diff options
137 files changed, 5508 insertions, 1578 deletions
diff --git a/Documentation/admin-guide/perf/hisi-pcie-pmu.rst b/Documentation/admin-guide/perf/hisi-pcie-pmu.rst index 7e863662e2d4..5541ff40e06a 100644 --- a/Documentation/admin-guide/perf/hisi-pcie-pmu.rst +++ b/Documentation/admin-guide/perf/hisi-pcie-pmu.rst @@ -37,9 +37,21 @@ Example usage of perf:: hisi_pcie0_core0/rx_mwr_cnt/ [kernel PMU event] ------------------------------------------ - $# perf stat -e hisi_pcie0_core0/rx_mwr_latency/ - $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt/ - $# perf stat -g -e hisi_pcie0_core0/rx_mwr_latency/ -e hisi_pcie0_core0/rx_mwr_cnt/ + $# perf stat -e hisi_pcie0_core0/rx_mwr_latency,port=0xffff/ + $# perf stat -e hisi_pcie0_core0/rx_mwr_cnt,port=0xffff/ + +The related events usually used to calculate the bandwidth, latency or others. +They need to start and end counting at the same time, therefore related events +are best used in the same event group to get the expected value. There are two +ways to know if they are related events: + +a) By event name, such as the latency events "xxx_latency, xxx_cnt" or + bandwidth events "xxx_flux, xxx_time". +b) By event type, such as "event=0xXXXX, event=0x1XXXX". + +Example usage of perf group:: + + $# perf stat -e "{hisi_pcie0_core0/rx_mwr_latency,port=0xffff/,hisi_pcie0_core0/rx_mwr_cnt,port=0xffff/}" The current driver does not support sampling. So "perf record" is unsupported. Also attach to a task is unsupported for PCIe PMU. @@ -51,8 +63,12 @@ Filter options PMU could only monitor the performance of traffic downstream target Root Ports or downstream target Endpoint. PCIe PMU driver support "port" and - "bdf" interfaces for users, and these two interfaces aren't supported at the - same time. + "bdf" interfaces for users. + Please notice that, one of these two interfaces must be set, and these two + interfaces aren't supported at the same time. If they are both set, only + "port" filter is valid. + If "port" filter not being set or is set explicitly to zero (default), the + "bdf" filter will be in effect, because "bdf=0" meaning 0000:000:00.0. - port @@ -95,7 +111,7 @@ Filter options Example usage of perf:: - $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,trig_len=0x4,trig_mode=1/ sleep 5 + $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,trig_len=0x4,trig_mode=1/ sleep 5 3. Threshold filter @@ -109,7 +125,7 @@ Filter options Example usage of perf:: - $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,thr_len=0x4,thr_mode=1/ sleep 5 + $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,thr_len=0x4,thr_mode=1/ sleep 5 4. TLP Length filter @@ -127,4 +143,4 @@ Filter options Example usage of perf:: - $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,len_mode=0x1/ sleep 5 + $# perf stat -e hisi_pcie0_core0/rx_mrd_flux,port=0xffff,len_mode=0x1/ sleep 5 diff --git a/Documentation/admin-guide/perf/index.rst b/Documentation/admin-guide/perf/index.rst index f4a4513c526f..7eb3dcd6f4da 100644 --- a/Documentation/admin-guide/perf/index.rst +++ b/Documentation/admin-guide/perf/index.rst @@ -13,6 +13,7 @@ Performance monitor support imx-ddr qcom_l2_pmu qcom_l3_pmu + starfive_starlink_pmu arm-ccn arm-cmn xgene-pmu diff --git a/Documentation/admin-guide/perf/starfive_starlink_pmu.rst b/Documentation/admin-guide/perf/starfive_starlink_pmu.rst new file mode 100644 index 000000000000..2932ddb4eb76 --- /dev/null +++ b/Documentation/admin-guide/perf/starfive_starlink_pmu.rst @@ -0,0 +1,46 @@ +================================================ +StarFive StarLink Performance Monitor Unit (PMU) +================================================ + +StarFive StarLink Performance Monitor Unit (PMU) exists within the +StarLink Coherent Network on Chip (CNoC) that connects multiple CPU +clusters with an L3 memory system. + +The uncore PMU supports overflow interrupt, up to 16 programmable 64bit +event counters, and an independent 64bit cycle counter. +The PMU can only be accessed via Memory Mapped I/O and are common to the +cores connected to the same PMU. + +Driver exposes supported PMU events in sysfs "events" directory under:: + + /sys/bus/event_source/devices/starfive_starlink_pmu/events/ + +Driver exposes cpu used to handle PMU events in sysfs "cpumask" directory +under:: + + /sys/bus/event_source/devices/starfive_starlink_pmu/cpumask/ + +Driver describes the format of config (event ID) in sysfs "format" directory +under:: + + /sys/bus/event_source/devices/starfive_starlink_pmu/format/ + +Example of perf usage:: + + $ perf list + + starfive_starlink_pmu/cycles/ [Kernel PMU event] + starfive_starlink_pmu/read_hit/ [Kernel PMU event] + starfive_starlink_pmu/read_miss/ [Kernel PMU event] + starfive_starlink_pmu/read_request/ [Kernel PMU event] + starfive_starlink_pmu/release_request/ [Kernel PMU event] + starfive_starlink_pmu/write_hit/ [Kernel PMU event] + starfive_starlink_pmu/write_miss/ [Kernel PMU event] + starfive_starlink_pmu/write_request/ [Kernel PMU event] + starfive_starlink_pmu/writeback/ [Kernel PMU event] + + + $ perf stat -a -e /starfive_starlink_pmu/cycles/ sleep 1 + +Sampling is not supported. As a result, "perf record" is not supported. +Attaching to a task is not supported, only system-wide counting is supported. diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index ced7b335e2e0..448c1664879b 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -317,6 +317,55 @@ HWCAP2_LRCPC3 HWCAP2_LSE128 Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011. +HWCAP2_FPMR + Functionality implied by ID_AA64PFR2_EL1.FMR == 0b0001. + +HWCAP2_LUT + Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0001. + +HWCAP2_FAMINMAX + Functionality implied by ID_AA64ISAR3_EL1.FAMINMAX == 0b0001. + +HWCAP2_F8CVT + Functionality implied by ID_AA64FPFR0_EL1.F8CVT == 0b1. + +HWCAP2_F8FMA + Functionality implied by ID_AA64FPFR0_EL1.F8FMA == 0b1. + +HWCAP2_F8DP4 + Functionality implied by ID_AA64FPFR0_EL1.F8DP4 == 0b1. + +HWCAP2_F8DP2 + Functionality implied by ID_AA64FPFR0_EL1.F8DP2 == 0b1. + +HWCAP2_F8E4M3 + Functionality implied by ID_AA64FPFR0_EL1.F8E4M3 == 0b1. + +HWCAP2_F8E5M2 + Functionality implied by ID_AA64FPFR0_EL1.F8E5M2 == 0b1. + +HWCAP2_SME_LUTV2 + Functionality implied by ID_AA64SMFR0_EL1.LUTv2 == 0b1. + +HWCAP2_SME_F8F16 + Functionality implied by ID_AA64SMFR0_EL1.F8F16 == 0b1. + +HWCAP2_SME_F8F32 + Functionality implied by ID_AA64SMFR0_EL1.F8F32 == 0b1. + +HWCAP2_SME_SF8FMA + Functionality implied by ID_AA64SMFR0_EL1.SF8FMA == 0b1. + +HWCAP2_SME_SF8DP4 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1. + +HWCAP2_SME_SF8DP2 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP2 == 0b1. + +HWCAP2_SME_SF8DP4 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1. + + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index 45a7f4932fe0..d33e27c5ce61 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -35,8 +35,9 @@ can be triggered by Linux). For software workarounds that may adversely impact systems unaffected by the erratum in question, a Kconfig entry is added under "Kernel Features" -> "ARM errata workarounds via the alternatives framework". -These are enabled by default and patched in at runtime when an affected -CPU is detected. For less-intrusive workarounds, a Kconfig option is not +With the exception of workarounds for errata deemed "rare" by Arm, these +are enabled by default and patched in at runtime when an affected CPU is +detected. For less-intrusive workarounds, a Kconfig option is not available and the code is structured (preferably with a comment) in such a way that the erratum will not be hit. diff --git a/Documentation/arch/arm64/sme.rst b/Documentation/arch/arm64/sme.rst index 3d0e53ecac4f..be317d457417 100644 --- a/Documentation/arch/arm64/sme.rst +++ b/Documentation/arch/arm64/sme.rst @@ -75,7 +75,7 @@ model features for SME is included in Appendix A. 2. Vector lengths ------------------ -SME defines a second vector length similar to the SVE vector length which is +SME defines a second vector length similar to the SVE vector length which controls the size of the streaming mode SVE vectors and the ZA matrix array. The ZA matrix is square with each side having as many bytes as a streaming mode SVE vector. @@ -238,12 +238,12 @@ prctl(PR_SME_SET_VL, unsigned long arg) bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become unspecified, including both streaming and non-streaming SVE state. Calling PR_SME_SET_VL with vl equal to the thread's current vector - length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. Calling PR_SME_SET_VL with vl equal to the thread's current vector - length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. @@ -379,9 +379,8 @@ The regset data starts with struct user_za_header, containing: /proc/sys/abi/sme_default_vector_length Writing the text representation of an integer to this file sets the system - default vector length to the specified value, unless the value is greater - than the maximum vector length supported by the system in which case the - default vector length is set to that maximum. + default vector length to the specified value rounded to a supported value + using the same rules as for setting vector length via PR_SME_SET_VL. The result can be determined by reopening the file and reading its contents. diff --git a/Documentation/arch/arm64/sve.rst b/Documentation/arch/arm64/sve.rst index 0d9a426e9f85..8d8837fc39ec 100644 --- a/Documentation/arch/arm64/sve.rst +++ b/Documentation/arch/arm64/sve.rst @@ -117,11 +117,6 @@ the SVE instruction set architecture. * The SVE registers are not used to pass arguments to or receive results from any syscall. -* In practice the affected registers/bits will be preserved or will be replaced - with zeros on return from a syscall, but userspace should not make - assumptions about this. The kernel behaviour may vary on a case-by-case - basis. - * All other SVE state of a thread, including the currently configured vector length, the state of the PR_SVE_VL_INHERIT flag, and the deferred vector length (if any), is preserved across all syscalls, subject to the specific @@ -428,9 +423,8 @@ The regset data starts with struct user_sve_header, containing: /proc/sys/abi/sve_default_vector_length Writing the text representation of an integer to this file sets the system - default vector length to the specified value, unless the value is greater - than the maximum vector length supported by the system in which case the - default vector length is set to that maximum. + default vector length to the specified value rounded to a supported value + using the same rules as for setting vector length via PR_SVE_SET_VL. The result can be determined by reopening the file and reading its contents. diff --git a/Documentation/devicetree/bindings/perf/arm,coresight-pmu.yaml b/Documentation/devicetree/bindings/perf/arm,coresight-pmu.yaml new file mode 100644 index 000000000000..985b62990f80 --- /dev/null +++ b/Documentation/devicetree/bindings/perf/arm,coresight-pmu.yaml @@ -0,0 +1,39 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/perf/arm,coresight-pmu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Arm Coresight Performance Monitoring Unit Architecture + +maintainers: + - Robin Murphy <robin.murphy@arm.com> + +properties: + compatible: + const: arm,coresight-pmu + + reg: + items: + - description: Register page 0 + - description: Register page 1, if the PMU implements the dual-page extension + minItems: 1 + + interrupts: + items: + - description: Overflow interrupt + + cpus: + description: If the PMU is associated with a particular CPU or subset of CPUs, + array of phandles to the appropriate CPU node(s) + + reg-io-width: + description: Granularity at which PMU register accesses are single-copy atomic + default: 4 + enum: [4, 8] + +required: + - compatible + - reg + +additionalProperties: false diff --git a/Documentation/devicetree/bindings/perf/starfive,jh8100-starlink-pmu.yaml b/Documentation/devicetree/bindings/perf/starfive,jh8100-starlink-pmu.yaml new file mode 100644 index 000000000000..915c6b814026 --- /dev/null +++ b/Documentation/devicetree/bindings/perf/starfive,jh8100-starlink-pmu.yaml @@ -0,0 +1,46 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/perf/starfive,jh8100-starlink-pmu.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: StarFive JH8100 StarLink PMU + +maintainers: + - Ji Sheng Teoh <jisheng.teoh@starfivetech.com> + +description: + StarFive's JH8100 StarLink PMU integrates one or more CPU cores with a + shared L3 memory system. The PMU support overflow interrupt, up to + 16 programmable 64bit event counters, and an independent 64bit cycle + counter. StarFive's JH8100 StarLink PMU is accessed via MMIO. + +properties: + compatible: + const: starfive,jh8100-starlink-pmu + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + soc { + #address-cells = <2>; + #size-cells = <2>; + + pmu@12900000 { + compatible = "starfive,jh8100-starlink-pmu"; + reg = <0x0 0x12900000 0x0 0x10000>; + interrupts = <34>; + }; + }; diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst index 73203ba1e901..5c4fa9f5d1cd 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -15,6 +15,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file. ============= ================ ============================================== Architecture Level of support Constraints ============= ================ ============================================== +``arm64`` Maintained Little Endian only. ``loongarch`` Maintained - ``um`` Maintained ``x86_64`` only. ``x86`` Maintained ``x86_64`` only. diff --git a/MAINTAINERS b/MAINTAINERS index 98226d076ef6..874f3645bf17 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20974,6 +20974,13 @@ S: Maintained T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ F: Documentation/devicetree/bindings/soc/starfive/ +STARFIVE STARLINK PMU DRIVER +M: Ji Sheng Teoh <jisheng.teoh@starfivetech.com> +S: Maintained +F: Documentation/admin-guide/perf/starfive_starlink_pmu.rst +F: Documentation/devicetree/bindings/perf/starfive,jh8100-starlink-pmu.yaml +F: drivers/perf/starfive_starlink_pmu.c + STARFIVE TRNG DRIVER M: Jia Jie Ho <jiajie.ho@starfivetech.com> S: Supported @@ -561,7 +561,6 @@ KBUILD_CFLAGS += -fno-strict-aliasing KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_RUSTFLAGS := $(rust_common_flags) \ - --target=$(objtree)/scripts/target.json \ -Cpanic=abort -Cembed-bitcode=n -Clto=n \ -Cforce-unwind-tables=n -Ccodegen-units=1 \ -Csymbol-mangling-version=v0 \ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ae0db7c97435..6e1a2edb2be0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -164,7 +164,7 @@ config ARM64 select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE - select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) + select HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE) @@ -198,7 +198,7 @@ config ARM64 if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \ - !CC_OPTIMIZE_FOR_SIZE) + (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE)) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_SAMPLE_FTRACE_DIRECT @@ -229,6 +229,7 @@ config ARM64 select HAVE_FUNCTION_ARG_ACCESS_API select MMU_GATHER_RCU_TABLE_FREE select HAVE_RSEQ + select HAVE_RUST if CPU_LITTLE_ENDIAN select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES @@ -362,7 +363,9 @@ config PGTABLE_LEVELS default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39 default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47 + default 4 if ARM64_16K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48 + default 5 if ARM64_4K_PAGES && ARM64_VA_BITS_52 config ARCH_SUPPORTS_UPROBES def_bool y @@ -390,13 +393,13 @@ config BUILTIN_RETURN_ADDRESS_STRIPS_PAC config KASAN_SHADOW_OFFSET hex depends on KASAN_GENERIC || KASAN_SW_TAGS - default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS - default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS + default 0xdfff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && !KASAN_SW_TAGS + default 0xdfffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && !KASAN_SW_TAGS default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS default 0xdfffffc000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS default 0xdffffff800000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS - default 0xefff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS - default 0xefffc00000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS + default 0xefff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && KASAN_SW_TAGS + default 0xefffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && KASAN_SW_TAGS default 0xeffffe0000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS default 0xefffffc000000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS @@ -541,9 +544,8 @@ config ARM64_ERRATUM_832075 If unsure, say Y. config ARM64_ERRATUM_834220 - bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault (rare)" depends on KVM - default y help This option adds an alternative code sequence to work around ARM erratum 834220 on Cortex-A57 parts up to r1p2. @@ -559,7 +561,7 @@ config ARM64_ERRATUM_834220 as it depends on the alternative framework, which will only patch the kernel if an affected CPU is detected. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1742098 bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence" @@ -686,8 +688,7 @@ config ARM64_WORKAROUND_REPEAT_TLBI bool config ARM64_ERRATUM_2441007 - bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" - default y + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A55 erratum #2441007. @@ -700,11 +701,10 @@ config ARM64_ERRATUM_2441007 Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1286807 - bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" - default y + bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A76 erratum 1286807. @@ -718,6 +718,8 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. + If unsure, say N. + config ARM64_ERRATUM_1463225 bool "Cortex-A76: Software Step might prevent interrupt recognition" default y @@ -737,8 +739,7 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. config ARM64_ERRATUM_1542419 - bool "Neoverse-N1: workaround mis-ordering of instruction fetches" - default y + bool "Neoverse-N1: workaround mis-ordering of instruction fetches (rare)" help This option adds a workaround for ARM Neoverse-N1 erratum 1542419. @@ -750,7 +751,7 @@ config ARM64_ERRATUM_1542419 Workaround the issue by hiding the DIC feature from EL0. This forces user-space to perform cache maintenance. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1508412 bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read" @@ -925,8 +926,7 @@ config ARM64_ERRATUM_2224489 If unsure, say Y. config ARM64_ERRATUM_2441009 - bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" - default y + bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A510 erratum #2441009. @@ -939,7 +939,7 @@ config ARM64_ERRATUM_2441009 Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_2064142 bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" @@ -1278,9 +1278,7 @@ endchoice choice prompt "Virtual address space size" - default ARM64_VA_BITS_39 if ARM64_4K_PAGES - default ARM64_VA_BITS_47 if ARM64_16K_PAGES - default ARM64_VA_BITS_42 if ARM64_64K_PAGES + default ARM64_VA_BITS_52 help Allows choosing one of multiple possible virtual address space sizes. The level of translation table is determined by @@ -1307,7 +1305,7 @@ config ARM64_VA_BITS_48 config ARM64_VA_BITS_52 bool "52-bit" - depends on ARM64_64K_PAGES && (ARM64_PAN || !ARM64_SW_TTBR0_PAN) + depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable 52-bit virtual addressing for userspace when explicitly requested via a hint to mmap(). The kernel will also use 52-bit @@ -1354,10 +1352,11 @@ choice config ARM64_PA_BITS_48 bool "48-bit" + depends on ARM64_64K_PAGES || !ARM64_VA_BITS_52 config ARM64_PA_BITS_52 - bool "52-bit (ARMv8.2)" - depends on ARM64_64K_PAGES + bool "52-bit" + depends on ARM64_64K_PAGES || ARM64_VA_BITS_52 depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable support for a 52-bit physical address space, introduced as @@ -1374,6 +1373,10 @@ config ARM64_PA_BITS default 48 if ARM64_PA_BITS_48 default 52 if ARM64_PA_BITS_52 +config ARM64_LPA2 + def_bool y + depends on ARM64_PA_BITS_52 && !ARM64_64K_PAGES + choice prompt "Endianness" default CPU_LITTLE_ENDIAN diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index a88cdf910687..0e075d3c546b 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -41,6 +41,8 @@ KBUILD_CFLAGS += -mgeneral-regs-only \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) +KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" + KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) @@ -65,7 +67,9 @@ endif ifeq ($(CONFIG_ARM64_BTI_KERNEL),y) KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti + KBUILD_RUSTFLAGS += -Zbranch-protection=bti,pac-ret else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y) + KBUILD_RUSTFLAGS += -Zbranch-protection=pac-ret ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y) KBUILD_CFLAGS += -mbranch-protection=pac-ret else diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index ed69b4636d0f..2c30d617e180 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -76,7 +76,6 @@ CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_VISCONTI=y CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZYNQMP=y -CONFIG_ARM64_VA_BITS_48=y CONFIG_SCHED_MC=y CONFIG_SCHED_SMT=y CONFIG_NUMA=y diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index ecdb3cfcd0f8..8babfbe31f95 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -129,6 +129,4 @@ static inline bool __init __early_cpu_has_rndr(void) return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf; } -u64 kaslr_early_init(void *fdt); - #endif /* _ASM_ARCHRANDOM_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 513787e43329..ab8b396428da 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -38,10 +38,6 @@ msr daifset, #0xf .endm - .macro enable_daif - msr daifclr, #0xf - .endm - /* * Save/restore interrupts. */ @@ -346,20 +342,6 @@ alternative_cb_end .endm /* - * idmap_get_t0sz - get the T0SZ value needed to cover the ID map - * - * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the - * entire ID map region can be mapped. As T0SZ == (64 - #bits used), - * this number conveniently equals the number of leading zeroes in - * the physical address of _end. - */ - .macro idmap_get_t0sz, reg - adrp \reg, _end - orr \reg, \reg, #(1 << VA_BITS_MIN) - 1 - clz \reg, \reg - .endm - -/* * tcr_compute_pa_size - set TCR.(I)PS to the highest supported * ID_AA64MMFR0_EL1.PARange value * @@ -590,18 +572,27 @@ alternative_endif .endm /* - * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD. + * If the kernel is built for 52-bit virtual addressing but the hardware only + * supports 48 bits, we cannot program the pgdir address into TTBR1 directly, + * but we have to add an offset so that the TTBR1 address corresponds with the + * pgdir entry that covers the lowest 48-bit addressable VA. + * + * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an + * additional paging level, and on LPA2/16k pages, we would end up with a root + * level table with only 2 entries, which is suboptimal in terms of TLB + * utilization, so there we fall back to 47 bits of translation if LPA2 is not + * supported. + * * orr is used as it can cover the immediate value (and is idempotent). - * In future this may be nop'ed out when dealing with 52-bit kernel VAs. * ttbr: Value of ttbr to set, modified. */ .macro offset_ttbr1, ttbr, tmp -#ifdef CONFIG_ARM64_VA_BITS_52 - mrs_s \tmp, SYS_ID_AA64MMFR2_EL1 - and \tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) - cbnz \tmp, .Lskipoffs_\@ - orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET -.Lskipoffs_\@ : +#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2) + mrs \tmp, tcr_el1 + and \tmp, \tmp, #TCR_T1SZ_MASK + cmp \tmp, #TCR_T1SZ(VA_BITS_MIN) + orr \tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET + csel \ttbr, \tmp, \ttbr, eq #endif .endm @@ -623,25 +614,13 @@ alternative_endif .macro phys_to_pte, pte, phys #ifdef CONFIG_ARM64_PA_BITS_52 - /* - * We assume \phys is 64K aligned and this is guaranteed by only - * supporting this configuration with 64K pages. - */ - orr \pte, \phys, \phys, lsr #36 - and \pte, \pte, #PTE_ADDR_MASK + orr \pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT + and \pte, \pte, #PHYS_TO_PTE_ADDR_MASK #else mov \pte, \phys #endif .endm - .macro pte_to_phys, phys, pte - and \phys, \pte, #PTE_ADDR_MASK -#ifdef CONFIG_ARM64_PA_BITS_52 - orr \phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT - and \phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT) -#endif - .endm - /* * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU. */ diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index 1abdcd508a11..beb42c62b6ac 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -11,6 +11,7 @@ * 0x004: for installing kprobes * 0x005: for installing uprobes * 0x006: for kprobe software single-step + * 0x007: for kretprobe return * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -23,6 +24,7 @@ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 #define KPROBES_BRK_SS_IMM 0x006 +#define KRETPROBES_BRK_IMM 0x007 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index b1e43f56ee46..96379be913cd 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -52,14 +52,17 @@ struct cpuinfo_arm64 { u64 reg_id_aa64isar0; u64 reg_id_aa64isar1; u64 reg_id_aa64isar2; + u64 reg_id_aa64isar3; u64 reg_id_aa64mmfr0; u64 reg_id_aa64mmfr1; u64 reg_id_aa64mmfr2; u64 reg_id_aa64mmfr3; u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; + u64 reg_id_aa64pfr2; u64 reg_id_aa64zfr0; u64 reg_id_aa64smfr0; + u64 reg_id_aa64fpfr0; struct cpuinfo_32bit aarch32; }; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index bd8d4ca81a48..df62b61ff467 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -17,6 +17,7 @@ #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 +#define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ @@ -768,6 +769,11 @@ static __always_inline bool system_supports_tpidr2(void) return system_supports_sme(); } +static __always_inline bool system_supports_fpmr(void) +{ + return alternative_has_cap_unlikely(ARM64_HAS_FPMR); +} + static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); @@ -905,7 +911,9 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); +extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; +extern struct arm64_ftr_override id_aa64mmfr2_override; extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; @@ -915,9 +923,114 @@ extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; +static inline +u64 arm64_apply_feature_override(u64 val, int feat, int width, + const struct arm64_ftr_override *override) +{ + u64 oval = override->val; + + /* + * When it encounters an invalid override (e.g., an override that + * cannot be honoured due to a missing CPU feature), the early idreg + * override code will set the mask to 0x0 and the value to non-zero for + * the field in question. In order to determine whether the override is + * valid or not for the field we are interested in, we first need to + * disregard bits belonging to other fields. + */ + oval &= GENMASK_ULL(feat + width - 1, feat); + + /* + * The override is valid if all value bits are accounted for in the + * mask. If so, replace the masked bits with the override value. + */ + if (oval == (oval & override->mask)) { + val &= ~override->mask; + val |= oval; + } + + /* Extract the field from the updated value */ + return cpuid_feature_extract_unsigned_field(val, feat); +} + +static inline bool arm64_test_sw_feature_override(int feat) +{ + /* + * Software features are pseudo CPU features that have no underlying + * CPUID system register value to apply the override to. + */ + return arm64_apply_feature_override(0, feat, 4, + &arm64_sw_feature_override); +} + +static inline bool kaslr_disabled_cmdline(void) +{ + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); +} + u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); +static inline bool cpu_has_bti(void) +{ + if (!IS_ENABLED(CONFIG_ARM64_BTI)) + return false; + + return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), + ID_AA64PFR1_EL1_BT_SHIFT, 4, + &id_aa64pfr1_override); +} + +static inline bool cpu_has_pac(void) +{ + u64 isar1, isar2; + + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) + return false; + + isar1 = read_cpuid(ID_AA64ISAR1_EL1); + isar2 = read_cpuid(ID_AA64ISAR2_EL1); + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, + &id_aa64isar2_override); +} + +static inline bool cpu_has_lva(void) +{ + u64 mmfr2; + + mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + mmfr2 &= ~id_aa64mmfr2_override.mask; + mmfr2 |= id_aa64mmfr2_override.val; + return cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_VARange_SHIFT); +} + +static inline bool cpu_has_lpa2(void) +{ +#ifdef CONFIG_ARM64_LPA2 + u64 mmfr0; + int feat; + + mmfr0 = read_sysreg(id_aa64mmfr0_el1); + mmfr0 &= ~id_aa64mmfr0_override.mask; + mmfr0 |= id_aa64mmfr0_override.val; + feat = cpuid_feature_extract_signed_field(mmfr0, + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + + return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; +#else + return false; +#endif +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 97932fbf973d..3f93f4eef953 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -201,16 +201,16 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define COMPAT_ELF_PLATFORM ("v8l") #endif -#ifdef CONFIG_COMPAT - -/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ -#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL - /* AArch32 registers. */ #define COMPAT_ELF_NGREG 18 typedef unsigned int compat_elf_greg_t; typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; +#ifdef CONFIG_COMPAT + +/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ +#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL + /* AArch32 EABI. */ #define EF_ARM_EABI_MASK 0xff000000 int compat_elf_check_arch(const struct elf32_hdr *); diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 353fe08546cf..81606bf7d5ac 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -117,15 +117,9 @@ #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) -#define ESR_ELx_FSC_SEA_TTW0 (0x14) -#define ESR_ELx_FSC_SEA_TTW1 (0x15) -#define ESR_ELx_FSC_SEA_TTW2 (0x16) -#define ESR_ELx_FSC_SEA_TTW3 (0x17) +#define ESR_ELx_FSC_SEA_TTW(n) (0x14 + (n)) #define ESR_ELx_FSC_SECC (0x18) -#define ESR_ELx_FSC_SECC_TTW0 (0x1c) -#define ESR_ELx_FSC_SECC_TTW1 (0x1d) -#define ESR_ELx_FSC_SECC_TTW2 (0x1e) -#define ESR_ELx_FSC_SECC_TTW3 (0x1f) +#define ESR_ELx_FSC_SECC_TTW(n) (0x1c + (n)) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) @@ -394,6 +388,9 @@ static inline bool esr_is_data_abort(unsigned long esr) static inline bool esr_fsc_is_translation_fault(unsigned long esr) { + /* Translation fault, level -1 */ + if ((esr & ESR_ELx_FSC) == 0b101011) + return true; return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; } diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index ad688e157c9b..f296662590c7 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -74,7 +74,7 @@ void do_el0_fpac(struct pt_regs *regs, unsigned long esr); void do_el1_fpac(struct pt_regs *regs, unsigned long esr); void do_el0_mops(struct pt_regs *regs, unsigned long esr); void do_serror(struct pt_regs *regs, unsigned long esr); -void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); +void do_signal(struct pt_regs *regs); void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 58c294a96676..87e307804b99 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -87,6 +87,7 @@ enum fixed_addresses { FIX_PTE, FIX_PMD, FIX_PUD, + FIX_P4D, FIX_PGD, __end_of_fixed_addresses @@ -100,7 +101,6 @@ enum fixed_addresses { #define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE) void __init early_fixmap_init(void); -void __init fixmap_copy(pgd_t *pgdir); #define __early_set_fixmap __set_fixmap diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index b67b89c54e1c..bc69ac368d73 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -21,7 +21,6 @@ #include <linux/stddef.h> #include <linux/types.h> -#ifdef CONFIG_COMPAT /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 @@ -30,7 +29,6 @@ * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) -#endif static inline unsigned long cpacr_save_enable_kernel_sve(void) { @@ -89,6 +87,7 @@ struct cpu_fp_state { void *sve_state; void *sme_state; u64 *svcr; + u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; @@ -154,6 +153,7 @@ extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); extern u64 read_smcr_features(void); diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 84055329cd8b..bd81cf17744a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -59,7 +59,6 @@ static inline void decode_ctrl_reg(u32 reg, /* Watchpoints */ #define ARM_BREAKPOINT_LOAD 1 #define ARM_BREAKPOINT_STORE 2 -#define AARCH64_ESR_ACCESS_MASK (1 << 6) /* Lengths */ #define ARM_BREAKPOINT_LEN_1 0x1 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index cd71e09ea14d..4edd3b61df11 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -142,6 +142,21 @@ #define KERNEL_HWCAP_SVE_B16B16 __khwcap2_feature(SVE_B16B16) #define KERNEL_HWCAP_LRCPC3 __khwcap2_feature(LRCPC3) #define KERNEL_HWCAP_LSE128 __khwcap2_feature(LSE128) +#define KERNEL_HWCAP_FPMR __khwcap2_feature(FPMR) +#define KERNEL_HWCAP_LUT __khwcap2_feature(LUT) +#define KERNEL_HWCAP_FAMINMAX __khwcap2_feature(FAMINMAX) +#define KERNEL_HWCAP_F8CVT __khwcap2_feature(F8CVT) +#define KERNEL_HWCAP_F8FMA __khwcap2_feature(F8FMA) +#define KERNEL_HWCAP_F8DP4 __khwcap2_feature(F8DP4) +#define KERNEL_HWCAP_F8DP2 __khwcap2_feature(F8DP2) +#define KERNEL_HWCAP_F8E4M3 __khwcap2_feature(F8E4M3) +#define KERNEL_HWCAP_F8E5M2 __khwcap2_feature(F8E5M2) +#define KERNEL_HWCAP_SME_LUTV2 __khwcap2_feature(SME_LUTV2) +#define KERNEL_HWCAP_SME_F8F16 __khwcap2_feature(SME_F8F16) +#define KERNEL_HWCAP_SME_F8F32 __khwcap2_feature(SME_F8F32) +#define KERNEL_HWCAP_SME_SF8FMA __khwcap2_feature(SME_SF8FMA) +#define KERNEL_HWCAP_SME_SF8DP4 __khwcap2_feature(SME_SF8DP4) +#define KERNEL_HWCAP_SME_SF8DP2 __khwcap2_feature(SME_SF8DP2) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 3b694511b98f..8d825522c55c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -24,25 +24,29 @@ #define __raw_writeb __raw_writeb static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr) { - asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u8 __iomem *ptr = addr; + asm volatile("strb %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writew __raw_writew static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr) { - asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u16 __iomem *ptr = addr; + asm volatile("strh %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writel __raw_writel static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { - asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u32 __iomem *ptr = addr; + asm volatile("str %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writeq __raw_writeq static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr) { - asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u64 __iomem *ptr = addr; + asm volatile("str %x0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_readb __raw_readb diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 7eefc525a9df..e1b57c13f8a4 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -17,11 +17,9 @@ asmlinkage void kasan_early_init(void); void kasan_init(void); -void kasan_copy_shadow(pgd_t *pgdir); #else static inline void kasan_init(void) { } -static inline void kasan_copy_shadow(pgd_t *pgdir) { } #endif #endif diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 83ddb14b95a5..bf05a77873a4 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -13,28 +13,27 @@ #include <asm/sparsemem.h> /* - * The linear mapping and the start of memory are both 2M aligned (per - * the arm64 booting.txt requirements). Hence we can use section mapping - * with 4K (section size = 2M) but not with 16K (section size = 32M) or - * 64K (section size = 512M). + * The physical and virtual addresses of the start of the kernel image are + * equal modulo 2 MiB (per the arm64 booting.txt requirements). Hence we can + * use section mapping with 4K (section size = 2M) but not with 16K (section + * size = 32M) or 64K (section size = 512M). */ - -/* - * The idmap and swapper page tables need some space reserved in the kernel - * image. Both require pgd, pud (4 levels only) and pmd tables to (section) - * map the kernel. With the 64K page configuration, swapper and idmap need to - * map to pte level. The swapper also maps the FDT (see __create_page_tables - * for more information). Note that the number of ID map translation levels - * could be increased on the fly if system RAM is out of reach for the default - * VA range, so pages required to map highest possible PA are reserved in all - * cases. - */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) +#if defined(PMD_SIZE) && PMD_SIZE <= MIN_KIMG_ALIGN +#define SWAPPER_BLOCK_SHIFT PMD_SHIFT +#define SWAPPER_SKIP_LEVEL 1 #else -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) +#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT +#define SWAPPER_SKIP_LEVEL 0 #endif +#define SWAPPER_BLOCK_SIZE (UL(1) << SWAPPER_BLOCK_SHIFT) +#define SWAPPER_TABLE_SHIFT (SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3) +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL) +#define INIT_IDMAP_PGTABLE_LEVELS (IDMAP_LEVELS - SWAPPER_SKIP_LEVEL) + +#define IDMAP_VA_BITS 48 +#define IDMAP_LEVELS ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS) +#define IDMAP_ROOT_LEVEL (4 - IDMAP_LEVELS) /* * A relocatable kernel may execute from an address that differs from the one at @@ -50,57 +49,39 @@ #define EARLY_ENTRIES(vstart, vend, shift, add) \ (SPAN_NR_ENTRIES(vstart, vend, shift) + (add)) -#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add)) - -#if SWAPPER_PGTABLE_LEVELS > 3 -#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add)) -#else -#define EARLY_PUDS(vstart, vend, add) (0) -#endif +#define EARLY_LEVEL(lvl, lvls, vstart, vend, add) \ + (lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0) -#if SWAPPER_PGTABLE_LEVELS > 2 -#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add)) -#else -#define EARLY_PMDS(vstart, vend, add) (0) -#endif +#define EARLY_PAGES(lvls, vstart, vend, add) (1 /* PGDIR page */ \ + + EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(2, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(1, (lvls), (vstart), (vend), add))/* each entry needs a next level page table */ +#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(SWAPPER_PGTABLE_LEVELS, KIMAGE_VADDR, _end, EXTRA_PAGE) \ + + EARLY_SEGMENT_EXTRA_PAGES)) -#define EARLY_PAGES(vstart, vend, add) ( 1 /* PGDIR page */ \ - + EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \ - + EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \ - + EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */ -#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE)) +#define INIT_IDMAP_DIR_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, _end, 1)) +#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + EARLY_IDMAP_EXTRA_PAGES) * PAGE_SIZE) -/* the initial ID map may need two extra pages if it needs to be extended */ -#if VA_BITS < 48 -#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + 2) * PAGE_SIZE) -#else -#define INIT_IDMAP_DIR_SIZE (INIT_IDMAP_DIR_PAGES * PAGE_SIZE) -#endif -#define INIT_IDMAP_DIR_PAGES EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1) +#define INIT_IDMAP_FDT_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, 0UL, UL(MAX_FDT_SIZE), 1) - 1) +#define INIT_IDMAP_FDT_SIZE ((INIT_IDMAP_FDT_PAGES + EARLY_IDMAP_EXTRA_FDT_PAGES) * PAGE_SIZE) -/* Initial memory map size */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_BLOCK_SHIFT PMD_SHIFT -#define SWAPPER_BLOCK_SIZE PMD_SIZE -#define SWAPPER_TABLE_SHIFT PUD_SHIFT -#else -#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT -#define SWAPPER_BLOCK_SIZE PAGE_SIZE -#define SWAPPER_TABLE_SHIFT PMD_SHIFT -#endif +/* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */ +#define KERNEL_SEGMENT_COUNT 5 +#if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN +#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) /* - * Initial memory map attributes. + * The initial ID map consists of the kernel image, mapped as two separate + * segments, and may appear misaligned wrt the swapper block size. This means + * we need 3 additional pages. The DT could straddle a swapper block boundary, + * so it may need 2. */ -#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN) -#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | PTE_UXN) - -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_RW_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY) +#define EARLY_IDMAP_EXTRA_PAGES 3 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 2 #else -#define SWAPPER_RW_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) +#define EARLY_SEGMENT_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 0 #endif #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3c6f8ba1e479..7f45ce9170bb 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -105,7 +105,7 @@ #define HCRX_GUEST_FLAGS \ (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \ (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0)) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En) +#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) /* TCR_EL2 Registers bits */ #define TCR_EL2_DS (1UL << 32) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index b804fe832184..6f5b41c70103 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -425,15 +425,9 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case ESR_ELx_FSC_EXTABT: - case ESR_ELx_FSC_SEA_TTW0: - case ESR_ELx_FSC_SEA_TTW1: - case ESR_ELx_FSC_SEA_TTW2: - case ESR_ELx_FSC_SEA_TTW3: + case ESR_ELx_FSC_SEA_TTW(-1) ... ESR_ELx_FSC_SEA_TTW(3): case ESR_ELx_FSC_SECC: - case ESR_ELx_FSC_SECC_TTW0: - case ESR_ELx_FSC_SECC_TTW1: - case ESR_ELx_FSC_SECC_TTW2: - case ESR_ELx_FSC_SECC_TTW3: + case ESR_ELx_FSC_SECC_TTW(-1) ... ESR_ELx_FSC_SECC_TTW(3): return true; default: return false; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 21c57b812569..b779cbc2211c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -543,6 +543,7 @@ struct kvm_vcpu_arch { enum fp_type fp_type; unsigned int sve_max_vl; u64 svcr; + u64 fpmr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index d82305ab420f..b850b1b91471 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -30,8 +30,8 @@ * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SHIFT (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT) -#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) >> VMEMMAP_SHIFT) +#define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) +#define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page)) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the @@ -47,14 +47,18 @@ #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (_PAGE_END(VA_BITS_MIN)) #define MODULES_VSIZE (SZ_2G) -#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT))) -#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE) -#define PCI_IO_END (VMEMMAP_START - SZ_8M) -#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) -#define FIXADDR_TOP (VMEMMAP_START - SZ_32M) +#define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE) +#define VMEMMAP_END (-UL(SZ_1G)) +#define PCI_IO_START (VMEMMAP_END + SZ_8M) +#define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE) +#define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 +#ifdef CONFIG_ARM64_16K_PAGES +#define VA_BITS_MIN (47) +#else #define VA_BITS_MIN (48) +#endif #else #define VA_BITS_MIN (VA_BITS) #endif @@ -209,9 +213,20 @@ #include <asm/boot.h> #include <asm/bug.h> #include <asm/sections.h> +#include <asm/sysreg.h> + +static inline u64 __pure read_tcr(void) +{ + u64 tcr; + + // read_sysreg() uses asm volatile, so avoid it here + asm("mrs %0, tcr_el1" : "=r"(tcr)); + return tcr; +} #if VA_BITS > 48 -extern u64 vabits_actual; +// For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here +#define vabits_actual (64 - ((read_tcr() >> 16) & 63)) #else #define vabits_actual ((u64)VA_BITS) #endif diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2fcf51231d6e..65977c7783c5 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -71,10 +71,46 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); -extern bool kaslr_requires_kpti(void); + +/* + * This check is triggered during the early boot before the cpufeature + * is initialised. Checking the status on the local CPU allows the boot + * CPU to detect the need for non-global mappings and thus avoiding a + * pagetable re-write after all the CPUs are booted. This check will be + * anyway run on individual CPUs, allowing us to get the consistent + * state once the SMP CPUs are up and thus make the switch to non-global + * mappings if required. + */ +static inline bool kaslr_requires_kpti(void) +{ + /* + * E0PD does a similar job to KPTI so can be used instead + * where available. + */ + if (IS_ENABLED(CONFIG_ARM64_E0PD)) { + u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + if (cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_E0PD_SHIFT)) + return false; + } + + /* + * Systems affected by Cavium erratum 24756 are incompatible + * with KPTI. + */ + if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { + extern const struct midr_range cavium_erratum_27456_cpus[]; + + if (is_midr_in_range_list(read_cpuid_id(), + cavium_erratum_27456_cpus)) + return false; + } + + return true; +} #define INIT_MM_CONTEXT(name) \ - .pgd = init_pg_dir, + .pgd = swapper_pg_dir, #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 9ce4200508b1..c768d16b81a4 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -61,11 +61,9 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) } /* - * TCR.T0SZ value to use when the ID map is active. Usually equals - * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in - * physical memory, in which case it will be smaller. + * TCR.T0SZ value to use when the ID map is active. */ -extern int idmap_t0sz; +#define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. @@ -110,18 +108,13 @@ static inline void cpu_uninstall_idmap(void) cpu_switch_mm(mm->pgd, mm); } -static inline void __cpu_install_idmap(pgd_t *idmap) +static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(lm_alias(idmap), &init_mm); -} - -static inline void cpu_install_idmap(void) -{ - __cpu_install_idmap(idmap_pg_dir); + cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* @@ -148,51 +141,21 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) isb(); } -/* - * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, - * avoiding the possibility of conflicting TLB entries being allocated. - */ -static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) -{ - typedef void (ttbr_replace_func)(phys_addr_t); - extern ttbr_replace_func idmap_cpu_replace_ttbr1; - ttbr_replace_func *replace_phys; - unsigned long daif; - - /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ - phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); - - if (cnp) - ttbr1 |= TTBR_CNP_BIT; - - replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); - - __cpu_install_idmap(idmap); - - /* - * We really don't want to take *any* exceptions while TTBR1 is - * in the process of being replaced so mask everything. - */ - daif = local_daif_save(); - replace_phys(ttbr1); - local_daif_restore(daif); - - cpu_uninstall_idmap(); -} +void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { - __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true); + __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } -static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); - __cpu_replace_ttbr1(pgdp, idmap, false); + __cpu_replace_ttbr1(pgdp, false); } /* diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 237224484d0f..8ff5f2a2579e 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -14,6 +14,7 @@ #include <asm/tlbflush.h> #define __HAVE_ARCH_PGD_FREE +#define __HAVE_ARCH_PUD_FREE #include <asm-generic/pgalloc.h> #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) @@ -43,7 +44,8 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { - set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); } static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) @@ -53,6 +55,13 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN; __p4d_populate(p4dp, __pa(pudp), p4dval); } + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!pgtable_l4_enabled()) + return; + __pud_free(mm, pud); +} #else static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { @@ -60,6 +69,47 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(__phys_to_pgd_val(p4dp) | prot)); +} + +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp) +{ + pgdval_t pgdval = PGD_TYPE_TABLE; + + pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN; + __pgd_populate(pgdp, __pa(p4dp), pgdval); +} + +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_PGTABLE_USER; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + return (p4d_t *)get_zeroed_page(gfp); +} + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + free_page((unsigned long)p4d); +} + +#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#else +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + BUILD_BUG(); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index e4944d517c99..ef207a0d4f0d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -26,10 +26,10 @@ #define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3)) /* - * Size mapped by an entry at level n ( 0 <= n <= 3) + * Size mapped by an entry at level n ( -1 <= n <= 3) * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits * in the final page. The maximum number of translation levels supported by - * the architecture is 4. Hence, starting at level n, we have further + * the architecture is 5. Hence, starting at level n, we have further * ((4 - n) - 1) levels of translation excluding the offset within the page. * So, the total number of bits mapped by an entry at level n is : * @@ -62,9 +62,16 @@ #define PTRS_PER_PUD (1 << (PAGE_SHIFT - 3)) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +#define P4D_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(0) +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) +#define PTRS_PER_P4D (1 << (PAGE_SHIFT - 3)) +#endif + /* * PGDIR_SHIFT determines the size a top-level page table entry can map - * (depending on the configuration, this level can be 0, 1 or 2). + * (depending on the configuration, this level can be -1, 0, 1 or 2). */ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) @@ -87,6 +94,15 @@ /* * Hardware page table definitions. * + * Level -1 descriptor (PGD). + */ +#define PGD_TYPE_TABLE (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_BIT (_AT(pgdval_t, 1) << 1) +#define PGD_TYPE_MASK (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_PXN (_AT(pgdval_t, 1) << 59) +#define PGD_TABLE_UXN (_AT(pgdval_t, 1) << 60) + +/* * Level 0 descriptor (P4D). */ #define P4D_TYPE_TABLE (_AT(p4dval_t, 3) << 0) @@ -155,13 +171,17 @@ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ -#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) +#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) #ifdef CONFIG_ARM64_PA_BITS_52 +#ifdef CONFIG_ARM64_64K_PAGES #define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12) -#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #define PTE_ADDR_HIGH_SHIFT 36 +#define PHYS_TO_PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #else -#define PTE_ADDR_MASK PTE_ADDR_LOW +#define PTE_ADDR_HIGH (_AT(pteval_t, 0x3) << 8) +#define PTE_ADDR_HIGH_SHIFT 42 +#define PHYS_TO_PTE_ADDR_MASK GENMASK_ULL(49, 8) +#endif #endif /* @@ -284,6 +304,7 @@ #define TCR_E0PD1 (UL(1) << 56) #define TCR_TCMA0 (UL(1) << 57) #define TCR_TCMA1 (UL(1) << 58) +#define TCR_DS (UL(1) << 59) /* * TTBR. diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 483dbfa39c4c..dd9ee67d1d87 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -30,8 +30,8 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) -#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) @@ -57,10 +57,6 @@ #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) -#ifdef __ASSEMBLY__ -#define PTE_MAYBE_NG 0 -#endif - #ifndef __ASSEMBLY__ #include <asm/cpufeature.h> @@ -71,7 +67,19 @@ extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) +#ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false +#define PTE_MAYBE_SHARED PTE_SHARED +#define PMD_MAYBE_SHARED PMD_SECT_S +#else +static inline bool __pure lpa2_is_enabled(void) +{ + return read_tcr() & TCR_DS; +} + +#define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) +#define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#endif /* * If we have userspace only BTI we don't want to mark kernel pages diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h index b8f158ae2527..6d6d4065b0cb 100644 --- a/arch/arm64/include/asm/pgtable-types.h +++ b/arch/arm64/include/asm/pgtable-types.h @@ -36,6 +36,12 @@ typedef struct { pudval_t pud; } pud_t; #define __pud(x) ((pud_t) { (x) } ) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; +#define p4d_val(x) ((x).p4d) +#define __p4d(x) ((p4d_t) { (x) } ) +#endif + typedef struct { pgdval_t pgd; } pgd_t; #define pgd_val(x) ((x).pgd) #define __pgd(x) ((pgd_t) { (x) } ) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 79ce70fbb751..8bec85350865 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -18,11 +18,15 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space - * and fixed mappings + * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (VMEMMAP_START - SZ_256M) +#if VA_BITS == VA_BITS_MIN +#define VMALLOC_END (VMEMMAP_START - SZ_8M) +#else +#define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) +#define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) +#endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) @@ -76,15 +80,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { + pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { - return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK; + return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else -#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK) +#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif @@ -616,12 +621,12 @@ static inline bool pud_table(pud_t pud) { return true; } PUD_TYPE_TABLE) #endif -extern pgd_t init_pg_dir[PTRS_PER_PGD]; +extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; -extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; -extern pgd_t tramp_pg_dir[PTRS_PER_PGD]; -extern pgd_t reserved_pg_dir[PTRS_PER_PGD]; +extern pgd_t swapper_pg_dir[]; +extern pgd_t idmap_pg_dir[]; +extern pgd_t tramp_pg_dir[]; +extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); @@ -694,14 +699,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) +static inline bool pgtable_l4_enabled(void); + static inline void set_pud(pud_t *pudp, pud_t pud) { -#ifdef __PAGETABLE_PUD_FOLDED - if (in_swapper_pgdir(pudp)) { + if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } -#endif /* __PAGETABLE_PUD_FOLDED */ WRITE_ONCE(*pudp, pud); @@ -754,12 +759,27 @@ static inline pmd_t *pud_pgtable(pud_t pud) #if CONFIG_PGTABLE_LEVELS > 3 +static __always_inline bool pgtable_l4_enabled(void) +{ + if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) + return true; + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_pud_folded(const struct mm_struct *mm) +{ + return !pgtable_l4_enabled(); +} +#define mm_pud_folded mm_pud_folded + #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) -#define p4d_none(p4d) (!p4d_val(p4d)) -#define p4d_bad(p4d) (!(p4d_val(p4d) & 2)) -#define p4d_present(p4d) (p4d_val(p4d)) +#define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { @@ -775,7 +795,8 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline void p4d_clear(p4d_t *p4dp) { - set_p4d(p4dp, __p4d(0)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) @@ -783,27 +804,75 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d) return __p4d_to_phys(p4d); } +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) +{ + return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); +} + static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } -/* Find an entry in the first-level page table. */ -#define pud_offset_phys(dir, addr) (p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) +static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) +{ + BUG_ON(!pgtable_l4_enabled()); -#define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) -#define pud_set_fixmap_offset(p4d, addr) pud_set_fixmap(pud_offset_phys(p4d, addr)) -#define pud_clear_fixmap() clear_fixmap(FIX_PUD) + return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); +} -#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) +static inline +pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) +{ + return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); +} +#define pud_offset pud_offset + +static inline pud_t *pud_set_fixmap(unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return NULL; + return (pud_t *)set_fixmap_offset(FIX_PUD, addr); +} + +static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return pud_set_fixmap(pud_offset_phys(p4dp, addr)); +} + +static inline void pud_clear_fixmap(void) +{ + if (pgtable_l4_enabled()) + clear_fixmap(FIX_PUD); +} /* use ONLY for statically allocated translation tables */ -#define pud_offset_kimg(dir,addr) ((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr)))) +static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); +} + +#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else +static inline bool pgtable_l4_enabled(void) { return false; } + #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) -#define pgd_page_paddr(pgd) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL @@ -814,6 +883,122 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static __always_inline bool pgtable_l5_enabled(void) +{ + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_p4d_folded(const struct mm_struct *mm) +{ + return !pgtable_l5_enabled(); +} +#define mm_p4d_folded mm_p4d_folded + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) + +#define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_present(pgd) (!pgd_none(pgd)) + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (in_swapper_pgdir(pgdp)) { + set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); + return; + } + + WRITE_ONCE(*pgdp, pgd); + dsb(ishst); + isb(); +} + +static inline void pgd_clear(pgd_t *pgdp) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(0)); +} + +static inline phys_addr_t pgd_page_paddr(pgd_t pgd) +{ + return __pgd_to_phys(pgd); +} + +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) +{ + return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); +} + +static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) +{ + BUG_ON(!pgtable_l5_enabled()); + + return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); +} + +static inline +p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); +} +#define p4d_offset_lockless p4d_offset_lockless + +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) +{ + return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); +} + +static inline p4d_t *p4d_set_fixmap(unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return NULL; + return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); +} + +static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); +} + +static inline void p4d_clear_fixmap(void) +{ + if (pgtable_l5_enabled()) + clear_fixmap(FIX_P4D); +} + +/* use ONLY for statically allocated translation tables */ +static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); +} + +#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) + +#else + +static inline bool pgtable_l5_enabled(void) { return false; } + +/* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ +#define p4d_set_fixmap(addr) NULL +#define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) +#define p4d_clear_fixmap() + +#define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5b0a04810b23..f77371232d8c 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -155,6 +155,8 @@ struct thread_struct { struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; + u64 fpmr; + unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; @@ -253,6 +255,8 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + + sizeof_field(struct thread_struct, uw.fpmr) + + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index 3fdae5fe3142..2e010ea76be2 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -33,37 +33,11 @@ #include <asm/cpufeature.h> #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS -static inline bool should_patch_pac_into_scs(void) -{ - u64 reg; - - /* - * We only enable the shadow call stack dynamically if we are running - * on a system that does not implement PAC or BTI. PAC and SCS provide - * roughly the same level of protection, and BTI relies on the PACIASP - * instructions serving as landing pads, preventing us from patching - * those instructions into something else. - */ - reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) | - SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg)) - return false; - - reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg)) - return false; - - if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { - reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1); - if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT)) - return false; - } - return true; -} - static inline void dynamic_scs_init(void) { - if (should_patch_pac_into_scs()) { + extern bool __pi_dynamic_scs_is_enabled; + + if (__pi_dynamic_scs_is_enabled) { pr_info("Enabling dynamic shadow call stack\n"); static_branch_enable(&dynamic_scs_enabled); } @@ -72,8 +46,8 @@ static inline void dynamic_scs_init(void) static inline void dynamic_scs_init(void) {} #endif -int scs_patch(const u8 eh_frame[], int size); -asmlinkage void scs_patch_vmlinux(void); +int __pi_scs_patch(const u8 eh_frame[], int size); +asmlinkage void __pi_scs_patch_vmlinux(void); #endif /* __ASSEMBLY __ */ diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index 2e4d7da74fb8..ba269a7a3201 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -7,9 +7,6 @@ #include <uapi/asm/setup.h> -void *get_early_fdt_ptr(void); -void early_fdt_map(u64 dt_phys); - /* * These two variables are used in the head.S file. */ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 0150deb332af..a947c6e784ed 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -103,6 +103,9 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, { struct ptdesc *ptdesc = virt_to_ptdesc(pudp); + if (!pgtable_l4_enabled()) + return; + pagetable_pud_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 5023599fa278..285610e626f5 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -107,5 +107,20 @@ #define HWCAP2_SVE_B16B16 (1UL << 45) #define HWCAP2_LRCPC3 (1UL << 46) #define HWCAP2_LSE128 (1UL << 47) +#define HWCAP2_FPMR (1UL << 48) +#define HWCAP2_LUT (1UL << 49) +#define HWCAP2_FAMINMAX (1UL << 50) +#define HWCAP2_F8CVT (1UL << 51) +#define HWCAP2_F8FMA (1UL << 52) +#define HWCAP2_F8DP4 (1UL << 53) +#define HWCAP2_F8DP2 (1UL << 54) +#define HWCAP2_F8E4M3 (1UL << 55) +#define HWCAP2_F8E5M2 (1UL << 56) +#define HWCAP2_SME_LUTV2 (1UL << 57) +#define HWCAP2_SME_F8F16 (1UL << 58) +#define HWCAP2_SME_F8F32 (1UL << 59) +#define HWCAP2_SME_SF8FMA (1UL << 60) +#define HWCAP2_SME_SF8DP4 (1UL << 61) +#define HWCAP2_SME_SF8DP2 (1UL << 62) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index f23c1dc3f002..8a45b7a411e0 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -152,6 +152,14 @@ struct tpidr2_context { __u64 tpidr2; }; +/* FPMR context */ +#define FPMR_MAGIC 0x46504d52 + +struct fpmr_context { + struct _aarch64_ctx head; + __u64 fpmr; +}; + #define ZA_MAGIC 0x54366345 struct za_context { diff --git a/arch/arm64/include/uapi/asm/sve_context.h b/arch/arm64/include/uapi/asm/sve_context.h index 754ab751b523..72aefc081061 100644 --- a/arch/arm64/include/uapi/asm/sve_context.h +++ b/arch/arm64/include/uapi/asm/sve_context.h @@ -13,6 +13,17 @@ #define __SVE_VQ_BYTES 16 /* number of bytes per quadword */ +/* + * Yes, __SVE_VQ_MAX is 512 QUADWORDS. + * + * To help ensure forward portability, this is much larger than the + * current maximum value defined by the SVE architecture. While arrays + * or static allocations can be sized based on this value, watch out! + * It will waste a surprisingly large amount of memory. + * + * Dynamic sizing based on the actual runtime vector length is likely to + * be preferable for most purposes. + */ #define __SVE_VQ_MIN 1 #define __SVE_VQ_MAX 512 diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 467cb7117273..14b4a179bad3 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -33,8 +33,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ - syscall.o proton-pack.o idreg-override.o idle.o \ - patching.o + syscall.o proton-pack.o idle.o patching.o pi/ obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o @@ -57,7 +56,7 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o -obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o pi/ +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_ELF_CORE) += elfcore.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ @@ -72,14 +71,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o -obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o - -# We need to prevent the SCS patching code from patching itself. Using -# -mbranch-protection=none here to avoid the patchable PAC opcodes from being -# generated triggers an issue with full LTO on Clang, which stops emitting PAC -# instructions altogether. So disable LTO as well for the compilation unit. -CFLAGS_patch-scs.o += -mbranch-protection=none -CFLAGS_REMOVE_patch-scs.o += $(CC_FLAGS_LTO) # Force dependency (vdso*-wrap.S includes vdso.so through incbin) $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 5a7dbbe0ce63..81496083c041 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,8 +75,8 @@ int main(void) DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); - DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_PC, offsetof(struct pt_regs, pc)); + DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 8d1a634a403e..d6679d8b737e 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -220,6 +220,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_LUT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), @@ -234,6 +235,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0), @@ -267,6 +273,11 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64pfr2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR2_EL1_FPMR_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0), @@ -295,6 +306,8 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUTv2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0), @@ -307,6 +320,10 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F16_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0), @@ -316,6 +333,22 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8CVT_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -655,13 +688,15 @@ static const struct arm64_ftr_bits ftr_raz[] = { #define ARM64_FTR_REG(id, table) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) -struct arm64_ftr_override __ro_after_init id_aa64mmfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64zfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64smfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64isar1_override; -struct arm64_ftr_override __ro_after_init id_aa64isar2_override; +struct arm64_ftr_override id_aa64mmfr0_override; +struct arm64_ftr_override id_aa64mmfr1_override; +struct arm64_ftr_override id_aa64mmfr2_override; +struct arm64_ftr_override id_aa64pfr0_override; +struct arm64_ftr_override id_aa64pfr1_override; +struct arm64_ftr_override id_aa64zfr0_override; +struct arm64_ftr_override id_aa64smfr0_override; +struct arm64_ftr_override id_aa64isar1_override; +struct arm64_ftr_override id_aa64isar2_override; struct arm64_ftr_override arm64_sw_feature_override; @@ -702,10 +737,12 @@ static const struct __ftr_reg_entry { &id_aa64pfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), + ARM64_FTR_REG(SYS_ID_AA64PFR2_EL1, ftr_id_aa64pfr2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0, &id_aa64zfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0, &id_aa64smfr0_override), + ARM64_FTR_REG(SYS_ID_AA64FPFR0_EL1, ftr_id_aa64fpfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -717,12 +754,15 @@ static const struct __ftr_reg_entry { &id_aa64isar1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), + ARM64_FTR_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3), /* Op1 = 0, CRn = 0, CRm = 7 */ - ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0, + &id_aa64mmfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1, &id_aa64mmfr1_override), - ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2, + &id_aa64mmfr2_override), ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), /* Op1 = 1, CRn = 0, CRm = 0 */ @@ -1043,14 +1083,17 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0); init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2); + init_cpu_ftr_reg(SYS_ID_AA64ISAR3_EL1, info->reg_id_aa64isar3); init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); + init_cpu_ftr_reg(SYS_ID_AA64PFR2_EL1, info->reg_id_aa64pfr2); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); + init_cpu_ftr_reg(SYS_ID_AA64FPFR0_EL1, info->reg_id_aa64fpfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -1272,6 +1315,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64isar1, boot->reg_id_aa64isar1); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu, info->reg_id_aa64isar2, boot->reg_id_aa64isar2); + taint |= check_update_ftr_reg(SYS_ID_AA64ISAR3_EL1, cpu, + info->reg_id_aa64isar3, boot->reg_id_aa64isar3); /* * Differing PARange support is fine as long as all peripherals and @@ -1291,6 +1336,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1); + taint |= check_update_ftr_reg(SYS_ID_AA64PFR2_EL1, cpu, + info->reg_id_aa64pfr2, boot->reg_id_aa64pfr2); taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); @@ -1298,6 +1345,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64FPFR0_EL1, cpu, + info->reg_id_aa64fpfr0, boot->reg_id_aa64fpfr0); + /* Probe vector lengths */ if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { @@ -1410,8 +1460,10 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); + read_sysreg_case(SYS_ID_AA64PFR2_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); read_sysreg_case(SYS_ID_AA64SMFR0_EL1); + read_sysreg_case(SYS_ID_AA64FPFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); @@ -1421,6 +1473,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64ISAR0_EL1); read_sysreg_case(SYS_ID_AA64ISAR1_EL1); read_sysreg_case(SYS_ID_AA64ISAR2_EL1); + read_sysreg_case(SYS_ID_AA64ISAR3_EL1); read_sysreg_case(SYS_CNTFRQ_EL0); read_sysreg_case(SYS_CTR_EL0); @@ -1620,46 +1673,6 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) return has_cpuid_feature(entry, scope); } -/* - * This check is triggered during the early boot before the cpufeature - * is initialised. Checking the status on the local CPU allows the boot - * CPU to detect the need for non-global mappings and thus avoiding a - * pagetable re-write after all the CPUs are booted. This check will be - * anyway run on individual CPUs, allowing us to get the consistent - * state once the SMP CPUs are up and thus make the switch to non-global - * mappings if required. - */ -bool kaslr_requires_kpti(void) -{ - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return false; - - /* - * E0PD does a similar job to KPTI so can be used instead - * where available. - */ - if (IS_ENABLED(CONFIG_ARM64_E0PD)) { - u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); - if (cpuid_feature_extract_unsigned_field(mmfr2, - ID_AA64MMFR2_EL1_E0PD_SHIFT)) - return false; - } - - /* - * Systems affected by Cavium erratum 24756 are incompatible - * with KPTI. - */ - if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { - extern const struct midr_range cavium_erratum_27456_cpus[]; - - if (is_midr_in_range_list(read_cpuid_id(), - cavium_erratum_27456_cpus)) - return false; - } - - return kaslr_enabled(); -} - static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ @@ -1712,7 +1725,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } /* Useful for KASLR robustness */ - if (kaslr_requires_kpti()) { + if (kaslr_enabled() && kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; @@ -1801,6 +1814,11 @@ static int __init __kpti_install_ng_mappings(void *__unused) pgd_t *kpti_ng_temp_pgd; u64 alloc = 0; + if (levels == 5 && !pgtable_l5_enabled()) + levels = 4; + else if (levels == 4 && !pgtable_l4_enabled()) + levels = 3; + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { @@ -1814,9 +1832,9 @@ static int __init __kpti_install_ng_mappings(void *__unused) // // The physical pages are laid out as follows: // - // +--------+-/-------+-/------ +-\\--------+ - // : PTE[] : | PMD[] : | PUD[] : || PGD[] : - // +--------+-\-------+-\------ +-//--------+ + // +--------+-/-------+-/------ +-/------ +-\\\--------+ + // : PTE[] : | PMD[] : | PUD[] : | P4D[] : ||| PGD[] : + // +--------+-\-------+-\------ +-\------ +-///--------+ // ^ // The first page is mapped into this hierarchy at a PMD_SHIFT // aligned virtual address, so that we can manipulate the PTE @@ -2042,14 +2060,7 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap, static bool hvhe_possible(const struct arm64_cpu_capabilities *entry, int __unused) { - u64 val; - - val = read_sysreg(id_aa64mmfr1_el1); - if (!cpuid_feature_extract_unsigned_field(val, ID_AA64MMFR1_EL1_VH_SHIFT)) - return false; - - val = arm64_sw_feature_override.val & arm64_sw_feature_override.mask; - return cpuid_feature_extract_unsigned_field(val, ARM64_SW_FEATURE_OVERRIDE_HVHE); + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE); } #ifdef CONFIG_ARM64_PAN @@ -2739,6 +2750,32 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_lpa2, }, + { + .desc = "FPMR", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_HAS_FPMR, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_fpmr, + ARM64_CPUID_FIELDS(ID_AA64PFR2_EL1, FPMR, IMP) + }, +#ifdef CONFIG_ARM64_VA_BITS_52 + { + .capability = ARM64_HAS_VA52, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .matches = has_cpuid_feature, +#ifdef CONFIG_ARM64_64K_PAGES + .desc = "52-bit Virtual Addressing (LVA)", + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, VARange, 52) +#else + .desc = "52-bit Virtual Addressing (LPA2)", +#ifdef CONFIG_ARM64_4K_PAGES + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN4, 52_BIT) +#else + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN16, 52_BIT) +#endif +#endif + }, +#endif {}, }; @@ -2822,6 +2859,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(ID_AA64PFR2_EL1, FPMR, IMP, CAP_HWCAP, KERNEL_HWCAP_FPMR), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT), @@ -2835,6 +2873,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM), + HWCAP_CAP(ID_AA64ISAR2_EL1, LUT, IMP, CAP_HWCAP, KERNEL_HWCAP_LUT), + HWCAP_CAP(ID_AA64ISAR3_EL1, FAMINMAX, IMP, CAP_HWCAP, KERNEL_HWCAP_FAMINMAX), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), @@ -2875,6 +2915,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -2882,12 +2923,23 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), #endif /* CONFIG_ARM64_SME */ + HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), {}, }; @@ -3052,13 +3104,9 @@ static void __init enable_cpu_capabilities(u16 scope_mask) boot_scope = !!(scope_mask & SCOPE_BOOT_CPU); for (i = 0; i < ARM64_NCAPS; i++) { - unsigned int num; - caps = cpucap_ptrs[i]; - if (!caps || !(caps->type & scope_mask)) - continue; - num = caps->capability; - if (!cpus_have_cap(num)) + if (!caps || !(caps->type & scope_mask) || + !cpus_have_cap(caps->capability)) continue; if (boot_scope && caps->cpu_enable) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 47043c0d95ec..f0abb150f73e 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -128,6 +128,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SVE_B16B16] = "sveb16b16", [KERNEL_HWCAP_LRCPC3] = "lrcpc3", [KERNEL_HWCAP_LSE128] = "lse128", + [KERNEL_HWCAP_FPMR] = "fpmr", + [KERNEL_HWCAP_LUT] = "lut", + [KERNEL_HWCAP_FAMINMAX] = "faminmax", + [KERNEL_HWCAP_F8CVT] = "f8cvt", + [KERNEL_HWCAP_F8FMA] = "f8fma", + [KERNEL_HWCAP_F8DP4] = "f8dp4", + [KERNEL_HWCAP_F8DP2] = "f8dp2", + [KERNEL_HWCAP_F8E4M3] = "f8e4m3", + [KERNEL_HWCAP_F8E5M2] = "f8e5m2", + [KERNEL_HWCAP_SME_LUTV2] = "smelutv2", + [KERNEL_HWCAP_SME_F8F16] = "smef8f16", + [KERNEL_HWCAP_SME_F8F32] = "smef8f32", + [KERNEL_HWCAP_SME_SF8FMA] = "smesf8fma", + [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", + [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", }; #ifdef CONFIG_COMPAT @@ -443,14 +458,17 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1); info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1); info->reg_id_aa64isar2 = read_cpuid(ID_AA64ISAR2_EL1); + info->reg_id_aa64isar3 = read_cpuid(ID_AA64ISAR3_EL1); info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1); info->reg_id_aa64mmfr3 = read_cpuid(ID_AA64MMFR3_EL1); info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); + info->reg_id_aa64pfr2 = read_cpuid(ID_AA64PFR2_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); + info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 0fc94207e69a..b77a15955f28 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -10,6 +10,7 @@ #include <linux/linkage.h> #include <linux/lockdep.h> #include <linux/ptrace.h> +#include <linux/resume_user_mode.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/thread_info.h> @@ -126,16 +127,49 @@ static __always_inline void __exit_to_user_mode(void) lockdep_hardirqs_on(CALLER_ADDR0); } +static void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) +{ + do { + local_irq_enable(); + + if (thread_flags & _TIF_NEED_RESCHED) + schedule(); + + if (thread_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + if (thread_flags & _TIF_MTE_ASYNC_FAULT) { + clear_thread_flag(TIF_MTE_ASYNC_FAULT); + send_sig_fault(SIGSEGV, SEGV_MTEAERR, + (void __user *)NULL, current); + } + + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + do_signal(regs); + + if (thread_flags & _TIF_NOTIFY_RESUME) + resume_user_mode_work(regs); + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + + local_irq_disable(); + thread_flags = read_thread_flags(); + } while (thread_flags & _TIF_WORK_MASK); +} + static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long flags; - local_daif_mask(); + local_irq_disable(); flags = read_thread_flags(); if (unlikely(flags & _TIF_WORK_MASK)) do_notify_resume(regs, flags); + local_daif_mask(); + lockdep_sys_exit(); } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index f27acca550d5..ebb0158997ca 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -359,6 +359,9 @@ static void task_fpsimd_load(void) WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); + if (system_supports_fpmr()) + write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: @@ -446,6 +449,9 @@ static void fpsimd_save_user_state(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; + if (system_supports_fpmr()) + *(last->fpmr) = read_sysreg_s(SYS_FPMR); + /* * If a task is in a syscall the ABI allows us to only * preserve the state shared with FPSIMD so don't bother @@ -688,6 +694,12 @@ static void sve_to_fpsimd(struct task_struct *task) } } +void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p) +{ + write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK, + SYS_SCTLR_EL1); +} + #ifdef CONFIG_ARM64_SVE /* * Call __sve_free() directly only if you know task can't be scheduled @@ -1134,6 +1146,8 @@ void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); + + write_sysreg_s(0, SYS_ZCR_EL1); } void __init sve_setup(void) @@ -1245,6 +1259,9 @@ void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p) write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); + /* Ensure all bits in SMCR are set to known values */ + write_sysreg_s(0, SYS_SMCR_EL1); + /* Allow EL0 to access TPIDR2 */ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); isb(); @@ -1696,6 +1713,7 @@ static void fpsimd_bind_task_to_cpu(void) last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; + last->fpmr = ¤t->thread.uw.fpmr; last->fp_type = ¤t->thread.fp_type; last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index cab7f91949d8..405e9bce8c73 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -80,28 +80,42 @@ * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 - * x22 create_idmap() .. start_kernel() ID map VA of the DT blob - * x23 primary_entry() .. start_kernel() physical misalignment/KASLR offset - * x24 __primary_switch() linear map KASLR seed - * x25 primary_entry() .. start_kernel() supported VA size - * x28 create_idmap() callee preserved temp register */ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args - bl create_idmap + + adrp x1, early_init_stack + mov sp, x1 + mov x29, xzr + adrp x0, init_idmap_pg_dir + mov x1, xzr + bl __pi_create_init_idmap + + /* + * If the page tables have been populated with non-cacheable + * accesses (MMU disabled), invalidate those tables again to + * remove any speculatively loaded cache lines. + */ + cbnz x19, 0f + dmb sy + mov x1, x0 // end of used region + adrp x0, init_idmap_pg_dir + adr_l x2, dcache_inval_poc + blr x2 + b 1f /* * If we entered with the MMU and caches on, clean the ID mapped part * of the primary boot code to the PoC so we can safely execute it with * the MMU off. */ - cbz x19, 0f - adrp x0, __idmap_text_start +0: adrp x0, __idmap_text_start adr_l x1, __idmap_text_end adr_l x2, dcache_clean_poc blr x2 -0: mov x0, x19 + +1: mov x0, x19 bl init_kernel_el // w0=cpu_boot_mode mov x20, x0 @@ -111,14 +125,6 @@ SYM_CODE_START(primary_entry) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ -#if VA_BITS > 48 - mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, ID_AA64MMFR2_EL1_VARange_MASK - mov x0, #VA_BITS - mov x25, #VA_BITS_MIN - csel x25, x25, x0, eq - mov x0, x25 -#endif bl __cpu_setup // initialise processor b __primary_switch SYM_CODE_END(primary_entry) @@ -177,267 +183,6 @@ SYM_CODE_START_LOCAL(preserve_boot_args) ret SYM_CODE_END(preserve_boot_args) -SYM_FUNC_START_LOCAL(clear_page_tables) - /* - * Clear the init page tables. - */ - adrp x0, init_pg_dir - adrp x1, init_pg_end - sub x2, x1, x0 - mov x1, xzr - b __pi_memset // tail call -SYM_FUNC_END(clear_page_tables) - -/* - * Macro to populate page table entries, these entries can be pointers to the next level - * or last level entries pointing to physical memory. - * - * tbl: page table address - * rtbl: pointer to page table or physical memory - * index: start index to write - * eindex: end index to write - [index, eindex] written to - * flags: flags for pagetable entry to or in - * inc: increment to rtbl between each entry - * tmp1: temporary variable - * - * Preserves: tbl, eindex, flags, inc - * Corrupts: index, tmp1 - * Returns: rtbl - */ - .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1 -.Lpe\@: phys_to_pte \tmp1, \rtbl - orr \tmp1, \tmp1, \flags // tmp1 = table entry - str \tmp1, [\tbl, \index, lsl #3] - add \rtbl, \rtbl, \inc // rtbl = pa next level - add \index, \index, #1 - cmp \index, \eindex - b.ls .Lpe\@ - .endm - -/* - * Compute indices of table entries from virtual address range. If multiple entries - * were needed in the previous page table level then the next page table level is assumed - * to be composed of multiple pages. (This effectively scales the end index). - * - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend] - * shift: shift used to transform virtual address into index - * order: #imm 2log(number of entries in page table) - * istart: index in table corresponding to vstart - * iend: index in table corresponding to vend - * count: On entry: how many extra entries were required in previous level, scales - * our end index. - * On exit: returns how many extra entries required for next page table level - * - * Preserves: vstart, vend - * Returns: istart, iend, count - */ - .macro compute_indices, vstart, vend, shift, order, istart, iend, count - ubfx \istart, \vstart, \shift, \order - ubfx \iend, \vend, \shift, \order - add \iend, \iend, \count, lsl \order - sub \count, \iend, \istart - .endm - -/* - * Map memory for specified virtual address range. Each level of page table needed supports - * multiple entries. If a level requires n entries the next page table level is assumed to be - * formed from n pages. - * - * tbl: location of page table - * rtbl: address to be used for first level page table entry (typically tbl + PAGE_SIZE) - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend - 1] - * flags: flags to use to map last level entries - * phys: physical address corresponding to vstart - physical memory is contiguous - * order: #imm 2log(number of entries in PGD table) - * - * If extra_shift is set, an extra level will be populated if the end address does - * not fit in 'extra_shift' bits. This assumes vend is in the TTBR0 range. - * - * Temporaries: istart, iend, tmp, count, sv - these need to be different registers - * Preserves: vstart, flags - * Corrupts: tbl, rtbl, vend, istart, iend, tmp, count, sv - */ - .macro map_memory, tbl, rtbl, vstart, vend, flags, phys, order, istart, iend, tmp, count, sv, extra_shift - sub \vend, \vend, #1 - add \rtbl, \tbl, #PAGE_SIZE - mov \count, #0 - - .ifnb \extra_shift - tst \vend, #~((1 << (\extra_shift)) - 1) - b.eq .L_\@ - compute_indices \vstart, \vend, #\extra_shift, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - .endif -.L_\@: - compute_indices \vstart, \vend, #PGDIR_SHIFT, #\order, \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - -#if SWAPPER_PGTABLE_LEVELS > 3 - compute_indices \vstart, \vend, #PUD_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - -#if SWAPPER_PGTABLE_LEVELS > 2 - compute_indices \vstart, \vend, #SWAPPER_TABLE_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - - compute_indices \vstart, \vend, #SWAPPER_BLOCK_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - bic \rtbl, \phys, #SWAPPER_BLOCK_SIZE - 1 - populate_entries \tbl, \rtbl, \istart, \iend, \flags, #SWAPPER_BLOCK_SIZE, \tmp - .endm - -/* - * Remap a subregion created with the map_memory macro with modified attributes - * or output address. The entire remapped region must have been covered in the - * invocation of map_memory. - * - * x0: last level table address (returned in first argument to map_memory) - * x1: start VA of the existing mapping - * x2: start VA of the region to update - * x3: end VA of the region to update (exclusive) - * x4: start PA associated with the region to update - * x5: attributes to set on the updated region - * x6: order of the last level mappings - */ -SYM_FUNC_START_LOCAL(remap_region) - sub x3, x3, #1 // make end inclusive - - // Get the index offset for the start of the last level table - lsr x1, x1, x6 - bfi x1, xzr, #0, #PAGE_SHIFT - 3 - - // Derive the start and end indexes into the last level table - // associated with the provided region - lsr x2, x2, x6 - lsr x3, x3, x6 - sub x2, x2, x1 - sub x3, x3, x1 - - mov x1, #1 - lsl x6, x1, x6 // block size at this level - - populate_entries x0, x4, x2, x3, x5, x6, x7 - ret -SYM_FUNC_END(remap_region) - -SYM_FUNC_START_LOCAL(create_idmap) - mov x28, lr - /* - * The ID map carries a 1:1 mapping of the physical address range - * covered by the loaded image, which could be anywhere in DRAM. This - * means that the required size of the VA (== PA) space is decided at - * boot time, and could be more than the configured size of the VA - * space for ordinary kernel and user space mappings. - * - * There are three cases to consider here: - * - 39 <= VA_BITS < 48, and the ID map needs up to 48 VA bits to cover - * the placement of the image. In this case, we configure one extra - * level of translation on the fly for the ID map only. (This case - * also covers 42-bit VA/52-bit PA on 64k pages). - * - * - VA_BITS == 48, and the ID map needs more than 48 VA bits. This can - * only happen when using 64k pages, in which case we need to extend - * the root level table rather than add a level. Note that we can - * treat this case as 'always extended' as long as we take care not - * to program an unsupported T0SZ value into the TCR register. - * - * - Combinations that would require two additional levels of - * translation are not supported, e.g., VA_BITS==36 on 16k pages, or - * VA_BITS==39/4k pages with 5-level paging, where the input address - * requires more than 47 or 48 bits, respectively. - */ -#if (VA_BITS < 48) -#define IDMAP_PGD_ORDER (VA_BITS - PGDIR_SHIFT) -#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) - - /* - * If VA_BITS < 48, we have to configure an additional table level. - * First, we have to verify our assumption that the current value of - * VA_BITS was chosen such that all translation levels are fully - * utilised, and that lowering T0SZ will always result in an additional - * translation level to be configured. - */ -#if VA_BITS != EXTRA_SHIFT -#error "Mismatch between VA_BITS and page size/number of translation levels" -#endif -#else -#define IDMAP_PGD_ORDER (PHYS_MASK_SHIFT - PGDIR_SHIFT) -#define EXTRA_SHIFT - /* - * If VA_BITS == 48, we don't have to configure an additional - * translation level, but the top-level table has more entries. - */ -#endif - adrp x0, init_idmap_pg_dir - adrp x3, _text - adrp x6, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - mov_q x7, SWAPPER_RX_MMUFLAGS - - map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT - - /* Remap the kernel page tables r/w in the ID map */ - adrp x1, _text - adrp x2, init_pg_dir - adrp x3, init_pg_end - bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* Remap the FDT after the kernel image */ - adrp x1, _text - adrp x22, _end + SWAPPER_BLOCK_SIZE - bic x2, x22, #SWAPPER_BLOCK_SIZE - 1 - bfi x22, x21, #0, #SWAPPER_BLOCK_SHIFT // remapped FDT address - add x3, x2, #MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - bic x4, x21, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* - * Since the page tables have been populated with non-cacheable - * accesses (MMU disabled), invalidate those tables again to - * remove any speculatively loaded cache lines. - */ - cbnz x19, 0f // skip cache invalidation if MMU is on - dmb sy - - adrp x0, init_idmap_pg_dir - adrp x1, init_idmap_pg_end - bl dcache_inval_poc -0: ret x28 -SYM_FUNC_END(create_idmap) - -SYM_FUNC_START_LOCAL(create_kernel_mapping) - adrp x0, init_pg_dir - mov_q x5, KIMAGE_VADDR // compile time __va(_text) -#ifdef CONFIG_RELOCATABLE - add x5, x5, x23 // add KASLR displacement -#endif - adrp x6, _end // runtime __pa(_end) - adrp x3, _text // runtime __pa(_text) - sub x6, x6, x3 // _end - _text - add x6, x6, x5 // runtime __va(_end) - mov_q x7, SWAPPER_RW_MMUFLAGS - - map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14 - - dsb ishst // sync with page table walker - ret -SYM_FUNC_END(create_kernel_mapping) - /* * Initialize CPU registers with task-specific and cpu-specific context. * @@ -489,34 +234,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) mov x0, x20 bl set_cpu_boot_mode_flag - // Clear BSS - adr_l x0, __bss_start - mov x1, xzr - adr_l x2, __bss_stop - sub x2, x2, x0 - bl __pi_memset - dsb ishst // Make zero page visible to PTW - -#if VA_BITS > 48 - adr_l x8, vabits_actual // Set this early so KASAN early init - str x25, [x8] // ... observes the correct value - dc civac, x8 // Make visible to booting secondaries -#endif - -#ifdef CONFIG_RANDOMIZE_BASE - adrp x5, memstart_offset_seed // Save KASLR linear map seed - strh w24, [x5, :lo12:memstart_offset_seed] -#endif #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif - mov x0, x21 // pass FDT address in x0 - bl early_fdt_map // Try mapping the FDT early - mov x0, x20 // pass the full boot status - bl init_feature_override // Parse cpu feature overrides -#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS - bl scs_patch_vmlinux -#endif mov x0, x20 bl finalise_el2 // Prefer VHE if possible ldp x29, x30, [sp], #16 @@ -643,10 +363,13 @@ SYM_FUNC_START_LOCAL(secondary_startup) * Common entry point for secondary CPUs. */ mov x20, x0 // preserve boot mode + +#ifdef CONFIG_ARM64_VA_BITS_52 +alternative_if ARM64_HAS_VA52 bl __cpu_secondary_check52bitva -#if VA_BITS > 48 - ldr_l x0, vabits_actual +alternative_else_nop_endif #endif + bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir adrp x2, idmap_pg_dir @@ -749,15 +472,18 @@ SYM_FUNC_START(__enable_mmu) ret SYM_FUNC_END(__enable_mmu) +#ifdef CONFIG_ARM64_VA_BITS_52 SYM_FUNC_START(__cpu_secondary_check52bitva) -#if VA_BITS > 48 - ldr_l x0, vabits_actual - cmp x0, #52 - b.ne 2f - +#ifndef CONFIG_ARM64_LPA2 mrs_s x0, SYS_ID_AA64MMFR2_EL1 and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f +#else + mrs x0, id_aa64mmfr0_el1 + sbfx x0, x0, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4 + cmp x0, #ID_AA64MMFR0_EL1_TGRAN_LPA2 + b.ge 2f +#endif update_early_cpu_boot_status \ CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1 @@ -765,9 +491,9 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) wfi b 1b -#endif 2: ret SYM_FUNC_END(__cpu_secondary_check52bitva) +#endif SYM_FUNC_START_LOCAL(__no_granule_support) /* Indicate that this CPU can't boot and is stuck in the kernel */ @@ -779,123 +505,18 @@ SYM_FUNC_START_LOCAL(__no_granule_support) b 1b SYM_FUNC_END(__no_granule_support) -#ifdef CONFIG_RELOCATABLE -SYM_FUNC_START_LOCAL(__relocate_kernel) - /* - * Iterate over each entry in the relocation table, and apply the - * relocations in place. - */ - adr_l x9, __rela_start - adr_l x10, __rela_end - mov_q x11, KIMAGE_VADDR // default virtual offset - add x11, x11, x23 // actual virtual offset - -0: cmp x9, x10 - b.hs 1f - ldp x12, x13, [x9], #24 - ldr x14, [x9, #-8] - cmp w13, #R_AARCH64_RELATIVE - b.ne 0b - add x14, x14, x23 // relocate - str x14, [x12, x23] - b 0b - -1: -#ifdef CONFIG_RELR - /* - * Apply RELR relocations. - * - * RELR is a compressed format for storing relative relocations. The - * encoded sequence of entries looks like: - * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] - * - * i.e. start with an address, followed by any number of bitmaps. The - * address entry encodes 1 relocation. The subsequent bitmap entries - * encode up to 63 relocations each, at subsequent offsets following - * the last address entry. - * - * The bitmap entries must have 1 in the least significant bit. The - * assumption here is that an address cannot have 1 in lsb. Odd - * addresses are not supported. Any odd addresses are stored in the RELA - * section, which is handled above. - * - * Excluding the least significant bit in the bitmap, each non-zero - * bit in the bitmap represents a relocation to be applied to - * a corresponding machine word that follows the base address - * word. The second least significant bit represents the machine - * word immediately following the initial address, and each bit - * that follows represents the next word, in linear order. As such, - * a single bitmap can encode up to 63 relocations in a 64-bit object. - * - * In this implementation we store the address of the next RELR table - * entry in x9, the address being relocated by the current address or - * bitmap entry in x13 and the address being relocated by the current - * bit in x14. - */ - adr_l x9, __relr_start - adr_l x10, __relr_end - -2: cmp x9, x10 - b.hs 7f - ldr x11, [x9], #8 - tbnz x11, #0, 3f // branch to handle bitmaps - add x13, x11, x23 - ldr x12, [x13] // relocate address entry - add x12, x12, x23 - str x12, [x13], #8 // adjust to start of bitmap - b 2b - -3: mov x14, x13 -4: lsr x11, x11, #1 - cbz x11, 6f - tbz x11, #0, 5f // skip bit if not set - ldr x12, [x14] // relocate bit - add x12, x12, x23 - str x12, [x14] - -5: add x14, x14, #8 // move to next bit's address - b 4b - -6: /* - * Move to the next bitmap's address. 8 is the word size, and 63 is the - * number of significant bits in a bitmap entry. - */ - add x13, x13, #(8 * 63) - b 2b - -7: -#endif - ret - -SYM_FUNC_END(__relocate_kernel) -#endif - SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu -#ifdef CONFIG_RELOCATABLE - adrp x23, KERNEL_START - and x23, x23, MIN_KIMG_ALIGN - 1 -#ifdef CONFIG_RANDOMIZE_BASE - mov x0, x22 - adrp x1, init_pg_end + + adrp x1, early_init_stack mov sp, x1 mov x29, xzr - bl __pi_kaslr_early_init - and x24, x0, #SZ_2M - 1 // capture memstart offset seed - bic x0, x0, #SZ_2M - 1 - orr x23, x23, x0 // record kernel offset -#endif -#endif - bl clear_page_tables - bl create_kernel_mapping + mov x0, x20 // pass the full boot status + mov x1, x21 // pass the FDT + bl __pi_early_map_kernel // Map and relocate the kernel - adrp x1, init_pg_dir - load_ttbr1 x1, x1, x2 -#ifdef CONFIG_RELOCATABLE - bl __relocate_kernel -#endif ldr x8, =__primary_switched adrp x0, KERNEL_START // __pa(KERNEL_START) br x8 diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 35225632d70a..2f5755192c2b 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -21,6 +21,7 @@ #include <asm/current.h> #include <asm/debug-monitors.h> +#include <asm/esr.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/cputype.h> @@ -779,7 +780,7 @@ static int watchpoint_handler(unsigned long addr, unsigned long esr, * Check that the access type matches. * 0 => load, otherwise => store */ - access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W : + access = (esr & ESR_ELx_WNR) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) continue; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 5e4dc72ab1bd..ba4f8f7d6a91 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -36,6 +36,41 @@ PROVIDE(__pi___memcpy = __pi_memcpy); PROVIDE(__pi___memmove = __pi_memmove); PROVIDE(__pi___memset = __pi_memset); +PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override); +PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override); +PROVIDE(__pi_id_aa64mmfr0_override = id_aa64mmfr0_override); +PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override); +PROVIDE(__pi_id_aa64mmfr2_override = id_aa64mmfr2_override); +PROVIDE(__pi_id_aa64pfr0_override = id_aa64pfr0_override); +PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override); +PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); +PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override); +PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override); +PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings); +#ifdef CONFIG_CAVIUM_ERRATUM_27456 +PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus); +#endif +PROVIDE(__pi__ctype = _ctype); +PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); + +PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir); +PROVIDE(__pi_init_idmap_pg_end = init_idmap_pg_end); +PROVIDE(__pi_init_pg_dir = init_pg_dir); +PROVIDE(__pi_init_pg_end = init_pg_end); +PROVIDE(__pi_swapper_pg_dir = swapper_pg_dir); + +PROVIDE(__pi__text = _text); +PROVIDE(__pi__stext = _stext); +PROVIDE(__pi__etext = _etext); +PROVIDE(__pi___start_rodata = __start_rodata); +PROVIDE(__pi___inittext_begin = __inittext_begin); +PROVIDE(__pi___inittext_end = __inittext_end); +PROVIDE(__pi___initdata_begin = __initdata_begin); +PROVIDE(__pi___initdata_end = __initdata_end); +PROVIDE(__pi__data = _data); +PROVIDE(__pi___bss_start = __bss_start); +PROVIDE(__pi__end = _end); + #ifdef CONFIG_KVM /* diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 12c7f3c8ba76..1da3e25f9d9e 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -16,9 +16,7 @@ bool __ro_after_init __kaslr_is_enabled = false; void __init kaslr_init(void) { - if (cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val & - arm64_sw_feature_override.mask, - ARM64_SW_FEATURE_OVERRIDE_NOKASLR)) { + if (kaslr_disabled_cmdline()) { pr_info("KASLR disabled on command line\n"); return; } diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index dd851297596e..47e0be610bb6 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -595,7 +595,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (scs_is_dynamic()) { s = find_section(hdr, sechdrs, ".init.eh_frame"); if (s) - scs_patch((void *)s->sh_addr, s->sh_size); + __pi_scs_patch((void *)s->sh_addr, s->sh_size); } return module_init_ftrace_plt(hdr, sechdrs, me); diff --git a/arch/arm64/kernel/pi/.gitignore b/arch/arm64/kernel/pi/.gitignore new file mode 100644 index 000000000000..efb29b663e85 --- /dev/null +++ b/arch/arm64/kernel/pi/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +relacheck diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index c844a0546d7f..4393b41f0b71 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -11,6 +11,9 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) +# this code may run with the MMU off so disable unaligned accesses +CFLAGS_map_range.o += -mstrict-align + # remove SCS flags from all objects in this directory KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) # disable LTO @@ -22,14 +25,26 @@ KCSAN_SANITIZE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +hostprogs := relacheck + +quiet_cmd_piobjcopy = $(quiet_cmd_objcopy) + cmd_piobjcopy = $(cmd_objcopy) && $(obj)/relacheck $(@) $(<) + $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ - --remove-section=.note.gnu.property \ - --prefix-alloc-sections=.init -$(obj)/%.pi.o: $(obj)/%.o FORCE - $(call if_changed,objcopy) + --remove-section=.note.gnu.property +$(obj)/%.pi.o: $(obj)/%.o $(obj)/relacheck FORCE + $(call if_changed,piobjcopy) + +# ensure that all the lib- code ends up as __init code and data +$(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -obj-y := kaslr_early.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o -extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) +obj-y := idreg-override.pi.o \ + map_kernel.pi.o map_range.pi.o \ + lib-fdt.pi.o lib-fdt_ro.pi.o +obj-$(CONFIG_RELOCATABLE) += relocate.pi.o +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o +obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index e30fd9e32ef3..aad399796e81 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -14,6 +14,8 @@ #include <asm/cpufeature.h> #include <asm/setup.h> +#include "pi.h" + #define FTR_DESC_NAME_LEN 20 #define FTR_DESC_FIELD_LEN 10 #define FTR_ALIAS_NAME_LEN 30 @@ -21,15 +23,6 @@ static u64 __boot_status __initdata; -// temporary __prel64 related definitions -// to be removed when this code is moved under pi/ - -#define __prel64_initconst __initconst - -#define PREL64(type, name) union { type *name; } - -#define prel64_pointer(__d) (__d) - typedef bool filter_t(u64 val); struct ftr_set_desc { @@ -66,6 +59,35 @@ static const struct ftr_set_desc mmfr1 __prel64_initconst = { }, }; + +static bool __init mmfr2_varange_filter(u64 val) +{ + int __maybe_unused feat; + + if (val) + return false; + +#ifdef CONFIG_ARM64_LPA2 + feat = cpuid_feature_extract_signed_field(read_sysreg(id_aa64mmfr0_el1), + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + if (feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2) { + id_aa64mmfr0_override.val |= + (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + } +#endif + return true; +} + +static const struct ftr_set_desc mmfr2 __prel64_initconst = { + .name = "id_aa64mmfr2", + .override = &id_aa64mmfr2_override, + .fields = { + FIELD("varange", ID_AA64MMFR2_EL1_VARange_SHIFT, mmfr2_varange_filter), + {} + }, +}; + static bool __init pfr0_sve_filter(u64 val) { /* @@ -166,6 +188,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { .fields = { FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), + FIELD("rodataoff", ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF, NULL), {} }, }; @@ -173,6 +196,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { static const PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { { &mmfr1 }, + { &mmfr2 }, { &pfr0 }, { &pfr1 }, { &isar1 }, @@ -197,6 +221,8 @@ static const struct { { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, + { "rodata=off", "arm64_sw.rodataoff=1" }, + { "arm64.nolva", "id_aa64mmfr2.varange=0" }, }; static int __init parse_hexdigit(const char *p, u64 *v) @@ -313,42 +339,35 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) } while (1); } -static __init const u8 *get_bootargs_cmdline(void) +static __init const u8 *get_bootargs_cmdline(const void *fdt, int node) { + static char const bootargs[] __initconst = "bootargs"; const u8 *prop; - void *fdt; - int node; - fdt = get_early_fdt_ptr(); - if (!fdt) - return NULL; - - node = fdt_path_offset(fdt, "/chosen"); if (node < 0) return NULL; - prop = fdt_getprop(fdt, node, "bootargs", NULL); + prop = fdt_getprop(fdt, node, bootargs, NULL); if (!prop) return NULL; return strlen(prop) ? prop : NULL; } -static __init void parse_cmdline(void) +static __init void parse_cmdline(const void *fdt, int chosen) { - const u8 *prop = get_bootargs_cmdline(); + static char const cmdline[] __initconst = CONFIG_CMDLINE; + const u8 *prop = get_bootargs_cmdline(fdt, chosen); if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop) - __parse_cmdline(CONFIG_CMDLINE, true); + __parse_cmdline(cmdline, true); if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop) __parse_cmdline(prop, true); } -/* Keep checkers quiet */ -void init_feature_override(u64 boot_status); - -asmlinkage void __init init_feature_override(u64 boot_status) +void __init init_feature_override(u64 boot_status, const void *fdt, + int chosen) { struct arm64_ftr_override *override; const struct ftr_set_desc *reg; @@ -364,7 +383,7 @@ asmlinkage void __init init_feature_override(u64 boot_status) __boot_status = boot_status; - parse_cmdline(); + parse_cmdline(fdt, chosen); for (i = 0; i < ARRAY_SIZE(regs); i++) { reg = prel64_pointer(regs[i].reg); @@ -373,3 +392,10 @@ asmlinkage void __init init_feature_override(u64 boot_status) (unsigned long)(override + 1)); } } + +char * __init skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index 17bff6e399e4..0257b43819db 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -14,69 +14,23 @@ #include <asm/archrandom.h> #include <asm/memory.h> +#include <asm/pgtable.h> -/* taken from lib/string.c */ -static char *__strstr(const char *s1, const char *s2) -{ - size_t l1, l2; - - l2 = strlen(s2); - if (!l2) - return (char *)s1; - l1 = strlen(s1); - while (l1 >= l2) { - l1--; - if (!memcmp(s1, s2, l2)) - return (char *)s1; - s1++; - } - return NULL; -} -static bool cmdline_contains_nokaslr(const u8 *cmdline) -{ - const u8 *str; - - str = __strstr(cmdline, "nokaslr"); - return str == cmdline || (str > cmdline && *(str - 1) == ' '); -} - -static bool is_kaslr_disabled_cmdline(void *fdt) -{ - if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { - int node; - const u8 *prop; - - node = fdt_path_offset(fdt, "/chosen"); - if (node < 0) - goto out; - - prop = fdt_getprop(fdt, node, "bootargs", NULL); - if (!prop) - goto out; - - if (cmdline_contains_nokaslr(prop)) - return true; +#include "pi.h" - if (IS_ENABLED(CONFIG_CMDLINE_EXTEND)) - goto out; +extern u16 memstart_offset_seed; - return false; - } -out: - return cmdline_contains_nokaslr(CONFIG_CMDLINE); -} - -static u64 get_kaslr_seed(void *fdt) +static u64 __init get_kaslr_seed(void *fdt, int node) { - int node, len; + static char const seed_str[] __initconst = "kaslr-seed"; fdt64_t *prop; u64 ret; + int len; - node = fdt_path_offset(fdt, "/chosen"); if (node < 0) return 0; - prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len); + prop = fdt_getprop_w(fdt, node, seed_str, &len); if (!prop || len != sizeof(u64)) return 0; @@ -85,26 +39,28 @@ static u64 get_kaslr_seed(void *fdt) return ret; } -asmlinkage u64 kaslr_early_init(void *fdt) +u64 __init kaslr_early_init(void *fdt, int chosen) { - u64 seed; + u64 seed, range; - if (is_kaslr_disabled_cmdline(fdt)) + if (kaslr_disabled_cmdline()) return 0; - seed = get_kaslr_seed(fdt); + seed = get_kaslr_seed(fdt, chosen); if (!seed) { if (!__early_cpu_has_rndr() || !__arm64_rndr((unsigned long *)&seed)) return 0; } + memstart_offset_seed = seed & U16_MAX; + /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the - * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of - * the lower and upper quarters to avoid colliding with other - * allocations. + * 'middle' half of the VMALLOC area, and stay clear of the lower and + * upper quarters to avoid colliding with other allocations. */ - return BIT(VA_BITS_MIN - 3) + (seed & GENMASK(VA_BITS_MIN - 3, 0)); + range = (VMALLOC_END - KIMAGE_VADDR) / 2; + return range / 2 + (((__uint128_t)range * seed) >> 64); } diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c new file mode 100644 index 000000000000..5fa08e13e17e --- /dev/null +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/init.h> +#include <linux/libfdt.h> +#include <linux/linkage.h> +#include <linux/types.h> +#include <linux/sizes.h> +#include <linux/string.h> + +#include <asm/memory.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> +#include <asm/tlbflush.h> + +#include "pi.h" + +extern const u8 __eh_frame_start[], __eh_frame_end[]; + +extern void idmap_cpu_replace_ttbr1(void *pgdir); + +static void __init map_segment(pgd_t *pg_dir, u64 *pgd, u64 va_offset, + void *start, void *end, pgprot_t prot, + bool may_use_cont, int root_level) +{ + map_range(pgd, ((u64)start + va_offset) & ~PAGE_OFFSET, + ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start, + prot, root_level, (pte_t *)pg_dir, may_use_cont, 0); +} + +static void __init unmap_segment(pgd_t *pg_dir, u64 va_offset, void *start, + void *end, int root_level) +{ + map_segment(pg_dir, NULL, va_offset, start, end, __pgprot(0), + false, root_level); +} + +static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) +{ + bool enable_scs = IS_ENABLED(CONFIG_UNWIND_PATCH_PAC_INTO_SCS); + bool twopass = IS_ENABLED(CONFIG_RELOCATABLE); + u64 pgdp = (u64)init_pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + pgprot_t prot; + + /* + * External debuggers may need to write directly to the text mapping to + * install SW breakpoints. Allow this (only) when explicitly requested + * with rodata=off. + */ + if (arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF)) + text_prot = PAGE_KERNEL_EXEC; + + /* + * We only enable the shadow call stack dynamically if we are running + * on a system that does not implement PAC or BTI. PAC and SCS provide + * roughly the same level of protection, and BTI relies on the PACIASP + * instructions serving as landing pads, preventing us from patching + * those instructions into something else. + */ + if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpu_has_pac()) + enable_scs = false; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpu_has_bti()) { + enable_scs = false; + + /* + * If we have a CPU that supports BTI and a kernel built for + * BTI then mark the kernel executable text as guarded pages + * now so we don't have to rewrite the page tables later. + */ + text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP); + } + + /* Map all code read-write on the first pass if needed */ + twopass |= enable_scs; + prot = twopass ? data_prot : text_prot; + + map_segment(init_pg_dir, &pgdp, va_offset, _stext, _etext, prot, + !twopass, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __start_rodata, + __inittext_begin, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __inittext_begin, + __inittext_end, prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __initdata_begin, + __initdata_end, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, _data, _end, data_prot, + true, root_level); + dsb(ishst); + + idmap_cpu_replace_ttbr1(init_pg_dir); + + if (twopass) { + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate_kernel(kaslr_offset); + + if (enable_scs) { + scs_patch(__eh_frame_start + va_offset, + __eh_frame_end - __eh_frame_start); + asm("ic ialluis"); + + dynamic_scs_is_enabled = true; + } + + /* + * Unmap the text region before remapping it, to avoid + * potential TLB conflicts when creating the contiguous + * descriptors. + */ + unmap_segment(init_pg_dir, va_offset, _stext, _etext, + root_level); + dsb(ishst); + isb(); + __tlbi(vmalle1); + isb(); + + /* + * Remap these segments with different permissions + * No new page table allocations should be needed + */ + map_segment(init_pg_dir, NULL, va_offset, _stext, _etext, + text_prot, true, root_level); + map_segment(init_pg_dir, NULL, va_offset, __inittext_begin, + __inittext_end, text_prot, false, root_level); + } + + /* Copy the root page table to its final location */ + memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PAGE_SIZE); + dsb(ishst); + idmap_cpu_replace_ttbr1(swapper_pg_dir); +} + +static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) +{ + u64 sctlr = read_sysreg(sctlr_el1); + u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + + asm(" msr sctlr_el1, %0 ;" + " isb ;" + " msr ttbr0_el1, %1 ;" + " msr tcr_el1, %2 ;" + " isb ;" + " tlbi vmalle1 ;" + " dsb nsh ;" + " isb ;" + " msr sctlr_el1, %3 ;" + " isb ;" + :: "r"(sctlr & ~SCTLR_ELx_M), "r"(ttbr), "r"(tcr), "r"(sctlr)); +} + +static void __init remap_idmap_for_lpa2(void) +{ + /* clear the bits that change meaning once LPA2 is turned on */ + pteval_t mask = PTE_SHARED; + + /* + * We have to clear bits [9:8] in all block or page descriptors in the + * initial ID map, as otherwise they will be (mis)interpreted as + * physical address bits once we flick the LPA2 switch (TCR.DS). Since + * we cannot manipulate live descriptors in that way without creating + * potential TLB conflicts, let's create another temporary ID map in a + * LPA2 compatible fashion, and update the initial ID map while running + * from that. + */ + create_init_idmap(init_pg_dir, mask); + dsb(ishst); + set_ttbr0_for_lpa2((u64)init_pg_dir); + + /* + * Recreate the initial ID map with the same granularity as before. + * Don't bother with the FDT, we no longer need it after this. + */ + memset(init_idmap_pg_dir, 0, + (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end); + + create_init_idmap(init_idmap_pg_dir, mask); + dsb(ishst); + + /* switch back to the updated initial ID map */ + set_ttbr0_for_lpa2((u64)init_idmap_pg_dir); + + /* wipe the temporary ID map from memory */ + memset(init_pg_dir, 0, (u64)init_pg_end - (u64)init_pg_dir); +} + +static void __init map_fdt(u64 fdt) +{ + static u8 ptes[INIT_IDMAP_FDT_SIZE] __initdata __aligned(PAGE_SIZE); + u64 efdt = fdt + MAX_FDT_SIZE; + u64 ptep = (u64)ptes; + + /* + * Map up to MAX_FDT_SIZE bytes, but avoid overlap with + * the kernel image. + */ + map_range(&ptep, fdt, (u64)_text > fdt ? min((u64)_text, efdt) : efdt, + fdt, PAGE_KERNEL, IDMAP_ROOT_LEVEL, + (pte_t *)init_idmap_pg_dir, false, 0); + dsb(ishst); +} + +asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) +{ + static char const chosen_str[] __initconst = "/chosen"; + u64 va_base, pa_base = (u64)&_text; + u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN; + int root_level = 4 - CONFIG_PGTABLE_LEVELS; + int va_bits = VA_BITS; + int chosen; + + map_fdt((u64)fdt); + + /* Clear BSS and the initial page tables */ + memset(__bss_start, 0, (u64)init_pg_end - (u64)__bss_start); + + /* Parse the command line for CPU feature overrides */ + chosen = fdt_path_offset(fdt, chosen_str); + init_feature_override(boot_status, fdt, chosen); + + if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && !cpu_has_lva()) { + va_bits = VA_BITS_MIN; + } else if (IS_ENABLED(CONFIG_ARM64_LPA2) && !cpu_has_lpa2()) { + va_bits = VA_BITS_MIN; + root_level++; + } + + if (va_bits > VA_BITS_MIN) + sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits)); + + /* + * The virtual KASLR displacement modulo 2MiB is decided by the + * physical placement of the image, as otherwise, we might not be able + * to create the early kernel mapping using 2 MiB block descriptors. So + * take the low bits of the KASLR offset from the physical address, and + * fill in the high bits from the seed. + */ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + u64 kaslr_seed = kaslr_early_init(fdt, chosen); + + if (kaslr_seed && kaslr_requires_kpti()) + arm64_use_ng_mappings = true; + + kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1); + } + + if (IS_ENABLED(CONFIG_ARM64_LPA2) && va_bits > VA_BITS_MIN) + remap_idmap_for_lpa2(); + + va_base = KIMAGE_VADDR + kaslr_offset; + map_kernel(kaslr_offset, va_base - pa_base, root_level); +} diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c new file mode 100644 index 000000000000..5410b2cac590 --- /dev/null +++ b/arch/arm64/kernel/pi/map_range.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/types.h> +#include <linux/sizes.h> + +#include <asm/memory.h> +#include <asm/pgalloc.h> +#include <asm/pgtable.h> + +#include "pi.h" + +/** + * map_range - Map a contiguous range of physical pages into virtual memory + * + * @pte: Address of physical pointer to array of pages to + * allocate page tables from + * @start: Virtual address of the start of the range + * @end: Virtual address of the end of the range (exclusive) + * @pa: Physical address of the start of the range + * @prot: Access permissions of the range + * @level: Translation level for the mapping + * @tbl: The level @level page table to create the mappings in + * @may_use_cont: Whether the use of the contiguous attribute is allowed + * @va_offset: Offset between a physical page and its current mapping + * in the VA space + */ +void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset) +{ + u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX; + u64 protval = pgprot_val(prot) & ~PTE_TYPE_MASK; + int lshift = (3 - level) * (PAGE_SHIFT - 3); + u64 lmask = (PAGE_SIZE << lshift) - 1; + + start &= PAGE_MASK; + pa &= PAGE_MASK; + + /* Advance tbl to the entry that covers start */ + tbl += (start >> (lshift + PAGE_SHIFT)) % PTRS_PER_PTE; + + /* + * Set the right block/page bits for this level unless we are + * clearing the mapping + */ + if (protval) + protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE; + + while (start < end) { + u64 next = min((start | lmask) + 1, PAGE_ALIGN(end)); + + if (level < 3 && (start | next | pa) & lmask) { + /* + * This chunk needs a finer grained mapping. Create a + * table mapping if necessary and recurse. + */ + if (pte_none(*tbl)) { + *tbl = __pte(__phys_to_pte_val(*pte) | + PMD_TYPE_TABLE | PMD_TABLE_UXN); + *pte += PTRS_PER_PTE * sizeof(pte_t); + } + map_range(pte, start, next, pa, prot, level + 1, + (pte_t *)(__pte_to_phys(*tbl) + va_offset), + may_use_cont, va_offset); + } else { + /* + * Start a contiguous range if start and pa are + * suitably aligned + */ + if (((start | pa) & cmask) == 0 && may_use_cont) + protval |= PTE_CONT; + + /* + * Clear the contiguous attribute if the remaining + * range does not cover a contiguous block + */ + if ((end & ~cmask) <= start) + protval &= ~PTE_CONT; + + /* Put down a block or page mapping */ + *tbl = __pte(__phys_to_pte_val(pa) | protval); + } + pa += next - start; + start = next; + tbl++; + } +} + +asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, pteval_t clrmask) +{ + u64 ptep = (u64)pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + + pgprot_val(text_prot) &= ~clrmask; + pgprot_val(data_prot) &= ~clrmask; + + map_range(&ptep, (u64)_stext, (u64)__initdata_begin, (u64)_stext, + text_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + map_range(&ptep, (u64)__initdata_begin, (u64)_end, (u64)__initdata_begin, + data_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + + return ptep; +} diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index a1fe4b4ff591..49d8b40e61bc 100644 --- a/arch/arm64/kernel/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -4,16 +4,17 @@ * Author: Ard Biesheuvel <ardb@google.com> */ -#include <linux/bug.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/linkage.h> -#include <linux/printk.h> #include <linux/types.h> -#include <asm/cacheflush.h> #include <asm/scs.h> +#include "pi.h" + +bool dynamic_scs_is_enabled; + // // This minimal DWARF CFI parser is partially based on the code in // arch/arc/kernel/unwind.c, and on the document below: @@ -49,8 +50,6 @@ #define DW_CFA_GNU_negative_offset_extended 0x2f #define DW_CFA_hi_user 0x3f -extern const u8 __eh_frame_start[], __eh_frame_end[]; - enum { PACIASP = 0xd503233f, AUTIASP = 0xd50323bf, @@ -81,7 +80,11 @@ static void __always_inline scs_patch_loc(u64 loc) */ return; } - dcache_clean_pou(loc, loc + sizeof(u32)); + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_CLEAN_CACHE)) + asm("dc civac, %0" :: "r"(loc)); + else + asm(ALTERNATIVE("dc cvau, %0", "nop", ARM64_HAS_CACHE_IDC) + :: "r"(loc)); } /* @@ -128,10 +131,10 @@ struct eh_frame { }; }; -static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, - bool fde_has_augmentation_data, - int code_alignment_factor, - bool dry_run) +static int scs_handle_fde_frame(const struct eh_frame *frame, + bool fde_has_augmentation_data, + int code_alignment_factor, + bool dry_run) { int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; u64 loc = (u64)offset_to_ptr(&frame->initial_loc); @@ -198,14 +201,13 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, break; default: - pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame); return -ENOEXEC; } } return 0; } -int noinstr scs_patch(const u8 eh_frame[], int size) +int scs_patch(const u8 eh_frame[], int size) { const u8 *p = eh_frame; @@ -250,13 +252,3 @@ int noinstr scs_patch(const u8 eh_frame[], int size) } return 0; } - -asmlinkage void __init scs_patch_vmlinux(void) -{ - if (!should_patch_pac_into_scs()) - return; - - WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start)); - icache_inval_all_pou(); - isb(); -} diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h new file mode 100644 index 000000000000..c91e5e965cd3 --- /dev/null +++ b/arch/arm64/kernel/pi/pi.h @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel <ardb@google.com> + +#include <linux/types.h> + +#define __prel64_initconst __section(".init.rodata.prel64") + +#define PREL64(type, name) union { type *name; prel64_t name ## _prel; } + +#define prel64_pointer(__d) (typeof(__d))prel64_to_pointer(&__d##_prel) + +typedef volatile signed long prel64_t; + +static inline void *prel64_to_pointer(const prel64_t *offset) +{ + if (!*offset) + return NULL; + return (void *)offset + *offset; +} + +extern bool dynamic_scs_is_enabled; + +extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[]; + +void init_feature_override(u64 boot_status, const void *fdt, int chosen); +u64 kaslr_early_init(void *fdt, int chosen); +void relocate_kernel(u64 offset); +int scs_patch(const u8 eh_frame[], int size); + +void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset); + +asmlinkage void early_map_kernel(u64 boot_status, void *fdt); + +asmlinkage u64 create_init_idmap(pgd_t *pgd, pteval_t clrmask); diff --git a/arch/arm64/kernel/pi/relacheck.c b/arch/arm64/kernel/pi/relacheck.c new file mode 100644 index 000000000000..b0cd4d0d275b --- /dev/null +++ b/arch/arm64/kernel/pi/relacheck.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 - Google LLC + * Author: Ard Biesheuvel <ardb@google.com> + */ + +#include <elf.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define HOST_ORDER ELFDATA2LSB +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define HOST_ORDER ELFDATA2MSB +#endif + +static Elf64_Ehdr *ehdr; +static Elf64_Shdr *shdr; +static const char *strtab; +static bool swap; + +static uint64_t swab_elfxword(uint64_t val) +{ + return swap ? __builtin_bswap64(val) : val; +} + +static uint32_t swab_elfword(uint32_t val) +{ + return swap ? __builtin_bswap32(val) : val; +} + +static uint16_t swab_elfhword(uint16_t val) +{ + return swap ? __builtin_bswap16(val) : val; +} + +int main(int argc, char *argv[]) +{ + struct stat stat; + int fd, ret; + + if (argc < 3) { + fprintf(stderr, "file arguments missing\n"); + exit(EXIT_FAILURE); + } + + fd = open(argv[1], O_RDWR); + if (fd < 0) { + fprintf(stderr, "failed to open %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ret = fstat(fd, &stat); + if (ret < 0) { + fprintf(stderr, "failed to stat() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ehdr = mmap(0, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (ehdr == MAP_FAILED) { + fprintf(stderr, "failed to mmap() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + swap = ehdr->e_ident[EI_DATA] != HOST_ORDER; + shdr = (void *)ehdr + swab_elfxword(ehdr->e_shoff); + strtab = (void *)ehdr + + swab_elfxword(shdr[swab_elfhword(ehdr->e_shstrndx)].sh_offset); + + for (int i = 0; i < swab_elfhword(ehdr->e_shnum); i++) { + unsigned long info, flags; + bool prel64 = false; + Elf64_Rela *rela; + int numrela; + + if (swab_elfword(shdr[i].sh_type) != SHT_RELA) + continue; + + /* only consider RELA sections operating on data */ + info = swab_elfword(shdr[i].sh_info); + flags = swab_elfxword(shdr[info].sh_flags); + if ((flags & (SHF_ALLOC | SHF_EXECINSTR)) != SHF_ALLOC) + continue; + + /* + * We generally don't permit ABS64 relocations in the code that + * runs before relocation processing occurs. If statically + * initialized absolute symbol references are unavoidable, they + * may be emitted into a *.rodata.prel64 section and they will + * be converted to place-relative 64-bit references. This + * requires special handling in the referring code. + */ + if (strstr(strtab + swab_elfword(shdr[info].sh_name), + ".rodata.prel64")) { + prel64 = true; + } + + rela = (void *)ehdr + swab_elfxword(shdr[i].sh_offset); + numrela = swab_elfxword(shdr[i].sh_size) / sizeof(*rela); + + for (int j = 0; j < numrela; j++) { + uint64_t info = swab_elfxword(rela[j].r_info); + + if (ELF64_R_TYPE(info) != R_AARCH64_ABS64) + continue; + + if (prel64) { + /* convert ABS64 into PREL64 */ + info ^= R_AARCH64_ABS64 ^ R_AARCH64_PREL64; + rela[j].r_info = swab_elfxword(info); + } else { + fprintf(stderr, + "Unexpected absolute relocations detected in %s\n", + argv[2]); + close(fd); + unlink(argv[1]); + exit(EXIT_FAILURE); + } + } + } + close(fd); + return 0; +} diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c new file mode 100644 index 000000000000..2407d2696398 --- /dev/null +++ b/arch/arm64/kernel/pi/relocate.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Authors: Ard Biesheuvel <ardb@google.com> +// Peter Collingbourne <pcc@google.com> + +#include <linux/elf.h> +#include <linux/init.h> +#include <linux/types.h> + +#include "pi.h" + +extern const Elf64_Rela rela_start[], rela_end[]; +extern const u64 relr_start[], relr_end[]; + +void __init relocate_kernel(u64 offset) +{ + u64 *place = NULL; + + for (const Elf64_Rela *rela = rela_start; rela < rela_end; rela++) { + if (ELF64_R_TYPE(rela->r_info) != R_AARCH64_RELATIVE) + continue; + *(u64 *)(rela->r_offset + offset) = rela->r_addend + offset; + } + + if (!IS_ENABLED(CONFIG_RELR) || !offset) + return; + + /* + * Apply RELR relocations. + * + * RELR is a compressed format for storing relative relocations. The + * encoded sequence of entries looks like: + * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] + * + * i.e. start with an address, followed by any number of bitmaps. The + * address entry encodes 1 relocation. The subsequent bitmap entries + * encode up to 63 relocations each, at subsequent offsets following + * the last address entry. + * + * The bitmap entries must have 1 in the least significant bit. The + * assumption here is that an address cannot have 1 in lsb. Odd + * addresses are not supported. Any odd addresses are stored in the + * RELA section, which is handled above. + * + * With the exception of the least significant bit, each bit in the + * bitmap corresponds with a machine word that follows the base address + * word, and the bit value indicates whether or not a relocation needs + * to be applied to it. The second least significant bit represents the + * machine word immediately following the initial address, and each bit + * that follows represents the next word, in linear order. As such, a + * single bitmap can encode up to 63 relocations in a 64-bit object. + */ + for (const u64 *relr = relr_start; relr < relr_end; relr++) { + if ((*relr & 1) == 0) { + place = (u64 *)(*relr + offset); + *place++ += offset; + } else { + for (u64 *p = place, r = *relr >> 1; r; p++, r >>= 1) + if (r & 1) + *p += offset; + place += 63; + } + } +} diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 70b91a8c6bb3..327855a11df2 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -371,6 +371,21 @@ static struct break_hook kprobes_break_ss_hook = { .fn = kprobe_breakpoint_ss_handler, }; +static int __kprobes +kretprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) +{ + if (regs->pc != (unsigned long)__kretprobe_trampoline) + return DBG_HOOK_ERROR; + + regs->pc = kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); + return DBG_HOOK_HANDLED; +} + +static struct break_hook kretprobes_break_hook = { + .imm = KRETPROBES_BRK_IMM, + .fn = kretprobe_breakpoint_handler, +}; + /* * Provide a blacklist of symbols identifying ranges which cannot be kprobed. * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). @@ -396,11 +411,6 @@ int __init arch_populate_kprobe_blacklist(void) return ret; } -void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) -{ - return (void *)kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); -} - void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -420,6 +430,7 @@ int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); register_kernel_break_hook(&kprobes_break_ss_hook); + register_kernel_break_hook(&kretprobes_break_hook); return 0; } diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 9a6499bed58b..a362f3dbb3d1 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -4,83 +4,17 @@ */ #include <linux/linkage.h> -#include <asm/asm-offsets.h> +#include <asm/asm-bug.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, #PT_REGS_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 - SYM_CODE_START(__kretprobe_trampoline) - sub sp, sp, #PT_REGS_SIZE - - save_all_base_regs - - /* Setup a frame pointer. */ - add x29, sp, #S_FP - - mov x0, sp - bl trampoline_probe_handler /* - * Replace trampoline address in lr with actual orig_ret_addr return - * address. + * Trigger a breakpoint exception. The PC will be adjusted by + * kretprobe_breakpoint_handler(), and no subsequent instructions will + * be executed from the trampoline. */ - mov lr, x0 - - /* The frame pointer (x29) is restored with other registers. */ - restore_all_base_regs - - add sp, sp, #PT_REGS_SIZE - ret - + brk #KRETPROBES_BRK_IMM + ASM_BUG() SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7387b68c745b..4ae31b7af6c3 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -290,9 +290,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) fpsimd_preserve_current_state(); *dst = *src; - /* We rely on the above assignment to initialize dst's thread_flags: */ - BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK)); - /* * Detach src's sve_state (if any) from dst so that it does not * get erroneously used or freed prematurely. dst's copies diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index e3bef38fc2e2..162b030ab9da 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -174,7 +174,6 @@ static void ptrace_hbptriggered(struct perf_event *bp, struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; -#ifdef CONFIG_COMPAT if (is_compat_task()) { int si_errno = 0; int i; @@ -196,7 +195,7 @@ static void ptrace_hbptriggered(struct perf_event *bp, desc); return; } -#endif + arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } @@ -698,6 +697,39 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, return ret; } +static int fpmr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_fpmr()) + return -EINVAL; + + if (target == current) + fpsimd_preserve_current_state(); + + return membuf_store(&to, target->thread.uw.fpmr); +} + +static int fpmr_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + unsigned long fpmr; + + if (!system_supports_fpmr()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); + if (ret) + return ret; + + target->thread.uw.fpmr = fpmr; + + fpsimd_flush_task_state(target); + + return 0; +} + static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) @@ -1419,6 +1451,7 @@ enum aarch64_regset { REGSET_HW_BREAK, REGSET_HW_WATCH, #endif + REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, @@ -1497,6 +1530,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = system_call_get, .set = system_call_set, }, + [REGSET_FPMR] = { + .core_note_type = NT_ARM_FPMR, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = fpmr_get, + .set = fpmr_set, + }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, @@ -1597,7 +1638,6 @@ static const struct user_regset_view user_aarch64_view = { .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; -#ifdef CONFIG_COMPAT enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, @@ -1854,6 +1894,7 @@ static const struct user_regset_view user_aarch32_ptrace_view = { .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; +#ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { @@ -2115,7 +2156,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, const struct user_regset_view *task_user_regset_view(struct task_struct *task) { -#ifdef CONFIG_COMPAT /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on @@ -2126,7 +2166,7 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; -#endif + return &user_aarch64_view; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 42c690bb2d60..65a052bf741f 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -166,21 +166,6 @@ static void __init smp_build_mpidr_hash(void) pr_warn("Large number of MPIDR hash buckets detected\n"); } -static void *early_fdt_ptr __initdata; - -void __init *get_early_fdt_ptr(void) -{ - return early_fdt_ptr; -} - -asmlinkage void __init early_fdt_map(u64 dt_phys) -{ - int fdt_size; - - early_fixmap_init(); - early_fdt_ptr = fixmap_remap_fdt(dt_phys, &fdt_size, PAGE_KERNEL); -} - static void __init setup_machine_fdt(phys_addr_t dt_phys) { int size; @@ -298,13 +283,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) kaslr_init(); - /* - * If know now we are going to need KPTI then use non-global - * mappings from the start, avoiding the cost of rewriting - * everything later. - */ - arm64_use_ng_mappings = kaslr_requires_kpti(); - early_fixmap_init(); early_ioremap_init(); @@ -320,9 +298,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) dynamic_scs_init(); /* - * Unmask asynchronous aborts and fiq after bringing up possible - * earlycon. (Report possible System Errors once we can report this - * occurred). + * Unmask SError as soon as possible after initializing earlycon so + * that we can report any SErrors immediately. */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 425b1bc17a3f..4a77f4976e11 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -16,8 +16,8 @@ #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> -#include <linux/resume_user_mode.h> #include <linux/ratelimit.h> +#include <linux/rseq.h> #include <linux/syscalls.h> #include <asm/daifflags.h> @@ -60,6 +60,7 @@ struct rt_sigframe_user_layout { unsigned long tpidr2_offset; unsigned long za_offset; unsigned long zt_offset; + unsigned long fpmr_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -182,6 +183,8 @@ struct user_ctxs { u32 za_size; struct zt_context __user *zt; u32 zt_size; + struct fpmr_context __user *fpmr; + u32 fpmr_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) @@ -227,6 +230,33 @@ static int restore_fpsimd_context(struct user_ctxs *user) return err ? -EFAULT : 0; } +static int preserve_fpmr_context(struct fpmr_context __user *ctx) +{ + int err = 0; + + current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR); + + __put_user_error(FPMR_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err); + + return err; +} + +static int restore_fpmr_context(struct user_ctxs *user) +{ + u64 fpmr; + int err = 0; + + if (user->fpmr_size != sizeof(*user->fpmr)) + return -EINVAL; + + __get_user_error(fpmr, &user->fpmr->fpmr, err); + if (!err) + write_sysreg_s(fpmr, SYS_FPMR); + + return err; +} #ifdef CONFIG_ARM64_SVE @@ -590,6 +620,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; + user->fpmr = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -684,6 +715,17 @@ static int parse_user_sigframe(struct user_ctxs *user, user->zt_size = size; break; + case FPMR_MAGIC: + if (!system_supports_fpmr()) + goto invalid; + + if (user->fpmr) + goto invalid; + + user->fpmr = (struct fpmr_context __user *)head; + user->fpmr_size = size; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -806,6 +848,9 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); + if (err == 0 && system_supports_fpmr() && user.fpmr) + err = restore_fpmr_context(&user); + if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); @@ -928,6 +973,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, } } + if (system_supports_fpmr()) { + err = sigframe_alloc(user, &user->fpmr_offset, + sizeof(struct fpmr_context)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -983,6 +1035,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_tpidr2_context(tpidr2_ctx); } + /* FPMR if supported */ + if (system_supports_fpmr() && err == 0) { + struct fpmr_context __user *fpmr_ctx = + apply_user_offset(user, user->fpmr_offset); + err |= preserve_fpmr_context(fpmr_ctx); + } + /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1207,7 +1266,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { unsigned long continue_addr = 0, restart_addr = 0; int retval = 0; @@ -1278,41 +1337,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) -{ - do { - if (thread_flags & _TIF_NEED_RESCHED) { - /* Unmask Debug and SError for the next task */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - schedule(); - } else { - local_daif_restore(DAIF_PROCCTX); - - if (thread_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - if (thread_flags & _TIF_MTE_ASYNC_FAULT) { - clear_thread_flag(TIF_MTE_ASYNC_FAULT); - send_sig_fault(SIGSEGV, SEGV_MTEAERR, - (void __user *)NULL, current); - } - - if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) - do_signal(regs); - - if (thread_flags & _TIF_NOTIFY_RESUME) - resume_user_mode_work(regs); - - if (thread_flags & _TIF_FOREIGN_FPSTATE) - fpsimd_restore_current_state(); - } - - local_daif_mask(); - thread_flags = read_thread_flags(); - } while (thread_flags & _TIF_WORK_MASK); -} - unsigned long __ro_after_init signal_minsigstksz; /* diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 2aa5129d8253..f093cdf71be1 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -102,9 +102,6 @@ SYM_CODE_START(cpu_resume) mov x0, xzr bl init_kernel_el mov x19, x0 // preserve boot mode -#if VA_BITS > 48 - ldr_l x0, vabits_actual -#endif bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a70d9746b66..ad198262b981 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -20,14 +20,11 @@ long sys_ni_syscall(void); static long do_ni_syscall(struct pt_regs *regs, int scno) { -#ifdef CONFIG_COMPAT - long ret; if (is_compat_task()) { - ret = compat_arm_syscall(regs, scno); + long ret = compat_arm_syscall(regs, scno); if (ret != -ENOSYS) return ret; } -#endif return sys_ni_syscall(); } diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 3cd7e76cc562..755a22d4f840 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -126,9 +126,9 @@ jiffies = jiffies_64; #ifdef CONFIG_UNWIND_TABLES #define UNWIND_DATA_SECTIONS \ .eh_frame : { \ - __eh_frame_start = .; \ + __pi___eh_frame_start = .; \ *(.eh_frame) \ - __eh_frame_end = .; \ + __pi___eh_frame_end = .; \ } #else #define UNWIND_DATA_SECTIONS @@ -270,15 +270,15 @@ SECTIONS HYPERVISOR_RELOC_SECTION .rela.dyn : ALIGN(8) { - __rela_start = .; + __pi_rela_start = .; *(.rela .rela*) - __rela_end = .; + __pi_rela_end = .; } .relr.dyn : ALIGN(8) { - __relr_start = .; + __pi_relr_start = .; *(.relr.dyn) - __relr_end = .; + __pi_relr_end = .; } . = ALIGN(SEGMENT_ALIGN); @@ -311,12 +311,17 @@ SECTIONS __pecoff_data_rawsize = ABSOLUTE(. - __initdata_begin); _edata = .; + /* start of zero-init region */ BSS_SECTION(SBSS_ALIGN, 0, 0) . = ALIGN(PAGE_SIZE); init_pg_dir = .; . += INIT_DIR_SIZE; init_pg_end = .; + /* end of zero-init region */ + + . += SZ_4K; /* stack for the early C runtime */ + early_init_stack = .; . = ALIGN(SEGMENT_ALIGN); __pecoff_data_size = ABSOLUTE(. - __initdata_begin); diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 8c1d0d4853df..e3e611e30e91 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -153,6 +153,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) fp_state.sve_vl = vcpu->arch.sve_max_vl; fp_state.sme_state = NULL; fp_state.svcr = &vcpu->arch.svcr; + fp_state.fpmr = &vcpu->arch.fpmr; fp_state.fp_type = &vcpu->arch.fp_type; if (vcpu_has_sve(vcpu)) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d14504821b79..cd9456a03e38 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -805,7 +805,7 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr) .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_LAST_LEVEL - - CONFIG_PGTABLE_LEVELS + 1), + ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; unsigned long flags; @@ -1874,16 +1874,9 @@ int __init kvm_mmu_init(u32 *hyp_va_bits) BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* - * The ID map may be configured to use an extended virtual address - * range. This is only the case if system RAM is out of range for the - * currently configured page size and VA_BITS_MIN, in which case we will - * also need the extended virtual range for the HYP ID map, or we won't - * be able to enable the EL2 MMU. - * - * However, in some cases the ID map may be configured for fewer than - * the number of VA bits used by the regular kernel stage 1. This - * happens when VA_BITS=52 and the kernel image is placed in PA space - * below 48 bits. + * The ID map is always configured for 48 bits of translation, which + * may be fewer than the number of VA bits used by the regular kernel + * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom @@ -1894,7 +1887,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits) * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ - idmap_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET); + idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 55f6455a8284..60265ede48fe 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -257,16 +257,14 @@ static bool is_el1_data_abort(unsigned long esr) static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { - unsigned long fsc_type = esr & ESR_ELx_FSC_TYPE; - if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; - if (fsc_type == ESR_ELx_FSC_PERM) + if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) - return fsc_type == ESR_ELx_FSC_FAULT && + return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; @@ -279,8 +277,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long flags; u64 par, dfsc; - if (!is_el1_data_abort(esr) || - (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT) + if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); @@ -301,7 +298,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); - return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; + return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, @@ -368,11 +365,6 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) return false; } -static bool is_translation_fault(unsigned long esr) -{ - return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; -} - static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { @@ -405,7 +397,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (is_translation_fault(esr) && + if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; @@ -782,18 +774,18 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 8" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 12" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 19" }, + { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, @@ -801,7 +793,7 @@ static const struct fault_info fault_info[] = { { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 27" }, + { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented @@ -815,9 +807,9 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 41" }, + { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 43" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index c0a3301203bd..d22506e9c7fd 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -16,6 +16,9 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> +/* ensure that the fixmap region does not grow down into the PCI I/O region */ +static_assert(FIXADDR_TOT_START > PCI_IO_END); + #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ @@ -101,7 +104,7 @@ void __init early_fixmap_init(void) unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } @@ -167,37 +170,3 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } - -/* - * Copy the fixmap region into a new pgdir. - */ -void __init fixmap_copy(pgd_t *pgdir) -{ - if (!READ_ONCE(pgd_val(*pgd_offset_pgd(pgdir, FIXADDR_TOT_START)))) { - /* - * The fixmap falls in a separate pgd to the kernel, and doesn't - * live in the carveout for the swapper_pg_dir. We can simply - * re-use the existing dir for the fixmap. - */ - set_pgd(pgd_offset_pgd(pgdir, FIXADDR_TOT_START), - READ_ONCE(*pgd_offset_k(FIXADDR_TOT_START))); - } else if (CONFIG_PGTABLE_LEVELS > 3) { - pgd_t *bm_pgdp; - p4d_t *bm_p4dp; - pud_t *bm_pudp; - /* - * The fixmap shares its top level pgd entry with the kernel - * mapping. This can really only occur when we are running - * with 16k/4 levels, so we can simply reuse the pud level - * entry instead. - */ - BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - bm_pgdp = pgd_offset_pgd(pgdir, FIXADDR_TOT_START); - bm_p4dp = p4d_offset(bm_pgdp, FIXADDR_TOT_START); - bm_pudp = pud_set_fixmap_offset(bm_p4dp, FIXADDR_TOT_START); - pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd)); - pud_clear_fixmap(); - } else { - BUG(); - } -} diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 74c1db8ce271..0f427b50fdc3 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -238,7 +238,7 @@ void __init arm64_memblock_init(void) * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) - memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 4c7ad574b946..fbddbf9faf19 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -23,7 +23,7 @@ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); +static pgd_t tmp_pg_dir[PTRS_PER_PTE] __initdata __aligned(PAGE_SIZE); /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used @@ -99,6 +99,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr); } +static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, + bool early) +{ + if (pgd_none(READ_ONCE(*pgdp))) { + phys_addr_t p4d_phys = early ? + __pa_symbol(kasan_early_shadow_p4d) + : kasan_alloc_zeroed_page(node); + __pgd_populate(pgdp, p4d_phys, PGD_TYPE_TABLE); + } + + return early ? p4d_offset_kimg(pgdp, addr) : p4d_offset(pgdp, addr); +} + static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { @@ -144,12 +157,12 @@ static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early); do { next = p4d_addr_end(addr, end); kasan_pud_populate(p4dp, addr, next, node, early); - } while (p4dp++, addr = next, addr != end); + } while (p4dp++, addr = next, addr != end && p4d_none(READ_ONCE(*p4dp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, @@ -165,19 +178,48 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, } while (pgdp++, addr = next, addr != end); } +#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS > 4 +#define SHADOW_ALIGN P4D_SIZE +#else +#define SHADOW_ALIGN PUD_SIZE +#endif + +/* + * Return whether 'addr' is aligned to the size covered by a root level + * descriptor. + */ +static bool __init root_level_aligned(u64 addr) +{ + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * (PAGE_SHIFT - 3); + + return (addr % (PAGE_SIZE << shift)) == 0; +} + /* The early shadow maps everything to a single page of zeroes */ asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); - /* - * We cannot check the actual value of KASAN_SHADOW_START during build, - * as it depends on vabits_actual. As a best-effort approach, check - * potential values calculated based on VA_BITS and VA_BITS_MIN. - */ - BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), SHADOW_ALIGN)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), SHADOW_ALIGN)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, SHADOW_ALIGN)); + + if (!root_level_aligned(KASAN_SHADOW_START)) { + /* + * The start address is misaligned, and so the next level table + * will be shared with the linear region. This can happen with + * 4 or 5 level paging, so install a generic pte_t[] as the + * next level. This prevents the kasan_pgd_populate call below + * from inserting an entry that refers to the shared KASAN zero + * shadow pud_t[]/p4d_t[], which could end up getting corrupted + * when the linear region is mapped. + */ + static pte_t tbl[PTRS_PER_PTE] __page_aligned_bss; + pgd_t *pgdp = pgd_offset_k(KASAN_SHADOW_START); + + set_pgd(pgdp, __pgd(__pa_symbol(tbl) | PGD_TYPE_TABLE)); + } + kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true); } @@ -190,34 +232,74 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, } /* - * Copy the current shadow region into a new pgdir. + * Return the descriptor index of 'addr' in the root level table */ -void __init kasan_copy_shadow(pgd_t *pgdir) +static int __init root_level_idx(u64 addr) { - pgd_t *pgdp, *pgdp_new, *pgdp_end; + /* + * On 64k pages, the TTBR1 range root tables are extended for 52-bit + * virtual addressing, and TTBR1 will simply point to the pgd_t entry + * that covers the start of the 48-bit addressable VA space if LVA is + * not implemented. This means we need to index the table as usual, + * instead of masking off bits based on vabits_actual. + */ + u64 vabits = IS_ENABLED(CONFIG_ARM64_64K_PAGES) ? VA_BITS + : vabits_actual; + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * (PAGE_SHIFT - 3); - pgdp = pgd_offset_k(KASAN_SHADOW_START); - pgdp_end = pgd_offset_k(KASAN_SHADOW_END); - pgdp_new = pgd_offset_pgd(pgdir, KASAN_SHADOW_START); - do { - set_pgd(pgdp_new, READ_ONCE(*pgdp)); - } while (pgdp++, pgdp_new++, pgdp != pgdp_end); + return (addr & ~_PAGE_OFFSET(vabits)) >> (shift + PAGE_SHIFT); +} + +/* + * Clone a next level table from swapper_pg_dir into tmp_pg_dir + */ +static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud) +{ + int idx = root_level_idx(addr); + pgd_t pgd = READ_ONCE(swapper_pg_dir[idx]); + pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); + + memcpy(pud, pudp, PAGE_SIZE); + tmp_pg_dir[idx] = __pgd(__phys_to_pgd_val(__pa_symbol(pud)) | + PUD_TYPE_TABLE); } -static void __init clear_pgds(unsigned long start, - unsigned long end) +/* + * Return the descriptor index of 'addr' in the next level table + */ +static int __init next_level_idx(u64 addr) { - /* - * Remove references to kasan page tables from - * swapper_pg_dir. pgd_clear() can't be used - * here because it's nop on 2,3-level pagetable setups - */ - for (; start < end; start += PGDIR_SIZE) - set_pgd(pgd_offset_k(start), __pgd(0)); + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * (PAGE_SHIFT - 3); + + return (addr >> (shift + PAGE_SHIFT)) % PTRS_PER_PTE; +} + +/* + * Dereference the table descriptor at 'pgd_idx' and clear the entries from + * 'start' to 'end' (exclusive) from the table. + */ +static void __init clear_next_level(int pgd_idx, int start, int end) +{ + pgd_t pgd = READ_ONCE(swapper_pg_dir[pgd_idx]); + pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); + + memset(&pudp[start], 0, (end - start) * sizeof(pud_t)); +} + +static void __init clear_shadow(u64 start, u64 end) +{ + int l = root_level_idx(start), m = root_level_idx(end); + + if (!root_level_aligned(start)) + clear_next_level(l++, next_level_idx(start), PTRS_PER_PTE); + if (!root_level_aligned(end)) + clear_next_level(m, 0, next_level_idx(end)); + memset(&swapper_pg_dir[l], 0, (m - l) * sizeof(pgd_t)); } static void __init kasan_init_shadow(void) { + static pud_t pud[2][PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); u64 kimg_shadow_start, kimg_shadow_end; u64 mod_shadow_start; u64 vmalloc_shadow_end; @@ -239,10 +321,23 @@ static void __init kasan_init_shadow(void) * setup will be finished. */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); + + /* + * If the start or end address of the shadow region is not aligned to + * the root level size, we have to allocate a temporary next-level table + * in each case, clone the next level of descriptors, and install the + * table into tmp_pg_dir. Note that with 5 levels of paging, the next + * level will in fact be p4d_t, but that makes no difference in this + * case. + */ + if (!root_level_aligned(KASAN_SHADOW_START)) + clone_next_level(KASAN_SHADOW_START, tmp_pg_dir, pud[0]); + if (!root_level_aligned(KASAN_SHADOW_END)) + clone_next_level(KASAN_SHADOW_END, tmp_pg_dir, pud[1]); dsb(ishst); - cpu_replace_ttbr1(lm_alias(tmp_pg_dir), idmap_pg_dir); + cpu_replace_ttbr1(lm_alias(tmp_pg_dir)); - clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + clear_shadow(KASAN_SHADOW_START, KASAN_SHADOW_END); kasan_map_populate(kimg_shadow_start, kimg_shadow_end, early_pfn_to_nid(virt_to_pfn(lm_alias(KERNEL_START)))); @@ -276,7 +371,7 @@ static void __init kasan_init_shadow(void) PAGE_KERNEL_RO)); memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir); + cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); } static void __init kasan_init_depth(void) diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 645fe60d000f..642bdf908b22 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -73,6 +73,10 @@ static int __init adjust_protection_map(void) protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } + if (lpa2_is_enabled()) + for (int i = 0; i < ARRAY_SIZE(protection_map); i++) + pgprot_val(protection_map[i]) &= ~PTE_SHARED; + return 0; } arch_initcall(adjust_protection_map); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1ac7467d34c9..bf5b1c426ad0 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -45,18 +45,13 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ -int idmap_t0sz __ro_after_init; - -#if VA_BITS > 48 -u64 vabits_actual __ro_after_init = VA_BITS_MIN; -EXPORT_SYMBOL(vabits_actual); -#endif - u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 }; +static bool rodata_is_rw __ro_after_init = true; + /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. @@ -73,10 +68,21 @@ EXPORT_SYMBOL(empty_zero_page); static DEFINE_SPINLOCK(swapper_pgdir_lock); static DEFINE_MUTEX(fixmap_lock); -void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) +void noinstr set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) { pgd_t *fixmap_pgdp; + /* + * Don't bother with the fixmap if swapper_pg_dir is still mapped + * writable in the kernel mapping. + */ + if (rodata_is_rw) { + WRITE_ONCE(*pgdp, pgd); + dsb(ishst); + isb(); + return; + } + spin_lock(&swapper_pgdir_lock); fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp)); WRITE_ONCE(*fixmap_pgdp, pgd); @@ -307,15 +313,14 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, } while (addr = next, addr != end); } -static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, +static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; - pud_t *pudp; - p4d_t *p4dp = p4d_offset(pgdp, addr); p4d_t p4d = READ_ONCE(*p4dp); + pud_t *pudp; if (p4d_none(p4d)) { p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN; @@ -363,6 +368,46 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, pud_clear_fixmap(); } +static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(int), + int flags) +{ + unsigned long next; + pgd_t pgd = READ_ONCE(*pgdp); + p4d_t *p4dp; + + if (pgd_none(pgd)) { + pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN; + phys_addr_t p4d_phys; + + if (flags & NO_EXEC_MAPPINGS) + pgdval |= PGD_TABLE_PXN; + BUG_ON(!pgtable_alloc); + p4d_phys = pgtable_alloc(P4D_SHIFT); + __pgd_populate(pgdp, p4d_phys, pgdval); + pgd = READ_ONCE(*pgdp); + } + BUG_ON(pgd_bad(pgd)); + + p4dp = p4d_set_fixmap_offset(pgdp, addr); + do { + p4d_t old_p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + + alloc_init_pud(p4dp, addr, next, phys, prot, + pgtable_alloc, flags); + + BUG_ON(p4d_val(old_p4d) != 0 && + p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); + + phys += next - addr; + } while (p4dp++, addr = next, addr != end); + + p4d_clear_fixmap(); +} + static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, @@ -385,7 +430,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, + alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; } while (pgdp++, addr = next, addr != end); @@ -576,8 +621,12 @@ static void __init map_mem(pgd_t *pgdp) * entries at any level are being shared between the linear region and * the vmalloc region. Check whether this is true for the PGD level, in * which case it is guaranteed to be true for all other levels as well. + * (Unless we are running with support for LPA2, in which case the + * entire reduced VA space is covered by a single pgd_t which will have + * been populated without the PXNTable attribute by the time we get here.) */ - BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end)); + BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) && + pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1); early_kfence_pool = arm64_kfence_alloc_pool(); @@ -630,15 +679,16 @@ void mark_rodata_ro(void) * to cover NOTES and EXCEPTION_TABLE. */ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; + WRITE_ONCE(rodata_is_rw, false); update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, - pgprot_t prot, struct vm_struct *vma, - int flags, unsigned long vm_flags) +static void __init declare_vma(struct vm_struct *vma, + void *va_start, void *va_end, + unsigned long vm_flags) { phys_addr_t pa_start = __pa_symbol(va_start); unsigned long size = va_end - va_start; @@ -646,9 +696,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, - early_pgtable_alloc, flags); - if (!(vm_flags & VM_NO_GUARD)) size += PAGE_SIZE; @@ -661,12 +708,12 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, vm_area_add_early(vma); } +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static pgprot_t kernel_exec_prot(void) { return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; } -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { int i; @@ -701,80 +748,36 @@ core_initcall(map_entry_trampoline); #endif /* - * Open coded check for BTI, only for use to determine configuration - * for early mappings for before the cpufeature code has run. + * Declare the VMA areas for the kernel */ -static bool arm64_early_this_cpu_has_bti(void) +static void __init declare_kernel_vmas(void) { - u64 pfr1; + static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT]; - if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) - return false; - - pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1); - return cpuid_feature_extract_unsigned_field(pfr1, - ID_AA64PFR1_EL1_BT_SHIFT); + declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD); + declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD); + declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD); + declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD); + declare_vma(&vmlinux_seg[4], _data, _end, 0); } -/* - * Create fine-grained mappings for the kernel. - */ -static void __init map_kernel(pgd_t *pgdp) -{ - static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, - vmlinux_initdata, vmlinux_data; +void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset); - /* - * External debuggers may need to write directly to the text - * mapping to install SW breakpoints. Allow this (only) when - * explicitly requested with rodata=off. - */ - pgprot_t text_prot = kernel_exec_prot(); - - /* - * If we have a CPU that supports BTI and a kernel built for - * BTI then mark the kernel executable text as guarded pages - * now so we don't have to rewrite the page tables later. - */ - if (arm64_early_this_cpu_has_bti()) - text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP); - - /* - * Only rodata will be remapped with different permissions later on, - * all other segments are allowed to use contiguous mappings. - */ - map_kernel_segment(pgdp, _stext, _etext, text_prot, &vmlinux_text, 0, - VM_NO_GUARD); - map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, - &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, - &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, - &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - - fixmap_copy(pgdp); - kasan_copy_shadow(pgdp); -} +static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init, + kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init; static void __init create_idmap(void) { u64 start = __pa_symbol(__idmap_text_start); - u64 size = __pa_symbol(__idmap_text_end) - start; - pgd_t *pgd = idmap_pg_dir; - u64 pgd_phys; - - /* check if we need an additional level of translation */ - if (VA_BITS < 48 && idmap_t0sz < (64 - VA_BITS_MIN)) { - pgd_phys = early_pgtable_alloc(PAGE_SHIFT); - set_pgd(&idmap_pg_dir[start >> VA_BITS], - __pgd(pgd_phys | P4D_TYPE_TABLE)); - pgd = __va(pgd_phys); - } - __create_pgd_mapping(pgd, start, start, size, PAGE_KERNEL_ROX, - early_pgtable_alloc, 0); + u64 end = __pa_symbol(__idmap_text_end); + u64 ptep = __pa_symbol(idmap_ptes); + + __pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX, + IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, + __phys_to_virt(ptep) - ptep); - if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) { + if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) { extern u32 __idmap_kpti_flag; u64 pa = __pa_symbol(&__idmap_kpti_flag); @@ -782,32 +785,21 @@ static void __init create_idmap(void) * The KPTI G-to-nG conversion code needs a read-write mapping * of its synchronization flag in the ID map. */ - __create_pgd_mapping(pgd, pa, pa, sizeof(u32), PAGE_KERNEL, - early_pgtable_alloc, 0); + ptep = __pa_symbol(kpti_ptes); + __pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL, + IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, + __phys_to_virt(ptep) - ptep); } } void __init paging_init(void) { - pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); - extern pgd_t init_idmap_pg_dir[]; - - idmap_t0sz = 63UL - __fls(__pa_symbol(_end) | GENMASK(VA_BITS_MIN - 1, 0)); - - map_kernel(pgdp); - map_mem(pgdp); - - pgd_clear_fixmap(); - - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), init_idmap_pg_dir); - init_mm.pgd = swapper_pg_dir; - - memblock_phys_free(__pa_symbol(init_pg_dir), - __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + map_mem(swapper_pg_dir); memblock_allow_resize(); create_idmap(); + declare_kernel_vmas(); } #ifdef CONFIG_MEMORY_HOTPLUG @@ -1073,10 +1065,10 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, free_empty_pmd_table(pudp, addr, next, floor, ceiling); } while (addr = next, addr < end); - if (CONFIG_PGTABLE_LEVELS <= 3) + if (!pgtable_l4_enabled()) return; - if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) + if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK)) return; /* @@ -1099,8 +1091,8 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { - unsigned long next; p4d_t *p4dp, p4d; + unsigned long i, next, start = addr; do { next = p4d_addr_end(addr, end); @@ -1112,6 +1104,27 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, WARN_ON(!p4d_present(p4d)); free_empty_pud_table(p4dp, addr, next, floor, ceiling); } while (addr = next, addr < end); + + if (!pgtable_l5_enabled()) + return; + + if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) + return; + + /* + * Check whether we can free the p4d page if the rest of the + * entries are empty. Overlap with other regions have been + * handled by the floor/ceiling check. + */ + p4dp = p4d_offset(pgdp, 0UL); + for (i = 0; i < PTRS_PER_P4D; i++) { + if (!p4d_none(READ_ONCE(p4dp[i]))) + return; + } + + pgd_clear(pgdp); + __flush_tlb_kernel_pgtable(start); + free_hotplug_pgtable_page(virt_to_page(p4dp)); } static void free_empty_tables(unsigned long addr, unsigned long end, @@ -1196,6 +1209,12 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) return 1; } +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_huge(p4d_t *p4dp) +{ +} +#endif + int pud_clear_huge(pud_t *pudp) { if (!pud_sect(READ_ONCE(*pudp))) @@ -1486,3 +1505,35 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte { set_pte_at(vma->vm_mm, addr, ptep, pte); } + +/* + * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, + * avoiding the possibility of conflicting TLB entries being allocated. + */ +void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) +{ + typedef void (ttbr_replace_func)(phys_addr_t); + extern ttbr_replace_func idmap_cpu_replace_ttbr1; + ttbr_replace_func *replace_phys; + unsigned long daif; + + /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ + phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); + + if (cnp) + ttbr1 |= TTBR_CNP_BIT; + + replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); + + cpu_install_idmap(); + + /* + * We really don't want to take *any* exceptions while TTBR1 is + * in the process of being replaced so mask everything. + */ + daif = local_daif_save(); + replace_phys(ttbr1); + local_daif_restore(daif); + + cpu_uninstall_idmap(); +} diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 4a64089e5771..0c501cabc238 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -17,11 +17,22 @@ static struct kmem_cache *pgd_cache __ro_after_init; +static bool pgdir_is_page_size(void) +{ + if (PGD_SIZE == PAGE_SIZE) + return true; + if (CONFIG_PGTABLE_LEVELS == 4) + return !pgtable_l4_enabled(); + if (CONFIG_PGTABLE_LEVELS == 5) + return !pgtable_l5_enabled(); + return false; +} + pgd_t *pgd_alloc(struct mm_struct *mm) { gfp_t gfp = GFP_PGTABLE_USER; - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) return (pgd_t *)__get_free_page(gfp); else return kmem_cache_alloc(pgd_cache, gfp); @@ -29,7 +40,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) free_page((unsigned long)pgd); else kmem_cache_free(pgd_cache, pgd); @@ -37,7 +48,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) void __init pgtable_cache_init(void) { - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) return; #ifdef CONFIG_ARM64_PA_BITS_52 diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index f66c37a1610e..9d40f3ffd8d2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -195,27 +195,36 @@ SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1) ret SYM_FUNC_END(idmap_cpu_replace_ttbr1) +SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) .popsection #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) +#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | PTE_TYPE_PAGE | \ + PTE_AF | PTE_SHARED | PTE_UXN | PTE_WRITE) .pushsection ".idmap.text", "a" + .macro pte_to_phys, phys, pte + and \phys, \pte, #PTE_ADDR_LOW +#ifdef CONFIG_ARM64_PA_BITS_52 + and \pte, \pte, #PTE_ADDR_HIGH + orr \phys, \phys, \pte, lsl #PTE_ADDR_HIGH_SHIFT +#endif + .endm + .macro kpti_mk_tbl_ng, type, num_entries add end_\type\()p, cur_\type\()p, #\num_entries * 8 .Ldo_\type: - ldr \type, [cur_\type\()p] // Load the entry + ldr \type, [cur_\type\()p], #8 // Load the entry and advance tbz \type, #0, .Lnext_\type // Skip invalid and tbnz \type, #11, .Lnext_\type // non-global entries orr \type, \type, #PTE_NG // Same bit for blocks and pages - str \type, [cur_\type\()p] // Update the entry + str \type, [cur_\type\()p, #-8] // Update the entry .ifnc \type, pte tbnz \type, #1, .Lderef_\type .endif .Lnext_\type: - add cur_\type\()p, cur_\type\()p, #8 cmp cur_\type\()p, end_\type\()p b.ne .Ldo_\type .endm @@ -225,18 +234,18 @@ SYM_FUNC_END(idmap_cpu_replace_ttbr1) * fixmap slot associated with the current level. */ .macro kpti_map_pgtbl, type, level - str xzr, [temp_pte, #8 * (\level + 1)] // break before make + str xzr, [temp_pte, #8 * (\level + 2)] // break before make dsb nshst - add pte, temp_pte, #PAGE_SIZE * (\level + 1) + add pte, temp_pte, #PAGE_SIZE * (\level + 2) lsr pte, pte, #12 tlbi vaae1, pte dsb nsh isb phys_to_pte pte, cur_\type\()p - add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 1) + add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 2) orr pte, pte, pte_flags - str pte, [temp_pte, #8 * (\level + 1)] + str pte, [temp_pte, #8 * (\level + 2)] dsb nshst .endm @@ -269,6 +278,8 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) end_ptep .req x15 pte .req x16 valid .req x17 + cur_p4dp .req x19 + end_p4dp .req x20 mov x5, x3 // preserve temp_pte arg mrs swapper_ttb, ttbr1_el1 @@ -276,6 +287,12 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) cbnz cpu, __idmap_kpti_secondary +#if CONFIG_PGTABLE_LEVELS > 4 + stp x29, x30, [sp, #-32]! + mov x29, sp + stp x19, x20, [sp, #16] +#endif + /* We're the boot CPU. Wait for the others to catch up */ sevl 1: wfe @@ -293,9 +310,32 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) mov_q pte_flags, KPTI_NG_PTE_FLAGS /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + +#ifdef CONFIG_ARM64_LPA2 + /* + * If LPA2 support is configured, but 52-bit virtual addressing is not + * enabled at runtime, we will fall back to one level of paging less, + * and so we have to walk swapper_pg_dir as if we dereferenced its + * address from a PGD level entry, and terminate the PGD level loop + * right after. + */ + adrp pgd, swapper_pg_dir // walk &swapper_pg_dir at the next level + mov cur_pgdp, end_pgdp // must be equal to terminate the PGD loop +alternative_if_not ARM64_HAS_VA52 + b .Lderef_pgd // skip to the next level +alternative_else_nop_endif + /* + * LPA2 based 52-bit virtual addressing requires 52-bit physical + * addressing to be enabled as well. In this case, the shareability + * bits are repurposed as physical address bits, and should not be + * set in pte_flags. + */ + bic pte_flags, pte_flags, #PTE_SHARED +#endif + /* PGD */ adrp cur_pgdp, swapper_pg_dir - kpti_map_pgtbl pgd, 0 + kpti_map_pgtbl pgd, -1 kpti_mk_tbl_ng pgd, PTRS_PER_PGD /* Ensure all the updated entries are visible to secondary CPUs */ @@ -308,16 +348,33 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] +#if CONFIG_PGTABLE_LEVELS > 4 + ldp x19, x20, [sp, #16] + ldp x29, x30, [sp], #32 +#endif ret .Lderef_pgd: + /* P4D */ + .if CONFIG_PGTABLE_LEVELS > 4 + p4d .req x30 + pte_to_phys cur_p4dp, pgd + kpti_map_pgtbl p4d, 0 + kpti_mk_tbl_ng p4d, PTRS_PER_P4D + b .Lnext_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 4 */ + p4d .req pgd + .set .Lnext_p4d, .Lnext_pgd + .endif + +.Lderef_p4d: /* PUD */ .if CONFIG_PGTABLE_LEVELS > 3 pud .req x10 - pte_to_phys cur_pudp, pgd + pte_to_phys cur_pudp, p4d kpti_map_pgtbl pud, 1 kpti_mk_tbl_ng pud, PTRS_PER_PUD - b .Lnext_pgd + b .Lnext_p4d .else /* CONFIG_PGTABLE_LEVELS <= 3 */ pud .req pgd .set .Lnext_pud, .Lnext_pgd @@ -361,6 +418,9 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) .unreq end_ptep .unreq pte .unreq valid + .unreq cur_p4dp + .unreq end_p4dp + .unreq p4d /* Secondary CPUs end up here */ __idmap_kpti_secondary: @@ -395,8 +455,6 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings) * * Initialise the processor for turning the MMU on. * - * Input: - * x0 - actual number of VA bits (ignored unless VA_BITS > 48) * Output: * Return in x0 the value of the SCTLR_EL1 register. */ @@ -420,20 +478,21 @@ SYM_FUNC_START(__cpu_setup) mair .req x17 tcr .req x16 mov_q mair, MAIR_EL1_SET - mov_q tcr, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ - TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ + TCR_SMP_FLAGS | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ + TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS tcr_clear_errata_bits tcr, x9, x5 #ifdef CONFIG_ARM64_VA_BITS_52 - sub x9, xzr, x0 - add x9, x9, #64 + mov x9, #64 - VA_BITS +alternative_if ARM64_HAS_VA52 tcr_set_t1sz tcr, x9 -#else - idmap_get_t0sz x9 +#ifdef CONFIG_ARM64_LPA2 + orr tcr, tcr, #TCR_DS +#endif +alternative_else_nop_endif #endif - tcr_set_t0sz tcr, x9 /* * Set the IPS bits in TCR_EL1. @@ -458,11 +517,26 @@ SYM_FUNC_START(__cpu_setup) ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 cbz x1, .Lskip_indirection + /* + * The PROT_* macros describing the various memory types may resolve to + * C expressions if they include the PTE_MAYBE_* macros, and so they + * can only be used from C code. The PIE_E* constants below are also + * defined in terms of those macros, but will mask out those + * PTE_MAYBE_* constants, whether they are set or not. So #define them + * as 0x0 here so we can evaluate the PIE_E* constants in asm context. + */ + +#define PTE_MAYBE_NG 0 +#define PTE_MAYBE_SHARED 0 + mov_q x0, PIE_E0 msr REG_PIRE0_EL1, x0 mov_q x0, PIE_E1 msr REG_PIR_EL1, x0 +#undef PTE_MAYBE_NG +#undef PTE_MAYBE_SHARED + mov x0, TCR2_EL1x_PIE msr REG_TCR2_EL1, x0 diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index e305b6593c4e..5b87f8d623f7 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -26,34 +26,6 @@ #include <asm/ptdump.h> -enum address_markers_idx { - PAGE_OFFSET_NR = 0, - PAGE_END_NR, -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - KASAN_START_NR, -#endif -}; - -static struct addr_marker address_markers[] = { - { PAGE_OFFSET, "Linear Mapping start" }, - { 0 /* PAGE_END */, "Linear Mapping end" }, -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - { 0 /* KASAN_SHADOW_START */, "Kasan shadow start" }, - { KASAN_SHADOW_END, "Kasan shadow end" }, -#endif - { MODULES_VADDR, "Modules start" }, - { MODULES_END, "Modules end" }, - { VMALLOC_START, "vmalloc() area" }, - { VMALLOC_END, "vmalloc() end" }, - { FIXADDR_TOT_START, "Fixmap start" }, - { FIXADDR_TOP, "Fixmap end" }, - { PCI_IO_START, "PCI I/O start" }, - { PCI_IO_END, "PCI I/O end" }, - { VMEMMAP_START, "vmemmap start" }, - { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" }, - { -1, NULL }, -}; - #define pt_dump_seq_printf(m, fmt, args...) \ ({ \ if (m) \ @@ -76,6 +48,7 @@ struct pg_state { struct ptdump_state ptdump; struct seq_file *seq; const struct addr_marker *marker; + const struct mm_struct *mm; unsigned long start_address; int level; u64 current_prot; @@ -172,12 +145,12 @@ static const struct prot_bits pte_bits[] = { struct pg_level { const struct prot_bits *bits; - const char *name; - size_t num; + char name[4]; + int num; u64 mask; }; -static struct pg_level pg_level[] = { +static struct pg_level pg_level[] __ro_after_init = { { /* pgd */ .name = "PGD", .bits = pte_bits, @@ -187,11 +160,11 @@ static struct pg_level pg_level[] = { .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pud */ - .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", + .name = "PUD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pmd */ - .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", + .name = "PMD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pte */ @@ -255,6 +228,11 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, static const char units[] = "KMGTPE"; u64 prot = 0; + /* check if the current level has been folded dynamically */ + if ((level == 1 && mm_p4d_folded(st->mm)) || + (level == 2 && mm_pud_folded(st->mm))) + level = 0; + if (level >= 0) prot = val & pg_level[level].mask; @@ -316,6 +294,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) st = (struct pg_state){ .seq = s, .marker = info->markers, + .mm = info->mm, .level = -1, .ptdump = { .note_page = note_page, @@ -339,10 +318,8 @@ static void __init ptdump_initialize(void) pg_level[i].mask |= pg_level[i].bits[j].mask; } -static struct ptdump_info kernel_ptdump_info = { +static struct ptdump_info kernel_ptdump_info __ro_after_init = { .mm = &init_mm, - .markers = address_markers, - .base_addr = PAGE_OFFSET, }; void ptdump_check_wx(void) @@ -358,7 +335,7 @@ void ptdump_check_wx(void) .ptdump = { .note_page = note_page, .range = (struct ptdump_range[]) { - {PAGE_OFFSET, ~0UL}, + {_PAGE_OFFSET(vabits_actual), ~0UL}, {0, 0} } } @@ -375,10 +352,32 @@ void ptdump_check_wx(void) static int __init ptdump_init(void) { - address_markers[PAGE_END_NR].start_address = PAGE_END; + u64 page_offset = _PAGE_OFFSET(vabits_actual); + u64 vmemmap_start = (u64)virt_to_page((void *)page_offset); + struct addr_marker m[] = { + { PAGE_OFFSET, "Linear Mapping start" }, + { PAGE_END, "Linear Mapping end" }, #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START; + { KASAN_SHADOW_START, "Kasan shadow start" }, + { KASAN_SHADOW_END, "Kasan shadow end" }, #endif + { MODULES_VADDR, "Modules start" }, + { MODULES_END, "Modules end" }, + { VMALLOC_START, "vmalloc() area" }, + { VMALLOC_END, "vmalloc() end" }, + { vmemmap_start, "vmemmap start" }, + { VMEMMAP_END, "vmemmap end" }, + { PCI_IO_START, "PCI I/O start" }, + { PCI_IO_END, "PCI I/O end" }, + { FIXADDR_TOT_START, "Fixmap start" }, + { FIXADDR_TOP, "Fixmap end" }, + { -1, NULL }, + }; + static struct addr_marker address_markers[ARRAY_SIZE(m)] __ro_after_init; + + kernel_ptdump_info.markers = memcpy(address_markers, m, sizeof(m)); + kernel_ptdump_info.base_addr = page_offset; + ptdump_initialize(); ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); return 0; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index b912b1409fc0..46ae9252bc3f 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -26,6 +26,7 @@ HAS_ECV HAS_ECV_CNTPOFF HAS_EPAN HAS_EVT +HAS_FPMR HAS_FGT HAS_FPSIMD HAS_GENERIC_AUTH @@ -50,6 +51,7 @@ HAS_STAGE2_FWB HAS_TCR2 HAS_TIDCP1 HAS_TLB_RANGE +HAS_VA52 HAS_VIRT_HOST_EXTN HAS_WFXT HW_DBM diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 4c9b67934367..3fc1650a329e 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -200,6 +200,7 @@ UnsignedEnum 27:24 PerfMon 0b0110 PMUv3p5 0b0111 PMUv3p7 0b1000 PMUv3p8 + 0b1001 PMUv3p9 0b1111 IMPDEF EndEnum Enum 23:20 MProfDbg @@ -231,6 +232,7 @@ Enum 3:0 CopDbg 0b1000 Debugv8p2 0b1001 Debugv8p4 0b1010 Debugv8p8 + 0b1011 Debugv8p9 EndEnum EndSysreg @@ -1221,6 +1223,7 @@ UnsignedEnum 35:32 PMSVer 0b0010 V1P1 0b0011 V1P2 0b0100 V1P3 + 0b0101 V1P4 EndEnum Field 31:28 CTX_CMPs Res0 27:24 @@ -1247,11 +1250,41 @@ UnsignedEnum 3:0 DebugVer 0b1000 V8P2 0b1001 V8P4 0b1010 V8P8 + 0b1011 V8P9 EndEnum EndSysreg Sysreg ID_AA64DFR1_EL1 3 0 0 5 1 -Res0 63:0 +Field 63:56 ABL_CMPs +UnsignedEnum 55:52 DPFZS + 0b0000 IGNR + 0b0001 FRZN +EndEnum +UnsignedEnum 51:48 EBEP + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 47:44 ITE + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 43:40 ABLE + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 39:36 PMICNTR + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 35:32 SPMU + 0b0000 NI + 0b0001 IMP + 0b0010 IMP_SPMZR +EndEnum +Field 31:24 CTX_CMPs +Field 23:16 WRPs +Field 15:8 BRPs +Field 7:0 SYSPMUID EndSysreg Sysreg ID_AA64AFR0_EL1 3 0 0 5 4 @@ -1540,16 +1573,16 @@ Enum 35:32 TGRAN16_2 0b0010 IMP 0b0011 52_BIT EndEnum -Enum 31:28 TGRAN4 +SignedEnum 31:28 TGRAN4 0b0000 IMP 0b0001 52_BIT 0b1111 NI EndEnum -Enum 27:24 TGRAN64 +SignedEnum 27:24 TGRAN64 0b0000 IMP 0b1111 NI EndEnum -Enum 23:20 TGRAN16 +UnsignedEnum 23:20 TGRAN16 0b0000 NI 0b0001 IMP 0b0010 52_BIT @@ -1697,7 +1730,7 @@ Enum 23:20 CCIDX 0b0000 32 0b0001 64 EndEnum -Enum 19:16 VARange +UnsignedEnum 19:16 VARange 0b0000 48 0b0001 52 EndEnum diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 983aa2b1629a..fa4fb09909ae 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -82,6 +82,7 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic ifeq ($(CONFIG_RELOCATABLE),y) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 1eccc2ee45fb..7b5a5615200a 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -71,6 +71,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig index ec6e0d9194a1..004d86230aa6 100644 --- a/drivers/perf/Kconfig +++ b/drivers/perf/Kconfig @@ -86,6 +86,15 @@ config RISCV_PMU_SBI full perf feature support i.e. counter overflow, privilege mode filtering, counter configuration. +config STARFIVE_STARLINK_PMU + depends on ARCH_STARFIVE || (COMPILE_TEST && 64BIT) + bool "StarFive StarLink PMU" + help + Provide support for StarLink Performance Monitor Unit. + StarLink Performance Monitor Unit integrates one or more cores with + an L3 memory system. The L3 cache events are added into perf event + subsystem, allowing monitoring of various L3 cache perf events. + config ARM_PMU_ACPI depends on ARM_PMU && ACPI def_bool y diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile index a06338e3401c..29b1c28203ef 100644 --- a/drivers/perf/Makefile +++ b/drivers/perf/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o obj-$(CONFIG_RISCV_PMU) += riscv_pmu.o obj-$(CONFIG_RISCV_PMU_LEGACY) += riscv_pmu_legacy.o obj-$(CONFIG_RISCV_PMU_SBI) += riscv_pmu_sbi.o +obj-$(CONFIG_STARFIVE_STARLINK_PMU) += starfive_starlink_pmu.o obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c index 19d459a36be5..a9277dcf90ce 100644 --- a/drivers/perf/alibaba_uncore_drw_pmu.c +++ b/drivers/perf/alibaba_uncore_drw_pmu.c @@ -729,7 +729,7 @@ static int ali_drw_pmu_probe(struct platform_device *pdev) return ret; } -static int ali_drw_pmu_remove(struct platform_device *pdev) +static void ali_drw_pmu_remove(struct platform_device *pdev) { struct ali_drw_pmu *drw_pmu = platform_get_drvdata(pdev); @@ -739,8 +739,6 @@ static int ali_drw_pmu_remove(struct platform_device *pdev) ali_drw_pmu_uninit_irq(drw_pmu); perf_pmu_unregister(&drw_pmu->pmu); - - return 0; } static int ali_drw_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) @@ -795,7 +793,7 @@ static struct platform_driver ali_drw_pmu_driver = { .acpi_match_table = ali_drw_acpi_match, }, .probe = ali_drw_pmu_probe, - .remove = ali_drw_pmu_remove, + .remove_new = ali_drw_pmu_remove, }; static int __init ali_drw_pmu_init(void) diff --git a/drivers/perf/amlogic/meson_g12_ddr_pmu.c b/drivers/perf/amlogic/meson_g12_ddr_pmu.c index 15d52ab3276a..99cc791892bc 100644 --- a/drivers/perf/amlogic/meson_g12_ddr_pmu.c +++ b/drivers/perf/amlogic/meson_g12_ddr_pmu.c @@ -355,11 +355,9 @@ static int g12_ddr_pmu_probe(struct platform_device *pdev) return meson_ddr_pmu_create(pdev); } -static int g12_ddr_pmu_remove(struct platform_device *pdev) +static void g12_ddr_pmu_remove(struct platform_device *pdev) { meson_ddr_pmu_remove(pdev); - - return 0; } static const struct of_device_id meson_ddr_pmu_dt_match[] = { @@ -381,7 +379,7 @@ MODULE_DEVICE_TABLE(of, meson_ddr_pmu_dt_match); static struct platform_driver g12_ddr_pmu_driver = { .probe = g12_ddr_pmu_probe, - .remove = g12_ddr_pmu_remove, + .remove_new = g12_ddr_pmu_remove, .driver = { .name = "meson-g12-ddr-pmu", diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c index 61de861eaf91..6be03f81ae5d 100644 --- a/drivers/perf/arm-cci.c +++ b/drivers/perf/arm-cci.c @@ -1697,16 +1697,14 @@ error_pmu_init: return ret; } -static int cci_pmu_remove(struct platform_device *pdev) +static void cci_pmu_remove(struct platform_device *pdev) { if (!g_cci_pmu) - return 0; + return; cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE); perf_pmu_unregister(&g_cci_pmu->pmu); g_cci_pmu = NULL; - - return 0; } static struct platform_driver cci_pmu_driver = { @@ -1716,7 +1714,7 @@ static struct platform_driver cci_pmu_driver = { .suppress_bind_attrs = true, }, .probe = cci_pmu_probe, - .remove = cci_pmu_remove, + .remove_new = cci_pmu_remove, }; module_platform_driver(cci_pmu_driver); diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c index 728d13d8e98a..641471bd5eff 100644 --- a/drivers/perf/arm-ccn.c +++ b/drivers/perf/arm-ccn.c @@ -1515,13 +1515,11 @@ static int arm_ccn_probe(struct platform_device *pdev) return arm_ccn_pmu_init(ccn); } -static int arm_ccn_remove(struct platform_device *pdev) +static void arm_ccn_remove(struct platform_device *pdev) { struct arm_ccn *ccn = platform_get_drvdata(pdev); arm_ccn_pmu_cleanup(ccn); - - return 0; } static const struct of_device_id arm_ccn_match[] = { @@ -1539,7 +1537,7 @@ static struct platform_driver arm_ccn_driver = { .suppress_bind_attrs = true, }, .probe = arm_ccn_probe, - .remove = arm_ccn_remove, + .remove_new = arm_ccn_remove, }; static int __init arm_ccn_init(void) diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index 7e3aa7e2345f..7ef9c7e4836b 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -493,6 +493,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d) for (dn = cmn->dns; dn->type; dn++) { struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id); + int pad = dn->logid < 10; if (dn->type == CMN_TYPE_XP) continue; @@ -503,7 +504,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d) if (nid.x != x || nid.y != y || nid.port != p || nid.dev != d) continue; - seq_printf(s, " #%-2d |", dn->logid); + seq_printf(s, " %*c#%-*d |", pad + 1, ' ', 3 - pad, dn->logid); return; } seq_puts(s, " |"); @@ -516,7 +517,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data) seq_puts(s, " X"); for (x = 0; x < cmn->mesh_x; x++) - seq_printf(s, " %d ", x); + seq_printf(s, " %-2d ", x); seq_puts(s, "\nY P D+"); y = cmn->mesh_y; while (y--) { @@ -526,13 +527,13 @@ static int arm_cmn_map_show(struct seq_file *s, void *data) for (x = 0; x < cmn->mesh_x; x++) seq_puts(s, "--------+"); - seq_printf(s, "\n%d |", y); + seq_printf(s, "\n%-2d |", y); for (x = 0; x < cmn->mesh_x; x++) { struct arm_cmn_node *xp = cmn->xps + xp_base + x; for (p = 0; p < CMN_MAX_PORTS; p++) port[p][x] = arm_cmn_device_connect_info(cmn, xp, p); - seq_printf(s, " XP #%-2d |", xp_base + x); + seq_printf(s, " XP #%-3d|", xp_base + x); } seq_puts(s, "\n |"); @@ -2515,7 +2516,7 @@ static int arm_cmn_probe(struct platform_device *pdev) return err; } -static int arm_cmn_remove(struct platform_device *pdev) +static void arm_cmn_remove(struct platform_device *pdev) { struct arm_cmn *cmn = platform_get_drvdata(pdev); @@ -2524,7 +2525,6 @@ static int arm_cmn_remove(struct platform_device *pdev) perf_pmu_unregister(&cmn->pmu); cpuhp_state_remove_instance_nocalls(arm_cmn_hp_state, &cmn->cpuhp_node); debugfs_remove(cmn->debug); - return 0; } #ifdef CONFIG_OF @@ -2555,7 +2555,7 @@ static struct platform_driver arm_cmn_driver = { .acpi_match_table = ACPI_PTR(arm_cmn_acpi_match), }, .probe = arm_cmn_probe, - .remove = arm_cmn_remove, + .remove_new = arm_cmn_remove, }; static int __init arm_cmn_init(void) diff --git a/drivers/perf/arm_cspmu/arm_cspmu.c b/drivers/perf/arm_cspmu/arm_cspmu.c index 50b89b989ce7..b9a252272f1e 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.c +++ b/drivers/perf/arm_cspmu/arm_cspmu.c @@ -27,6 +27,7 @@ #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/module.h> #include <linux/mutex.h> +#include <linux/of.h> #include <linux/perf_event.h> #include <linux/platform_device.h> @@ -100,13 +101,6 @@ #define ARM_CSPMU_ACTIVE_CPU_MASK 0x0 #define ARM_CSPMU_ASSOCIATED_CPU_MASK 0x1 -/* Check and use default if implementer doesn't provide attribute callback */ -#define CHECK_DEFAULT_IMPL_OPS(ops, callback) \ - do { \ - if (!ops->callback) \ - ops->callback = arm_cspmu_ ## callback; \ - } while (0) - /* * Maximum poll count for reading counter value using high-low-high sequence. */ @@ -121,7 +115,9 @@ static void arm_cspmu_set_ev_filter(struct arm_cspmu *cspmu, static struct acpi_apmt_node *arm_cspmu_apmt_node(struct device *dev) { - return *(struct acpi_apmt_node **)dev_get_platdata(dev); + struct acpi_apmt_node **ptr = dev_get_platdata(dev); + + return ptr ? *ptr : NULL; } /* @@ -317,6 +313,10 @@ static const char *arm_cspmu_get_name(const struct arm_cspmu *cspmu) dev = cspmu->dev; apmt_node = arm_cspmu_apmt_node(dev); + if (!apmt_node) + return devm_kasprintf(dev, GFP_KERNEL, PMUNAME "_%u", + atomic_fetch_inc(&pmu_idx[0])); + pmu_type = apmt_node->type; if (pmu_type >= ACPI_APMT_NODE_TYPE_COUNT) { @@ -408,21 +408,32 @@ static struct arm_cspmu_impl_match *arm_cspmu_impl_match_get(u32 pmiidr) return NULL; } +#define DEFAULT_IMPL_OP(name) .name = arm_cspmu_##name + static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) { int ret = 0; - struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; struct acpi_apmt_node *apmt_node = arm_cspmu_apmt_node(cspmu->dev); struct arm_cspmu_impl_match *match; - /* - * Get PMU implementer and product id from APMT node. - * If APMT node doesn't have implementer/product id, try get it - * from PMIIDR. - */ - cspmu->impl.pmiidr = - (apmt_node->impl_id) ? apmt_node->impl_id : - readl(cspmu->base0 + PMIIDR); + /* Start with a default PMU implementation */ + cspmu->impl.module = THIS_MODULE; + cspmu->impl.pmiidr = readl(cspmu->base0 + PMIIDR); + cspmu->impl.ops = (struct arm_cspmu_impl_ops) { + DEFAULT_IMPL_OP(get_event_attrs), + DEFAULT_IMPL_OP(get_format_attrs), + DEFAULT_IMPL_OP(get_identifier), + DEFAULT_IMPL_OP(get_name), + DEFAULT_IMPL_OP(is_cycle_counter_event), + DEFAULT_IMPL_OP(event_type), + DEFAULT_IMPL_OP(event_filter), + DEFAULT_IMPL_OP(set_ev_filter), + DEFAULT_IMPL_OP(event_attr_is_visible), + }; + + /* Firmware may override implementer/product ID from PMIIDR */ + if (apmt_node && apmt_node->impl_id) + cspmu->impl.pmiidr = apmt_node->impl_id; /* Find implementer specific attribute ops. */ match = arm_cspmu_impl_match_get(cspmu->impl.pmiidr); @@ -450,24 +461,9 @@ static int arm_cspmu_init_impl_ops(struct arm_cspmu *cspmu) } mutex_unlock(&arm_cspmu_lock); + } - if (ret) - return ret; - } else - cspmu->impl.module = THIS_MODULE; - - /* Use default callbacks if implementer doesn't provide one. */ - CHECK_DEFAULT_IMPL_OPS(impl_ops, get_event_attrs); - CHECK_DEFAULT_IMPL_OPS(impl_ops, get_format_attrs); - CHECK_DEFAULT_IMPL_OPS(impl_ops, get_identifier); - CHECK_DEFAULT_IMPL_OPS(impl_ops, get_name); - CHECK_DEFAULT_IMPL_OPS(impl_ops, is_cycle_counter_event); - CHECK_DEFAULT_IMPL_OPS(impl_ops, event_type); - CHECK_DEFAULT_IMPL_OPS(impl_ops, event_filter); - CHECK_DEFAULT_IMPL_OPS(impl_ops, event_attr_is_visible); - CHECK_DEFAULT_IMPL_OPS(impl_ops, set_ev_filter); - - return 0; + return ret; } static struct attribute_group * @@ -512,23 +508,16 @@ arm_cspmu_alloc_format_attr_group(struct arm_cspmu *cspmu) return format_group; } -static struct attribute_group ** -arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu) +static int arm_cspmu_alloc_attr_groups(struct arm_cspmu *cspmu) { - struct attribute_group **attr_groups = NULL; - struct device *dev = cspmu->dev; + const struct attribute_group **attr_groups = cspmu->attr_groups; const struct arm_cspmu_impl_ops *impl_ops = &cspmu->impl.ops; cspmu->identifier = impl_ops->get_identifier(cspmu); cspmu->name = impl_ops->get_name(cspmu); if (!cspmu->identifier || !cspmu->name) - return NULL; - - attr_groups = devm_kcalloc(dev, 5, sizeof(struct attribute_group *), - GFP_KERNEL); - if (!attr_groups) - return NULL; + return -ENOMEM; attr_groups[0] = arm_cspmu_alloc_event_attr_group(cspmu); attr_groups[1] = arm_cspmu_alloc_format_attr_group(cspmu); @@ -536,18 +525,14 @@ arm_cspmu_alloc_attr_group(struct arm_cspmu *cspmu) attr_groups[3] = &arm_cspmu_cpumask_attr_group; if (!attr_groups[0] || !attr_groups[1]) - return NULL; + return -ENOMEM; - return attr_groups; + return 0; } static inline void arm_cspmu_reset_counters(struct arm_cspmu *cspmu) { - u32 pmcr = 0; - - pmcr |= PMCR_P; - pmcr |= PMCR_C; - writel(pmcr, cspmu->base0 + PMCR); + writel(PMCR_C | PMCR_P, cspmu->base0 + PMCR); } static inline void arm_cspmu_start_counters(struct arm_cspmu *cspmu) @@ -962,7 +947,14 @@ static struct arm_cspmu *arm_cspmu_alloc(struct platform_device *pdev) platform_set_drvdata(pdev, cspmu); apmt_node = arm_cspmu_apmt_node(dev); - cspmu->has_atomic_dword = apmt_node->flags & ACPI_APMT_FLAGS_ATOMIC; + if (apmt_node) { + cspmu->has_atomic_dword = apmt_node->flags & ACPI_APMT_FLAGS_ATOMIC; + } else { + u32 width = 0; + + device_property_read_u32(dev, "reg-io-width", &width); + cspmu->has_atomic_dword = (width == 8); + } return cspmu; } @@ -1153,11 +1145,6 @@ static int arm_cspmu_acpi_get_cpus(struct arm_cspmu *cspmu) } } - if (cpumask_empty(&cspmu->associated_cpus)) { - dev_dbg(cspmu->dev, "No cpu associated with the PMU\n"); - return -ENODEV; - } - return 0; } #else @@ -1167,19 +1154,45 @@ static int arm_cspmu_acpi_get_cpus(struct arm_cspmu *cspmu) } #endif +static int arm_cspmu_of_get_cpus(struct arm_cspmu *cspmu) +{ + struct of_phandle_iterator it; + int ret, cpu; + + of_for_each_phandle(&it, ret, dev_of_node(cspmu->dev), "cpus", NULL, 0) { + cpu = of_cpu_node_to_id(it.node); + if (cpu < 0) + continue; + cpumask_set_cpu(cpu, &cspmu->associated_cpus); + } + return ret == -ENOENT ? 0 : ret; +} + static int arm_cspmu_get_cpus(struct arm_cspmu *cspmu) { - return arm_cspmu_acpi_get_cpus(cspmu); + int ret = 0; + + if (arm_cspmu_apmt_node(cspmu->dev)) + ret = arm_cspmu_acpi_get_cpus(cspmu); + else if (device_property_present(cspmu->dev, "cpus")) + ret = arm_cspmu_of_get_cpus(cspmu); + else + cpumask_copy(&cspmu->associated_cpus, cpu_possible_mask); + + if (!ret && cpumask_empty(&cspmu->associated_cpus)) { + dev_dbg(cspmu->dev, "No cpu associated with the PMU\n"); + ret = -ENODEV; + } + return ret; } static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu) { int ret, capabilities; - struct attribute_group **attr_groups; - attr_groups = arm_cspmu_alloc_attr_group(cspmu); - if (!attr_groups) - return -ENOMEM; + ret = arm_cspmu_alloc_attr_groups(cspmu); + if (ret) + return ret; ret = cpuhp_state_add_instance(arm_cspmu_cpuhp_state, &cspmu->cpuhp_node); @@ -1201,12 +1214,11 @@ static int arm_cspmu_register_pmu(struct arm_cspmu *cspmu) .start = arm_cspmu_start, .stop = arm_cspmu_stop, .read = arm_cspmu_read, - .attr_groups = (const struct attribute_group **)attr_groups, + .attr_groups = cspmu->attr_groups, .capabilities = capabilities, }; /* Hardware counter init */ - arm_cspmu_stop_counters(cspmu); arm_cspmu_reset_counters(cspmu); ret = perf_pmu_register(&cspmu->pmu, cspmu->name, -1); @@ -1252,14 +1264,12 @@ static int arm_cspmu_device_probe(struct platform_device *pdev) return ret; } -static int arm_cspmu_device_remove(struct platform_device *pdev) +static void arm_cspmu_device_remove(struct platform_device *pdev) { struct arm_cspmu *cspmu = platform_get_drvdata(pdev); perf_pmu_unregister(&cspmu->pmu); cpuhp_state_remove_instance(arm_cspmu_cpuhp_state, &cspmu->cpuhp_node); - - return 0; } static const struct platform_device_id arm_cspmu_id[] = { @@ -1268,13 +1278,20 @@ static const struct platform_device_id arm_cspmu_id[] = { }; MODULE_DEVICE_TABLE(platform, arm_cspmu_id); +static const struct of_device_id arm_cspmu_of_match[] = { + { .compatible = "arm,coresight-pmu" }, + {} +}; +MODULE_DEVICE_TABLE(of, arm_cspmu_of_match); + static struct platform_driver arm_cspmu_driver = { .driver = { - .name = DRVNAME, - .suppress_bind_attrs = true, - }, + .name = DRVNAME, + .of_match_table = arm_cspmu_of_match, + .suppress_bind_attrs = true, + }, .probe = arm_cspmu_device_probe, - .remove = arm_cspmu_device_remove, + .remove_new = arm_cspmu_device_remove, .id_table = arm_cspmu_id, }; diff --git a/drivers/perf/arm_cspmu/arm_cspmu.h b/drivers/perf/arm_cspmu/arm_cspmu.h index 2fe723555a6b..c9163acfe810 100644 --- a/drivers/perf/arm_cspmu/arm_cspmu.h +++ b/drivers/perf/arm_cspmu/arm_cspmu.h @@ -157,6 +157,7 @@ struct arm_cspmu { int cycle_counter_logical_idx; struct arm_cspmu_hw_events hw_events; + const struct attribute_group *attr_groups[5]; struct arm_cspmu_impl impl; }; diff --git a/drivers/perf/arm_cspmu/nvidia_cspmu.c b/drivers/perf/arm_cspmu/nvidia_cspmu.c index 0382b702f092..5b84b701ad62 100644 --- a/drivers/perf/arm_cspmu/nvidia_cspmu.c +++ b/drivers/perf/arm_cspmu/nvidia_cspmu.c @@ -388,12 +388,6 @@ static int nv_cspmu_init_ops(struct arm_cspmu *cspmu) impl_ops->get_format_attrs = nv_cspmu_get_format_attrs; impl_ops->get_name = nv_cspmu_get_name; - /* Set others to NULL to use default callback. */ - impl_ops->event_type = NULL; - impl_ops->event_attr_is_visible = NULL; - impl_ops->get_identifier = NULL; - impl_ops->is_cycle_counter_event = NULL; - return 0; } diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c index 30cea6859574..8a81be2dd5ec 100644 --- a/drivers/perf/arm_dmc620_pmu.c +++ b/drivers/perf/arm_dmc620_pmu.c @@ -724,7 +724,7 @@ out_teardown_dev: return ret; } -static int dmc620_pmu_device_remove(struct platform_device *pdev) +static void dmc620_pmu_device_remove(struct platform_device *pdev) { struct dmc620_pmu *dmc620_pmu = platform_get_drvdata(pdev); @@ -732,8 +732,6 @@ static int dmc620_pmu_device_remove(struct platform_device *pdev) /* perf will synchronise RCU before devres can free dmc620_pmu */ perf_pmu_unregister(&dmc620_pmu->pmu); - - return 0; } static const struct acpi_device_id dmc620_acpi_match[] = { @@ -748,7 +746,7 @@ static struct platform_driver dmc620_pmu_driver = { .suppress_bind_attrs = true, }, .probe = dmc620_pmu_device_probe, - .remove = dmc620_pmu_device_remove, + .remove_new = dmc620_pmu_device_remove, }; static int __init dmc620_pmu_init(void) diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c index 7ec4498e312f..bae3ca37f846 100644 --- a/drivers/perf/arm_dsu_pmu.c +++ b/drivers/perf/arm_dsu_pmu.c @@ -774,14 +774,12 @@ static int dsu_pmu_device_probe(struct platform_device *pdev) return rc; } -static int dsu_pmu_device_remove(struct platform_device *pdev) +static void dsu_pmu_device_remove(struct platform_device *pdev) { struct dsu_pmu *dsu_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&dsu_pmu->pmu); cpuhp_state_remove_instance(dsu_pmu_cpuhp_state, &dsu_pmu->cpuhp_node); - - return 0; } static const struct of_device_id dsu_pmu_of_match[] = { @@ -806,7 +804,7 @@ static struct platform_driver dsu_pmu_driver = { .suppress_bind_attrs = true, }, .probe = dsu_pmu_device_probe, - .remove = dsu_pmu_device_remove, + .remove_new = dsu_pmu_device_remove, }; static int dsu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index 9e5d7fa647b6..719aa953a1c4 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -965,14 +965,12 @@ out_unregister: return err; } -static int smmu_pmu_remove(struct platform_device *pdev) +static void smmu_pmu_remove(struct platform_device *pdev) { struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&smmu_pmu->pmu); cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node); - - return 0; } static void smmu_pmu_shutdown(struct platform_device *pdev) @@ -997,7 +995,7 @@ static struct platform_driver smmu_pmu_driver = { .suppress_bind_attrs = true, }, .probe = smmu_pmu_probe, - .remove = smmu_pmu_remove, + .remove_new = smmu_pmu_remove, .shutdown = smmu_pmu_shutdown, }; diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index b622d75d8c9e..35f0de03416f 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -1263,14 +1263,13 @@ out_free_handle: return ret; } -static int arm_spe_pmu_device_remove(struct platform_device *pdev) +static void arm_spe_pmu_device_remove(struct platform_device *pdev) { struct arm_spe_pmu *spe_pmu = platform_get_drvdata(pdev); arm_spe_pmu_perf_destroy(spe_pmu); arm_spe_pmu_dev_teardown(spe_pmu); free_percpu(spe_pmu->handle); - return 0; } static struct platform_driver arm_spe_pmu_driver = { @@ -1281,7 +1280,7 @@ static struct platform_driver arm_spe_pmu_driver = { .suppress_bind_attrs = true, }, .probe = arm_spe_pmu_device_probe, - .remove = arm_spe_pmu_device_remove, + .remove_new = arm_spe_pmu_device_remove, }; static int __init arm_spe_pmu_init(void) diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 7dbfaee372c7..4e8fa5a48fcf 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -826,7 +826,7 @@ cpuhp_state_err: return ret; } -static int ddr_perf_remove(struct platform_device *pdev) +static void ddr_perf_remove(struct platform_device *pdev) { struct ddr_pmu *pmu = platform_get_drvdata(pdev); @@ -836,7 +836,6 @@ static int ddr_perf_remove(struct platform_device *pdev) perf_pmu_unregister(&pmu->pmu); ida_free(&ddr_ida, pmu->id); - return 0; } static struct platform_driver imx_ddr_pmu_driver = { @@ -846,7 +845,7 @@ static struct platform_driver imx_ddr_pmu_driver = { .suppress_bind_attrs = true, }, .probe = ddr_perf_probe, - .remove = ddr_perf_remove, + .remove_new = ddr_perf_remove, }; module_platform_driver(imx_ddr_pmu_driver); diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c index 9685645bfe04..72c2d3074cde 100644 --- a/drivers/perf/fsl_imx9_ddr_perf.c +++ b/drivers/perf/fsl_imx9_ddr_perf.c @@ -679,7 +679,7 @@ format_string_err: return ret; } -static int ddr_perf_remove(struct platform_device *pdev) +static void ddr_perf_remove(struct platform_device *pdev) { struct ddr_pmu *pmu = platform_get_drvdata(pdev); @@ -689,8 +689,6 @@ static int ddr_perf_remove(struct platform_device *pdev) perf_pmu_unregister(&pmu->pmu); ida_free(&ddr_ida, pmu->id); - - return 0; } static struct platform_driver imx_ddr_pmu_driver = { @@ -700,7 +698,7 @@ static struct platform_driver imx_ddr_pmu_driver = { .suppress_bind_attrs = true, }, .probe = ddr_perf_probe, - .remove = ddr_perf_remove, + .remove_new = ddr_perf_remove, }; module_platform_driver(imx_ddr_pmu_driver); diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c index b90ba8aca3fa..5d1f0e9fdb08 100644 --- a/drivers/perf/hisilicon/hisi_pcie_pmu.c +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -216,10 +216,8 @@ static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, writeq_relaxed(val, pcie_pmu->base + offset); } -static void hisi_pcie_pmu_config_filter(struct perf_event *event) +static u64 hisi_pcie_pmu_get_event_ctrl_val(struct perf_event *event) { - struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); - struct hw_perf_event *hwc = &event->hw; u64 port, trig_len, thr_len, len_mode; u64 reg = HISI_PCIE_INIT_SET; @@ -256,10 +254,19 @@ static void hisi_pcie_pmu_config_filter(struct perf_event *event) else reg |= FIELD_PREP(HISI_PCIE_LEN_M, HISI_PCIE_LEN_M_DEFAULT); + return reg; +} + +static void hisi_pcie_pmu_config_event_ctrl(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + u64 reg = hisi_pcie_pmu_get_event_ctrl_val(event); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, reg); } -static void hisi_pcie_pmu_clear_filter(struct perf_event *event) +static void hisi_pcie_pmu_clear_event_ctrl(struct perf_event *event) { struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); struct hw_perf_event *hwc = &event->hw; @@ -299,18 +306,24 @@ static bool hisi_pcie_pmu_valid_filter(struct perf_event *event, if (hisi_pcie_get_trig_len(event) > HISI_PCIE_TRIG_MAX_VAL) return false; - if (requester_id) { - if (!hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id)) - return false; - } + /* Need to explicitly set filter of "port" or "bdf" */ + if (!hisi_pcie_get_port(event) && + !hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id)) + return false; return true; } +/* + * Check Whether two events share the same config. The same config means not + * only the event code, but also the filter settings of the two events are + * the same. + */ static bool hisi_pcie_pmu_cmp_event(struct perf_event *target, struct perf_event *event) { - return hisi_pcie_get_real_event(target) == hisi_pcie_get_real_event(event); + return hisi_pcie_pmu_get_event_ctrl_val(target) == + hisi_pcie_pmu_get_event_ctrl_val(event); } static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event) @@ -385,40 +398,32 @@ static u64 hisi_pcie_pmu_read_counter(struct perf_event *event) return hisi_pcie_pmu_readq(pcie_pmu, event->hw.event_base, idx); } -static int hisi_pcie_pmu_find_related_event(struct hisi_pcie_pmu *pcie_pmu, - struct perf_event *event) +/* + * Check all work events, if a relevant event is found then we return it + * first, otherwise return the first idle counter (need to reset). + */ +static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu, + struct perf_event *event) { + int first_idle = -EAGAIN; struct perf_event *sibling; int idx; for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { sibling = pcie_pmu->hw_events[idx]; - if (!sibling) - continue; - - if (!hisi_pcie_pmu_cmp_event(sibling, event)) + if (!sibling) { + if (first_idle == -EAGAIN) + first_idle = idx; continue; + } /* Related events must be used in group */ - if (sibling->group_leader == event->group_leader) + if (hisi_pcie_pmu_cmp_event(sibling, event) && + sibling->group_leader == event->group_leader) return idx; - else - return -EINVAL; } - return idx; -} - -static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu) -{ - int idx; - - for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { - if (!pcie_pmu->hw_events[idx]) - return idx; - } - - return -EINVAL; + return first_idle; } static void hisi_pcie_pmu_event_update(struct perf_event *event) @@ -505,7 +510,7 @@ static void hisi_pcie_pmu_start(struct perf_event *event, int flags) WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); hwc->state = 0; - hisi_pcie_pmu_config_filter(event); + hisi_pcie_pmu_config_event_ctrl(event); hisi_pcie_pmu_enable_counter(pcie_pmu, hwc); hisi_pcie_pmu_enable_int(pcie_pmu, hwc); hisi_pcie_pmu_set_period(event); @@ -526,7 +531,7 @@ static void hisi_pcie_pmu_stop(struct perf_event *event, int flags) hisi_pcie_pmu_event_update(event); hisi_pcie_pmu_disable_int(pcie_pmu, hwc); hisi_pcie_pmu_disable_counter(pcie_pmu, hwc); - hisi_pcie_pmu_clear_filter(event); + hisi_pcie_pmu_clear_event_ctrl(event); WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); hwc->state |= PERF_HES_STOPPED; @@ -544,27 +549,18 @@ static int hisi_pcie_pmu_add(struct perf_event *event, int flags) hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; - /* Check all working events to find a related event. */ - idx = hisi_pcie_pmu_find_related_event(pcie_pmu, event); - if (idx < 0) - return idx; - - /* Current event shares an enabled counter with the related event */ - if (idx < HISI_PCIE_MAX_COUNTERS) { - hwc->idx = idx; - goto start_count; - } - - idx = hisi_pcie_pmu_get_event_idx(pcie_pmu); + idx = hisi_pcie_pmu_get_event_idx(pcie_pmu, event); if (idx < 0) return idx; hwc->idx = idx; - pcie_pmu->hw_events[idx] = event; - /* Reset Counter to avoid previous statistic interference. */ - hisi_pcie_pmu_reset_counter(pcie_pmu, idx); -start_count: + /* No enabled counter found with related event, reset it */ + if (!pcie_pmu->hw_events[idx]) { + hisi_pcie_pmu_reset_counter(pcie_pmu, idx); + pcie_pmu->hw_events[idx] = event; + } + if (flags & PERF_EF_START) hisi_pcie_pmu_start(event, PERF_EF_RELOAD); @@ -714,10 +710,18 @@ static struct attribute *hisi_pcie_pmu_events_attr[] = { HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_cnt, 0x10210), HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_latency, 0x0011), HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_cnt, 0x10011), + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_flux, 0x0104), + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_time, 0x10104), HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x0804), HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x10804), + HISI_PCIE_PMU_EVENT_ATTR(rx_cpl_flux, 0x2004), + HISI_PCIE_PMU_EVENT_ATTR(rx_cpl_time, 0x12004), + HISI_PCIE_PMU_EVENT_ATTR(tx_mwr_flux, 0x0105), + HISI_PCIE_PMU_EVENT_ATTR(tx_mwr_time, 0x10105), HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x0405), HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x10405), + HISI_PCIE_PMU_EVENT_ATTR(tx_cpl_flux, 0x1005), + HISI_PCIE_PMU_EVENT_ATTR(tx_cpl_time, 0x11005), NULL }; diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c index 40f1bc9f9b91..0e923f94fa5b 100644 --- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c @@ -341,7 +341,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_cpa_pmu_remove(struct platform_device *pdev) +static void hisi_cpa_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *cpa_pmu = platform_get_drvdata(pdev); @@ -349,7 +349,6 @@ static int hisi_cpa_pmu_remove(struct platform_device *pdev) cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, &cpa_pmu->node); hisi_cpa_pmu_enable_pm(cpa_pmu); - return 0; } static struct platform_driver hisi_cpa_pmu_driver = { @@ -359,7 +358,7 @@ static struct platform_driver hisi_cpa_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_cpa_pmu_probe, - .remove = hisi_cpa_pmu_remove, + .remove_new = hisi_cpa_pmu_remove, }; static int __init hisi_cpa_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index ffb039d05d07..b804e3738113 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -531,14 +531,13 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_ddrc_pmu_remove(struct platform_device *pdev) +static void hisi_ddrc_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *ddrc_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&ddrc_pmu->pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, &ddrc_pmu->node); - return 0; } static struct platform_driver hisi_ddrc_pmu_driver = { @@ -548,7 +547,7 @@ static struct platform_driver hisi_ddrc_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_ddrc_pmu_probe, - .remove = hisi_ddrc_pmu_remove, + .remove_new = hisi_ddrc_pmu_remove, }; static int __init hisi_ddrc_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index 15caf99e1eef..21e69b1cdd4d 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -534,14 +534,13 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_hha_pmu_remove(struct platform_device *pdev) +static void hisi_hha_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *hha_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&hha_pmu->pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, &hha_pmu->node); - return 0; } static struct platform_driver hisi_hha_pmu_driver = { @@ -551,7 +550,7 @@ static struct platform_driver hisi_hha_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_hha_pmu_probe, - .remove = hisi_hha_pmu_remove, + .remove_new = hisi_hha_pmu_remove, }; static int __init hisi_hha_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 794dbcd19b7a..51ba76871097 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -568,14 +568,13 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_l3c_pmu_remove(struct platform_device *pdev) +static void hisi_l3c_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *l3c_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&l3c_pmu->pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, &l3c_pmu->node); - return 0; } static struct platform_driver hisi_l3c_pmu_driver = { @@ -585,7 +584,7 @@ static struct platform_driver hisi_l3c_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_l3c_pmu_probe, - .remove = hisi_l3c_pmu_remove, + .remove_new = hisi_l3c_pmu_remove, }; static int __init hisi_l3c_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index 797cf201996a..3cdb35c741f9 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -514,14 +514,13 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_pa_pmu_remove(struct platform_device *pdev) +static void hisi_pa_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *pa_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&pa_pmu->pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, &pa_pmu->node); - return 0; } static const struct acpi_device_id hisi_pa_pmu_acpi_match[] = { @@ -539,7 +538,7 @@ static struct platform_driver hisi_pa_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_pa_pmu_probe, - .remove = hisi_pa_pmu_remove, + .remove_new = hisi_pa_pmu_remove, }; static int __init hisi_pa_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c index e706ca567676..765bbd61db26 100644 --- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c @@ -460,14 +460,13 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev) return ret; } -static int hisi_sllc_pmu_remove(struct platform_device *pdev) +static void hisi_sllc_pmu_remove(struct platform_device *pdev) { struct hisi_pmu *sllc_pmu = platform_get_drvdata(pdev); perf_pmu_unregister(&sllc_pmu->pmu); cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, &sllc_pmu->node); - return 0; } static struct platform_driver hisi_sllc_pmu_driver = { @@ -477,7 +476,7 @@ static struct platform_driver hisi_sllc_pmu_driver = { .suppress_bind_attrs = true, }, .probe = hisi_sllc_pmu_probe, - .remove = hisi_sllc_pmu_remove, + .remove_new = hisi_sllc_pmu_remove, }; static int __init hisi_sllc_pmu_module_init(void) diff --git a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c index 636fb79647c8..481dcc9e8fbf 100644 --- a/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_uc_pmu.c @@ -287,12 +287,52 @@ static u64 hisi_uc_pmu_read_counter(struct hisi_pmu *uc_pmu, return readq(uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); } -static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu, +static bool hisi_uc_pmu_get_glb_en_state(struct hisi_pmu *uc_pmu) +{ + u32 val; + + val = readl(uc_pmu->base + HISI_UC_EVENT_CTRL_REG); + return !!FIELD_GET(HISI_UC_EVENT_GLB_EN, val); +} + +static void hisi_uc_pmu_write_counter_normal(struct hisi_pmu *uc_pmu, struct hw_perf_event *hwc, u64 val) { writeq(val, uc_pmu->base + HISI_UC_CNTR_REGn(hwc->idx)); } +static void hisi_uc_pmu_write_counter_quirk_v2(struct hisi_pmu *uc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + hisi_uc_pmu_start_counters(uc_pmu); + hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val); + hisi_uc_pmu_stop_counters(uc_pmu); +} + +static void hisi_uc_pmu_write_counter(struct hisi_pmu *uc_pmu, + struct hw_perf_event *hwc, u64 val) +{ + bool enable = hisi_uc_pmu_get_glb_en_state(uc_pmu); + bool erratum = uc_pmu->identifier == HISI_PMU_V2; + + /* + * HiSilicon UC PMU v2 suffers the erratum 162700402 that the + * PMU counter cannot be set due to the lack of clock under power + * saving mode. This will lead to error or inaccurate counts. + * The clock can be enabled by the PMU global enabling control. + * The irq handler and pmu_start() will call the function to set + * period. If the function under irq context, the PMU has been + * enabled therefore we set counter directly. Other situations + * the PMU is disabled, we need to enable it to turn on the + * counter clock to set period, and then restore PMU enable + * status, the counter can hold its value without a clock. + */ + if (enable || !erratum) + hisi_uc_pmu_write_counter_normal(uc_pmu, hwc, val); + else + hisi_uc_pmu_write_counter_quirk_v2(uc_pmu, hwc, val); +} + static void hisi_uc_pmu_enable_counter_int(struct hisi_pmu *uc_pmu, struct hw_perf_event *hwc) { diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c index 524ba82bfce2..e2abca188dbe 100644 --- a/drivers/perf/marvell_cn10k_ddr_pmu.c +++ b/drivers/perf/marvell_cn10k_ddr_pmu.c @@ -697,7 +697,7 @@ error: return ret; } -static int cn10k_ddr_perf_remove(struct platform_device *pdev) +static void cn10k_ddr_perf_remove(struct platform_device *pdev) { struct cn10k_ddr_pmu *ddr_pmu = platform_get_drvdata(pdev); @@ -706,7 +706,6 @@ static int cn10k_ddr_perf_remove(struct platform_device *pdev) &ddr_pmu->node); perf_pmu_unregister(&ddr_pmu->pmu); - return 0; } #ifdef CONFIG_OF @@ -733,7 +732,7 @@ static struct platform_driver cn10k_ddr_pmu_driver = { .suppress_bind_attrs = true, }, .probe = cn10k_ddr_perf_probe, - .remove = cn10k_ddr_perf_remove, + .remove_new = cn10k_ddr_perf_remove, }; static int __init cn10k_ddr_pmu_init(void) diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c index fec8e82edb95..9e635f355470 100644 --- a/drivers/perf/marvell_cn10k_tad_pmu.c +++ b/drivers/perf/marvell_cn10k_tad_pmu.c @@ -351,15 +351,13 @@ static int tad_pmu_probe(struct platform_device *pdev) return ret; } -static int tad_pmu_remove(struct platform_device *pdev) +static void tad_pmu_remove(struct platform_device *pdev) { struct tad_pmu *pmu = platform_get_drvdata(pdev); cpuhp_state_remove_instance_nocalls(tad_pmu_cpuhp_state, &pmu->node); perf_pmu_unregister(&pmu->pmu); - - return 0; } #ifdef CONFIG_OF @@ -385,7 +383,7 @@ static struct platform_driver tad_pmu_driver = { .suppress_bind_attrs = true, }, .probe = tad_pmu_probe, - .remove = tad_pmu_remove, + .remove_new = tad_pmu_remove, }; static int tad_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) diff --git a/drivers/perf/qcom_l2_pmu.c b/drivers/perf/qcom_l2_pmu.c index 3f9a98c17a89..148df5ae8ef8 100644 --- a/drivers/perf/qcom_l2_pmu.c +++ b/drivers/perf/qcom_l2_pmu.c @@ -965,7 +965,7 @@ out_unregister: return err; } -static int l2_cache_pmu_remove(struct platform_device *pdev) +static void l2_cache_pmu_remove(struct platform_device *pdev) { struct l2cache_pmu *l2cache_pmu = to_l2cache_pmu(platform_get_drvdata(pdev)); @@ -973,7 +973,6 @@ static int l2_cache_pmu_remove(struct platform_device *pdev) perf_pmu_unregister(&l2cache_pmu->pmu); cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, &l2cache_pmu->node); - return 0; } static struct platform_driver l2_cache_pmu_driver = { @@ -983,7 +982,7 @@ static struct platform_driver l2_cache_pmu_driver = { .suppress_bind_attrs = true, }, .probe = l2_cache_pmu_probe, - .remove = l2_cache_pmu_remove, + .remove_new = l2_cache_pmu_remove, }; static int __init register_l2_cache_pmu_driver(void) diff --git a/drivers/perf/starfive_starlink_pmu.c b/drivers/perf/starfive_starlink_pmu.c new file mode 100644 index 000000000000..5e5a672b4229 --- /dev/null +++ b/drivers/perf/starfive_starlink_pmu.c @@ -0,0 +1,642 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * StarFive's StarLink PMU driver + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Ji Sheng Teoh <jisheng.teoh@starfivetech.com> + * + */ + +#define STARLINK_PMU_PDEV_NAME "starfive_starlink_pmu" +#define pr_fmt(fmt) STARLINK_PMU_PDEV_NAME ": " fmt + +#include <linux/bitmap.h> +#include <linux/cpu_pm.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mod_devicetable.h> +#include <linux/perf_event.h> +#include <linux/platform_device.h> +#include <linux/sysfs.h> + +#define STARLINK_PMU_MAX_COUNTERS 64 +#define STARLINK_PMU_NUM_COUNTERS 16 +#define STARLINK_PMU_IDX_CYCLE_COUNTER 63 + +#define STARLINK_PMU_EVENT_SELECT 0x060 +#define STARLINK_PMU_EVENT_COUNTER 0x160 +#define STARLINK_PMU_COUNTER_MASK GENMASK_ULL(63, 0) +#define STARLINK_PMU_CYCLE_COUNTER 0x058 + +#define STARLINK_PMU_CONTROL 0x040 +#define STARLINK_PMU_GLOBAL_ENABLE BIT_ULL(0) + +#define STARLINK_PMU_INTERRUPT_ENABLE 0x050 +#define STARLINK_PMU_COUNTER_OVERFLOW_STATUS 0x048 +#define STARLINK_PMU_CYCLE_OVERFLOW_MASK BIT_ULL(63) + +#define STARLINK_CYCLES 0x058 +#define CACHE_READ_REQUEST 0x04000701 +#define CACHE_WRITE_REQUEST 0x03000001 +#define CACHE_RELEASE_REQUEST 0x0003e001 +#define CACHE_READ_HIT 0x00901202 +#define CACHE_READ_MISS 0x04008002 +#define CACHE_WRITE_HIT 0x006c0002 +#define CACHE_WRITE_MISS 0x03000002 +#define CACHE_WRITEBACK 0x00000403 + +#define to_starlink_pmu(p) (container_of(p, struct starlink_pmu, pmu)) + +#define STARLINK_FORMAT_ATTR(_name, _config) \ + (&((struct dev_ext_attribute[]) { \ + { .attr = __ATTR(_name, 0444, starlink_pmu_sysfs_format_show, NULL), \ + .var = (void *)_config, } \ + })[0].attr.attr) + +#define STARLINK_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR_ID(_name, starlink_pmu_sysfs_event_show, _id) + +static int starlink_pmu_cpuhp_state; + +struct starlink_hw_events { + struct perf_event *events[STARLINK_PMU_MAX_COUNTERS]; + DECLARE_BITMAP(used_mask, STARLINK_PMU_MAX_COUNTERS); +}; + +struct starlink_pmu { + struct pmu pmu; + struct starlink_hw_events __percpu *hw_events; + struct hlist_node node; + struct notifier_block starlink_pmu_pm_nb; + void __iomem *pmu_base; + cpumask_t cpumask; + int irq; +}; + +static ssize_t +starlink_pmu_sysfs_format_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *eattr = container_of(attr, + struct dev_ext_attribute, attr); + + return sysfs_emit(buf, "%s\n", (char *)eattr->var); +} + +static struct attribute *starlink_pmu_format_attrs[] = { + STARLINK_FORMAT_ATTR(event, "config:0-31"), + NULL +}; + +static const struct attribute_group starlink_pmu_format_attr_group = { + .name = "format", + .attrs = starlink_pmu_format_attrs, +}; + +static ssize_t +starlink_pmu_sysfs_event_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct perf_pmu_events_attr *eattr = container_of(attr, + struct perf_pmu_events_attr, attr); + + return sysfs_emit(buf, "event=0x%02llx\n", eattr->id); +} + +static struct attribute *starlink_pmu_event_attrs[] = { + STARLINK_EVENT_ATTR(cycles, STARLINK_CYCLES), + STARLINK_EVENT_ATTR(read_request, CACHE_READ_REQUEST), + STARLINK_EVENT_ATTR(write_request, CACHE_WRITE_REQUEST), + STARLINK_EVENT_ATTR(release_request, CACHE_RELEASE_REQUEST), + STARLINK_EVENT_ATTR(read_hit, CACHE_READ_HIT), + STARLINK_EVENT_ATTR(read_miss, CACHE_READ_MISS), + STARLINK_EVENT_ATTR(write_hit, CACHE_WRITE_HIT), + STARLINK_EVENT_ATTR(write_miss, CACHE_WRITE_MISS), + STARLINK_EVENT_ATTR(writeback, CACHE_WRITEBACK), + NULL +}; + +static const struct attribute_group starlink_pmu_events_attr_group = { + .name = "events", + .attrs = starlink_pmu_event_attrs, +}; + +static ssize_t +cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, &starlink_pmu->cpumask); +} + +static DEVICE_ATTR_RO(cpumask); + +static struct attribute *starlink_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static const struct attribute_group starlink_pmu_cpumask_attr_group = { + .attrs = starlink_pmu_cpumask_attrs, +}; + +static const struct attribute_group *starlink_pmu_attr_groups[] = { + &starlink_pmu_format_attr_group, + &starlink_pmu_events_attr_group, + &starlink_pmu_cpumask_attr_group, + NULL +}; + +static void starlink_pmu_set_event_period(struct perf_event *event) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = event->hw.idx; + + /* + * Program counter to half of it's max count to handle + * cases of extreme interrupt latency. + */ + u64 val = STARLINK_PMU_COUNTER_MASK >> 1; + + local64_set(&hwc->prev_count, val); + if (hwc->config == STARLINK_CYCLES) + writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_CYCLE_COUNTER); + else + writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_EVENT_COUNTER + + idx * sizeof(u64)); +} + +static void starlink_pmu_counter_start(struct perf_event *event, + struct starlink_pmu *starlink_pmu) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = event->hw.idx; + u64 val; + + /* + * Enable counter overflow interrupt[63:0], + * which is mapped as follow: + * + * event counter 0 - Bit [0] + * event counter 1 - Bit [1] + * ... + * cycle counter - Bit [63] + */ + val = readq(starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE); + + if (hwc->config == STARLINK_CYCLES) { + /* + * Cycle count has its dedicated register, and it starts + * counting as soon as STARLINK_PMU_GLOBAL_ENABLE is set. + */ + val |= STARLINK_PMU_CYCLE_OVERFLOW_MASK; + } else { + writeq(event->hw.config, starlink_pmu->pmu_base + + STARLINK_PMU_EVENT_SELECT + idx * sizeof(u64)); + + val |= BIT_ULL(idx); + } + + writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE); + + writeq(STARLINK_PMU_GLOBAL_ENABLE, starlink_pmu->pmu_base + + STARLINK_PMU_CONTROL); +} + +static void starlink_pmu_counter_stop(struct perf_event *event, + struct starlink_pmu *starlink_pmu) +{ + struct hw_perf_event *hwc = &event->hw; + int idx = event->hw.idx; + u64 val; + + val = readq(starlink_pmu->pmu_base + STARLINK_PMU_CONTROL); + val &= ~STARLINK_PMU_GLOBAL_ENABLE; + writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_CONTROL); + + val = readq(starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE); + if (hwc->config == STARLINK_CYCLES) + val &= ~STARLINK_PMU_CYCLE_OVERFLOW_MASK; + else + val &= ~BIT_ULL(idx); + + writeq(val, starlink_pmu->pmu_base + STARLINK_PMU_INTERRUPT_ENABLE); +} + +static void starlink_pmu_update(struct perf_event *event) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + u64 prev_raw_count, new_raw_count; + u64 oldval; + u64 delta; + + do { + prev_raw_count = local64_read(&hwc->prev_count); + if (hwc->config == STARLINK_CYCLES) + new_raw_count = readq(starlink_pmu->pmu_base + + STARLINK_PMU_CYCLE_COUNTER); + else + new_raw_count = readq(starlink_pmu->pmu_base + + STARLINK_PMU_EVENT_COUNTER + + idx * sizeof(u64)); + oldval = local64_cmpxchg(&hwc->prev_count, prev_raw_count, + new_raw_count); + } while (oldval != prev_raw_count); + + delta = (new_raw_count - prev_raw_count) & STARLINK_PMU_COUNTER_MASK; + local64_add(delta, &event->count); +} + +static void starlink_pmu_start(struct perf_event *event, int flags) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) + WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); + + hwc->state = 0; + + starlink_pmu_set_event_period(event); + starlink_pmu_counter_start(event, starlink_pmu); + + perf_event_update_userpage(event); +} + +static void starlink_pmu_stop(struct perf_event *event, int flags) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + if (hwc->state & PERF_HES_STOPPED) + return; + + starlink_pmu_counter_stop(event, starlink_pmu); + starlink_pmu_update(event); + hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE; +} + +static int starlink_pmu_add(struct perf_event *event, int flags) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct starlink_hw_events *hw_events = + this_cpu_ptr(starlink_pmu->hw_events); + struct hw_perf_event *hwc = &event->hw; + unsigned long *used_mask = hw_events->used_mask; + u32 n_events = STARLINK_PMU_NUM_COUNTERS; + int idx; + + /* + * Cycle counter has dedicated register to hold counter value. + * Event other than cycle count has to be enabled through + * event select register, and assigned with independent counter + * as they appear. + */ + + if (hwc->config == STARLINK_CYCLES) { + idx = STARLINK_PMU_IDX_CYCLE_COUNTER; + } else { + idx = find_first_zero_bit(used_mask, n_events); + /* All counter are in use */ + if (idx < 0) + return idx; + + set_bit(idx, used_mask); + } + + hwc->idx = idx; + hw_events->events[idx] = event; + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (flags & PERF_EF_START) + starlink_pmu_start(event, PERF_EF_RELOAD); + + perf_event_update_userpage(event); + + return 0; +} + +static void starlink_pmu_del(struct perf_event *event, int flags) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct starlink_hw_events *hw_events = + this_cpu_ptr(starlink_pmu->hw_events); + struct hw_perf_event *hwc = &event->hw; + + starlink_pmu_stop(event, PERF_EF_UPDATE); + hw_events->events[hwc->idx] = NULL; + clear_bit(hwc->idx, hw_events->used_mask); + + perf_event_update_userpage(event); +} + +static bool starlink_pmu_validate_event_group(struct perf_event *event) +{ + struct perf_event *leader = event->group_leader; + struct perf_event *sibling; + int counter = 1; + + /* + * Ensure hardware events in the group are on the same PMU, + * software events are acceptable. + */ + if (event->group_leader->pmu != event->pmu && + !is_software_event(event->group_leader)) + return false; + + for_each_sibling_event(sibling, leader) { + if (sibling->pmu != event->pmu && !is_software_event(sibling)) + return false; + + counter++; + } + + return counter <= STARLINK_PMU_NUM_COUNTERS; +} + +static int starlink_pmu_event_init(struct perf_event *event) +{ + struct starlink_pmu *starlink_pmu = to_starlink_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + /* + * Sampling is not supported, as counters are shared + * by all CPU. + */ + if (hwc->sample_period) + return -EOPNOTSUPP; + + /* + * Per-task and attach to a task are not supported, + * as uncore events are not specific to any CPU. + */ + if (event->cpu < 0 || event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + + if (!starlink_pmu_validate_event_group(event)) + return -EINVAL; + + hwc->idx = -1; + hwc->config = event->attr.config; + event->cpu = cpumask_first(&starlink_pmu->cpumask); + + return 0; +} + +static irqreturn_t starlink_pmu_handle_irq(int irq_num, void *data) +{ + struct starlink_pmu *starlink_pmu = data; + struct starlink_hw_events *hw_events = + this_cpu_ptr(starlink_pmu->hw_events); + bool handled = false; + int idx; + u64 overflow_status; + + for (idx = 0; idx < STARLINK_PMU_MAX_COUNTERS; idx++) { + struct perf_event *event = hw_events->events[idx]; + + if (!event) + continue; + + overflow_status = readq(starlink_pmu->pmu_base + + STARLINK_PMU_COUNTER_OVERFLOW_STATUS); + if (!(overflow_status & BIT_ULL(idx))) + continue; + + writeq(BIT_ULL(idx), starlink_pmu->pmu_base + + STARLINK_PMU_COUNTER_OVERFLOW_STATUS); + + starlink_pmu_update(event); + starlink_pmu_set_event_period(event); + handled = true; + } + return IRQ_RETVAL(handled); +} + +static int starlink_setup_irqs(struct starlink_pmu *starlink_pmu, + struct platform_device *pdev) +{ + int ret, irq; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return -EINVAL; + + ret = devm_request_irq(&pdev->dev, irq, starlink_pmu_handle_irq, + 0, STARLINK_PMU_PDEV_NAME, starlink_pmu); + if (ret) + return dev_err_probe(&pdev->dev, ret, "Failed to request IRQ\n"); + + starlink_pmu->irq = irq; + + return 0; +} + +static int starlink_pmu_pm_notify(struct notifier_block *b, + unsigned long cmd, void *v) +{ + struct starlink_pmu *starlink_pmu = container_of(b, struct starlink_pmu, + starlink_pmu_pm_nb); + struct starlink_hw_events *hw_events = + this_cpu_ptr(starlink_pmu->hw_events); + int enabled = bitmap_weight(hw_events->used_mask, + STARLINK_PMU_MAX_COUNTERS); + struct perf_event *event; + int idx; + + if (!enabled) + return NOTIFY_OK; + + for (idx = 0; idx < STARLINK_PMU_MAX_COUNTERS; idx++) { + event = hw_events->events[idx]; + if (!event) + continue; + + switch (cmd) { + case CPU_PM_ENTER: + /* Stop and update the counter */ + starlink_pmu_stop(event, PERF_EF_UPDATE); + break; + case CPU_PM_EXIT: + case CPU_PM_ENTER_FAILED: + /* Restore and enable the counter */ + starlink_pmu_start(event, PERF_EF_RELOAD); + break; + default: + break; + } + } + + return NOTIFY_OK; +} + +static int starlink_pmu_pm_register(struct starlink_pmu *starlink_pmu) +{ + if (!IS_ENABLED(CONFIG_CPU_PM)) + return 0; + + starlink_pmu->starlink_pmu_pm_nb.notifier_call = starlink_pmu_pm_notify; + return cpu_pm_register_notifier(&starlink_pmu->starlink_pmu_pm_nb); +} + +static void starlink_pmu_pm_unregister(struct starlink_pmu *starlink_pmu) +{ + if (!IS_ENABLED(CONFIG_CPU_PM)) + return; + + cpu_pm_unregister_notifier(&starlink_pmu->starlink_pmu_pm_nb); +} + +static void starlink_pmu_destroy(struct starlink_pmu *starlink_pmu) +{ + starlink_pmu_pm_unregister(starlink_pmu); + cpuhp_state_remove_instance(starlink_pmu_cpuhp_state, + &starlink_pmu->node); +} + +static int starlink_pmu_probe(struct platform_device *pdev) +{ + struct starlink_pmu *starlink_pmu; + struct starlink_hw_events *hw_events; + struct resource *res; + int cpuid, i, ret; + + starlink_pmu = devm_kzalloc(&pdev->dev, sizeof(*starlink_pmu), GFP_KERNEL); + if (!starlink_pmu) + return -ENOMEM; + + starlink_pmu->pmu_base = + devm_platform_get_and_ioremap_resource(pdev, 0, &res); + if (IS_ERR(starlink_pmu->pmu_base)) + return PTR_ERR(starlink_pmu->pmu_base); + + starlink_pmu->hw_events = alloc_percpu_gfp(struct starlink_hw_events, + GFP_KERNEL); + if (!starlink_pmu->hw_events) { + dev_err(&pdev->dev, "Failed to allocate per-cpu PMU data\n"); + return -ENOMEM; + } + + for_each_possible_cpu(cpuid) { + hw_events = per_cpu_ptr(starlink_pmu->hw_events, cpuid); + for (i = 0; i < STARLINK_PMU_MAX_COUNTERS; i++) + hw_events->events[i] = NULL; + } + + ret = starlink_setup_irqs(starlink_pmu, pdev); + if (ret) + return ret; + + ret = cpuhp_state_add_instance(starlink_pmu_cpuhp_state, + &starlink_pmu->node); + if (ret) { + dev_err(&pdev->dev, "Failed to register hotplug\n"); + return ret; + } + + ret = starlink_pmu_pm_register(starlink_pmu); + if (ret) { + cpuhp_state_remove_instance(starlink_pmu_cpuhp_state, + &starlink_pmu->node); + return ret; + } + + starlink_pmu->pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .event_init = starlink_pmu_event_init, + .add = starlink_pmu_add, + .del = starlink_pmu_del, + .start = starlink_pmu_start, + .stop = starlink_pmu_stop, + .read = starlink_pmu_update, + .attr_groups = starlink_pmu_attr_groups, + }; + + ret = perf_pmu_register(&starlink_pmu->pmu, STARLINK_PMU_PDEV_NAME, -1); + if (ret) + starlink_pmu_destroy(starlink_pmu); + + return ret; +} + +static const struct of_device_id starlink_pmu_of_match[] = { + { .compatible = "starfive,jh8100-starlink-pmu" }, + {} +}; +MODULE_DEVICE_TABLE(of, starlink_pmu_of_match); + +static struct platform_driver starlink_pmu_driver = { + .driver = { + .name = STARLINK_PMU_PDEV_NAME, + .of_match_table = starlink_pmu_of_match, + .suppress_bind_attrs = true, + }, + .probe = starlink_pmu_probe, +}; + +static int +starlink_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct starlink_pmu *starlink_pmu = hlist_entry_safe(node, + struct starlink_pmu, + node); + + if (cpumask_empty(&starlink_pmu->cpumask)) + cpumask_set_cpu(cpu, &starlink_pmu->cpumask); + + WARN_ON(irq_set_affinity(starlink_pmu->irq, cpumask_of(cpu))); + + return 0; +} + +static int +starlink_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct starlink_pmu *starlink_pmu = hlist_entry_safe(node, + struct starlink_pmu, + node); + unsigned int target; + + if (!cpumask_test_and_clear_cpu(cpu, &starlink_pmu->cpumask)) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) + return 0; + + perf_pmu_migrate_context(&starlink_pmu->pmu, cpu, target); + + cpumask_set_cpu(target, &starlink_pmu->cpumask); + WARN_ON(irq_set_affinity(starlink_pmu->irq, cpumask_of(target))); + + return 0; +} + +static int __init starlink_pmu_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, + "soc/starfive/starlink_pmu:online", + starlink_pmu_online_cpu, + starlink_pmu_offline_cpu); + if (ret < 0) + return ret; + + starlink_pmu_cpuhp_state = ret; + + return platform_driver_register(&starlink_pmu_driver); +} + +device_initcall(starlink_pmu_init); diff --git a/drivers/perf/thunderx2_pmu.c b/drivers/perf/thunderx2_pmu.c index 1edb9c03704f..e16d10c763de 100644 --- a/drivers/perf/thunderx2_pmu.c +++ b/drivers/perf/thunderx2_pmu.c @@ -993,7 +993,7 @@ static int tx2_uncore_probe(struct platform_device *pdev) return 0; } -static int tx2_uncore_remove(struct platform_device *pdev) +static void tx2_uncore_remove(struct platform_device *pdev) { struct tx2_uncore_pmu *tx2_pmu, *temp; struct device *dev = &pdev->dev; @@ -1009,7 +1009,6 @@ static int tx2_uncore_remove(struct platform_device *pdev) } } } - return 0; } static struct platform_driver tx2_uncore_driver = { @@ -1019,7 +1018,7 @@ static struct platform_driver tx2_uncore_driver = { .suppress_bind_attrs = true, }, .probe = tx2_uncore_probe, - .remove = tx2_uncore_remove, + .remove_new = tx2_uncore_remove, }; static int __init tx2_uncore_driver_init(void) diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c index 7ce344248dda..0d49343d704b 100644 --- a/drivers/perf/xgene_pmu.c +++ b/drivers/perf/xgene_pmu.c @@ -1937,7 +1937,7 @@ xgene_pmu_dev_cleanup(struct xgene_pmu *xgene_pmu, struct list_head *pmus) } } -static int xgene_pmu_remove(struct platform_device *pdev) +static void xgene_pmu_remove(struct platform_device *pdev) { struct xgene_pmu *xgene_pmu = dev_get_drvdata(&pdev->dev); @@ -1947,13 +1947,11 @@ static int xgene_pmu_remove(struct platform_device *pdev) xgene_pmu_dev_cleanup(xgene_pmu, &xgene_pmu->mcpmus); cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE, &xgene_pmu->node); - - return 0; } static struct platform_driver xgene_pmu_driver = { .probe = xgene_pmu_probe, - .remove = xgene_pmu_remove, + .remove_new = xgene_pmu_remove, .driver = { .name = "xgene-pmu", .of_match_table = xgene_pmu_of_match, diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 9417309b7230..b54b313bcf07 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -440,6 +440,7 @@ typedef struct elf64_shdr { #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/rust/Makefile b/rust/Makefile index a78fcf4004b0..1eaefc34f4b7 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -297,6 +297,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ # Derived from `scripts/Makefile.clang`. BINDGEN_TARGET_x86 := x86_64-linux-gnu +BINDGEN_TARGET_arm64 := aarch64-linux-gnu BINDGEN_TARGET := $(BINDGEN_TARGET_$(SRCARCH)) # All warnings are inhibited since GCC builds are very experimental, @@ -434,8 +435,11 @@ $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Dunreachable_pub $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) $(obj)/core.o: private rustc_target_flags = $(core-cfgs) -$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs scripts/target.json FORCE +$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs FORCE +$(call if_changed_dep,rustc_library) +ifneq ($(or $(CONFIG_X86_64),$(CONFIG_LOONGARCH)),) +$(obj)/core.o: scripts/target.json +endif $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE diff --git a/scripts/Makefile b/scripts/Makefile index 576cf64be667..6673cbb6194f 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -11,12 +11,14 @@ hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS) += rustdoc_test_builder hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS) += rustdoc_test_gen -always-$(CONFIG_RUST) += target.json +ifneq ($(or $(CONFIG_X86_64),$(CONFIG_LOONGARCH)),) +always-$(CONFIG_RUST) += target.json filechk_rust_target = $< < include/config/auto.conf $(obj)/target.json: scripts/generate_rust_target include/config/auto.conf FORCE $(call filechk,rust_target) +endif hostprogs += generate_rust_target generate_rust_target-rust := y diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 19f72bfdbb82..54919cf48621 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -148,7 +148,9 @@ fn main() { let mut ts = TargetSpec::new(); // `llvm-target`s are taken from `scripts/Makefile.clang`. - if cfg.has("X86_64") { + if cfg.has("ARM64") { + panic!("arm64 uses the builtin rustc aarch64-unknown-none target"); + } else if cfg.has("X86_64") { ts.push("arch", "x86_64"); ts.push( "data-layout", diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 1189e77c8152..d8909b2b535a 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -58,11 +58,46 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void f8cvt_sigill(void) +{ + /* FSCALE V0.4H, V0.4H, V0.4H */ + asm volatile(".inst 0x2ec03c00"); +} + +static void f8dp2_sigill(void) +{ + /* FDOT V0.4H, V0.4H, V0.5H */ + asm volatile(".inst 0xe40fc00"); +} + +static void f8dp4_sigill(void) +{ + /* FDOT V0.2S, V0.2S, V0.2S */ + asm volatile(".inst 0xe00fc00"); +} + +static void f8fma_sigill(void) +{ + /* FMLALB V0.8H, V0.16B, V0.16B */ + asm volatile(".inst 0xec0fc00"); +} + +static void faminmax_sigill(void) +{ + /* FAMIN V0.4H, V0.4H, V0.4H */ + asm volatile(".inst 0x2ec01c00"); +} + static void fp_sigill(void) { asm volatile("fmov s0, #1"); } +static void fpmr_sigill(void) +{ + asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0"); +} + static void ilrcpc_sigill(void) { /* LDAPUR W0, [SP, #8] */ @@ -95,6 +130,12 @@ static void lse128_sigill(void) : "cc", "memory"); } +static void lut_sigill(void) +{ + /* LUTI2 V0.16B, { V0.16B }, V[0] */ + asm volatile(".inst 0x4e801000"); +} + static void mops_sigill(void) { char dst[1], src[1]; @@ -216,6 +257,78 @@ static void smef16f16_sigill(void) asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); } +static void smef8f16_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT ZA.H[W0, 0], Z0.B-Z1.B, Z0.B-Z1.B */ + asm volatile(".inst 0xc1a01020" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smef8f32_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT ZA.S[W0, 0], { Z0.B-Z1.B }, Z0.B[0] */ + asm volatile(".inst 0xc1500038" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smelutv2_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* LUTI4 { Z0.B-Z3.B }, ZT0, { Z0-Z1 } */ + asm volatile(".inst 0xc08b0000" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8dp2_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT Z0.H, Z0.B, Z0.B[0] */ + asm volatile(".inst 0x64204400" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8dp4_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT Z0.S, Z0.B, Z0.B[0] */ + asm volatile(".inst 0xc1a41C00" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8fma_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FMLALB V0.8H, V0.16B, V0.16B */ + asm volatile(".inst 0xec0fc00"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + static void sve_sigill(void) { /* RDVL x0, #0 */ @@ -354,6 +467,53 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "F8CVT", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8CVT, + .cpuinfo = "f8cvt", + .sigill_fn = f8cvt_sigill, + }, + { + .name = "F8DP4", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8DP4, + .cpuinfo = "f8dp4", + .sigill_fn = f8dp4_sigill, + }, + { + .name = "F8DP2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8DP2, + .cpuinfo = "f8dp4", + .sigill_fn = f8dp2_sigill, + }, + { + .name = "F8E5M2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8E5M2, + .cpuinfo = "f8e5m2", + }, + { + .name = "F8E4M3", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8E4M3, + .cpuinfo = "f8e4m3", + }, + { + .name = "F8FMA", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8FMA, + .cpuinfo = "f8fma", + .sigill_fn = f8fma_sigill, + }, + { + .name = "FAMINMAX", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_FAMINMAX, + .cpuinfo = "faminmax", + .sigill_fn = faminmax_sigill, + }, + { .name = "FP", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_FP, @@ -361,6 +521,14 @@ static const struct hwcap_data { .sigill_fn = fp_sigill, }, { + .name = "FPMR", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_FPMR, + .cpuinfo = "fpmr", + .sigill_fn = fpmr_sigill, + .sigill_reliable = true, + }, + { .name = "JSCVT", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_JSCVT, @@ -412,6 +580,13 @@ static const struct hwcap_data { .sigill_fn = lse128_sigill, }, { + .name = "LUT", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_LUT, + .cpuinfo = "lut", + .sigill_fn = lut_sigill, + }, + { .name = "MOPS", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_MOPS, @@ -512,6 +687,48 @@ static const struct hwcap_data { .sigill_fn = smef16f16_sigill, }, { + .name = "SME F8F16", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_F8F16, + .cpuinfo = "smef8f16", + .sigill_fn = smef8f16_sigill, + }, + { + .name = "SME F8F32", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_F8F32, + .cpuinfo = "smef8f32", + .sigill_fn = smef8f32_sigill, + }, + { + .name = "SME LUTV2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_LUTV2, + .cpuinfo = "smelutv2", + .sigill_fn = smelutv2_sigill, + }, + { + .name = "SME SF8FMA", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8FMA, + .cpuinfo = "smesf8fma", + .sigill_fn = smesf8fma_sigill, + }, + { + .name = "SME SF8DP2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8DP2, + .cpuinfo = "smesf8dp2", + .sigill_fn = smesf8dp2_sigill, + }, + { + .name = "SME SF8DP4", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8DP4, + .cpuinfo = "smesf8dp4", + .sigill_fn = smesf8dp4_sigill, + }, + { .name = "SVE", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_SVE, diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index ebc86757bdd8..00e52c966281 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,4 +1,5 @@ fp-pidbench +fp-ptrace fp-stress fpsimd-test rdvl-sme diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index b413b0af07f9..55d4f00d9e8e 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -5,7 +5,9 @@ top_srcdir = $(realpath ../../../../../) CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := fp-stress \ +TEST_GEN_PROGS := \ + fp-ptrace \ + fp-stress \ sve-ptrace sve-probe-vls \ vec-syscfg \ za-fork za-ptrace @@ -24,6 +26,7 @@ EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o # Build with nolibc to avoid effects due to libc's clone() support $(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ +$(OUTPUT)/fp-ptrace: fp-ptrace.c fp-ptrace-asm.S $(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ $(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S new file mode 100644 index 000000000000..7ad59d92d02b --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-3 ARM Limited. +// +// Assembly portion of the FP ptrace test + +// +// Load values from memory into registers, break on a breakpoint, then +// break on a further breakpoint +// + +#include "fp-ptrace.h" +#include "sme-inst.h" + +.arch_extension sve + +// Load and save register values with pauses for ptrace +// +// x0 - SVE in use +// x1 - SME in use +// x2 - SME2 in use +// x3 - FA64 supported + +.globl load_and_save +load_and_save: + stp x11, x12, [sp, #-0x10]! + + // This should be redundant in the SVE case + ldr x7, =v_in + ldp q0, q1, [x7] + ldp q2, q3, [x7, #16 * 2] + ldp q4, q5, [x7, #16 * 4] + ldp q6, q7, [x7, #16 * 6] + ldp q8, q9, [x7, #16 * 8] + ldp q10, q11, [x7, #16 * 10] + ldp q12, q13, [x7, #16 * 12] + ldp q14, q15, [x7, #16 * 14] + ldp q16, q17, [x7, #16 * 16] + ldp q18, q19, [x7, #16 * 18] + ldp q20, q21, [x7, #16 * 20] + ldp q22, q23, [x7, #16 * 22] + ldp q24, q25, [x7, #16 * 24] + ldp q26, q27, [x7, #16 * 26] + ldp q28, q29, [x7, #16 * 28] + ldp q30, q31, [x7, #16 * 30] + + // SME? + cbz x1, check_sve_in + + adrp x7, svcr_in + ldr x7, [x7, :lo12:svcr_in] + // SVCR is 0 by default, avoid triggering SME if not in use + cbz x7, check_sve_in + msr S3_3_C4_C2_2, x7 + + // ZA? + tbz x7, #SVCR_ZA_SHIFT, check_sm_in + rdsvl 11, 1 + mov w12, #0 + ldr x6, =za_in +1: _ldr_za 12, 6 + add x6, x6, x11 + add x12, x12, #1 + cmp x11, x12 + bne 1b + + // ZT? + cbz x2, check_sm_in + adrp x6, zt_in + add x6, x6, :lo12:zt_in + _ldr_zt 6 + + // In streaming mode? +check_sm_in: + tbz x7, #SVCR_SM_SHIFT, check_sve_in + mov x4, x3 // Load FFR if we have FA64 + b load_sve + + // SVE? +check_sve_in: + cbz x0, wait_for_writes + mov x4, #1 + +load_sve: + ldr x7, =z_in + ldr z0, [x7, #0, MUL VL] + ldr z1, [x7, #1, MUL VL] + ldr z2, [x7, #2, MUL VL] + ldr z3, [x7, #3, MUL VL] + ldr z4, [x7, #4, MUL VL] + ldr z5, [x7, #5, MUL VL] + ldr z6, [x7, #6, MUL VL] + ldr z7, [x7, #7, MUL VL] + ldr z8, [x7, #8, MUL VL] + ldr z9, [x7, #9, MUL VL] + ldr z10, [x7, #10, MUL VL] + ldr z11, [x7, #11, MUL VL] + ldr z12, [x7, #12, MUL VL] + ldr z13, [x7, #13, MUL VL] + ldr z14, [x7, #14, MUL VL] + ldr z15, [x7, #15, MUL VL] + ldr z16, [x7, #16, MUL VL] + ldr z17, [x7, #17, MUL VL] + ldr z18, [x7, #18, MUL VL] + ldr z19, [x7, #19, MUL VL] + ldr z20, [x7, #20, MUL VL] + ldr z21, [x7, #21, MUL VL] + ldr z22, [x7, #22, MUL VL] + ldr z23, [x7, #23, MUL VL] + ldr z24, [x7, #24, MUL VL] + ldr z25, [x7, #25, MUL VL] + ldr z26, [x7, #26, MUL VL] + ldr z27, [x7, #27, MUL VL] + ldr z28, [x7, #28, MUL VL] + ldr z29, [x7, #29, MUL VL] + ldr z30, [x7, #30, MUL VL] + ldr z31, [x7, #31, MUL VL] + + // FFR is not present in base SME + cbz x4, 1f + ldr x7, =ffr_in + ldr p0, [x7] + ldr x7, [x7, #0] + cbz x7, 1f + wrffr p0.b +1: + + ldr x7, =p_in + ldr p0, [x7, #0, MUL VL] + ldr p1, [x7, #1, MUL VL] + ldr p2, [x7, #2, MUL VL] + ldr p3, [x7, #3, MUL VL] + ldr p4, [x7, #4, MUL VL] + ldr p5, [x7, #5, MUL VL] + ldr p6, [x7, #6, MUL VL] + ldr p7, [x7, #7, MUL VL] + ldr p8, [x7, #8, MUL VL] + ldr p9, [x7, #9, MUL VL] + ldr p10, [x7, #10, MUL VL] + ldr p11, [x7, #11, MUL VL] + ldr p12, [x7, #12, MUL VL] + ldr p13, [x7, #13, MUL VL] + ldr p14, [x7, #14, MUL VL] + ldr p15, [x7, #15, MUL VL] + +wait_for_writes: + // Wait for the parent + brk #0 + + // Save values + ldr x7, =v_out + stp q0, q1, [x7] + stp q2, q3, [x7, #16 * 2] + stp q4, q5, [x7, #16 * 4] + stp q6, q7, [x7, #16 * 6] + stp q8, q9, [x7, #16 * 8] + stp q10, q11, [x7, #16 * 10] + stp q12, q13, [x7, #16 * 12] + stp q14, q15, [x7, #16 * 14] + stp q16, q17, [x7, #16 * 16] + stp q18, q19, [x7, #16 * 18] + stp q20, q21, [x7, #16 * 20] + stp q22, q23, [x7, #16 * 22] + stp q24, q25, [x7, #16 * 24] + stp q26, q27, [x7, #16 * 26] + stp q28, q29, [x7, #16 * 28] + stp q30, q31, [x7, #16 * 30] + + // SME? + cbz x1, check_sve_out + + rdsvl 11, 1 + adrp x6, sme_vl_out + str x11, [x6, :lo12:sme_vl_out] + + mrs x7, S3_3_C4_C2_2 + adrp x6, svcr_out + str x7, [x6, :lo12:svcr_out] + + // ZA? + tbz x7, #SVCR_ZA_SHIFT, check_sm_out + mov w12, #0 + ldr x6, =za_out +1: _str_za 12, 6 + add x6, x6, x11 + add x12, x12, #1 + cmp x11, x12 + bne 1b + + // ZT? + cbz x2, check_sm_out + adrp x6, zt_out + add x6, x6, :lo12:zt_out + _str_zt 6 + + // In streaming mode? +check_sm_out: + tbz x7, #SVCR_SM_SHIFT, check_sve_out + mov x4, x3 // FFR? + b read_sve + + // SVE? +check_sve_out: + cbz x0, wait_for_reads + mov x4, #1 + + rdvl x7, #1 + adrp x6, sve_vl_out + str x7, [x6, :lo12:sve_vl_out] + +read_sve: + ldr x7, =z_out + str z0, [x7, #0, MUL VL] + str z1, [x7, #1, MUL VL] + str z2, [x7, #2, MUL VL] + str z3, [x7, #3, MUL VL] + str z4, [x7, #4, MUL VL] + str z5, [x7, #5, MUL VL] + str z6, [x7, #6, MUL VL] + str z7, [x7, #7, MUL VL] + str z8, [x7, #8, MUL VL] + str z9, [x7, #9, MUL VL] + str z10, [x7, #10, MUL VL] + str z11, [x7, #11, MUL VL] + str z12, [x7, #12, MUL VL] + str z13, [x7, #13, MUL VL] + str z14, [x7, #14, MUL VL] + str z15, [x7, #15, MUL VL] + str z16, [x7, #16, MUL VL] + str z17, [x7, #17, MUL VL] + str z18, [x7, #18, MUL VL] + str z19, [x7, #19, MUL VL] + str z20, [x7, #20, MUL VL] + str z21, [x7, #21, MUL VL] + str z22, [x7, #22, MUL VL] + str z23, [x7, #23, MUL VL] + str z24, [x7, #24, MUL VL] + str z25, [x7, #25, MUL VL] + str z26, [x7, #26, MUL VL] + str z27, [x7, #27, MUL VL] + str z28, [x7, #28, MUL VL] + str z29, [x7, #29, MUL VL] + str z30, [x7, #30, MUL VL] + str z31, [x7, #31, MUL VL] + + ldr x7, =p_out + str p0, [x7, #0, MUL VL] + str p1, [x7, #1, MUL VL] + str p2, [x7, #2, MUL VL] + str p3, [x7, #3, MUL VL] + str p4, [x7, #4, MUL VL] + str p5, [x7, #5, MUL VL] + str p6, [x7, #6, MUL VL] + str p7, [x7, #7, MUL VL] + str p8, [x7, #8, MUL VL] + str p9, [x7, #9, MUL VL] + str p10, [x7, #10, MUL VL] + str p11, [x7, #11, MUL VL] + str p12, [x7, #12, MUL VL] + str p13, [x7, #13, MUL VL] + str p14, [x7, #14, MUL VL] + str p15, [x7, #15, MUL VL] + + // Only save FFR if it exists + cbz x4, wait_for_reads + ldr x7, =ffr_out + rdffr p0.b + str p0, [x7] + +wait_for_reads: + // Wait for the parent + brk #0 + + // Ensure we don't leave ourselves in streaming mode + cbz x1, out + msr S3_3_C4_C2_2, xzr + +out: + ldp x11, x12, [sp, #-0x10] + ret diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c new file mode 100644 index 000000000000..c7ceafe5f471 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -0,0 +1,1503 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 ARM Limited. + * Original author: Mark Brown <broonie@kernel.org> + */ + +#define _GNU_SOURCE + +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/ptrace.h> +#include <sys/types.h> +#include <sys/uio.h> +#include <sys/wait.h> + +#include <linux/kernel.h> + +#include <asm/sigcontext.h> +#include <asm/sve_context.h> +#include <asm/ptrace.h> + +#include "../../kselftest.h" + +#include "fp-ptrace.h" + +/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ +#ifndef NT_ARM_SVE +#define NT_ARM_SVE 0x405 +#endif + +#ifndef NT_ARM_SSVE +#define NT_ARM_SSVE 0x40b +#endif + +#ifndef NT_ARM_ZA +#define NT_ARM_ZA 0x40c +#endif + +#ifndef NT_ARM_ZT +#define NT_ARM_ZT 0x40d +#endif + +#define ARCH_VQ_MAX 256 + +/* VL 128..2048 in powers of 2 */ +#define MAX_NUM_VLS 5 + +#define NUM_FPR 32 +__uint128_t v_in[NUM_FPR]; +__uint128_t v_expected[NUM_FPR]; +__uint128_t v_out[NUM_FPR]; + +char z_in[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; +char z_expected[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; +char z_out[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; + +char p_in[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; +char p_expected[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; +char p_out[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; + +char ffr_in[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; +char ffr_expected[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; +char ffr_out[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; + +char za_in[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; +char za_expected[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; +char za_out[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; + +char zt_in[ZT_SIG_REG_BYTES]; +char zt_expected[ZT_SIG_REG_BYTES]; +char zt_out[ZT_SIG_REG_BYTES]; + +uint64_t sve_vl_out; +uint64_t sme_vl_out; +uint64_t svcr_in, svcr_expected, svcr_out; + +void load_and_save(int sve, int sme, int sme2, int fa64); + +static bool got_alarm; + +static void handle_alarm(int sig, siginfo_t *info, void *context) +{ + got_alarm = true; +} + +#ifdef CONFIG_CPU_BIG_ENDIAN +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + u64 a = swab64(x); + u64 b = swab64(x >> 64); + + return ((__uint128_t)a << 64) | b; +} +#else +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + return x; +} +#endif + +#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) + +static bool sve_supported(void) +{ + return getauxval(AT_HWCAP) & HWCAP_SVE; +} + +static bool sme_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME; +} + +static bool sme2_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME2; +} + +static bool fa64_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME_FA64; +} + +static bool compare_buffer(const char *name, void *out, + void *expected, size_t size) +{ + void *tmp; + + if (memcmp(out, expected, size) == 0) + return true; + + ksft_print_msg("Mismatch in %s\n", name); + + /* Did we just get zeros back? */ + tmp = malloc(size); + if (!tmp) { + ksft_print_msg("OOM allocating %lu bytes for %s\n", + size, name); + ksft_exit_fail(); + } + memset(tmp, 0, size); + + if (memcmp(out, tmp, size) == 0) + ksft_print_msg("%s is zero\n", name); + + free(tmp); + + return false; +} + +struct test_config { + int sve_vl_in; + int sve_vl_expected; + int sme_vl_in; + int sme_vl_expected; + int svcr_in; + int svcr_expected; +}; + +struct test_definition { + const char *name; + bool sve_vl_change; + bool (*supported)(struct test_config *config); + void (*set_expected_values)(struct test_config *config); + void (*modify_values)(pid_t child, struct test_config *test_config); +}; + +static int vl_in(struct test_config *config) +{ + int vl; + + if (config->svcr_in & SVCR_SM) + vl = config->sme_vl_in; + else + vl = config->sve_vl_in; + + return vl; +} + +static int vl_expected(struct test_config *config) +{ + int vl; + + if (config->svcr_expected & SVCR_SM) + vl = config->sme_vl_expected; + else + vl = config->sve_vl_expected; + + return vl; +} + +static void run_child(struct test_config *config) +{ + int ret; + + /* Let the parent attach to us */ + ret = ptrace(PTRACE_TRACEME, 0, 0, 0); + if (ret < 0) + ksft_exit_fail_msg("PTRACE_TRACEME failed: %s (%d)\n", + strerror(errno), errno); + + /* VL setup */ + if (sve_supported()) { + ret = prctl(PR_SVE_SET_VL, config->sve_vl_in); + if (ret != config->sve_vl_in) { + ksft_print_msg("Failed to set SVE VL %d: %d\n", + config->sve_vl_in, ret); + } + } + + if (sme_supported()) { + ret = prctl(PR_SME_SET_VL, config->sme_vl_in); + if (ret != config->sme_vl_in) { + ksft_print_msg("Failed to set SME VL %d: %d\n", + config->sme_vl_in, ret); + } + } + + /* Load values and wait for the parent */ + load_and_save(sve_supported(), sme_supported(), + sme2_supported(), fa64_supported()); + + exit(0); +} + +static void read_one_child_regs(pid_t child, char *name, + struct iovec *iov_parent, + struct iovec *iov_child) +{ + int len = iov_parent->iov_len; + int ret; + + ret = process_vm_readv(child, iov_parent, 1, iov_child, 1, 0); + if (ret == -1) + ksft_print_msg("%s read failed: %s (%d)\n", + name, strerror(errno), errno); + else if (ret != len) + ksft_print_msg("Short read of %s: %d\n", name, ret); +} + +static void read_child_regs(pid_t child) +{ + struct iovec iov_parent, iov_child; + + /* + * Since the child fork()ed from us the buffer addresses are + * the same in parent and child. + */ + iov_parent.iov_base = &v_out; + iov_parent.iov_len = sizeof(v_out); + iov_child.iov_base = &v_out; + iov_child.iov_len = sizeof(v_out); + read_one_child_regs(child, "FPSIMD", &iov_parent, &iov_child); + + if (sve_supported() || sme_supported()) { + iov_parent.iov_base = &sve_vl_out; + iov_parent.iov_len = sizeof(sve_vl_out); + iov_child.iov_base = &sve_vl_out; + iov_child.iov_len = sizeof(sve_vl_out); + read_one_child_regs(child, "SVE VL", &iov_parent, &iov_child); + + iov_parent.iov_base = &z_out; + iov_parent.iov_len = sizeof(z_out); + iov_child.iov_base = &z_out; + iov_child.iov_len = sizeof(z_out); + read_one_child_regs(child, "Z", &iov_parent, &iov_child); + + iov_parent.iov_base = &p_out; + iov_parent.iov_len = sizeof(p_out); + iov_child.iov_base = &p_out; + iov_child.iov_len = sizeof(p_out); + read_one_child_regs(child, "P", &iov_parent, &iov_child); + + iov_parent.iov_base = &ffr_out; + iov_parent.iov_len = sizeof(ffr_out); + iov_child.iov_base = &ffr_out; + iov_child.iov_len = sizeof(ffr_out); + read_one_child_regs(child, "FFR", &iov_parent, &iov_child); + } + + if (sme_supported()) { + iov_parent.iov_base = &sme_vl_out; + iov_parent.iov_len = sizeof(sme_vl_out); + iov_child.iov_base = &sme_vl_out; + iov_child.iov_len = sizeof(sme_vl_out); + read_one_child_regs(child, "SME VL", &iov_parent, &iov_child); + + iov_parent.iov_base = &svcr_out; + iov_parent.iov_len = sizeof(svcr_out); + iov_child.iov_base = &svcr_out; + iov_child.iov_len = sizeof(svcr_out); + read_one_child_regs(child, "SVCR", &iov_parent, &iov_child); + + iov_parent.iov_base = &za_out; + iov_parent.iov_len = sizeof(za_out); + iov_child.iov_base = &za_out; + iov_child.iov_len = sizeof(za_out); + read_one_child_regs(child, "ZA", &iov_parent, &iov_child); + } + + if (sme2_supported()) { + iov_parent.iov_base = &zt_out; + iov_parent.iov_len = sizeof(zt_out); + iov_child.iov_base = &zt_out; + iov_child.iov_len = sizeof(zt_out); + read_one_child_regs(child, "ZT", &iov_parent, &iov_child); + } +} + +static bool continue_breakpoint(pid_t child, + enum __ptrace_request restart_type) +{ + struct user_pt_regs pt_regs; + struct iovec iov; + int ret; + + /* Get PC */ + iov.iov_base = &pt_regs; + iov.iov_len = sizeof(pt_regs); + ret = ptrace(PTRACE_GETREGSET, child, NT_PRSTATUS, &iov); + if (ret < 0) { + ksft_print_msg("Failed to get PC: %s (%d)\n", + strerror(errno), errno); + return false; + } + + /* Skip over the BRK */ + pt_regs.pc += 4; + ret = ptrace(PTRACE_SETREGSET, child, NT_PRSTATUS, &iov); + if (ret < 0) { + ksft_print_msg("Failed to skip BRK: %s (%d)\n", + strerror(errno), errno); + return false; + } + + /* Restart */ + ret = ptrace(restart_type, child, 0, 0); + if (ret < 0) { + ksft_print_msg("Failed to restart child: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return true; +} + +static bool check_ptrace_values_sve(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sve_supported()) + return true; + + vq = __sve_vq_from_vl(config->sve_vl_in); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte SVE buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SVE, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial SVE: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + sve = iov.iov_base; + + if (sve->vl != config->sve_vl_in) { + ksft_print_msg("Mismatch in initial SVE VL: %d != %d\n", + sve->vl, config->sve_vl_in); + pass = false; + } + + /* If we are in streaming mode we should just read FPSIMD */ + if ((config->svcr_in & SVCR_SM) && (sve->flags & SVE_PT_REGS_SVE)) { + ksft_print_msg("NT_ARM_SVE reports SVE with PSTATE.SM\n"); + pass = false; + } + + if (sve->size != SVE_PT_SIZE(vq, sve->flags)) { + ksft_print_msg("Mismatch in SVE header size: %d != %lu\n", + sve->size, SVE_PT_SIZE(vq, sve->flags)); + pass = false; + } + + /* The registers might be in completely different formats! */ + if (sve->flags & SVE_PT_REGS_SVE) { + if (!compare_buffer("initial SVE Z", + iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_in, SVE_PT_SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SVE P", + iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_in, SVE_PT_SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SVE FFR", + iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_in, SVE_PT_SVE_PREG_SIZE(vq))) + pass = false; + } else { + fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET; + if (!compare_buffer("initial V via SVE", &fpsimd->vregs[0], + v_in, sizeof(v_in))) + pass = false; + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_ssve(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sme_supported()) + return true; + + vq = __sve_vq_from_vl(config->sme_vl_in); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte SSVE buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SSVE, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial SSVE: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + sve = iov.iov_base; + + if (sve->vl != config->sme_vl_in) { + ksft_print_msg("Mismatch in initial SSVE VL: %d != %d\n", + sve->vl, config->sme_vl_in); + pass = false; + } + + if ((config->svcr_in & SVCR_SM) && !(sve->flags & SVE_PT_REGS_SVE)) { + ksft_print_msg("NT_ARM_SSVE reports FPSIMD with PSTATE.SM\n"); + pass = false; + } + + if (sve->size != SVE_PT_SIZE(vq, sve->flags)) { + ksft_print_msg("Mismatch in SSVE header size: %d != %lu\n", + sve->size, SVE_PT_SIZE(vq, sve->flags)); + pass = false; + } + + /* The registers might be in completely different formats! */ + if (sve->flags & SVE_PT_REGS_SVE) { + if (!compare_buffer("initial SSVE Z", + iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_in, SVE_PT_SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SSVE P", + iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_in, SVE_PT_SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SSVE FFR", + iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_in, SVE_PT_SVE_PREG_SIZE(vq))) + pass = false; + } else { + fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET; + if (!compare_buffer("initial V via SSVE", + &fpsimd->vregs[0], v_in, sizeof(v_in))) + pass = false; + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_za(pid_t child, struct test_config *config) +{ + struct user_za_header *za; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sme_supported()) + return true; + + vq = __sve_vq_from_vl(config->sme_vl_in); + + iov.iov_len = ZA_SIG_CONTEXT_SIZE(vq); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte ZA buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZA, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial ZA: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + za = iov.iov_base; + + if (za->vl != config->sme_vl_in) { + ksft_print_msg("Mismatch in initial SME VL: %d != %d\n", + za->vl, config->sme_vl_in); + pass = false; + } + + /* If PSTATE.ZA is not set we should just read the header */ + if (config->svcr_in & SVCR_ZA) { + if (za->size != ZA_PT_SIZE(vq)) { + ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n", + za->size, ZA_PT_SIZE(vq)); + pass = false; + } + + if (!compare_buffer("initial ZA", + iov.iov_base + ZA_PT_ZA_OFFSET, + za_in, ZA_PT_ZA_SIZE(vq))) + pass = false; + } else { + if (za->size != sizeof(*za)) { + ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n", + za->size, sizeof(*za)); + pass = false; + } + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_zt(pid_t child, struct test_config *config) +{ + uint8_t buf[512]; + struct iovec iov; + int ret; + + if (!sme2_supported()) + return true; + + iov.iov_base = &buf; + iov.iov_len = ZT_SIG_REG_BYTES; + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZT, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial ZT: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return compare_buffer("initial ZT", buf, zt_in, ZT_SIG_REG_BYTES); +} + + +static bool check_ptrace_values(pid_t child, struct test_config *config) +{ + bool pass = true; + struct user_fpsimd_state fpsimd; + struct iovec iov; + int ret; + + iov.iov_base = &fpsimd; + iov.iov_len = sizeof(fpsimd); + ret = ptrace(PTRACE_GETREGSET, child, NT_PRFPREG, &iov); + if (ret == 0) { + if (!compare_buffer("initial V", &fpsimd.vregs, v_in, + sizeof(v_in))) { + pass = false; + } + } else { + ksft_print_msg("Failed to read initial V: %s (%d)\n", + strerror(errno), errno); + pass = false; + } + + if (!check_ptrace_values_sve(child, config)) + pass = false; + + if (!check_ptrace_values_ssve(child, config)) + pass = false; + + if (!check_ptrace_values_za(child, config)) + pass = false; + + if (!check_ptrace_values_zt(child, config)) + pass = false; + + return pass; +} + +static bool run_parent(pid_t child, struct test_definition *test, + struct test_config *config) +{ + int wait_status, ret; + pid_t pid; + bool pass; + + /* Initial attach */ + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + + if (WIFEXITED(wait_status)) { + ksft_print_msg("Child exited loading values with status %d\n", + WEXITSTATUS(wait_status)); + pass = false; + goto out; + } + + if (WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d loading values\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + /* Read initial values via ptrace */ + pass = check_ptrace_values(child, config); + + /* Do whatever writes we want to do */ + if (test->modify_values) + test->modify_values(child, config); + + if (!continue_breakpoint(child, PTRACE_CONT)) + goto cleanup; + + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + + if (WIFEXITED(wait_status)) { + ksft_print_msg("Child exited saving values with status %d\n", + WEXITSTATUS(wait_status)); + pass = false; + goto out; + } + + if (WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d saving values\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + /* See what happened as a result */ + read_child_regs(child); + + if (!continue_breakpoint(child, PTRACE_DETACH)) + goto cleanup; + + /* The child should exit cleanly */ + got_alarm = false; + alarm(1); + while (1) { + if (got_alarm) { + ksft_print_msg("Wait for child timed out\n"); + goto cleanup; + } + + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + alarm(0); + + if (got_alarm) { + ksft_print_msg("Timed out waiting for child\n"); + pass = false; + goto cleanup; + } + + if (pid == child && WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d cleaning up\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + if (pid == child && WIFEXITED(wait_status)) { + if (WEXITSTATUS(wait_status) != 0) { + ksft_print_msg("Child exited with error %d\n", + WEXITSTATUS(wait_status)); + pass = false; + } + } else { + ksft_print_msg("Child did not exit cleanly\n"); + pass = false; + goto cleanup; + } + + goto out; + +cleanup: + ret = kill(child, SIGKILL); + if (ret != 0) { + ksft_print_msg("kill() failed: %s (%d)\n", + strerror(errno), errno); + return false; + } + + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + +out: + return pass; +} + +static void fill_random(void *buf, size_t size) +{ + int i; + uint32_t *lbuf = buf; + + /* random() returns a 32 bit number regardless of the size of long */ + for (i = 0; i < size / sizeof(uint32_t); i++) + lbuf[i] = random(); +} + +static void fill_random_ffr(void *buf, size_t vq) +{ + uint8_t *lbuf = buf; + int bits, i; + + /* + * Only values with a continuous set of 0..n bits set are + * valid for FFR, set all bits then clear a random number of + * high bits. + */ + memset(buf, 0, __SVE_FFR_SIZE(vq)); + + bits = random() % (__SVE_FFR_SIZE(vq) * 8); + for (i = 0; i < bits / 8; i++) + lbuf[i] = 0xff; + if (bits / 8 != __SVE_FFR_SIZE(vq)) + lbuf[i] = (1 << (bits % 8)) - 1; +} + +static void fpsimd_to_sve(__uint128_t *v, char *z, int vl) +{ + int vq = __sve_vq_from_vl(vl); + int i; + __uint128_t *p; + + if (!vl) + return; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + p = (__uint128_t *)&z[__SVE_ZREG_OFFSET(vq, i)]; + *p = arm64_cpu_to_le128(v[i]); + } +} + +static void set_initial_values(struct test_config *config) +{ + int vq = __sve_vq_from_vl(vl_in(config)); + int sme_vq = __sve_vq_from_vl(config->sme_vl_in); + + svcr_in = config->svcr_in; + svcr_expected = config->svcr_expected; + svcr_out = 0; + + fill_random(&v_in, sizeof(v_in)); + memcpy(v_expected, v_in, sizeof(v_in)); + memset(v_out, 0, sizeof(v_out)); + + /* Changes will be handled in the test case */ + if (sve_supported() || (config->svcr_in & SVCR_SM)) { + /* The low 128 bits of Z are shared with the V registers */ + fill_random(&z_in, __SVE_ZREGS_SIZE(vq)); + fpsimd_to_sve(v_in, z_in, vl_in(config)); + memcpy(z_expected, z_in, __SVE_ZREGS_SIZE(vq)); + memset(z_out, 0, sizeof(z_out)); + + fill_random(&p_in, __SVE_PREGS_SIZE(vq)); + memcpy(p_expected, p_in, __SVE_PREGS_SIZE(vq)); + memset(p_out, 0, sizeof(p_out)); + + if ((config->svcr_in & SVCR_SM) && !fa64_supported()) + memset(ffr_in, 0, __SVE_PREG_SIZE(vq)); + else + fill_random_ffr(&ffr_in, vq); + memcpy(ffr_expected, ffr_in, __SVE_PREG_SIZE(vq)); + memset(ffr_out, 0, __SVE_PREG_SIZE(vq)); + } + + if (config->svcr_in & SVCR_ZA) + fill_random(za_in, ZA_SIG_REGS_SIZE(sme_vq)); + else + memset(za_in, 0, ZA_SIG_REGS_SIZE(sme_vq)); + if (config->svcr_expected & SVCR_ZA) + memcpy(za_expected, za_in, ZA_SIG_REGS_SIZE(sme_vq)); + else + memset(za_expected, 0, ZA_SIG_REGS_SIZE(sme_vq)); + if (sme_supported()) + memset(za_out, 0, sizeof(za_out)); + + if (sme2_supported()) { + if (config->svcr_in & SVCR_ZA) + fill_random(zt_in, ZT_SIG_REG_BYTES); + else + memset(zt_in, 0, ZT_SIG_REG_BYTES); + if (config->svcr_expected & SVCR_ZA) + memcpy(zt_expected, zt_in, ZT_SIG_REG_BYTES); + else + memset(zt_expected, 0, ZT_SIG_REG_BYTES); + memset(zt_out, 0, sizeof(zt_out)); + } +} + +static bool check_memory_values(struct test_config *config) +{ + bool pass = true; + int vq, sme_vq; + + if (!compare_buffer("saved V", v_out, v_expected, sizeof(v_out))) + pass = false; + + vq = __sve_vq_from_vl(vl_expected(config)); + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (svcr_out != svcr_expected) { + ksft_print_msg("Mismatch in saved SVCR %lx != %lx\n", + svcr_out, svcr_expected); + pass = false; + } + + if (sve_vl_out != config->sve_vl_expected) { + ksft_print_msg("Mismatch in SVE VL: %ld != %d\n", + sve_vl_out, config->sve_vl_expected); + pass = false; + } + + if (sme_vl_out != config->sme_vl_expected) { + ksft_print_msg("Mismatch in SME VL: %ld != %d\n", + sme_vl_out, config->sme_vl_expected); + pass = false; + } + + if (!compare_buffer("saved Z", z_out, z_expected, + __SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved P", p_out, p_expected, + __SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved FFR", ffr_out, ffr_expected, + __SVE_PREG_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved ZA", za_out, za_expected, + ZA_PT_ZA_SIZE(sme_vq))) + pass = false; + + if (!compare_buffer("saved ZT", zt_out, zt_expected, ZT_SIG_REG_BYTES)) + pass = false; + + return pass; +} + +static bool sve_sme_same(struct test_config *config) +{ + if (config->sve_vl_in != config->sve_vl_expected) + return false; + + if (config->sme_vl_in != config->sme_vl_expected) + return false; + + if (config->svcr_in != config->svcr_expected) + return false; + + return true; +} + +static bool sve_write_supported(struct test_config *config) +{ + if (!sve_supported() && !sme_supported()) + return false; + + if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA)) + return false; + + if (config->svcr_expected & SVCR_SM) { + if (config->sve_vl_in != config->sve_vl_expected) { + return false; + } + + /* Changing the SME VL disables ZA */ + if ((config->svcr_expected & SVCR_ZA) && + (config->sme_vl_in != config->sme_vl_expected)) { + return false; + } + } else { + if (config->sme_vl_in != config->sme_vl_expected) { + return false; + } + } + + return true; +} + +static void fpsimd_write_expected(struct test_config *config) +{ + int vl; + + fill_random(&v_expected, sizeof(v_expected)); + + /* The SVE registers are flushed by a FPSIMD write */ + vl = vl_expected(config); + + memset(z_expected, 0, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl))); + memset(p_expected, 0, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl))); + memset(ffr_expected, 0, __SVE_PREG_SIZE(__sve_vq_from_vl(vl))); + + fpsimd_to_sve(v_expected, z_expected, vl); +} + +static void fpsimd_write(pid_t child, struct test_config *test_config) +{ + struct user_fpsimd_state fpsimd; + struct iovec iov; + int ret; + + memset(&fpsimd, 0, sizeof(fpsimd)); + memcpy(&fpsimd.vregs, v_expected, sizeof(v_expected)); + + iov.iov_base = &fpsimd; + iov.iov_len = sizeof(fpsimd); + ret = ptrace(PTRACE_SETREGSET, child, NT_PRFPREG, &iov); + if (ret == -1) + ksft_print_msg("FPSIMD set failed: (%s) %d\n", + strerror(errno), errno); +} + +static void sve_write_expected(struct test_config *config) +{ + int vl = vl_expected(config); + int sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + fill_random(z_expected, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl))); + fill_random(p_expected, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl))); + + if ((svcr_expected & SVCR_SM) && !fa64_supported()) + memset(ffr_expected, 0, __SVE_PREG_SIZE(sme_vq)); + else + fill_random_ffr(ffr_expected, __sve_vq_from_vl(vl)); + + /* Share the low bits of Z with V */ + fill_random(&v_expected, sizeof(v_expected)); + fpsimd_to_sve(v_expected, z_expected, vl); + + if (config->sme_vl_in != config->sme_vl_expected) { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } +} + +static void sve_write(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct iovec iov; + int ret, vl, vq, regset; + + vl = vl_expected(config); + vq = __sve_vq_from_vl(vl); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", + iov.iov_len); + return; + } + memset(iov.iov_base, 0, iov.iov_len); + + sve = iov.iov_base; + sve->size = iov.iov_len; + sve->flags = SVE_PT_REGS_SVE; + sve->vl = vl; + + memcpy(iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_expected, SVE_PT_SVE_ZREGS_SIZE(vq)); + memcpy(iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_expected, SVE_PT_SVE_PREGS_SIZE(vq)); + memcpy(iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_expected, SVE_PT_SVE_PREG_SIZE(vq)); + + if (svcr_expected & SVCR_SM) + regset = NT_ARM_SSVE; + else + regset = NT_ARM_SVE; + + ret = ptrace(PTRACE_SETREGSET, child, regset, &iov); + if (ret != 0) + ksft_print_msg("Failed to write SVE: %s (%d)\n", + strerror(errno), errno); + + free(iov.iov_base); +} + +static bool za_write_supported(struct test_config *config) +{ + if (config->svcr_expected & SVCR_SM) { + if (!(config->svcr_in & SVCR_SM)) + return false; + + /* Changing the SME VL exits streaming mode */ + if (config->sme_vl_in != config->sme_vl_expected) { + return false; + } + } + + /* Can't disable SM outside a VL change */ + if ((config->svcr_in & SVCR_SM) && + !(config->svcr_expected & SVCR_SM)) + return false; + + return true; +} + +static void za_write_expected(struct test_config *config) +{ + int sme_vq, sve_vq; + + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) { + fill_random(za_expected, ZA_PT_ZA_SIZE(sme_vq)); + } else { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } + + /* Changing the SME VL flushes ZT, SVE state and exits SM */ + if (config->sme_vl_in != config->sme_vl_expected) { + svcr_expected &= ~SVCR_SM; + + sve_vq = __sve_vq_from_vl(vl_expected(config)); + memset(z_expected, 0, __SVE_ZREGS_SIZE(sve_vq)); + memset(p_expected, 0, __SVE_PREGS_SIZE(sve_vq)); + memset(ffr_expected, 0, __SVE_PREG_SIZE(sve_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + + fpsimd_to_sve(v_expected, z_expected, vl_expected(config)); + } +} + +static void za_write(pid_t child, struct test_config *config) +{ + struct user_za_header *za; + struct iovec iov; + int ret, vq; + + vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) + iov.iov_len = ZA_PT_SIZE(vq); + else + iov.iov_len = sizeof(*za); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("Failed allocating %lu byte ZA write buffer\n", + iov.iov_len); + return; + } + memset(iov.iov_base, 0, iov.iov_len); + + za = iov.iov_base; + za->size = iov.iov_len; + za->vl = config->sme_vl_expected; + if (config->svcr_expected & SVCR_ZA) + memcpy(iov.iov_base + ZA_PT_ZA_OFFSET, za_expected, + ZA_PT_ZA_SIZE(vq)); + + ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZA, &iov); + if (ret != 0) + ksft_print_msg("Failed to write ZA: %s (%d)\n", + strerror(errno), errno); + + free(iov.iov_base); +} + +static bool zt_write_supported(struct test_config *config) +{ + if (!sme2_supported()) + return false; + if (config->sme_vl_in != config->sme_vl_expected) + return false; + if (!(config->svcr_expected & SVCR_ZA)) + return false; + if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM)) + return false; + + return true; +} + +static void zt_write_expected(struct test_config *config) +{ + int sme_vq; + + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) { + fill_random(zt_expected, sizeof(zt_expected)); + } else { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } +} + +static void zt_write(pid_t child, struct test_config *config) +{ + struct iovec iov; + int ret; + + iov.iov_len = ZT_SIG_REG_BYTES; + iov.iov_base = zt_expected; + ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZT, &iov); + if (ret != 0) + ksft_print_msg("Failed to write ZT: %s (%d)\n", + strerror(errno), errno); +} + +/* Actually run a test */ +static void run_test(struct test_definition *test, struct test_config *config) +{ + pid_t child; + char name[1024]; + bool pass; + + if (sve_supported() && sme_supported()) + snprintf(name, sizeof(name), "%s, SVE %d->%d, SME %d/%x->%d/%x", + test->name, + config->sve_vl_in, config->sve_vl_expected, + config->sme_vl_in, config->svcr_in, + config->sme_vl_expected, config->svcr_expected); + else if (sve_supported()) + snprintf(name, sizeof(name), "%s, SVE %d->%d", test->name, + config->sve_vl_in, config->sve_vl_expected); + else if (sme_supported()) + snprintf(name, sizeof(name), "%s, SME %d/%x->%d/%x", + test->name, + config->sme_vl_in, config->svcr_in, + config->sme_vl_expected, config->svcr_expected); + else + snprintf(name, sizeof(name), "%s", test->name); + + if (test->supported && !test->supported(config)) { + ksft_test_result_skip("%s\n", name); + return; + } + + set_initial_values(config); + + if (test->set_expected_values) + test->set_expected_values(config); + + child = fork(); + if (child < 0) + ksft_exit_fail_msg("fork() failed: %s (%d)\n", + strerror(errno), errno); + /* run_child() never returns */ + if (child == 0) + run_child(config); + + pass = run_parent(child, test, config); + if (!check_memory_values(config)) + pass = false; + + ksft_test_result(pass, "%s\n", name); +} + +static void run_tests(struct test_definition defs[], int count, + struct test_config *config) +{ + int i; + + for (i = 0; i < count; i++) + run_test(&defs[i], config); +} + +static struct test_definition base_test_defs[] = { + { + .name = "No writes", + .supported = sve_sme_same, + }, + { + .name = "FPSIMD write", + .supported = sve_sme_same, + .set_expected_values = fpsimd_write_expected, + .modify_values = fpsimd_write, + }, +}; + +static struct test_definition sve_test_defs[] = { + { + .name = "SVE write", + .supported = sve_write_supported, + .set_expected_values = sve_write_expected, + .modify_values = sve_write, + }, +}; + +static struct test_definition za_test_defs[] = { + { + .name = "ZA write", + .supported = za_write_supported, + .set_expected_values = za_write_expected, + .modify_values = za_write, + }, +}; + +static struct test_definition zt_test_defs[] = { + { + .name = "ZT write", + .supported = zt_write_supported, + .set_expected_values = zt_write_expected, + .modify_values = zt_write, + }, +}; + +static int sve_vls[MAX_NUM_VLS], sme_vls[MAX_NUM_VLS]; +static int sve_vl_count, sme_vl_count; + +static void probe_vls(const char *name, int vls[], int *vl_count, int set_vl) +{ + unsigned int vq; + int vl; + + *vl_count = 0; + + for (vq = ARCH_VQ_MAX; vq > 0; vq /= 2) { + vl = prctl(set_vl, vq * 16); + if (vl == -1) + ksft_exit_fail_msg("SET_VL failed: %s (%d)\n", + strerror(errno), errno); + + vl &= PR_SVE_VL_LEN_MASK; + + if (*vl_count && (vl == vls[*vl_count - 1])) + break; + + vq = sve_vq_from_vl(vl); + + vls[*vl_count] = vl; + *vl_count += 1; + } + + if (*vl_count > 2) { + /* Just use the minimum and maximum */ + vls[1] = vls[*vl_count - 1]; + ksft_print_msg("%d %s VLs, using %d and %d\n", + *vl_count, name, vls[0], vls[1]); + *vl_count = 2; + } else { + ksft_print_msg("%d %s VLs\n", *vl_count, name); + } +} + +static struct { + int svcr_in, svcr_expected; +} svcr_combinations[] = { + { .svcr_in = 0, .svcr_expected = 0, }, + { .svcr_in = 0, .svcr_expected = SVCR_SM, }, + { .svcr_in = 0, .svcr_expected = SVCR_ZA, }, + /* Can't enable both SM and ZA with a single ptrace write */ + + { .svcr_in = SVCR_SM, .svcr_expected = 0, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM | SVCR_ZA, }, + + { .svcr_in = SVCR_ZA, .svcr_expected = 0, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, }, + + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = 0, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, }, +}; + +static void run_sve_tests(void) +{ + struct test_config test_config; + int i, j; + + if (!sve_supported()) + return; + + test_config.sme_vl_in = sme_vls[0]; + test_config.sme_vl_expected = sme_vls[0]; + test_config.svcr_in = 0; + test_config.svcr_expected = 0; + + for (i = 0; i < sve_vl_count; i++) { + test_config.sve_vl_in = sve_vls[i]; + + for (j = 0; j < sve_vl_count; j++) { + test_config.sve_vl_expected = sve_vls[j]; + + run_tests(base_test_defs, + ARRAY_SIZE(base_test_defs), + &test_config); + if (sve_supported()) + run_tests(sve_test_defs, + ARRAY_SIZE(sve_test_defs), + &test_config); + } + } + +} + +static void run_sme_tests(void) +{ + struct test_config test_config; + int i, j, k; + + if (!sme_supported()) + return; + + test_config.sve_vl_in = sve_vls[0]; + test_config.sve_vl_expected = sve_vls[0]; + + /* + * Every SME VL/SVCR combination + */ + for (i = 0; i < sme_vl_count; i++) { + test_config.sme_vl_in = sme_vls[i]; + + for (j = 0; j < sme_vl_count; j++) { + test_config.sme_vl_expected = sme_vls[j]; + + for (k = 0; k < ARRAY_SIZE(svcr_combinations); k++) { + test_config.svcr_in = svcr_combinations[k].svcr_in; + test_config.svcr_expected = svcr_combinations[k].svcr_expected; + + run_tests(base_test_defs, + ARRAY_SIZE(base_test_defs), + &test_config); + run_tests(sve_test_defs, + ARRAY_SIZE(sve_test_defs), + &test_config); + run_tests(za_test_defs, + ARRAY_SIZE(za_test_defs), + &test_config); + + if (sme2_supported()) + run_tests(zt_test_defs, + ARRAY_SIZE(zt_test_defs), + &test_config); + } + } + } +} + +int main(void) +{ + struct test_config test_config; + struct sigaction sa; + int tests, ret, tmp; + + srandom(getpid()); + + ksft_print_header(); + + if (sve_supported()) { + probe_vls("SVE", sve_vls, &sve_vl_count, PR_SVE_SET_VL); + + tests = ARRAY_SIZE(base_test_defs) + + ARRAY_SIZE(sve_test_defs); + tests *= sve_vl_count * sve_vl_count; + } else { + /* Only run the FPSIMD tests */ + sve_vl_count = 1; + tests = ARRAY_SIZE(base_test_defs); + } + + if (sme_supported()) { + probe_vls("SME", sme_vls, &sme_vl_count, PR_SME_SET_VL); + + tmp = ARRAY_SIZE(base_test_defs) + ARRAY_SIZE(sve_test_defs) + + ARRAY_SIZE(za_test_defs); + + if (sme2_supported()) + tmp += ARRAY_SIZE(zt_test_defs); + + tmp *= sme_vl_count * sme_vl_count; + tmp *= ARRAY_SIZE(svcr_combinations); + tests += tmp; + } else { + sme_vl_count = 1; + } + + if (sme2_supported()) + ksft_print_msg("SME2 supported\n"); + + if (fa64_supported()) + ksft_print_msg("FA64 supported\n"); + + ksft_set_plan(tests); + + /* Get signal handers ready before we start any children */ + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handle_alarm; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGALRM, &sa, NULL); + if (ret < 0) + ksft_print_msg("Failed to install SIGALRM handler: %s (%d)\n", + strerror(errno), errno); + + /* + * Run the test set if there is no SVE or SME, with those we + * have to pick a VL for each run. + */ + if (!sve_supported()) { + test_config.sve_vl_in = 0; + test_config.sve_vl_expected = 0; + test_config.sme_vl_in = 0; + test_config.sme_vl_expected = 0; + test_config.svcr_in = 0; + test_config.svcr_expected = 0; + + run_tests(base_test_defs, ARRAY_SIZE(base_test_defs), + &test_config); + } + + run_sve_tests(); + run_sme_tests(); + + ksft_finished(); +} diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.h b/tools/testing/selftests/arm64/fp/fp-ptrace.h new file mode 100644 index 000000000000..db4f2c4d750c --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-3 ARM Limited. + +#ifndef FP_PTRACE_H +#define FP_PTRACE_H + +#define SVCR_SM_SHIFT 0 +#define SVCR_ZA_SHIFT 1 + +#define SVCR_SM (1 << SVCR_SM_SHIFT) +#define SVCR_ZA (1 << SVCR_ZA_SHIFT) + +#endif diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 839e3a252629..1ce5b5eac386 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +fpmr_* sme_* ssve_* sve_* diff --git a/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c new file mode 100644 index 000000000000..e9d24685e741 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + * + * Verify that the FPMR register context in signal frames is set up as + * expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/sigcontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static union { + ucontext_t uc; + char buf[1024 * 128]; +} context; + +#define SYS_FPMR "S3_3_C4_C4_2" + +static uint64_t get_fpmr(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_FPMR "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +int fpmr_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context); + struct fpmr_context *fpmr_ctx; + size_t offset; + bool in_sigframe; + bool have_fpmr; + __u64 orig_fpmr; + + have_fpmr = getauxval(AT_HWCAP2) & HWCAP2_FPMR; + if (have_fpmr) + orig_fpmr = get_fpmr(); + + if (!get_current_context(td, &context.uc, sizeof(context))) + return 1; + + fpmr_ctx = (struct fpmr_context *) + get_header(head, FPMR_MAGIC, td->live_sz, &offset); + + in_sigframe = fpmr_ctx != NULL; + + fprintf(stderr, "FPMR sigframe %s on system %s FPMR\n", + in_sigframe ? "present" : "absent", + have_fpmr ? "with" : "without"); + + td->pass = (in_sigframe == have_fpmr); + + if (have_fpmr && fpmr_ctx) { + if (fpmr_ctx->fpmr != orig_fpmr) { + fprintf(stderr, "FPMR in frame is %llx, was %llx\n", + fpmr_ctx->fpmr, orig_fpmr); + td->pass = false; + } + } + + return 0; +} + +struct tdescr tde = { + .name = "FPMR", + .descr = "Validate that FPMR is present as expected", + .timeout = 3, + .run = fpmr_present, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 9f580b55b388..674b88cc8c39 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -209,6 +209,14 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) zt = (struct zt_context *)head; new_flags |= ZT_CTX; break; + case FPMR_MAGIC: + if (flags & FPMR_CTX) + *err = "Multiple FPMR_MAGIC"; + else if (head->size != + sizeof(struct fpmr_context)) + *err = "Bad size for fpmr_context"; + new_flags |= FPMR_CTX; + break; case EXTRA_MAGIC: if (flags & EXTRA_CTX) *err = "Multiple EXTRA_MAGIC"; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h index a08ab0d6207a..7727126347e0 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.h +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -19,6 +19,7 @@ #define ZA_CTX (1 << 2) #define EXTRA_CTX (1 << 3) #define ZT_CTX (1 << 4) +#define FPMR_CTX (1 << 5) #define KSFT_BAD_MAGIC 0xdeadbeef |