xE201, + AARCH64_INSN_SPCLREG_SP_EL1 = 0xE208, + AARCH64_INSN_SPCLREG_SPSR_INQ = 0xE218, + AARCH64_INSN_SPCLREG_SPSR_ABT = 0xE219, + AARCH64_INSN_SPCLREG_SPSR_UND = 0xE21A, + AARCH64_INSN_SPCLREG_SPSR_FIQ = 0xE21B, + AARCH64_INSN_SPCLREG_SPSR_EL3 = 0xF200, + AARCH64_INSN_SPCLREG_ELR_EL3 = 0xF201, + AARCH64_INSN_SPCLREG_SP_EL2 = 0xF210 +}; + enum aarch64_insn_variant { AARCH64_INSN_VARIANT_32BIT, AARCH64_INSN_VARIANT_64BIT @@ -223,8 +246,15 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ { return (val); } +__AARCH64_INSN_FUNCS(adr_adrp, 0x1F000000, 0x10000000) +__AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000) __AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800) __AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800) +__AARCH64_INSN_FUNCS(ldr_lit, 0xBF000000, 0x18000000) +__AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) +__AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000) +__AARCH64_INSN_FUNCS(load_ex, 0x3F400000, 0x08400000) +__AARCH64_INSN_FUNCS(store_ex, 0x3F400000, 0x08000000) __AARCH64_INSN_FUNCS(stp_post, 0x7FC00000, 0x28800000) __AARCH64_INSN_FUNCS(ldp_post, 0x7FC00000, 0x28C00000) __AARCH64_INSN_FUNCS(stp_pre, 0x7FC00000, 0x29800000) @@ -273,10 +303,15 @@ __AARCH64_INSN_FUNCS(svc, 0xFFE0001F, 0xD4000001) __AARCH64_INSN_FUNCS(hvc, 0xFFE0001F, 0xD4000002) __AARCH64_INSN_FUNCS(smc, 0xFFE0001F, 0xD4000003) __AARCH64_INSN_FUNCS(brk, 0xFFE0001F, 0xD4200000) +__AARCH64_INSN_FUNCS(exception, 0xFF000000, 0xD4000000) __AARCH64_INSN_FUNCS(hint, 0xFFFFF01F, 0xD503201F) __AARCH64_INSN_FUNCS(br, 0xFFFFFC1F, 0xD61F0000) __AARCH64_INSN_FUNCS(blr, 0xFFFFFC1F, 0xD63F0000) __AARCH64_INSN_FUNCS(ret, 0xFFFFFC1F, 0xD65F0000) +__AARCH64_INSN_FUNCS(eret, 0xFFFFFFFF, 0xD69F03E0) +__AARCH64_INSN_FUNCS(mrs, 0xFFF00000, 0xD5300000) +__AARCH64_INSN_FUNCS(msr_imm, 0xFFF8F01F, 0xD500401F) +__AARCH64_INSN_FUNCS(msr_reg, 0xFFF00000, 0xD5100000) #undef __AARCH64_INSN_FUNCS @@ -286,6 +321,8 @@ bool aarch64_insn_is_branch_imm(u32 insn); int aarch64_insn_read(void *addr, u32 *insnp); int aarch64_insn_write(void *addr, u32 insn); enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn); +bool aarch64_insn_uses_literal(u32 insn); +bool aarch64_insn_is_branch(u32 insn); u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn); u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, u32 insn, u64 imm); @@ -367,9 +404,13 @@ bool aarch32_insn_is_wide(u32 insn); #define A32_RT_OFFSET 12 #define A32_RT2_OFFSET 0 +u32 aarch64_insn_extract_system_reg(u32 insn); u32 aarch32_insn_extract_reg_num(u32 insn, int offset); u32 aarch32_insn_mcr_extract_opc2(u32 insn); u32 aarch32_insn_mcr_extract_crm(u32 insn); + +typedef bool (pstate_check_t)(unsigned long); +extern pstate_check_t * const aarch32_opcode_cond_checks[16]; #endif /* __ASSEMBLY__ */ #endif /* __ASM_INSN_H */ diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index 11cc941bd107..8c581281fa12 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -110,8 +110,5 @@ static inline int arch_irqs_disabled_flags(unsigned long flags) : : "r" (flags) : "memory"); \ } while (0) -#define local_dbg_enable() asm("msr daifclr, #8" : : : "memory") -#define local_dbg_disable() asm("msr daifset, #8" : : : "memory") - #endif #endif diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h new file mode 100644 index 000000000000..04744dc5fb61 --- /dev/null +++ b/arch/arm64/include/asm/kexec.h @@ -0,0 +1,48 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_KEXEC_H +#define _ARM64_KEXEC_H + +/* Maximum physical address we can use pages from */ + +#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) + +/* Maximum address we can reach in physical address mode */ + +#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL) + +/* Maximum address we can use for the control code buffer */ + +#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL) + +#define KEXEC_CONTROL_PAGE_SIZE 4096 + +#define KEXEC_ARCH KEXEC_ARCH_AARCH64 + +#ifndef __ASSEMBLY__ + +/** + * crash_setup_regs() - save registers for the panic kernel + * + * @newregs: registers are saved here + * @oldregs: registers to be saved (may be %NULL) + */ + +static inline void crash_setup_regs(struct pt_regs *newregs, + struct pt_regs *oldregs) +{ + /* Empty routine needed to avoid build errors. */ +} + +#endif /* __ASSEMBLY__ */ + +#endif diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h new file mode 100644 index 000000000000..61b49150dfa3 --- /dev/null +++ b/arch/arm64/include/asm/kprobes.h @@ -0,0 +1,62 @@ +/* + * arch/arm64/include/asm/kprobes.h + * + * Copyright (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KPROBES_H +#define _ARM_KPROBES_H + +#include <linux/types.h> +#include <linux/ptrace.h> +#include <linux/percpu.h> + +#define __ARCH_WANT_KPROBES_INSN_SLOT +#define MAX_INSN_SIZE 1 +#define MAX_STACK_SIZE 128 + +#define flush_insn_slot(p) do { } while (0) +#define kretprobe_blacklist_size 0 + +#include <asm/probes.h> + +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* Single step context for kprobe */ +struct kprobe_step_ctx { + unsigned long ss_pending; + unsigned long match_addr; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + unsigned long saved_irqflag; + struct prev_kprobe prev_kprobe; + struct kprobe_step_ctx ss_ctx; + struct pt_regs jprobe_saved_regs; + char jprobes_stack[MAX_STACK_SIZE]; +}; + +void arch_remove_kprobe(struct kprobe *); +int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr); +int kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data); +int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr); +int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr); +void kretprobe_trampoline(void); +void __kprobes *trampoline_probe_handler(struct pt_regs *regs); + +#endif /* _ARM_KPROBES_H */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 40bc1681b6d5..4cdeae3b17c6 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -210,7 +210,7 @@ static inline bool kvm_vcpu_trap_il_is32bit(const struct kvm_vcpu *vcpu) static inline u8 kvm_vcpu_trap_get_class(const struct kvm_vcpu *vcpu) { - return kvm_vcpu_get_hsr(vcpu) >> ESR_ELx_EC_SHIFT; + return ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu)); } static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 97b1d8f26b9c..8d9fce037b2f 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -34,7 +34,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void init_mem_pgprot(void); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot); + pgprot_t prot, bool allow_block_mappings); extern void *fixmap_remap_fdt(phys_addr_t dt_phys); #endif diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h new file mode 100644 index 000000000000..5af574d632fa --- /dev/null +++ b/arch/arm64/include/asm/probes.h @@ -0,0 +1,35 @@ +/* + * arch/arm64/include/asm/probes.h + * + * Copyright (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ +#ifndef _ARM_PROBES_H +#define _ARM_PROBES_H + +#include <asm/opcodes.h> + +struct kprobe; +struct arch_specific_insn; + +typedef u32 kprobe_opcode_t; +typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *); + +/* architecture specific copy of original instruction */ +struct arch_specific_insn { + kprobe_opcode_t *insn; + pstate_check_t *pstate_cc; + kprobes_handler_t *handler; + /* restore address after step xol */ + unsigned long restore; +}; + +#endif diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index cef1cf398356..ace0a96e7d6e 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -192,5 +192,6 @@ static inline void spin_lock_prefetch(const void *ptr) void cpu_enable_pan(void *__unused); void cpu_enable_uao(void *__unused); +void cpu_enable_cache_maint_trap(void *__unused); #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/ptdump.h b/arch/arm64/include/asm/ptdump.h new file mode 100644 index 000000000000..07b8ed037dee --- /dev/null +++ b/arch/arm64/include/asm/ptdump.h @@ -0,0 +1,44 @@ +/* + * Copyright (C) 2014 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +#ifndef __ASM_PTDUMP_H +#define __ASM_PTDUMP_H + +#ifdef CONFIG_ARM64_PTDUMP + +#include <linux/mm_types.h> + +struct addr_marker { + unsigned long start_address; + char *name; +}; + +struct ptdump_info { + struct mm_struct *mm; + const struct addr_marker *markers; + unsigned long base_addr; + unsigned long max_addr; +}; + +int ptdump_register(struct ptdump_info *info, const char *name); + +#else +static inline int ptdump_register(struct ptdump_info *info, const char *name) +{ + return 0; +} +#endif /* CONFIG_ARM64_PTDUMP */ + +#endif /* __ASM_PTDUMP_H */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 7f94755089e2..ada08b5b036d 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -46,7 +46,6 @@ #define COMPAT_PSR_MODE_UND 0x0000001b #define COMPAT_PSR_MODE_SYS 0x0000001f #define COMPAT_PSR_T_BIT 0x00000020 -#define COMPAT_PSR_E_BIT 0x00000200 #define COMPAT_PSR_F_BIT 0x00000040 #define COMPAT_PSR_I_BIT 0x00000080 #define COMPAT_PSR_A_BIT 0x00000100 @@ -74,6 +73,7 @@ #define COMPAT_PT_DATA_ADDR 0x10004 #define COMPAT_PT_TEXT_END_ADDR 0x10008 #ifndef __ASSEMBLY__ +#include <linux/bug.h> /* sizeof(struct user) for AArch32 */ #define COMPAT_USER_SZ 296 @@ -121,6 +121,8 @@ struct pt_regs { u64 unused; // maintain 16 byte alignment }; +#define MAX_REG_OFFSET offsetof(struct pt_regs, pstate) + #define arch_has_single_step() (1) #ifdef CONFIG_COMPAT @@ -146,9 +148,58 @@ struct pt_regs { #define fast_interrupts_enabled(regs) \ (!((regs)->pstate & PSR_F_BIT)) -#define user_stack_pointer(regs) \ +#define GET_USP(regs) \ (!compat_user_mode(regs) ? (regs)->sp : (regs)->compat_sp) +#define SET_USP(ptregs, value) \ + (!compat_user_mode(regs) ? ((regs)->sp = value) : ((regs)->compat_sp = value)) + +extern int regs_query_register_offset(const char *name); +extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n); + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset of the register. + * + * regs_get_register returns the value of a register whose offset from @regs. + * The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline u64 regs_get_register(struct pt_regs *regs, unsigned int offset) +{ + u64 val = 0; + + WARN_ON(offset & 7); + + offset >>= 3; + switch (offset) { + case 0 ... 30: + val = regs->regs[offset]; + break; + case offsetof(struct pt_regs, sp) >> 3: + val = regs->sp; + break; + case offsetof(struct pt_regs, pc) >> 3: + val = regs->pc; + break; + case offsetof(struct pt_regs, pstate) >> 3: + val = regs->pstate; + break; + default: + val = 0; + } + + return val; +} + +/* Valid only for Kernel mode traps. */ +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + static inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->regs[0]; @@ -158,8 +209,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs) struct task_struct; int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task); -#define instruction_pointer(regs) ((unsigned long)(regs)->pc) +#define GET_IP(regs) ((unsigned long)(regs)->pc) +#define SET_IP(regs, value) ((regs)->pc = ((u64) (value))) + +#define GET_FP(ptregs) ((unsigned long)(ptregs)->regs[29]) +#define SET_FP(ptregs, value) ((ptregs)->regs[29] = ((u64) (value))) + +#include <asm-generic/ptrace.h> +#undef profile_pc extern unsigned long profile_pc(struct pt_regs *regs); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 751e901c8d37..cc06794b7346 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -98,11 +98,11 @@ SCTLR_ELx_SA | SCTLR_ELx_I) /* SCTLR_EL1 specific flags. */ +#define SCTLR_EL1_UCI (1 << 26) #define SCTLR_EL1_SPAN (1 << 23) #define SCTLR_EL1_SED (1 << 8) #define SCTLR_EL1_CP15BEN (1 << 5) - /* id_aa64isar0 */ #define ID_AA64ISAR0_RDM_SHIFT 28 #define ID_AA64ISAR0_ATOMICS_SHIFT 20 diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 0cc2f29bf9da..9cd03f3e812f 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -34,6 +34,8 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); +void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr); + #ifdef CONFIG_FUNCTION_GRAPH_TRACER static inline int __in_irqentry_text(unsigned long ptr) { diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 9e397a542756..5e834d10b291 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -21,6 +21,7 @@ /* * User space memory access functions */ +#include <linux/kasan-checks.h> #include <linux/string.h> #include <linux/thread_info.h> @@ -256,15 +257,29 @@ do { \ -EFAULT; \ }) -extern unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n); -extern unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n); +extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); +extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n); extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n); extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n); +static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n) +{ + kasan_check_write(to, n); + return __arch_copy_from_user(to, from, n); +} + +static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) +{ + kasan_check_read(from, n); + return __arch_copy_to_user(to, from, n); +} + static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { + kasan_check_write(to, n); + if (access_ok(VERIFY_READ, from, n)) - n = __copy_from_user(to, from, n); + n = __arch_copy_from_user(to, from, n); else /* security hole - plug it */ memset(to, 0, n); return n; @@ -272,8 +287,10 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n) { + kasan_check_read(from, n); + if (access_ok(VERIFY_WRITE, to, n)) - n = __copy_to_user(to, from, n); + n = __arch_copy_to_user(to, from, n); return n; } diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h index de66199673d7..2b9a63771eda 100644 --- a/arch/arm64/include/asm/vdso_datapage.h +++ b/arch/arm64/include/asm/vdso_datapage.h @@ -22,6 +22,8 @@ struct vdso_data { __u64 cs_cycle_last; /* Timebase at clocksource init */ + __u64 raw_time_sec; /* Raw time */ + __u64 raw_time_nsec; __u64 xtime_clock_sec; /* Kernel time */ __u64 xtime_clock_nsec; __u64 xtime_coarse_sec; /* Coarse time */ @@ -29,8 +31,10 @@ struct vdso_data { __u64 wtm_clock_sec; /* Wall to monotonic time */ __u64 wtm_clock_nsec; __u32 tb_seq_count; /* Timebase sequence counter */ - __u32 cs_mult; /* Clocksource multiplier */ - __u32 cs_shift; /* Clocksource shift */ + /* cs_* members must be adjacent and in this order (ldp accesses) */ + __u32 cs_mono_mult; /* NTP-adjusted clocksource multiplier */ + __u32 cs_shift; /* Clocksource shift (mono = raw) */ + __u32 cs_raw_mult; /* Raw clocksource multiplier */ __u32 tz_minuteswest; /* Whacky timezone stuff */ __u32 tz_dsttime; __u32 use_syscall; diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index dcbcf8dcbefb..bbc6a8cf83f1 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -34,6 +34,11 @@ */ #define HVC_SET_VECTORS 1 +/* + * HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine. + */ +#define HVC_SOFT_RESTART 2 + #define BOOT_CPU_MODE_EL1 (0xe11) #define BOOT_CPU_MODE_EL2 (0xe12) diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index a5125c6d1f87..14f7b651c787 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -26,8 +26,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE $(call if_changed,objcopy) arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ - sys_compat.o entry32.o \ - ../../arm/kernel/opcodes.o + sys_compat.o entry32.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o @@ -47,12 +46,10 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o +arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ + cpu-reset.o -obj-y += $(arm64-obj-y) vdso/ +obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) head-y := head.o extra-y += $(head-y) vmlinux.lds - -# vDSO - this must be built first to generate the symbol offsets -$(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h -$(obj)/vdso/vdso-offsets.h: $(obj)/vdso diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 678f30b05a45..78f368039c79 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -27,6 +27,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/arm-smccc.h> +#include <linux/kprobes.h> #include <asm/checksum.h> @@ -34,8 +35,8 @@ EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); /* user mem (segment) */ -EXPORT_SYMBOL(__copy_from_user); -EXPORT_SYMBOL(__copy_to_user); +EXPORT_SYMBOL(__arch_copy_from_user); +EXPORT_SYMBOL(__arch_copy_to_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__copy_in_user); @@ -68,6 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit); #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); +NOKPROBE_SYMBOL(_mcount); #endif /* arm-smccc */ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c37202c0c838..5f72475e2e3b 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -316,28 +316,6 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table) */ #define TYPE_SWPB (1 << 22) -/* - * Set up process info to signal segmentation fault - called on access error. - */ -static void set_segfault(struct pt_regs *regs, unsigned long addr) -{ - siginfo_t info; - - down_read(¤t->mm->mmap_sem); - if (find_vma(current->mm, addr) == NULL) - info.si_code = SEGV_MAPERR; - else - info.si_code = SEGV_ACCERR; - up_read(¤t->mm->mmap_sem); - - info.si_signo = SIGSEGV; - info.si_errno = 0; - info.si_addr = (void *) instruction_pointer(regs); - - pr_debug("SWP{B} emulation: access caused memory abort!\n"); - arm64_notify_die("Illegal memory access", regs, &info, 0); -} - static int emulate_swpX(unsigned int address, unsigned int *data, unsigned int type) { @@ -366,6 +344,21 @@ static int emulate_swpX(unsigned int address, unsigned int *data, return res; } +#define ARM_OPCODE_CONDITION_UNCOND 0xf + +static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr) +{ + u32 cc_bits = opcode >> 28; + + if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) { + if ((*aarch32_opcode_cond_checks[cc_bits])(psr)) + return ARM_OPCODE_CONDTEST_PASS; + else + return ARM_OPCODE_CONDTEST_FAIL; + } + return ARM_OPCODE_CONDTEST_UNCOND; +} + /* * swp_handler logs the id of calling process, dissects the instruction, sanity * checks the memory location, calls emulate_swpX for the actual operation and @@ -380,7 +373,7 @@ static int swp_handler(struct pt_regs *regs, u32 instr) type = instr & TYPE_SWPB; - switch (arm_check_condition(instr, regs->pstate)) { + switch (aarch32_check_condition(instr, regs->pstate)) { case ARM_OPCODE_CONDTEST_PASS: break; case ARM_OPCODE_CONDTEST_FAIL: @@ -430,7 +423,8 @@ ret: return 0; fault: - set_segfault(regs, address); + pr_debug("SWP{B} emulation: access caused memory abort!\n"); + arm64_notify_segfault(regs, address); return 0; } @@ -461,7 +455,7 @@ static int cp15barrier_handler(struct pt_regs *regs, u32 instr) { perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc); - switch (arm_check_condition(instr, regs->pstate)) { + switch (aarch32_check_condition(instr, regs->pstate)) { case ARM_OPCODE_CONDTEST_PASS: break; case ARM_OPCODE_CONDTEST_FAIL: diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 2f4ba774488a..05070b72fc28 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -51,6 +51,17 @@ int main(void) DEFINE(S_X5, offsetof(struct pt_regs, regs[5])); DEFINE(S_X6, offsetof(struct pt_regs, regs[6])); DEFINE(S_X7, offsetof(struct pt_regs, regs[7])); + DEFINE(S_X8, offsetof(struct pt_regs, regs[8])); + DEFINE(S_X10, offsetof(struct pt_regs, regs[10])); + DEFINE(S_X12, offsetof(struct pt_regs, regs[12])); + DEFINE(S_X14, offsetof(struct pt_regs, regs[14])); + DEFINE(S_X16, offsetof(struct pt_regs, regs[16])); + DEFINE(S_X18, offsetof(struct pt_regs, regs[18])); + DEFINE(S_X20, offsetof(struct pt_regs, regs[20])); + DEFINE(S_X22, offsetof(struct pt_regs, regs[22])); + DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); + DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); + DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); #ifdef CONFIG_COMPAT @@ -78,6 +89,7 @@ int main(void) BLANK(); DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE); @@ -85,6 +97,8 @@ int main(void) DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); BLANK(); DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last)); + DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec)); + DEFINE(VDSO_RAW_TIME_NSEC, offsetof(struct vdso_data, raw_time_nsec)); DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec)); DEFINE(VDSO_XTIME_CLK_NSEC, offsetof(struct vdso_data, xtime_clock_nsec)); DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec)); @@ -92,7 +106,8 @@ int main(void) DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec)); DEFINE(VDSO_WTM_CLK_NSEC, offsetof(struct vdso_data, wtm_clock_nsec)); DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count)); - DEFINE(VDSO_CS_MULT, offsetof(struct vdso_data, cs_mult)); + DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult)); + DEFINE(VDSO_CS_RAW_MULT, offsetof(struct vdso_data, cs_raw_mult)); DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift)); DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(VDSO_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S new file mode 100644 index 000000000000..65f42d257414 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.S @@ -0,0 +1,54 @@ +/* + * CPU reset routines + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/sysreg.h> +#include <asm/virt.h> + +.text +.pushsection .idmap.text, "ax" + +/* + * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for + * cpu_soft_restart. + * + * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @entry: Location to jump to for soft reset. + * arg0: First argument passed to @entry. + * arg1: Second argument passed to @entry. + * arg2: Third argument passed to @entry. + * + * Put the CPU into the same state as it would be if it had been reset, and + * branch to what would be the reset vector. It must be executed with the + * flat identity mapping. + */ +ENTRY(__cpu_soft_restart) + /* Clear sctlr_el1 flags. */ + mrs x12, sctlr_el1 + ldr x13, =SCTLR_ELx_FLAGS + bic x12, x12, x13 + msr sctlr_el1, x12 + isb + + cbz x0, 1f // el2_switch? + mov x0, #HVC_SOFT_RESTART + hvc #0 // no return + +1: mov x18, x1 // entry + mov x0, x2 // arg0 + mov x1, x3 // arg1 + mov x2, x4 // arg2 + br x18 +ENDPROC(__cpu_soft_restart) + +.popsection diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h new file mode 100644 index 000000000000..d4e9ecb264f0 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.h @@ -0,0 +1,34 @@ +/* + * CPU reset routines + * + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_CPU_RESET_H +#define _ARM64_CPU_RESET_H + +#include <asm/virt.h> + +void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry, + unsigned long arg0, unsigned long arg1, unsigned long arg2); + +static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, + unsigned long entry, unsigned long arg0, unsigned long arg1, + unsigned long arg2) +{ + typeof(__cpu_soft_restart) *restart; + + el2_switch = el2_switch && !is_kernel_in_hyp_mode() && + is_hyp_mode_available(); + restart = (void *)virt_to_phys(__cpu_soft_restart); + + cpu_install_idmap(); + restart(el2_switch, entry, arg0, arg1, arg2); + unreachable(); +} + +#endif diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index af716b65110d..82b0fc2e637b 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -46,6 +46,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM errata 826319, 827319, 824069", .capability = ARM64_WORKAROUND_CLEAN_CACHE, MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02), + .enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_819472 @@ -54,6 +55,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM errata 819472", .capability = ARM64_WORKAROUND_CLEAN_CACHE, MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01), + .enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_832075 @@ -133,3 +135,8 @@ void check_local_cpu_errata(void) { update_cpu_capabilities(arm64_errata, "enabling workaround for"); } + +void __init enable_errata_workarounds(void) +{ + enable_cpu_capabilities(arm64_errata); +} diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 811773d1c1d0..916d27ad79c1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -913,8 +913,7 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void __init -enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) if (caps->enable && cpus_have_cap(caps->capability)) @@ -1036,6 +1035,7 @@ void __init setup_cpu_features(void) /* Set the CPU feature capabilies */ setup_feature_capabilities(); + enable_errata_workarounds(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index c173d329397f..ed1b84fe6925 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -183,6 +183,123 @@ const struct seq_operations cpuinfo_op = { .show = c_show }; + +static struct kobj_type cpuregs_kobj_type = { + .sysfs_ops = &kobj_sysfs_ops, +}; + +/* + * The ARM ARM uses the phrase "32-bit register" to describe a register + * whose upper 32 bits are RES0 (per C5.1.1, ARM DDI 0487A.i), however + * no statement is made as to whether the upper 32 bits will or will not + * be made use of in future, and between ARM DDI 0487A.c and ARM DDI + * 0487A.d CLIDR_EL1 was expanded from 32-bit to 64-bit. + * + * Thus, while both MIDR_EL1 and REVIDR_EL1 are described as 32-bit + * registers, we expose them both as 64 bit values to cater for possible + * future expansion without an ABI break. + */ +#define kobj_to_cpuinfo(kobj) container_of(kobj, struct cpuinfo_arm64, kobj) +#define CPUREGS_ATTR_RO(_name, _field) \ + static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + struct cpuinfo_arm64 *info = kobj_to_cpuinfo(kobj); \ + \ + if (info->reg_midr) \ + return sprintf(buf, "0x%016x\n", info->reg_##_field); \ + else \ + return 0; \ + } \ + static struct kobj_attribute cpuregs_attr_##_name = __ATTR_RO(_name) + +CPUREGS_ATTR_RO(midr_el1, midr); +CPUREGS_ATTR_RO(revidr_el1, revidr); + +static struct attribute *cpuregs_id_attrs[] = { + &cpuregs_attr_midr_el1.attr, + &cpuregs_attr_revidr_el1.attr, + NULL +}; + +static struct attribute_group cpuregs_attr_group = { + .attrs = cpuregs_id_attrs, + .name = "identification" +}; + +static int cpuid_add_regs(int cpu) +{ + int rc; + struct device *dev; + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + dev = get_cpu_device(cpu); + if (!dev) { + rc = -ENODEV; + goto out; + } + rc = kobject_add(&info->kobj, &dev->kobj, "regs"); + if (rc) + goto out; + rc = sysfs_create_group(&info->kobj, &cpuregs_attr_group); + if (rc) + kobject_del(&info->kobj); +out: + return rc; +} + +static int cpuid_remove_regs(int cpu) +{ + struct device *dev; + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + dev = get_cpu_device(cpu); + if (!dev) + return -ENODEV; + if (info->kobj.parent) { + sysfs_remove_group(&info->kobj, &cpuregs_attr_group); + kobject_del(&info->kobj); + } + + return 0; +} + +static int cpuid_callback(struct notifier_block *nb, + unsigned long action, void *hcpu) +{ + int rc = 0; + unsigned long cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + rc = cpuid_add_regs(cpu); + break; + case CPU_DEAD: + rc = cpuid_remove_regs(cpu); + break; + } + + return notifier_from_errno(rc); +} + +static int __init cpuinfo_regs_init(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_possible_cpu(cpu) { + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + kobject_init(&info->kobj, &cpuregs_kobj_type); + if (cpu_online(cpu)) + cpuid_add_regs(cpu); + } + __hotcpu_notifier(cpuid_callback, 0); + + cpu_notifier_register_done(); + return 0; +} static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) { unsigned int cpu = smp_processor_id(); @@ -212,6 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_ctr = read_cpuid_cachetype(); info->reg_dczid = read_cpuid(DCZID_EL0); info->reg_midr = read_cpuid_id(); + info->reg_revidr = read_cpuid(REVIDR_EL1); info->reg_id_aa64dfr0 = read_cpuid(ID_AA64DFR0_EL1); info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1); @@ -264,3 +382,5 @@ void __init cpuinfo_store_boot_cpu(void) boot_cpu_data = *info; init_cpu_features(&boot_cpu_data); } + +device_initcall(cpuinfo_regs_init); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 4fbf3c54275c..91fff48d0f57 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -23,6 +23,7 @@ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/ptrace.h> +#include <linux/kprobes.h> #include <linux/stat.h> #include <linux/uaccess.h> @@ -48,6 +49,7 @@ static void mdscr_write(u32 mdscr) asm volatile("msr mdscr_el1, %0" :: "r" (mdscr)); local_dbg_restore(flags); } +NOKPROBE_SYMBOL(mdscr_write); static u32 mdscr_read(void) { @@ -55,6 +57,7 @@ static u32 mdscr_read(void) asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr)); return mdscr; } +NOKPROBE_SYMBOL(mdscr_read); /* * Allow root to disable self-hosted debug from userspace. @@ -103,6 +106,7 @@ void enable_debug_monitors(enum dbg_active_el el) mdscr_write(mdscr); } } +NOKPROBE_SYMBOL(enable_debug_monitors); void disable_debug_monitors(enum dbg_active_el el) { @@ -123,6 +127,7 @@ void disable_debug_monitors(enum dbg_active_el el) mdscr_write(mdscr); } } +NOKPROBE_SYMBOL(disable_debug_monitors); /* * OS lock clearing. @@ -151,7 +156,6 @@ static int debug_monitors_init(void) /* Clear the OS lock. */ on_each_cpu(clear_os_lock, NULL, 1); isb(); - local_dbg_enable(); /* Register hotplug handler. */ __register_cpu_notifier(&os_lock_nb); @@ -166,22 +170,15 @@ postcore_initcall(debug_monitors_init); */ static void set_regs_spsr_ss(struct pt_regs *regs) { - unsigned long spsr; - - spsr = regs->pstate; - spsr &= ~DBG_SPSR_SS; - spsr |= DBG_SPSR_SS; - regs->pstate = spsr; + regs->pstate |= DBG_SPSR_SS; } +NOKPROBE_SYMBOL(set_regs_spsr_ss); static void clear_regs_spsr_ss(struct pt_regs *regs) { - unsigned long spsr; - - spsr = regs->pstate; - spsr &= ~DBG_SPSR_SS; - regs->pstate = spsr; + regs->pstate &= ~DBG_SPSR_SS; } +NOKPROBE_SYMBOL(clear_regs_spsr_ss); /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); @@ -225,6 +222,7 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) return retval; } +NOKPROBE_SYMBOL(call_step_hook); static void send_user_sigtrap(int si_code) { @@ -266,6 +264,10 @@ static int single_step_handler(unsigned long addr, unsigned int esr, */ user_rewind_single_step(current); } else { +#ifdef CONFIG_KPROBES + if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED) + return 0; +#endif if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED) return 0; @@ -279,6 +281,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr, return 0; } +NOKPROBE_SYMBOL(single_step_handler); /* * Breakpoint handler is re-entrant as another breakpoint can @@ -316,19 +319,28 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } +NOKPROBE_SYMBOL(call_break_hook); static int brk_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { if (user_mode(regs)) { send_user_sigtrap(TRAP_BRKPT); - } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { - pr_warning("Unexpected kernel BRK exception at EL1\n"); + } +#ifdef CONFIG_KPROBES + else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) { + if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED) + return -EFAULT; + } +#endif + else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { + pr_warn("Unexpected kernel BRK exception at EL1\n"); return -EFAULT; } return 0; } +NOKPROBE_SYMBOL(brk_handler); int aarch32_break_handler(struct pt_regs *regs) { @@ -365,6 +377,7 @@ int aarch32_break_handler(struct pt_regs *regs) send_user_sigtrap(TRAP_BRKPT); return 0; } +NOKPROBE_SYMBOL(aarch32_break_handler); static int __init debug_traps_init(void) { @@ -386,6 +399,7 @@ void user_rewind_single_step(struct task_struct *task) if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } +NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { @@ -401,6 +415,7 @@ void kernel_enable_single_step(struct pt_regs *regs) mdscr_write(mdscr_read() | DBG_MDSCR_SS); enable_debug_monitors(DBG_ACTIVE_EL1); } +NOKPROBE_SYMBOL(kernel_enable_single_step); void kernel_disable_single_step(void) { @@ -408,12 +423,14 @@ void kernel_disable_single_step(void) mdscr_write(mdscr_read() & ~DBG_MDSCR_SS); disable_debug_monitors(DBG_ACTIVE_EL1); } +NOKPROBE_SYMBOL(kernel_disable_single_step); int kernel_active_single_step(void) { WARN_ON(!irqs_disabled()); return mdscr_read() & DBG_MDSCR_SS; } +NOKPROBE_SYMBOL(kernel_active_single_step); /* ptrace API */ void user_enable_single_step(struct task_struct *task) @@ -421,8 +438,10 @@ void user_enable_single_step(struct task_struct *task) set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); set_regs_spsr_ss(task_pt_regs(task)); } +NOKPROBE_SYMBOL(user_enable_single_step); void user_disable_single_step(struct task_struct *task) { clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); } +NOKPROBE_SYMBOL(user_disable_single_step); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 78f52488f9ff..ba9bee389fd5 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -62,13 +62,61 @@ struct screen_info screen_info __section(.data); int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { pteval_t prot_val = create_mapping_protection(md); + bool allow_block_mappings = (md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + if (!PAGE_ALIGNED(md->phys_addr) || + !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) { + /* + * If the end address of this region is not aligned to page + * size, the mapping is rounded up, and may end up sharing a + * page frame with the next UEFI memory region. If we create + * a block entry now, we may need to split it again when mapping + * the next region, and support for that is going to be removed + * from the MMU routines. So avoid block mappings altogether in + * that case. + */ + allow_block_mappings = false; + } create_pgd_mapping(mm, md->phys_addr, md->virt_addr, md->num_pages << EFI_PAGE_SHIFT, - __pgprot(prot_val | PTE_NG)); + __pgprot(prot_val | PTE_NG), allow_block_mappings); + return 0; +} + +static int __init set_permissions(pte_t *ptep, pgtable_t token, + unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = *ptep; + + if (md->attribute & EFI_MEMORY_RO) + pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); + if (md->attribute & EFI_MEMORY_XP) + pte = set_pte_bit(pte, __pgprot(PTE_PXN)); + set_pte(ptep, pte); return 0; } +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md) +{ + BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + /* + * Calling apply_to_page_range() is only safe on regions that are + * guaranteed to be mapped down to pages. Since we are only called + * for regions that have been mapped using efi_create_mapping() above + * (and this is checked by the generic Memory Attributes table parsing + * routines), there is no need to check that again here. + */ + return apply_to_page_range(mm, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + set_permissions, md); +} + static int __init arm64_dmi_init(void) { /* diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 6c3b7345a6c4..96e4a2b64cc1 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -258,6 +258,7 @@ tsk .req x28 // current thread_info /* * Exception vectors. */ + .pushsection ".entry.text", "ax" .align 11 ENTRY(vectors) @@ -466,7 +467,7 @@ el0_sync: cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el0_undef + b.eq el0_sys cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception b.eq el0_sp_pc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception @@ -547,7 +548,7 @@ el0_ia: enable_dbg_and_irq ct_user_exit mov x0, x26 - orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts + mov x1, x25 mov x2, sp bl do_mem_abort b ret_to_user @@ -594,6 +595,16 @@ el0_undef: mov x0, sp bl do_undefinstr b ret_to_user +el0_sys: + /* + * System instructions, for trapped cache maintenance instructions + */ + enable_dbg_and_irq + ct_user_exit + mov x0, x25 + mov x1, sp + bl do_sysinstr + b ret_to_user el0_dbg: /* * Debug exception handling @@ -789,6 +800,8 @@ __ni_sys_trace: bl do_ni_syscall b __sys_trace_return + .popsection // .entry.text + /* * Special system call wrappers. */ diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index ce21aa88263f..26a6bf77d272 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -24,6 +24,7 @@ #include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/hw_breakpoint.h> +#include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/smp.h> @@ -127,6 +128,7 @@ static u64 read_wb_reg(int reg, int n) return val; } +NOKPROBE_SYMBOL(read_wb_reg); static void write_wb_reg(int reg, int n, u64 val) { @@ -140,6 +142,7 @@ static void write_wb_reg(int reg, int n, u64 val) } isb(); } +NOKPROBE_SYMBOL(write_wb_reg); /* * Convert a breakpoint privilege level to the corresponding exception @@ -157,6 +160,7 @@ static enum dbg_active_el debug_exception_level(int privilege) return -EINVAL; } } +NOKPROBE_SYMBOL(debug_exception_level); enum hw_breakpoint_ops { HW_BREAKPOINT_INSTALL, @@ -575,6 +579,7 @@ static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable) write_wb_reg(reg, i, ctrl); } } +NOKPROBE_SYMBOL(toggle_bp_registers); /* * Debug exception handlers. @@ -654,6 +659,7 @@ unlock: return 0; } +NOKPROBE_SYMBOL(breakpoint_handler); static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) @@ -756,6 +762,7 @@ unlock: return 0; } +NOKPROBE_SYMBOL(watchpoint_handler); /* * Handle single-step exception. @@ -813,6 +820,7 @@ int reinstall_suspended_bps(struct pt_regs *regs) return !handled_exception; } +NOKPROBE_SYMBOL(reinstall_suspended_bps); /* * Context-switcher for restoring suspended breakpoints. diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 8727f4490772..d3b5f75e652e 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -71,8 +71,16 @@ el1_sync: msr vbar_el2, x1 b 9f +2: cmp x0, #HVC_SOFT_RESTART + b.ne 3f + mov x0, x2 + mov x2, x4 + mov x4, x1 + mov x1, x3 + br x4 // no return + /* Someone called kvm_call_hyp() against the hyp-stub... */ -2: mov x0, #ARM_EXCEPTION_HYP_GONE +3: mov x0, #ARM_EXCEPTION_HYP_GONE 9: eret ENDPROC(el1_sync) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 368c08290dd8..63f9432d05e8 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -30,6 +30,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/fixmap.h> +#include <asm/opcodes.h> #include <asm/insn.h> #define AARCH64_INSN_SF_BIT BIT(31) @@ -162,6 +163,32 @@ static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn) aarch64_insn_is_nop(insn); } +bool __kprobes aarch64_insn_uses_literal(u32 insn) +{ + /* ldr/ldrsw (literal), prfm */ + + return aarch64_insn_is_ldr_lit(insn) || + aarch64_insn_is_ldrsw_lit(insn) || + aarch64_insn_is_adr_adrp(insn) || + aarch64_insn_is_prfm_lit(insn); +} + +bool __kprobes aarch64_insn_is_branch(u32 insn) +{ + /* b, bl, cb*, tb*, b.cond, br, blr */ + + return aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn) || + aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn) || + aarch64_insn_is_ret(insn) || + aarch64_insn_is_br(insn) || + aarch64_insn_is_blr(insn) || + aarch64_insn_is_bcond(insn); +} + /* * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a * Section B2.6.5 "Concurrent modification and execution of instructions": @@ -1175,6 +1202,14 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset) BUG(); } +/* + * Extract the Op/CR data from a msr/mrs instruction. + */ +u32 aarch64_insn_extract_system_reg(u32 insn) +{ + return (insn & 0x1FFFE0) >> 5; +} + bool aarch32_insn_is_wide(u32 insn) { return insn >= 0xe800; @@ -1200,3 +1235,101 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn) { return insn & CRM_MASK; } + +static bool __kprobes __check_eq(unsigned long pstate) +{ + return (pstate & PSR_Z_BIT) != 0; +} + +static bool __kprobes __check_ne(unsigned long pstate) +{ + return (pstate & PSR_Z_BIT) == 0; +} + +static bool __kprobes __check_cs(unsigned long pstate) +{ + return (pstate & PSR_C_BIT) != 0; +} + +static bool __kprobes __check_cc(unsigned long pstate) +{ + return (pstate & PSR_C_BIT) == 0; +} + +static bool __kprobes __check_mi(unsigned long pstate) +{ + return (pstate & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_pl(unsigned long pstate) +{ + return (pstate & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_vs(unsigned long pstate) +{ + return (pstate & PSR_V_BIT) != 0; +} + +static bool __kprobes __check_vc(unsigned long pstate) +{ + return (pstate & PSR_V_BIT) == 0; +} + +static bool __kprobes __check_hi(unsigned long pstate) +{ + pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (pstate & PSR_C_BIT) != 0; +} + +static bool __kprobes __check_ls(unsigned long pstate) +{ + pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (pstate & PSR_C_BIT) == 0; +} + +static bool __kprobes __check_ge(unsigned long pstate) +{ + pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (pstate & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_lt(unsigned long pstate) +{ + pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (pstate & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_gt(unsigned long pstate) +{ + /*PSR_N_BIT ^= PSR_V_BIT */ + unsigned long temp = pstate ^ (pstate << 3); + + temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ + return (temp & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_le(unsigned long pstate) +{ + /*PSR_N_BIT ^= PSR_V_BIT */ + unsigned long temp = pstate ^ (pstate << 3); + + temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ + return (temp & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_al(unsigned long pstate) +{ + return true; +} + +/* + * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that + * it behaves identically to 0b1110 ("al"). + */ +pstate_check_t * const aarch32_opcode_cond_checks[16] = { + __check_eq, __check_ne, __check_cs, __check_cc, + __check_mi, __check_pl, __check_vs, __check_vc, + __check_hi, __check_ls, __check_ge, __check_lt, + __check_gt, __check_le, __check_al, __check_al +}; diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index b5f063e5eff7..8c57f6496e56 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -22,6 +22,7 @@ #include <linux/irq.h> #include <linux/kdebug.h> #include <linux/kgdb.h> +#include <linux/kprobes.h> #include <asm/traps.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { @@ -230,6 +231,7 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr) kgdb_handle_exception(1, SIGTRAP, 0, regs); return 0; } +NOKPROBE_SYMBOL(kgdb_brk_fn) static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) { @@ -238,12 +240,14 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) return 0; } +NOKPROBE_SYMBOL(kgdb_compiled_brk_fn); static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) { kgdb_handle_exception(1, SIGTRAP, 0, regs); return 0; } +NOKPROBE_SYMBOL(kgdb_step_brk_fn); static struct break_hook kgdb_brkpt_hook = { .esr_mask = 0xffffffff, diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c new file mode 100644 index 000000000000..bc96c8a7fc79 --- /dev/null +++ b/arch/arm64/kernel/machine_kexec.c @@ -0,0 +1,212 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/smp.h> + +#include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/mmu_context.h> + +#include "cpu-reset.h" + +/* Global variables for the arm64_relocate_new_kernel routine. */ +extern const unsigned char arm64_relocate_new_kernel[]; +extern const unsigned long arm64_relocate_new_kernel_size; + +static unsigned long kimage_start; + +/** + * kexec_image_info - For debugging output. + */ +#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i) +static void _kexec_image_info(const char *func, int line, + const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:%d:\n", func, line); + pr_debug(" kexec kimage info:\n"); + pr_debug(" type: %d\n", kimage->type); + pr_debug(" start: %lx\n", kimage->start); + pr_debug(" head: %lx\n", kimage->head); + pr_debug(" nr_segments: %lu\n", kimage->nr_segments); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + } +} + +void machine_kexec_cleanup(struct kimage *kimage) +{ + /* Empty routine needed to avoid build errors. */ +} + +/** + * machine_kexec_prepare - Prepare for a kexec reboot. + * + * Called from the core kexec code when a kernel image is loaded. + * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus + * are stuck in the kernel. This avoids a panic once we hit machine_kexec(). + */ +int machine_kexec_prepare(struct kimage *kimage) +{ + kimage_start = kimage->start; + + kexec_image_info(kimage); + + if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) { + pr_err("Can't kexec: CPUs are stuck in the kernel.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * kexec_list_flush - Helper to flush the kimage list and source pages to PoC. + */ +static void kexec_list_flush(struct kimage *kimage) +{ + kimage_entry_t *entry; + + for (entry = &kimage->head; ; entry++) { + unsigned int flag; + void *addr; + + /* flush the list entries. */ + __flush_dcache_area(entry, sizeof(kimage_entry_t)); + + flag = *entry & IND_FLAGS; + if (flag == IND_DONE) + break; + + addr = phys_to_virt(*entry & PAGE_MASK); + + switch (flag) { + case IND_INDIRECTION: + /* Set entry point just before the new list page. */ + entry = (kimage_entry_t *)addr - 1; + break; + case IND_SOURCE: + /* flush the source pages. */ + __flush_dcache_area(addr, PAGE_SIZE); + break; + case IND_DESTINATION: + break; + default: + BUG(); + } + } +} + +/** + * kexec_segment_flush - Helper to flush the kimage segments to PoC. + */ +static void kexec_segment_flush(const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:\n", __func__); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + + __flush_dcache_area(phys_to_virt(kimage->segment[i].mem), + kimage->segment[i].memsz); + } +} + +/** + * machine_kexec - Do the kexec reboot. + * + * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC. + */ +void machine_kexec(struct kimage *kimage) +{ + phys_addr_t reboot_code_buffer_phys; + void *reboot_code_buffer; + + /* + * New cpus may have become stuck_in_kernel after we loaded the image. + */ + BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1)); + + reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); + reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys); + + kexec_image_info(kimage); + + pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, + kimage->control_code_page); + pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, + &reboot_code_buffer_phys); + pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, + reboot_code_buffer); + pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, + arm64_relocate_new_kernel); + pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", + __func__, __LINE__, arm64_relocate_new_kernel_size, + arm64_relocate_new_kernel_size); + + /* + * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use + * after the kernel is shut down. + */ + memcpy(reboot_code_buffer, arm64_relocate_new_kernel, + arm64_relocate_new_kernel_size); + + /* Flush the reboot_code_buffer in preparation for its execution. */ + __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); + flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); + + /* Flush the kimage list and its buffers. */ + kexec_list_flush(kimage); + + /* Flush the new image if already in place. */ + if (kimage->head & IND_DONE) + kexec_segment_flush(kimage); + + pr_info("Bye!\n"); + + /* Disable all DAIF exceptions. */ + asm volatile ("msr daifset, #0xf" : : : "memory"); + + /* + * cpu_soft_restart will shutdown the MMU, disable data caches, then + * transfer control to the reboot_code_buffer which contains a copy of + * the arm64_relocate_new_kernel routine. arm64_relocate_new_kernel + * uses physical addressing to relocate the new image to its final + * position and transfers control to the image entry point when the + * relocation is complete. + */ + + cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, + kimage_start, 0); + + BUG(); /* Should never get here. */ +} + +void machine_crash_shutdown(struct pt_regs *regs) +{ + /* Empty routine needed to avoid build errors. */ +} diff --git a/arch/arm64/kernel/probes/Makefile b/arch/arm64/kernel/probes/Makefile new file mode 100644 index 000000000000..ce06312e3d34 --- /dev/null +++ b/arch/arm64/kernel/probes/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o \ + kprobes_trampoline.o \ + simulate-insn.o diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c new file mode 100644 index 000000000000..37e47a9d617e --- /dev/null +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -0,0 +1,174 @@ +/* + * arch/arm64/kernel/probes/decode-insn.c + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <asm/kprobes.h> +#include <asm/insn.h> +#include <asm/sections.h> + +#include "decode-insn.h" +#include "simulate-insn.h" + +static bool __kprobes aarch64_insn_is_steppable(u32 insn) +{ + /* + * Branch instructions will write a new value into the PC which is + * likely to be relative to the XOL address and therefore invalid. + * Deliberate generation of an exception during stepping is also not + * currently safe. Lastly, MSR instructions can do any number of nasty + * things we can't handle during single-stepping. + */ + if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) { + if (aarch64_insn_is_branch(insn) || + aarch64_insn_is_msr_imm(insn) || + aarch64_insn_is_msr_reg(insn) || + aarch64_insn_is_exception(insn) || + aarch64_insn_is_eret(insn)) + return false; + + /* + * The MRS instruction may not return a correct value when + * executing in the single-stepping environment. We do make one + * exception, for reading the DAIF bits. + */ + if (aarch64_insn_is_mrs(insn)) + return aarch64_insn_extract_system_reg(insn) + != AARCH64_INSN_SPCLREG_DAIF; + + /* + * The HINT instruction is is problematic when single-stepping, + * except for the NOP case. + */ + if (aarch64_insn_is_hint(insn)) + return aarch64_insn_is_nop(insn); + + return true; + } + + /* + * Instructions which load PC relative literals are not going to work + * when executed from an XOL slot. Instructions doing an exclusive + * load/store are not going to complete successfully when single-step + * exception handling happens in the middle of the sequence. + */ + if (aarch64_insn_uses_literal(insn) || + aarch64_insn_is_exclusive(insn)) + return false; + + return true; +} + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD If instruction is supported and uses instruction slot, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + */ +static enum kprobe_insn __kprobes +arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* + * Instructions reading or modifying the PC won't work from the XOL + * slot. + */ + if (aarch64_insn_is_steppable(insn)) + return INSN_GOOD; + + if (aarch64_insn_is_bcond(insn)) { + asi->handler = simulate_b_cond; + } else if (aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn)) { + asi->handler = simulate_cbz_cbnz; + } else if (aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn)) { + asi->handler = simulate_tbz_tbnz; + } else if (aarch64_insn_is_adr_adrp(insn)) { + asi->handler = simulate_adr_adrp; + } else if (aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn)) { + asi->handler = simulate_b_bl; + } else if (aarch64_insn_is_br(insn) || + aarch64_insn_is_blr(insn) || + aarch64_insn_is_ret(insn)) { + asi->handler = simulate_br_blr_ret; + } else if (aarch64_insn_is_ldr_lit(insn)) { + asi->handler = simulate_ldr_literal; + } else if (aarch64_insn_is_ldrsw_lit(insn)) { + asi->handler = simulate_ldrsw_literal; + } else { + /* + * Instruction cannot be stepped out-of-line and we don't + * (yet) simulate it. + */ + return INSN_REJECTED; + } + + return INSN_GOOD_NO_SLOT; +} + +static bool __kprobes +is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end) +{ + while (scan_start > scan_end) { + /* + * atomic region starts from exclusive load and ends with + * exclusive store. + */ + if (aarch64_insn_is_store_ex(le32_to_cpu(*scan_start))) + return false; + else if (aarch64_insn_is_load_ex(le32_to_cpu(*scan_start))) + return true; + scan_start--; + } + + return false; +} + +enum kprobe_insn __kprobes +arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) +{ + enum kprobe_insn decoded; + kprobe_opcode_t insn = le32_to_cpu(*addr); + kprobe_opcode_t *scan_start = addr - 1; + kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) + struct module *mod; +#endif + + if (addr >= (kprobe_opcode_t *)_text && + scan_end < (kprobe_opcode_t *)_text) + scan_end = (kprobe_opcode_t *)_text; +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) + else { + preempt_disable(); + mod = __module_address((unsigned long)addr); + if (mod && within_module_init((unsigned long)addr, mod) && + !within_module_init((unsigned long)scan_end, mod)) + scan_end = (kprobe_opcode_t *)mod->init_layout.base; + else if (mod && within_module_core((unsigned long)addr, mod) && + !within_module_core((unsigned long)scan_end, mod)) + scan_end = (kprobe_opcode_t *)mod->core_layout.base; + preempt_enable(); + } +#endif + decoded = arm_probe_decode_insn(insn, asi); + + if (decoded == INSN_REJECTED || + is_probed_address_atomic(scan_start, scan_end)) + return INSN_REJECTED; + + return decoded; +} diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h new file mode 100644 index 000000000000..d438289646a6 --- /dev/null +++ b/arch/arm64/kernel/probes/decode-insn.h @@ -0,0 +1,35 @@ +/* + * arch/arm64/kernel/probes/decode-insn.h + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KERNEL_KPROBES_ARM64_H +#define _ARM_KERNEL_KPROBES_ARM64_H + +/* + * ARM strongly recommends a limit of 128 bytes between LoadExcl and + * StoreExcl instructions in a single thread of execution. So keep the + * max atomic context size as 32. + */ +#define MAX_ATOMIC_CONTEXT_SIZE (128 / sizeof(kprobe_opcode_t)) + +enum kprobe_insn { + INSN_REJECTED, + INSN_GOOD_NO_SLOT, + INSN_GOOD, +}; + +enum kprobe_insn __kprobes +arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi); + +#endif /* _ARM_KERNEL_KPROBES_ARM64_H */ diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c new file mode 100644 index 000000000000..bf9768588288 --- /dev/null +++ b/arch/arm64/kernel/probes/kprobes.c @@ -0,0 +1,686 @@ +/* + * arch/arm64/kernel/probes/kprobes.c + * + * Kprobes support for ARM64 + * + * Copyright (C) 2013 Linaro Limited. + * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ +#include <linux/kasan.h> +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> +#include <linux/stringify.h> +#include <asm/traps.h> +#include <asm/ptrace.h> +#include <asm/cacheflush.h> +#include <asm/debug-monitors.h> +#include <asm/system_misc.h> +#include <asm/insn.h> +#include <asm/uaccess.h> +#include <asm/irq.h> +#include <asm-generic/sections.h> + +#include "decode-insn.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); + +static inline unsigned long min_stack_size(unsigned long addr) +{ + unsigned long size; + + if (on_irq_stack(addr, raw_smp_processor_id())) + size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr; + else + size = (unsigned long)current_thread_info() + THREAD_START_SP - addr; + + return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack)); +} + +static void __kprobes arch_prepare_ss_slot(struct kprobe *p) +{ + /* prepare insn slot */ + p->ainsn.insn[0] = cpu_to_le32(p->opcode); + + flush_icache_range((uintptr_t) (p->ainsn.insn), + (uintptr_t) (p->ainsn.insn) + + MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + + /* + * Needs restoring of return address after stepping xol. + */ + p->ainsn.restore = (unsigned long) p->addr + + sizeof(kprobe_opcode_t); +} + +static void __kprobes arch_prepare_simulate(struct kprobe *p) +{ + /* This instructions is not executed xol. No need to adjust the PC */ + p->ainsn.restore = 0; +} + +static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (p->ainsn.handler) + p->ainsn.handler((u32)p->opcode, (long)p->addr, regs); + + /* single step simulated, now go for post processing */ + post_kprobe_handler(kcb, regs); +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + unsigned long probe_addr = (unsigned long)p->addr; + extern char __start_rodata[]; + extern char __end_rodata[]; + + if (probe_addr & 0x3) + return -EINVAL; + + /* copy instruction */ + p->opcode = le32_to_cpu(*p->addr); + + if (in_exception_text(probe_addr)) + return -EINVAL; + if (probe_addr >= (unsigned long) __start_rodata && + probe_addr <= (unsigned long) __end_rodata) + return -EINVAL; + + /* decode instruction */ + switch (arm_kprobe_decode_insn(p->addr, &p->ainsn)) { + case INSN_REJECTED: /* insn not supported */ + return -EINVAL; + + case INSN_GOOD_NO_SLOT: /* insn need simulation */ + p->ainsn.insn = NULL; + break; + + case INSN_GOOD: /* instruction uses slot */ + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + break; + }; + + /* prepare the instruction */ + if (p->ainsn.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} + +static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) +{ + void *addrs[1]; + u32 insns[1]; + + addrs[0] = (void *)addr; + insns[0] = (u32)opcode; + + return aarch64_insn_patch_text(addrs, insns, 1); +} + +/* arm kprobe: install breakpoint in text */ +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, BRK64_OPCODE_KPROBES); +} + +/* disarm kprobe: remove breakpoint from text */ +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, p->opcode); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static void __kprobes set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} + +/* + * The D-flag (Debug mask) is set (masked) upon debug exception entry. + * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive + * probe i.e. when probe hit from kprobe handler context upon + * executing the pre/post handlers. In this case we return with + * D-flag clear so that single-stepping can be carried-out. + * + * Leave D-flag set in all other cases. + */ +static void __kprobes +spsr_set_debug_flag(struct pt_regs *regs, int mask) +{ + unsigned long spsr = regs->pstate; + + if (mask) + spsr |= PSR_D_BIT; + else + spsr &= ~PSR_D_BIT; + + regs->pstate = spsr; +} + +/* + * Interrupts need to be disabled before single-step mode is set, and not + * reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start of + * out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_irqflag = regs->pstate; + regs->pstate |= PSR_I_BIT; +} + +static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + if (kcb->saved_irqflag & PSR_I_BIT) + regs->pstate |= PSR_I_BIT; + else + regs->pstate &= ~PSR_I_BIT; +} + +static void __kprobes +set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr) +{ + kcb->ss_ctx.ss_pending = true; + kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t); +} + +static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb) +{ + kcb->ss_ctx.ss_pending = false; + kcb->ss_ctx.match_addr = 0; +} + +static void __kprobes setup_singlestep(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + unsigned long slot; + + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + + if (p->ainsn.insn) { + /* prepare for single stepping */ + slot = (unsigned long)p->ainsn.insn; + + set_ss_context(kcb, slot); /* mark pending ss */ + + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 0); + else + WARN_ON(regs->pstate & PSR_D_BIT); + + /* IRQs and single stepping do not mix well. */ + kprobes_save_local_irqflag(kcb, regs); + kernel_enable_single_step(regs); + instruction_pointer_set(regs, slot); + } else { + /* insn simulation */ + arch_simulate_insn(p, regs); + } +} + +static int __kprobes reenter_kprobe(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr); + dump_kprobe(p); + BUG(); + break; + default: + WARN_ON(1); + return 0; + } + + return 1; +} + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + + if (!cur) + return; + + /* return addr restore if non-branching insn */ + if (cur->ainsn.restore != 0) + instruction_pointer_set(regs, cur->ainsn.restore); + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + return; + } + /* call post handler */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) { + /* post_handler can hit breakpoint and single step + * again, so we enable D-flag for recursive exception. + */ + cur->post_handler(cur, regs, 0); + } + + reset_current_kprobe(); +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + instruction_pointer_set(regs, (unsigned long) cur->addr); + if (!instruction_pointer(regs)) + BUG(); + + kernel_disable_single_step(); + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 1); + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, fsr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + } + return 0; +} + +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} + +static void __kprobes kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *p, *cur_kprobe; + struct kprobe_ctlblk *kcb; + unsigned long addr = instruction_pointer(regs); + + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe((kprobe_opcode_t *) addr); + + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it prepped + * for calling the break_handler below on re-entry, + * so get out doing nothing more here. + * + * pre_handler can hit a breakpoint and can step thru + * before return, keep PSTATE D-flag enabled until + * pre_handler return back. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) { + setup_singlestep(p, regs, kcb, 0); + return; + } + } + } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) == + BRK64_OPCODE_KPROBES) && cur_kprobe) { + /* We probably hit a jprobe. Call its break handler. */ + if (cur_kprobe->break_handler && + cur_kprobe->break_handler(cur_kprobe, regs)) { + setup_singlestep(cur_kprobe, regs, kcb, 0); + return; + } + } + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ +} + +static int __kprobes +kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) +{ + if ((kcb->ss_ctx.ss_pending) + && (kcb->ss_ctx.match_addr == addr)) { + clear_ss_context(kcb); /* clear pending ss */ + return DBG_HOOK_HANDLED; + } + /* not ours, kprobes should ignore it */ + return DBG_HOOK_ERROR; +} + +int __kprobes +kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + int retval; + + /* return error if this is not our step */ + retval = kprobe_ss_hit(kcb, instruction_pointer(regs)); + + if (retval == DBG_HOOK_HANDLED) { + kprobes_restore_local_irqflag(kcb, regs); + kernel_disable_single_step(); + + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 1); + + post_kprobe_handler(kcb, regs); + } + + return retval; +} + +int __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) +{ + kprobe_handler(regs); + return DBG_HOOK_HANDLED; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + long stack_ptr = kernel_stack_pointer(regs); + + kcb->jprobe_saved_regs = *regs; + /* + * As Linus pointed out, gcc assumes that the callee + * owns the argument space and could overwrite it, e.g. + * tailcall optimization. So, to be absolutely safe + * we also save and restore enough stack bytes to cover + * the argument area. + */ + kasan_disable_current(); + memcpy(kcb->jprobes_stack, (void *)stack_ptr, + min_stack_size(stack_ptr)); + kasan_enable_current(); + + instruction_pointer_set(regs, (unsigned long) jp->entry); + preempt_disable(); + pause_graph_tracing(); + return 1; +} + +void __kprobes jprobe_return(void) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + /* + * Jprobe handler return by entering break exception, + * encoded same as kprobe, but with following conditions + * -a special PC to identify it from the other kprobes. + * -restore stack addr to original saved pt_regs + */ + asm volatile(" mov sp, %0 \n" + "jprobe_return_break: brk %1 \n" + : + : "r" (kcb->jprobe_saved_regs.sp), + "I" (BRK64_ESR_KPROBES) + : "memory"); + + unreachable(); +} + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + long stack_addr = kcb->jprobe_saved_regs.sp; + long orig_sp = kernel_stack_pointer(regs); + struct jprobe *jp = container_of(p, struct jprobe, kp); + extern const char jprobe_return_break[]; + + if (instruction_pointer(regs) != (u64) jprobe_return_break) + return 0; + + if (orig_sp != stack_addr) { + struct pt_regs *saved_regs = + (struct pt_regs *)kcb->jprobe_saved_regs.sp; + pr_err("current sp %lx does not match saved sp %lx\n", + orig_sp, stack_addr); + pr_err("Saved registers for jprobe %p\n", jp); + show_regs(saved_regs); + pr_err("Current registers\n"); + show_regs(regs); + BUG(); + } + unpause_graph_tracing(); + *regs = kcb->jprobe_saved_regs; + kasan_disable_current(); + memcpy((void *)stack_addr, kcb->jprobes_stack, + min_stack_size(stack_addr)); + kasan_enable_current(); + preempt_enable_no_resched(); + return 1; +} + +bool arch_within_kprobe_blacklist(unsigned long addr) +{ + extern char __idmap_text_start[], __idmap_text_end[]; + extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; + + if ((addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end) || + (addr >= (unsigned long)__entry_text_start && + addr < (unsigned long)__entry_text_end) || + (addr >= (unsigned long)__idmap_text_start && + addr < (unsigned long)__idmap_text_end) || + !!search_exception_tables(addr)) + return true; + + if (!is_kernel_in_hyp_mode()) { + if ((addr >= (unsigned long)__hyp_text_start && + addr < (unsigned long)__hyp_text_end) || + (addr >= (unsigned long)__hyp_idmap_text_start && + addr < (unsigned long)__hyp_idmap_text_end)) + return true; + } + + return false; +} + +void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) +{ + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *tmp; + unsigned long flags, orig_ret_address = 0; + unsigned long trampoline_address = + (unsigned long)&kretprobe_trampoline; + kprobe_opcode_t *correct_ret_addr = NULL; + + INIT_HLIST_HEAD(&empty_rp); + kretprobe_hash_lock(current, &head, &flags); + + /* + * It is possible to have multiple instances associated with a given + * task either because multiple functions in the call path have + * return probes installed on them, and/or more than one + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always pushed into the head of the list + * - when multiple return probes are registered for the same + * function, the (chronologically) first instance's ret_addr + * will be the real return address, and all the rest will + * point to kretprobe_trampoline. + */ + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + if (ri->rp && ri->rp->handler) { + __this_cpu_write(current_kprobe, &ri->rp->kp); + get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; + ri->ret_addr = correct_ret_addr; + ri->rp->handler(ri, regs); + __this_cpu_write(current_kprobe, NULL); + } + + recycle_rp_inst(ri, &empty_rp); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_hash_unlock(current, &flags); + + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + return (void *)orig_ret_address; +} + +void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *)regs->regs[30]; + + /* replace return addr (x30) with trampoline */ + regs->regs[30] = (long)&kretprobe_trampoline; +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + +int __init arch_init_kprobes(void) +{ + return 0; +} diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S new file mode 100644 index 000000000000..5d6e7f14638c --- /dev/null +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -0,0 +1,81 @@ +/* + * trampoline entry and return code for kretprobes. + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> + + .text + + .macro save_all_base_regs + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + add x0, sp, #S_FRAME_SIZE + stp lr, x0, [sp, #S_LR] + /* + * Construct a useful saved PSTATE + */ + mrs x0, nzcv + mrs x1, daif + orr x0, x0, x1 + mrs x1, CurrentEL + orr x0, x0, x1 + mrs x1, SPSel + orr x0, x0, x1 + stp xzr, x0, [sp, #S_PC] + .endm + + .macro restore_all_base_regs + ldr x0, [sp, #S_PSTATE] + and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT) + msr nzcv, x0 + ldp x0, x1, [sp, #S_X0] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldp x8, x9, [sp, #S_X8] + ldp x10, x11, [sp, #S_X10] + ldp x12, x13, [sp, #S_X12] + ldp x14, x15, [sp, #S_X14] + ldp x16, x17, [sp, #S_X16] + ldp x18, x19, [sp, #S_X18] + ldp x20, x21, [sp, #S_X20] + ldp x22, x23, [sp, #S_X22] + ldp x24, x25, [sp, #S_X24] + ldp x26, x27, [sp, #S_X26] + ldp x28, x29, [sp, #S_X28] + .endm + +ENTRY(kretprobe_trampoline) + sub sp, sp, #S_FRAME_SIZE + + save_all_base_regs + + mov x0, sp + bl trampoline_probe_handler + /* + * Replace trampoline address in lr with actual orig_ret_addr return + * address. + */ + mov lr, x0 + + restore_all_base_regs + + add sp, sp, #S_FRAME_SIZE + ret + +ENDPROC(kretprobe_trampoline) diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c new file mode 100644 index 000000000000..8977ce9d009d --- /dev/null +++ b/arch/arm64/kernel/probes/simulate-insn.c @@ -0,0 +1,217 @@ +/* + * arch/arm64/kernel/probes/simulate-insn.c + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/kprobes.h> + +#include "simulate-insn.h" + +#define sign_extend(x, signbit) \ + ((x) | (0 - ((x) & (1 << (signbit))))) + +#define bbl_displacement(insn) \ + sign_extend(((insn) & 0x3ffffff) << 2, 27) + +#define bcond_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +#define cbz_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +#define tbz_displacement(insn) \ + sign_extend(((insn >> 5) & 0x3fff) << 2, 15) + +#define ldr_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val) +{ + if (reg < 31) + regs->regs[reg] = val; +} + +static inline void set_w_reg(struct pt_regs *regs, int reg, u64 val) +{ + if (reg < 31) + regs->regs[reg] = lower_32_bits(val); +} + +static inline u64 get_x_reg(struct pt_regs *regs, int reg) +{ + if (reg < 31) + return regs->regs[reg]; + else + return 0; +} + +static inline u32 get_w_reg(struct pt_regs *regs, int reg) +{ + if (reg < 31) + return lower_32_bits(regs->regs[reg]); + else + return 0; +} + +static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + + return (opcode & (1 << 31)) ? + (get_x_reg(regs, xn) == 0) : (get_w_reg(regs, xn) == 0); +} + +static bool __kprobes check_cbnz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + + return (opcode & (1 << 31)) ? + (get_x_reg(regs, xn) != 0) : (get_w_reg(regs, xn) != 0); +} + +static bool __kprobes check_tbz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f); + + return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) == 0; +} + +static bool __kprobes check_tbnz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f); + + return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) != 0; +} + +/* + * instruction simulation functions + */ +void __kprobes +simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs) +{ + long imm, xn, val; + + xn = opcode & 0x1f; + imm = ((opcode >> 3) & 0x1ffffc) | ((opcode >> 29) & 0x3); + imm = sign_extend(imm, 20); + if (opcode & 0x80000000) + val = (imm<<12) + (addr & 0xfffffffffffff000); + else + val = imm + addr; + + set_x_reg(regs, xn, val); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} + +void __kprobes +simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = bbl_displacement(opcode); + + /* Link register is x30 */ + if (opcode & (1 << 31)) + set_x_reg(regs, 30, addr + 4); + + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (aarch32_opcode_cond_checks[opcode & 0xf](regs->pstate & 0xffffffff)) + disp = bcond_displacement(opcode); + + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs) +{ + int xn = (opcode >> 5) & 0x1f; + + /* update pc first in case we're doing a "blr lr" */ + instruction_pointer_set(regs, get_x_reg(regs, xn)); + + /* Link register is x30 */ + if (((opcode >> 21) & 0x3) == 1) + set_x_reg(regs, 30, addr + 4); +} + +void __kprobes +simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (opcode & (1 << 24)) { + if (check_cbnz(opcode, regs)) + disp = cbz_displacement(opcode); + } else { + if (check_cbz(opcode, regs)) + disp = cbz_displacement(opcode); + } + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (opcode & (1 << 24)) { + if (check_tbnz(opcode, regs)) + disp = tbz_displacement(opcode); + } else { + if (check_tbz(opcode, regs)) + disp = tbz_displacement(opcode); + } + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) +{ + u64 *load_addr; + int xn = opcode & 0x1f; + int disp; + + disp = ldr_displacement(opcode); + load_addr = (u64 *) (addr + disp); + + if (opcode & (1 << 30)) /* x0-x30 */ + set_x_reg(regs, xn, *load_addr); + else /* w0-w30 */ + set_w_reg(regs, xn, *load_addr); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} + +void __kprobes +simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs) +{ + s32 *load_addr; + int xn = opcode & 0x1f; + int disp; + + disp = ldr_displacement(opcode); + load_addr = (s32 *) (addr + disp); + + set_x_reg(regs, xn, *load_addr); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h new file mode 100644 index 000000000000..050bde683c2d --- /dev/null +++ b/arch/arm64/kernel/probes/simulate-insn.h @@ -0,0 +1,28 @@ +/* + * arch/arm64/kernel/probes/simulate-insn.h + * + * Copyright (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KERNEL_KPROBES_SIMULATE_INSN_H +#define _ARM_KERNEL_KPROBES_SIMULATE_INSN_H + +void simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs); +void simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs); +void simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs); +void simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs); +void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs); +void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs); +void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs); +void simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs); + +#endif /* _ARM_KERNEL_KPROBES_SIMULATE_INSN_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 3f6cd5c5234f..030c1d5aa46d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -48,6 +48,107 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} +#define GPR_OFFSET_NAME(r) \ + {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])} + +static const struct pt_regs_offset regoffset_table[] = { + GPR_OFFSET_NAME(0), + GPR_OFFSET_NAME(1), + GPR_OFFSET_NAME(2), + GPR_OFFSET_NAME(3), + GPR_OFFSET_NAME(4), + GPR_OFFSET_NAME(5), + GPR_OFFSET_NAME(6), + GPR_OFFSET_NAME(7), + GPR_OFFSET_NAME(8), + GPR_OFFSET_NAME(9), + GPR_OFFSET_NAME(10), + GPR_OFFSET_NAME(11), + GPR_OFFSET_NAME(12), + GPR_OFFSET_NAME(13), + GPR_OFFSET_NAME(14), + GPR_OFFSET_NAME(15), + GPR_OFFSET_NAME(16), + GPR_OFFSET_NAME(17), + GPR_OFFSET_NAME(18), + GPR_OFFSET_NAME(19), + GPR_OFFSET_NAME(20), + GPR_OFFSET_NAME(21), + GPR_OFFSET_NAME(22), + GPR_OFFSET_NAME(23), + GPR_OFFSET_NAME(24), + GPR_OFFSET_NAME(25), + GPR_OFFSET_NAME(26), + GPR_OFFSET_NAME(27), + GPR_OFFSET_NAME(28), + GPR_OFFSET_NAME(29), + GPR_OFFSET_NAME(30), + {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])}, + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(pc), + REG_OFFSET_NAME(pstate), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || + on_irq_stack(addr, raw_smp_processor_id()); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S new file mode 100644 index 000000000000..51b73cdde287 --- /dev/null +++ b/arch/arm64/kernel/relocate_kernel.S @@ -0,0 +1,130 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/kexec.h> +#include <asm/page.h> +#include <asm/sysreg.h> + +/* + * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it. + * + * The memory that the old kernel occupies may be overwritten when coping the + * new image to its final location. To assure that the + * arm64_relocate_new_kernel routine which does that copy is not overwritten, + * all code and data needed by arm64_relocate_new_kernel must be between the + * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end. The + * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec + * control_code_page, a special page which has been set up to be preserved + * during the copy operation. + */ +ENTRY(arm64_relocate_new_kernel) + + /* Setup the list loop variables. */ + mov x17, x1 /* x17 = kimage_start */ + mov x16, x0 /* x16 = kimage_head */ + dcache_line_size x15, x0 /* x15 = dcache line size */ + mov x14, xzr /* x14 = entry ptr */ + mov x13, xzr /* x13 = copy dest */ + + /* Clear the sctlr_el2 flags. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.ne 1f + mrs x0, sctlr_el2 + ldr x1, =SCTLR_ELx_FLAGS + bic x0, x0, x1 + msr sctlr_el2, x0 + isb +1: + + /* Check if the new image needs relocation. */ + tbnz x16, IND_DONE_BIT, .Ldone + +.Lloop: + and x12, x16, PAGE_MASK /* x12 = addr */ + + /* Test the entry flags. */ +.Ltest_source: + tbz x16, IND_SOURCE_BIT, .Ltest_indirection + + /* Invalidate dest page to PoC. */ + mov x0, x13 + add x20, x0, #PAGE_SIZE + sub x1, x15, #1 + bic x0, x0, x1 +2: dc ivac, x0 + add x0, x0, x15 + cmp x0, x20 + b.lo 2b + dsb sy + + mov x20, x13 + mov x21, x12 + copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7 + + /* dest += PAGE_SIZE */ + add x13, x13, PAGE_SIZE + b .Lnext + +.Ltest_indirection: + tbz x16, IND_INDIRECTION_BIT, .Ltest_destination + + /* ptr = addr */ + mov x14, x12 + b .Lnext + +.Ltest_destination: + tbz x16, IND_DESTINATION_BIT, .Lnext + + /* dest = addr */ + mov x13, x12 + +.Lnext: + /* entry = *ptr++ */ + ldr x16, [x14], #8 + + /* while (!(entry & DONE)) */ + tbz x16, IND_DONE_BIT, .Lloop + +.Ldone: + /* wait for writes from copy_page to finish */ + dsb nsh + ic iallu + dsb nsh + isb + + /* Start new image. */ + mov x0, xzr + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x17 + +ENDPROC(arm64_relocate_new_kernel) + +.ltorg + +.align 3 /* To keep the 64-bit values below naturally aligned. */ + +.Lcopy_end: +.org KEXEC_CONTROL_PAGE_SIZE + +/* + * arm64_relocate_new_kernel_size - Number of bytes to copy to the + * control_code_page. + */ +.globl arm64_relocate_new_kernel_size +arm64_relocate_new_kernel_size: + .quad .Lcopy_end - arm64_relocate_new_kernel diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 92f0e1e767cf..5b8256770e22 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -202,7 +202,7 @@ static void __init request_standard_resources(void) struct resource *res; kernel_code.start = virt_to_phys(_text); - kernel_code.end = virt_to_phys(_etext - 1); + kernel_code.end = virt_to_phys(__init_begin - 1); kernel_data.start = virt_to_phys(_sdata); kernel_data.end = virt_to_phys(_end - 1); diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index a68e0ccd9f4b..76a6d9263908 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -267,7 +267,6 @@ asmlinkage void secondary_start_kernel(void) set_cpu_online(cpu, true); complete(&cpu_running); - local_dbg_enable(); local_irq_enable(); local_async_enable(); @@ -437,9 +436,9 @@ void __init smp_cpus_done(unsigned int max_cpus) void __init smp_prepare_boot_cpu(void) { + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); cpuinfo_store_boot_cpu(); save_boot_cpu_run_el(); - set_my_cpu_offset(per_cpu_offset(smp_processor_id())); } static u64 __init of_get_cpu_mpidr(struct device_node *dn) @@ -696,6 +695,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus) smp_store_cpu_info(smp_processor_id()); /* + * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set + * secondary CPUs present. + */ + if (max_cpus == 0) + return; + + /* * Initialise the present map (which describes the set of CPUs * actually populated at the present time) and release the * secondaries from the bootloader. diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 2a43012616b7..e04f83873af7 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -41,6 +41,7 @@ #include <asm/stacktrace.h> #include <asm/exception.h> #include <asm/system_misc.h> +#include <asm/sysreg.h> static const char *handler[]= { "Synchronous Abort", @@ -52,15 +53,14 @@ static const char *handler[]= { int show_unhandled_signals = 1; /* - * Dump out the contents of some memory nicely... + * Dump out the contents of some kernel memory nicely... */ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, - unsigned long top, bool compat) + unsigned long top) { unsigned long first; mm_segment_t fs; int i; - unsigned int width = compat ? 4 : 8; /* * We need to switch to kernel mode so that we can use __get_user @@ -78,22 +78,15 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, memset(str, ' ', sizeof(str)); str[sizeof(str) - 1] = '\0'; - for (p = first, i = 0; i < (32 / width) - && p < top; i++, p += width) { + for (p = first, i = 0; i < (32 / 8) + && p < top; i++, p += 8) { if (p >= bottom && p < top) { unsigned long val; - if (width == 8) { - if (__get_user(val, (unsigned long *)p) == 0) - sprintf(str + i * 17, " %016lx", val); - else - sprintf(str + i * 17, " ????????????????"); - } else { - if (__get_user(val, (unsigned int *)p) == 0) - sprintf(str + i * 9, " %08lx", val); - else - sprintf(str + i * 9, " ????????"); - } + if (__get_user(val, (unsigned long *)p) == 0) + sprintf(str + i * 17, " %016lx", val); + else + sprintf(str + i * 17, " ????????????????"); } } printk("%s%04lx:%s\n", lvl, first & 0xffff, str); @@ -216,7 +209,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); dump_mem("", "Exception stack", stack, - stack + sizeof(struct pt_regs), false); + stack + sizeof(struct pt_regs)); } } } @@ -254,10 +247,9 @@ static int __die(const char *str, int err, struct thread_info *thread, pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1); - if (!user_mode(regs) || in_interrupt()) { + if (!user_mode(regs)) { dump_mem(KERN_EMERG, "Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_stack_page(tsk), - compat_user_mode(regs)); + THREAD_SIZE + (unsigned long)task_stack_page(tsk)); dump_backtrace(regs, tsk); dump_instr(KERN_EMERG, regs); } @@ -373,11 +365,59 @@ exit: return fn ? fn(regs, instr) : 1; } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +static void force_signal_inject(int signal, int code, struct pt_regs *regs, + unsigned long address) { siginfo_t info; void __user *pc = (void __user *)instruction_pointer(regs); + const char *desc; + switch (signal) { + case SIGILL: + desc = "undefined instruction"; + break; + case SIGSEGV: + desc = "illegal memory access"; + break; + default: + desc = "bad mode"; + break; + } + + if (unhandled_signal(current, signal) && + show_unhandled_signals_ratelimited()) { + pr_info("%s[%d]: %s: pc=%p\n", + current->comm, task_pid_nr(current), desc, pc); + dump_instr(KERN_INFO, regs); + } + + info.si_signo = signal; + info.si_errno = 0; + info.si_code = code; + info.si_addr = pc; + + arm64_notify_die(desc, regs, &info, 0); +} + +/* + * Set up process info to signal segmentation fault - called on access error. + */ +void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr) +{ + int code; + + down_read(¤t->mm->mmap_sem); + if (find_vma(current->mm, addr) == NULL) + code = SEGV_MAPERR; + else + code = SEGV_ACCERR; + up_read(¤t->mm->mmap_sem); + + force_signal_inject(SIGSEGV, code, regs, addr); +} + +asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +{ /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) return; @@ -385,18 +425,66 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (call_undef_hook(regs) == 0) return; - if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) { - pr_info("%s[%d]: undefined instruction: pc=%p\n", - current->comm, task_pid_nr(current), pc); - dump_instr(KERN_INFO, regs); - } + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); +} - info.si_signo = SIGILL; - info.si_errno = 0; - info.si_code = ILL_ILLOPC; - info.si_addr = pc; +void cpu_enable_cache_maint_trap(void *__unused) +{ + config_sctlr_el1(SCTLR_EL1_UCI, 0); +} + +#define __user_cache_maint(insn, address, res) \ + asm volatile ( \ + "1: " insn ", %1\n" \ + " mov %w0, #0\n" \ + "2:\n" \ + " .pushsection .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: mov %w0, %w2\n" \ + " b 2b\n" \ + " .popsection\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "=r" (res) \ + : "r" (address), "i" (-EFAULT) ) + +asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +{ + unsigned long address; + int ret; - arm64_notify_die("Oops - undefined instruction", regs, &info, 0); + /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */ + if ((esr & 0x01fffc01) == 0x0012dc00) { + int rt = (esr >> 5) & 0x1f; + int crm = (esr >> 1) & 0x0f; + + address = (rt == 31) ? 0 : regs->regs[rt]; + + switch (crm) { + case 11: /* DC CVAU, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case 10: /* DC CVAC, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case 14: /* DC CIVAC */ + __user_cache_maint("dc civac", address, ret); + break; + case 5: /* IC IVAU */ + __user_cache_maint("ic ivau", address, ret); + break; + default: + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + return; + } + } else { + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + return; + } + + if (ret) + arm64_notify_segfault(regs, address); + else + regs->pc += 4; } long compat_arm_syscall(struct pt_regs *regs); @@ -465,7 +553,7 @@ static const char *esr_class_str[] = { const char *esr_get_class_string(u32 esr) { - return esr_class_str[esr >> ESR_ELx_EC_SHIFT]; + return esr_class_str[ESR_ELx_EC(esr)]; } /* diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 9fefb005812a..076312b17d4f 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -214,10 +214,16 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { + /* tkr_mono.cycle_last == tkr_raw.cycle_last */ vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; + vdso_data->raw_time_sec = tk->raw_time.tv_sec; + vdso_data->raw_time_nsec = tk->raw_time.tv_nsec; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; - vdso_data->cs_mult = tk->tkr_mono.mult; + /* tkr_raw.xtime_nsec == 0 */ + vdso_data->cs_mono_mult = tk->tkr_mono.mult; + vdso_data->cs_raw_mult = tk->tkr_raw.mult; + /* tkr_mono.shift == tkr_raw.shift */ vdso_data->cs_shift = tk->tkr_mono.shift; } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index b467fd0a384b..62c84f7cb01b 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,7 +23,7 @@ GCOV_PROFILE := n ccflags-y += -Wl,-shared obj-y += vdso.o -extra-y += vdso.lds vdso-offsets.h +extra-y += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) # Force dependency (incbin is bad) @@ -42,11 +42,10 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ define cmd_vdsosym - $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ && \ - cp $@ include/generated/ + $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ endef -$(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE +include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Assembly rules for the .S files diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index efa79e8d4196..e00b4671bd7c 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -26,24 +26,109 @@ #define NSEC_PER_SEC_HI16 0x3b9a vdso_data .req x6 -use_syscall .req w7 -seqcnt .req w8 +seqcnt .req w7 +w_tmp .req w8 +x_tmp .req x8 + +/* + * Conventions for macro arguments: + * - An argument is write-only if its name starts with "res". + * - All other arguments are read-only, unless otherwise specified. + */ .macro seqcnt_acquire 9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT] tbnz seqcnt, #0, 9999b dmb ishld - ldr use_syscall, [vdso_data, #VDSO_USE_SYSCALL] .endm - .macro seqcnt_read, cnt + .macro seqcnt_check fail dmb ishld - ldr \cnt, [vdso_data, #VDSO_TB_SEQ_COUNT] + ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT] + cmp w_tmp, seqcnt + b.ne \fail .endm - .macro seqcnt_check, cnt, fail - cmp \cnt, seqcnt - b.ne \fail + .macro syscall_check fail + ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL] + cbnz w_tmp, \fail + .endm + + .macro get_nsec_per_sec res + mov \res, #NSEC_PER_SEC_LO16 + movk \res, #NSEC_PER_SEC_HI16, lsl #16 + .endm + + /* + * Returns the clock delta, in nanoseconds left-shifted by the clock + * shift. + */ + .macro get_clock_shifted_nsec res, cycle_last, mult + /* Read the virtual counter. */ + isb + mrs x_tmp, cntvct_el0 + /* Calculate cycle delta and convert to ns. */ + sub \res, x_tmp, \cycle_last + /* We can only guarantee 56 bits of precision. */ + movn x_tmp, #0xff00, lsl #48 + and \res, x_tmp, \res + mul \res, \res, \mult + .endm + + /* + * Returns in res_{sec,nsec} the REALTIME timespec, based on the + * "wall time" (xtime) and the clock_mono delta. + */ + .macro get_ts_realtime res_sec, res_nsec, \ + clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec + add \res_nsec, \clock_nsec, \xtime_nsec + udiv x_tmp, \res_nsec, \nsec_to_sec + add \res_sec, \xtime_sec, x_tmp + msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec + .endm + + /* + * Returns in res_{sec,nsec} the timespec based on the clock_raw delta, + * used for CLOCK_MONOTONIC_RAW. + */ + .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec + udiv \res_sec, \clock_nsec, \nsec_to_sec + msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec + .endm + + /* sec and nsec are modified in place. */ + .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec + /* Add timespec. */ + add \sec, \sec, \ts_sec + add \nsec, \nsec, \ts_nsec + + /* Normalise the new timespec. */ + cmp \nsec, \nsec_to_sec + b.lt 9999f + sub \nsec, \nsec, \nsec_to_sec + add \sec, \sec, #1 +9999: + cmp \nsec, #0 + b.ge 9998f + add \nsec, \nsec, \nsec_to_sec + sub \sec, \sec, #1 +9998: + .endm + + .macro clock_gettime_return, shift=0 + .if \shift == 1 + lsr x11, x11, x12 + .endif + stp x10, x11, [x1, #TSPEC_TV_SEC] + mov x0, xzr + ret + .endm + + .macro jump_slot jumptable, index, label + .if (. - \jumptable) != 4 * (\index) + .error "Jump slot index mismatch" + .endif + b \label .endm .text @@ -51,18 +136,25 @@ seqcnt .req w8 /* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */ ENTRY(__kernel_gettimeofday) .cfi_startproc - mov x2, x30 - .cfi_register x30, x2 - - /* Acquire the sequence counter and get the timespec. */ adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 4f - /* If tv is NULL, skip to the timezone code. */ cbz x0, 2f - bl __do_get_tspec - seqcnt_check w9, 1b + + /* Compute the time of day. */ +1: seqcnt_acquire + syscall_check fail=4f + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=1b + + get_nsec_per_sec res=x9 + lsl x9, x9, x12 + + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 /* Convert ns to us. */ mov x13, #1000 @@ -76,95 +168,126 @@ ENTRY(__kernel_gettimeofday) stp w4, w5, [x1, #TZ_MINWEST] 3: mov x0, xzr - ret x2 + ret 4: /* Syscall fallback. */ mov x8, #__NR_gettimeofday svc #0 - ret x2 + ret .cfi_endproc ENDPROC(__kernel_gettimeofday) +#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE + /* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */ ENTRY(__kernel_clock_gettime) .cfi_startproc - cmp w0, #CLOCK_REALTIME - ccmp w0, #CLOCK_MONOTONIC, #0x4, ne - b.ne 2f + cmp w0, #JUMPSLOT_MAX + b.hi syscall + adr vdso_data, _vdso_data + adr x_tmp, jumptable + add x_tmp, x_tmp, w0, uxtw #2 + br x_tmp + + ALIGN +jumptable: + jump_slot jumptable, CLOCK_REALTIME, realtime + jump_slot jumptable, CLOCK_MONOTONIC, monotonic + b syscall + b syscall + jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw + jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse + jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse + + .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1) + .error "Wrong jumptable size" + .endif + + ALIGN +realtime: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=realtime - mov x2, x30 - .cfi_register x30, x2 + /* All computations are done with left-shifted nsecs. */ + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get kernel timespec. */ - adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 7f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 - bl __do_get_tspec - seqcnt_check w9, 1b + ALIGN +monotonic: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic - mov x30, x2 + /* All computations are done with left-shifted nsecs. */ + lsl x4, x4, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - cmp w0, #CLOCK_MONOTONIC - b.ne 6f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - /* Get wtm timespec. */ - ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9 + clock_gettime_return, shift=1 - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 1b - b 4f -2: - cmp w0, #CLOCK_REALTIME_COARSE - ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne - b.ne 8f + ALIGN +monotonic_raw: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_raw_mult, w12 = cs_shift */ + ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT] + ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC] + seqcnt_check fail=monotonic_raw - /* xtime_coarse_nsec is already right-shifted */ - mov x12, #0 + /* All computations are done with left-shifted nsecs. */ + lsl x14, x14, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get coarse timespec. */ - adr vdso_data, _vdso_data -3: seqcnt_acquire + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_clock_raw res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, nsec_to_sec=x9 + + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 + + ALIGN +realtime_coarse: + seqcnt_acquire ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] + seqcnt_check fail=realtime_coarse + clock_gettime_return - /* Get wtm timespec. */ + ALIGN +monotonic_coarse: + seqcnt_acquire + ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic_coarse - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 3b + /* Computations are done in (non-shifted) nsecs. */ + get_nsec_per_sec res=x9 + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return - cmp w0, #CLOCK_MONOTONIC_COARSE - b.ne 6f -4: - /* Add on wtm timespec. */ - add x10, x10, x13 - lsl x14, x14, x12 - add x11, x11, x14 - - /* Normalise the new timespec. */ - mov x15, #NSEC_PER_SEC_LO16 - movk x15, #NSEC_PER_SEC_HI16, lsl #16 - lsl x15, x15, x12 - cmp x11, x15 - b.lt 5f - sub x11, x11, x15 - add x10, x10, #1 -5: - cmp x11, #0 - b.ge 6f - add x11, x11, x15 - sub x10, x10, #1 - -6: /* Store to the user timespec. */ - lsr x11, x11, x12 - stp x10, x11, [x1, #TSPEC_TV_SEC] - mov x0, xzr - ret -7: - mov x30, x2 -8: /* Syscall fallback. */ + ALIGN +syscall: /* Syscall fallback. */ mov x8, #__NR_clock_gettime svc #0 ret @@ -176,6 +299,7 @@ ENTRY(__kernel_clock_getres) .cfi_startproc cmp w0, #CLOCK_REALTIME ccmp w0, #CLOCK_MONOTONIC, #0x4, ne + ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne b.ne 1f ldr x2, 5f @@ -203,46 +327,3 @@ ENTRY(__kernel_clock_getres) .quad CLOCK_COARSE_RES .cfi_endproc ENDPROC(__kernel_clock_getres) - -/* - * Read the current time from the architected counter. - * Expects vdso_data to be initialised. - * Clobbers the temporary registers (x9 - x15). - * Returns: - * - w9 = vDSO sequence counter - * - (x10, x11) = (ts->tv_sec, shifted ts->tv_nsec) - * - w12 = cs_shift - */ -ENTRY(__do_get_tspec) - .cfi_startproc - - /* Read from the vDSO data page. */ - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - ldp w11, w12, [vdso_data, #VDSO_CS_MULT] - seqcnt_read w9 - - /* Read the virtual counter. */ - isb - mrs x15, cntvct_el0 - - /* Calculate cycle delta and convert to ns. */ - sub x10, x15, x10 - /* We can only guarantee 56 bits of precision. */ - movn x15, #0xff00, lsl #48 - and x10, x15, x10 - mul x10, x10, x11 - - /* Use the kernel time to calculate the new timespec. */ - mov x11, #NSEC_PER_SEC_LO16 - movk x11, #NSEC_PER_SEC_HI16, lsl #16 - lsl x11, x11, x12 - add x15, x10, x14 - udiv x14, x15, x11 - add x10, x13, x14 - mul x13, x14, x11 - sub x11, x15, x13 - - ret - .cfi_endproc -ENDPROC(__do_get_tspec) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 435e820e898d..89d6e177ecbd 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -118,9 +118,11 @@ SECTIONS __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT + ENTRY_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT + KPROBES_TEXT HYPERVISOR_TEXT IDMAP_TEXT HIBERNATE_TEXT @@ -131,12 +133,13 @@ SECTIONS } . = ALIGN(SEGMENT_ALIGN); - RO_DATA(PAGE_SIZE) /* everything from this point to */ - EXCEPTION_TABLE(8) /* _etext will be marked RO NX */ + _etext = .; /* End of text section */ + + RO_DATA(PAGE_SIZE) /* everything from this point to */ + EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */ NOTES . = ALIGN(SEGMENT_ALIGN); - _etext = .; /* End of text and rodata section */ __init_begin = .; INIT_TEXT_SECTION(8) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 3246c4aba5b1..fa96fe2bd469 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -106,7 +106,7 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run) run->exit_reason = KVM_EXIT_DEBUG; run->debug.arch.hsr = hsr; - switch (hsr >> ESR_ELx_EC_SHIFT) { + switch (ESR_ELx_EC(hsr)) { case ESR_ELx_EC_WATCHPT_LOW: run->debug.arch.far = vcpu->arch.fault.far_el2; /* fall through */ @@ -149,7 +149,7 @@ static exit_handle_fn arm_exit_handlers[] = { static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) { u32 hsr = kvm_vcpu_get_hsr(vcpu); - u8 hsr_ec = hsr >> ESR_ELx_EC_SHIFT; + u8 hsr_ec = ESR_ELx_EC(hsr); if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) || !arm_exit_handlers[hsr_ec]) { diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile index 778d0effa2af..0c85febcc1eb 100644 --- a/arch/arm64/kvm/hyp/Makefile +++ b/arch/arm64/kvm/hyp/Makefile @@ -17,6 +17,10 @@ obj-$(CONFIG_KVM_ARM_HOST) += tlb.o obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o +# KVM code is run at a different exception code with a different map, so +# compiler instrumentation that inserts callbacks or checks into the code may +# cause crashes. Just disable it. GCOV_PROFILE := n KASAN_SANITIZE := n UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 437cfad5e3d8..4373997d1a70 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -198,7 +198,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) { u64 esr = read_sysreg_el2(esr); - u8 ec = esr >> ESR_ELx_EC_SHIFT; + u8 ec = ESR_ELx_EC(esr); u64 hpfar, far; vcpu->arch.fault.esr_el2 = esr; diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 17e8306dca29..0b90497d4424 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -66,7 +66,7 @@ .endm end .req x5 -ENTRY(__copy_from_user) +ENTRY(__arch_copy_from_user) ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) add end, x0, x2 @@ -75,7 +75,7 @@ ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x0, #0 // Nothing to copy ret -ENDPROC(__copy_from_user) +ENDPROC(__arch_copy_from_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 21faae60f988..7a7efe255034 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -65,7 +65,7 @@ .endm end .req x5 -ENTRY(__copy_to_user) +ENTRY(__arch_copy_to_user) ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) add end, x0, x2 @@ -74,7 +74,7 @@ ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \ CONFIG_ARM64_PAN) mov x0, #0 ret -ENDPROC(__copy_to_user) +ENDPROC(__arch_copy_to_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 50ff9ba3a236..07d7352d7c38 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -52,7 +52,7 @@ ENTRY(__flush_cache_user_range) sub x3, x2, #1 bic x4, x0, x3 1: -USER(9f, dc cvau, x4 ) // clean D line to PoU +user_alt 9f, "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE add x4, x4, x2 cmp x4, x1 b.lo 1b diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index c566ec83719f..f6c55afab3e2 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -19,6 +19,7 @@ #include <linux/gfp.h> #include <linux/acpi.h> +#include <linux/bootmem.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -29,6 +30,8 @@ #include <asm/cacheflush.h> +static int swiotlb __read_mostly; + static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -341,6 +344,13 @@ static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, return ret; } +static int __swiotlb_dma_supported(struct device *hwdev, u64 mask) +{ + if (swiotlb) + return swiotlb_dma_supported(hwdev, mask); + return 1; +} + static struct dma_map_ops swiotlb_dma_ops = { .alloc = __dma_alloc, .free = __dma_free, @@ -354,7 +364,7 @@ static struct dma_map_ops swiotlb_dma_ops = { .sync_single_for_device = __swiotlb_sync_single_for_device, .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu, .sync_sg_for_device = __swiotlb_sync_sg_for_device, - .dma_supported = swiotlb_dma_supported, + .dma_supported = __swiotlb_dma_supported, .mapping_error = swiotlb_dma_mapping_error, }; @@ -513,6 +523,9 @@ EXPORT_SYMBOL(dummy_dma_ops); static int __init arm64_dma_init(void) { + if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + swiotlb = 1; + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -848,15 +861,16 @@ static int __iommu_attach_notifier(struct notifier_block *nb, { struct iommu_dma_notifier_data *master, *tmp; - if (action != BUS_NOTIFY_ADD_DEVICE) + if (action != BUS_NOTIFY_BIND_DRIVER) return 0; mutex_lock(&iommu_dma_notifier_lock); list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) { - if (do_iommu_attach(master->dev, master->ops, - master->dma_base, master->size)) { + if (data == master->dev && do_iommu_attach(master->dev, + master->ops, master->dma_base, master->size)) { list_del(&master->list); kfree(master); + break; } } mutex_unlock(&iommu_dma_notifier_lock); @@ -870,17 +884,8 @@ static int __init register_iommu_dma_ops_notifier(struct bus_type *bus) if (!nb) return -ENOMEM; - /* - * The device must be attached to a domain before the driver probe - * routine gets a chance to start allocating DMA buffers. However, - * the IOMMU driver also needs a chance to configure the iommu_group - * via its add_device callback first, so we need to make the attach - * happen between those two points. Since the IOMMU core uses a bus - * notifier with default priority for add_device, do the same but - * with a lower priority to ensure the appropriate ordering. - */ + nb->notifier_call = __iommu_attach_notifier; - nb->priority = -100; ret = bus_register_notifier(bus, nb); if (ret) { @@ -904,10 +909,6 @@ static int __init __iommu_dma_init(void) if (!ret) ret = register_iommu_dma_ops_notifier(&pci_bus_type); #endif - - /* handle devices queued before this arch_initcall */ - if (!ret) - __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index ccfde237d6e6..f94b80eb295d 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -27,11 +27,7 @@ #include <asm/memory.h> #include <asm/pgtable.h> #include <asm/pgtable-hwdef.h> - -struct addr_marker { - unsigned long start_address; - const char *name; -}; +#include <asm/ptdump.h> static const struct addr_marker address_markers[] = { #ifdef CONFIG_KASAN @@ -290,7 +286,8 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) } } -static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) +static void walk_pgd(struct pg_state *st, struct mm_struct *mm, + unsigned long start) { pgd_t *pgd = pgd_offset(mm, 0UL); unsigned i; @@ -309,12 +306,13 @@ static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long st static int ptdump_show(struct seq_file *m, void *v) { + struct ptdump_info *info = m->private; struct pg_state st = { .seq = m, - .marker = address_markers, + .marker = info->markers, }; - walk_pgd(&st, &init_mm, VA_START); + walk_pgd(&st, info->mm, info->base_addr); note_page(&st, 0, 0, 0); return 0; @@ -322,7 +320,7 @@ static int ptdump_show(struct seq_file *m, void *v) static int ptdump_open(struct inode *inode, struct file *file) { - return single_open(file, ptdump_show, NULL); + return single_open(file, ptdump_show, inode->i_private); } static const struct file_operations ptdump_fops = { @@ -332,7 +330,7 @@ static const struct file_operations ptdump_fops = { .release = single_release, }; -static int ptdump_init(void) +int ptdump_register(struct ptdump_info *info, const char *name) { struct dentry *pe; unsigned i, j; @@ -342,8 +340,18 @@ static int ptdump_init(void) for (j = 0; j < pg_level[i].num; j++) pg_level[i].mask |= pg_level[i].bits[j].mask; - pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, - &ptdump_fops); + pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops); return pe ? 0 : -ENOMEM; } + +static struct ptdump_info kernel_ptdump_info = { + .mm = &init_mm, + .markers = address_markers, + .base_addr = VA_START, +}; + +static int ptdump_init(void) +{ + return ptdump_register(&kernel_ptdump_info, "kernel_page_tables"); +} device_initcall(ptdump_init); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 031820d989a8..c8beaa0da7df 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -41,6 +41,28 @@ static const char *fault_name(unsigned int esr); +#ifdef CONFIG_KPROBES +static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) +{ + int ret = 0; + + /* kprobe_running() needs smp_processor_id() */ + if (!user_mode(regs)) { + preempt_disable(); + if (kprobe_running() && kprobe_fault_handler(regs, esr)) + ret = 1; + preempt_enable(); + } + + return ret; +} +#else +static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr) +{ + return 0; +} +#endif + /* * Dump out the page tables associated with 'addr' in mm 'mm'. */ @@ -202,8 +224,6 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re #define VM_FAULT_BADMAP 0x010000 #define VM_FAULT_BADACCESS 0x020000 -#define ESR_LNX_EXEC (1 << 24) - static int __do_page_fault(struct mm_struct *mm, unsigned long addr, unsigned int mm_flags, unsigned long vm_flags, struct task_struct *tsk) @@ -242,14 +262,19 @@ out: return fault; } -static inline int permission_fault(unsigned int esr) +static inline bool is_permission_fault(unsigned int esr) { - unsigned int ec = (esr & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT; + unsigned int ec = ESR_ELx_EC(esr); unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); } +static bool is_el0_instruction_abort(unsigned int esr) +{ + return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; +} + static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { @@ -259,6 +284,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC; unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; + if (notify_page_fault(regs, esr)) + return 0; + tsk = current; mm = tsk->mm; @@ -272,14 +300,14 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; - if (esr & ESR_LNX_EXEC) { + if (is_el0_instruction_abort(esr)) { vm_flags = VM_EXEC; } else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) { vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } - if (permission_fault(esr) && (addr < USER_DS)) { + if (is_permission_fault(esr) && (addr < USER_DS)) { /* regs->orig_addr_limit may be 0 if we entered from EL0 */ if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); @@ -630,6 +658,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, return rv; } +NOKPROBE_SYMBOL(do_debug_exception); #ifdef CONFIG_ARM64_PAN void cpu_enable_pan(void *__unused) diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d45f8627012c..2ade7a6a10a7 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -160,12 +160,10 @@ static void __init arm64_memory_present(void) static void __init arm64_memory_present(void) { struct memblock_region *reg; - int nid = 0; for_each_memblock(memory, reg) { -#ifdef CONFIG_NUMA - nid = reg->nid; -#endif + int nid = memblock_get_region_node(reg); + memory_present(nid, memblock_region_memory_base_pfn(reg), memblock_region_memory_end_pfn(reg)); } @@ -403,7 +401,8 @@ static void __init free_unused_memmap(void) */ void __init mem_init(void) { - swiotlb_init(1); + if (swiotlb_force || max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT)) + swiotlb_init(1); set_max_mapnr(pfn_to_page(max_pfn) - mem_map); @@ -430,9 +429,9 @@ void __init mem_init(void) pr_cont(" vmalloc : 0x%16lx - 0x%16lx (%6ld GB)\n", MLG(VMALLOC_START, VMALLOC_END)); pr_cont(" .text : 0x%p" " - 0x%p" " (%6ld KB)\n", - MLK_ROUNDUP(_text, __start_rodata)); + MLK_ROUNDUP(_text, _etext)); pr_cont(" .rodata : 0x%p" " - 0x%p" " (%6ld KB)\n", - MLK_ROUNDUP(__start_rodata, _etext)); + MLK_ROUNDUP(__start_rodata, __init_begin)); pr_cont(" .init : 0x%p" " - 0x%p" " (%6ld KB)\n", MLK_ROUNDUP(__init_begin, __init_end)); pr_cont(" .data : 0x%p" " - 0x%p" " (%6ld KB)\n", diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 0f85a46c3e18..51a558195bb9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -77,7 +77,6 @@ static phys_addr_t __init early_pgtable_alloc(void) void *ptr; phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - BUG_ON(!phys); /* * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE @@ -97,24 +96,6 @@ static phys_addr_t __init early_pgtable_alloc(void) return phys; } -/* - * remap a PMD into pages - */ -static void split_pmd(pmd_t *pmd, pte_t *pte) -{ - unsigned long pfn = pmd_pfn(*pmd); - int i = 0; - - do { - /* - * Need to have the least restrictive permissions available - * permissions will be fixed up later - */ - set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC)); - pfn++; - } while (pte++, i++, i < PTRS_PER_PTE); -} - static void alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot, @@ -122,15 +103,13 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, { pte_t *pte; - if (pmd_none(*pmd) || pmd_sect(*pmd)) { + BUG_ON(pmd_sect(*pmd)); + if (pmd_none(*pmd)) { phys_addr_t pte_phys; BUG_ON(!pgtable_alloc); pte_phys = pgtable_alloc(); pte = pte_set_fixmap(pte_phys); - if (pmd_sect(*pmd)) - split_pmd(pmd, pte); __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE); - flush_tlb_all(); pte_clear_fixmap(); } BUG_ON(pmd_bad(*pmd)); @@ -144,41 +123,10 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr, pte_clear_fixmap(); } -static void split_pud(pud_t *old_pud, pmd_t *pmd) -{ - unsigned long addr = pud_pfn(*old_pud) << PAGE_SHIFT; - pgprot_t prot = __pgprot(pud_val(*old_pud) ^ addr); - int i = 0; - - do { - set_pmd(pmd, __pmd(addr | pgprot_val(prot))); - addr += PMD_SIZE; - } while (pmd++, i++, i < PTRS_PER_PMD); -} - -#ifdef CONFIG_DEBUG_PAGEALLOC -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - - /* - * If debug_page_alloc is enabled we must map the linear map - * using pages. However, other mappings created by - * create_mapping_noalloc must use sections in some cases. Allow - * sections to be used in those cases, where no pgtable_alloc - * function is provided. - */ - return !pgtable_alloc || !debug_pagealloc_enabled(); -} -#else -static bool block_mappings_allowed(phys_addr_t (*pgtable_alloc)(void)) -{ - return true; -} -#endif - static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pmd_t *pmd; unsigned long next; @@ -186,20 +134,13 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, /* * Check for initial section mappings in the pgd/pud and remove them. */ - if (pud_none(*pud) || pud_sect(*pud)) { + BUG_ON(pud_sect(*pud)); + if (pud_none(*pud)) { phys_addr_t pmd_phys; BUG_ON(!pgtable_alloc); pmd_phys = pgtable_alloc(); pmd = pmd_set_fixmap(pmd_phys); - if (pud_sect(*pud)) { - /* - * need to have the 1G of mappings continue to be - * present - */ - split_pud(pud, pmd); - } __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE); - flush_tlb_all(); pmd_clear_fixmap(); } BUG_ON(pud_bad(*pud)); @@ -209,7 +150,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, next = pmd_addr_end(addr, end); /* try section mapping first */ if (((addr | next | phys) & ~SECTION_MASK) == 0 && - block_mappings_allowed(pgtable_alloc)) { + allow_block_mappings) { pmd_t old_pmd =*pmd; pmd_set_huge(pmd, phys, prot); /* @@ -248,7 +189,8 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next, static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { pud_t *pud; unsigned long next; @@ -268,8 +210,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, /* * For 4K granule only, attempt to put down a 1GB block */ - if (use_1G_block(addr, next, phys) && - block_mappings_allowed(pgtable_alloc)) { + if (use_1G_block(addr, next, phys) && allow_block_mappings) { pud_t old_pud = *pud; pud_set_huge(pud, phys, prot); @@ -290,7 +231,7 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, } } else { alloc_init_pmd(pud, addr, next, phys, prot, - pgtable_alloc); + pgtable_alloc, allow_block_mappings); } phys += next - addr; } while (pud++, addr = next, addr != end); @@ -298,15 +239,14 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, pud_clear_fixmap(); } -/* - * Create the page directory entries and any necessary page tables for the - * mapping specified by 'md'. - */ -static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, - phys_addr_t size, pgprot_t prot, - phys_addr_t (*pgtable_alloc)(void)) +static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, + unsigned long virt, phys_addr_t size, + pgprot_t prot, + phys_addr_t (*pgtable_alloc)(void), + bool allow_block_mappings) { unsigned long addr, length, end, next; + pgd_t *pgd = pgd_offset_raw(pgdir, virt); /* * If the virtual and physical address don't have the same offset @@ -322,29 +262,23 @@ static void init_pgd(pgd_t *pgd, phys_addr_t phys, unsigned long virt, end = addr + length; do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc); + alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc, + allow_block_mappings); phys += next - addr; } while (pgd++, addr = next, addr != end); } -static phys_addr_t late_pgtable_alloc(void) +static phys_addr_t pgd_pgtable_alloc(void) { void *ptr = (void *)__get_free_page(PGALLOC_GFP); - BUG_ON(!ptr); + if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) + BUG(); /* Ensure the zeroed page is visible to the page table walker */ dsb(ishst); return __pa(ptr); } -static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys, - unsigned long virt, phys_addr_t size, - pgprot_t prot, - phys_addr_t (*alloc)(void)) -{ - init_pgd(pgd_offset_raw(pgdir, virt), phys, virt, size, prot, alloc); -} - /* * This function can only be used to modify existing table entries, * without allocating new levels of table. Note that this permits the @@ -358,16 +292,17 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - NULL); + __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true); } void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, - pgprot_t prot) + pgprot_t prot, bool allow_block_mappings) { + BUG_ON(mm == &init_mm); + __create_pgd_mapping(mm->pgd, phys, virt, size, prot, - late_pgtable_alloc); + pgd_pgtable_alloc, allow_block_mappings); } static void create_mapping_late(phys_addr_t phys, unsigned long virt, @@ -380,51 +315,54 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, } __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, - late_pgtable_alloc); + NULL, !debug_pagealloc_enabled()); } static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end) { unsigned long kernel_start = __pa(_text); - unsigned long kernel_end = __pa(_etext); + unsigned long kernel_end = __pa(__init_begin); /* * Take care not to create a writable alias for the * read-only text and rodata sections of the kernel image. */ - /* No overlap with the kernel text */ + /* No overlap with the kernel text/rodata */ if (end < kernel_start || start >= kernel_end) { __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start, PAGE_KERNEL, - early_pgtable_alloc); + early_pgtable_alloc, + !debug_pagealloc_enabled()); return; } /* - * This block overlaps the kernel text mapping. + * This block overlaps the kernel text/rodata mappings. * Map the portion(s) which don't overlap. */ if (start < kernel_start) __create_pgd_mapping(pgd, start, __phys_to_virt(start), kernel_start - start, PAGE_KERNEL, - early_pgtable_alloc); + early_pgtable_alloc, + !debug_pagealloc_enabled()); if (kernel_end < end) __create_pgd_mapping(pgd, kernel_end, __phys_to_virt(kernel_end), end - kernel_end, PAGE_KERNEL, - early_pgtable_alloc); + early_pgtable_alloc, + !debug_pagealloc_enabled()); /* - * Map the linear alias of the [_text, _etext) interval as + * Map the linear alias of the [_text, __init_begin) interval as * read-only/non-executable. This makes the contents of the * region accessible to subsystems such as hibernate, but * protects it from inadvertent modification or execution. */ __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start), kernel_end - kernel_start, PAGE_KERNEL_RO, - early_pgtable_alloc); + early_pgtable_alloc, !debug_pagealloc_enabled()); } static void __init map_mem(pgd_t *pgd) @@ -449,14 +387,14 @@ void mark_rodata_ro(void) { unsigned long section_size; - section_size = (unsigned long)__start_rodata - (unsigned long)_text; + section_size = (unsigned long)_etext - (unsigned long)_text; create_mapping_late(__pa(_text), (unsigned long)_text, section_size, PAGE_KERNEL_ROX); /* - * mark .rodata as read only. Use _etext rather than __end_rodata to - * cover NOTES and EXCEPTION_TABLE. + * mark .rodata as read only. Use __init_begin rather than __end_rodata + * to cover NOTES and EXCEPTION_TABLE. */ - section_size = (unsigned long)_etext - (unsigned long)__start_rodata; + section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); } @@ -481,7 +419,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(size)); __create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot, - early_pgtable_alloc); + early_pgtable_alloc, !debug_pagealloc_enabled()); vma->addr = va_start; vma->phys_addr = pa_start; @@ -499,8 +437,8 @@ static void __init map_kernel(pgd_t *pgd) { static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data; - map_kernel_segment(pgd, _text, __start_rodata, PAGE_KERNEL_EXEC, &vmlinux_text); - map_kernel_segment(pgd, __start_rodata, _etext, PAGE_KERNEL, &vmlinux_rodata); + map_kernel_segment(pgd, _text, _etext, PAGE_KERNEL_EXEC, &vmlinux_text); + map_kernel_segment(pgd, __start_rodata, __init_begin, PAGE_KERNEL, &vmlinux_rodata); map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC, &vmlinux_init); map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index c4317879b938..5bb61de23201 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -180,6 +180,8 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + isb // Unmask debug exceptions now, + enable_dbg // since this is per-cpu reset_pmuserenr_el0 x0 // Disable PMU access from EL0 /* * Memory region attributes for LPAE: diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 140436a046c0..8e4d7f590b06 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -603,7 +603,8 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu) irq = platform_get_irq(pmu_device, 0); if (irq >= 0 && irq_is_percpu(irq)) { - on_each_cpu(cpu_pmu_disable_percpu_irq, &irq, 1); + on_each_cpu_mask(&cpu_pmu->supported_cpus, + cpu_pmu_disable_percpu_irq, &irq, 1); free_percpu_irq(irq, &hw_events->percpu_pmu); } else { for (i = 0; i < irqs; ++i) { @@ -645,7 +646,9 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) irq); return err; } - on_each_cpu(cpu_pmu_enable_percpu_irq, &irq, 1); + + on_each_cpu_mask(&cpu_pmu->supported_cpus, + cpu_pmu_enable_percpu_irq, &irq, 1); } else { for (i = 0; i < irqs; ++i) { int cpu = i; @@ -961,9 +964,23 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) i++; } while (1); - /* If we didn't manage to parse anything, claim to support all CPUs */ - if (cpumask_weight(&pmu->supported_cpus) == 0) - cpumask_setall(&pmu->supported_cpus); + /* If we didn't manage to parse anything, try the interrupt affinity */ + if (cpumask_weight(&pmu->supported_cpus) == 0) { + if (!using_spi) { + /* If using PPIs, check the affinity of the partition */ + int ret, irq; + + irq = platform_get_irq(pdev, 0); + ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus); + if (ret) { + kfree(irqs); + return ret; + } + } else { + /* Otherwise default to all CPUs */ + cpumask_setall(&pmu->supported_cpus); + } + } /* If we matched up the IRQ affinities, use them to route the SPIs */ if (using_spi && i == pdev->num_resources) diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index 99048e501b88..aae5ebf2022b 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -39,6 +39,7 @@ #define KEXEC_ARCH_SH (42 << 16) #define KEXEC_ARCH_MIPS_LE (10 << 16) #define KEXEC_ARCH_MIPS ( 8 << 16) +#define KEXEC_ARCH_AARCH64 (183 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c index ed0ca0c07242..f3b61b4ee09c 100644 --- a/samples/kprobes/kprobe_example.c +++ b/samples/kprobes/kprobe_example.c @@ -46,6 +46,11 @@ static int handler_pre(struct kprobe *p, struct pt_regs *regs) " ex1 = 0x%lx\n", p->symbol_name, p->addr, regs->pc, regs->ex1); #endif +#ifdef CONFIG_ARM64 + pr_info("<%s> pre_handler: p->addr = 0x%p, pc = 0x%lx," + " pstate = 0x%lx\n", + p->symbol_name, p->addr, (long)regs->pc, (long)regs->pstate); +#endif /* A dump_stack() here will give a stack backtrace */ return 0; @@ -71,6 +76,10 @@ static void handler_post(struct kprobe *p, struct pt_regs *regs, printk(KERN_INFO "<%s> post_handler: p->addr = 0x%p, ex1 = 0x%lx\n", p->symbol_name, p->addr, regs->ex1); #endif +#ifdef CONFIG_ARM64 + pr_info("<%s> post_handler: p->addr = 0x%p, pstate = 0x%lx\n", + p->symbol_name, p->addr, (long)regs->pstate); +#endif } /* |