diff options
Diffstat (limited to 'arch/arm64')
136 files changed, 4328 insertions, 1828 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index ea2ab0330e3a..a4168d366127 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -5,7 +5,7 @@ config ARM64 select ACPI_GTDT if ACPI select ACPI_IORT if ACPI select ACPI_REDUCED_HARDWARE_ONLY if ACPI - select ACPI_MCFG if ACPI + select ACPI_MCFG if (ACPI && PCI) select ACPI_SPCR_TABLE if ACPI select ACPI_PPTT if ACPI select ARCH_CLOCKSOURCE_DATA @@ -23,7 +23,6 @@ config ARM64 select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SET_MEMORY - select ARCH_HAS_SG_CHAIN select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_DMA_FOR_DEVICE @@ -81,7 +80,7 @@ config ARM64 select CPU_PM if (SUSPEND || CPU_IDLE) select CRC32 select DCACHE_WORD_ACCESS - select DMA_DIRECT_OPS + select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER select GENERIC_ALLOCATOR @@ -103,6 +102,7 @@ config ARM64 select GENERIC_TIME_VSYSCALL select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND + select HAVE_PCI select HAVE_ACPI_APEI if (ACPI && EFI) select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL @@ -111,6 +111,7 @@ config ARM64 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_SW_TAGS if HAVE_ARCH_KASAN select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT @@ -163,7 +164,9 @@ config ARM64 select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM - select PCI_ECAM if ACPI + select PCI_DOMAINS_GENERIC if PCI + select PCI_ECAM if (ACPI && PCI) + select PCI_SYSCALL if PCI select POWER_RESET select POWER_SUPPLY select REFCOUNT_FULL @@ -261,6 +264,9 @@ config ZONE_DMA32 config HAVE_GENERIC_GUP def_bool y +config ARCH_ENABLE_MEMORY_HOTPLUG + def_bool y + config SMP def_bool y @@ -274,7 +280,7 @@ config PGTABLE_LEVELS int default 2 if ARM64_16K_PAGES && ARM64_VA_BITS_36 default 2 if ARM64_64K_PAGES && ARM64_VA_BITS_42 - default 3 if ARM64_64K_PAGES && ARM64_VA_BITS_48 + default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_USER_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_64K_PAGES && ARM64_VA_BITS_48 @@ -287,35 +293,17 @@ config ARCH_PROC_KCORE_TEXT source "arch/arm64/Kconfig.platforms" -menu "Bus support" - -config PCI - bool "PCI support" - help - This feature enables support for PCI bus system. If you say Y - here, the kernel will include drivers and infrastructure code - to support PCI bus devices. - -config PCI_DOMAINS - def_bool PCI - -config PCI_DOMAINS_GENERIC - def_bool PCI - -config PCI_SYSCALL - def_bool PCI - -source "drivers/pci/Kconfig" - -endmenu - menu "Kernel Features" menu "ARM errata workarounds via the alternatives framework" +config ARM64_WORKAROUND_CLEAN_CACHE + def_bool n + config ARM64_ERRATUM_826319 bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted" default y + select ARM64_WORKAROUND_CLEAN_CACHE help This option adds an alternative code sequence to work around ARM erratum 826319 on Cortex-A53 parts up to r0p2 with an AMBA 4 ACE or @@ -337,6 +325,7 @@ config ARM64_ERRATUM_826319 config ARM64_ERRATUM_827319 bool "Cortex-A53: 827319: Data cache clean instructions might cause overlapping transactions to the interconnect" default y + select ARM64_WORKAROUND_CLEAN_CACHE help This option adds an alternative code sequence to work around ARM erratum 827319 on Cortex-A53 parts up to r0p2 with an AMBA 5 CHI @@ -358,6 +347,7 @@ config ARM64_ERRATUM_827319 config ARM64_ERRATUM_824069 bool "Cortex-A53: 824069: Cache line might not be marked as clean after a CleanShared snoop" default y + select ARM64_WORKAROUND_CLEAN_CACHE help This option adds an alternative code sequence to work around ARM erratum 824069 on Cortex-A53 parts up to r0p2 when it is connected @@ -380,6 +370,7 @@ config ARM64_ERRATUM_824069 config ARM64_ERRATUM_819472 bool "Cortex-A53: 819472: Store exclusive instructions might cause data corruption" default y + select ARM64_WORKAROUND_CLEAN_CACHE help This option adds an alternative code sequence to work around ARM erratum 819472 on Cortex-A53 parts up to r0p1 with an L2 cache @@ -497,6 +488,18 @@ config ARM64_ERRATUM_1188873 If unsure, say Y. +config ARM64_ERRATUM_1165522 + bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation" + default y + help + This option adds work arounds for ARM Cortex-A76 erratum 1165522 + + Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could end-up with + corrupted TLBs by speculating an AT instruction during a guest + context switch. + + If unsure, say Y. + 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 @@ -700,15 +703,43 @@ config ARM64_VA_BITS_47 config ARM64_VA_BITS_48 bool "48-bit" +config ARM64_USER_VA_BITS_52 + bool "52-bit (user)" + depends on ARM64_64K_PAGES && (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 continue to + use 48-bit virtual addresses for its own mappings. + + NOTE: Enabling 52-bit virtual addressing in conjunction with + ARMv8.3 Pointer Authentication will result in the PAC being + reduced from 7 bits to 3 bits, which may have a significant + impact on its susceptibility to brute-force attacks. + + If unsure, select 48-bit virtual addressing instead. + endchoice +config ARM64_FORCE_52BIT + bool "Force 52-bit virtual addresses for userspace" + depends on ARM64_USER_VA_BITS_52 && EXPERT + help + For systems with 52-bit userspace VAs enabled, the kernel will attempt + to maintain compatibility with older software by providing 48-bit VAs + unless a hint is supplied to mmap. + + This configuration option disables the 48-bit compatibility logic, and + forces all userspace addresses to be 52-bit on HW that supports it. One + should only enable this configuration option for stress testing userspace + memory management code. If unsure say N here. + config ARM64_VA_BITS int default 36 if ARM64_VA_BITS_36 default 39 if ARM64_VA_BITS_39 default 42 if ARM64_VA_BITS_42 default 47 if ARM64_VA_BITS_47 - default 48 if ARM64_VA_BITS_48 + default 48 if ARM64_VA_BITS_48 || ARM64_USER_VA_BITS_52 choice prompt "Physical address space size" @@ -807,7 +838,7 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK config HOLES_IN_ZONE def_bool y -source kernel/Kconfig.hz +source "kernel/Kconfig.hz" config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y @@ -883,6 +914,39 @@ config KEXEC but it is independent of the system firmware. And like a reboot you can start any kernel with it, not just Linux. +config KEXEC_FILE + bool "kexec file based system call" + select KEXEC_CORE + help + This is new version of kexec system call. This system call is + file based and takes file descriptors as system call argument + for kernel and initramfs as opposed to list of segments as + accepted by previous system call. + +config KEXEC_VERIFY_SIG + bool "Verify kernel signature during kexec_file_load() syscall" + depends on KEXEC_FILE + help + Select this option to verify a signature with loaded kernel + image. If configured, any attempt of loading a image without + valid signature will fail. + + In addition to that option, you need to enable signature + verification for the corresponding kernel image type being + loaded in order for this to work. + +config KEXEC_IMAGE_VERIFY_SIG + bool "Enable Image signature verification support" + default y + depends on KEXEC_VERIFY_SIG + depends on EFI && SIGNED_PE_FILE_VERIFICATION + help + Enable Image signature verification support. + +comment "Support for PE file signature verification disabled" + depends on KEXEC_VERIFY_SIG + depends on !EFI || !SIGNED_PE_FILE_VERIFICATION + config CRASH_DUMP bool "Build kdump crash kernel" help @@ -983,6 +1047,20 @@ config ARM64_SSBD If unsure, say Y. +config RODATA_FULL_DEFAULT_ENABLED + bool "Apply r/o permissions of VM areas also to their linear aliases" + default y + help + Apply read-only attributes of VM areas to the linear alias of + the backing pages as well. This prevents code or read-only data + from being modified (inadvertently or intentionally) via another + mapping of the same memory page. This additional enhancement can + be turned off at runtime by passing rodata=[off|on] (and turned on + with rodata=full if this option is set to 'n') + + This requires the linear region to be mapped down to pages, + which may adversely affect performance in some cases. + menuconfig ARMV8_DEPRECATED bool "Emulate deprecated/obsolete ARMv8 instructions" depends on COMPAT @@ -1188,6 +1266,29 @@ config ARM64_CNP endmenu +menu "ARMv8.3 architectural features" + +config ARM64_PTR_AUTH + bool "Enable support for pointer authentication" + default y + help + Pointer authentication (part of the ARMv8.3 Extensions) provides + instructions for signing and authenticating pointers against secret + keys, which can be used to mitigate Return Oriented Programming (ROP) + and other attacks. + + This option enables these instructions at EL0 (i.e. for userspace). + + Choosing this option will cause the kernel to initialise secret keys + for each process at exec() time, with these keys being + context-switched along with the process. + + The feature is detected at runtime. If the feature is not present in + hardware it will not be advertised to userspace nor will it be + enabled. + +endmenu + config ARM64_SVE bool "ARM Scalable Vector Extension support" default y @@ -1272,6 +1373,13 @@ config RANDOMIZE_MODULE_REGION_FULL a limited range that contains the [_stext, _etext] interval of the core kernel, so branch relocations are always in range. +config CC_HAVE_STACKPROTECTOR_SYSREG + def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0) + +config STACKPROTECTOR_PER_TASK + def_bool y + depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_SYSREG + endmenu menu "Boot options" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 6cb9fc7e9382..b025304bde46 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -18,7 +18,7 @@ ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour # for relative relocs, since this leads to better Image compression # with the relocation offsets always being zero. -LDFLAGS_vmlinux += -pie -shared -Bsymbolic \ +LDFLAGS_vmlinux += -shared -Bsymbolic -z notext -z norelro \ $(call ld-option, --no-apply-dynamic-relocs) endif @@ -56,6 +56,16 @@ KBUILD_AFLAGS += $(lseinstr) $(brokengasinst) KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) +ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) +prepare: stack_protector_prepare +stack_protector_prepare: prepare0 + $(eval KBUILD_CFLAGS += -mstack-protector-guard=sysreg \ + -mstack-protector-guard-reg=sp_el0 \ + -mstack-protector-guard-offset=$(shell \ + awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \ + include/generated/asm-offsets.h)) +endif + ifeq ($(CONFIG_CPU_BIG_ENDIAN), y) KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ @@ -91,10 +101,19 @@ else TEXT_OFFSET := 0x00080000 endif +ifeq ($(CONFIG_KASAN_SW_TAGS), y) +KASAN_SHADOW_SCALE_SHIFT := 4 +else +KASAN_SHADOW_SCALE_SHIFT := 3 +endif + +KBUILD_CFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) +KBUILD_CPPFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) +KBUILD_AFLAGS += -DKASAN_SHADOW_SCALE_SHIFT=$(KASAN_SHADOW_SCALE_SHIFT) + # KASAN_SHADOW_OFFSET = VA_START + (1 << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) # - (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) # in 32-bit arithmetic -KASAN_SHADOW_SCALE_SHIFT := 3 KASAN_SHADOW_OFFSET := $(shell printf "0x%08x00000000\n" $$(( \ (0xffffffff & (-1 << ($(CONFIG_ARM64_VA_BITS) - 32))) \ + (1 << ($(CONFIG_ARM64_VA_BITS) - 32 - $(KASAN_SHADOW_SCALE_SHIFT))) \ diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index fef7351e9f67..a20df0d9c96d 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -24,6 +24,19 @@ #address-cells = <2>; #size-cells = <2>; + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + service_reserved: svcbuffer@0 { + compatible = "shared-dma-pool"; + reg = <0x0 0x0 0x0 0x1000000>; + alignment = <0x1000>; + no-map; + }; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -93,6 +106,14 @@ interrupt-parent = <&intc>; ranges = <0 0 0 0xffffffff>; + base_fpga_region { + #address-cells = <0x1>; + #size-cells = <0x1>; + + compatible = "fpga-region"; + fpga-mgr = <&fpga_mgr>; + }; + clkmgr: clock-controller@ffd10000 { compatible = "intel,stratix10-clkmgr"; reg = <0xffd10000 0x1000>; @@ -537,5 +558,17 @@ status = "disabled"; }; + + firmware { + svc { + compatible = "intel,stratix10-svc"; + method = "smc"; + memory-region = <&service_reserved>; + + fpga_mgr: fpga-mgr { + compatible = "intel,stratix10-soc-fpga-mgr"; + }; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts index d667eee4e6d0..b3def0358177 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts @@ -343,6 +343,12 @@ }; }; +&gcc { + protected-clocks = <GCC_QSPI_CORE_CLK>, + <GCC_QSPI_CORE_CLK_SRC>, + <GCC_QSPI_CNOC_PERIPH_AHB_CLK>; +}; + &i2c10 { status = "okay"; clock-frequency = <400000>; diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig index a5606823ed4d..d9a523ecdd83 100644 --- a/arch/arm64/crypto/Kconfig +++ b/arch/arm64/crypto/Kconfig @@ -101,11 +101,16 @@ config CRYPTO_AES_ARM64_NEON_BLK select CRYPTO_SIMD config CRYPTO_CHACHA20_NEON - tristate "NEON accelerated ChaCha20 symmetric cipher" + tristate "ChaCha20, XChaCha20, and XChaCha12 stream ciphers using NEON instructions" depends on KERNEL_MODE_NEON select CRYPTO_BLKCIPHER select CRYPTO_CHACHA20 +config CRYPTO_NHPOLY1305_NEON + tristate "NHPoly1305 hash function using NEON instructions (for Adiantum)" + depends on KERNEL_MODE_NEON + select CRYPTO_NHPOLY1305 + config CRYPTO_AES_ARM64_BS tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm" depends on KERNEL_MODE_NEON diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile index f476fede09ba..e766daf43b7c 100644 --- a/arch/arm64/crypto/Makefile +++ b/arch/arm64/crypto/Makefile @@ -50,8 +50,11 @@ sha256-arm64-y := sha256-glue.o sha256-core.o obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o sha512-arm64-y := sha512-glue.o sha512-core.o -obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o -chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o +obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o +chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o + +obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o +nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o @@ -75,4 +78,4 @@ $(src)/sha512-core.S_shipped: $(src)/sha512-armv8.pl $(call cmd,perlasm) endif -targets += sha256-core.S sha512-core.S +clean-files += sha256-core.S sha512-core.S diff --git a/arch/arm64/crypto/chacha20-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S index 13c85e272c2a..021bb9e9784b 100644 --- a/arch/arm64/crypto/chacha20-neon-core.S +++ b/arch/arm64/crypto/chacha-neon-core.S @@ -1,13 +1,13 @@ /* - * ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions + * ChaCha/XChaCha NEON helper functions * - * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org> + * Copyright (C) 2016-2018 Linaro, Ltd. <ard.biesheuvel@linaro.org> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * - * Based on: + * Originally based on: * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions * * Copyright (C) 2015 Martin Willi @@ -19,29 +19,27 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/cache.h> .text .align 6 -ENTRY(chacha20_block_xor_neon) - // x0: Input state matrix, s - // x1: 1 data block output, o - // x2: 1 data block input, i - - // - // This function encrypts one ChaCha20 block by loading the state matrix - // in four NEON registers. It performs matrix operation on four words in - // parallel, but requires shuffling to rearrange the words after each - // round. - // - - // x0..3 = s0..3 - adr x3, ROT8 - ld1 {v0.4s-v3.4s}, [x0] - ld1 {v8.4s-v11.4s}, [x0] - ld1 {v12.4s}, [x3] +/* + * chacha_permute - permute one block + * + * Permute one 64-byte block where the state matrix is stored in the four NEON + * registers v0-v3. It performs matrix operations on four words in parallel, + * but requires shuffling to rearrange the words after each round. + * + * The round count is given in w3. + * + * Clobbers: w3, x10, v4, v12 + */ +chacha_permute: - mov x3, #10 + adr_l x10, ROT8 + ld1 {v12.4s}, [x10] .Ldoubleround: // x0 += x1, x3 = rotl32(x3 ^ x0, 16) @@ -102,9 +100,27 @@ ENTRY(chacha20_block_xor_neon) // x3 = shuffle32(x3, MASK(0, 3, 2, 1)) ext v3.16b, v3.16b, v3.16b, #4 - subs x3, x3, #1 + subs w3, w3, #2 b.ne .Ldoubleround + ret +ENDPROC(chacha_permute) + +ENTRY(chacha_block_xor_neon) + // x0: Input state matrix, s + // x1: 1 data block output, o + // x2: 1 data block input, i + // w3: nrounds + + stp x29, x30, [sp, #-16]! + mov x29, sp + + // x0..3 = s0..3 + ld1 {v0.4s-v3.4s}, [x0] + ld1 {v8.4s-v11.4s}, [x0] + + bl chacha_permute + ld1 {v4.16b-v7.16b}, [x2] // o0 = i0 ^ (x0 + s0) @@ -125,71 +141,156 @@ ENTRY(chacha20_block_xor_neon) st1 {v0.16b-v3.16b}, [x1] + ldp x29, x30, [sp], #16 ret -ENDPROC(chacha20_block_xor_neon) +ENDPROC(chacha_block_xor_neon) + +ENTRY(hchacha_block_neon) + // x0: Input state matrix, s + // x1: output (8 32-bit words) + // w2: nrounds + + stp x29, x30, [sp, #-16]! + mov x29, sp + + ld1 {v0.4s-v3.4s}, [x0] + + mov w3, w2 + bl chacha_permute + + st1 {v0.16b}, [x1], #16 + st1 {v3.16b}, [x1] + + ldp x29, x30, [sp], #16 + ret +ENDPROC(hchacha_block_neon) + + a0 .req w12 + a1 .req w13 + a2 .req w14 + a3 .req w15 + a4 .req w16 + a5 .req w17 + a6 .req w19 + a7 .req w20 + a8 .req w21 + a9 .req w22 + a10 .req w23 + a11 .req w24 + a12 .req w25 + a13 .req w26 + a14 .req w27 + a15 .req w28 .align 6 -ENTRY(chacha20_4block_xor_neon) +ENTRY(chacha_4block_xor_neon) + frame_push 10 + // x0: Input state matrix, s // x1: 4 data blocks output, o // x2: 4 data blocks input, i + // w3: nrounds + // x4: byte count + + adr_l x10, .Lpermute + and x5, x4, #63 + add x10, x10, x5 + add x11, x10, #64 // - // This function encrypts four consecutive ChaCha20 blocks by loading + // This function encrypts four consecutive ChaCha blocks by loading // the state matrix in NEON registers four times. The algorithm performs // each operation on the corresponding word of each state matrix, hence // requires no word shuffling. For final XORing step we transpose the // matrix by interleaving 32- and then 64-bit words, which allows us to // do XOR in NEON registers. // - adr x3, CTRINC // ... and ROT8 - ld1 {v30.4s-v31.4s}, [x3] + // At the same time, a fifth block is encrypted in parallel using + // scalar registers + // + adr_l x9, CTRINC // ... and ROT8 + ld1 {v30.4s-v31.4s}, [x9] // x0..15[0-3] = s0..3[0..3] - mov x4, x0 - ld4r { v0.4s- v3.4s}, [x4], #16 - ld4r { v4.4s- v7.4s}, [x4], #16 - ld4r { v8.4s-v11.4s}, [x4], #16 - ld4r {v12.4s-v15.4s}, [x4] - - // x12 += counter values 0-3 + add x8, x0, #16 + ld4r { v0.4s- v3.4s}, [x0] + ld4r { v4.4s- v7.4s}, [x8], #16 + ld4r { v8.4s-v11.4s}, [x8], #16 + ld4r {v12.4s-v15.4s}, [x8] + + mov a0, v0.s[0] + mov a1, v1.s[0] + mov a2, v2.s[0] + mov a3, v3.s[0] + mov a4, v4.s[0] + mov a5, v5.s[0] + mov a6, v6.s[0] + mov a7, v7.s[0] + mov a8, v8.s[0] + mov a9, v9.s[0] + mov a10, v10.s[0] + mov a11, v11.s[0] + mov a12, v12.s[0] + mov a13, v13.s[0] + mov a14, v14.s[0] + mov a15, v15.s[0] + + // x12 += counter values 1-4 add v12.4s, v12.4s, v30.4s - mov x3, #10 - .Ldoubleround4: // x0 += x4, x12 = rotl32(x12 ^ x0, 16) // x1 += x5, x13 = rotl32(x13 ^ x1, 16) // x2 += x6, x14 = rotl32(x14 ^ x2, 16) // x3 += x7, x15 = rotl32(x15 ^ x3, 16) add v0.4s, v0.4s, v4.4s + add a0, a0, a4 add v1.4s, v1.4s, v5.4s + add a1, a1, a5 add v2.4s, v2.4s, v6.4s + add a2, a2, a6 add v3.4s, v3.4s, v7.4s + add a3, a3, a7 eor v12.16b, v12.16b, v0.16b + eor a12, a12, a0 eor v13.16b, v13.16b, v1.16b + eor a13, a13, a1 eor v14.16b, v14.16b, v2.16b + eor a14, a14, a2 eor v15.16b, v15.16b, v3.16b + eor a15, a15, a3 rev32 v12.8h, v12.8h + ror a12, a12, #16 rev32 v13.8h, v13.8h + ror a13, a13, #16 rev32 v14.8h, v14.8h + ror a14, a14, #16 rev32 v15.8h, v15.8h + ror a15, a15, #16 // x8 += x12, x4 = rotl32(x4 ^ x8, 12) // x9 += x13, x5 = rotl32(x5 ^ x9, 12) // x10 += x14, x6 = rotl32(x6 ^ x10, 12) // x11 += x15, x7 = rotl32(x7 ^ x11, 12) add v8.4s, v8.4s, v12.4s + add a8, a8, a12 add v9.4s, v9.4s, v13.4s + add a9, a9, a13 add v10.4s, v10.4s, v14.4s + add a10, a10, a14 add v11.4s, v11.4s, v15.4s + add a11, a11, a15 eor v16.16b, v4.16b, v8.16b + eor a4, a4, a8 eor v17.16b, v5.16b, v9.16b + eor a5, a5, a9 eor v18.16b, v6.16b, v10.16b + eor a6, a6, a10 eor v19.16b, v7.16b, v11.16b + eor a7, a7, a11 shl v4.4s, v16.4s, #12 shl v5.4s, v17.4s, #12 @@ -197,42 +298,66 @@ ENTRY(chacha20_4block_xor_neon) shl v7.4s, v19.4s, #12 sri v4.4s, v16.4s, #20 + ror a4, a4, #20 sri v5.4s, v17.4s, #20 + ror a5, a5, #20 sri v6.4s, v18.4s, #20 + ror a6, a6, #20 sri v7.4s, v19.4s, #20 + ror a7, a7, #20 // x0 += x4, x12 = rotl32(x12 ^ x0, 8) // x1 += x5, x13 = rotl32(x13 ^ x1, 8) // x2 += x6, x14 = rotl32(x14 ^ x2, 8) // x3 += x7, x15 = rotl32(x15 ^ x3, 8) add v0.4s, v0.4s, v4.4s + add a0, a0, a4 add v1.4s, v1.4s, v5.4s + add a1, a1, a5 add v2.4s, v2.4s, v6.4s + add a2, a2, a6 add v3.4s, v3.4s, v7.4s + add a3, a3, a7 eor v12.16b, v12.16b, v0.16b + eor a12, a12, a0 eor v13.16b, v13.16b, v1.16b + eor a13, a13, a1 eor v14.16b, v14.16b, v2.16b + eor a14, a14, a2 eor v15.16b, v15.16b, v3.16b + eor a15, a15, a3 tbl v12.16b, {v12.16b}, v31.16b + ror a12, a12, #24 tbl v13.16b, {v13.16b}, v31.16b + ror a13, a13, #24 tbl v14.16b, {v14.16b}, v31.16b + ror a14, a14, #24 tbl v15.16b, {v15.16b}, v31.16b + ror a15, a15, #24 // x8 += x12, x4 = rotl32(x4 ^ x8, 7) // x9 += x13, x5 = rotl32(x5 ^ x9, 7) // x10 += x14, x6 = rotl32(x6 ^ x10, 7) // x11 += x15, x7 = rotl32(x7 ^ x11, 7) add v8.4s, v8.4s, v12.4s + add a8, a8, a12 add v9.4s, v9.4s, v13.4s + add a9, a9, a13 add v10.4s, v10.4s, v14.4s + add a10, a10, a14 add v11.4s, v11.4s, v15.4s + add a11, a11, a15 eor v16.16b, v4.16b, v8.16b + eor a4, a4, a8 eor v17.16b, v5.16b, v9.16b + eor a5, a5, a9 eor v18.16b, v6.16b, v10.16b + eor a6, a6, a10 eor v19.16b, v7.16b, v11.16b + eor a7, a7, a11 shl v4.4s, v16.4s, #7 shl v5.4s, v17.4s, #7 @@ -240,42 +365,66 @@ ENTRY(chacha20_4block_xor_neon) shl v7.4s, v19.4s, #7 sri v4.4s, v16.4s, #25 + ror a4, a4, #25 sri v5.4s, v17.4s, #25 + ror a5, a5, #25 sri v6.4s, v18.4s, #25 + ror a6, a6, #25 sri v7.4s, v19.4s, #25 + ror a7, a7, #25 // x0 += x5, x15 = rotl32(x15 ^ x0, 16) // x1 += x6, x12 = rotl32(x12 ^ x1, 16) // x2 += x7, x13 = rotl32(x13 ^ x2, 16) // x3 += x4, x14 = rotl32(x14 ^ x3, 16) add v0.4s, v0.4s, v5.4s + add a0, a0, a5 add v1.4s, v1.4s, v6.4s + add a1, a1, a6 add v2.4s, v2.4s, v7.4s + add a2, a2, a7 add v3.4s, v3.4s, v4.4s + add a3, a3, a4 eor v15.16b, v15.16b, v0.16b + eor a15, a15, a0 eor v12.16b, v12.16b, v1.16b + eor a12, a12, a1 eor v13.16b, v13.16b, v2.16b + eor a13, a13, a2 eor v14.16b, v14.16b, v3.16b + eor a14, a14, a3 rev32 v15.8h, v15.8h + ror a15, a15, #16 rev32 v12.8h, v12.8h + ror a12, a12, #16 rev32 v13.8h, v13.8h + ror a13, a13, #16 rev32 v14.8h, v14.8h + ror a14, a14, #16 // x10 += x15, x5 = rotl32(x5 ^ x10, 12) // x11 += x12, x6 = rotl32(x6 ^ x11, 12) // x8 += x13, x7 = rotl32(x7 ^ x8, 12) // x9 += x14, x4 = rotl32(x4 ^ x9, 12) add v10.4s, v10.4s, v15.4s + add a10, a10, a15 add v11.4s, v11.4s, v12.4s + add a11, a11, a12 add v8.4s, v8.4s, v13.4s + add a8, a8, a13 add v9.4s, v9.4s, v14.4s + add a9, a9, a14 eor v16.16b, v5.16b, v10.16b + eor a5, a5, a10 eor v17.16b, v6.16b, v11.16b + eor a6, a6, a11 eor v18.16b, v7.16b, v8.16b + eor a7, a7, a8 eor v19.16b, v4.16b, v9.16b + eor a4, a4, a9 shl v5.4s, v16.4s, #12 shl v6.4s, v17.4s, #12 @@ -283,42 +432,66 @@ ENTRY(chacha20_4block_xor_neon) shl v4.4s, v19.4s, #12 sri v5.4s, v16.4s, #20 + ror a5, a5, #20 sri v6.4s, v17.4s, #20 + ror a6, a6, #20 sri v7.4s, v18.4s, #20 + ror a7, a7, #20 sri v4.4s, v19.4s, #20 + ror a4, a4, #20 // x0 += x5, x15 = rotl32(x15 ^ x0, 8) // x1 += x6, x12 = rotl32(x12 ^ x1, 8) // x2 += x7, x13 = rotl32(x13 ^ x2, 8) // x3 += x4, x14 = rotl32(x14 ^ x3, 8) add v0.4s, v0.4s, v5.4s + add a0, a0, a5 add v1.4s, v1.4s, v6.4s + add a1, a1, a6 add v2.4s, v2.4s, v7.4s + add a2, a2, a7 add v3.4s, v3.4s, v4.4s + add a3, a3, a4 eor v15.16b, v15.16b, v0.16b + eor a15, a15, a0 eor v12.16b, v12.16b, v1.16b + eor a12, a12, a1 eor v13.16b, v13.16b, v2.16b + eor a13, a13, a2 eor v14.16b, v14.16b, v3.16b + eor a14, a14, a3 tbl v15.16b, {v15.16b}, v31.16b + ror a15, a15, #24 tbl v12.16b, {v12.16b}, v31.16b + ror a12, a12, #24 tbl v13.16b, {v13.16b}, v31.16b + ror a13, a13, #24 tbl v14.16b, {v14.16b}, v31.16b + ror a14, a14, #24 // x10 += x15, x5 = rotl32(x5 ^ x10, 7) // x11 += x12, x6 = rotl32(x6 ^ x11, 7) // x8 += x13, x7 = rotl32(x7 ^ x8, 7) // x9 += x14, x4 = rotl32(x4 ^ x9, 7) add v10.4s, v10.4s, v15.4s + add a10, a10, a15 add v11.4s, v11.4s, v12.4s + add a11, a11, a12 add v8.4s, v8.4s, v13.4s + add a8, a8, a13 add v9.4s, v9.4s, v14.4s + add a9, a9, a14 eor v16.16b, v5.16b, v10.16b + eor a5, a5, a10 eor v17.16b, v6.16b, v11.16b + eor a6, a6, a11 eor v18.16b, v7.16b, v8.16b + eor a7, a7, a8 eor v19.16b, v4.16b, v9.16b + eor a4, a4, a9 shl v5.4s, v16.4s, #7 shl v6.4s, v17.4s, #7 @@ -326,11 +499,15 @@ ENTRY(chacha20_4block_xor_neon) shl v4.4s, v19.4s, #7 sri v5.4s, v16.4s, #25 + ror a5, a5, #25 sri v6.4s, v17.4s, #25 + ror a6, a6, #25 sri v7.4s, v18.4s, #25 + ror a7, a7, #25 sri v4.4s, v19.4s, #25 + ror a4, a4, #25 - subs x3, x3, #1 + subs w3, w3, #2 b.ne .Ldoubleround4 ld4r {v16.4s-v19.4s}, [x0], #16 @@ -344,9 +521,17 @@ ENTRY(chacha20_4block_xor_neon) // x2[0-3] += s0[2] // x3[0-3] += s0[3] add v0.4s, v0.4s, v16.4s + mov w6, v16.s[0] + mov w7, v17.s[0] add v1.4s, v1.4s, v17.4s + mov w8, v18.s[0] + mov w9, v19.s[0] add v2.4s, v2.4s, v18.4s + add a0, a0, w6 + add a1, a1, w7 add v3.4s, v3.4s, v19.4s + add a2, a2, w8 + add a3, a3, w9 ld4r {v24.4s-v27.4s}, [x0], #16 ld4r {v28.4s-v31.4s}, [x0] @@ -356,95 +541,304 @@ ENTRY(chacha20_4block_xor_neon) // x6[0-3] += s1[2] // x7[0-3] += s1[3] add v4.4s, v4.4s, v20.4s + mov w6, v20.s[0] + mov w7, v21.s[0] add v5.4s, v5.4s, v21.4s + mov w8, v22.s[0] + mov w9, v23.s[0] add v6.4s, v6.4s, v22.4s + add a4, a4, w6 + add a5, a5, w7 add v7.4s, v7.4s, v23.4s + add a6, a6, w8 + add a7, a7, w9 // x8[0-3] += s2[0] // x9[0-3] += s2[1] // x10[0-3] += s2[2] // x11[0-3] += s2[3] add v8.4s, v8.4s, v24.4s + mov w6, v24.s[0] + mov w7, v25.s[0] add v9.4s, v9.4s, v25.4s + mov w8, v26.s[0] + mov w9, v27.s[0] add v10.4s, v10.4s, v26.4s + add a8, a8, w6 + add a9, a9, w7 add v11.4s, v11.4s, v27.4s + add a10, a10, w8 + add a11, a11, w9 // x12[0-3] += s3[0] // x13[0-3] += s3[1] // x14[0-3] += s3[2] // x15[0-3] += s3[3] add v12.4s, v12.4s, v28.4s + mov w6, v28.s[0] + mov w7, v29.s[0] add v13.4s, v13.4s, v29.4s + mov w8, v30.s[0] + mov w9, v31.s[0] add v14.4s, v14.4s, v30.4s + add a12, a12, w6 + add a13, a13, w7 add v15.4s, v15.4s, v31.4s + add a14, a14, w8 + add a15, a15, w9 // interleave 32-bit words in state n, n+1 + ldp w6, w7, [x2], #64 zip1 v16.4s, v0.4s, v1.4s + ldp w8, w9, [x2, #-56] + eor a0, a0, w6 zip2 v17.4s, v0.4s, v1.4s + eor a1, a1, w7 zip1 v18.4s, v2.4s, v3.4s + eor a2, a2, w8 zip2 v19.4s, v2.4s, v3.4s + eor a3, a3, w9 + ldp w6, w7, [x2, #-48] zip1 v20.4s, v4.4s, v5.4s + ldp w8, w9, [x2, #-40] + eor a4, a4, w6 zip2 v21.4s, v4.4s, v5.4s + eor a5, a5, w7 zip1 v22.4s, v6.4s, v7.4s + eor a6, a6, w8 zip2 v23.4s, v6.4s, v7.4s + eor a7, a7, w9 + ldp w6, w7, [x2, #-32] zip1 v24.4s, v8.4s, v9.4s + ldp w8, w9, [x2, #-24] + eor a8, a8, w6 zip2 v25.4s, v8.4s, v9.4s + eor a9, a9, w7 zip1 v26.4s, v10.4s, v11.4s + eor a10, a10, w8 zip2 v27.4s, v10.4s, v11.4s + eor a11, a11, w9 + ldp w6, w7, [x2, #-16] zip1 v28.4s, v12.4s, v13.4s + ldp w8, w9, [x2, #-8] + eor a12, a12, w6 zip2 v29.4s, v12.4s, v13.4s + eor a13, a13, w7 zip1 v30.4s, v14.4s, v15.4s + eor a14, a14, w8 zip2 v31.4s, v14.4s, v15.4s + eor a15, a15, w9 + + mov x3, #64 + subs x5, x4, #128 + add x6, x5, x2 + csel x3, x3, xzr, ge + csel x2, x2, x6, ge // interleave 64-bit words in state n, n+2 zip1 v0.2d, v16.2d, v18.2d zip2 v4.2d, v16.2d, v18.2d + stp a0, a1, [x1], #64 zip1 v8.2d, v17.2d, v19.2d zip2 v12.2d, v17.2d, v19.2d - ld1 {v16.16b-v19.16b}, [x2], #64 + stp a2, a3, [x1, #-56] + ld1 {v16.16b-v19.16b}, [x2], x3 + + subs x6, x4, #192 + ccmp x3, xzr, #4, lt + add x7, x6, x2 + csel x3, x3, xzr, eq + csel x2, x2, x7, eq zip1 v1.2d, v20.2d, v22.2d zip2 v5.2d, v20.2d, v22.2d + stp a4, a5, [x1, #-48] zip1 v9.2d, v21.2d, v23.2d zip2 v13.2d, v21.2d, v23.2d - ld1 {v20.16b-v23.16b}, [x2], #64 + stp a6, a7, [x1, #-40] + ld1 {v20.16b-v23.16b}, [x2], x3 + + subs x7, x4, #256 + ccmp x3, xzr, #4, lt + add x8, x7, x2 + csel x3, x3, xzr, eq + csel x2, x2, x8, eq zip1 v2.2d, v24.2d, v26.2d zip2 v6.2d, v24.2d, v26.2d + stp a8, a9, [x1, #-32] zip1 v10.2d, v25.2d, v27.2d zip2 v14.2d, v25.2d, v27.2d - ld1 {v24.16b-v27.16b}, [x2], #64 + stp a10, a11, [x1, #-24] + ld1 {v24.16b-v27.16b}, [x2], x3 + + subs x8, x4, #320 + ccmp x3, xzr, #4, lt + add x9, x8, x2 + csel x2, x2, x9, eq zip1 v3.2d, v28.2d, v30.2d zip2 v7.2d, v28.2d, v30.2d + stp a12, a13, [x1, #-16] zip1 v11.2d, v29.2d, v31.2d zip2 v15.2d, v29.2d, v31.2d + stp a14, a15, [x1, #-8] ld1 {v28.16b-v31.16b}, [x2] // xor with corresponding input, write to output + tbnz x5, #63, 0f eor v16.16b, v16.16b, v0.16b eor v17.16b, v17.16b, v1.16b eor v18.16b, v18.16b, v2.16b eor v19.16b, v19.16b, v3.16b + st1 {v16.16b-v19.16b}, [x1], #64 + cbz x5, .Lout + + tbnz x6, #63, 1f eor v20.16b, v20.16b, v4.16b eor v21.16b, v21.16b, v5.16b - st1 {v16.16b-v19.16b}, [x1], #64 eor v22.16b, v22.16b, v6.16b eor v23.16b, v23.16b, v7.16b + st1 {v20.16b-v23.16b}, [x1], #64 + cbz x6, .Lout + + tbnz x7, #63, 2f eor v24.16b, v24.16b, v8.16b eor v25.16b, v25.16b, v9.16b - st1 {v20.16b-v23.16b}, [x1], #64 eor v26.16b, v26.16b, v10.16b eor v27.16b, v27.16b, v11.16b - eor v28.16b, v28.16b, v12.16b st1 {v24.16b-v27.16b}, [x1], #64 + cbz x7, .Lout + + tbnz x8, #63, 3f + eor v28.16b, v28.16b, v12.16b eor v29.16b, v29.16b, v13.16b eor v30.16b, v30.16b, v14.16b eor v31.16b, v31.16b, v15.16b st1 {v28.16b-v31.16b}, [x1] +.Lout: frame_pop ret -ENDPROC(chacha20_4block_xor_neon) -CTRINC: .word 0, 1, 2, 3 + // fewer than 128 bytes of in/output +0: ld1 {v8.16b}, [x10] + ld1 {v9.16b}, [x11] + movi v10.16b, #16 + sub x2, x1, #64 + add x1, x1, x5 + ld1 {v16.16b-v19.16b}, [x2] + tbl v4.16b, {v0.16b-v3.16b}, v8.16b + tbx v20.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v5.16b, {v0.16b-v3.16b}, v8.16b + tbx v21.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v6.16b, {v0.16b-v3.16b}, v8.16b + tbx v22.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v7.16b, {v0.16b-v3.16b}, v8.16b + tbx v23.16b, {v16.16b-v19.16b}, v9.16b + + eor v20.16b, v20.16b, v4.16b + eor v21.16b, v21.16b, v5.16b + eor v22.16b, v22.16b, v6.16b + eor v23.16b, v23.16b, v7.16b + st1 {v20.16b-v23.16b}, [x1] + b .Lout + + // fewer than 192 bytes of in/output +1: ld1 {v8.16b}, [x10] + ld1 {v9.16b}, [x11] + movi v10.16b, #16 + add x1, x1, x6 + tbl v0.16b, {v4.16b-v7.16b}, v8.16b + tbx v20.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v1.16b, {v4.16b-v7.16b}, v8.16b + tbx v21.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v2.16b, {v4.16b-v7.16b}, v8.16b + tbx v22.16b, {v16.16b-v19.16b}, v9.16b + add v8.16b, v8.16b, v10.16b + add v9.16b, v9.16b, v10.16b + tbl v3.16b, {v4.16b-v7.16b}, v8.16b + tbx v23.16b, {v16.16b-v19.16b}, v9.16b + + eor v20.16b, v20.16b, v0.16b + eor v21.16b, v21.16b, v1.16b + eor v22.16b, v22.16b, v2.16b + eor v23.16b, v23.16b, v3.16b + st1 {v20.16b-v23.16b}, [x1] + b .Lout + + // fewer than 256 bytes of in/output +2: ld1 {v4.16b}, [x10] + ld1 {v5.16b}, [x11] + movi v6.16b, #16 + add x1, x1, x7 + tbl v0.16b, {v8.16b-v11.16b}, v4.16b + tbx v24.16b, {v20.16b-v23.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v1.16b, {v8.16b-v11.16b}, v4.16b + tbx v25.16b, {v20.16b-v23.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v2.16b, {v8.16b-v11.16b}, v4.16b + tbx v26.16b, {v20.16b-v23.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v3.16b, {v8.16b-v11.16b}, v4.16b + tbx v27.16b, {v20.16b-v23.16b}, v5.16b + + eor v24.16b, v24.16b, v0.16b + eor v25.16b, v25.16b, v1.16b + eor v26.16b, v26.16b, v2.16b + eor v27.16b, v27.16b, v3.16b + st1 {v24.16b-v27.16b}, [x1] + b .Lout + + // fewer than 320 bytes of in/output +3: ld1 {v4.16b}, [x10] + ld1 {v5.16b}, [x11] + movi v6.16b, #16 + add x1, x1, x8 + tbl v0.16b, {v12.16b-v15.16b}, v4.16b + tbx v28.16b, {v24.16b-v27.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v1.16b, {v12.16b-v15.16b}, v4.16b + tbx v29.16b, {v24.16b-v27.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v2.16b, {v12.16b-v15.16b}, v4.16b + tbx v30.16b, {v24.16b-v27.16b}, v5.16b + add v4.16b, v4.16b, v6.16b + add v5.16b, v5.16b, v6.16b + tbl v3.16b, {v12.16b-v15.16b}, v4.16b + tbx v31.16b, {v24.16b-v27.16b}, v5.16b + + eor v28.16b, v28.16b, v0.16b + eor v29.16b, v29.16b, v1.16b + eor v30.16b, v30.16b, v2.16b + eor v31.16b, v31.16b, v3.16b + st1 {v28.16b-v31.16b}, [x1] + b .Lout +ENDPROC(chacha_4block_xor_neon) + + .section ".rodata", "a", %progbits + .align L1_CACHE_SHIFT +.Lpermute: + .set .Li, 0 + .rept 192 + .byte (.Li - 64) + .set .Li, .Li + 1 + .endr + +CTRINC: .word 1, 2, 3, 4 ROT8: .word 0x02010003, 0x06050407, 0x0a09080b, 0x0e0d0c0f diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c new file mode 100644 index 000000000000..bece1d85bd81 --- /dev/null +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -0,0 +1,198 @@ +/* + * ARM NEON accelerated ChaCha and XChaCha stream ciphers, + * including ChaCha20 (RFC7539) + * + * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on: + * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code + * + * Copyright (C) 2015 Martin Willi + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <crypto/algapi.h> +#include <crypto/chacha.h> +#include <crypto/internal/skcipher.h> +#include <linux/kernel.h> +#include <linux/module.h> + +#include <asm/hwcap.h> +#include <asm/neon.h> +#include <asm/simd.h> + +asmlinkage void chacha_block_xor_neon(u32 *state, u8 *dst, const u8 *src, + int nrounds); +asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src, + int nrounds, int bytes); +asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds); + +static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, + int bytes, int nrounds) +{ + while (bytes > 0) { + int l = min(bytes, CHACHA_BLOCK_SIZE * 5); + + if (l <= CHACHA_BLOCK_SIZE) { + u8 buf[CHACHA_BLOCK_SIZE]; + + memcpy(buf, src, l); + chacha_block_xor_neon(state, buf, buf, nrounds); + memcpy(dst, buf, l); + state[12] += 1; + break; + } + chacha_4block_xor_neon(state, dst, src, nrounds, l); + bytes -= CHACHA_BLOCK_SIZE * 5; + src += CHACHA_BLOCK_SIZE * 5; + dst += CHACHA_BLOCK_SIZE * 5; + state[12] += 5; + } +} + +static int chacha_neon_stream_xor(struct skcipher_request *req, + struct chacha_ctx *ctx, u8 *iv) +{ + struct skcipher_walk walk; + u32 state[16]; + int err; + + err = skcipher_walk_virt(&walk, req, false); + + crypto_chacha_init(state, ctx, iv); + + while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = rounddown(nbytes, walk.stride); + + kernel_neon_begin(); + chacha_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, + nbytes, ctx->nrounds); + kernel_neon_end(); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +} + +static int chacha_neon(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_chacha_crypt(req); + + return chacha_neon_stream_xor(req, ctx, req->iv); +} + +static int xchacha_neon(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm); + struct chacha_ctx subctx; + u32 state[16]; + u8 real_iv[16]; + + if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd()) + return crypto_xchacha_crypt(req); + + crypto_chacha_init(state, ctx, req->iv); + + kernel_neon_begin(); + hchacha_block_neon(state, subctx.key, ctx->nrounds); + kernel_neon_end(); + subctx.nrounds = ctx->nrounds; + + memcpy(&real_iv[0], req->iv + 24, 8); + memcpy(&real_iv[8], req->iv + 16, 8); + return chacha_neon_stream_xor(req, &subctx, real_iv); +} + +static struct skcipher_alg algs[] = { + { + .base.cra_name = "chacha20", + .base.cra_driver_name = "chacha20-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = CHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = chacha_neon, + .decrypt = chacha_neon, + }, { + .base.cra_name = "xchacha20", + .base.cra_driver_name = "xchacha20-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha20_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + }, { + .base.cra_name = "xchacha12", + .base.cra_driver_name = "xchacha12-neon", + .base.cra_priority = 300, + .base.cra_blocksize = 1, + .base.cra_ctxsize = sizeof(struct chacha_ctx), + .base.cra_module = THIS_MODULE, + + .min_keysize = CHACHA_KEY_SIZE, + .max_keysize = CHACHA_KEY_SIZE, + .ivsize = XCHACHA_IV_SIZE, + .chunksize = CHACHA_BLOCK_SIZE, + .walksize = 5 * CHACHA_BLOCK_SIZE, + .setkey = crypto_chacha12_setkey, + .encrypt = xchacha_neon, + .decrypt = xchacha_neon, + } +}; + +static int __init chacha_simd_mod_init(void) +{ + if (!(elf_hwcap & HWCAP_ASIMD)) + return -ENODEV; + + return crypto_register_skciphers(algs, ARRAY_SIZE(algs)); +} + +static void __exit chacha_simd_mod_fini(void) +{ + crypto_unregister_skciphers(algs, ARRAY_SIZE(algs)); +} + +module_init(chacha_simd_mod_init); +module_exit(chacha_simd_mod_fini); + +MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS_CRYPTO("chacha20"); +MODULE_ALIAS_CRYPTO("chacha20-neon"); +MODULE_ALIAS_CRYPTO("xchacha20"); +MODULE_ALIAS_CRYPTO("xchacha20-neon"); +MODULE_ALIAS_CRYPTO("xchacha12"); +MODULE_ALIAS_CRYPTO("xchacha12-neon"); diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c deleted file mode 100644 index 727579c93ded..000000000000 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ /dev/null @@ -1,133 +0,0 @@ -/* - * ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions - * - * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on: - * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code - * - * Copyright (C) 2015 Martin Willi - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <crypto/algapi.h> -#include <crypto/chacha20.h> -#include <crypto/internal/skcipher.h> -#include <linux/kernel.h> -#include <linux/module.h> - -#include <asm/hwcap.h> -#include <asm/neon.h> -#include <asm/simd.h> - -asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src); -asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src); - -static void chacha20_doneon(u32 *state, u8 *dst, const u8 *src, - unsigned int bytes) -{ - u8 buf[CHACHA20_BLOCK_SIZE]; - - while (bytes >= CHACHA20_BLOCK_SIZE * 4) { - kernel_neon_begin(); - chacha20_4block_xor_neon(state, dst, src); - kernel_neon_end(); - bytes -= CHACHA20_BLOCK_SIZE * 4; - src += CHACHA20_BLOCK_SIZE * 4; - dst += CHACHA20_BLOCK_SIZE * 4; - state[12] += 4; - } - - if (!bytes) - return; - - kernel_neon_begin(); - while (bytes >= CHACHA20_BLOCK_SIZE) { - chacha20_block_xor_neon(state, dst, src); - bytes -= CHACHA20_BLOCK_SIZE; - src += CHACHA20_BLOCK_SIZE; - dst += CHACHA20_BLOCK_SIZE; - state[12]++; - } - if (bytes) { - memcpy(buf, src, bytes); - chacha20_block_xor_neon(state, buf, buf); - memcpy(dst, buf, bytes); - } - kernel_neon_end(); -} - -static int chacha20_neon(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct chacha20_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - u32 state[16]; - int err; - - if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE) - return crypto_chacha20_crypt(req); - - err = skcipher_walk_virt(&walk, req, false); - - crypto_chacha20_init(state, ctx, walk.iv); - - while (walk.nbytes > 0) { - unsigned int nbytes = walk.nbytes; - - if (nbytes < walk.total) - nbytes = round_down(nbytes, walk.stride); - - chacha20_doneon(state, walk.dst.virt.addr, walk.src.virt.addr, - nbytes); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); - } - - return err; -} - -static struct skcipher_alg alg = { - .base.cra_name = "chacha20", - .base.cra_driver_name = "chacha20-neon", - .base.cra_priority = 300, - .base.cra_blocksize = 1, - .base.cra_ctxsize = sizeof(struct chacha20_ctx), - .base.cra_module = THIS_MODULE, - - .min_keysize = CHACHA20_KEY_SIZE, - .max_keysize = CHACHA20_KEY_SIZE, - .ivsize = CHACHA20_IV_SIZE, - .chunksize = CHACHA20_BLOCK_SIZE, - .walksize = 4 * CHACHA20_BLOCK_SIZE, - .setkey = crypto_chacha20_setkey, - .encrypt = chacha20_neon, - .decrypt = chacha20_neon, -}; - -static int __init chacha20_simd_mod_init(void) -{ - if (!(elf_hwcap & HWCAP_ASIMD)) - return -ENODEV; - - return crypto_register_skcipher(&alg); -} - -static void __exit chacha20_simd_mod_fini(void) -{ - crypto_unregister_skcipher(&alg); -} - -module_init(chacha20_simd_mod_init); -module_exit(chacha20_simd_mod_fini); - -MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS_CRYPTO("chacha20"); diff --git a/arch/arm64/crypto/nh-neon-core.S b/arch/arm64/crypto/nh-neon-core.S new file mode 100644 index 000000000000..e05570c38de7 --- /dev/null +++ b/arch/arm64/crypto/nh-neon-core.S @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NH - ε-almost-universal hash function, ARM64 NEON accelerated version + * + * Copyright 2018 Google LLC + * + * Author: Eric Biggers <ebiggers@google.com> + */ + +#include <linux/linkage.h> + + KEY .req x0 + MESSAGE .req x1 + MESSAGE_LEN .req x2 + HASH .req x3 + + PASS0_SUMS .req v0 + PASS1_SUMS .req v1 + PASS2_SUMS .req v2 + PASS3_SUMS .req v3 + K0 .req v4 + K1 .req v5 + K2 .req v6 + K3 .req v7 + T0 .req v8 + T1 .req v9 + T2 .req v10 + T3 .req v11 + T4 .req v12 + T5 .req v13 + T6 .req v14 + T7 .req v15 + +.macro _nh_stride k0, k1, k2, k3 + + // Load next message stride + ld1 {T3.16b}, [MESSAGE], #16 + + // Load next key stride + ld1 {\k3\().4s}, [KEY], #16 + + // Add message words to key words + add T0.4s, T3.4s, \k0\().4s + add T1.4s, T3.4s, \k1\().4s + add T2.4s, T3.4s, \k2\().4s + add T3.4s, T3.4s, \k3\().4s + + // Multiply 32x32 => 64 and accumulate + mov T4.d[0], T0.d[1] + mov T5.d[0], T1.d[1] + mov T6.d[0], T2.d[1] + mov T7.d[0], T3.d[1] + umlal PASS0_SUMS.2d, T0.2s, T4.2s + umlal PASS1_SUMS.2d, T1.2s, T5.2s + umlal PASS2_SUMS.2d, T2.2s, T6.2s + umlal PASS3_SUMS.2d, T3.2s, T7.2s +.endm + +/* + * void nh_neon(const u32 *key, const u8 *message, size_t message_len, + * u8 hash[NH_HASH_BYTES]) + * + * It's guaranteed that message_len % 16 == 0. + */ +ENTRY(nh_neon) + + ld1 {K0.4s,K1.4s}, [KEY], #32 + movi PASS0_SUMS.2d, #0 + movi PASS1_SUMS.2d, #0 + ld1 {K2.4s}, [KEY], #16 + movi PASS2_SUMS.2d, #0 + movi PASS3_SUMS.2d, #0 + + subs MESSAGE_LEN, MESSAGE_LEN, #64 + blt .Lloop4_done +.Lloop4: + _nh_stride K0, K1, K2, K3 + _nh_stride K1, K2, K3, K0 + _nh_stride K2, K3, K0, K1 + _nh_stride K3, K0, K1, K2 + subs MESSAGE_LEN, MESSAGE_LEN, #64 + bge .Lloop4 + +.Lloop4_done: + ands MESSAGE_LEN, MESSAGE_LEN, #63 + beq .Ldone + _nh_stride K0, K1, K2, K3 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K1, K2, K3, K0 + + subs MESSAGE_LEN, MESSAGE_LEN, #16 + beq .Ldone + _nh_stride K2, K3, K0, K1 + +.Ldone: + // Sum the accumulators for each pass, then store the sums to 'hash' + addp T0.2d, PASS0_SUMS.2d, PASS1_SUMS.2d + addp T1.2d, PASS2_SUMS.2d, PASS3_SUMS.2d + st1 {T0.16b,T1.16b}, [HASH] + ret +ENDPROC(nh_neon) diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c new file mode 100644 index 000000000000..22cc32ac9448 --- /dev/null +++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * NHPoly1305 - ε-almost-∆-universal hash function for Adiantum + * (ARM64 NEON accelerated version) + * + * Copyright 2018 Google LLC + */ + +#include <asm/neon.h> +#include <asm/simd.h> +#include <crypto/internal/hash.h> +#include <crypto/nhpoly1305.h> +#include <linux/module.h> + +asmlinkage void nh_neon(const u32 *key, const u8 *message, size_t message_len, + u8 hash[NH_HASH_BYTES]); + +/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */ +static void _nh_neon(const u32 *key, const u8 *message, size_t message_len, + __le64 hash[NH_NUM_PASSES]) +{ + nh_neon(key, message, message_len, (u8 *)hash); +} + +static int nhpoly1305_neon_update(struct shash_desc *desc, + const u8 *src, unsigned int srclen) +{ + if (srclen < 64 || !may_use_simd()) + return crypto_nhpoly1305_update(desc, src, srclen); + + do { + unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + + kernel_neon_begin(); + crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); + kernel_neon_end(); + src += n; + srclen -= n; + } while (srclen); + return 0; +} + +static struct shash_alg nhpoly1305_alg = { + .base.cra_name = "nhpoly1305", + .base.cra_driver_name = "nhpoly1305-neon", + .base.cra_priority = 200, + .base.cra_ctxsize = sizeof(struct nhpoly1305_key), + .base.cra_module = THIS_MODULE, + .digestsize = POLY1305_DIGEST_SIZE, + .init = crypto_nhpoly1305_init, + .update = nhpoly1305_neon_update, + .final = crypto_nhpoly1305_final, + .setkey = crypto_nhpoly1305_setkey, + .descsize = sizeof(struct nhpoly1305_state), +}; + +static int __init nhpoly1305_mod_init(void) +{ + if (!(elf_hwcap & HWCAP_ASIMD)) + return -ENODEV; + + return crypto_register_shash(&nhpoly1305_alg); +} + +static void __exit nhpoly1305_mod_exit(void) +{ + crypto_unregister_shash(&nhpoly1305_alg); +} + +module_init(nhpoly1305_mod_init); +module_exit(nhpoly1305_mod_exit); + +MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function (NEON-accelerated)"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>"); +MODULE_ALIAS_CRYPTO("nhpoly1305"); +MODULE_ALIAS_CRYPTO("nhpoly1305-neon"); diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 6cd5d77b6b44..1e17ea5c372b 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -14,7 +14,6 @@ generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h generic-y += msi.h -generic-y += preempt.h generic-y += qrwlock.h generic-y += qspinlock.h generic-y += rwsem.h @@ -27,4 +26,3 @@ generic-y += trace_clock.h generic-y += unaligned.h generic-y += user.h generic-y += vga.h -generic-y += xor.h diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index 709208dfdc8b..2def77ec14be 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -22,12 +22,23 @@ #include <asm/tlbflush.h> /* Macros for consistency checks of the GICC subtable of MADT */ -#define ACPI_MADT_GICC_LENGTH \ - (acpi_gbl_FADT.header.revision < 6 ? 76 : 80) + +/* + * MADT GICC minimum length refers to the MADT GICC structure table length as + * defined in the earliest ACPI version supported on arm64, ie ACPI 5.1. + * + * The efficiency_class member was added to the + * struct acpi_madt_generic_interrupt to represent the MADT GICC structure + * "Processor Power Efficiency Class" field, added in ACPI 6.0 whose offset + * is therefore used to delimit the MADT GICC structure minimum length + * appropriately. + */ +#define ACPI_MADT_GICC_MIN_LENGTH ACPI_OFFSET( \ + struct acpi_madt_generic_interrupt, efficiency_class) #define BAD_MADT_GICC_ENTRY(entry, end) \ - (!(entry) || (entry)->header.length != ACPI_MADT_GICC_LENGTH || \ - (unsigned long)(entry) + ACPI_MADT_GICC_LENGTH > (end)) + (!(entry) || (entry)->header.length < ACPI_MADT_GICC_MIN_LENGTH || \ + (unsigned long)(entry) + (entry)->header.length > (end)) /* Basic configuration for ACPI */ #ifdef CONFIG_ACPI diff --git a/arch/arm64/include/asm/asm-prototypes.h b/arch/arm64/include/asm/asm-prototypes.h new file mode 100644 index 000000000000..2173ad32d550 --- /dev/null +++ b/arch/arm64/include/asm/asm-prototypes.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_PROTOTYPES_H +#define __ASM_PROTOTYPES_H +/* + * CONFIG_MODEVERIONS requires a C declaration to generate the appropriate CRC + * for each symbol. Since commit: + * + * 4efca4ed05cbdfd1 ("kbuild: modversions for EXPORT_SYMBOL() for asm") + * + * ... kbuild will automatically pick these up from <asm/asm-prototypes.h> and + * feed this to genksyms when building assembly files. + */ +#include <linux/arm-smccc.h> + +#include <asm/ftrace.h> +#include <asm/page.h> +#include <asm/string.h> +#include <asm/uaccess.h> + +#include <asm-generic/asm-prototypes.h> + +long long __ashlti3(long long a, int b); +long long __ashrti3(long long a, int b); +long long __lshrti3(long long a, int b); + +#endif /* __ASM_PROTOTYPES_H */ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 6142402c2eb4..4feb6119c3c9 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -23,6 +23,8 @@ #ifndef __ASM_ASSEMBLER_H #define __ASM_ASSEMBLER_H +#include <asm-generic/export.h> + #include <asm/asm-offsets.h> #include <asm/cpufeature.h> #include <asm/debug-monitors.h> @@ -123,6 +125,19 @@ .endm /* + * Speculation barrier + */ + .macro sb +alternative_if_not ARM64_HAS_SB + dsb nsh + isb +alternative_else + SB_BARRIER_INSN + nop +alternative_endif + .endm + +/* * Sanitise a 64-bit bounded index wrt speculation, returning zero if out * of bounds. */ @@ -342,11 +357,10 @@ alternative_endif .endm /* - * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map + * tcr_set_t0sz - update TCR.T0SZ so that we can load the ID map */ - .macro tcr_set_idmap_t0sz, valreg, tmpreg - ldr_l \tmpreg, idmap_t0sz - bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH + .macro tcr_set_t0sz, valreg, t0sz + bfi \valreg, \t0sz, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH .endm /* @@ -377,27 +391,33 @@ alternative_endif * size: size of the region * Corrupts: kaddr, size, tmp1, tmp2 */ + .macro __dcache_op_workaround_clean_cache, op, kaddr +alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE + dc \op, \kaddr +alternative_else + dc civac, \kaddr +alternative_endif + .endm + .macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2 dcache_line_size \tmp1, \tmp2 add \size, \kaddr, \size sub \tmp2, \tmp1, #1 bic \kaddr, \kaddr, \tmp2 9998: - .if (\op == cvau || \op == cvac) -alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE - dc \op, \kaddr -alternative_else - dc civac, \kaddr -alternative_endif - .elseif (\op == cvap) -alternative_if ARM64_HAS_DCPOP - sys 3, c7, c12, 1, \kaddr // dc cvap -alternative_else - dc cvac, \kaddr -alternative_endif + .ifc \op, cvau + __dcache_op_workaround_clean_cache \op, \kaddr + .else + .ifc \op, cvac + __dcache_op_workaround_clean_cache \op, \kaddr + .else + .ifc \op, cvap + sys 3, c7, c12, 1, \kaddr // dc cvap .else dc \op, \kaddr .endif + .endif + .endif add \kaddr, \kaddr, \tmp1 cmp \kaddr, \size b.lo 9998b @@ -477,6 +497,13 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU #else #define NOKPROBE(x) #endif + +#ifdef CONFIG_KASAN +#define EXPORT_SYMBOL_NOKASAN(name) +#else +#define EXPORT_SYMBOL_NOKASAN(name) EXPORT_SYMBOL(name) +#endif + /* * Emit a 64-bit absolute little endian symbol reference in a way that * ensures that it will be resolved at build time, even when building a @@ -516,6 +543,29 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .endm /* + * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD. + * 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 +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET +#endif + .endm + +/* + * Perform the reverse of offset_ttbr1. + * bic is used as it can cover the immediate value and, in future, won't need + * to be nop'ed out when dealing with 52-bit kernel VAs. + */ + .macro restore_ttbr1, ttbr +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + bic \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET +#endif + .endm + +/* * Arrange a physical address in a TTBR register, taking care of 52-bit * addresses. * @@ -672,11 +722,9 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU .macro if_will_cond_yield_neon #ifdef CONFIG_PREEMPT get_thread_info x0 - ldr w1, [x0, #TSK_TI_PREEMPT] - ldr x0, [x0, #TSK_TI_FLAGS] - cmp w1, #PREEMPT_DISABLE_OFFSET - csel x0, x0, xzr, eq - tbnz x0, #TIF_NEED_RESCHED, .Lyield_\@ // needs rescheduling? + ldr x0, [x0, #TSK_TI_PREEMPT] + sub x0, x0, #PREEMPT_DISABLE_OFFSET + cbz x0, .Lyield_\@ /* fall through to endif_yield_neon */ .subsection 1 .Lyield_\@ : diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index f5a2d09afb38..af7b99005453 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -248,48 +248,57 @@ __LL_SC_PREFIX(atomic64_dec_if_positive(atomic64_t *v)) } __LL_SC_EXPORT(atomic64_dec_if_positive); -#define __CMPXCHG_CASE(w, sz, name, mb, acq, rel, cl) \ -__LL_SC_INLINE unsigned long \ -__LL_SC_PREFIX(__cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new)) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, acq, rel, cl) \ +__LL_SC_INLINE u##sz \ +__LL_SC_PREFIX(__cmpxchg_case_##name##sz(volatile void *ptr, \ + unsigned long old, \ + u##sz new)) \ { \ - unsigned long tmp, oldval; \ + unsigned long tmp; \ + u##sz oldval; \ + \ + /* \ + * Sub-word sizes require explicit casting so that the compare \ + * part of the cmpxchg doesn't end up interpreting non-zero \ + * upper bits of the register containing "old". \ + */ \ + if (sz < 32) \ + old = (u##sz)old; \ \ asm volatile( \ " prfm pstl1strm, %[v]\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "[oldval], %[v]\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "[oldval], %[v]\n" \ " eor %" #w "[tmp], %" #w "[oldval], %" #w "[old]\n" \ " cbnz %" #w "[tmp], 2f\n" \ - " st" #rel "xr" #sz "\t%w[tmp], %" #w "[new], %[v]\n" \ + " st" #rel "xr" #sfx "\t%w[tmp], %" #w "[new], %[v]\n" \ " cbnz %w[tmp], 1b\n" \ " " #mb "\n" \ "2:" \ : [tmp] "=&r" (tmp), [oldval] "=&r" (oldval), \ - [v] "+Q" (*(unsigned long *)ptr) \ - : [old] "Lr" (old), [new] "r" (new) \ + [v] "+Q" (*(u##sz *)ptr) \ + : [old] "Kr" (old), [new] "r" (new) \ : cl); \ \ return oldval; \ } \ -__LL_SC_EXPORT(__cmpxchg_case_##name); +__LL_SC_EXPORT(__cmpxchg_case_##name##sz); -__CMPXCHG_CASE(w, b, 1, , , , ) -__CMPXCHG_CASE(w, h, 2, , , , ) -__CMPXCHG_CASE(w, , 4, , , , ) -__CMPXCHG_CASE( , , 8, , , , ) -__CMPXCHG_CASE(w, b, acq_1, , a, , "memory") -__CMPXCHG_CASE(w, h, acq_2, , a, , "memory") -__CMPXCHG_CASE(w, , acq_4, , a, , "memory") -__CMPXCHG_CASE( , , acq_8, , a, , "memory") -__CMPXCHG_CASE(w, b, rel_1, , , l, "memory") -__CMPXCHG_CASE(w, h, rel_2, , , l, "memory") -__CMPXCHG_CASE(w, , rel_4, , , l, "memory") -__CMPXCHG_CASE( , , rel_8, , , l, "memory") -__CMPXCHG_CASE(w, b, mb_1, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, h, mb_2, dmb ish, , l, "memory") -__CMPXCHG_CASE(w, , mb_4, dmb ish, , l, "memory") -__CMPXCHG_CASE( , , mb_8, dmb ish, , l, "memory") +__CMPXCHG_CASE(w, b, , 8, , , , ) +__CMPXCHG_CASE(w, h, , 16, , , , ) +__CMPXCHG_CASE(w, , , 32, , , , ) +__CMPXCHG_CASE( , , , 64, , , , ) +__CMPXCHG_CASE(w, b, acq_, 8, , a, , "memory") +__CMPXCHG_CASE(w, h, acq_, 16, , a, , "memory") +__CMPXCHG_CASE(w, , acq_, 32, , a, , "memory") +__CMPXCHG_CASE( , , acq_, 64, , a, , "memory") +__CMPXCHG_CASE(w, b, rel_, 8, , , l, "memory") +__CMPXCHG_CASE(w, h, rel_, 16, , , l, "memory") +__CMPXCHG_CASE(w, , rel_, 32, , , l, "memory") +__CMPXCHG_CASE( , , rel_, 64, , , l, "memory") +__CMPXCHG_CASE(w, b, mb_, 8, dmb ish, , l, "memory") +__CMPXCHG_CASE(w, h, mb_, 16, dmb ish, , l, "memory") +__CMPXCHG_CASE(w, , mb_, 32, dmb ish, , l, "memory") +__CMPXCHG_CASE( , , mb_, 64, dmb ish, , l, "memory") #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index f9b0b09153e0..a424355240c5 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -446,22 +446,22 @@ static inline long atomic64_dec_if_positive(atomic64_t *v) #define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op) -#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \ -static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ - unsigned long old, \ - unsigned long new) \ +#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ +static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \ + u##sz old, \ + u##sz new) \ { \ register unsigned long x0 asm ("x0") = (unsigned long)ptr; \ - register unsigned long x1 asm ("x1") = old; \ - register unsigned long x2 asm ("x2") = new; \ + register u##sz x1 asm ("x1") = old; \ + register u##sz x2 asm ("x2") = new; \ \ asm volatile(ARM64_LSE_ATOMIC_INSN( \ /* LL/SC */ \ - __LL_SC_CMPXCHG(name) \ + __LL_SC_CMPXCHG(name##sz) \ __nops(2), \ /* LSE atomics */ \ " mov " #w "30, %" #w "[old]\n" \ - " cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n" \ + " cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \ " mov %" #w "[ret], " #w "30") \ : [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \ : [old] "r" (x1), [new] "r" (x2) \ @@ -470,22 +470,22 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \ return x0; \ } -__CMPXCHG_CASE(w, b, 1, ) -__CMPXCHG_CASE(w, h, 2, ) -__CMPXCHG_CASE(w, , 4, ) -__CMPXCHG_CASE(x, , 8, ) -__CMPXCHG_CASE(w, b, acq_1, a, "memory") -__CMPXCHG_CASE(w, h, acq_2, a, "memory") -__CMPXCHG_CASE(w, , acq_4, a, "memory") -__CMPXCHG_CASE(x, , acq_8, a, "memory") -__CMPXCHG_CASE(w, b, rel_1, l, "memory") -__CMPXCHG_CASE(w, h, rel_2, l, "memory") -__CMPXCHG_CASE(w, , rel_4, l, "memory") -__CMPXCHG_CASE(x, , rel_8, l, "memory") -__CMPXCHG_CASE(w, b, mb_1, al, "memory") -__CMPXCHG_CASE(w, h, mb_2, al, "memory") -__CMPXCHG_CASE(w, , mb_4, al, "memory") -__CMPXCHG_CASE(x, , mb_8, al, "memory") +__CMPXCHG_CASE(w, b, , 8, ) +__CMPXCHG_CASE(w, h, , 16, ) +__CMPXCHG_CASE(w, , , 32, ) +__CMPXCHG_CASE(x, , , 64, ) +__CMPXCHG_CASE(w, b, acq_, 8, a, "memory") +__CMPXCHG_CASE(w, h, acq_, 16, a, "memory") +__CMPXCHG_CASE(w, , acq_, 32, a, "memory") +__CMPXCHG_CASE(x, , acq_, 64, a, "memory") +__CMPXCHG_CASE(w, b, rel_, 8, l, "memory") +__CMPXCHG_CASE(w, h, rel_, 16, l, "memory") +__CMPXCHG_CASE(w, , rel_, 32, l, "memory") +__CMPXCHG_CASE(x, , rel_, 64, l, "memory") +__CMPXCHG_CASE(w, b, mb_, 8, al, "memory") +__CMPXCHG_CASE(w, h, mb_, 16, al, "memory") +__CMPXCHG_CASE(w, , mb_, 32, al, "memory") +__CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __LL_SC_CMPXCHG #undef __CMPXCHG_CASE diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 822a9192c551..f66bb04fdf2d 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -34,6 +34,10 @@ #define psb_csync() asm volatile("hint #17" : : : "memory") #define csdb() asm volatile("hint #20" : : : "memory") +#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ + SB_BARRIER_INSN"nop\n", \ + ARM64_HAS_SB)) + #define mb() dsb(sy) #define rmb() dsb(ld) #define wmb() dsb(st) diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index ed693c5bcec0..2945fe6cd863 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -16,10 +16,12 @@ * 0x400: for dynamic BRK instruction * 0x401: for compile time BRK instruction * 0x800: kernel-mode BUG() and WARN() traps + * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff) */ #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 #define BUG_BRK_IMM 0x800 +#define KASAN_BRK_IMM 0x900 #endif diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 3b0938281541..3f9376f1c409 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -30,46 +30,46 @@ * barrier case is generated as release+dmb for the former and * acquire+release for the latter. */ -#define __XCHG_CASE(w, sz, name, mb, nop_lse, acq, acq_lse, rel, cl) \ -static inline unsigned long __xchg_case_##name(unsigned long x, \ - volatile void *ptr) \ -{ \ - unsigned long ret, tmp; \ - \ - asm volatile(ARM64_LSE_ATOMIC_INSN( \ - /* LL/SC */ \ - " prfm pstl1strm, %2\n" \ - "1: ld" #acq "xr" #sz "\t%" #w "0, %2\n" \ - " st" #rel "xr" #sz "\t%w1, %" #w "3, %2\n" \ - " cbnz %w1, 1b\n" \ - " " #mb, \ - /* LSE atomics */ \ - " swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n" \ - __nops(3) \ - " " #nop_lse) \ - : "=&r" (ret), "=&r" (tmp), "+Q" (*(unsigned long *)ptr) \ - : "r" (x) \ - : cl); \ - \ - return ret; \ +#define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl) \ +static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr) \ +{ \ + u##sz ret; \ + unsigned long tmp; \ + \ + asm volatile(ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + " prfm pstl1strm, %2\n" \ + "1: ld" #acq "xr" #sfx "\t%" #w "0, %2\n" \ + " st" #rel "xr" #sfx "\t%w1, %" #w "3, %2\n" \ + " cbnz %w1, 1b\n" \ + " " #mb, \ + /* LSE atomics */ \ + " swp" #acq_lse #rel #sfx "\t%" #w "3, %" #w "0, %2\n" \ + __nops(3) \ + " " #nop_lse) \ + : "=&r" (ret), "=&r" (tmp), "+Q" (*(u##sz *)ptr) \ + : "r" (x) \ + : cl); \ + \ + return ret; \ } -__XCHG_CASE(w, b, 1, , , , , , ) -__XCHG_CASE(w, h, 2, , , , , , ) -__XCHG_CASE(w, , 4, , , , , , ) -__XCHG_CASE( , , 8, , , , , , ) -__XCHG_CASE(w, b, acq_1, , , a, a, , "memory") -__XCHG_CASE(w, h, acq_2, , , a, a, , "memory") -__XCHG_CASE(w, , acq_4, , , a, a, , "memory") -__XCHG_CASE( , , acq_8, , , a, a, , "memory") -__XCHG_CASE(w, b, rel_1, , , , , l, "memory") -__XCHG_CASE(w, h, rel_2, , , , , l, "memory") -__XCHG_CASE(w, , rel_4, , , , , l, "memory") -__XCHG_CASE( , , rel_8, , , , , l, "memory") -__XCHG_CASE(w, b, mb_1, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, h, mb_2, dmb ish, nop, , a, l, "memory") -__XCHG_CASE(w, , mb_4, dmb ish, nop, , a, l, "memory") -__XCHG_CASE( , , mb_8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, b, , 8, , , , , , ) +__XCHG_CASE(w, h, , 16, , , , , , ) +__XCHG_CASE(w, , , 32, , , , , , ) +__XCHG_CASE( , , , 64, , , , , , ) +__XCHG_CASE(w, b, acq_, 8, , , a, a, , "memory") +__XCHG_CASE(w, h, acq_, 16, , , a, a, , "memory") +__XCHG_CASE(w, , acq_, 32, , , a, a, , "memory") +__XCHG_CASE( , , acq_, 64, , , a, a, , "memory") +__XCHG_CASE(w, b, rel_, 8, , , , , l, "memory") +__XCHG_CASE(w, h, rel_, 16, , , , , l, "memory") +__XCHG_CASE(w, , rel_, 32, , , , , l, "memory") +__XCHG_CASE( , , rel_, 64, , , , , l, "memory") +__XCHG_CASE(w, b, mb_, 8, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, h, mb_, 16, dmb ish, nop, , a, l, "memory") +__XCHG_CASE(w, , mb_, 32, dmb ish, nop, , a, l, "memory") +__XCHG_CASE( , , mb_, 64, dmb ish, nop, , a, l, "memory") #undef __XCHG_CASE @@ -80,13 +80,13 @@ static inline unsigned long __xchg##sfx(unsigned long x, \ { \ switch (size) { \ case 1: \ - return __xchg_case##sfx##_1(x, ptr); \ + return __xchg_case##sfx##_8(x, ptr); \ case 2: \ - return __xchg_case##sfx##_2(x, ptr); \ + return __xchg_case##sfx##_16(x, ptr); \ case 4: \ - return __xchg_case##sfx##_4(x, ptr); \ + return __xchg_case##sfx##_32(x, ptr); \ case 8: \ - return __xchg_case##sfx##_8(x, ptr); \ + return __xchg_case##sfx##_64(x, ptr); \ default: \ BUILD_BUG(); \ } \ @@ -123,13 +123,13 @@ static inline unsigned long __cmpxchg##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpxchg_case##sfx##_1(ptr, (u8)old, new); \ + return __cmpxchg_case##sfx##_8(ptr, old, new); \ case 2: \ - return __cmpxchg_case##sfx##_2(ptr, (u16)old, new); \ + return __cmpxchg_case##sfx##_16(ptr, old, new); \ case 4: \ - return __cmpxchg_case##sfx##_4(ptr, old, new); \ + return __cmpxchg_case##sfx##_32(ptr, old, new); \ case 8: \ - return __cmpxchg_case##sfx##_8(ptr, old, new); \ + return __cmpxchg_case##sfx##_64(ptr, old, new); \ default: \ BUILD_BUG(); \ } \ @@ -197,16 +197,16 @@ __CMPXCHG_GEN(_mb) __ret; \ }) -#define __CMPWAIT_CASE(w, sz, name) \ -static inline void __cmpwait_case_##name(volatile void *ptr, \ - unsigned long val) \ +#define __CMPWAIT_CASE(w, sfx, sz) \ +static inline void __cmpwait_case_##sz(volatile void *ptr, \ + unsigned long val) \ { \ unsigned long tmp; \ \ asm volatile( \ " sevl\n" \ " wfe\n" \ - " ldxr" #sz "\t%" #w "[tmp], %[v]\n" \ + " ldxr" #sfx "\t%" #w "[tmp], %[v]\n" \ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ " cbnz %" #w "[tmp], 1f\n" \ " wfe\n" \ @@ -215,10 +215,10 @@ static inline void __cmpwait_case_##name(volatile void *ptr, \ : [val] "r" (val)); \ } -__CMPWAIT_CASE(w, b, 1); -__CMPWAIT_CASE(w, h, 2); -__CMPWAIT_CASE(w, , 4); -__CMPWAIT_CASE( , , 8); +__CMPWAIT_CASE(w, b, 8); +__CMPWAIT_CASE(w, h, 16); +__CMPWAIT_CASE(w, , 32); +__CMPWAIT_CASE( , , 64); #undef __CMPWAIT_CASE @@ -229,13 +229,13 @@ static inline void __cmpwait##sfx(volatile void *ptr, \ { \ switch (size) { \ case 1: \ - return __cmpwait_case##sfx##_1(ptr, (u8)val); \ + return __cmpwait_case##sfx##_8(ptr, (u8)val); \ case 2: \ - return __cmpwait_case##sfx##_2(ptr, (u16)val); \ + return __cmpwait_case##sfx##_16(ptr, (u16)val); \ case 4: \ - return __cmpwait_case##sfx##_4(ptr, val); \ + return __cmpwait_case##sfx##_32(ptr, val); \ case 8: \ - return __cmpwait_case##sfx##_8(ptr, val); \ + return __cmpwait_case##sfx##_64(ptr, val); \ default: \ BUILD_BUG(); \ } \ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index 6e2d254c09eb..82e9099834ae 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -54,7 +54,13 @@ #define ARM64_HAS_CRC32 33 #define ARM64_SSBS 34 #define ARM64_WORKAROUND_1188873 35 +#define ARM64_HAS_SB 36 +#define ARM64_WORKAROUND_1165522 37 +#define ARM64_HAS_ADDRESS_AUTH_ARCH 38 +#define ARM64_HAS_ADDRESS_AUTH_IMP_DEF 39 +#define ARM64_HAS_GENERIC_AUTH_ARCH 40 +#define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41 -#define ARM64_NCAPS 36 +#define ARM64_NCAPS 42 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 7e2ec64aa414..dfcfba725d72 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -321,19 +321,20 @@ struct arm64_cpu_capabilities { bool sign; unsigned long hwcap; }; - /* - * A list of "matches/cpu_enable" pair for the same - * "capability" of the same "type" as described by the parent. - * Only matches(), cpu_enable() and fields relevant to these - * methods are significant in the list. The cpu_enable is - * invoked only if the corresponding entry "matches()". - * However, if a cpu_enable() method is associated - * with multiple matches(), care should be taken that either - * the match criteria are mutually exclusive, or that the - * method is robust against being called multiple times. - */ - const struct arm64_cpu_capabilities *match_list; }; + + /* + * An optional list of "matches/cpu_enable" pair for the same + * "capability" of the same "type" as described by the parent. + * Only matches(), cpu_enable() and fields relevant to these + * methods are significant in the list. The cpu_enable is + * invoked only if the corresponding entry "matches()". + * However, if a cpu_enable() method is associated + * with multiple matches(), care should be taken that either + * the match criteria are mutually exclusive, or that the + * method is robust against being called multiple times. + */ + const struct arm64_cpu_capabilities *match_list; }; static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) @@ -353,10 +354,46 @@ cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); } +/* + * Generic helper for handling capabilties with multiple (match,enable) pairs + * of call backs, sharing the same capability bit. + * Iterate over each entry to see if at least one matches. + */ +static inline bool +cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, + int scope) +{ + const struct arm64_cpu_capabilities *caps; + + for (caps = entry->match_list; caps->matches; caps++) + if (caps->matches(caps, scope)) + return true; + + return false; +} + +/* + * Take appropriate action for all matching entries in the shared capability + * entry. + */ +static inline void +cpucap_multi_entry_cap_cpu_enable(const struct arm64_cpu_capabilities *entry) +{ + const struct arm64_cpu_capabilities *caps; + + for (caps = entry->match_list; caps->matches; caps++) + if (caps->matches(caps, SCOPE_LOCAL_CPU) && + caps->cpu_enable) + caps->cpu_enable(caps); +} + extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; +#define for_each_available_cap(cap) \ + for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS) + bool this_cpu_has_cap(unsigned int cap); static inline bool cpu_have_feature(unsigned int num) @@ -473,7 +510,6 @@ static inline bool id_aa64pfr0_sve(u64 pfr0) void __init setup_cpu_features(void); void check_local_cpu_capabilities(void); - u64 read_sanitised_ftr_reg(u32 id); static inline bool cpu_supports_mixed_endian_el0(void) @@ -486,11 +522,59 @@ static inline bool system_supports_32bit_el0(void) return cpus_have_const_cap(ARM64_HAS_32BIT_EL0); } +static inline bool system_supports_4kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN4_SHIFT); + + return val == ID_AA64MMFR0_TGRAN4_SUPPORTED; +} + +static inline bool system_supports_64kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN64_SHIFT); + + return val == ID_AA64MMFR0_TGRAN64_SUPPORTED; +} + +static inline bool system_supports_16kb_granule(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_TGRAN16_SHIFT); + + return val == ID_AA64MMFR0_TGRAN16_SUPPORTED; +} + static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } +static inline bool system_supports_mixed_endian(void) +{ + u64 mmfr0; + u32 val; + + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); + val = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_BIGENDEL_SHIFT); + + return val == 0x1; +} + static inline bool system_supports_fpsimd(void) { return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); @@ -514,6 +598,20 @@ static inline bool system_supports_cnp(void) cpus_have_const_cap(ARM64_HAS_CNP); } +static inline bool system_supports_address_auth(void) +{ + return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && + (cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_ARCH) || + cpus_have_const_cap(ARM64_HAS_ADDRESS_AUTH_IMP_DEF)); +} + +static inline bool system_supports_generic_auth(void) +{ + return IS_ENABLED(CONFIG_ARM64_PTR_AUTH) && + (cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_ARCH) || + cpus_have_const_cap(ARM64_HAS_GENERIC_AUTH_IMP_DEF)); +} + #define ARM64_SSBD_UNKNOWN -1 #define ARM64_SSBD_FORCE_DISABLE 0 #define ARM64_SSBD_KERNEL 1 diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 12f93e4d2452..951ed1a4e5c9 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -151,6 +151,8 @@ struct midr_range { .rv_max = MIDR_CPU_VAR_REV(v_max, r_max), \ } +#define MIDR_REV_RANGE(m, v, r_min, r_max) MIDR_RANGE(m, v, r_min, v, r_max) +#define MIDR_REV(m, v, r) MIDR_RANGE(m, v, r, v, r) #define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf) static inline bool is_midr_in_range(u32 midr, struct midr_range const *range) diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index c41f3fb1446c..95dbf3ef735a 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -24,15 +24,9 @@ #include <xen/xen.h> #include <asm/xen/hypervisor.h> -extern const struct dma_map_ops dummy_dma_ops; - static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus) { - /* - * We expect no ISA devices, and all other DMA masters are expected to - * have someone call arch_setup_dma_ops at device creation time. - */ - return &dummy_dma_ops; + return NULL; } void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 433b9554c6a1..6adc1a90e7e6 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -117,7 +117,11 @@ * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ +#ifdef CONFIG_ARM64_FORCE_52BIT #define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) +#else +#define ELF_ET_DYN_BASE (2 * DEFAULT_MAP_WINDOW_64 / 3) +#endif /* CONFIG_ARM64_FORCE_52BIT */ #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 676de2ec1762..52233f00d53d 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -29,23 +29,24 @@ #define ESR_ELx_EC_CP14_MR (0x05) #define ESR_ELx_EC_CP14_LS (0x06) #define ESR_ELx_EC_FP_ASIMD (0x07) -#define ESR_ELx_EC_CP10_ID (0x08) -/* Unallocated EC: 0x09 - 0x0B */ +#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */ +#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */ +/* Unallocated EC: 0x0A - 0x0B */ #define ESR_ELx_EC_CP14_64 (0x0C) /* Unallocated EC: 0x0d */ #define ESR_ELx_EC_ILL (0x0E) /* Unallocated EC: 0x0F - 0x10 */ #define ESR_ELx_EC_SVC32 (0x11) -#define ESR_ELx_EC_HVC32 (0x12) -#define ESR_ELx_EC_SMC32 (0x13) +#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */ +#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */ /* Unallocated EC: 0x14 */ #define ESR_ELx_EC_SVC64 (0x15) -#define ESR_ELx_EC_HVC64 (0x16) -#define ESR_ELx_EC_SMC64 (0x17) +#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */ +#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */ #define ESR_ELx_EC_SYS64 (0x18) #define ESR_ELx_EC_SVE (0x19) /* Unallocated EC: 0x1A - 0x1E */ -#define ESR_ELx_EC_IMP_DEF (0x1f) +#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */ #define ESR_ELx_EC_IABT_LOW (0x20) #define ESR_ELx_EC_IABT_CUR (0x21) #define ESR_ELx_EC_PC_ALIGN (0x22) @@ -68,7 +69,7 @@ /* Unallocated EC: 0x36 - 0x37 */ #define ESR_ELx_EC_BKPT32 (0x38) /* Unallocated EC: 0x39 */ -#define ESR_ELx_EC_VECTOR32 (0x3A) +#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */ /* Unallocted EC: 0x3B */ #define ESR_ELx_EC_BRK64 (0x3C) /* Unallocated EC: 0x3D - 0x3F */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index fac54fb050d0..15a6587e12f9 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -13,6 +13,7 @@ #include <asm/insn.h> +#define HAVE_FUNCTION_GRAPH_FP_TEST #define MCOUNT_ADDR ((unsigned long)_mcount) #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE diff --git a/arch/arm64/include/asm/image.h b/arch/arm64/include/asm/image.h new file mode 100644 index 000000000000..e2c27a2278e9 --- /dev/null +++ b/arch/arm64/include/asm/image.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_IMAGE_H +#define __ASM_IMAGE_H + +#define ARM64_IMAGE_MAGIC "ARM\x64" + +#define ARM64_IMAGE_FLAG_BE_SHIFT 0 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT (ARM64_IMAGE_FLAG_BE_SHIFT + 1) +#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \ + (ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2) +#define ARM64_IMAGE_FLAG_BE_MASK 0x1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK 0x3 +#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK 0x1 + +#define ARM64_IMAGE_FLAG_LE 0 +#define ARM64_IMAGE_FLAG_BE 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K 1 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K 2 +#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K 3 +#define ARM64_IMAGE_FLAG_PHYS_BASE 1 + +#ifndef __ASSEMBLY__ + +#define arm64_image_flag_field(flags, field) \ + (((flags) >> field##_SHIFT) & field##_MASK) + +/* + * struct arm64_image_header - arm64 kernel image header + * See Documentation/arm64/booting.txt for details + * + * @code0: Executable code, or + * @mz_header alternatively used for part of MZ header + * @code1: Executable code + * @text_offset: Image load offset + * @image_size: Effective Image size + * @flags: kernel flags + * @reserved: reserved + * @magic: Magic number + * @reserved5: reserved, or + * @pe_header: alternatively used for PE COFF offset + */ + +struct arm64_image_header { + __le32 code0; + __le32 code1; + __le64 text_offset; + __le64 image_size; + __le64 flags; + __le64 res2; + __le64 res3; + __le64 res4; + __le32 magic; + __le32 res5; +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* __ASM_IMAGE_H */ diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index c6802dea6cab..9c01f04db64d 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -261,6 +261,11 @@ enum aarch64_insn_prfm_policy { AARCH64_INSN_PRFM_POLICY_STRM, }; +enum aarch64_insn_adr_type { + AARCH64_INSN_ADR_TYPE_ADRP, + AARCH64_INSN_ADR_TYPE_ADR, +}; + #define __AARCH64_INSN_FUNCS(abbr, mask, val) \ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \ { return (code & (mask)) == (val); } \ @@ -393,6 +398,9 @@ u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, enum aarch64_insn_adsb_type type); +u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, + enum aarch64_insn_register reg, + enum aarch64_insn_adr_type type); u32 aarch64_insn_gen_bitfield(enum aarch64_insn_register dst, enum aarch64_insn_register src, int immr, int imms, diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 9f8b915af3a7..ee723835c1f4 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -104,7 +104,23 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) } /* IO barriers */ -#define __iormb() rmb() +#define __iormb(v) \ +({ \ + unsigned long tmp; \ + \ + rmb(); \ + \ + /* \ + * Create a dummy control dependency from the IO read to any \ + * later instructions. This ensures that a subsequent call to \ + * udelay() will be ordered due to the ISB in get_cycles(). \ + */ \ + asm volatile("eor %0, %1, %1\n" \ + "cbnz %0, ." \ + : "=r" (tmp) : "r" ((unsigned long)(v)) \ + : "memory"); \ +}) + #define __iowmb() wmb() #define mmiowb() do { } while (0) @@ -129,10 +145,10 @@ static inline u64 __raw_readq(const volatile void __iomem *addr) * following Normal memory access. Writes are ordered relative to any prior * Normal memory access. */ -#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(); __v; }) -#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(); __v; }) -#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(); __v; }) -#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(); __v; }) +#define readb(c) ({ u8 __v = readb_relaxed(c); __iormb(__v); __v; }) +#define readw(c) ({ u16 __v = readw_relaxed(c); __iormb(__v); __v; }) +#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; }) +#define readq(c) ({ u64 __v = readq_relaxed(c); __iormb(__v); __v; }) #define writeb(v,c) ({ __iowmb(); writeb_relaxed((v),(c)); }) #define writew(v,c) ({ __iowmb(); writew_relaxed((v),(c)); }) @@ -183,9 +199,9 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size); /* * io{read,write}{16,32,64}be() macros */ -#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; }) -#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; }) -#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; }) +#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(__v); __v; }) +#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(__v); __v; }) +#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(__v); __v; }) #define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); }) #define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); }) diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 8758bb008436..b52aacd2c526 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -4,12 +4,16 @@ #ifndef __ASSEMBLY__ -#ifdef CONFIG_KASAN - #include <linux/linkage.h> #include <asm/memory.h> #include <asm/pgtable-types.h> +#define arch_kasan_set_tag(addr, tag) __tag_set(addr, tag) +#define arch_kasan_reset_tag(addr) __tag_reset(addr) +#define arch_kasan_get_tag(addr) __tag_get(addr) + +#ifdef CONFIG_KASAN + /* * KASAN_SHADOW_START: beginning of the kernel virtual addresses. * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h index e17f0529a882..67e4cb75d1fd 100644 --- a/arch/arm64/include/asm/kexec.h +++ b/arch/arm64/include/asm/kexec.h @@ -93,6 +93,25 @@ static inline void crash_prepare_suspend(void) {} static inline void crash_post_resume(void) {} #endif +#ifdef CONFIG_KEXEC_FILE +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *dtb; + unsigned long dtb_mem; +}; + +extern const struct kexec_file_ops kexec_image_ops; + +struct kimage; + +extern int arch_kimage_file_post_load_cleanup(struct kimage *image); +extern int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline); +#endif + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 6f602af5263c..7f9d2bfcf82e 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -24,6 +24,8 @@ /* Hyp Configuration Register (HCR) bits */ #define HCR_FWB (UL(1) << 46) +#define HCR_API (UL(1) << 41) +#define HCR_APK (UL(1) << 40) #define HCR_TEA (UL(1) << 37) #define HCR_TERR (UL(1) << 36) #define HCR_TLOR (UL(1) << 35) @@ -87,6 +89,7 @@ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) +#define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ @@ -104,7 +107,7 @@ TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK) /* VTCR_EL2 Registers bits */ -#define VTCR_EL2_RES1 (1 << 31) +#define VTCR_EL2_RES1 (1U << 31) #define VTCR_EL2_HD (1 << 22) #define VTCR_EL2_HA (1 << 21) #define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT @@ -320,10 +323,6 @@ #define PAR_TO_HPFAR(par) \ (((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8) -#define kvm_arm_exception_type \ - {0, "IRQ" }, \ - {1, "TRAP" } - #define ECN(x) { ESR_ELx_EC_##x, #x } #define kvm_arm_exception_class \ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index aea01a09eb94..f5b79e995f40 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -25,6 +25,7 @@ #define ARM_EXIT_WITH_SERROR_BIT 31 #define ARM_EXCEPTION_CODE(x) ((x) & ~(1U << ARM_EXIT_WITH_SERROR_BIT)) +#define ARM_EXCEPTION_IS_TRAP(x) (ARM_EXCEPTION_CODE((x)) == ARM_EXCEPTION_TRAP) #define ARM_SERROR_PENDING(x) !!((x) & (1U << ARM_EXIT_WITH_SERROR_BIT)) #define ARM_EXCEPTION_IRQ 0 @@ -34,6 +35,12 @@ /* The hyp-stub will return this for any kvm_call_hyp() call */ #define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR +#define kvm_arm_exception_type \ + {ARM_EXCEPTION_IRQ, "IRQ" }, \ + {ARM_EXCEPTION_EL1_SERROR, "SERROR" }, \ + {ARM_EXCEPTION_TRAP, "TRAP" }, \ + {ARM_EXCEPTION_HYP_GONE, "HYP_GONE" } + #ifndef __ASSEMBLY__ #include <linux/mm.h> diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 21247870def7..506386a3edde 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -24,6 +24,7 @@ #include <linux/kvm_host.h> +#include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kvm_arm.h> #include <asm/kvm_hyp.h> @@ -147,14 +148,6 @@ static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu) return true; } -static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) -{ - if (vcpu_mode_is_32bit(vcpu)) - kvm_skip_instr32(vcpu, is_wide_instr); - else - *vcpu_pc(vcpu) += 4; -} - static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu) { *vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT; @@ -424,4 +417,30 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, return data; /* Leave LE untouched */ } +static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr) +{ + if (vcpu_mode_is_32bit(vcpu)) + kvm_skip_instr32(vcpu, is_wide_instr); + else + *vcpu_pc(vcpu) += 4; + + /* advance the singlestep state machine */ + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; +} + +/* + * Skip an instruction which has been emulated at hyp while most guest sysregs + * are live. + */ +static inline void __hyp_text __kvm_skip_instr(struct kvm_vcpu *vcpu) +{ + *vcpu_pc(vcpu) = read_sysreg_el2(elr); + vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr); + + kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); + + write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr); + write_sysreg_el2(*vcpu_pc(vcpu), elr); +} + #endif /* __ARM64_KVM_EMULATE_H__ */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 52fbc823ff8c..7732d0ba4e60 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -319,7 +319,7 @@ struct kvm_vcpu_arch { */ #define __vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)]) -u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg); +u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); /* @@ -360,7 +360,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -422,7 +422,7 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, } } -static inline bool kvm_arch_check_sve_has_vhe(void) +static inline bool kvm_arch_requires_vhe(void) { /* * The Arm architecture specifies that implementation of SVE @@ -430,9 +430,13 @@ static inline bool kvm_arch_check_sve_has_vhe(void) * relies on this when SVE is present: */ if (system_supports_sve()) - return has_vhe(); - else return true; + + /* Some implementations have defects that confine them to VHE */ + if (cpus_have_cap(ARM64_WORKAROUND_1165522)) + return true; + + return false; } static inline void kvm_arch_hardware_unsetup(void) {} @@ -445,7 +449,6 @@ void kvm_arm_init_debug(void); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); -bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run); int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 23aca66767f9..a80a7ef57325 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -20,6 +20,7 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> +#include <asm/alternative.h> #include <asm/sysreg.h> #define __hyp_text __section(.hyp.text) notrace @@ -163,6 +164,13 @@ static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm) { write_sysreg(kvm->arch.vtcr, vtcr_el2); write_sysreg(kvm->arch.vttbr, vttbr_el2); + + /* + * ARM erratum 1165522 requires the actual execution of the above + * before we can switch to the EL1/EL0 translation regime used by + * the guest. + */ + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522)); } #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 658657367f2f..8af4b1befa42 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -184,6 +184,17 @@ void kvm_clear_hyp_idmap(void); #define kvm_mk_pgd(pudp) \ __pgd(__phys_to_pgd_val(__pa(pudp)) | PUD_TYPE_TABLE) +#define kvm_set_pud(pudp, pud) set_pud(pudp, pud) + +#define kvm_pfn_pte(pfn, prot) pfn_pte(pfn, prot) +#define kvm_pfn_pmd(pfn, prot) pfn_pmd(pfn, prot) +#define kvm_pfn_pud(pfn, prot) pfn_pud(pfn, prot) + +#define kvm_pud_pfn(pud) pud_pfn(pud) + +#define kvm_pmd_mkhuge(pmd) pmd_mkhuge(pmd) +#define kvm_pud_mkhuge(pud) pud_mkhuge(pud) + static inline pte_t kvm_s2pte_mkwrite(pte_t pte) { pte_val(pte) |= PTE_S2_RDWR; @@ -196,6 +207,12 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd) return pmd; } +static inline pud_t kvm_s2pud_mkwrite(pud_t pud) +{ + pud_val(pud) |= PUD_S2_RDWR; + return pud; +} + static inline pte_t kvm_s2pte_mkexec(pte_t pte) { pte_val(pte) &= ~PTE_S2_XN; @@ -208,6 +225,12 @@ static inline pmd_t kvm_s2pmd_mkexec(pmd_t pmd) return pmd; } +static inline pud_t kvm_s2pud_mkexec(pud_t pud) +{ + pud_val(pud) &= ~PUD_S2_XN; + return pud; +} + static inline void kvm_set_s2pte_readonly(pte_t *ptep) { pteval_t old_pteval, pteval; @@ -246,6 +269,31 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp) return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN); } +static inline void kvm_set_s2pud_readonly(pud_t *pudp) +{ + kvm_set_s2pte_readonly((pte_t *)pudp); +} + +static inline bool kvm_s2pud_readonly(pud_t *pudp) +{ + return kvm_s2pte_readonly((pte_t *)pudp); +} + +static inline bool kvm_s2pud_exec(pud_t *pudp) +{ + return !(READ_ONCE(pud_val(*pudp)) & PUD_S2_XN); +} + +static inline pud_t kvm_s2pud_mkyoung(pud_t pud) +{ + return pud_mkyoung(pud); +} + +static inline bool kvm_s2pud_young(pud_t pud) +{ + return pud_young(pud); +} + #define hyp_pte_table_empty(ptep) kvm_page_empty(ptep) #ifdef __PAGETABLE_PMD_FOLDED diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index b96442960aea..e1ec947e7c0c 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -35,15 +35,6 @@ #define PCI_IO_SIZE SZ_16M /* - * Log2 of the upper bound of the size of a struct page. Used for sizing - * the vmemmap region only, does not affect actual memory footprint. - * We don't use sizeof(struct page) directly since taking its size here - * requires its definition to be available at this point in the inclusion - * chain, and it may not be a power of 2 in the first place. - */ -#define STRUCT_PAGE_MAX_SHIFT 6 - -/* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array */ @@ -62,8 +53,11 @@ #define PAGE_OFFSET (UL(0xffffffffffffffff) - \ (UL(1) << (VA_BITS - 1)) + 1) #define KIMAGE_VADDR (MODULES_END) +#define BPF_JIT_REGION_START (VA_START + KASAN_SHADOW_SIZE) +#define BPF_JIT_REGION_SIZE (SZ_128M) +#define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) -#define MODULES_VADDR (VA_START + KASAN_SHADOW_SIZE) +#define MODULES_VADDR (BPF_JIT_REGION_END) #define MODULES_VSIZE (SZ_128M) #define VMEMMAP_START (PAGE_OFFSET - VMEMMAP_SIZE) #define PCI_IO_END (VMEMMAP_START - SZ_2M) @@ -73,15 +67,24 @@ #define KERNEL_START _text #define KERNEL_END _end +#ifdef CONFIG_ARM64_USER_VA_BITS_52 +#define MAX_USER_VA_BITS 52 +#else +#define MAX_USER_VA_BITS VA_BITS +#endif + /* - * KASAN requires 1/8th of the kernel virtual address space for the shadow - * region. KASAN can bloat the stack significantly, so double the (minimum) - * stack size when KASAN is in use. + * Generic and tag-based KASAN require 1/8th and 1/16th of the kernel virtual + * address space for the shadow region respectively. They can bloat the stack + * significantly, so double the (minimum) stack size when they are in use. */ #ifdef CONFIG_KASAN -#define KASAN_SHADOW_SCALE_SHIFT 3 #define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT)) +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_THREAD_SHIFT 2 +#else #define KASAN_THREAD_SHIFT 1 +#endif /* CONFIG_KASAN_EXTRA */ #else #define KASAN_SHADOW_SIZE (0) #define KASAN_THREAD_SHIFT 0 @@ -168,14 +171,6 @@ #define IOREMAP_MAX_ORDER (PMD_SHIFT) #endif -#ifdef CONFIG_BLK_DEV_INITRD -#define __early_init_dt_declare_initrd(__start, __end) \ - do { \ - initrd_start = (__start); \ - initrd_end = (__end); \ - } while (0) -#endif - #ifndef __ASSEMBLY__ #include <linux/bitops.h> @@ -196,6 +191,9 @@ static inline unsigned long kaslr_offset(void) return kimage_vaddr - KIMAGE_VADDR; } +/* the actual size of a user virtual address */ +extern u64 vabits_user; + /* * Allow all memory at the discovery stage. We will clip it later. */ @@ -213,6 +211,26 @@ static inline unsigned long kaslr_offset(void) #define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) /* + * When dealing with data aborts, watchpoints, or instruction traps we may end + * up with a tagged userland pointer. Clear the tag to get a sane pointer to + * pass on to access_ok(), for instance. + */ +#define untagged_addr(addr) \ + ((__typeof__(addr))sign_extend64((u64)(addr), 55)) + +#ifdef CONFIG_KASAN_SW_TAGS +#define __tag_shifted(tag) ((u64)(tag) << 56) +#define __tag_set(addr, tag) (__typeof__(addr))( \ + ((u64)(addr) & ~__tag_shifted(0xff)) | __tag_shifted(tag)) +#define __tag_reset(addr) untagged_addr(addr) +#define __tag_get(addr) (__u8)((u64)(addr) >> 56) +#else +#define __tag_set(addr, tag) (addr) +#define __tag_reset(addr) (addr) +#define __tag_get(addr) 0 +#endif + +/* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. @@ -295,7 +313,13 @@ static inline void *phys_to_virt(phys_addr_t x) #define __virt_to_pgoff(kaddr) (((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page)) #define __page_to_voff(kaddr) (((u64)(kaddr) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page)) -#define page_to_virt(page) ((void *)((__page_to_voff(page)) | PAGE_OFFSET)) +#define page_to_virt(page) ({ \ + unsigned long __addr = \ + ((__page_to_voff(page)) | PAGE_OFFSET); \ + __addr = __tag_set(__addr, page_kasan_tag(page)); \ + ((void *)__addr); \ +}) + #define virt_to_page(vaddr) ((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START)) #define _virt_addr_valid(kaddr) pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \ @@ -303,9 +327,10 @@ static inline void *phys_to_virt(phys_addr_t x) #endif #endif -#define _virt_addr_is_linear(kaddr) (((u64)(kaddr)) >= PAGE_OFFSET) -#define virt_addr_valid(kaddr) (_virt_addr_is_linear(kaddr) && \ - _virt_addr_valid(kaddr)) +#define _virt_addr_is_linear(kaddr) \ + (__tag_reset((u64)(kaddr)) >= PAGE_OFFSET) +#define virt_addr_valid(kaddr) \ + (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) #include <asm-generic/memory_model.h> diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 1e58bf58c22b..2da3e478fd8f 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -35,6 +35,8 @@ #include <asm/sysreg.h> #include <asm/tlbflush.h> +extern bool rodata_full; + static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) @@ -72,6 +74,9 @@ extern u64 idmap_ptrs_per_pgd; static inline bool __cpu_uses_extended_idmap(void) { + if (IS_ENABLED(CONFIG_ARM64_USER_VA_BITS_52)) + return false; + return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS)); } diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 97d0ef12e2ff..905e1bb0e7bd 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -22,7 +22,7 @@ #ifdef CONFIG_ARM64_MODULE_PLTS struct mod_plt_sec { - struct elf64_shdr *plt; + int plt_shndx; int plt_num_entries; int plt_max_entries; }; @@ -36,10 +36,12 @@ struct mod_arch_specific { }; #endif -u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela, +u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, + void *loc, const Elf64_Rela *rela, Elf64_Sym *sym); -u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val); +u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs, + void *loc, u64 val); #ifdef CONFIG_RANDOMIZE_BASE extern u64 module_alloc_base; @@ -56,39 +58,19 @@ struct plt_entry { * is exactly what we are dealing with here, we are free to use x16 * as a scratch register in the PLT veneers. */ - __le32 mov0; /* movn x16, #0x.... */ - __le32 mov1; /* movk x16, #0x...., lsl #16 */ - __le32 mov2; /* movk x16, #0x...., lsl #32 */ + __le32 adrp; /* adrp x16, .... */ + __le32 add; /* add x16, x16, #0x.... */ __le32 br; /* br x16 */ }; -static inline struct plt_entry get_plt_entry(u64 val) +static inline bool is_forbidden_offset_for_adrp(void *place) { - /* - * MOVK/MOVN/MOVZ opcode: - * +--------+------------+--------+-----------+-------------+---------+ - * | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] | - * +--------+------------+--------+-----------+-------------+---------+ - * - * Rd := 0x10 (x16) - * hw := 0b00 (no shift), 0b01 (lsl #16), 0b10 (lsl #32) - * opc := 0b11 (MOVK), 0b00 (MOVN), 0b10 (MOVZ) - * sf := 1 (64-bit variant) - */ - return (struct plt_entry){ - cpu_to_le32(0x92800010 | (((~val ) & 0xffff)) << 5), - cpu_to_le32(0xf2a00010 | ((( val >> 16) & 0xffff)) << 5), - cpu_to_le32(0xf2c00010 | ((( val >> 32) & 0xffff)) << 5), - cpu_to_le32(0xd61f0200) - }; + return IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) && + cpus_have_const_cap(ARM64_WORKAROUND_843419) && + ((u64)place & 0xfff) >= 0xff8; } -static inline bool plt_entries_equal(const struct plt_entry *a, - const struct plt_entry *b) -{ - return a->mov0 == b->mov0 && - a->mov1 == b->mov1 && - a->mov2 == b->mov2; -} +struct plt_entry get_plt_entry(u64 dst, void *pc); +bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b); #endif /* __ASM_MODULE_H */ diff --git a/arch/arm64/include/asm/neon-intrinsics.h b/arch/arm64/include/asm/neon-intrinsics.h new file mode 100644 index 000000000000..2ba6c6b9541f --- /dev/null +++ b/arch/arm64/include/asm/neon-intrinsics.h @@ -0,0 +1,39 @@ +/* + * Copyright (C) 2018 Linaro, Ltd. <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_NEON_INTRINSICS_H +#define __ASM_NEON_INTRINSICS_H + +#include <asm-generic/int-ll64.h> + +/* + * In the kernel, u64/s64 are [un]signed long long, not [un]signed long. + * So by redefining these macros to the former, we can force gcc-stdint.h + * to define uint64_t / in64_t in a compatible manner. + */ + +#ifdef __INT64_TYPE__ +#undef __INT64_TYPE__ +#define __INT64_TYPE__ long long +#endif + +#ifdef __UINT64_TYPE__ +#undef __UINT64_TYPE__ +#define __UINT64_TYPE__ unsigned long long +#endif + +/* + * genksyms chokes on the ARM NEON instrinsics system header, but we + * don't export anything it defines anyway, so just disregard when + * genksyms execute. + */ +#ifndef __GENKSYMS__ +#include <arm_neon.h> +#endif + +#endif /* __ASM_NEON_INTRINSICS_H */ diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 21a81b59a0cc..6b81dd8cee01 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -48,263 +48,193 @@ static inline unsigned long __my_cpu_offset(void) } #define __my_cpu_offset __my_cpu_offset() -#define PERCPU_OP(op, asm_op) \ -static inline unsigned long __percpu_##op(void *ptr, \ - unsigned long val, int size) \ +#define PERCPU_RW_OPS(sz) \ +static inline unsigned long __percpu_read_##sz(void *ptr) \ { \ - unsigned long loop, ret; \ + return READ_ONCE(*(u##sz *)ptr); \ +} \ \ - switch (size) { \ - case 1: \ - asm ("//__per_cpu_" #op "_1\n" \ - "1: ldxrb %w[ret], %[ptr]\n" \ - #asm_op " %w[ret], %w[ret], %w[val]\n" \ - " stxrb %w[loop], %w[ret], %[ptr]\n" \ - " cbnz %w[loop], 1b" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u8 *)ptr) \ - : [val] "Ir" (val)); \ - break; \ - case 2: \ - asm ("//__per_cpu_" #op "_2\n" \ - "1: ldxrh %w[ret], %[ptr]\n" \ - #asm_op " %w[ret], %w[ret], %w[val]\n" \ - " stxrh %w[loop], %w[ret], %[ptr]\n" \ - " cbnz %w[loop], 1b" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u16 *)ptr) \ - : [val] "Ir" (val)); \ - break; \ - case 4: \ - asm ("//__per_cpu_" #op "_4\n" \ - "1: ldxr %w[ret], %[ptr]\n" \ - #asm_op " %w[ret], %w[ret], %w[val]\n" \ - " stxr %w[loop], %w[ret], %[ptr]\n" \ - " cbnz %w[loop], 1b" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u32 *)ptr) \ - : [val] "Ir" (val)); \ - break; \ - case 8: \ - asm ("//__per_cpu_" #op "_8\n" \ - "1: ldxr %[ret], %[ptr]\n" \ - #asm_op " %[ret], %[ret], %[val]\n" \ - " stxr %w[loop], %[ret], %[ptr]\n" \ - " cbnz %w[loop], 1b" \ - : [loop] "=&r" (loop), [ret] "=&r" (ret), \ - [ptr] "+Q"(*(u64 *)ptr) \ - : [val] "Ir" (val)); \ - break; \ - default: \ - ret = 0; \ - BUILD_BUG(); \ - } \ - \ - return ret; \ -} - -PERCPU_OP(add, add) -PERCPU_OP(and, and) -PERCPU_OP(or, orr) -#undef PERCPU_OP - -static inline unsigned long __percpu_read(void *ptr, int size) -{ - unsigned long ret; - - switch (size) { - case 1: - ret = READ_ONCE(*(u8 *)ptr); - break; - case 2: - ret = READ_ONCE(*(u16 *)ptr); - break; - case 4: - ret = READ_ONCE(*(u32 *)ptr); - break; - case 8: - ret = READ_ONCE(*(u64 *)ptr); - break; - default: - ret = 0; - BUILD_BUG(); - } - - return ret; +static inline void __percpu_write_##sz(void *ptr, unsigned long val) \ +{ \ + WRITE_ONCE(*(u##sz *)ptr, (u##sz)val); \ } -static inline void __percpu_write(void *ptr, unsigned long val, int size) -{ - switch (size) { - case 1: - WRITE_ONCE(*(u8 *)ptr, (u8)val); - break; - case 2: - WRITE_ONCE(*(u16 *)ptr, (u16)val); - break; - case 4: - WRITE_ONCE(*(u32 *)ptr, (u32)val); - break; - case 8: - WRITE_ONCE(*(u64 *)ptr, (u64)val); - break; - default: - BUILD_BUG(); - } +#define __PERCPU_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \ +static inline void \ +__percpu_##name##_case_##sz(void *ptr, unsigned long val) \ +{ \ + unsigned int loop; \ + u##sz tmp; \ + \ + asm volatile (ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + "1: ldxr" #sfx "\t%" #w "[tmp], %[ptr]\n" \ + #op_llsc "\t%" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \ + " stxr" #sfx "\t%w[loop], %" #w "[tmp], %[ptr]\n" \ + " cbnz %w[loop], 1b", \ + /* LSE atomics */ \ + #op_lse "\t%" #w "[val], %[ptr]\n" \ + __nops(3)) \ + : [loop] "=&r" (loop), [tmp] "=&r" (tmp), \ + [ptr] "+Q"(*(u##sz *)ptr) \ + : [val] "r" ((u##sz)(val))); \ } -static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, - int size) -{ - unsigned long ret, loop; - - switch (size) { - case 1: - asm ("//__percpu_xchg_1\n" - "1: ldxrb %w[ret], %[ptr]\n" - " stxrb %w[loop], %w[val], %[ptr]\n" - " cbnz %w[loop], 1b" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u8 *)ptr) - : [val] "r" (val)); - break; - case 2: - asm ("//__percpu_xchg_2\n" - "1: ldxrh %w[ret], %[ptr]\n" - " stxrh %w[loop], %w[val], %[ptr]\n" - " cbnz %w[loop], 1b" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u16 *)ptr) - : [val] "r" (val)); - break; - case 4: - asm ("//__percpu_xchg_4\n" - "1: ldxr %w[ret], %[ptr]\n" - " stxr %w[loop], %w[val], %[ptr]\n" - " cbnz %w[loop], 1b" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u32 *)ptr) - : [val] "r" (val)); - break; - case 8: - asm ("//__percpu_xchg_8\n" - "1: ldxr %[ret], %[ptr]\n" - " stxr %w[loop], %[val], %[ptr]\n" - " cbnz %w[loop], 1b" - : [loop] "=&r"(loop), [ret] "=&r"(ret), - [ptr] "+Q"(*(u64 *)ptr) - : [val] "r" (val)); - break; - default: - ret = 0; - BUILD_BUG(); - } - - return ret; +#define __PERCPU_RET_OP_CASE(w, sfx, name, sz, op_llsc, op_lse) \ +static inline u##sz \ +__percpu_##name##_return_case_##sz(void *ptr, unsigned long val) \ +{ \ + unsigned int loop; \ + u##sz ret; \ + \ + asm volatile (ARM64_LSE_ATOMIC_INSN( \ + /* LL/SC */ \ + "1: ldxr" #sfx "\t%" #w "[ret], %[ptr]\n" \ + #op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \ + " stxr" #sfx "\t%w[loop], %" #w "[ret], %[ptr]\n" \ + " cbnz %w[loop], 1b", \ + /* LSE atomics */ \ + #op_lse "\t%" #w "[val], %" #w "[ret], %[ptr]\n" \ + #op_llsc "\t%" #w "[ret], %" #w "[ret], %" #w "[val]\n" \ + __nops(2)) \ + : [loop] "=&r" (loop), [ret] "=&r" (ret), \ + [ptr] "+Q"(*(u##sz *)ptr) \ + : [val] "r" ((u##sz)(val))); \ + \ + return ret; \ } -/* this_cpu_cmpxchg */ -#define _protect_cmpxchg_local(pcp, o, n) \ -({ \ - typeof(*raw_cpu_ptr(&(pcp))) __ret; \ - preempt_disable(); \ - __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \ - preempt_enable(); \ - __ret; \ -}) - -#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define PERCPU_OP(name, op_llsc, op_lse) \ + __PERCPU_OP_CASE(w, b, name, 8, op_llsc, op_lse) \ + __PERCPU_OP_CASE(w, h, name, 16, op_llsc, op_lse) \ + __PERCPU_OP_CASE(w, , name, 32, op_llsc, op_lse) \ + __PERCPU_OP_CASE( , , name, 64, op_llsc, op_lse) + +#define PERCPU_RET_OP(name, op_llsc, op_lse) \ + __PERCPU_RET_OP_CASE(w, b, name, 8, op_llsc, op_lse) \ + __PERCPU_RET_OP_CASE(w, h, name, 16, op_llsc, op_lse) \ + __PERCPU_RET_OP_CASE(w, , name, 32, op_llsc, op_lse) \ + __PERCPU_RET_OP_CASE( , , name, 64, op_llsc, op_lse) + +PERCPU_RW_OPS(8) +PERCPU_RW_OPS(16) +PERCPU_RW_OPS(32) +PERCPU_RW_OPS(64) +PERCPU_OP(add, add, stadd) +PERCPU_OP(andnot, bic, stclr) +PERCPU_OP(or, orr, stset) +PERCPU_RET_OP(add, add, ldadd) + +#undef PERCPU_RW_OPS +#undef __PERCPU_OP_CASE +#undef __PERCPU_RET_OP_CASE +#undef PERCPU_OP +#undef PERCPU_RET_OP +/* + * It would be nice to avoid the conditional call into the scheduler when + * re-enabling preemption for preemptible kernels, but doing that in a way + * which builds inside a module would mean messing directly with the preempt + * count. If you do this, peterz and tglx will hunt you down. + */ #define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ ({ \ int __ret; \ - preempt_disable(); \ + preempt_disable_notrace(); \ __ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \ raw_cpu_ptr(&(ptr2)), \ o1, o2, n1, n2); \ - preempt_enable(); \ + preempt_enable_notrace(); \ __ret; \ }) -#define _percpu_read(pcp) \ +#define _pcp_protect(op, pcp, ...) \ ({ \ - typeof(pcp) __retval; \ preempt_disable_notrace(); \ - __retval = (typeof(pcp))__percpu_read(raw_cpu_ptr(&(pcp)), \ - sizeof(pcp)); \ + op(raw_cpu_ptr(&(pcp)), __VA_ARGS__); \ preempt_enable_notrace(); \ - __retval; \ }) -#define _percpu_write(pcp, val) \ -do { \ +#define _pcp_protect_return(op, pcp, args...) \ +({ \ + typeof(pcp) __retval; \ preempt_disable_notrace(); \ - __percpu_write(raw_cpu_ptr(&(pcp)), (unsigned long)(val), \ - sizeof(pcp)); \ + __retval = (typeof(pcp))op(raw_cpu_ptr(&(pcp)), ##args); \ preempt_enable_notrace(); \ -} while(0) \ - -#define _pcp_protect(operation, pcp, val) \ -({ \ - typeof(pcp) __retval; \ - preempt_disable(); \ - __retval = (typeof(pcp))operation(raw_cpu_ptr(&(pcp)), \ - (val), sizeof(pcp)); \ - preempt_enable(); \ - __retval; \ + __retval; \ }) -#define _percpu_add(pcp, val) \ - _pcp_protect(__percpu_add, pcp, val) - -#define _percpu_add_return(pcp, val) _percpu_add(pcp, val) - -#define _percpu_and(pcp, val) \ - _pcp_protect(__percpu_and, pcp, val) - -#define _percpu_or(pcp, val) \ - _pcp_protect(__percpu_or, pcp, val) - -#define _percpu_xchg(pcp, val) (typeof(pcp)) \ - _pcp_protect(__percpu_xchg, pcp, (unsigned long)(val)) - -#define this_cpu_add_1(pcp, val) _percpu_add(pcp, val) -#define this_cpu_add_2(pcp, val) _percpu_add(pcp, val) -#define this_cpu_add_4(pcp, val) _percpu_add(pcp, val) -#define this_cpu_add_8(pcp, val) _percpu_add(pcp, val) - -#define this_cpu_add_return_1(pcp, val) _percpu_add_return(pcp, val) -#define this_cpu_add_return_2(pcp, val) _percpu_add_return(pcp, val) -#define this_cpu_add_return_4(pcp, val) _percpu_add_return(pcp, val) -#define this_cpu_add_return_8(pcp, val) _percpu_add_return(pcp, val) - -#define this_cpu_and_1(pcp, val) _percpu_and(pcp, val) -#define this_cpu_and_2(pcp, val) _percpu_and(pcp, val) -#define this_cpu_and_4(pcp, val) _percpu_and(pcp, val) -#define this_cpu_and_8(pcp, val) _percpu_and(pcp, val) - -#define this_cpu_or_1(pcp, val) _percpu_or(pcp, val) -#define this_cpu_or_2(pcp, val) _percpu_or(pcp, val) -#define this_cpu_or_4(pcp, val) _percpu_or(pcp, val) -#define this_cpu_or_8(pcp, val) _percpu_or(pcp, val) - -#define this_cpu_read_1(pcp) _percpu_read(pcp) -#define this_cpu_read_2(pcp) _percpu_read(pcp) -#define this_cpu_read_4(pcp) _percpu_read(pcp) -#define this_cpu_read_8(pcp) _percpu_read(pcp) - -#define this_cpu_write_1(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_2(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_4(pcp, val) _percpu_write(pcp, val) -#define this_cpu_write_8(pcp, val) _percpu_write(pcp, val) - -#define this_cpu_xchg_1(pcp, val) _percpu_xchg(pcp, val) -#define this_cpu_xchg_2(pcp, val) _percpu_xchg(pcp, val) -#define this_cpu_xchg_4(pcp, val) _percpu_xchg(pcp, val) -#define this_cpu_xchg_8(pcp, val) _percpu_xchg(pcp, val) +#define this_cpu_read_1(pcp) \ + _pcp_protect_return(__percpu_read_8, pcp) +#define this_cpu_read_2(pcp) \ + _pcp_protect_return(__percpu_read_16, pcp) +#define this_cpu_read_4(pcp) \ + _pcp_protect_return(__percpu_read_32, pcp) +#define this_cpu_read_8(pcp) \ + _pcp_protect_return(__percpu_read_64, pcp) + +#define this_cpu_write_1(pcp, val) \ + _pcp_protect(__percpu_write_8, pcp, (unsigned long)val) +#define this_cpu_write_2(pcp, val) \ + _pcp_protect(__percpu_write_16, pcp, (unsigned long)val) +#define this_cpu_write_4(pcp, val) \ + _pcp_protect(__percpu_write_32, pcp, (unsigned long)val) +#define this_cpu_write_8(pcp, val) \ + _pcp_protect(__percpu_write_64, pcp, (unsigned long)val) + +#define this_cpu_add_1(pcp, val) \ + _pcp_protect(__percpu_add_case_8, pcp, val) +#define this_cpu_add_2(pcp, val) \ + _pcp_protect(__percpu_add_case_16, pcp, val) +#define this_cpu_add_4(pcp, val) \ + _pcp_protect(__percpu_add_case_32, pcp, val) +#define this_cpu_add_8(pcp, val) \ + _pcp_protect(__percpu_add_case_64, pcp, val) + +#define this_cpu_add_return_1(pcp, val) \ + _pcp_protect_return(__percpu_add_return_case_8, pcp, val) +#define this_cpu_add_return_2(pcp, val) \ + _pcp_protect_return(__percpu_add_return_case_16, pcp, val) +#define this_cpu_add_return_4(pcp, val) \ + _pcp_protect_return(__percpu_add_return_case_32, pcp, val) +#define this_cpu_add_return_8(pcp, val) \ + _pcp_protect_return(__percpu_add_return_case_64, pcp, val) + +#define this_cpu_and_1(pcp, val) \ + _pcp_protect(__percpu_andnot_case_8, pcp, ~val) +#define this_cpu_and_2(pcp, val) \ + _pcp_protect(__percpu_andnot_case_16, pcp, ~val) +#define this_cpu_and_4(pcp, val) \ + _pcp_protect(__percpu_andnot_case_32, pcp, ~val) +#define this_cpu_and_8(pcp, val) \ + _pcp_protect(__percpu_andnot_case_64, pcp, ~val) + +#define this_cpu_or_1(pcp, val) \ + _pcp_protect(__percpu_or_case_8, pcp, val) +#define this_cpu_or_2(pcp, val) \ + _pcp_protect(__percpu_or_case_16, pcp, val) +#define this_cpu_or_4(pcp, val) \ + _pcp_protect(__percpu_or_case_32, pcp, val) +#define this_cpu_or_8(pcp, val) \ + _pcp_protect(__percpu_or_case_64, pcp, val) + +#define this_cpu_xchg_1(pcp, val) \ + _pcp_protect_return(xchg_relaxed, pcp, val) +#define this_cpu_xchg_2(pcp, val) \ + _pcp_protect_return(xchg_relaxed, pcp, val) +#define this_cpu_xchg_4(pcp, val) \ + _pcp_protect_return(xchg_relaxed, pcp, val) +#define this_cpu_xchg_8(pcp, val) \ + _pcp_protect_return(xchg_relaxed, pcp, val) + +#define this_cpu_cmpxchg_1(pcp, o, n) \ + _pcp_protect_return(cmpxchg_relaxed, pcp, o, n) +#define this_cpu_cmpxchg_2(pcp, o, n) \ + _pcp_protect_return(cmpxchg_relaxed, pcp, o, n) +#define this_cpu_cmpxchg_4(pcp, o, n) \ + _pcp_protect_return(cmpxchg_relaxed, pcp, o, n) +#define this_cpu_cmpxchg_8(pcp, o, n) \ + _pcp_protect_return(cmpxchg_relaxed, pcp, o, n) #include <asm-generic/percpu.h> diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h index f9ccc36d3dc3..c593761ba61c 100644 --- a/arch/arm64/include/asm/perf_event.h +++ b/arch/arm64/include/asm/perf_event.h @@ -24,6 +24,160 @@ #define ARMV8_PMU_COUNTER_MASK (ARMV8_PMU_MAX_COUNTERS - 1) /* + * Common architectural and microarchitectural event numbers. + */ +#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x00 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x01 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x02 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x03 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x04 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x05 +#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x06 +#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x07 +#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x08 +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x09 +#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x0A +#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x0B +#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x0C +#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x0D +#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x0E +#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x0F +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x10 +#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x11 +#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x12 +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x13 +#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x14 +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x15 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x16 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x17 +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x18 +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x19 +#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x1A +#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x1B +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x1C +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x1D +#define ARMV8_PMUV3_PERFCTR_CHAIN 0x1E +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x1F +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x20 +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x21 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x22 +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x23 +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x24 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x25 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x26 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x27 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x28 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x29 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x2A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x2B +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x2C +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x2D +#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x2E +#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x2F +#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x30 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS 0x31 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE 0x32 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS 0x33 +#define ARMV8_PMUV3_PERFCTR_DTLB_WALK 0x34 +#define ARMV8_PMUV3_PERFCTR_ITLB_WALK 0x35 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_RD 0x36 +#define ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD 0x37 +#define ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD 0x38 + +/* Statistical profiling extension microarchitectural events */ +#define ARMV8_SPE_PERFCTR_SAMPLE_POP 0x4000 +#define ARMV8_SPE_PERFCTR_SAMPLE_FEED 0x4001 +#define ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE 0x4002 +#define ARMV8_SPE_PERFCTR_SAMPLE_COLLISION 0x4003 + +/* ARMv8 recommended implementation defined event types */ +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x40 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x41 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x42 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x43 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x44 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x45 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x46 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x47 +#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x48 + +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x4C +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x4D +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x4E +#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x4F +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x50 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x51 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x52 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x53 + +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x56 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x57 +#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x58 + +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x5C +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x5D +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x5E +#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x5F +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x60 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x61 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x62 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x63 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x64 +#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x65 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x66 +#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x67 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x68 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x69 +#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x6A + +#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x6C +#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x6D +#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x6E +#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x6F +#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x70 +#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x71 +#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x72 +#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x73 +#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x74 +#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x75 +#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x76 +#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x77 +#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x78 +#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x79 +#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x7A + +#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x7C +#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x7D +#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x7E + +#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x81 +#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x82 +#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x83 +#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x84 + +#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x86 +#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x87 +#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x88 + +#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x8A +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x8B +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x8C +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x8D +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x8E +#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x8F +#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x90 +#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x91 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0xA0 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0xA1 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0xA2 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0xA3 + +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0xA6 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0xA7 +#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0xA8 + +/* * Per-CPU PMCR: config reg */ #define ARMV8_PMU_PMCR_E (1 << 0) /* Enable all counters */ @@ -50,21 +204,11 @@ #define ARMV8_PMU_EVTYPE_EVENT 0xffff /* Mask for EVENT bits */ /* - * PMUv3 event types: required events - */ -#define ARMV8_PMUV3_PERFCTR_SW_INCR 0x00 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL 0x03 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE 0x04 -#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED 0x10 -#define ARMV8_PMUV3_PERFCTR_CPU_CYCLES 0x11 -#define ARMV8_PMUV3_PERFCTR_BR_PRED 0x12 - -/* * Event filters for PMUv3 */ -#define ARMV8_PMU_EXCLUDE_EL1 (1 << 31) -#define ARMV8_PMU_EXCLUDE_EL0 (1 << 30) -#define ARMV8_PMU_INCLUDE_EL2 (1 << 27) +#define ARMV8_PMU_EXCLUDE_EL1 (1U << 31) +#define ARMV8_PMU_EXCLUDE_EL0 (1U << 30) +#define ARMV8_PMU_INCLUDE_EL2 (1U << 27) /* * PMUSERENR: user enable reg diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 1d7d8da2ef9b..e9b0a7d75184 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -80,7 +80,7 @@ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) #define PGDIR_MASK (~(PGDIR_SIZE-1)) -#define PTRS_PER_PGD (1 << (VA_BITS - PGDIR_SHIFT)) +#define PTRS_PER_PGD (1 << (MAX_USER_VA_BITS - PGDIR_SHIFT)) /* * Section address mask and size definitions. @@ -193,6 +193,10 @@ #define PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ #define PMD_S2_XN (_AT(pmdval_t, 2) << 53) /* XN[1:0] */ +#define PUD_S2_RDONLY (_AT(pudval_t, 1) << 6) /* HAP[2:1] */ +#define PUD_S2_RDWR (_AT(pudval_t, 3) << 6) /* HAP[2:1] */ +#define PUD_S2_XN (_AT(pudval_t, 2) << 53) /* XN[1:0] */ + /* * Memory Attribute override for Stage-2 (MemAttr[3:0]) */ @@ -224,6 +228,8 @@ #define TCR_TxSZ_WIDTH 6 #define TCR_T0SZ_MASK (((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET) +#define TCR_EPD0_SHIFT 7 +#define TCR_EPD0_MASK (UL(1) << TCR_EPD0_SHIFT) #define TCR_IRGN0_SHIFT 8 #define TCR_IRGN0_MASK (UL(3) << TCR_IRGN0_SHIFT) #define TCR_IRGN0_NC (UL(0) << TCR_IRGN0_SHIFT) @@ -231,6 +237,8 @@ #define TCR_IRGN0_WT (UL(2) << TCR_IRGN0_SHIFT) #define TCR_IRGN0_WBnWA (UL(3) << TCR_IRGN0_SHIFT) +#define TCR_EPD1_SHIFT 23 +#define TCR_EPD1_MASK (UL(1) << TCR_EPD1_SHIFT) #define TCR_IRGN1_SHIFT 24 #define TCR_IRGN1_MASK (UL(3) << TCR_IRGN1_SHIFT) #define TCR_IRGN1_NC (UL(0) << TCR_IRGN1_SHIFT) @@ -291,6 +299,7 @@ #define TCR_A1 (UL(1) << 22) #define TCR_ASID16 (UL(1) << 36) #define TCR_TBI0 (UL(1) << 37) +#define TCR_TBI1 (UL(1) << 38) #define TCR_HA (UL(1) << 39) #define TCR_HD (UL(1) << 40) #define TCR_NFD1 (UL(1) << 54) @@ -306,4 +315,10 @@ #define TTBR_BADDR_MASK_52 (((UL(1) << 46) - 1) << 2) #endif +#ifdef CONFIG_ARM64_USER_VA_BITS_52 +/* Must be at least 64-byte aligned to prevent corruption of the TTBR */ +#define TTBR1_BADDR_4852_OFFSET (((UL(1) << (52 - PGDIR_SHIFT)) - \ + (UL(1) << (48 - PGDIR_SHIFT))) * 8) +#endif + #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 50b1ef8584c0..de70c1eabf33 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -22,6 +22,7 @@ #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable-prot.h> +#include <asm/tlbflush.h> /* * VMALLOC range. @@ -314,6 +315,11 @@ static inline pte_t pud_pte(pud_t pud) return __pte(pud_val(pud)); } +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} + static inline pmd_t pud_pmd(pud_t pud) { return __pmd(pud_val(pud)); @@ -381,8 +387,12 @@ static inline int pmd_protnone(pmd_t pmd) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) +#define pud_young(pud) pte_young(pud_pte(pud)) +#define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) +#define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) + #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) @@ -685,6 +695,27 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, return __ptep_test_and_clear_young(ptep); } +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +static inline int ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + int young = ptep_test_and_clear_young(vma, address, ptep); + + if (young) { + /* + * We can elide the trailing DSB here since the worst that can + * happen is that a CPU continues to use the young entry in its + * TLB and we mistakenly reclaim the associated page. The + * window for such an event is bounded by the next + * context-switch, which provides a DSB to complete the TLB + * invalidation. + */ + flush_tlb_page_nosync(vma, address); + } + + return young; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h new file mode 100644 index 000000000000..15d49515efdd --- /dev/null +++ b/arch/arm64/include/asm/pointer_auth.h @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __ASM_POINTER_AUTH_H +#define __ASM_POINTER_AUTH_H + +#include <linux/bitops.h> +#include <linux/random.h> + +#include <asm/cpufeature.h> +#include <asm/memory.h> +#include <asm/sysreg.h> + +#ifdef CONFIG_ARM64_PTR_AUTH +/* + * Each key is a 128-bit quantity which is split across a pair of 64-bit + * registers (Lo and Hi). + */ +struct ptrauth_key { + unsigned long lo, hi; +}; + +/* + * We give each process its own keys, which are shared by all threads. The keys + * are inherited upon fork(), and reinitialised upon exec*(). + */ +struct ptrauth_keys { + struct ptrauth_key apia; + struct ptrauth_key apib; + struct ptrauth_key apda; + struct ptrauth_key apdb; + struct ptrauth_key apga; +}; + +static inline void ptrauth_keys_init(struct ptrauth_keys *keys) +{ + if (system_supports_address_auth()) { + get_random_bytes(&keys->apia, sizeof(keys->apia)); + get_random_bytes(&keys->apib, sizeof(keys->apib)); + get_random_bytes(&keys->apda, sizeof(keys->apda)); + get_random_bytes(&keys->apdb, sizeof(keys->apdb)); + } + + if (system_supports_generic_auth()) + get_random_bytes(&keys->apga, sizeof(keys->apga)); +} + +#define __ptrauth_key_install(k, v) \ +do { \ + struct ptrauth_key __pki_v = (v); \ + write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1); \ + write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1); \ +} while (0) + +static inline void ptrauth_keys_switch(struct ptrauth_keys *keys) +{ + if (system_supports_address_auth()) { + __ptrauth_key_install(APIA, keys->apia); + __ptrauth_key_install(APIB, keys->apib); + __ptrauth_key_install(APDA, keys->apda); + __ptrauth_key_install(APDB, keys->apdb); + } + + if (system_supports_generic_auth()) + __ptrauth_key_install(APGA, keys->apga); +} + +extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg); + +/* + * The EL0 pointer bits used by a pointer authentication code. + * This is dependent on TBI0 being enabled, or bits 63:56 would also apply. + */ +#define ptrauth_user_pac_mask() GENMASK(54, vabits_user) + +/* Only valid for EL0 TTBR0 instruction pointers */ +static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr) +{ + return ptr & ~ptrauth_user_pac_mask(); +} + +#define ptrauth_thread_init_user(tsk) \ +do { \ + struct task_struct *__ptiu_tsk = (tsk); \ + ptrauth_keys_init(&__ptiu_tsk->thread.keys_user); \ + ptrauth_keys_switch(&__ptiu_tsk->thread.keys_user); \ +} while (0) + +#define ptrauth_thread_switch(tsk) \ + ptrauth_keys_switch(&(tsk)->thread.keys_user) + +#else /* CONFIG_ARM64_PTR_AUTH */ +#define ptrauth_prctl_reset_keys(tsk, arg) (-EINVAL) +#define ptrauth_strip_insn_pac(lr) (lr) +#define ptrauth_thread_init_user(tsk) +#define ptrauth_thread_switch(tsk) +#endif /* CONFIG_ARM64_PTR_AUTH */ + +#endif /* __ASM_POINTER_AUTH_H */ diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h new file mode 100644 index 000000000000..d49951647014 --- /dev/null +++ b/arch/arm64/include/asm/preempt.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_PREEMPT_H +#define __ASM_PREEMPT_H + +#include <linux/thread_info.h> + +#define PREEMPT_NEED_RESCHED BIT(32) +#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED) + +static inline int preempt_count(void) +{ + return READ_ONCE(current_thread_info()->preempt.count); +} + +static inline void preempt_count_set(u64 pc) +{ + /* Preserve existing value of PREEMPT_NEED_RESCHED */ + WRITE_ONCE(current_thread_info()->preempt.count, pc); +} + +#define init_task_preempt_count(p) do { \ + task_thread_info(p)->preempt_count = FORK_PREEMPT_COUNT; \ +} while (0) + +#define init_idle_preempt_count(p, cpu) do { \ + task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \ +} while (0) + +static inline void set_preempt_need_resched(void) +{ + current_thread_info()->preempt.need_resched = 0; +} + +static inline void clear_preempt_need_resched(void) +{ + current_thread_info()->preempt.need_resched = 1; +} + +static inline bool test_preempt_need_resched(void) +{ + return !current_thread_info()->preempt.need_resched; +} + +static inline void __preempt_count_add(int val) +{ + u32 pc = READ_ONCE(current_thread_info()->preempt.count); + pc += val; + WRITE_ONCE(current_thread_info()->preempt.count, pc); +} + +static inline void __preempt_count_sub(int val) +{ + u32 pc = READ_ONCE(current_thread_info()->preempt.count); + pc -= val; + WRITE_ONCE(current_thread_info()->preempt.count, pc); +} + +static inline bool __preempt_count_dec_and_test(void) +{ + struct thread_info *ti = current_thread_info(); + u64 pc = READ_ONCE(ti->preempt_count); + + /* Update only the count field, leaving need_resched unchanged */ + WRITE_ONCE(ti->preempt.count, --pc); + + /* + * If we wrote back all zeroes, then we're preemptible and in + * need of a reschedule. Otherwise, we need to reload the + * preempt_count in case the need_resched flag was cleared by an + * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE + * pair. + */ + return !pc || !READ_ONCE(ti->preempt_count); +} + +static inline bool should_resched(int preempt_offset) +{ + u64 pc = READ_ONCE(current_thread_info()->preempt_count); + return pc == preempt_offset; +} + +#ifdef CONFIG_PREEMPT +void preempt_schedule(void); +#define __preempt_schedule() preempt_schedule() +void preempt_schedule_notrace(void); +#define __preempt_schedule_notrace() preempt_schedule_notrace() +#endif /* CONFIG_PREEMPT */ + +#endif /* __ASM_PREEMPT_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 6b0d4dff5012..f1a7ab18faf3 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -19,10 +19,8 @@ #ifndef __ASM_PROCESSOR_H #define __ASM_PROCESSOR_H -#define TASK_SIZE_64 (UL(1) << VA_BITS) - -#define KERNEL_DS UL(-1) -#define USER_DS (TASK_SIZE_64 - 1) +#define KERNEL_DS UL(-1) +#define USER_DS ((UL(1) << MAX_USER_VA_BITS) - 1) /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is @@ -46,6 +44,7 @@ #include <asm/hw_breakpoint.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> +#include <asm/pointer_auth.h> #include <asm/ptrace.h> #include <asm/types.h> @@ -53,19 +52,31 @@ * TASK_SIZE - the maximum size of a user space task. * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area. */ + +#define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS) +#define TASK_SIZE_64 (UL(1) << vabits_user) + #ifdef CONFIG_COMPAT #define TASK_SIZE_32 UL(0x100000000) #define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) #define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \ TASK_SIZE_32 : TASK_SIZE_64) +#define DEFAULT_MAP_WINDOW (test_thread_flag(TIF_32BIT) ? \ + TASK_SIZE_32 : DEFAULT_MAP_WINDOW_64) #else #define TASK_SIZE TASK_SIZE_64 +#define DEFAULT_MAP_WINDOW DEFAULT_MAP_WINDOW_64 #endif /* CONFIG_COMPAT */ +#ifdef CONFIG_ARM64_FORCE_52BIT +#define STACK_TOP_MAX TASK_SIZE_64 #define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 4)) +#else +#define STACK_TOP_MAX DEFAULT_MAP_WINDOW_64 +#define TASK_UNMAPPED_BASE (PAGE_ALIGN(DEFAULT_MAP_WINDOW / 4)) +#endif /* CONFIG_ARM64_FORCE_52BIT */ -#define STACK_TOP_MAX TASK_SIZE_64 #ifdef CONFIG_COMPAT #define AARCH32_VECTORS_BASE 0xffff0000 #define STACK_TOP (test_thread_flag(TIF_32BIT) ? \ @@ -74,6 +85,15 @@ #define STACK_TOP STACK_TOP_MAX #endif /* CONFIG_COMPAT */ +#ifndef CONFIG_ARM64_FORCE_52BIT +#define arch_get_mmap_end(addr) ((addr > DEFAULT_MAP_WINDOW) ? TASK_SIZE :\ + DEFAULT_MAP_WINDOW) + +#define arch_get_mmap_base(addr, base) ((addr > DEFAULT_MAP_WINDOW) ? \ + base + TASK_SIZE - DEFAULT_MAP_WINDOW :\ + base) +#endif /* CONFIG_ARM64_FORCE_52BIT */ + extern phys_addr_t arm64_dma_phys_limit; #define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) @@ -127,6 +147,9 @@ struct thread_struct { unsigned long fault_address; /* fault info */ unsigned long fault_code; /* ESR_EL1 value */ struct debug_info debug; /* debugging */ +#ifdef CONFIG_ARM64_PTR_AUTH + struct ptrauth_keys keys_user; +#endif }; static inline void arch_thread_struct_whitelist(unsigned long *offset, @@ -270,6 +293,9 @@ extern void __init minsigstksz_setup(void); #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() +/* PR_PAC_RESET_KEYS prctl */ +#define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg) + /* * For CONFIG_GCC_PLUGIN_STACKLEAK * diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h index f82b447bd34f..1895561839a9 100644 --- a/arch/arm64/include/asm/smp.h +++ b/arch/arm64/include/asm/smp.h @@ -17,15 +17,20 @@ #define __ASM_SMP_H /* Values for secondary_data.status */ +#define CPU_STUCK_REASON_SHIFT (8) +#define CPU_BOOT_STATUS_MASK ((1U << CPU_STUCK_REASON_SHIFT) - 1) -#define CPU_MMU_OFF (-1) -#define CPU_BOOT_SUCCESS (0) +#define CPU_MMU_OFF (-1) +#define CPU_BOOT_SUCCESS (0) /* The cpu invoked ops->cpu_die, synchronise it with cpu_kill */ -#define CPU_KILL_ME (1) +#define CPU_KILL_ME (1) /* The cpu couldn't die gracefully and is looping in the kernel */ -#define CPU_STUCK_IN_KERNEL (2) +#define CPU_STUCK_IN_KERNEL (2) /* Fatal system error detected by secondary CPU, crash the system */ -#define CPU_PANIC_KERNEL (3) +#define CPU_PANIC_KERNEL (3) + +#define CPU_STUCK_REASON_52_BIT_VA (1U << CPU_STUCK_REASON_SHIFT) +#define CPU_STUCK_REASON_NO_GRAN (2U << CPU_STUCK_REASON_SHIFT) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/stackprotector.h b/arch/arm64/include/asm/stackprotector.h index 58d15be11c4d..5884a2b02827 100644 --- a/arch/arm64/include/asm/stackprotector.h +++ b/arch/arm64/include/asm/stackprotector.h @@ -34,7 +34,8 @@ static __always_inline void boot_init_stack_canary(void) canary &= CANARY_MASK; current->stack_canary = canary; - __stack_chk_guard = current->stack_canary; + if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK)) + __stack_chk_guard = current->stack_canary; } #endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h index d352f6df8d2c..5412fa40825e 100644 --- a/arch/arm64/include/asm/stage2_pgtable.h +++ b/arch/arm64/include/asm/stage2_pgtable.h @@ -30,16 +30,14 @@ #define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls)) /* - * The hardware supports concatenation of up to 16 tables at stage2 entry level - * and we use the feature whenever possible. + * The hardware supports concatenation of up to 16 tables at stage2 entry + * level and we use the feature whenever possible, which means we resolve 4 + * additional bits of address at the entry level. * - * Now, the minimum number of bits resolved at any level is (PAGE_SHIFT - 3). - * On arm64, the smallest PAGE_SIZE supported is 4k, which means - * (PAGE_SHIFT - 3) > 4 holds for all page sizes. - * This implies, the total number of page table levels at stage2 expected - * by the hardware is actually the number of levels required for (IPA_SHIFT - 4) - * in normal translations(e.g, stage1), since we cannot have another level in - * the range (IPA_SHIFT, IPA_SHIFT - 4). + * This implies, the total number of page table levels required for + * IPA_SHIFT at stage2 expected by the hardware can be calculated using + * the same logic used for the (non-collapsable) stage1 page tables but for + * (IPA_SHIFT - 4). */ #define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4) #define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 842fb9572661..72dc4c011014 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -20,6 +20,7 @@ #ifndef __ASM_SYSREG_H #define __ASM_SYSREG_H +#include <linux/const.h> #include <linux/stringify.h> /* @@ -104,6 +105,11 @@ #define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift)) #define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift)) +#define __SYS_BARRIER_INSN(CRm, op2, Rt) \ + __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f)) + +#define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31) + #define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2) #define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2) #define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2) @@ -183,6 +189,19 @@ #define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1) #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2) +#define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) +#define SYS_APIAKEYHI_EL1 sys_reg(3, 0, 2, 1, 1) +#define SYS_APIBKEYLO_EL1 sys_reg(3, 0, 2, 1, 2) +#define SYS_APIBKEYHI_EL1 sys_reg(3, 0, 2, 1, 3) + +#define SYS_APDAKEYLO_EL1 sys_reg(3, 0, 2, 2, 0) +#define SYS_APDAKEYHI_EL1 sys_reg(3, 0, 2, 2, 1) +#define SYS_APDBKEYLO_EL1 sys_reg(3, 0, 2, 2, 2) +#define SYS_APDBKEYHI_EL1 sys_reg(3, 0, 2, 2, 3) + +#define SYS_APGAKEYLO_EL1 sys_reg(3, 0, 2, 3, 0) +#define SYS_APGAKEYHI_EL1 sys_reg(3, 0, 2, 3, 1) + #define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) #define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0) @@ -431,27 +450,31 @@ #define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7) /* Common SCTLR_ELx flags. */ -#define SCTLR_ELx_DSSBS (1UL << 44) -#define SCTLR_ELx_EE (1 << 25) -#define SCTLR_ELx_IESB (1 << 21) -#define SCTLR_ELx_WXN (1 << 19) -#define SCTLR_ELx_I (1 << 12) -#define SCTLR_ELx_SA (1 << 3) -#define SCTLR_ELx_C (1 << 2) -#define SCTLR_ELx_A (1 << 1) -#define SCTLR_ELx_M 1 +#define SCTLR_ELx_DSSBS (_BITUL(44)) +#define SCTLR_ELx_ENIA (_BITUL(31)) +#define SCTLR_ELx_ENIB (_BITUL(30)) +#define SCTLR_ELx_ENDA (_BITUL(27)) +#define SCTLR_ELx_EE (_BITUL(25)) +#define SCTLR_ELx_IESB (_BITUL(21)) +#define SCTLR_ELx_WXN (_BITUL(19)) +#define SCTLR_ELx_ENDB (_BITUL(13)) +#define SCTLR_ELx_I (_BITUL(12)) +#define SCTLR_ELx_SA (_BITUL(3)) +#define SCTLR_ELx_C (_BITUL(2)) +#define SCTLR_ELx_A (_BITUL(1)) +#define SCTLR_ELx_M (_BITUL(0)) #define SCTLR_ELx_FLAGS (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \ SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_IESB) /* SCTLR_EL2 specific flags. */ -#define SCTLR_EL2_RES1 ((1 << 4) | (1 << 5) | (1 << 11) | (1 << 16) | \ - (1 << 18) | (1 << 22) | (1 << 23) | (1 << 28) | \ - (1 << 29)) -#define SCTLR_EL2_RES0 ((1 << 6) | (1 << 7) | (1 << 8) | (1 << 9) | \ - (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \ - (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \ - (1 << 27) | (1 << 30) | (1 << 31) | \ +#define SCTLR_EL2_RES1 ((_BITUL(4)) | (_BITUL(5)) | (_BITUL(11)) | (_BITUL(16)) | \ + (_BITUL(18)) | (_BITUL(22)) | (_BITUL(23)) | (_BITUL(28)) | \ + (_BITUL(29))) +#define SCTLR_EL2_RES0 ((_BITUL(6)) | (_BITUL(7)) | (_BITUL(8)) | (_BITUL(9)) | \ + (_BITUL(10)) | (_BITUL(13)) | (_BITUL(14)) | (_BITUL(15)) | \ + (_BITUL(17)) | (_BITUL(20)) | (_BITUL(24)) | (_BITUL(26)) | \ + (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \ (0xffffefffUL << 32)) #ifdef CONFIG_CPU_BIG_ENDIAN @@ -473,23 +496,23 @@ #endif /* SCTLR_EL1 specific flags. */ -#define SCTLR_EL1_UCI (1 << 26) -#define SCTLR_EL1_E0E (1 << 24) -#define SCTLR_EL1_SPAN (1 << 23) -#define SCTLR_EL1_NTWE (1 << 18) -#define SCTLR_EL1_NTWI (1 << 16) -#define SCTLR_EL1_UCT (1 << 15) -#define SCTLR_EL1_DZE (1 << 14) -#define SCTLR_EL1_UMA (1 << 9) -#define SCTLR_EL1_SED (1 << 8) -#define SCTLR_EL1_ITD (1 << 7) -#define SCTLR_EL1_CP15BEN (1 << 5) -#define SCTLR_EL1_SA0 (1 << 4) - -#define SCTLR_EL1_RES1 ((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \ - (1 << 29)) -#define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \ - (1 << 27) | (1 << 30) | (1 << 31) | \ +#define SCTLR_EL1_UCI (_BITUL(26)) +#define SCTLR_EL1_E0E (_BITUL(24)) +#define SCTLR_EL1_SPAN (_BITUL(23)) +#define SCTLR_EL1_NTWE (_BITUL(18)) +#define SCTLR_EL1_NTWI (_BITUL(16)) +#define SCTLR_EL1_UCT (_BITUL(15)) +#define SCTLR_EL1_DZE (_BITUL(14)) +#define SCTLR_EL1_UMA (_BITUL(9)) +#define SCTLR_EL1_SED (_BITUL(8)) +#define SCTLR_EL1_ITD (_BITUL(7)) +#define SCTLR_EL1_CP15BEN (_BITUL(5)) +#define SCTLR_EL1_SA0 (_BITUL(4)) + +#define SCTLR_EL1_RES1 ((_BITUL(11)) | (_BITUL(20)) | (_BITUL(22)) | (_BITUL(28)) | \ + (_BITUL(29))) +#define SCTLR_EL1_RES0 ((_BITUL(6)) | (_BITUL(10)) | (_BITUL(13)) | (_BITUL(17)) | \ + (_BITUL(27)) | (_BITUL(30)) | (_BITUL(31)) | \ (0xffffefffUL << 32)) #ifdef CONFIG_CPU_BIG_ENDIAN @@ -528,11 +551,25 @@ #define ID_AA64ISAR0_AES_SHIFT 4 /* id_aa64isar1 */ +#define ID_AA64ISAR1_SB_SHIFT 36 +#define ID_AA64ISAR1_GPI_SHIFT 28 +#define ID_AA64ISAR1_GPA_SHIFT 24 #define ID_AA64ISAR1_LRCPC_SHIFT 20 #define ID_AA64ISAR1_FCMA_SHIFT 16 #define ID_AA64ISAR1_JSCVT_SHIFT 12 +#define ID_AA64ISAR1_API_SHIFT 8 +#define ID_AA64ISAR1_APA_SHIFT 4 #define ID_AA64ISAR1_DPB_SHIFT 0 +#define ID_AA64ISAR1_APA_NI 0x0 +#define ID_AA64ISAR1_APA_ARCHITECTED 0x1 +#define ID_AA64ISAR1_API_NI 0x0 +#define ID_AA64ISAR1_API_IMP_DEF 0x1 +#define ID_AA64ISAR1_GPA_NI 0x0 +#define ID_AA64ISAR1_GPA_ARCHITECTED 0x1 +#define ID_AA64ISAR1_GPI_NI 0x0 +#define ID_AA64ISAR1_GPI_IMP_DEF 0x1 + /* id_aa64pfr0 */ #define ID_AA64PFR0_CSV3_SHIFT 60 #define ID_AA64PFR0_CSV2_SHIFT 56 @@ -676,13 +713,13 @@ #define ZCR_ELx_LEN_SIZE 9 #define ZCR_ELx_LEN_MASK 0x1ff -#define CPACR_EL1_ZEN_EL1EN (1 << 16) /* enable EL1 access */ -#define CPACR_EL1_ZEN_EL0EN (1 << 17) /* enable EL0 access, if EL1EN set */ +#define CPACR_EL1_ZEN_EL1EN (_BITUL(16)) /* enable EL1 access */ +#define CPACR_EL1_ZEN_EL0EN (_BITUL(17)) /* enable EL0 access, if EL1EN set */ #define CPACR_EL1_ZEN (CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN) /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ -#define SYS_MPIDR_SAFE_VAL (1UL << 31) +#define SYS_MPIDR_SAFE_VAL (_BITUL(31)) #ifdef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index cb2c10a8f0a8..bbca68b54732 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -42,7 +42,18 @@ struct thread_info { #ifdef CONFIG_ARM64_SW_TTBR0_PAN u64 ttbr0; /* saved TTBR0_EL1 */ #endif - int preempt_count; /* 0 => preemptable, <0 => bug */ + union { + u64 preempt_count; /* 0 => preemptible, <0 => bug */ + struct { +#ifdef CONFIG_CPU_BIG_ENDIAN + u32 need_resched; + u32 count; +#else + u32 count; + u32 need_resched; +#endif + } preempt; + }; }; #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 5dfd23897dea..3a1870228946 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -21,6 +21,7 @@ #ifndef __ASSEMBLY__ +#include <linux/mm_types.h> #include <linux/sched.h> #include <asm/cputype.h> #include <asm/mmu.h> @@ -164,14 +165,20 @@ static inline void flush_tlb_mm(struct mm_struct *mm) dsb(ish); } -static inline void flush_tlb_page(struct vm_area_struct *vma, - unsigned long uaddr) +static inline void flush_tlb_page_nosync(struct vm_area_struct *vma, + unsigned long uaddr) { unsigned long addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); dsb(ishst); __tlbi(vale1is, addr); __tlbi_user(vale1is, addr); +} + +static inline void flush_tlb_page(struct vm_area_struct *vma, + unsigned long uaddr) +{ + flush_tlb_page_nosync(vma, uaddr); dsb(ish); } @@ -179,7 +186,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, * This is meant to avoid soft lock-ups on large TLB flushing ranges and not * necessarily a performance improvement. */ -#define MAX_TLBI_OPS 1024UL +#define MAX_TLBI_OPS PTRS_PER_PTE static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, @@ -188,7 +195,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long asid = ASID(vma->vm_mm); unsigned long addr; - if ((end - start) > (MAX_TLBI_OPS * stride)) { + if ((end - start) >= (MAX_TLBI_OPS * stride)) { flush_tlb_mm(vma->vm_mm); return; } diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 07c34087bd5e..ed252435fd92 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -45,8 +45,7 @@ static inline void set_fs(mm_segment_t fs) * Prevent a mispredicted conditional call to set_fs from forwarding * the wrong address limit to access_ok under speculation. */ - dsb(nsh); - isb(); + spec_bar(); /* On user-mode return, check fs is correct */ set_thread_flag(TIF_FSCHECK); @@ -96,13 +95,6 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si return ret; } -/* - * When dealing with data aborts, watchpoints, or instruction traps we may end - * up with a tagged userland pointer. Clear the tag to get a sane pointer to - * pass on to access_ok(), for instance. - */ -#define untagged_addr(addr) sign_extend64(addr, 55) - #define access_ok(type, addr, size) __range_ok(addr, size) #define user_addr_max get_fs diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h new file mode 100644 index 000000000000..856386ad076c --- /dev/null +++ b/arch/arm64/include/asm/xor.h @@ -0,0 +1,73 @@ +/* + * arch/arm64/include/asm/xor.h + * + * Authors: Jackie Liu <liuyun01@kylinos.cn> + * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/hardirq.h> +#include <asm-generic/xor.h> +#include <asm/hwcap.h> +#include <asm/neon.h> + +#ifdef CONFIG_KERNEL_MODE_NEON + +extern struct xor_block_template const xor_block_inner_neon; + +static void +xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_2(bytes, p1, p2); + kernel_neon_end(); +} + +static void +xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_3(bytes, p1, p2, p3); + kernel_neon_end(); +} + +static void +xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4); + kernel_neon_end(); +} + +static void +xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, + unsigned long *p3, unsigned long *p4, unsigned long *p5) +{ + kernel_neon_begin(); + xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5); + kernel_neon_end(); +} + +static struct xor_block_template xor_block_arm64 = { + .name = "arm64_neon", + .do_2 = xor_neon_2, + .do_3 = xor_neon_3, + .do_4 = xor_neon_4, + .do_5 = xor_neon_5 +}; +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ + do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_32regs); \ + if (cpu_has_neon()) { \ + xor_speed(&xor_block_arm64);\ + } \ + } while (0) + +#endif /* ! CONFIG_KERNEL_MODE_NEON */ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 2bcd6e4f3474..5f0750c2199c 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -49,5 +49,8 @@ #define HWCAP_ILRCPC (1 << 26) #define HWCAP_FLAGM (1 << 27) #define HWCAP_SSBS (1 << 28) +#define HWCAP_SB (1 << 29) +#define HWCAP_PACA (1 << 30) +#define HWCAP_PACG (1UL << 31) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index a36227fdb084..c2f249bcd829 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -229,6 +229,13 @@ struct user_sve_header { SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) +/* pointer authentication masks (NT_ARM_PAC_MASK) */ + +struct user_pac_mask { + __u64 data_mask; + __u64 insn_mask; +}; + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 4c8b13bede80..df08d735b21d 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -30,7 +30,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ sys_compat.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o -arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o +arm64-obj-$(CONFIG_MODULES) += module.o arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o arm64-obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o arm64-obj-$(CONFIG_HW_PERF_EVENTS) += perf_event.o @@ -49,14 +49,16 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o -arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ +arm64-obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ cpu-reset.o +arm64-obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o +arm64-obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c deleted file mode 100644 index 72f63a59b008..000000000000 --- a/arch/arm64/kernel/arm64ksyms.c +++ /dev/null @@ -1,88 +0,0 @@ -/* - * Based on arch/arm/kernel/armksyms.c - * - * Copyright (C) 2000 Russell King - * Copyright (C) 2012 ARM Ltd. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/export.h> -#include <linux/sched.h> -#include <linux/string.h> -#include <linux/cryptohash.h> -#include <linux/delay.h> -#include <linux/in6.h> -#include <linux/syscalls.h> -#include <linux/uaccess.h> -#include <linux/io.h> -#include <linux/arm-smccc.h> -#include <linux/kprobes.h> - -#include <asm/checksum.h> - -EXPORT_SYMBOL(copy_page); -EXPORT_SYMBOL(clear_page); - - /* user mem (segment) */ -EXPORT_SYMBOL(__arch_copy_from_user); -EXPORT_SYMBOL(__arch_copy_to_user); -EXPORT_SYMBOL(__arch_clear_user); -EXPORT_SYMBOL(__arch_copy_in_user); - - /* physical memory */ -EXPORT_SYMBOL(memstart_addr); - - /* string / mem functions */ -#ifndef CONFIG_KASAN -EXPORT_SYMBOL(strchr); -EXPORT_SYMBOL(strrchr); -EXPORT_SYMBOL(strcmp); -EXPORT_SYMBOL(strncmp); -EXPORT_SYMBOL(strlen); -EXPORT_SYMBOL(strnlen); -EXPORT_SYMBOL(memcmp); -EXPORT_SYMBOL(memchr); -#endif - -EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(memcpy); -EXPORT_SYMBOL(memmove); -EXPORT_SYMBOL(__memset); -EXPORT_SYMBOL(__memcpy); -EXPORT_SYMBOL(__memmove); - - /* atomic bitops */ -EXPORT_SYMBOL(set_bit); -EXPORT_SYMBOL(test_and_set_bit); -EXPORT_SYMBOL(clear_bit); -EXPORT_SYMBOL(test_and_clear_bit); -EXPORT_SYMBOL(change_bit); -EXPORT_SYMBOL(test_and_change_bit); - -#ifdef CONFIG_FUNCTION_TRACER -EXPORT_SYMBOL(_mcount); -NOKPROBE_SYMBOL(_mcount); -#endif - - /* arm-smccc */ -EXPORT_SYMBOL(__arm_smccc_smc); -EXPORT_SYMBOL(__arm_smccc_hvc); - - /* tishift.S */ -extern long long __ashlti3(long long a, int b); -EXPORT_SYMBOL(__ashlti3); -extern long long __ashrti3(long long a, int b); -EXPORT_SYMBOL(__ashrti3); -extern long long __lshrti3(long long a, int b); -EXPORT_SYMBOL(__lshrti3); diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 323aeb5f2fe6..65b8afc84466 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -46,6 +46,9 @@ int main(void) DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); #endif DEFINE(TSK_STACK, offsetof(struct task_struct, stack)); +#ifdef CONFIG_STACKPROTECTOR + DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); +#endif BLANK(); DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context)); BLANK(); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 8021b46c9743..a2be30275a73 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -22,11 +22,11 @@ * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for * cpu_soft_restart. * - * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @el2_switch: Flag to indicate a switch to EL2 is needed. * @entry: Location to jump to for soft reset. - * arg0: First argument passed to @entry. - * arg1: Second argument passed to @entry. - * arg2: Third argument passed to @entry. + * arg0: First argument passed to @entry. (relocation list) + * arg1: Second argument passed to @entry.(physical kernel entry) + * arg2: Third argument passed to @entry. (physical dtb address) * * Put the CPU into the same state as it would be if it had been reset, and * branch to what would be the reset vector. It must be executed with the diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6ad715d67df8..09ac548c9d44 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -135,7 +135,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, const char *hyp_vecs_start, const char *hyp_vecs_end) { - static DEFINE_SPINLOCK(bp_lock); + static DEFINE_RAW_SPINLOCK(bp_lock); int cpu, slot = -1; /* @@ -147,7 +147,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, return; } - spin_lock(&bp_lock); + raw_spin_lock(&bp_lock); for_each_possible_cpu(cpu) { if (per_cpu(bp_hardening_data.fn, cpu) == fn) { slot = per_cpu(bp_hardening_data.hyp_vectors_slot, cpu); @@ -163,7 +163,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn, __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); __this_cpu_write(bp_hardening_data.fn, fn); - spin_unlock(&bp_lock); + raw_spin_unlock(&bp_lock); } #else #define __smccc_workaround_1_smc_start NULL @@ -507,38 +507,6 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused) .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, \ CAP_MIDR_RANGE_LIST(midr_list) -/* - * Generic helper for handling capabilties with multiple (match,enable) pairs - * of call backs, sharing the same capability bit. - * Iterate over each entry to see if at least one matches. - */ -static bool __maybe_unused -multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope) -{ - const struct arm64_cpu_capabilities *caps; - - for (caps = entry->match_list; caps->matches; caps++) - if (caps->matches(caps, scope)) - return true; - - return false; -} - -/* - * Take appropriate action for all matching entries in the shared capability - * entry. - */ -static void __maybe_unused -multi_entry_cap_cpu_enable(const struct arm64_cpu_capabilities *entry) -{ - const struct arm64_cpu_capabilities *caps; - - for (caps = entry->match_list; caps->matches; caps++) - if (caps->matches(caps, SCOPE_LOCAL_CPU) && - caps->cpu_enable) - caps->cpu_enable(caps); -} - #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR /* @@ -584,24 +552,63 @@ static const struct midr_range arm64_repeat_tlbi_cpus[] = { #endif -const struct arm64_cpu_capabilities arm64_errata[] = { +#ifdef CONFIG_CAVIUM_ERRATUM_27456 +static const struct midr_range cavium_erratum_27456_cpus[] = { + /* Cavium ThunderX, T88 pass 1.x - 2.1 */ + MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 1), + /* Cavium ThunderX, T81 pass 1.0 */ + MIDR_REV(MIDR_THUNDERX_81XX, 0, 0), + {}, +}; +#endif + +#ifdef CONFIG_CAVIUM_ERRATUM_30115 +static const struct midr_range cavium_erratum_30115_cpus[] = { + /* Cavium ThunderX, T88 pass 1.x - 2.2 */ + MIDR_RANGE(MIDR_THUNDERX, 0, 0, 1, 2), + /* Cavium ThunderX, T81 pass 1.0 - 1.2 */ + MIDR_REV_RANGE(MIDR_THUNDERX_81XX, 0, 0, 2), + /* Cavium ThunderX, T83 pass 1.0 */ + MIDR_REV(MIDR_THUNDERX_83XX, 0, 0), + {}, +}; +#endif + +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 +static const struct arm64_cpu_capabilities qcom_erratum_1003_list[] = { + { + ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0), + }, + { + .midr_range.model = MIDR_QCOM_KRYO, + .matches = is_kryo_midr, + }, + {}, +}; +#endif + +#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE +static const struct midr_range workaround_clean_cache[] = { #if defined(CONFIG_ARM64_ERRATUM_826319) || \ defined(CONFIG_ARM64_ERRATUM_827319) || \ defined(CONFIG_ARM64_ERRATUM_824069) - { - /* Cortex-A53 r0p[012] */ - .desc = "ARM errata 826319, 827319, 824069", - .capability = ARM64_WORKAROUND_CLEAN_CACHE, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 2), - .cpu_enable = cpu_enable_cache_maint_trap, - }, + /* Cortex-A53 r0p[012]: ARM errata 826319, 827319, 824069 */ + MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 2), +#endif +#ifdef CONFIG_ARM64_ERRATUM_819472 + /* Cortex-A53 r0p[01] : ARM errata 819472 */ + MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 1), #endif -#ifdef CONFIG_ARM64_ERRATUM_819472 + {}, +}; +#endif + +const struct arm64_cpu_capabilities arm64_errata[] = { +#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { - /* Cortex-A53 r0p[01] */ - .desc = "ARM errata 819472", + .desc = "ARM errata 826319, 827319, 824069, 819472", .capability = ARM64_WORKAROUND_CLEAN_CACHE, - ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 1), + ERRATA_MIDR_RANGE_LIST(workaround_clean_cache), .cpu_enable = cpu_enable_cache_maint_trap, }, #endif @@ -652,40 +659,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #endif #ifdef CONFIG_CAVIUM_ERRATUM_27456 { - /* Cavium ThunderX, T88 pass 1.x - 2.1 */ - .desc = "Cavium erratum 27456", - .capability = ARM64_WORKAROUND_CAVIUM_27456, - ERRATA_MIDR_RANGE(MIDR_THUNDERX, - 0, 0, - 1, 1), - }, - { - /* Cavium ThunderX, T81 pass 1.0 */ .desc = "Cavium erratum 27456", .capability = ARM64_WORKAROUND_CAVIUM_27456, - ERRATA_MIDR_REV(MIDR_THUNDERX_81XX, 0, 0), + ERRATA_MIDR_RANGE_LIST(cavium_erratum_27456_cpus), }, #endif #ifdef CONFIG_CAVIUM_ERRATUM_30115 { - /* Cavium ThunderX, T88 pass 1.x - 2.2 */ .desc = "Cavium erratum 30115", .capability = ARM64_WORKAROUND_CAVIUM_30115, - ERRATA_MIDR_RANGE(MIDR_THUNDERX, - 0, 0, - 1, 2), - }, - { - /* Cavium ThunderX, T81 pass 1.0 - 1.2 */ - .desc = "Cavium erratum 30115", - .capability = ARM64_WORKAROUND_CAVIUM_30115, - ERRATA_MIDR_REV_RANGE(MIDR_THUNDERX_81XX, 0, 0, 2), - }, - { - /* Cavium ThunderX, T83 pass 1.0 */ - .desc = "Cavium erratum 30115", - .capability = ARM64_WORKAROUND_CAVIUM_30115, - ERRATA_MIDR_REV(MIDR_THUNDERX_83XX, 0, 0), + ERRATA_MIDR_RANGE_LIST(cavium_erratum_30115_cpus), }, #endif { @@ -697,16 +680,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = { }, #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 { - .desc = "Qualcomm Technologies Falkor erratum 1003", - .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, - ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0), - }, - { - .desc = "Qualcomm Technologies Kryo erratum 1003", + .desc = "Qualcomm Technologies Falkor/Kryo erratum 1003", .capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003, - .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, - .midr_range.model = MIDR_QCOM_KRYO, - .matches = is_kryo_midr, + .matches = cpucap_multi_entry_cap_matches, + .match_list = qcom_erratum_1003_list, }, #endif #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI @@ -754,6 +731,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_1165522 + { + /* Cortex-A76 r0p0 to r2p0 */ + .desc = "ARM erratum 1165522", + .capability = ARM64_WORKAROUND_1165522, + ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index aec5ecb85737..4f272399de89 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -52,6 +52,7 @@ unsigned int compat_elf_hwcap2 __read_mostly; DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); EXPORT_SYMBOL(cpu_hwcaps); +static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM64_NCAPS]; /* * Flag to indicate if we have computed the system wide @@ -141,9 +142,18 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPI_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_GPA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FCMA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_API_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_APA_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DPB_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -518,6 +528,29 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new) } extern const struct arm64_cpu_capabilities arm64_errata[]; +static const struct arm64_cpu_capabilities arm64_features[]; + +static void __init +init_cpu_hwcaps_indirect_list_from_array(const struct arm64_cpu_capabilities *caps) +{ + for (; caps->matches; caps++) { + if (WARN(caps->capability >= ARM64_NCAPS, + "Invalid capability %d\n", caps->capability)) + continue; + if (WARN(cpu_hwcaps_ptrs[caps->capability], + "Duplicate entry for capability %d\n", + caps->capability)) + continue; + cpu_hwcaps_ptrs[caps->capability] = caps; + } +} + +static void __init init_cpu_hwcaps_indirect_list(void) +{ + init_cpu_hwcaps_indirect_list_from_array(arm64_features); + init_cpu_hwcaps_indirect_list_from_array(arm64_errata); +} + static void __init setup_boot_cpu_capabilities(void); void __init init_cpu_features(struct cpuinfo_arm64 *info) @@ -564,6 +597,12 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) } /* + * Initialize the indirect array of CPU hwcaps capabilities pointers + * before we handle the boot CPU below. + */ + init_cpu_hwcaps_indirect_list(); + + /* * Detect and enable early CPU capabilities based on the boot CPU, * after we have initialised the CPU feature infrastructure. */ @@ -915,6 +954,12 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, static const struct midr_range kpti_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), { /* sentinel */ } }; char const *str = "command line option"; @@ -1145,6 +1190,14 @@ static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused) } #endif /* CONFIG_ARM64_RAS_EXTN */ +#ifdef CONFIG_ARM64_PTR_AUTH +static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap) +{ + sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | + SCTLR_ELx_ENDA | SCTLR_ELx_ENDB); +} +#endif /* CONFIG_ARM64_PTR_AUTH */ + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -1368,22 +1421,115 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_enable_cnp, }, #endif + { + .desc = "Speculation barrier (SB)", + .capability = ARM64_HAS_SB, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .field_pos = ID_AA64ISAR1_SB_SHIFT, + .sign = FTR_UNSIGNED, + .min_field_value = 1, + }, +#ifdef CONFIG_ARM64_PTR_AUTH + { + .desc = "Address authentication (architected algorithm)", + .capability = ARM64_HAS_ADDRESS_AUTH_ARCH, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR1_APA_SHIFT, + .min_field_value = ID_AA64ISAR1_APA_ARCHITECTED, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_address_auth, + }, + { + .desc = "Address authentication (IMP DEF algorithm)", + .capability = ARM64_HAS_ADDRESS_AUTH_IMP_DEF, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR1_API_SHIFT, + .min_field_value = ID_AA64ISAR1_API_IMP_DEF, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_address_auth, + }, + { + .desc = "Generic authentication (architected algorithm)", + .capability = ARM64_HAS_GENERIC_AUTH_ARCH, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR1_GPA_SHIFT, + .min_field_value = ID_AA64ISAR1_GPA_ARCHITECTED, + .matches = has_cpuid_feature, + }, + { + .desc = "Generic authentication (IMP DEF algorithm)", + .capability = ARM64_HAS_GENERIC_AUTH_IMP_DEF, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR1_GPI_SHIFT, + .min_field_value = ID_AA64ISAR1_GPI_IMP_DEF, + .matches = has_cpuid_feature, + }, +#endif /* CONFIG_ARM64_PTR_AUTH */ {}, }; -#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ - { \ - .desc = #cap, \ - .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ - .matches = has_cpuid_feature, \ - .sys_reg = reg, \ - .field_pos = field, \ - .sign = s, \ - .min_field_value = min_value, \ - .hwcap_type = cap_type, \ - .hwcap = cap, \ +#define HWCAP_CPUID_MATCH(reg, field, s, min_value) \ + .matches = has_cpuid_feature, \ + .sys_reg = reg, \ + .field_pos = field, \ + .sign = s, \ + .min_field_value = min_value, + +#define __HWCAP_CAP(name, cap_type, cap) \ + .desc = name, \ + .type = ARM64_CPUCAP_SYSTEM_FEATURE, \ + .hwcap_type = cap_type, \ + .hwcap = cap, \ + +#define HWCAP_CAP(reg, field, s, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, s, min_value) \ } +#define HWCAP_MULTI_CAP(list, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + .matches = cpucap_multi_entry_cap_matches, \ + .match_list = list, \ + } + +#ifdef CONFIG_ARM64_PTR_AUTH +static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { + { + HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_APA_SHIFT, + FTR_UNSIGNED, ID_AA64ISAR1_APA_ARCHITECTED) + }, + { + HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_API_SHIFT, + FTR_UNSIGNED, ID_AA64ISAR1_API_IMP_DEF) + }, + {}, +}; + +static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { + { + HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPA_SHIFT, + FTR_UNSIGNED, ID_AA64ISAR1_GPA_ARCHITECTED) + }, + { + HWCAP_CPUID_MATCH(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_GPI_SHIFT, + FTR_UNSIGNED, ID_AA64ISAR1_GPI_IMP_DEF) + }, + {}, +}; +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES), @@ -1409,11 +1555,16 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB), HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE), #endif HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS), +#ifdef CONFIG_ARM64_PTR_AUTH + HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, HWCAP_PACA), + HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, HWCAP_PACG), +#endif {}, }; @@ -1482,52 +1633,46 @@ static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps) cap_set_elf_hwcap(hwcaps); } -/* - * Check if the current CPU has a given feature capability. - * Should be called from non-preemptible context. - */ -static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array, - unsigned int cap) +static void update_cpu_capabilities(u16 scope_mask) { + int i; const struct arm64_cpu_capabilities *caps; - if (WARN_ON(preemptible())) - return false; - - for (caps = cap_array; caps->matches; caps++) - if (caps->capability == cap) - return caps->matches(caps, SCOPE_LOCAL_CPU); - - return false; -} - -static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, - u16 scope_mask, const char *info) -{ scope_mask &= ARM64_CPUCAP_SCOPE_MASK; - for (; caps->matches; caps++) { - if (!(caps->type & scope_mask) || + for (i = 0; i < ARM64_NCAPS; i++) { + caps = cpu_hwcaps_ptrs[i]; + if (!caps || !(caps->type & scope_mask) || + cpus_have_cap(caps->capability) || !caps->matches(caps, cpucap_default_scope(caps))) continue; - if (!cpus_have_cap(caps->capability) && caps->desc) - pr_info("%s %s\n", info, caps->desc); + if (caps->desc) + pr_info("detected: %s\n", caps->desc); cpus_set_cap(caps->capability); } } -static void update_cpu_capabilities(u16 scope_mask) +/* + * Enable all the available capabilities on this CPU. The capabilities + * with BOOT_CPU scope are handled separately and hence skipped here. + */ +static int cpu_enable_non_boot_scope_capabilities(void *__unused) { - __update_cpu_capabilities(arm64_errata, scope_mask, - "enabling workaround for"); - __update_cpu_capabilities(arm64_features, scope_mask, "detected:"); -} + int i; + u16 non_boot_scope = SCOPE_ALL & ~SCOPE_BOOT_CPU; -static int __enable_cpu_capability(void *arg) -{ - const struct arm64_cpu_capabilities *cap = arg; + for_each_available_cap(i) { + const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[i]; + + if (WARN_ON(!cap)) + continue; - cap->cpu_enable(cap); + if (!(cap->type & non_boot_scope)) + continue; + + if (cap->cpu_enable) + cap->cpu_enable(cap); + } return 0; } @@ -1535,21 +1680,29 @@ static int __enable_cpu_capability(void *arg) * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void __init -__enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, - u16 scope_mask) +static void __init enable_cpu_capabilities(u16 scope_mask) { + int i; + const struct arm64_cpu_capabilities *caps; + bool boot_scope; + scope_mask &= ARM64_CPUCAP_SCOPE_MASK; - for (; caps->matches; caps++) { - unsigned int num = caps->capability; + boot_scope = !!(scope_mask & SCOPE_BOOT_CPU); - if (!(caps->type & scope_mask) || !cpus_have_cap(num)) + for (i = 0; i < ARM64_NCAPS; i++) { + unsigned int num; + + caps = cpu_hwcaps_ptrs[i]; + if (!caps || !(caps->type & scope_mask)) + continue; + num = caps->capability; + if (!cpus_have_cap(num)) continue; /* Ensure cpus_have_const_cap(num) works */ static_branch_enable(&cpu_hwcap_keys[num]); - if (caps->cpu_enable) { + if (boot_scope && caps->cpu_enable) /* * Capabilities with SCOPE_BOOT_CPU scope are finalised * before any secondary CPU boots. Thus, each secondary @@ -1558,25 +1711,19 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * the boot CPU, for which the capability must be * enabled here. This approach avoids costly * stop_machine() calls for this case. - * - * Otherwise, use stop_machine() as it schedules the - * work allowing us to modify PSTATE, instead of - * on_each_cpu() which uses an IPI, giving us a PSTATE - * that disappears when we return. */ - if (scope_mask & SCOPE_BOOT_CPU) - caps->cpu_enable(caps); - else - stop_machine(__enable_cpu_capability, - (void *)caps, cpu_online_mask); - } + caps->cpu_enable(caps); } -} -static void __init enable_cpu_capabilities(u16 scope_mask) -{ - __enable_cpu_capabilities(arm64_errata, scope_mask); - __enable_cpu_capabilities(arm64_features, scope_mask); + /* + * For all non-boot scope capabilities, use stop_machine() + * as it schedules the work allowing us to modify PSTATE, + * instead of on_each_cpu() which uses an IPI, giving us a + * PSTATE that disappears when we return. + */ + if (!boot_scope) + stop_machine(cpu_enable_non_boot_scope_capabilities, + NULL, cpu_online_mask); } /* @@ -1586,16 +1733,17 @@ static void __init enable_cpu_capabilities(u16 scope_mask) * * Returns "false" on conflicts. */ -static bool -__verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps, - u16 scope_mask) +static bool verify_local_cpu_caps(u16 scope_mask) { + int i; bool cpu_has_cap, system_has_cap; + const struct arm64_cpu_capabilities *caps; scope_mask &= ARM64_CPUCAP_SCOPE_MASK; - for (; caps->matches; caps++) { - if (!(caps->type & scope_mask)) + for (i = 0; i < ARM64_NCAPS; i++) { + caps = cpu_hwcaps_ptrs[i]; + if (!caps || !(caps->type & scope_mask)) continue; cpu_has_cap = caps->matches(caps, SCOPE_LOCAL_CPU); @@ -1626,7 +1774,7 @@ __verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps, } } - if (caps->matches) { + if (i < ARM64_NCAPS) { pr_crit("CPU%d: Detected conflict for capability %d (%s), System: %d, CPU: %d\n", smp_processor_id(), caps->capability, caps->desc, system_has_cap, cpu_has_cap); @@ -1636,12 +1784,6 @@ __verify_local_cpu_caps(const struct arm64_cpu_capabilities *caps, return true; } -static bool verify_local_cpu_caps(u16 scope_mask) -{ - return __verify_local_cpu_caps(arm64_errata, scope_mask) && - __verify_local_cpu_caps(arm64_features, scope_mask); -} - /* * Check for CPU features that are used in early boot * based on the Boot CPU value. @@ -1750,12 +1892,16 @@ static void __init mark_const_caps_ready(void) static_branch_enable(&arm64_const_caps_ready); } -extern const struct arm64_cpu_capabilities arm64_errata[]; - -bool this_cpu_has_cap(unsigned int cap) +bool this_cpu_has_cap(unsigned int n) { - return (__this_cpu_has_cap(arm64_features, cap) || - __this_cpu_has_cap(arm64_errata, cap)); + if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { + const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; + + if (cap) + return cap->matches(cap, SCOPE_LOCAL_CPU); + } + + return false; } static void __init setup_system_capabilities(void) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index bcc2831399cb..ca0685f33900 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -82,6 +82,9 @@ static const char *const hwcap_str[] = { "ilrcpc", "flagm", "ssbs", + "sb", + "paca", + "pacg", NULL }; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 1175f5827ae1..81b8eb5c4633 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -79,7 +79,6 @@ .macro mcount_get_lr reg ldr \reg, [x29] ldr \reg, [\reg, #8] - mcount_adjust_addr \reg, \reg .endm .macro mcount_get_lr_addr reg @@ -121,6 +120,8 @@ skip_ftrace_call: // } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ mcount_exit ENDPROC(_mcount) +EXPORT_SYMBOL(_mcount) +NOKPROBE(_mcount) #else /* CONFIG_DYNAMIC_FTRACE */ /* @@ -132,6 +133,8 @@ ENDPROC(_mcount) ENTRY(_mcount) ret ENDPROC(_mcount) +EXPORT_SYMBOL(_mcount) +NOKPROBE(_mcount) /* * void ftrace_caller(unsigned long return_address) @@ -148,14 +151,12 @@ ENTRY(ftrace_caller) mcount_get_pc0 x0 // function's pc mcount_get_lr x1 // function's lr - .global ftrace_call -ftrace_call: // tracer(pc, lr); +GLOBAL(ftrace_call) // tracer(pc, lr); nop // This will be replaced with "bl xxx" // where xxx can be any kind of tracer. #ifdef CONFIG_FUNCTION_GRAPH_TRACER - .global ftrace_graph_call -ftrace_graph_call: // ftrace_graph_caller(); +GLOBAL(ftrace_graph_call) // ftrace_graph_caller(); nop // If enabled, this will be replaced // "b ftrace_graph_caller" #endif @@ -169,24 +170,6 @@ ENTRY(ftrace_stub) ENDPROC(ftrace_stub) #ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* save return value regs*/ - .macro save_return_regs - sub sp, sp, #64 - stp x0, x1, [sp] - stp x2, x3, [sp, #16] - stp x4, x5, [sp, #32] - stp x6, x7, [sp, #48] - .endm - - /* restore return value regs*/ - .macro restore_return_regs - ldp x0, x1, [sp] - ldp x2, x3, [sp, #16] - ldp x4, x5, [sp, #32] - ldp x6, x7, [sp, #48] - add sp, sp, #64 - .endm - /* * void ftrace_graph_caller(void) * @@ -197,10 +180,10 @@ ENDPROC(ftrace_stub) * and run return_to_handler() later on its exit. */ ENTRY(ftrace_graph_caller) - mcount_get_lr_addr x0 // pointer to function's saved lr - mcount_get_pc x1 // function's pc + mcount_get_pc x0 // function's pc + mcount_get_lr_addr x1 // pointer to function's saved lr mcount_get_parent_fp x2 // parent's fp - bl prepare_ftrace_return // prepare_ftrace_return(&lr, pc, fp) + bl prepare_ftrace_return // prepare_ftrace_return(pc, &lr, fp) mcount_exit ENDPROC(ftrace_graph_caller) @@ -209,15 +192,27 @@ ENDPROC(ftrace_graph_caller) * void return_to_handler(void) * * Run ftrace_return_to_handler() before going back to parent. - * @fp is checked against the value passed by ftrace_graph_caller() - * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled. + * @fp is checked against the value passed by ftrace_graph_caller(). */ ENTRY(return_to_handler) - save_return_regs + /* save return value regs */ + sub sp, sp, #64 + stp x0, x1, [sp] + stp x2, x3, [sp, #16] + stp x4, x5, [sp, #32] + stp x6, x7, [sp, #48] + mov x0, x29 // parent's fp bl ftrace_return_to_handler// addr = ftrace_return_to_hander(fp); mov x30, x0 // restore the original return address - restore_return_regs + + /* restore return value regs */ + ldp x0, x1, [sp] + ldp x2, x3, [sp, #16] + ldp x4, x5, [sp, #32] + ldp x6, x7, [sp, #48] + add sp, sp, #64 + ret END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 039144ecbcb2..763f03dc4d9e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -344,10 +344,6 @@ alternative_else_nop_endif ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] add sp, sp, #S_FRAME_SIZE // restore sp - /* - * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on eret context synchronization - * when returning from IPI handler, and when returning to user-space. - */ .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -363,6 +359,7 @@ alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 .else eret .endif + sb .endm .macro irq_stack_entry @@ -622,10 +619,8 @@ el1_irq: irq_handler #ifdef CONFIG_PREEMPT - ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count - cbnz w24, 1f // preempt count != 0 - ldr x0, [tsk, #TSK_TI_FLAGS] // get flags - tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? + ldr x24, [tsk, #TSK_TI_PREEMPT] // get preempt count + cbnz x24, 1f // preempt count != 0 bl el1_preempt 1: #endif @@ -1006,6 +1001,7 @@ alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 mrs x30, far_el1 .endif eret + sb .endm .align 11 diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 57e962290df3..8e4431a8821f 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -104,7 +104,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * is added in the future, but for now, the pr_err() below * deals with a theoretical issue only. */ - trampoline = get_plt_entry(addr); + trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline); if (!plt_entries_equal(mod->arch.ftrace_trampoline, &trampoline)) { if (!plt_entries_equal(mod->arch.ftrace_trampoline, @@ -193,6 +193,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, void arch_ftrace_update_code(int command) { + command |= FTRACE_MAY_SLEEP; ftrace_modify_all_code(command); } @@ -211,7 +212,7 @@ int __init ftrace_dyn_arch_init(void) * * Note that @frame_pointer is used only for sanity check later. */ -void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, +void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long)&return_to_handler; diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 4471f570a295..c7213674cb24 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -31,6 +31,7 @@ #include <asm/cache.h> #include <asm/cputype.h> #include <asm/elf.h> +#include <asm/image.h> #include <asm/kernel-pgtable.h> #include <asm/kvm_arm.h> #include <asm/memory.h> @@ -91,7 +92,7 @@ _head: .quad 0 // reserved .quad 0 // reserved .quad 0 // reserved - .ascii "ARM\x64" // Magic number + .ascii ARM64_IMAGE_MAGIC // Magic number #ifdef CONFIG_EFI .long pe_header - _head // Offset to the PE header. @@ -318,6 +319,19 @@ __create_page_tables: adrp x0, idmap_pg_dir adrp x3, __idmap_text_start // __pa(__idmap_text_start) +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + mrs_s x6, SYS_ID_AA64MMFR2_EL1 + and x6, x6, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + mov x5, #52 + cbnz x6, 1f +#endif + mov x5, #VA_BITS +1: + adr_l x6, vabits_user + str x5, [x6] + dmb sy + dc ivac, x6 // Invalidate potentially stale cache line + /* * VA_BITS may be too small to allow for an ID mapping to be created * that covers system RAM if that is located sufficiently high in the @@ -496,10 +510,9 @@ ENTRY(el2_setup) #endif /* Hyp configuration. */ - mov x0, #HCR_RW // 64-bit EL1 + mov_q x0, HCR_HOST_NVHE_FLAGS cbz x2, set_hcr - orr x0, x0, #HCR_TGE // Enable Host Extensions - orr x0, x0, #HCR_E2H + mov_q x0, HCR_HOST_VHE_FLAGS set_hcr: msr hcr_el2, x0 isb @@ -707,6 +720,7 @@ secondary_startup: /* * Common entry point for secondary CPUs. */ + bl __cpu_secondary_check52bitva bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir bl __enable_mmu @@ -769,6 +783,7 @@ ENTRY(__enable_mmu) phys_to_ttbr x1, x1 phys_to_ttbr x2, x2 msr ttbr0_el1, x2 // load TTBR0 + offset_ttbr1 x1 msr ttbr1_el1, x1 // load TTBR1 isb msr sctlr_el1, x0 @@ -784,9 +799,30 @@ ENTRY(__enable_mmu) ret ENDPROC(__enable_mmu) +ENTRY(__cpu_secondary_check52bitva) +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + ldr_l x0, vabits_user + cmp x0, #52 + b.ne 2f + + mrs_s x0, SYS_ID_AA64MMFR2_EL1 + and x0, x0, #(0xf << ID_AA64MMFR2_LVA_SHIFT) + cbnz x0, 2f + + update_early_cpu_boot_status \ + CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1 +1: wfe + wfi + b 1b + +#endif +2: ret +ENDPROC(__cpu_secondary_check52bitva) + __no_granule_support: /* Indicate that this CPU can't boot and is stuck in the kernel */ - update_early_cpu_boot_status CPU_STUCK_IN_KERNEL, x1, x2 + update_early_cpu_boot_status \ + CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_NO_GRAN, x1, x2 1: wfe wfi diff --git a/arch/arm64/kernel/hibernate-asm.S b/arch/arm64/kernel/hibernate-asm.S index dd14ab8c9f72..fe36d85c60bd 100644 --- a/arch/arm64/kernel/hibernate-asm.S +++ b/arch/arm64/kernel/hibernate-asm.S @@ -40,6 +40,7 @@ tlbi vmalle1 dsb nsh phys_to_ttbr \tmp, \page_table + offset_ttbr1 \tmp msr ttbr1_el1, \tmp isb .endm diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 6b2686d54411..29cdc99688f3 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -214,7 +214,7 @@ static int create_safe_exec_page(void *src_start, size_t length, } memcpy((void *)dst, src_start, length); - flush_icache_range(dst, dst + length); + __flush_icache_range(dst, dst + length); pgdp = pgd_offset_raw(allocator(mask), dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index a820ed07fb80..33f14e484040 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -15,13 +15,15 @@ * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ -#ifndef __ASM_IMAGE_H -#define __ASM_IMAGE_H +#ifndef __ARM64_KERNEL_IMAGE_H +#define __ARM64_KERNEL_IMAGE_H #ifndef LINKER_SCRIPT #error This file should only be included in vmlinux.lds.S #endif +#include <asm/image.h> + /* * There aren't any ELF relocations we can use to endian-swap values known only * at link time (e.g. the subtraction of two symbol addresses), so we must get @@ -47,19 +49,22 @@ sym##_lo32 = DATA_LE32((data) & 0xffffffff); \ sym##_hi32 = DATA_LE32((data) >> 32) +#define __HEAD_FLAG(field) (__HEAD_FLAG_##field << \ + ARM64_IMAGE_FLAG_##field##_SHIFT) + #ifdef CONFIG_CPU_BIG_ENDIAN -#define __HEAD_FLAG_BE 1 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_BE #else -#define __HEAD_FLAG_BE 0 +#define __HEAD_FLAG_BE ARM64_IMAGE_FLAG_LE #endif #define __HEAD_FLAG_PAGE_SIZE ((PAGE_SHIFT - 10) / 2) #define __HEAD_FLAG_PHYS_BASE 1 -#define __HEAD_FLAGS ((__HEAD_FLAG_BE << 0) | \ - (__HEAD_FLAG_PAGE_SIZE << 1) | \ - (__HEAD_FLAG_PHYS_BASE << 3)) +#define __HEAD_FLAGS (__HEAD_FLAG(BE) | \ + __HEAD_FLAG(PAGE_SIZE) | \ + __HEAD_FLAG(PHYS_BASE)) /* * These will output as part of the Image header, which should be little-endian @@ -76,16 +81,6 @@ __efistub_stext_offset = stext - _text; /* - * Prevent the symbol aliases below from being emitted into the kallsyms - * table, by forcing them to be absolute symbols (which are conveniently - * ignored by scripts/kallsyms) rather than section relative symbols. - * The distinction is only relevant for partial linking, and only for symbols - * that are defined within a section declaration (which is not the case for - * the definitions below) so the resulting values will be identical. - */ -#define KALLSYMS_HIDE(sym) ABSOLUTE(sym) - -/* * The EFI stub has its own symbol namespace prefixed by __efistub_, to * isolate it from the kernel proper. The following symbols are legally * accessed by the stub, so provide some aliases to make them accessible. @@ -94,29 +89,29 @@ __efistub_stext_offset = stext - _text; * linked at. The routines below are all implemented in assembler in a * position independent manner */ -__efistub_memcmp = KALLSYMS_HIDE(__pi_memcmp); -__efistub_memchr = KALLSYMS_HIDE(__pi_memchr); -__efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); -__efistub_memmove = KALLSYMS_HIDE(__pi_memmove); -__efistub_memset = KALLSYMS_HIDE(__pi_memset); -__efistub_strlen = KALLSYMS_HIDE(__pi_strlen); -__efistub_strnlen = KALLSYMS_HIDE(__pi_strnlen); -__efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); -__efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); -__efistub_strrchr = KALLSYMS_HIDE(__pi_strrchr); -__efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); +__efistub_memcmp = __pi_memcmp; +__efistub_memchr = __pi_memchr; +__efistub_memcpy = __pi_memcpy; +__efistub_memmove = __pi_memmove; +__efistub_memset = __pi_memset; +__efistub_strlen = __pi_strlen; +__efistub_strnlen = __pi_strnlen; +__efistub_strcmp = __pi_strcmp; +__efistub_strncmp = __pi_strncmp; +__efistub_strrchr = __pi_strrchr; +__efistub___flush_dcache_area = __pi___flush_dcache_area; #ifdef CONFIG_KASAN -__efistub___memcpy = KALLSYMS_HIDE(__pi_memcpy); -__efistub___memmove = KALLSYMS_HIDE(__pi_memmove); -__efistub___memset = KALLSYMS_HIDE(__pi_memset); +__efistub___memcpy = __pi_memcpy; +__efistub___memmove = __pi_memmove; +__efistub___memset = __pi_memset; #endif -__efistub__text = KALLSYMS_HIDE(_text); -__efistub__end = KALLSYMS_HIDE(_end); -__efistub__edata = KALLSYMS_HIDE(_edata); -__efistub_screen_info = KALLSYMS_HIDE(screen_info); +__efistub__text = _text; +__efistub__end = _end; +__efistub__edata = _edata; +__efistub_screen_info = screen_info; #endif -#endif /* __ASM_IMAGE_H */ +#endif /* __ARM64_KERNEL_IMAGE_H */ diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 2b3413549734..7820a4a688fa 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -1239,6 +1239,35 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_6, insn, shift); } +u32 aarch64_insn_gen_adr(unsigned long pc, unsigned long addr, + enum aarch64_insn_register reg, + enum aarch64_insn_adr_type type) +{ + u32 insn; + s32 offset; + + switch (type) { + case AARCH64_INSN_ADR_TYPE_ADR: + insn = aarch64_insn_get_adr_value(); + offset = addr - pc; + break; + case AARCH64_INSN_ADR_TYPE_ADRP: + insn = aarch64_insn_get_adrp_value(); + offset = (addr - ALIGN_DOWN(pc, SZ_4K)) >> 12; + break; + default: + pr_err("%s: unknown adr encoding %d\n", __func__, type); + return AARCH64_BREAK_FAULT; + } + + if (offset < -SZ_1M || offset >= SZ_1M) + return AARCH64_BREAK_FAULT; + + insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RD, insn, reg); + + return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn, offset); +} + /* * Decode the imm field of a branch, and return the byte offset as a * signed value (so it can be used when computing a new branch diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c new file mode 100644 index 000000000000..07bf740bea91 --- /dev/null +++ b/arch/arm64/kernel/kexec_image.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kexec image loader + + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include <linux/err.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/pe.h> +#include <linux/string.h> +#include <linux/verification.h> +#include <asm/byteorder.h> +#include <asm/cpufeature.h> +#include <asm/image.h> +#include <asm/memory.h> + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct arm64_image_header *h = + (const struct arm64_image_header *)(kernel_buf); + + if (!h || (kernel_len < sizeof(*h))) + return -EINVAL; + + if (memcmp(&h->magic, ARM64_IMAGE_MAGIC, sizeof(h->magic))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct arm64_image_header *h; + u64 flags, value; + bool be_image, be_kernel; + struct kexec_buf kbuf; + unsigned long text_offset; + struct kexec_segment *kernel_segment; + int ret; + + /* We don't support crash kernels yet. */ + if (image->type == KEXEC_TYPE_CRASH) + return ERR_PTR(-EOPNOTSUPP); + + /* + * We require a kernel with an unambiguous Image header. Per + * Documentation/booting.txt, this is the case when image_size + * is non-zero (practically speaking, since v3.17). + */ + h = (struct arm64_image_header *)kernel; + if (!h->image_size) + return ERR_PTR(-EINVAL); + + /* Check cpu features */ + flags = le64_to_cpu(h->flags); + be_image = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if ((be_image != be_kernel) && !system_supports_mixed_endian()) + return ERR_PTR(-EINVAL); + + value = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_PAGE_SIZE); + if (((value == ARM64_IMAGE_FLAG_PAGE_SIZE_4K) && + !system_supports_4kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_64K) && + !system_supports_64kb_granule()) || + ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_16K) && + !system_supports_16kb_granule())) + return ERR_PTR(-EINVAL); + + /* Load the kernel */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = 0; + kbuf.memsz = le64_to_cpu(h->image_size); + text_offset = le64_to_cpu(h->text_offset); + kbuf.buf_align = MIN_KIMG_ALIGN; + + /* Adjust kernel segment with TEXT_OFFSET */ + kbuf.memsz += text_offset; + + ret = kexec_add_buffer(&kbuf); + if (ret) + return ERR_PTR(ret); + + kernel_segment = &image->segment[image->nr_segments - 1]; + kernel_segment->mem += text_offset; + kernel_segment->memsz -= text_offset; + image->start = kernel_segment->mem; + + pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_segment->mem, kbuf.bufsz, + kernel_segment->memsz); + + /* Load additional data */ + ret = load_other_segments(image, + kernel_segment->mem, kernel_segment->memsz, + initrd, initrd_len, cmdline); + + return ERR_PTR(ret); +} + +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG +static int image_verify_sig(const char *kernel, unsigned long kernel_len) +{ + return verify_pefile_signature(kernel, kernel_len, NULL, + VERIFYING_KEXEC_PE_SIGNATURE); +} +#endif + +const struct kexec_file_ops kexec_image_ops = { + .probe = image_probe, + .load = image_load, +#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG + .verify_sig = image_verify_sig, +#endif +}; diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 922add8adb74..aa9c94113700 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -212,9 +212,17 @@ void machine_kexec(struct kimage *kimage) * uses physical addressing to relocate the new image to its final * position and transfers control to the image entry point when the * relocation is complete. + * In kexec case, kimage->start points to purgatory assuming that + * kernel entry and dtb address are embedded in purgatory by + * userspace (kexec-tools). + * In kexec_file case, the kernel starts directly without purgatory. */ - - cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0); + cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, +#ifdef CONFIG_KEXEC_FILE + kimage->arch.dtb_mem); +#else + 0); +#endif BUG(); /* Should never get here. */ } diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c new file mode 100644 index 000000000000..10e33860e47a --- /dev/null +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kexec_file for arm64 + * + * Copyright (C) 2018 Linaro Limited + * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> + * + * Most code is derived from arm64 port of kexec-tools + */ + +#define pr_fmt(fmt) "kexec_file: " fmt + +#include <linux/ioport.h> +#include <linux/kernel.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <linux/random.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/vmalloc.h> +#include <asm/byteorder.h> + +/* relevant device tree properties */ +#define FDT_PROP_INITRD_START "linux,initrd-start" +#define FDT_PROP_INITRD_END "linux,initrd-end" +#define FDT_PROP_BOOTARGS "bootargs" +#define FDT_PROP_KASLR_SEED "kaslr-seed" + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &kexec_image_ops, + NULL +}; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + vfree(image->arch.dtb); + image->arch.dtb = NULL; + + return kexec_image_post_load_cleanup_default(image); +} + +static int setup_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void *dtb) +{ + int off, ret; + + ret = fdt_path_offset(dtb, "/chosen"); + if (ret < 0) + goto out; + + off = ret; + + /* add bootargs */ + if (cmdline) { + ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add initrd-* */ + if (initrd_load_addr) { + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START, + initrd_load_addr); + if (ret) + goto out; + + ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END, + initrd_load_addr + initrd_len); + if (ret) + goto out; + } else { + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + } + + /* add kaslr-seed */ + ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED); + if (ret && (ret != -FDT_ERR_NOTFOUND)) + goto out; + + if (rng_is_initialized()) { + u64 seed = get_random_u64(); + ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed); + if (ret) + goto out; + } else { + pr_notice("RNG is not initialised: omitting \"%s\" property\n", + FDT_PROP_KASLR_SEED); + } + +out: + if (ret) + return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL; + + return 0; +} + +/* + * More space needed so that we can add initrd, bootargs and kaslr-seed. + */ +#define DTB_EXTRA_SPACE 0x1000 + +static int create_dtb(struct kimage *image, + unsigned long initrd_load_addr, unsigned long initrd_len, + char *cmdline, void **dtb) +{ + void *buf; + size_t buf_size; + int ret; + + buf_size = fdt_totalsize(initial_boot_params) + + strlen(cmdline) + DTB_EXTRA_SPACE; + + for (;;) { + buf = vmalloc(buf_size); + if (!buf) + return -ENOMEM; + + /* duplicate a device tree blob */ + ret = fdt_open_into(initial_boot_params, buf, buf_size); + if (ret) + return -EINVAL; + + ret = setup_dtb(image, initrd_load_addr, initrd_len, + cmdline, buf); + if (ret) { + vfree(buf); + if (ret == -ENOMEM) { + /* unlikely, but just in case */ + buf_size += DTB_EXTRA_SPACE; + continue; + } else { + return ret; + } + } + + /* trim it */ + fdt_pack(buf); + *dtb = buf; + + return 0; + } +} + +int load_other_segments(struct kimage *image, + unsigned long kernel_load_addr, + unsigned long kernel_size, + char *initrd, unsigned long initrd_len, + char *cmdline) +{ + struct kexec_buf kbuf; + void *dtb = NULL; + unsigned long initrd_load_addr = 0, dtb_len; + int ret = 0; + + kbuf.image = image; + /* not allocate anything below the kernel */ + kbuf.buf_min = kernel_load_addr + kernel_size; + + /* load initrd */ + if (initrd) { + kbuf.buffer = initrd; + kbuf.bufsz = initrd_len; + kbuf.mem = 0; + kbuf.memsz = initrd_len; + kbuf.buf_align = 0; + /* within 1GB-aligned window of up to 32GB in size */ + kbuf.buf_max = round_down(kernel_load_addr, SZ_1G) + + (unsigned long)SZ_1G * 32; + kbuf.top_down = false; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + initrd_load_addr = kbuf.mem; + + pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); + } + + /* load dtb */ + ret = create_dtb(image, initrd_load_addr, initrd_len, cmdline, &dtb); + if (ret) { + pr_err("Preparing for new dtb failed\n"); + goto out_err; + } + + dtb_len = fdt_totalsize(dtb); + kbuf.buffer = dtb; + kbuf.bufsz = dtb_len; + kbuf.mem = 0; + kbuf.memsz = dtb_len; + /* not across 2MB boundary */ + kbuf.buf_align = SZ_2M; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out_err; + image->arch.dtb = dtb; + image->arch.dtb_mem = kbuf.mem; + + pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, dtb_len, dtb_len); + + return 0; + +out_err: + vfree(dtb); + return ret; +} diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index f0690c2ca3e0..255941394941 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -11,31 +11,91 @@ #include <linux/module.h> #include <linux/sort.h> +static struct plt_entry __get_adrp_add_pair(u64 dst, u64 pc, + enum aarch64_insn_register reg) +{ + u32 adrp, add; + + adrp = aarch64_insn_gen_adr(pc, dst, reg, AARCH64_INSN_ADR_TYPE_ADRP); + add = aarch64_insn_gen_add_sub_imm(reg, reg, dst % SZ_4K, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_ADSB_ADD); + + return (struct plt_entry){ cpu_to_le32(adrp), cpu_to_le32(add) }; +} + +struct plt_entry get_plt_entry(u64 dst, void *pc) +{ + struct plt_entry plt; + static u32 br; + + if (!br) + br = aarch64_insn_gen_branch_reg(AARCH64_INSN_REG_16, + AARCH64_INSN_BRANCH_NOLINK); + + plt = __get_adrp_add_pair(dst, (u64)pc, AARCH64_INSN_REG_16); + plt.br = cpu_to_le32(br); + + return plt; +} + +bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b) +{ + u64 p, q; + + /* + * Check whether both entries refer to the same target: + * do the cheapest checks first. + * If the 'add' or 'br' opcodes are different, then the target + * cannot be the same. + */ + if (a->add != b->add || a->br != b->br) + return false; + + p = ALIGN_DOWN((u64)a, SZ_4K); + q = ALIGN_DOWN((u64)b, SZ_4K); + + /* + * If the 'adrp' opcodes are the same then we just need to check + * that they refer to the same 4k region. + */ + if (a->adrp == b->adrp && p == q) + return true; + + return (p + aarch64_insn_adrp_get_offset(le32_to_cpu(a->adrp))) == + (q + aarch64_insn_adrp_get_offset(le32_to_cpu(b->adrp))); +} + static bool in_init(const struct module *mod, void *loc) { return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size; } -u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela, +u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, + void *loc, const Elf64_Rela *rela, Elf64_Sym *sym) { struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : &mod->arch.init; - struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr; + struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries; + int j = i - 1; u64 val = sym->st_value + rela->r_addend; - plt[i] = get_plt_entry(val); + if (is_forbidden_offset_for_adrp(&plt[i].adrp)) + i++; + + plt[i] = get_plt_entry(val, &plt[i]); /* * Check if the entry we just created is a duplicate. Given that the * relocations are sorted, this will be the last entry we allocated. * (if one exists). */ - if (i > 0 && plt_entries_equal(plt + i, plt + i - 1)) - return (u64)&plt[i - 1]; + if (j >= 0 && plt_entries_equal(plt + i, plt + j)) + return (u64)&plt[j]; - pltsec->plt_num_entries++; + pltsec->plt_num_entries += i - j; if (WARN_ON(pltsec->plt_num_entries > pltsec->plt_max_entries)) return 0; @@ -43,41 +103,31 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela, } #ifdef CONFIG_ARM64_ERRATUM_843419 -u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val) +u64 module_emit_veneer_for_adrp(struct module *mod, Elf64_Shdr *sechdrs, + void *loc, u64 val) { struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : &mod->arch.init; - struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr; + struct plt_entry *plt = (struct plt_entry *)sechdrs[pltsec->plt_shndx].sh_addr; int i = pltsec->plt_num_entries++; - u32 mov0, mov1, mov2, br; + u32 br; int rd; if (WARN_ON(pltsec->plt_num_entries > pltsec->plt_max_entries)) return 0; + if (is_forbidden_offset_for_adrp(&plt[i].adrp)) + i = pltsec->plt_num_entries++; + /* get the destination register of the ADRP instruction */ rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, le32_to_cpup((__le32 *)loc)); - /* generate the veneer instructions */ - mov0 = aarch64_insn_gen_movewide(rd, (u16)~val, 0, - AARCH64_INSN_VARIANT_64BIT, - AARCH64_INSN_MOVEWIDE_INVERSE); - mov1 = aarch64_insn_gen_movewide(rd, (u16)(val >> 16), 16, - AARCH64_INSN_VARIANT_64BIT, - AARCH64_INSN_MOVEWIDE_KEEP); - mov2 = aarch64_insn_gen_movewide(rd, (u16)(val >> 32), 32, - AARCH64_INSN_VARIANT_64BIT, - AARCH64_INSN_MOVEWIDE_KEEP); br = aarch64_insn_gen_branch_imm((u64)&plt[i].br, (u64)loc + 4, AARCH64_INSN_BRANCH_NOLINK); - plt[i] = (struct plt_entry){ - cpu_to_le32(mov0), - cpu_to_le32(mov1), - cpu_to_le32(mov2), - cpu_to_le32(br) - }; + plt[i] = __get_adrp_add_pair(val, (u64)&plt[i], rd); + plt[i].br = cpu_to_le32(br); return (u64)&plt[i]; } @@ -193,6 +243,15 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, break; } } + + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) && + cpus_have_const_cap(ARM64_WORKAROUND_843419)) + /* + * Add some slack so we can skip PLT slots that may trigger + * the erratum due to the placement of the ADRP instruction. + */ + ret += DIV_ROUND_UP(ret, (SZ_4K / sizeof(struct plt_entry))); + return ret; } @@ -202,7 +261,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned long core_plts = 0; unsigned long init_plts = 0; Elf64_Sym *syms = NULL; - Elf_Shdr *tramp = NULL; + Elf_Shdr *pltsec, *tramp = NULL; int i; /* @@ -211,9 +270,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, */ for (i = 0; i < ehdr->e_shnum; i++) { if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt")) - mod->arch.core.plt = sechdrs + i; + mod->arch.core.plt_shndx = i; else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt")) - mod->arch.init.plt = sechdrs + i; + mod->arch.init.plt_shndx = i; else if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE) && !strcmp(secstrings + sechdrs[i].sh_name, ".text.ftrace_trampoline")) @@ -222,7 +281,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, syms = (Elf64_Sym *)sechdrs[i].sh_addr; } - if (!mod->arch.core.plt || !mod->arch.init.plt) { + if (!mod->arch.core.plt_shndx || !mod->arch.init.plt_shndx) { pr_err("%s: module PLT section(s) missing\n", mod->name); return -ENOEXEC; } @@ -254,17 +313,19 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, sechdrs[i].sh_info, dstsec); } - mod->arch.core.plt->sh_type = SHT_NOBITS; - mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; - mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES; - mod->arch.core.plt->sh_size = (core_plts + 1) * sizeof(struct plt_entry); + pltsec = sechdrs + mod->arch.core.plt_shndx; + pltsec->sh_type = SHT_NOBITS; + pltsec->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + pltsec->sh_addralign = L1_CACHE_BYTES; + pltsec->sh_size = (core_plts + 1) * sizeof(struct plt_entry); mod->arch.core.plt_num_entries = 0; mod->arch.core.plt_max_entries = core_plts; - mod->arch.init.plt->sh_type = SHT_NOBITS; - mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; - mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES; - mod->arch.init.plt->sh_size = (init_plts + 1) * sizeof(struct plt_entry); + pltsec = sechdrs + mod->arch.init.plt_shndx; + pltsec->sh_type = SHT_NOBITS; + pltsec->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + pltsec->sh_addralign = L1_CACHE_BYTES; + pltsec->sh_size = (init_plts + 1) * sizeof(struct plt_entry); mod->arch.init.plt_num_entries = 0; mod->arch.init.plt_max_entries = init_plts; diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f0f27aeefb73..f713e2fc4d75 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -198,13 +198,12 @@ static int reloc_insn_imm(enum aarch64_reloc_op op, __le32 *place, u64 val, return 0; } -static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val) +static int reloc_insn_adrp(struct module *mod, Elf64_Shdr *sechdrs, + __le32 *place, u64 val) { u32 insn; - if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_843419) || - !cpus_have_const_cap(ARM64_WORKAROUND_843419) || - ((u64)place & 0xfff) < 0xff8) + if (!is_forbidden_offset_for_adrp(place)) return reloc_insn_imm(RELOC_OP_PAGE, place, val, 12, 21, AARCH64_INSN_IMM_ADR); @@ -215,7 +214,7 @@ static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val) insn &= ~BIT(31); } else { /* out of range for ADR -> emit a veneer */ - val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff); + val = module_emit_veneer_for_adrp(mod, sechdrs, place, val & ~0xfff); if (!val) return -ENOEXEC; insn = aarch64_insn_gen_branch_imm((u64)place, val, @@ -368,7 +367,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_ADR_PREL_PG_HI21_NC: overflow_check = false; case R_AARCH64_ADR_PREL_PG_HI21: - ovf = reloc_insn_adrp(me, loc, val); + ovf = reloc_insn_adrp(me, sechdrs, loc, val); if (ovf && ovf != -ERANGE) return ovf; break; @@ -413,7 +412,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && ovf == -ERANGE) { - val = module_emit_plt_entry(me, loc, &rel[i], sym); + val = module_emit_plt_entry(me, sechdrs, loc, &rel[i], sym); if (!val) return -ENOEXEC; ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2, diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index bcafd7dcfe8b..a34c26afacb0 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -18,6 +18,7 @@ #include <linux/perf_event.h> #include <linux/uaccess.h> +#include <asm/pointer_auth.h> #include <asm/stacktrace.h> struct frame_tail { @@ -35,6 +36,7 @@ user_backtrace(struct frame_tail __user *tail, { struct frame_tail buftail; unsigned long err; + unsigned long lr; /* Also check accessibility of one struct frame_tail beyond */ if (!access_ok(VERIFY_READ, tail, sizeof(buftail))) @@ -47,7 +49,9 @@ user_backtrace(struct frame_tail __user *tail, if (err) return NULL; - perf_callchain_store(entry, buftail.lr); + lr = ptrauth_strip_insn_pac(buftail.lr); + + perf_callchain_store(entry, lr); /* * Frame pointers should strictly progress back up the stack @@ -164,7 +168,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = current->curr_ret_stack; + frame.graph = 0; #endif walk_stackframe(current, &frame, callchain_trace, entry); diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index e213f8e867f6..1620a371b1f5 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1,5 +1,5 @@ /* - * PMU support + * ARMv8 PMUv3 Performance Events handling code. * * Copyright (C) 2012 ARM Limited * Author: Will Deacon <will.deacon@arm.com> @@ -30,149 +30,6 @@ #include <linux/perf/arm_pmu.h> #include <linux/platform_device.h> -/* - * ARMv8 PMUv3 Performance Events handling code. - * Common event types (some are defined in asm/perf_event.h). - */ - -/* At least one of the following is required. */ -#define ARMV8_PMUV3_PERFCTR_INST_RETIRED 0x08 -#define ARMV8_PMUV3_PERFCTR_INST_SPEC 0x1B - -/* Common architectural events. */ -#define ARMV8_PMUV3_PERFCTR_LD_RETIRED 0x06 -#define ARMV8_PMUV3_PERFCTR_ST_RETIRED 0x07 -#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x09 -#define ARMV8_PMUV3_PERFCTR_EXC_RETURN 0x0A -#define ARMV8_PMUV3_PERFCTR_CID_WRITE_RETIRED 0x0B -#define ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED 0x0C -#define ARMV8_PMUV3_PERFCTR_BR_IMMED_RETIRED 0x0D -#define ARMV8_PMUV3_PERFCTR_BR_RETURN_RETIRED 0x0E -#define ARMV8_PMUV3_PERFCTR_UNALIGNED_LDST_RETIRED 0x0F -#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE_RETIRED 0x1C -#define ARMV8_PMUV3_PERFCTR_CHAIN 0x1E -#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x21 - -/* Common microarchitectural events. */ -#define ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL 0x01 -#define ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL 0x02 -#define ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL 0x05 -#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x13 -#define ARMV8_PMUV3_PERFCTR_L1I_CACHE 0x14 -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_WB 0x15 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE 0x16 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL 0x17 -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_WB 0x18 -#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x19 -#define ARMV8_PMUV3_PERFCTR_MEMORY_ERROR 0x1A -#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x1D -#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x1F -#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x20 -#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x22 -#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x23 -#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x24 -#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x25 -#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x26 -#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x27 -#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x28 -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x29 -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x2A -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x2B -#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x2C -#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x2D -#define ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL 0x2E -#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x2F -#define ARMV8_PMUV3_PERFCTR_L2I_TLB 0x30 - -/* ARMv8 recommended implementation defined event types */ -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD 0x40 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR 0x41 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_RD 0x42 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR 0x43 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_INNER 0x44 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_OUTER 0x45 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_VICTIM 0x46 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WB_CLEAN 0x47 -#define ARMV8_IMPDEF_PERFCTR_L1D_CACHE_INVAL 0x48 - -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD 0x4C -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR 0x4D -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD 0x4E -#define ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR 0x4F -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_RD 0x50 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WR 0x51 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_RD 0x52 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_REFILL_WR 0x53 - -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_VICTIM 0x56 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_WB_CLEAN 0x57 -#define ARMV8_IMPDEF_PERFCTR_L2D_CACHE_INVAL 0x58 - -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_RD 0x5C -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_REFILL_WR 0x5D -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_RD 0x5E -#define ARMV8_IMPDEF_PERFCTR_L2D_TLB_WR 0x5F - -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD 0x60 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR 0x61 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_SHARED 0x62 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NOT_SHARED 0x63 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_NORMAL 0x64 -#define ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_PERIPH 0x65 - -#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_RD 0x66 -#define ARMV8_IMPDEF_PERFCTR_MEM_ACCESS_WR 0x67 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LD_SPEC 0x68 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_ST_SPEC 0x69 -#define ARMV8_IMPDEF_PERFCTR_UNALIGNED_LDST_SPEC 0x6A - -#define ARMV8_IMPDEF_PERFCTR_LDREX_SPEC 0x6C -#define ARMV8_IMPDEF_PERFCTR_STREX_PASS_SPEC 0x6D -#define ARMV8_IMPDEF_PERFCTR_STREX_FAIL_SPEC 0x6E -#define ARMV8_IMPDEF_PERFCTR_STREX_SPEC 0x6F -#define ARMV8_IMPDEF_PERFCTR_LD_SPEC 0x70 -#define ARMV8_IMPDEF_PERFCTR_ST_SPEC 0x71 -#define ARMV8_IMPDEF_PERFCTR_LDST_SPEC 0x72 -#define ARMV8_IMPDEF_PERFCTR_DP_SPEC 0x73 -#define ARMV8_IMPDEF_PERFCTR_ASE_SPEC 0x74 -#define ARMV8_IMPDEF_PERFCTR_VFP_SPEC 0x75 -#define ARMV8_IMPDEF_PERFCTR_PC_WRITE_SPEC 0x76 -#define ARMV8_IMPDEF_PERFCTR_CRYPTO_SPEC 0x77 -#define ARMV8_IMPDEF_PERFCTR_BR_IMMED_SPEC 0x78 -#define ARMV8_IMPDEF_PERFCTR_BR_RETURN_SPEC 0x79 -#define ARMV8_IMPDEF_PERFCTR_BR_INDIRECT_SPEC 0x7A - -#define ARMV8_IMPDEF_PERFCTR_ISB_SPEC 0x7C -#define ARMV8_IMPDEF_PERFCTR_DSB_SPEC 0x7D -#define ARMV8_IMPDEF_PERFCTR_DMB_SPEC 0x7E - -#define ARMV8_IMPDEF_PERFCTR_EXC_UNDEF 0x81 -#define ARMV8_IMPDEF_PERFCTR_EXC_SVC 0x82 -#define ARMV8_IMPDEF_PERFCTR_EXC_PABORT 0x83 -#define ARMV8_IMPDEF_PERFCTR_EXC_DABORT 0x84 - -#define ARMV8_IMPDEF_PERFCTR_EXC_IRQ 0x86 -#define ARMV8_IMPDEF_PERFCTR_EXC_FIQ 0x87 -#define ARMV8_IMPDEF_PERFCTR_EXC_SMC 0x88 - -#define ARMV8_IMPDEF_PERFCTR_EXC_HVC 0x8A -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_PABORT 0x8B -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_DABORT 0x8C -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_OTHER 0x8D -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_IRQ 0x8E -#define ARMV8_IMPDEF_PERFCTR_EXC_TRAP_FIQ 0x8F -#define ARMV8_IMPDEF_PERFCTR_RC_LD_SPEC 0x90 -#define ARMV8_IMPDEF_PERFCTR_RC_ST_SPEC 0x91 - -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_RD 0xA0 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WR 0xA1 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_RD 0xA2 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_REFILL_WR 0xA3 - -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_VICTIM 0xA6 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_WB_CLEAN 0xA7 -#define ARMV8_IMPDEF_PERFCTR_L3D_CACHE_INVAL 0xA8 - /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -183,12 +40,10 @@ #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS 0xEC #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS 0xED -/* PMUv3 HW events mapping. */ - /* * ARMv8 Architectural defined events, not all of these may - * be supported on any given implementation. Undefined events will - * be disabled at run-time. + * be supported on any given implementation. Unsupported events will + * be disabled at run-time based on the PMCEID registers. */ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, @@ -210,8 +65,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, - [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE, - [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL, [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE, [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL, @@ -224,8 +77,6 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, - [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED, - [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED, }; static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] @@ -370,6 +221,18 @@ ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); ARMV8_EVENT_ATTR(l2i_tlb_refill, ARMV8_PMUV3_PERFCTR_L2I_TLB_REFILL); ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); ARMV8_EVENT_ATTR(l2i_tlb, ARMV8_PMUV3_PERFCTR_L2I_TLB); +ARMV8_EVENT_ATTR(remote_access, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS); +ARMV8_EVENT_ATTR(ll_cache, ARMV8_PMUV3_PERFCTR_LL_CACHE); +ARMV8_EVENT_ATTR(ll_cache_miss, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS); +ARMV8_EVENT_ATTR(dtlb_walk, ARMV8_PMUV3_PERFCTR_DTLB_WALK); +ARMV8_EVENT_ATTR(itlb_walk, ARMV8_PMUV3_PERFCTR_ITLB_WALK); +ARMV8_EVENT_ATTR(ll_cache_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_RD); +ARMV8_EVENT_ATTR(ll_cache_miss_rd, ARMV8_PMUV3_PERFCTR_LL_CACHE_MISS_RD); +ARMV8_EVENT_ATTR(remote_access_rd, ARMV8_PMUV3_PERFCTR_REMOTE_ACCESS_RD); +ARMV8_EVENT_ATTR(sample_pop, ARMV8_SPE_PERFCTR_SAMPLE_POP); +ARMV8_EVENT_ATTR(sample_feed, ARMV8_SPE_PERFCTR_SAMPLE_FEED); +ARMV8_EVENT_ATTR(sample_filtrate, ARMV8_SPE_PERFCTR_SAMPLE_FILTRATE); +ARMV8_EVENT_ATTR(sample_collision, ARMV8_SPE_PERFCTR_SAMPLE_COLLISION); static struct attribute *armv8_pmuv3_event_attrs[] = { &armv8_event_attr_sw_incr.attr.attr, @@ -420,6 +283,18 @@ static struct attribute *armv8_pmuv3_event_attrs[] = { &armv8_event_attr_l2i_tlb_refill.attr.attr, &armv8_event_attr_l2d_tlb.attr.attr, &armv8_event_attr_l2i_tlb.attr.attr, + &armv8_event_attr_remote_access.attr.attr, + &armv8_event_attr_ll_cache.attr.attr, + &armv8_event_attr_ll_cache_miss.attr.attr, + &armv8_event_attr_dtlb_walk.attr.attr, + &armv8_event_attr_itlb_walk.attr.attr, + &armv8_event_attr_ll_cache_rd.attr.attr, + &armv8_event_attr_ll_cache_miss_rd.attr.attr, + &armv8_event_attr_remote_access_rd.attr.attr, + &armv8_event_attr_sample_pop.attr.attr, + &armv8_event_attr_sample_feed.attr.attr, + &armv8_event_attr_sample_filtrate.attr.attr, + &armv8_event_attr_sample_collision.attr.attr, NULL, }; @@ -434,7 +309,13 @@ armv8pmu_event_attr_is_visible(struct kobject *kobj, pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr); - if (test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) + if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && + test_bit(pmu_attr->id, cpu_pmu->pmceid_bitmap)) + return attr->mode; + + pmu_attr->id -= ARMV8_PMUV3_EXT_COMMON_EVENT_BASE; + if (pmu_attr->id < ARMV8_PMUV3_MAX_COMMON_EVENTS && + test_bit(pmu_attr->id, cpu_pmu->pmceid_ext_bitmap)) return attr->mode; return 0; @@ -1009,7 +890,7 @@ static int __armv8_pmuv3_map_event(struct perf_event *event, if (armv8pmu_event_is_64bit(event)) event->hw.flags |= ARMPMU_EVT_64BIT; - /* Onl expose micro/arch events supported by this PMU */ + /* Only expose micro/arch events supported by this PMU */ if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) && test_bit(hw_event_id, armpmu->pmceid_bitmap)) { return hw_event_id; @@ -1061,6 +942,7 @@ static void __armv8pmu_probe_pmu(void *info) struct armv8pmu_probe_info *probe = info; struct arm_pmu *cpu_pmu = probe->pmu; u64 dfr0; + u64 pmceid_raw[2]; u32 pmceid[2]; int pmuver; @@ -1079,11 +961,17 @@ static void __armv8pmu_probe_pmu(void *info) /* Add the CPU cycles counter */ cpu_pmu->num_events += 1; - pmceid[0] = read_sysreg(pmceid0_el0); - pmceid[1] = read_sysreg(pmceid1_el0); + pmceid[0] = pmceid_raw[0] = read_sysreg(pmceid0_el0); + pmceid[1] = pmceid_raw[1] = read_sysreg(pmceid1_el0); bitmap_from_arr32(cpu_pmu->pmceid_bitmap, pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); + + pmceid[0] = pmceid_raw[0] >> 32; + pmceid[1] = pmceid_raw[1] >> 32; + + bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap, + pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS); } static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu) @@ -1109,16 +997,16 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu) if (ret) return ret; - cpu_pmu->handle_irq = armv8pmu_handle_irq, - cpu_pmu->enable = armv8pmu_enable_event, - cpu_pmu->disable = armv8pmu_disable_event, - cpu_pmu->read_counter = armv8pmu_read_counter, - cpu_pmu->write_counter = armv8pmu_write_counter, - cpu_pmu->get_event_idx = armv8pmu_get_event_idx, - cpu_pmu->clear_event_idx = armv8pmu_clear_event_idx, - cpu_pmu->start = armv8pmu_start, - cpu_pmu->stop = armv8pmu_stop, - cpu_pmu->reset = armv8pmu_reset, + cpu_pmu->handle_irq = armv8pmu_handle_irq; + cpu_pmu->enable = armv8pmu_enable_event; + cpu_pmu->disable = armv8pmu_disable_event; + cpu_pmu->read_counter = armv8pmu_read_counter; + cpu_pmu->write_counter = armv8pmu_write_counter; + cpu_pmu->get_event_idx = armv8pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv8pmu_clear_event_idx; + cpu_pmu->start = armv8pmu_start; + cpu_pmu->stop = armv8pmu_stop; + cpu_pmu->reset = armv8pmu_reset; cpu_pmu->set_event_filter = armv8pmu_set_event_filter; cpu_pmu->filter_match = armv8pmu_filter_match; @@ -1274,6 +1162,7 @@ static struct platform_driver armv8_pmu_driver = { .driver = { .name = ARMV8_PMU_PDEV_NAME, .of_match_table = armv8_pmu_of_device_ids, + .suppress_bind_attrs = true, }, .probe = armv8_pmu_device_probe, }; diff --git a/arch/arm64/kernel/pointer_auth.c b/arch/arm64/kernel/pointer_auth.c new file mode 100644 index 000000000000..c507b584259d --- /dev/null +++ b/arch/arm64/kernel/pointer_auth.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/errno.h> +#include <linux/prctl.h> +#include <linux/random.h> +#include <linux/sched.h> +#include <asm/cpufeature.h> +#include <asm/pointer_auth.h> + +int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg) +{ + struct ptrauth_keys *keys = &tsk->thread.keys_user; + unsigned long addr_key_mask = PR_PAC_APIAKEY | PR_PAC_APIBKEY | + PR_PAC_APDAKEY | PR_PAC_APDBKEY; + unsigned long key_mask = addr_key_mask | PR_PAC_APGAKEY; + + if (!system_supports_address_auth() && !system_supports_generic_auth()) + return -EINVAL; + + if (!arg) { + ptrauth_keys_init(keys); + ptrauth_keys_switch(keys); + return 0; + } + + if (arg & ~key_mask) + return -EINVAL; + + if (((arg & addr_key_mask) && !system_supports_address_auth()) || + ((arg & PR_PAC_APGAKEY) && !system_supports_generic_auth())) + return -EINVAL; + + if (arg & PR_PAC_APIAKEY) + get_random_bytes(&keys->apia, sizeof(keys->apia)); + if (arg & PR_PAC_APIBKEY) + get_random_bytes(&keys->apib, sizeof(keys->apib)); + if (arg & PR_PAC_APDAKEY) + get_random_bytes(&keys->apda, sizeof(keys->apda)); + if (arg & PR_PAC_APDBKEY) + get_random_bytes(&keys->apdb, sizeof(keys->apdb)); + if (arg & PR_PAC_APGAKEY) + get_random_bytes(&keys->apga, sizeof(keys->apga)); + + ptrauth_keys_switch(keys); + + return 0; +} diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index d9a4c2d6dd8b..a0f985a6ac50 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -57,9 +57,10 @@ #include <asm/fpsimd.h> #include <asm/mmu_context.h> #include <asm/processor.h> +#include <asm/pointer_auth.h> #include <asm/stacktrace.h> -#ifdef CONFIG_STACKPROTECTOR +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> unsigned long __stack_chk_guard __read_mostly; EXPORT_SYMBOL(__stack_chk_guard); @@ -429,6 +430,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, contextidr_thread_switch(next); entry_task_switch(next); uao_thread_switch(next); + ptrauth_thread_switch(next); /* * Complete any pending TLB or cache maintenance on this CPU in case @@ -459,7 +461,7 @@ unsigned long get_wchan(struct task_struct *p) frame.fp = thread_saved_fp(p); frame.pc = thread_saved_pc(p); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = p->curr_ret_stack; + frame.graph = 0; #endif do { if (unwind_frame(p, &frame)) @@ -496,4 +498,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) void arch_setup_new_exec(void) { current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0; + + ptrauth_thread_init_user(current); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1710a2d01669..9dce33b0e260 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -46,6 +46,7 @@ #include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/pgtable.h> +#include <asm/pointer_auth.h> #include <asm/stacktrace.h> #include <asm/syscall.h> #include <asm/traps.h> @@ -956,6 +957,30 @@ out: #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_PTR_AUTH +static int pac_mask_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + /* + * The PAC bits can differ across data and instruction pointers + * depending on TCR_EL1.TBID*, which we may make use of in future, so + * we expose separate masks. + */ + unsigned long mask = ptrauth_user_pac_mask(); + struct user_pac_mask uregs = { + .data_mask = mask, + .insn_mask = mask, + }; + + if (!system_supports_address_auth()) + return -EINVAL; + + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &uregs, 0, -1); +} +#endif /* CONFIG_ARM64_PTR_AUTH */ + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -968,6 +993,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_PTR_AUTH + REGSET_PAC_MASK, +#endif }; static const struct user_regset aarch64_regsets[] = { @@ -1037,6 +1065,16 @@ static const struct user_regset aarch64_regsets[] = { .get_size = sve_get_size, }, #endif +#ifdef CONFIG_ARM64_PTR_AUTH + [REGSET_PAC_MASK] = { + .core_note_type = NT_ARM_PAC_MASK, + .n = sizeof(struct user_pac_mask) / sizeof(u64), + .size = sizeof(u64), + .align = sizeof(u64), + .get = pac_mask_get, + /* this cannot be set dynamically */ + }, +#endif }; static const struct user_regset_view user_aarch64_view = { diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S index f407e422a720..95fd94209aae 100644 --- a/arch/arm64/kernel/relocate_kernel.S +++ b/arch/arm64/kernel/relocate_kernel.S @@ -32,6 +32,7 @@ ENTRY(arm64_relocate_new_kernel) /* Setup the list loop variables. */ + mov x18, x2 /* x18 = dtb address */ mov x17, x1 /* x17 = kimage_start */ mov x16, x0 /* x16 = kimage_head */ raw_dcache_line_size x15, x0 /* x15 = dcache line size */ @@ -107,7 +108,7 @@ ENTRY(arm64_relocate_new_kernel) isb /* Start new image. */ - mov x0, xzr + mov x0, x18 mov x1, xzr mov x2, xzr mov x3, xzr diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 933adbc0f654..53c40196b607 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -44,7 +44,7 @@ void *return_address(unsigned int level) frame.fp = (unsigned long)__builtin_frame_address(0); frame.pc = (unsigned long)return_address; /* dummy */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = current->curr_ret_stack; + frame.graph = 0; #endif walk_stackframe(current, &frame, save_return_addr, &data); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index f4fc1e0544b7..4b0e1231625c 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -388,6 +388,7 @@ static int dump_kernel_offset(struct notifier_block *self, unsigned long v, if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) { pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n", offset, KIMAGE_VADDR); + pr_emerg("PHYS_OFFSET: 0x%llx\n", PHYS_OFFSET); } else { pr_emerg("Kernel Offset: disabled\n"); } diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S index 62522342e1e4..184332286a81 100644 --- a/arch/arm64/kernel/smccc-call.S +++ b/arch/arm64/kernel/smccc-call.S @@ -13,7 +13,9 @@ */ #include <linux/linkage.h> #include <linux/arm-smccc.h> + #include <asm/asm-offsets.h> +#include <asm/assembler.h> .macro SMCCC instr .cfi_startproc @@ -40,6 +42,7 @@ ENTRY(__arm_smccc_smc) SMCCC smc ENDPROC(__arm_smccc_smc) +EXPORT_SYMBOL(__arm_smccc_smc) /* * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, @@ -50,3 +53,4 @@ ENDPROC(__arm_smccc_smc) ENTRY(__arm_smccc_hvc) SMCCC hvc ENDPROC(__arm_smccc_hvc) +EXPORT_SYMBOL(__arm_smccc_hvc) diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 96b8f2f51ab2..1598d6f7200a 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -141,6 +141,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) } } else { pr_err("CPU%u: failed to boot: %d\n", cpu, ret); + return ret; } secondary_data.task = NULL; @@ -151,7 +152,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) if (status == CPU_MMU_OFF) status = READ_ONCE(__early_cpu_boot_status); - switch (status) { + switch (status & CPU_BOOT_STATUS_MASK) { default: pr_err("CPU%u: failed in unknown state : 0x%lx\n", cpu, status); @@ -165,6 +166,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_crit("CPU%u: may not have shut down cleanly\n", cpu); case CPU_STUCK_IN_KERNEL: pr_crit("CPU%u: is stuck in kernel\n", cpu); + if (status & CPU_STUCK_REASON_52_BIT_VA) + pr_crit("CPU%u: does not support 52-bit VAs\n", cpu); + if (status & CPU_STUCK_REASON_NO_GRAN) + pr_crit("CPU%u: does not support %luK granule \n", cpu, PAGE_SIZE / SZ_1K); cpus_stuck_in_kernel++; break; case CPU_PANIC_KERNEL: diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 4989f7ea1e59..1a29f2695ff2 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -59,18 +59,17 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { - if (WARN_ON_ONCE(frame->graph == -1)) - return -EINVAL; - if (frame->graph < -1) - frame->graph += FTRACE_NOTRACE_DEPTH; - + struct ftrace_ret_stack *ret_stack; /* * This is a case where function graph tracer has * modified a return address (LR) in a stack frame * to hook a function return. * So replace it to an original value. */ - frame->pc = tsk->ret_stack[frame->graph--].ret; + ret_stack = ftrace_graph_get_ret_stack(tsk, frame->graph++); + if (WARN_ON_ONCE(!ret_stack)) + return -EINVAL; + frame->pc = ret_stack->ret; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -137,7 +136,7 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = current->curr_ret_stack; + frame.graph = 0; #endif walk_stackframe(current, &frame, save_trace, &data); @@ -168,7 +167,7 @@ static noinline void __save_stack_trace(struct task_struct *tsk, frame.pc = (unsigned long)__save_stack_trace; } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = tsk->curr_ret_stack; + frame.graph = 0; #endif walk_stackframe(tsk, &frame, save_trace, &data); diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index f258636273c9..a777ae90044d 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,7 +52,7 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.pc = regs->pc; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = current->curr_ret_stack; + frame.graph = 0; #endif do { int ret = unwind_frame(NULL, &frame); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 5f4d9acb32f5..4e2fb877f8d5 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -35,6 +35,7 @@ #include <linux/sizes.h> #include <linux/syscalls.h> #include <linux/mm_types.h> +#include <linux/kasan.h> #include <asm/atomic.h> #include <asm/bug.h> @@ -122,7 +123,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.pc = thread_saved_pc(tsk); } #ifdef CONFIG_FUNCTION_GRAPH_TRACER - frame.graph = tsk->curr_ret_stack; + frame.graph = 0; #endif skip = !!regs; @@ -969,6 +970,58 @@ static struct break_hook bug_break_hook = { .fn = bug_handler, }; +#ifdef CONFIG_KASAN_SW_TAGS + +#define KASAN_ESR_RECOVER 0x20 +#define KASAN_ESR_WRITE 0x10 +#define KASAN_ESR_SIZE_MASK 0x0f +#define KASAN_ESR_SIZE(esr) (1 << ((esr) & KASAN_ESR_SIZE_MASK)) + +static int kasan_handler(struct pt_regs *regs, unsigned int esr) +{ + bool recover = esr & KASAN_ESR_RECOVER; + bool write = esr & KASAN_ESR_WRITE; + size_t size = KASAN_ESR_SIZE(esr); + u64 addr = regs->regs[0]; + u64 pc = regs->pc; + + if (user_mode(regs)) + return DBG_HOOK_ERROR; + + kasan_report(addr, size, write, pc); + + /* + * The instrumentation allows to control whether we can proceed after + * a crash was detected. This is done by passing the -recover flag to + * the compiler. Disabling recovery allows to generate more compact + * code. + * + * Unfortunately disabling recovery doesn't work for the kernel right + * now. KASAN reporting is disabled in some contexts (for example when + * the allocator accesses slab object metadata; this is controlled by + * current->kasan_depth). All these accesses are detected by the tool, + * even though the reports for them are not printed. + * + * This is something that might be fixed at some point in the future. + */ + if (!recover) + die("Oops - KASAN", regs, 0); + + /* If thread survives, skip over the brk instruction and continue: */ + arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); + return DBG_HOOK_HANDLED; +} + +#define KASAN_ESR_VAL (0xf2000000 | KASAN_BRK_IMM) +#define KASAN_ESR_MASK 0xffffff00 + +static struct break_hook kasan_break_hook = { + .esr_val = KASAN_ESR_VAL, + .esr_mask = KASAN_ESR_MASK, + .fn = kasan_handler, +}; +#endif + /* * Initial handler for AArch64 BRK exceptions * This handler only used until debug_traps_init(). @@ -976,6 +1029,10 @@ static struct break_hook bug_break_hook = { int __init early_brk64(unsigned long addr, unsigned int esr, struct pt_regs *regs) { +#ifdef CONFIG_KASAN_SW_TAGS + if ((esr & KASAN_ESR_MASK) == KASAN_ESR_VAL) + return kasan_handler(regs, esr) != DBG_HOOK_HANDLED; +#endif return bug_handler(regs, esr) != DBG_HOOK_HANDLED; } @@ -983,4 +1040,7 @@ int __init early_brk64(unsigned long addr, unsigned int esr, void __init trap_init(void) { register_break_hook(&bug_break_hook); +#ifdef CONFIG_KASAN_SW_TAGS + register_break_hook(&kasan_break_hook); +#endif } diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 03b00007553d..7fa008374907 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -99,7 +99,8 @@ SECTIONS *(.discard) *(.discard.*) *(.interp .dynamic) - *(.dynsym .dynstr .hash) + *(.dynsym .dynstr .hash .gnu.hash) + *(.eh_frame) } . = KIMAGE_VADDR + TEXT_OFFSET; @@ -192,12 +193,12 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) - .rela : ALIGN(8) { + .rela.dyn : ALIGN(8) { *(.rela .rela*) } - __rela_offset = ABSOLUTE(ADDR(.rela) - KIMAGE_VADDR); - __rela_size = SIZEOF(.rela); + __rela_offset = ABSOLUTE(ADDR(.rela.dyn) - KIMAGE_VADDR); + __rela_size = SIZEOF(.rela.dyn); . = ALIGN(SEGMENT_ALIGN); __initdata_end = .; diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 47b23bf617c7..a3f85624313e 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -61,6 +61,6 @@ config KVM_ARM_PMU config KVM_INDIRECT_VECTORS def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS) -source drivers/vhost/Kconfig +source "drivers/vhost/Kconfig" endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 00d422336a45..f39801e4136c 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -236,24 +236,3 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) } } } - - -/* - * After successfully emulating an instruction, we might want to - * return to user space with a KVM_EXIT_DEBUG. We can only do this - * once the emulation is complete, though, so for userspace emulations - * we have to wait until we have re-entered KVM before calling this - * helper. - * - * Return true (and set exit_reason) to return to userspace or false - * if no further action is required. - */ -bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run) -{ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - run->exit_reason = KVM_EXIT_DEBUG; - run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT; - return true; - } - return false; -} diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 35a81bebd02b..0b7983442071 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -173,6 +173,23 @@ static int handle_sve(struct kvm_vcpu *vcpu, struct kvm_run *run) return 1; } +/* + * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into + * a NOP). + */ +static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + /* + * We don't currently support ptrauth in a guest, and we mask the ID + * registers to prevent well-behaved guests from trying to make use of + * it. + * + * Inject an UNDEF, as if the feature really isn't present. + */ + kvm_inject_undefined(vcpu); + return 1; +} + static exit_handle_fn arm_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec, [ESR_ELx_EC_WFx] = kvm_handle_wfx, @@ -195,6 +212,7 @@ static exit_handle_fn arm_exit_handlers[] = { [ESR_ELx_EC_BKPT32] = kvm_handle_guest_debug, [ESR_ELx_EC_BRK64] = kvm_handle_guest_debug, [ESR_ELx_EC_FP_ASIMD] = handle_no_fpsimd, + [ESR_ELx_EC_PAC] = kvm_handle_ptrauth, }; static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu) @@ -229,13 +247,6 @@ static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run) handled = exit_handler(vcpu, run); } - /* - * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run - * structure if we need to return to userspace. - */ - if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run)) - handled = 0; - return handled; } @@ -269,12 +280,7 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, case ARM_EXCEPTION_IRQ: return 1; case ARM_EXCEPTION_EL1_SERROR: - /* We may still need to return for single-step */ - if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS) - && kvm_arm_handle_step_debug(vcpu, run)) - return 0; - else - return 1; + return 1; case ARM_EXCEPTION_TRAP: return handle_trap_exceptions(vcpu, run); case ARM_EXCEPTION_HYP_GONE: diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index fad1e164fe48..675fdc186e3b 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -83,6 +83,7 @@ ENTRY(__guest_enter) // Do not touch any register after this! eret + sb ENDPROC(__guest_enter) ENTRY(__guest_exit) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index b1f14f736962..73c1b483ec39 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -96,6 +96,7 @@ el1_sync: // Guest trapped into EL2 do_el2_call eret + sb el1_hvc_guest: /* @@ -146,6 +147,7 @@ wa_epilogue: mov x0, xzr add sp, sp, #16 eret + sb el1_trap: get_vcpu_ptr x1, x0 @@ -199,6 +201,7 @@ el2_error: b.ne __hyp_panic mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) eret + sb ENTRY(__hyp_do_panic) mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ @@ -207,6 +210,7 @@ ENTRY(__hyp_do_panic) ldr lr, =panic msr elr_el2, lr eret + sb ENDPROC(__hyp_do_panic) ENTRY(__hyp_panic) diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index 7cc175c88a37..b0b1478094b4 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -143,6 +143,14 @@ static void deactivate_traps_vhe(void) { extern char vectors[]; /* kernel exception vectors */ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + + /* + * ARM erratum 1165522 requires the actual execution of the above + * before we can switch to the EL2/EL0 translation regime used by + * the host. + */ + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_1165522)); + write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); } @@ -157,7 +165,7 @@ static void __hyp_text __deactivate_traps_nvhe(void) mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; write_sysreg(mdcr_el2, mdcr_el2); - write_sysreg(HCR_RW, hcr_el2); + write_sysreg(HCR_HOST_NVHE_FLAGS, hcr_el2); write_sysreg(CPTR_EL2_DEFAULT, cptr_el2); } @@ -305,33 +313,6 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu) return true; } -/* Skip an instruction which has been emulated. Returns true if - * execution can continue or false if we need to exit hyp mode because - * single-step was in effect. - */ -static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu) -{ - *vcpu_pc(vcpu) = read_sysreg_el2(elr); - - if (vcpu_mode_is_32bit(vcpu)) { - vcpu->arch.ctxt.gp_regs.regs.pstate = read_sysreg_el2(spsr); - kvm_skip_instr32(vcpu, kvm_vcpu_trap_il_is32bit(vcpu)); - write_sysreg_el2(vcpu->arch.ctxt.gp_regs.regs.pstate, spsr); - } else { - *vcpu_pc(vcpu) += 4; - } - - write_sysreg_el2(*vcpu_pc(vcpu), elr); - - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - vcpu->arch.fault.esr_el2 = - (ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22; - return false; - } else { - return true; - } -} - static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu) { struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state; @@ -420,20 +401,12 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); - if (ret == 1 && __skip_instr(vcpu)) + if (ret == 1) return true; - if (ret == -1) { - /* Promote an illegal access to an - * SError. If we would be returning - * due to single-step clear the SS - * bit so handle_exit knows what to - * do after dealing with the error. - */ - if (!__skip_instr(vcpu)) - *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; + /* Promote an illegal access to an SError.*/ + if (ret == -1) *exit_code = ARM_EXCEPTION_EL1_SERROR; - } goto exit; } @@ -444,7 +417,7 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) { int ret = __vgic_v3_perform_cpuif_access(vcpu); - if (ret == 1 && __skip_instr(vcpu)) + if (ret == 1) return true; } @@ -499,8 +472,19 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); - __activate_traps(vcpu); + /* + * ARM erratum 1165522 requires us to configure both stage 1 and + * stage 2 translation for the guest context before we clear + * HCR_EL2.TGE. + * + * We have already configured the guest's stage 1 translation in + * kvm_vcpu_load_sysregs above. We must now call __activate_vm + * before __activate_traps, because __activate_vm configures + * stage 2 translation, and __activate_traps clear HCR_EL2.TGE + * (among other things). + */ __activate_vm(vcpu->kvm); + __activate_traps(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); @@ -545,8 +529,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_save_state_nvhe(host_ctxt); - __activate_traps(vcpu); __activate_vm(kern_hyp_va(vcpu->kvm)); + __activate_traps(vcpu); __hyp_vgic_restore_state(vcpu); __timer_enable_traps(vcpu); diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c index 4dbd9c69a96d..76c30866069e 100644 --- a/arch/arm64/kvm/hyp/tlb.c +++ b/arch/arm64/kvm/hyp/tlb.c @@ -15,20 +15,54 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/irqflags.h> + #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/tlbflush.h> -static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm) +struct tlb_inv_context { + unsigned long flags; + u64 tcr; + u64 sctlr; +}; + +static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm, + struct tlb_inv_context *cxt) { u64 val; + local_irq_save(cxt->flags); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { + /* + * For CPUs that are affected by ARM erratum 1165522, we + * cannot trust stage-1 to be in a correct state at that + * point. Since we do not want to force a full load of the + * vcpu state, we prevent the EL1 page-table walker to + * allocate new TLBs. This is done by setting the EPD bits + * in the TCR_EL1 register. We also need to prevent it to + * allocate IPA->PA walks, so we enable the S1 MMU... + */ + val = cxt->tcr = read_sysreg_el1(tcr); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, tcr); + val = cxt->sctlr = read_sysreg_el1(sctlr); + val |= SCTLR_ELx_M; + write_sysreg_el1(val, sctlr); + } + /* * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and * most TLB operations target EL2/EL0. In order to affect the * guest TLBs (EL1/EL0), we need to change one of these two * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so * let's flip TGE before executing the TLB operation. + * + * ARM erratum 1165522 requires some special handling (again), + * as we need to make sure both stages of translation are in + * place before clearing TGE. __load_guest_stage2() already + * has an ISB in order to deal with this. */ __load_guest_stage2(kvm); val = read_sysreg(hcr_el2); @@ -37,7 +71,8 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm) isb(); } -static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm) +static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm, + struct tlb_inv_context *cxt) { __load_guest_stage2(kvm); isb(); @@ -48,7 +83,8 @@ static hyp_alternate_select(__tlb_switch_to_guest, __tlb_switch_to_guest_vhe, ARM64_HAS_VIRT_HOST_EXTN); -static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm) +static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm, + struct tlb_inv_context *cxt) { /* * We're done with the TLB operation, let's restore the host's @@ -56,9 +92,19 @@ static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm) */ write_sysreg(0, vttbr_el2); write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + isb(); + + if (cpus_have_const_cap(ARM64_WORKAROUND_1165522)) { + /* Restore the registers to what they were */ + write_sysreg_el1(cxt->tcr, tcr); + write_sysreg_el1(cxt->sctlr, sctlr); + } + + local_irq_restore(cxt->flags); } -static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm) +static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm, + struct tlb_inv_context *cxt) { write_sysreg(0, vttbr_el2); } @@ -70,11 +116,13 @@ static hyp_alternate_select(__tlb_switch_to_host, void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) { + struct tlb_inv_context cxt; + dsb(ishst); /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm); + __tlb_switch_to_guest()(kvm, &cxt); /* * We could do so much better if we had the VA as well. @@ -117,36 +165,39 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) if (!has_vhe() && icache_is_vpipt()) __flush_icache_all(); - __tlb_switch_to_host()(kvm); + __tlb_switch_to_host()(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm) { + struct tlb_inv_context cxt; + dsb(ishst); /* Switch to requested VMID */ kvm = kern_hyp_va(kvm); - __tlb_switch_to_guest()(kvm); + __tlb_switch_to_guest()(kvm, &cxt); __tlbi(vmalls12e1is); dsb(ish); isb(); - __tlb_switch_to_host()(kvm); + __tlb_switch_to_host()(kvm, &cxt); } void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu) { struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm); + struct tlb_inv_context cxt; /* Switch to requested VMID */ - __tlb_switch_to_guest()(kvm); + __tlb_switch_to_guest()(kvm, &cxt); __tlbi(vmalle1); dsb(nsh); isb(); - __tlb_switch_to_host()(kvm); + __tlb_switch_to_host()(kvm, &cxt); } void __hyp_text __kvm_flush_vm_context(void) diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c index 215c7c0eb3b0..9cbdd034a563 100644 --- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -41,7 +41,7 @@ static bool __hyp_text __is_be(struct kvm_vcpu *vcpu) * Returns: * 1: GICV access successfully performed * 0: Not a GICV access - * -1: Illegal GICV access + * -1: Illegal GICV access successfully performed */ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) { @@ -61,12 +61,16 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) return 0; /* Reject anything but a 32bit access */ - if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) + if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) { + __kvm_skip_instr(vcpu); return -1; + } /* Not aligned? Don't bother */ - if (fault_ipa & 3) + if (fault_ipa & 3) { + __kvm_skip_instr(vcpu); return -1; + } rd = kvm_vcpu_dabt_get_rd(vcpu); addr = hyp_symbol_addr(kvm_vgic_global_state)->vcpu_hyp_va; @@ -88,5 +92,7 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) vcpu_set_reg(vcpu, rd, data); } + __kvm_skip_instr(vcpu); + return 1; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 22fbbdbece3c..e3e37228ae4e 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -76,7 +76,7 @@ static bool write_to_read_only(struct kvm_vcpu *vcpu, return false; } -u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg) +u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg) { if (!vcpu->arch.sysregs_loaded_on_cpu) goto immediate_read; @@ -1040,6 +1040,14 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz) kvm_debug("SVE unsupported for guests, suppressing\n"); val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); + } else if (id == SYS_ID_AA64ISAR1_EL1) { + const u64 ptrauth_mask = (0xfUL << ID_AA64ISAR1_APA_SHIFT) | + (0xfUL << ID_AA64ISAR1_API_SHIFT) | + (0xfUL << ID_AA64ISAR1_GPA_SHIFT) | + (0xfUL << ID_AA64ISAR1_GPI_SHIFT); + if (val & ptrauth_mask) + kvm_debug("ptrauth unsupported for guests, suppressing\n"); + val &= ~ptrauth_mask; } else if (id == SYS_ID_AA64MMFR1_EL1) { if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT)) kvm_debug("LORegions unsupported for guests, suppressing\n"); @@ -1850,6 +1858,8 @@ static void perform_access(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) { + trace_kvm_sys_access(*vcpu_pc(vcpu), params, r); + /* * Not having an accessor means that we have configured a trap * that we don't know how to handle. This certainly qualifies @@ -1912,8 +1922,8 @@ static void unhandled_cp_access(struct kvm_vcpu *vcpu, WARN_ON(1); } - kvm_err("Unsupported guest CP%d access at: %08lx\n", - cp, *vcpu_pc(vcpu)); + kvm_err("Unsupported guest CP%d access at: %08lx [%08lx]\n", + cp, *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); print_sys_reg_instr(params); kvm_inject_undefined(vcpu); } @@ -2063,8 +2073,8 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu, if (likely(r)) { perform_access(vcpu, params, r); } else { - kvm_err("Unsupported guest sys_reg access at: %lx\n", - *vcpu_pc(vcpu)); + kvm_err("Unsupported guest sys_reg access at: %lx [%08lx]\n", + *vcpu_pc(vcpu), *vcpu_cpsr(vcpu)); print_sys_reg_instr(params); kvm_inject_undefined(vcpu); } diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index cd710f8b63e0..3b1bc7f01d0b 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -35,6 +35,9 @@ struct sys_reg_params { }; struct sys_reg_desc { + /* Sysreg string for debug */ + const char *name; + /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; @@ -130,6 +133,7 @@ const struct sys_reg_desc *find_reg_by_id(u64 id, #define Op2(_x) .Op2 = _x #define SYS_DESC(reg) \ + .name = #reg, \ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) diff --git a/arch/arm64/kvm/trace.h b/arch/arm64/kvm/trace.h index 3b82fb1ddd09..eab91ad0effb 100644 --- a/arch/arm64/kvm/trace.h +++ b/arch/arm64/kvm/trace.h @@ -3,6 +3,7 @@ #define _TRACE_ARM64_KVM_H #include <linux/tracepoint.h> +#include "sys_regs.h" #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm @@ -152,6 +153,40 @@ TRACE_EVENT(kvm_handle_sys_reg, TP_printk("HSR 0x%08lx", __entry->hsr) ); +TRACE_EVENT(kvm_sys_access, + TP_PROTO(unsigned long vcpu_pc, struct sys_reg_params *params, const struct sys_reg_desc *reg), + TP_ARGS(vcpu_pc, params, reg), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_pc) + __field(bool, is_write) + __field(const char *, name) + __field(u8, Op0) + __field(u8, Op1) + __field(u8, CRn) + __field(u8, CRm) + __field(u8, Op2) + ), + + TP_fast_assign( + __entry->vcpu_pc = vcpu_pc; + __entry->is_write = params->is_write; + __entry->name = reg->name; + __entry->Op0 = reg->Op0; + __entry->Op0 = reg->Op0; + __entry->Op1 = reg->Op1; + __entry->CRn = reg->CRn; + __entry->CRm = reg->CRm; + __entry->Op2 = reg->Op2; + ), + + TP_printk("PC: %lx %s (%d,%d,%d,%d,%d) %s", + __entry->vcpu_pc, __entry->name ?: "UNKN", + __entry->Op0, __entry->Op1, __entry->CRn, + __entry->CRm, __entry->Op2, + __entry->is_write ? "write" : "read") +); + TRACE_EVENT(kvm_set_guest_debug, TP_PROTO(struct kvm_vcpu *vcpu, __u32 guest_debug), TP_ARGS(vcpu, guest_debug), diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index 69ff9887f724..5540a1638baf 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -5,6 +5,12 @@ lib-y := clear_user.o delay.o copy_from_user.o \ memcmp.o strcmp.o strncmp.o strlen.o strnlen.o \ strchr.o strrchr.o tishift.o +ifeq ($(CONFIG_KERNEL_MODE_NEON), y) +obj-$(CONFIG_XOR_BLOCKS) += xor-neon.o +CFLAGS_REMOVE_xor-neon.o += -mgeneral-regs-only +CFLAGS_xor-neon.o += -ffreestanding +endif + # Tell the compiler to treat all general purpose registers (with the # exception of the IP registers, which are already handled by the caller # in case of a PLT) as callee-saved, which allows for efficient runtime diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S index ef08e905e35b..6d13b0d64ad5 100644 --- a/arch/arm64/lib/clear_page.S +++ b/arch/arm64/lib/clear_page.S @@ -37,3 +37,4 @@ ENTRY(clear_page) b.ne 1b ret ENDPROC(clear_page) +EXPORT_SYMBOL(clear_page) diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 21ba0b29621b..feb225bd4b80 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -18,6 +18,7 @@ #include <linux/linkage.h> #include <asm/asm-uaccess.h> +#include <asm/assembler.h> .text @@ -53,6 +54,7 @@ uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 uaccess_disable_not_uao x2, x3 ret ENDPROC(__arch_clear_user) +EXPORT_SYMBOL(__arch_clear_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 20305d485046..dea6c762d52f 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -16,8 +16,9 @@ #include <linux/linkage.h> -#include <asm/cache.h> #include <asm/asm-uaccess.h> +#include <asm/assembler.h> +#include <asm/cache.h> /* * Copy from user space to a kernel buffer (alignment handled by the hardware) @@ -71,6 +72,7 @@ ENTRY(__arch_copy_from_user) mov x0, #0 // Nothing to copy ret ENDPROC(__arch_copy_from_user) +EXPORT_SYMBOL(__arch_copy_from_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 54b75deb1d16..a84227fbf716 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -18,8 +18,9 @@ #include <linux/linkage.h> -#include <asm/cache.h> #include <asm/asm-uaccess.h> +#include <asm/assembler.h> +#include <asm/cache.h> /* * Copy from user space to user space (alignment handled by the hardware) @@ -73,6 +74,7 @@ ENTRY(__arch_copy_in_user) mov x0, #0 ret ENDPROC(__arch_copy_in_user) +EXPORT_SYMBOL(__arch_copy_in_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S index 076c43715e64..98313e24a987 100644 --- a/arch/arm64/lib/copy_page.S +++ b/arch/arm64/lib/copy_page.S @@ -87,3 +87,4 @@ alternative_else_nop_endif ret ENDPROC(copy_page) +EXPORT_SYMBOL(copy_page) diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index fda6172d6b88..ef44c7ca3ffb 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -16,8 +16,9 @@ #include <linux/linkage.h> -#include <asm/cache.h> #include <asm/asm-uaccess.h> +#include <asm/assembler.h> +#include <asm/cache.h> /* * Copy to user space from a kernel buffer (alignment handled by the hardware) @@ -70,6 +71,7 @@ ENTRY(__arch_copy_to_user) mov x0, #0 ret ENDPROC(__arch_copy_to_user) +EXPORT_SYMBOL(__arch_copy_to_user) .section .fixup,"ax" .align 2 diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S index 5bc1e85b4e1c..f132f2a7522e 100644 --- a/arch/arm64/lib/crc32.S +++ b/arch/arm64/lib/crc32.S @@ -15,15 +15,59 @@ .cpu generic+crc .macro __crc32, c -0: subs x2, x2, #16 - b.mi 8f - ldp x3, x4, [x1], #16 + cmp x2, #16 + b.lt 8f // less than 16 bytes + + and x7, x2, #0x1f + and x2, x2, #~0x1f + cbz x7, 32f // multiple of 32 bytes + + and x8, x7, #0xf + ldp x3, x4, [x1] + add x8, x8, x1 + add x1, x1, x7 + ldp x5, x6, [x8] CPU_BE( rev x3, x3 ) CPU_BE( rev x4, x4 ) +CPU_BE( rev x5, x5 ) +CPU_BE( rev x6, x6 ) + + tst x7, #8 + crc32\c\()x w8, w0, x3 + csel x3, x3, x4, eq + csel w0, w0, w8, eq + tst x7, #4 + lsr x4, x3, #32 + crc32\c\()w w8, w0, w3 + csel x3, x3, x4, eq + csel w0, w0, w8, eq + tst x7, #2 + lsr w4, w3, #16 + crc32\c\()h w8, w0, w3 + csel w3, w3, w4, eq + csel w0, w0, w8, eq + tst x7, #1 + crc32\c\()b w8, w0, w3 + csel w0, w0, w8, eq + tst x7, #16 + crc32\c\()x w8, w0, x5 + crc32\c\()x w8, w8, x6 + csel w0, w0, w8, eq + cbz x2, 0f + +32: ldp x3, x4, [x1], #32 + sub x2, x2, #32 + ldp x5, x6, [x1, #-16] +CPU_BE( rev x3, x3 ) +CPU_BE( rev x4, x4 ) +CPU_BE( rev x5, x5 ) +CPU_BE( rev x6, x6 ) crc32\c\()x w0, w0, x3 crc32\c\()x w0, w0, x4 - b.ne 0b - ret + crc32\c\()x w0, w0, x5 + crc32\c\()x w0, w0, x6 + cbnz x2, 32b +0: ret 8: tbz x2, #3, 4f ldr x3, [x1], #8 diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S index 0f164a4baf52..f146b7ecd28f 100644 --- a/arch/arm64/lib/memchr.S +++ b/arch/arm64/lib/memchr.S @@ -42,3 +42,4 @@ WEAK(memchr) 2: mov x0, #0 ret ENDPIPROC(memchr) +EXPORT_SYMBOL_NOKASAN(memchr) diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S index fb295f52e9f8..e2e629b09049 100644 --- a/arch/arm64/lib/memcmp.S +++ b/arch/arm64/lib/memcmp.S @@ -256,3 +256,4 @@ CPU_LE( rev data2, data2 ) mov result, #0 ret ENDPIPROC(memcmp) +EXPORT_SYMBOL_NOKASAN(memcmp) diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index 67613937711f..b4f82888ed60 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -74,4 +74,6 @@ ENTRY(memcpy) #include "copy_template.S" ret ENDPIPROC(memcpy) +EXPORT_SYMBOL(memcpy) ENDPROC(__memcpy) +EXPORT_SYMBOL(__memcpy) diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S index a5a4459013b1..ef12f719d99d 100644 --- a/arch/arm64/lib/memmove.S +++ b/arch/arm64/lib/memmove.S @@ -197,4 +197,6 @@ ENTRY(memmove) b.ne .Ltail63 ret ENDPIPROC(memmove) +EXPORT_SYMBOL(memmove) ENDPROC(__memmove) +EXPORT_SYMBOL(__memmove) diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S index f2670a9f218c..a79cf118d6d0 100644 --- a/arch/arm64/lib/memset.S +++ b/arch/arm64/lib/memset.S @@ -216,4 +216,6 @@ ENTRY(memset) b.ne .Ltail_maybe_long ret ENDPIPROC(memset) +EXPORT_SYMBOL(memset) ENDPROC(__memset) +EXPORT_SYMBOL(__memset) diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S index 7c83091d1bcd..b179421f46c7 100644 --- a/arch/arm64/lib/strchr.S +++ b/arch/arm64/lib/strchr.S @@ -40,3 +40,4 @@ WEAK(strchr) csel x0, x0, xzr, eq ret ENDPROC(strchr) +EXPORT_SYMBOL_NOKASAN(strchr) diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S index 7d5d15398bfb..c306c7b88574 100644 --- a/arch/arm64/lib/strcmp.S +++ b/arch/arm64/lib/strcmp.S @@ -232,3 +232,4 @@ CPU_BE( orr syndrome, diff, has_nul ) sub result, data1, data2, lsr #56 ret ENDPIPROC(strcmp) +EXPORT_SYMBOL_NOKASAN(strcmp) diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S index 8e0b14205dcb..2a0240937416 100644 --- a/arch/arm64/lib/strlen.S +++ b/arch/arm64/lib/strlen.S @@ -124,3 +124,4 @@ CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */ csel data2, data2, data2a, le b .Lrealigned ENDPIPROC(strlen) +EXPORT_SYMBOL_NOKASAN(strlen) diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index 66bd145935d9..c5d567afb039 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -308,3 +308,4 @@ CPU_BE( orr syndrome, diff, has_nul ) mov result, #0 ret ENDPIPROC(strncmp) +EXPORT_SYMBOL_NOKASAN(strncmp) diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index 355be04441fe..e21e536d420e 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -169,3 +169,4 @@ CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ mov len, limit ret ENDPIPROC(strnlen) +EXPORT_SYMBOL_NOKASAN(strnlen) diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S index ea84924d5990..47e1593016dc 100644 --- a/arch/arm64/lib/strrchr.S +++ b/arch/arm64/lib/strrchr.S @@ -41,3 +41,4 @@ WEAK(strrchr) 2: mov x0, x3 ret ENDPIPROC(strrchr) +EXPORT_SYMBOL_NOKASAN(strrchr) diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S index 0fdff97794de..047622536535 100644 --- a/arch/arm64/lib/tishift.S +++ b/arch/arm64/lib/tishift.S @@ -5,6 +5,8 @@ #include <linux/linkage.h> +#include <asm/assembler.h> + ENTRY(__ashlti3) cbz x2, 1f mov x3, #64 @@ -25,6 +27,7 @@ ENTRY(__ashlti3) mov x0, x2 ret ENDPROC(__ashlti3) +EXPORT_SYMBOL(__ashlti3) ENTRY(__ashrti3) cbz x2, 1f @@ -46,6 +49,7 @@ ENTRY(__ashrti3) mov x1, x2 ret ENDPROC(__ashrti3) +EXPORT_SYMBOL(__ashrti3) ENTRY(__lshrti3) cbz x2, 1f @@ -67,3 +71,4 @@ ENTRY(__lshrti3) mov x1, x2 ret ENDPROC(__lshrti3) +EXPORT_SYMBOL(__lshrti3) diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c new file mode 100644 index 000000000000..131c60c27dff --- /dev/null +++ b/arch/arm64/lib/xor-neon.c @@ -0,0 +1,184 @@ +/* + * arch/arm64/lib/xor-neon.c + * + * Authors: Jackie Liu <liuyun01@kylinos.cn> + * Copyright (C) 2018,Tianjin KYLIN Information Technology Co., Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/raid/xor.h> +#include <linux/module.h> +#include <asm/neon-intrinsics.h> + +void xor_arm64_neon_2(unsigned long bytes, unsigned long *p1, + unsigned long *p2) +{ + uint64_t *dp1 = (uint64_t *)p1; + uint64_t *dp2 = (uint64_t *)p2; + + register uint64x2_t v0, v1, v2, v3; + long lines = bytes / (sizeof(uint64x2_t) * 4); + + do { + /* p1 ^= p2 */ + v0 = veorq_u64(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0)); + v1 = veorq_u64(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2)); + v2 = veorq_u64(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4)); + v3 = veorq_u64(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6)); + + /* store */ + vst1q_u64(dp1 + 0, v0); + vst1q_u64(dp1 + 2, v1); + vst1q_u64(dp1 + 4, v2); + vst1q_u64(dp1 + 6, v3); + + dp1 += 8; + dp2 += 8; + } while (--lines > 0); +} + +void xor_arm64_neon_3(unsigned long bytes, unsigned long *p1, + unsigned long *p2, unsigned long *p3) +{ + uint64_t *dp1 = (uint64_t *)p1; + uint64_t *dp2 = (uint64_t *)p2; + uint64_t *dp3 = (uint64_t *)p3; + + register uint64x2_t v0, v1, v2, v3; + long lines = bytes / (sizeof(uint64x2_t) * 4); + + do { + /* p1 ^= p2 */ + v0 = veorq_u64(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0)); + v1 = veorq_u64(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2)); + v2 = veorq_u64(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4)); + v3 = veorq_u64(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6)); + + /* p1 ^= p3 */ + v0 = veorq_u64(v0, vld1q_u64(dp3 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp3 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp3 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp3 + 6)); + + /* store */ + vst1q_u64(dp1 + 0, v0); + vst1q_u64(dp1 + 2, v1); + vst1q_u64(dp1 + 4, v2); + vst1q_u64(dp1 + 6, v3); + + dp1 += 8; + dp2 += 8; + dp3 += 8; + } while (--lines > 0); +} + +void xor_arm64_neon_4(unsigned long bytes, unsigned long *p1, + unsigned long *p2, unsigned long *p3, unsigned long *p4) +{ + uint64_t *dp1 = (uint64_t *)p1; + uint64_t *dp2 = (uint64_t *)p2; + uint64_t *dp3 = (uint64_t *)p3; + uint64_t *dp4 = (uint64_t *)p4; + + register uint64x2_t v0, v1, v2, v3; + long lines = bytes / (sizeof(uint64x2_t) * 4); + + do { + /* p1 ^= p2 */ + v0 = veorq_u64(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0)); + v1 = veorq_u64(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2)); + v2 = veorq_u64(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4)); + v3 = veorq_u64(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6)); + + /* p1 ^= p3 */ + v0 = veorq_u64(v0, vld1q_u64(dp3 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp3 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp3 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp3 + 6)); + + /* p1 ^= p4 */ + v0 = veorq_u64(v0, vld1q_u64(dp4 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp4 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp4 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp4 + 6)); + + /* store */ + vst1q_u64(dp1 + 0, v0); + vst1q_u64(dp1 + 2, v1); + vst1q_u64(dp1 + 4, v2); + vst1q_u64(dp1 + 6, v3); + + dp1 += 8; + dp2 += 8; + dp3 += 8; + dp4 += 8; + } while (--lines > 0); +} + +void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1, + unsigned long *p2, unsigned long *p3, + unsigned long *p4, unsigned long *p5) +{ + uint64_t *dp1 = (uint64_t *)p1; + uint64_t *dp2 = (uint64_t *)p2; + uint64_t *dp3 = (uint64_t *)p3; + uint64_t *dp4 = (uint64_t *)p4; + uint64_t *dp5 = (uint64_t *)p5; + + register uint64x2_t v0, v1, v2, v3; + long lines = bytes / (sizeof(uint64x2_t) * 4); + + do { + /* p1 ^= p2 */ + v0 = veorq_u64(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0)); + v1 = veorq_u64(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2)); + v2 = veorq_u64(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4)); + v3 = veorq_u64(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6)); + + /* p1 ^= p3 */ + v0 = veorq_u64(v0, vld1q_u64(dp3 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp3 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp3 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp3 + 6)); + + /* p1 ^= p4 */ + v0 = veorq_u64(v0, vld1q_u64(dp4 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp4 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp4 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp4 + 6)); + + /* p1 ^= p5 */ + v0 = veorq_u64(v0, vld1q_u64(dp5 + 0)); + v1 = veorq_u64(v1, vld1q_u64(dp5 + 2)); + v2 = veorq_u64(v2, vld1q_u64(dp5 + 4)); + v3 = veorq_u64(v3, vld1q_u64(dp5 + 6)); + + /* store */ + vst1q_u64(dp1 + 0, v0); + vst1q_u64(dp1 + 2, v1); + vst1q_u64(dp1 + 4, v2); + vst1q_u64(dp1 + 6, v3); + + dp1 += 8; + dp2 += 8; + dp3 += 8; + dp4 += 8; + dp5 += 8; + } while (--lines > 0); +} + +struct xor_block_template const xor_block_inner_neon = { + .name = "__inner_neon__", + .do_2 = xor_arm64_neon_2, + .do_3 = xor_arm64_neon_3, + .do_4 = xor_arm64_neon_4, + .do_5 = xor_arm64_neon_5, +}; +EXPORT_SYMBOL(xor_block_inner_neon); + +MODULE_AUTHOR("Jackie Liu <liuyun01@kylinos.cn>"); +MODULE_DESCRIPTION("ARMv8 XOR Extensions"); +MODULE_LICENSE("GPL"); diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index 0c22ede52f90..a194fd0e837f 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -212,6 +212,9 @@ ENDPROC(__dma_clean_area) * - size - size in question */ ENTRY(__clean_dcache_area_pop) + alternative_if_not ARM64_HAS_DCPOP + b __clean_dcache_area_poc + alternative_else_nop_endif dcache_by_line_op cvap, sy, x0, x1, x2, x3 ret ENDPIPROC(__clean_dcache_area_pop) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index a3ac26284845..fb0908456a1f 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -33,113 +33,6 @@ #include <asm/cacheflush.h> -static struct gen_pool *atomic_pool __ro_after_init; - -#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; - -static int __init early_coherent_pool(char *p) -{ - atomic_pool_size = memparse(p, &p); - return 0; -} -early_param("coherent_pool", early_coherent_pool); - -static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) -{ - unsigned long val; - void *ptr = NULL; - - if (!atomic_pool) { - WARN(1, "coherent pool not initialised!\n"); - return NULL; - } - - val = gen_pool_alloc(atomic_pool, size); - if (val) { - phys_addr_t phys = gen_pool_virt_to_phys(atomic_pool, val); - - *ret_page = phys_to_page(phys); - ptr = (void *)val; - memset(ptr, 0, size); - } - - return ptr; -} - -static bool __in_atomic_pool(void *start, size_t size) -{ - return addr_in_gen_pool(atomic_pool, (unsigned long)start, size); -} - -static int __free_from_pool(void *start, size_t size) -{ - if (!__in_atomic_pool(start, size)) - return 0; - - gen_pool_free(atomic_pool, (unsigned long)start, size); - - return 1; -} - -void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, - gfp_t flags, unsigned long attrs) -{ - struct page *page; - void *ptr, *coherent_ptr; - pgprot_t prot = pgprot_writecombine(PAGE_KERNEL); - - size = PAGE_ALIGN(size); - - if (!gfpflags_allow_blocking(flags)) { - struct page *page = NULL; - void *addr = __alloc_from_pool(size, &page, flags); - - if (addr) - *dma_handle = phys_to_dma(dev, page_to_phys(page)); - - return addr; - } - - ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs); - if (!ptr) - goto no_mem; - - /* remove any dirty cache lines on the kernel alias */ - __dma_flush_area(ptr, size); - - /* create a coherent mapping */ - page = virt_to_page(ptr); - coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - prot, __builtin_return_address(0)); - if (!coherent_ptr) - goto no_map; - - return coherent_ptr; - -no_map: - dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs); -no_mem: - return NULL; -} - -void arch_dma_free(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_handle, unsigned long attrs) -{ - if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) { - void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle)); - - vunmap(vaddr); - dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs); - } -} - -long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr, - dma_addr_t dma_addr) -{ - return __phys_to_pfn(dma_to_phys(dev, dma_addr)); -} - pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot, unsigned long attrs) { @@ -160,6 +53,11 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, __dma_unmap_area(phys_to_virt(paddr), size, dir); } +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + __dma_flush_area(page_address(page), size); +} + #ifdef CONFIG_IOMMU_DMA static int __swiotlb_get_sgtable_page(struct sg_table *sgt, struct page *page, size_t size) @@ -191,167 +89,13 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma, } #endif /* CONFIG_IOMMU_DMA */ -static int __init atomic_pool_init(void) -{ - pgprot_t prot = __pgprot(PROT_NORMAL_NC); - unsigned long nr_pages = atomic_pool_size >> PAGE_SHIFT; - struct page *page; - void *addr; - unsigned int pool_size_order = get_order(atomic_pool_size); - - if (dev_get_cma_area(NULL)) - page = dma_alloc_from_contiguous(NULL, nr_pages, - pool_size_order, false); - else - page = alloc_pages(GFP_DMA32, pool_size_order); - - if (page) { - int ret; - void *page_addr = page_address(page); - - memset(page_addr, 0, atomic_pool_size); - __dma_flush_area(page_addr, atomic_pool_size); - - atomic_pool = gen_pool_create(PAGE_SHIFT, -1); - if (!atomic_pool) - goto free_page; - - addr = dma_common_contiguous_remap(page, atomic_pool_size, - VM_USERMAP, prot, atomic_pool_init); - - if (!addr) - goto destroy_genpool; - - ret = gen_pool_add_virt(atomic_pool, (unsigned long)addr, - page_to_phys(page), - atomic_pool_size, -1); - if (ret) - goto remove_mapping; - - gen_pool_set_algo(atomic_pool, - gen_pool_first_fit_order_align, - NULL); - - pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n", - atomic_pool_size / 1024); - return 0; - } - goto out; - -remove_mapping: - dma_common_free_remap(addr, atomic_pool_size, VM_USERMAP); -destroy_genpool: - gen_pool_destroy(atomic_pool); - atomic_pool = NULL; -free_page: - if (!dma_release_from_contiguous(NULL, page, nr_pages)) - __free_pages(page, pool_size_order); -out: - pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", - atomic_pool_size / 1024); - return -ENOMEM; -} - -/******************************************** - * The following APIs are for dummy DMA ops * - ********************************************/ - -static void *__dummy_alloc(struct device *dev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, - unsigned long attrs) -{ - return NULL; -} - -static void __dummy_free(struct device *dev, size_t size, - void *vaddr, dma_addr_t dma_handle, - unsigned long attrs) -{ -} - -static int __dummy_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - unsigned long attrs) -{ - return -ENXIO; -} - -static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, - unsigned long offset, size_t size, - enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, - size_t size, enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, - int nelems, enum dma_data_direction dir, - unsigned long attrs) -{ - return 0; -} - -static void __dummy_unmap_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir, - unsigned long attrs) -{ -} - -static void __dummy_sync_single(struct device *dev, - dma_addr_t dev_addr, size_t size, - enum dma_data_direction dir) -{ -} - -static void __dummy_sync_sg(struct device *dev, - struct scatterlist *sgl, int nelems, - enum dma_data_direction dir) -{ -} - -static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) -{ - return 1; -} - -static int __dummy_dma_supported(struct device *hwdev, u64 mask) -{ - return 0; -} - -const struct dma_map_ops dummy_dma_ops = { - .alloc = __dummy_alloc, - .free = __dummy_free, - .mmap = __dummy_mmap, - .map_page = __dummy_map_page, - .unmap_page = __dummy_unmap_page, - .map_sg = __dummy_map_sg, - .unmap_sg = __dummy_unmap_sg, - .sync_single_for_cpu = __dummy_sync_single, - .sync_single_for_device = __dummy_sync_single, - .sync_sg_for_cpu = __dummy_sync_sg, - .sync_sg_for_device = __dummy_sync_sg, - .mapping_error = __dummy_mapping_error, - .dma_supported = __dummy_dma_supported, -}; -EXPORT_SYMBOL(dummy_dma_ops); - static int __init arm64_dma_init(void) { WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(), TAINT_CPU_OUT_OF_SPEC, "ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)", ARCH_DMA_MINALIGN, cache_line_size()); - - return atomic_pool_init(); + return dma_atomic_pool_init(GFP_DMA32, __pgprot(PROT_NORMAL_NC)); } arch_initcall(arm64_dma_init); @@ -397,17 +141,17 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, page = alloc_pages(gfp, get_order(size)); addr = page ? page_address(page) : NULL; } else { - addr = __alloc_from_pool(size, &page, gfp); + addr = dma_alloc_from_pool(size, &page, gfp); } if (!addr) return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { if (coherent) __free_pages(page, get_order(size)); else - __free_from_pool(addr, size); + dma_free_from_pool(addr, size); addr = NULL; } } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { @@ -420,7 +164,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, return NULL; *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); - if (iommu_dma_mapping_error(dev, *handle)) { + if (*handle == DMA_MAPPING_ERROR) { dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT); return NULL; @@ -429,9 +173,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size, prot, __builtin_return_address(0)); if (addr) { - memset(addr, 0, size); if (!coherent) __dma_flush_area(page_to_virt(page), iosize); + memset(addr, 0, size); } else { iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs); dma_release_from_contiguous(dev, page, @@ -471,9 +215,9 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, * coherent devices. * Hence how dodgy the below logic looks... */ - if (__in_atomic_pool(cpu_addr, size)) { + if (dma_in_atomic_pool(cpu_addr, size)) { iommu_dma_unmap_page(dev, handle, iosize, 0, 0); - __free_from_pool(cpu_addr, size); + dma_free_from_pool(cpu_addr, size); } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) { struct page *page = vmalloc_to_page(cpu_addr); @@ -580,7 +324,7 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - !iommu_dma_mapping_error(dev, dev_addr)) + dev_addr != DMA_MAPPING_ERROR) __dma_map_area(page_address(page) + offset, size, dir); return dev_addr; @@ -663,7 +407,6 @@ static const struct dma_map_ops iommu_dma_ops = { .sync_sg_for_device = __iommu_sync_sg_for_device, .map_resource = iommu_dma_map_resource, .unmap_resource = iommu_dma_unmap_resource, - .mapping_error = iommu_dma_mapping_error, }; static int __init __iommu_dma_init(void) @@ -719,9 +462,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, const struct iommu_ops *iommu, bool coherent) { - if (!dev->dma_ops) - dev->dma_ops = &swiotlb_dma_ops; - dev->dma_coherent = coherent; __iommu_setup_dma_ops(dev, dma_base, size, iommu); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 7d9571f4ae3d..efb7b2cbead5 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -40,6 +40,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> +#include <asm/kasan.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/pgtable.h> @@ -132,6 +133,18 @@ static void mem_abort_decode(unsigned int esr) data_abort_decode(esr); } +static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= VA_START; +} + /* * Dump out the page tables associated with 'addr' in the currently active mm. */ @@ -141,7 +154,7 @@ void show_pte(unsigned long addr) pgd_t *pgdp; pgd_t pgd; - if (addr < TASK_SIZE) { + if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { @@ -149,7 +162,7 @@ void show_pte(unsigned long addr) addr); return; } - } else if (addr >= VA_START) { + } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { @@ -160,7 +173,7 @@ void show_pte(unsigned long addr) pr_alert("%s pgtable: %luk pages, %u-bit VAs, pgdp = %p\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, - VA_BITS, mm->pgd); + mm == &init_mm ? VA_BITS : (int) vabits_user, mm->pgd); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); @@ -254,7 +267,7 @@ static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr, if (fsc_type == ESR_ELx_FSC_PERM) return true; - if (addr < TASK_SIZE && system_uses_ttbr0_pan()) + if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return fsc_type == ESR_ELx_FSC_FAULT && (regs->pstate & PSR_PAN_BIT); @@ -319,7 +332,7 @@ static void set_thread_esr(unsigned long address, unsigned int esr) * type", so we ignore this wrinkle and just return the translation * fault.) */ - if (current->thread.fault_address >= TASK_SIZE) { + if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* @@ -455,7 +468,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, mm_flags |= FAULT_FLAG_WRITE; } - if (addr < TASK_SIZE && is_el1_permission_fault(addr, esr, regs)) { + if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { /* regs->orig_addr_limit may be 0 if we entered from EL0 */ if (regs->orig_addr_limit == KERNEL_DS) die_kernel_fault("access to user memory with fs=KERNEL_DS", @@ -603,7 +616,7 @@ static int __kprobes do_translation_fault(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - if (addr < TASK_SIZE) + if (is_ttbr0_addr(addr)) return do_page_fault(addr, esr, regs); do_bad_area(addr, esr, regs); @@ -758,7 +771,7 @@ asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr, * re-enabled IRQs. If the address is a kernel address, apply * BP hardening prior to enabling IRQs and pre-emption. */ - if (addr > TASK_SIZE) + if (!is_ttbr0_addr(addr)) arm64_apply_bp_hardening(); local_daif_restore(DAIF_PROCCTX); @@ -771,7 +784,7 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr, struct pt_regs *regs) { if (user_mode(regs)) { - if (instruction_pointer(regs) > TASK_SIZE) + if (!is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); local_daif_restore(DAIF_PROCCTX); } @@ -825,7 +838,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr, if (interrupts_enabled(regs)) trace_hardirqs_off(); - if (user_mode(regs) && instruction_pointer(regs) > TASK_SIZE) + if (user_mode(regs) && !is_ttbr0_addr(instruction_pointer(regs))) arm64_apply_bp_hardening(); if (!inf->fn(addr, esr, regs)) { diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index f58ea503ad01..28cbc22d7e30 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -429,6 +429,27 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma, clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig); } +static void __init add_huge_page_size(unsigned long size) +{ + if (size_to_hstate(size)) + return; + + hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); +} + +static int __init hugetlbpage_init(void) +{ +#ifdef CONFIG_ARM64_4K_PAGES + add_huge_page_size(PUD_SIZE); +#endif + add_huge_page_size(PMD_SIZE * CONT_PMDS); + add_huge_page_size(PMD_SIZE); + add_huge_page_size(PAGE_SIZE * CONT_PTES); + + return 0; +} +arch_initcall(hugetlbpage_init); + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); @@ -440,7 +461,7 @@ static __init int setup_hugepagesz(char *opt) case PMD_SIZE * CONT_PMDS: case PMD_SIZE: case PAGE_SIZE * CONT_PTES: - hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT); + add_huge_page_size(ps); return 1; } @@ -449,13 +470,3 @@ static __init int setup_hugepagesz(char *opt) return 0; } __setup("hugepagesz=", setup_hugepagesz); - -#ifdef CONFIG_ARM64_64K_PAGES -static __init int add_default_hugepagesz(void) -{ - if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) - hugetlb_add_hstate(CONT_PTE_SHIFT); - return 0; -} -arch_initcall(add_default_hugepagesz); -#endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9b432d9fcada..a8f2e4792ef9 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -59,25 +59,9 @@ * that cannot be mistaken for a real physical address. */ s64 memstart_addr __ro_after_init = -1; -phys_addr_t arm64_dma_phys_limit __ro_after_init; - -#ifdef CONFIG_BLK_DEV_INITRD -static int __init early_initrd(char *p) -{ - unsigned long start, size; - char *endp; - - start = memparse(p, &endp); - if (*endp == ',') { - size = memparse(endp + 1, NULL); +EXPORT_SYMBOL(memstart_addr); - initrd_start = start; - initrd_end = start + size; - } - return 0; -} -early_param("initrd", early_initrd); -#endif +phys_addr_t arm64_dma_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -289,6 +273,14 @@ int pfn_valid(unsigned long pfn) if ((addr >> PAGE_SHIFT) != pfn) return 0; + +#ifdef CONFIG_SPARSEMEM + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) + return 0; + + if (!valid_section(__nr_to_section(pfn_to_section_nr(pfn)))) + return 0; +#endif return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_valid); @@ -407,14 +399,14 @@ void __init arm64_memblock_init(void) memblock_add(__pa_symbol(_text), (u64)(_end - _text)); } - if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) { + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* * Add back the memory we just removed if it results in the * initrd to become inaccessible via the linear mapping. * Otherwise, this is a no-op */ - u64 base = initrd_start & PAGE_MASK; - u64 size = PAGE_ALIGN(initrd_end) - base; + u64 base = phys_initrd_start & PAGE_MASK; + u64 size = PAGE_ALIGN(phys_initrd_size); /* * We can only add back the initrd memory if we don't end up @@ -458,15 +450,11 @@ void __init arm64_memblock_init(void) * pagetables with memblock. */ memblock_reserve(__pa_symbol(_text), _end - _text); -#ifdef CONFIG_BLK_DEV_INITRD - if (initrd_start) { - memblock_reserve(initrd_start, initrd_end - initrd_start); - + if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ - initrd_start = __phys_to_virt(initrd_start); - initrd_end = __phys_to_virt(initrd_end); + initrd_start = __phys_to_virt(phys_initrd_start); + initrd_end = initrd_start + phys_initrd_size; } -#endif early_init_fdt_scan_reserved_mem(); @@ -607,15 +595,7 @@ void __init mem_init(void) * detected at build time already. */ #ifdef CONFIG_COMPAT - BUILD_BUG_ON(TASK_SIZE_32 > TASK_SIZE_64); -#endif - -#ifdef CONFIG_SPARSEMEM_VMEMMAP - /* - * Make sure we chose the upper bound of sizeof(struct page) - * correctly when sizing the VMEMMAP array. - */ - BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT)); + BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64); #endif if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) { diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 63527e585aac..4b55b15707a3 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -39,7 +39,15 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) { void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, node); + MEMBLOCK_ALLOC_KASAN, node); + return __pa(p); +} + +static phys_addr_t __init kasan_alloc_raw_page(int node) +{ + void *p = memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE, + __pa(MAX_DMA_ADDRESS), + MEMBLOCK_ALLOC_KASAN, node); return __pa(p); } @@ -47,8 +55,9 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early) { if (pmd_none(READ_ONCE(*pmdp))) { - phys_addr_t pte_phys = early ? __pa_symbol(kasan_zero_pte) - : kasan_alloc_zeroed_page(node); + phys_addr_t pte_phys = early ? + __pa_symbol(kasan_early_shadow_pte) + : kasan_alloc_zeroed_page(node); __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE); } @@ -60,8 +69,9 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early) { if (pud_none(READ_ONCE(*pudp))) { - phys_addr_t pmd_phys = early ? __pa_symbol(kasan_zero_pmd) - : kasan_alloc_zeroed_page(node); + phys_addr_t pmd_phys = early ? + __pa_symbol(kasan_early_shadow_pmd) + : kasan_alloc_zeroed_page(node); __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE); } @@ -72,8 +82,9 @@ static pud_t *__init kasan_pud_offset(pgd_t *pgdp, unsigned long addr, int node, bool early) { if (pgd_none(READ_ONCE(*pgdp))) { - phys_addr_t pud_phys = early ? __pa_symbol(kasan_zero_pud) - : kasan_alloc_zeroed_page(node); + phys_addr_t pud_phys = early ? + __pa_symbol(kasan_early_shadow_pud) + : kasan_alloc_zeroed_page(node); __pgd_populate(pgdp, pud_phys, PMD_TYPE_TABLE); } @@ -87,8 +98,11 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, pte_t *ptep = kasan_pte_offset(pmdp, addr, node, early); do { - phys_addr_t page_phys = early ? __pa_symbol(kasan_zero_page) - : kasan_alloc_zeroed_page(node); + phys_addr_t page_phys = early ? + __pa_symbol(kasan_early_shadow_page) + : kasan_alloc_raw_page(node); + if (!early) + memset(__va(page_phys), KASAN_SHADOW_INIT, PAGE_SIZE); next = addr + PAGE_SIZE; set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL)); } while (ptep++, addr = next, addr != end && pte_none(READ_ONCE(*ptep))); @@ -205,14 +219,14 @@ void __init kasan_init(void) kasan_map_populate(kimg_shadow_start, kimg_shadow_end, early_pfn_to_nid(virt_to_pfn(lm_alias(_text)))); - kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, - (void *)mod_shadow_start); - kasan_populate_zero_shadow((void *)kimg_shadow_end, - kasan_mem_to_shadow((void *)PAGE_OFFSET)); + kasan_populate_early_shadow((void *)KASAN_SHADOW_START, + (void *)mod_shadow_start); + kasan_populate_early_shadow((void *)kimg_shadow_end, + kasan_mem_to_shadow((void *)PAGE_OFFSET)); if (kimg_shadow_start > mod_shadow_end) - kasan_populate_zero_shadow((void *)mod_shadow_end, - (void *)kimg_shadow_start); + kasan_populate_early_shadow((void *)mod_shadow_end, + (void *)kimg_shadow_start); for_each_memblock(memory, reg) { void *start = (void *)__phys_to_virt(reg->base); @@ -227,16 +241,19 @@ void __init kasan_init(void) } /* - * KAsan may reuse the contents of kasan_zero_pte directly, so we - * should make sure that it maps the zero page read-only. + * KAsan may reuse the contents of kasan_early_shadow_pte directly, + * so we should make sure that it maps the zero page read-only. */ for (i = 0; i < PTRS_PER_PTE; i++) - set_pte(&kasan_zero_pte[i], - pfn_pte(sym_to_pfn(kasan_zero_page), PAGE_KERNEL_RO)); + set_pte(&kasan_early_shadow_pte[i], + pfn_pte(sym_to_pfn(kasan_early_shadow_page), + PAGE_KERNEL_RO)); - memset(kasan_zero_page, 0, PAGE_SIZE); + memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); + kasan_init_tags(); + /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; pr_info("KernelAddressSanitizer initialized\n"); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d1d6601b385d..b6f5aa52ac67 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -52,6 +52,8 @@ u64 idmap_t0sz = TCR_T0SZ(VA_BITS); u64 idmap_ptrs_per_pgd = PTRS_PER_PGD; +u64 vabits_user __ro_after_init; +EXPORT_SYMBOL(vabits_user); u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); @@ -451,7 +453,7 @@ static void __init map_mem(pgd_t *pgdp) struct memblock_region *reg; int flags = 0; - if (debug_pagealloc_enabled()) + if (rodata_full || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* @@ -552,7 +554,19 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, static int __init parse_rodata(char *arg) { - return strtobool(arg, &rodata_enabled); + int ret = strtobool(arg, &rodata_enabled); + if (!ret) { + rodata_full = false; + return 0; + } + + /* permit 'full' in addition to boolean options */ + if (strcmp(arg, "full")) + return -EINVAL; + + rodata_enabled = true; + rodata_full = true; + return 0; } early_param("rodata", parse_rodata); @@ -989,10 +1003,8 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - if (!pmd_present(pmd)) - return 1; if (!pmd_table(pmd)) { - VM_WARN_ON(!pmd_table(pmd)); + VM_WARN_ON(1); return 1; } @@ -1012,10 +1024,8 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - if (!pud_present(pud)) - return 1; if (!pud_table(pud)) { - VM_WARN_ON(!pud_table(pud)); + VM_WARN_ON(1); return 1; } @@ -1032,3 +1042,25 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pmd_free(NULL, table); return 1; } + +int p4d_free_pud_page(p4d_t *p4d, unsigned long addr) +{ + return 0; /* Don't attempt a block mapping */ +} + +#ifdef CONFIG_MEMORY_HOTPLUG +int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap, + bool want_memblock) +{ + int flags = 0; + + if (rodata_full || debug_pagealloc_enabled()) + flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; + + __create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start), + size, PAGE_KERNEL, pgd_pgtable_alloc, flags); + + return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, + altmap, want_memblock); +} +#endif diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 27a31efd9e8e..ae34e3a1cef1 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -466,3 +466,13 @@ void __init arm64_numa_init(void) numa_init(dummy_numa_init); } + +/* + * We hope that we will be hotplugging memory on nodes we already know about, + * such that acpi_get_node() succeeds and we never fall back to this... + */ +int memory_add_physaddr_to_nid(u64 addr) +{ + pr_warn("Unknown node for memory at 0x%llx, assuming node 0\n", addr); + return 0; +} diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c index a56359373d8b..6cd645edcf35 100644 --- a/arch/arm64/mm/pageattr.c +++ b/arch/arm64/mm/pageattr.c @@ -25,6 +25,8 @@ struct page_change_data { pgprot_t clear_mask; }; +bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED); + static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { @@ -64,6 +66,7 @@ static int change_memory_common(unsigned long addr, int numpages, unsigned long size = PAGE_SIZE*numpages; unsigned long end = start + size; struct vm_struct *area; + int i; if (!PAGE_ALIGNED(addr)) { start &= PAGE_MASK; @@ -93,6 +96,24 @@ static int change_memory_common(unsigned long addr, int numpages, if (!numpages) return 0; + /* + * If we are manipulating read-only permissions, apply the same + * change to the linear mapping of the pages that back this VM area. + */ + if (rodata_full && (pgprot_val(set_mask) == PTE_RDONLY || + pgprot_val(clear_mask) == PTE_RDONLY)) { + for (i = 0; i < area->nr_pages; i++) { + __change_memory_common((u64)page_address(area->pages[i]), + PAGE_SIZE, set_mask, clear_mask); + } + } + + /* + * Get rid of potentially aliasing lazily unmapped vm areas that may + * have permissions set that deviate from the ones we are setting here. + */ + vm_unmap_aliases(); + return __change_memory_common(start, size, set_mask, clear_mask); } diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 2c75b0b903ae..73886a5f1f30 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -47,6 +47,12 @@ /* PTWs cacheable, inner/outer WBWA */ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA +#ifdef CONFIG_KASAN_SW_TAGS +#define TCR_KASAN_FLAGS TCR_TBI1 +#else +#define TCR_KASAN_FLAGS 0 +#endif + #define MAIR(attr, mt) ((attr) << ((mt) * 8)) /* @@ -182,6 +188,7 @@ ENDPROC(cpu_do_switch_mm) .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 adrp \tmp1, empty_zero_page phys_to_ttbr \tmp2, \tmp1 + offset_ttbr1 \tmp2 msr ttbr1_el1, \tmp2 isb tlbi vmalle1 @@ -200,6 +207,7 @@ ENTRY(idmap_cpu_replace_ttbr1) __idmap_cpu_set_reserved_ttbr1 x1, x3 + offset_ttbr1 x0 msr ttbr1_el1, x0 isb @@ -254,6 +262,7 @@ ENTRY(idmap_kpti_install_ng_mappings) pte .req x16 mrs swapper_ttb, ttbr1_el1 + restore_ttbr1 swapper_ttb adr flag_ptr, __idmap_kpti_flag cbnz cpu, __idmap_kpti_secondary @@ -373,6 +382,7 @@ __idmap_kpti_secondary: cbnz w18, 1b /* All done, act like nothing happened */ + offset_ttbr1 swapper_ttb msr ttbr1_el1, swapper_ttb isb ret @@ -445,8 +455,16 @@ ENTRY(__cpu_setup) */ ldr x10, =TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 - tcr_set_idmap_t0sz x10, x9 + TCR_TBI0 | TCR_A1 | TCR_KASAN_FLAGS + +#ifdef CONFIG_ARM64_USER_VA_BITS_52 + ldr_l x9, vabits_user + sub x9, xzr, x9 + add x9, x9, #64 +#else + ldr_l x9, idmap_t0sz +#endif + tcr_set_t0sz x10, x9 /* * Set the IPS bits in TCR_EL1. diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 89198017e8e6..1542df00b23c 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -134,10 +134,9 @@ static inline void emit_a64_mov_i64(const int reg, const u64 val, } /* - * This is an unoptimized 64 immediate emission used for BPF to BPF call - * addresses. It will always do a full 64 bit decomposition as otherwise - * more complexity in the last extra pass is required since we previously - * reserved 4 instructions for the address. + * Kernel addresses in the vmalloc space use at most 48 bits, and the + * remaining bits are guaranteed to be 0x1. So we can compose the address + * with a fixed length movn/movk/movk sequence. */ static inline void emit_addr_mov_i64(const int reg, const u64 val, struct jit_ctx *ctx) @@ -145,8 +144,8 @@ static inline void emit_addr_mov_i64(const int reg, const u64 val, u64 tmp = val; int shift = 0; - emit(A64_MOVZ(1, reg, tmp & 0xffff, shift), ctx); - for (;shift < 48;) { + emit(A64_MOVN(1, reg, ~tmp & 0xffff, shift), ctx); + while (shift < 32) { tmp >>= 16; shift += 16; emit(A64_MOVK(1, reg, tmp & 0xffff, shift), ctx); @@ -634,11 +633,7 @@ emit_cond_jmp: &func_addr, &func_addr_fixed); if (ret < 0) return ret; - if (func_addr_fixed) - /* We can use optimized emission here. */ - emit_a64_mov_i64(tmp, func_addr, ctx); - else - emit_addr_mov_i64(tmp, func_addr, ctx); + emit_addr_mov_i64(tmp, func_addr, ctx); emit(A64_BLR(tmp), ctx); emit(A64_MOV(1, r0, A64_R(0)), ctx); break; @@ -937,6 +932,7 @@ skip_init_ctx: prog->jited_len = image_size; if (!prog->is_func || extra_pass) { + bpf_prog_fill_jited_linfo(prog, ctx.offset); out_off: kfree(ctx.offset); kfree(jit_data); @@ -948,3 +944,16 @@ out: tmp : orig_prog); return prog; } + +void *bpf_jit_alloc_exec(unsigned long size) +{ + return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START, + BPF_JIT_REGION_END, GFP_KERNEL, + PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} + +void bpf_jit_free_exec(void *addr) +{ + return vfree(addr); +} |