summaryrefslogtreecommitdiff
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig54
-rw-r--r--arch/arm64/Makefile2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi12
-rw-r--r--arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi4
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts12
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts1
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi8
-rw-r--r--arch/arm64/boot/dts/freescale/imx8ulp.dtsi2
-rw-r--r--arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/msm8939.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/sm8450.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100-crd.dts10
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100-qcp.dts2
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100.dtsi53
-rw-r--r--arch/arm64/boot/dts/renesas/r9a09g057.dtsi90
-rw-r--r--arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts4
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328.dtsi3
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts6
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi6
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts3
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-base.dtsi20
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts4
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts1
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-glue.c2
-rw-r--r--arch/arm64/crypto/aes-ce-glue.c2
-rw-r--r--arch/arm64/crypto/crct10dif-ce-core.S335
-rw-r--r--arch/arm64/crypto/crct10dif-ce-glue.c48
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c2
-rw-r--r--arch/arm64/crypto/poly1305-glue.c2
-rw-r--r--arch/arm64/crypto/sha1-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sha2-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sha3-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sha512-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sm3-ce-glue.c2
-rw-r--r--arch/arm64/crypto/sm3-neon-glue.c2
-rw-r--r--arch/arm64/include/asm/arm_pmuv3.h10
-rw-r--r--arch/arm64/include/asm/assembler.h7
-rw-r--r--arch/arm64/include/asm/cpucaps.h2
-rw-r--r--arch/arm64/include/asm/cpufeature.h18
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/daifflags.h2
-rw-r--r--arch/arm64/include/asm/debug-monitors.h1
-rw-r--r--arch/arm64/include/asm/el2_setup.h30
-rw-r--r--arch/arm64/include/asm/esr.h28
-rw-r--r--arch/arm64/include/asm/exception.h3
-rw-r--r--arch/arm64/include/asm/ftrace.h21
-rw-r--r--arch/arm64/include/asm/gcs.h107
-rw-r--r--arch/arm64/include/asm/hugetlb.h8
-rw-r--r--arch/arm64/include/asm/hwcap.h7
-rw-r--r--arch/arm64/include/asm/insn.h6
-rw-r--r--arch/arm64/include/asm/io.h8
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h1
-rw-r--r--arch/arm64/include/asm/kvm_asm.h1
-rw-r--r--arch/arm64/include/asm/kvm_host.h32
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h3
-rw-r--r--arch/arm64/include/asm/kvm_nested.h4
-rw-r--r--arch/arm64/include/asm/mem_encrypt.h9
-rw-r--r--arch/arm64/include/asm/mman.h38
-rw-r--r--arch/arm64/include/asm/mmu_context.h9
-rw-r--r--arch/arm64/include/asm/mte.h67
-rw-r--r--arch/arm64/include/asm/page-def.h5
-rw-r--r--arch/arm64/include/asm/perf_event.h4
-rw-r--r--arch/arm64/include/asm/pgalloc.h12
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h4
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h19
-rw-r--r--arch/arm64/include/asm/pgtable.h31
-rw-r--r--arch/arm64/include/asm/probes.h11
-rw-r--r--arch/arm64/include/asm/processor.h57
-rw-r--r--arch/arm64/include/asm/ptrace.h22
-rw-r--r--arch/arm64/include/asm/rsi.h68
-rw-r--r--arch/arm64/include/asm/rsi_cmds.h160
-rw-r--r--arch/arm64/include/asm/rsi_smc.h193
-rw-r--r--arch/arm64/include/asm/scs.h8
-rw-r--r--arch/arm64/include/asm/set_memory.h3
-rw-r--r--arch/arm64/include/asm/stacktrace/common.h74
-rw-r--r--arch/arm64/include/asm/stacktrace/frame.h48
-rw-r--r--arch/arm64/include/asm/sysreg.h20
-rw-r--r--arch/arm64/include/asm/tlbflush.h43
-rw-r--r--arch/arm64/include/asm/topology.h4
-rw-r--r--arch/arm64/include/asm/uaccess.h40
-rw-r--r--arch/arm64/include/asm/uprobes.h8
-rw-r--r--arch/arm64/include/asm/vdso.h9
-rw-r--r--arch/arm64/include/asm/vdso/vsyscall.h3
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h7
-rw-r--r--arch/arm64/include/uapi/asm/ptrace.h8
-rw-r--r--arch/arm64/include/uapi/asm/sigcontext.h9
-rw-r--r--arch/arm64/kernel/Makefile3
-rw-r--r--arch/arm64/kernel/asm-offsets.c50
-rw-r--r--arch/arm64/kernel/cpu_errata.c3
-rw-r--r--arch/arm64/kernel/cpufeature.c45
-rw-r--r--arch/arm64/kernel/cpuinfo.c1
-rw-r--r--arch/arm64/kernel/debug-monitors.c10
-rw-r--r--arch/arm64/kernel/efi.c12
-rw-r--r--arch/arm64/kernel/entry-common.c35
-rw-r--r--arch/arm64/kernel/entry.S16
-rw-r--r--arch/arm64/kernel/fpsimd.c3
-rw-r--r--arch/arm64/kernel/ftrace.c10
-rw-r--r--arch/arm64/kernel/head.S3
-rw-r--r--arch/arm64/kernel/hibernate.c6
-rw-r--r--arch/arm64/kernel/module.c10
-rw-r--r--arch/arm64/kernel/mte.c27
-rw-r--r--arch/arm64/kernel/perf_callchain.c28
-rw-r--r--arch/arm64/kernel/pi/idreg-override.c12
-rw-r--r--arch/arm64/kernel/pi/map_range.c2
-rw-r--r--arch/arm64/kernel/pi/patch-scs.c93
-rw-r--r--arch/arm64/kernel/probes/decode-insn.c38
-rw-r--r--arch/arm64/kernel/probes/decode-insn.h2
-rw-r--r--arch/arm64/kernel/probes/kprobes.c39
-rw-r--r--arch/arm64/kernel/probes/simulate-insn.c24
-rw-r--r--arch/arm64/kernel/probes/simulate-insn.h1
-rw-r--r--arch/arm64/kernel/probes/uprobes.c16
-rw-r--r--arch/arm64/kernel/process.c104
-rw-r--r--arch/arm64/kernel/ptrace.c74
-rw-r--r--arch/arm64/kernel/rsi.c142
-rw-r--r--arch/arm64/kernel/setup.c3
-rw-r--r--arch/arm64/kernel/signal.c327
-rw-r--r--arch/arm64/kernel/smccc-call.S35
-rw-r--r--arch/arm64/kernel/stacktrace.c176
-rw-r--r--arch/arm64/kernel/traps.c18
-rw-r--r--arch/arm64/kernel/vdso.c44
-rw-r--r--arch/arm64/kernel/vdso/vdso.lds.S2
-rw-r--r--arch/arm64/kernel/vdso32/vdso.lds.S2
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S6
-rw-r--r--arch/arm64/kvm/arm.c5
-rw-r--r--arch/arm64/kvm/guest.c16
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-init.S52
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c12
-rw-r--r--arch/arm64/kvm/hyp/nvhe/pkvm.c6
-rw-r--r--arch/arm64/kvm/hypercalls.c12
-rw-r--r--arch/arm64/kvm/mmu.c26
-rw-r--r--arch/arm64/kvm/nested.c53
-rw-r--r--arch/arm64/kvm/sys_regs.c77
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c41
-rw-r--r--arch/arm64/kvm/vgic/vgic-kvm-device.c7
-rw-r--r--arch/arm64/lib/Makefile2
-rw-r--r--arch/arm64/lib/clear_page.S13
-rw-r--r--arch/arm64/lib/copy_page.S13
-rw-r--r--arch/arm64/lib/crc32-glue.c82
-rw-r--r--arch/arm64/lib/crc32.S344
-rw-r--r--arch/arm64/lib/memcpy.S19
-rw-r--r--arch/arm64/lib/memset.S20
-rw-r--r--arch/arm64/mm/Makefile1
-rw-r--r--arch/arm64/mm/copypage.c27
-rw-r--r--arch/arm64/mm/fault.c40
-rw-r--r--arch/arm64/mm/fixmap.c9
-rw-r--r--arch/arm64/mm/gcs.c254
-rw-r--r--arch/arm64/mm/hugetlbpage.c21
-rw-r--r--arch/arm64/mm/init.c10
-rw-r--r--arch/arm64/mm/mmap.c9
-rw-r--r--arch/arm64/mm/mmu.c10
-rw-r--r--arch/arm64/mm/pageattr.c98
-rw-r--r--arch/arm64/mm/proc.S19
-rw-r--r--arch/arm64/mm/ptdump.c8
-rw-r--r--arch/arm64/net/bpf_jit_comp.c12
-rw-r--r--arch/arm64/tools/cpucaps2
-rw-r--r--arch/arm64/tools/syscall_32.tbl4
-rw-r--r--arch/arm64/tools/sysreg12
180 files changed, 3869 insertions, 930 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3e29b44d2d7b..d743737bf9ce 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -21,6 +21,7 @@ config ARM64
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_CACHE_LINE_SIZE
+ select ARCH_HAS_CC_PLATFORM
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE
@@ -38,12 +39,15 @@ config ARM64
select ARCH_HAS_MEM_ENCRYPT
select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+ select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
select ARCH_HAS_PTE_DEVMAP
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_HW_PTE_YOUNG
select ARCH_HAS_SETUP_DMA_OPS
select ARCH_HAS_SET_DIRECT_MAP
select ARCH_HAS_SET_MEMORY
+ select ARCH_HAS_MEM_ENCRYPT
+ select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select ARCH_STACKWALK
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
@@ -200,7 +204,8 @@ config ARM64
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_ARGS \
- if $(cc-option,-fpatchable-function-entry=2)
+ if (GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS || \
+ CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS)
select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS \
if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS
select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \
@@ -286,12 +291,10 @@ config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS
def_bool CC_IS_CLANG
# https://github.com/ClangBuiltLinux/linux/issues/1507
depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600))
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS
config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS
def_bool CC_IS_GCC
depends on $(cc-option,-fpatchable-function-entry=2)
- select HAVE_DYNAMIC_FTRACE_WITH_ARGS
config 64BIT
def_bool y
@@ -1097,6 +1100,7 @@ config ARM64_ERRATUM_3194386
* ARM Cortex-A78C erratum 3324346
* ARM Cortex-A78C erratum 3324347
* ARM Cortex-A710 erratam 3324338
+ * ARM Cortex-A715 errartum 3456084
* ARM Cortex-A720 erratum 3456091
* ARM Cortex-A725 erratum 3456106
* ARM Cortex-X1 erratum 3324344
@@ -1107,6 +1111,7 @@ config ARM64_ERRATUM_3194386
* ARM Cortex-X925 erratum 3324334
* ARM Neoverse-N1 erratum 3324349
* ARM Neoverse N2 erratum 3324339
+ * ARM Neoverse-N3 erratum 3456111
* ARM Neoverse-V1 erratum 3324341
* ARM Neoverse V2 erratum 3324336
* ARM Neoverse-V3 erratum 3312417
@@ -1575,6 +1580,9 @@ config ARCH_DEFAULT_KEXEC_IMAGE_VERIFY_SIG
config ARCH_SUPPORTS_CRASH_DUMP
def_bool y
+config ARCH_DEFAULT_CRASH_DUMP
+ def_bool y
+
config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
def_bool CRASH_RESERVE
@@ -2155,6 +2163,9 @@ config ARM64_EPAN
if the cpu does not implement the feature.
endmenu # "ARMv8.7 architectural features"
+config AS_HAS_MOPS
+ def_bool $(as-instr,.arch_extension mops)
+
menu "ARMv8.9 architectural features"
config ARM64_POE
@@ -2176,8 +2187,44 @@ config ARCH_PKEY_BITS
int
default 3
+config ARM64_HAFT
+ bool "Support for Hardware managed Access Flag for Table Descriptors"
+ depends on ARM64_HW_AFDBM
+ default y
+ help
+ The ARMv8.9/ARMv9.5 introduces the feature Hardware managed Access
+ Flag for Table descriptors. When enabled an architectural executed
+ memory access will update the Access Flag in each Table descriptor
+ which is accessed during the translation table walk and for which
+ the Access Flag is 0. The Access Flag of the Table descriptor use
+ the same bit of PTE_AF.
+
+ The feature will only be enabled if all the CPUs in the system
+ support this feature. If unsure, say Y.
+
endmenu # "ARMv8.9 architectural features"
+menu "v9.4 architectural features"
+
+config ARM64_GCS
+ bool "Enable support for Guarded Control Stack (GCS)"
+ default y
+ select ARCH_HAS_USER_SHADOW_STACK
+ select ARCH_USES_HIGH_VMA_FLAGS
+ depends on !UPROBES
+ help
+ Guarded Control Stack (GCS) provides support for a separate
+ stack with restricted access which contains only return
+ addresses. This can be used to harden against some attacks
+ by comparing return address used by the program with what is
+ stored in the GCS, and may also be used to efficiently obtain
+ the call stack for applications such as profiling.
+
+ The feature is detected at runtime, and will remain disabled
+ if the system does not implement the feature.
+
+endmenu # "v9.4 architectural features"
+
config ARM64_SVE
bool "ARM Scalable Vector Extension support"
default y
@@ -2213,6 +2260,7 @@ config ARM64_SME
bool "ARM Scalable Matrix Extension support"
default y
depends on ARM64_SVE
+ depends on BROKEN
help
The Scalable Matrix Extension (SME) is an extension to the AArch64
execution state which utilises a substantial subset of the SVE
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b058c4803efb..9efd3f37c2fd 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -10,7 +10,7 @@
#
# Copyright (C) 1995-2001 by Russell King
-LDFLAGS_vmlinux :=--no-undefined -X
+LDFLAGS_vmlinux :=--no-undefined -X --pic-veneer
ifeq ($(CONFIG_RELOCATABLE), y)
# Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi
index d00036204a8c..dad0dc8fb431 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-lvds0.dtsi
@@ -14,7 +14,7 @@ lvds0_subsys: bus@56240000 {
compatible = "fsl,imx8qxp-lpcg";
reg = <0x56243000 0x4>;
#clock-cells = <1>;
- clock-output-names = "mipi1_lis_lpcg_ipg_clk";
+ clock-output-names = "lvds0_lis_lpcg_ipg_clk";
power-domains = <&pd IMX_SC_R_MIPI_1>;
};
@@ -22,9 +22,9 @@ lvds0_subsys: bus@56240000 {
compatible = "fsl,imx8qxp-lpcg";
reg = <0x5624300c 0x4>;
#clock-cells = <1>;
- clock-output-names = "mipi1_pwm_lpcg_clk",
- "mipi1_pwm_lpcg_ipg_clk",
- "mipi1_pwm_lpcg_32k_clk";
+ clock-output-names = "lvds0_pwm_lpcg_clk",
+ "lvds0_pwm_lpcg_ipg_clk",
+ "lvds0_pwm_lpcg_32k_clk";
power-domains = <&pd IMX_SC_R_MIPI_1_PWM_0>;
};
@@ -32,8 +32,8 @@ lvds0_subsys: bus@56240000 {
compatible = "fsl,imx8qxp-lpcg";
reg = <0x56243010 0x4>;
#clock-cells = <1>;
- clock-output-names = "mipi1_i2c0_lpcg_clk",
- "mipi1_i2c0_lpcg_ipg_clk";
+ clock-output-names = "lvds0_i2c0_lpcg_clk",
+ "lvds0_i2c0_lpcg_ipg_clk";
power-domains = <&pd IMX_SC_R_MIPI_1_I2C_0>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi
index c6540768bdb9..87211c18d65a 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-vpu.dtsi
@@ -15,7 +15,7 @@ vpu: vpu@2c000000 {
mu_m0: mailbox@2d000000 {
compatible = "fsl,imx6sx-mu";
reg = <0x2d000000 0x20000>;
- interrupts = <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 472 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <2>;
power-domains = <&pd IMX_SC_R_VPU_MU_0>;
status = "disabled";
@@ -24,7 +24,7 @@ vpu: vpu@2c000000 {
mu1_m0: mailbox@2d020000 {
compatible = "fsl,imx6sx-mu";
reg = <0x2d020000 0x20000>;
- interrupts = <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 473 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <2>;
power-domains = <&pd IMX_SC_R_VPU_MU_1>;
status = "disabled";
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
index 50debe821c42..9c102acb8052 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts
@@ -218,6 +218,18 @@
};
};
+&media_blk_ctrl {
+ /*
+ * The LVDS panel on this device uses 72.4 MHz pixel clock,
+ * set IMX8MP_VIDEO_PLL1 to 72.4 * 7 = 506.8 MHz so the LDB
+ * serializer and LCDIFv3 scanout engine can reach accurate
+ * pixel clock of exactly 72.4 MHz.
+ */
+ assigned-clock-rates = <500000000>, <200000000>,
+ <0>, <0>, <500000000>,
+ <506800000>;
+};
+
&snvs_pwrkey {
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
index 3c2efdc59bfa..30962922b361 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-skov-revb-mi1010ait-1cp1.dts
@@ -71,6 +71,7 @@
assigned-clock-rates = <500000000>, <200000000>, <0>,
/* IMX8MP_CLK_MEDIA_DISP2_PIX = pixelclk of lvds panel */
<68900000>,
+ <500000000>,
/* IMX8MP_VIDEO_PLL1 = IMX8MP_CLK_MEDIA_LDB * 2 */
<964600000>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index f3531cfb0d79..40e847bc0b7f 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -1261,7 +1261,7 @@
compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
reg = <0x30b40000 0x10000>;
interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&clk IMX8MP_CLK_DUMMY>,
+ clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
<&clk IMX8MP_CLK_NAND_USDHC_BUS>,
<&clk IMX8MP_CLK_USDHC1_ROOT>;
clock-names = "ipg", "ahb", "per";
@@ -1275,7 +1275,7 @@
compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
reg = <0x30b50000 0x10000>;
interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&clk IMX8MP_CLK_DUMMY>,
+ clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
<&clk IMX8MP_CLK_NAND_USDHC_BUS>,
<&clk IMX8MP_CLK_USDHC2_ROOT>;
clock-names = "ipg", "ahb", "per";
@@ -1289,7 +1289,7 @@
compatible = "fsl,imx8mp-usdhc", "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
reg = <0x30b60000 0x10000>;
interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&clk IMX8MP_CLK_DUMMY>,
+ clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
<&clk IMX8MP_CLK_NAND_USDHC_BUS>,
<&clk IMX8MP_CLK_USDHC3_ROOT>;
clock-names = "ipg", "ahb", "per";
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi
index 7894a3ab26d6..f81937b5fb72 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-ss-vpu.dtsi
@@ -5,6 +5,14 @@
* Author: Alexander Stein
*/
+&mu_m0 {
+ interrupts = <GIC_SPI 469 IRQ_TYPE_LEVEL_HIGH>;
+};
+
+&mu1_m0 {
+ interrupts = <GIC_SPI 470 IRQ_TYPE_LEVEL_HIGH>;
+};
+
&vpu_core0 {
reg = <0x2d040000 0x10000>;
};
diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
index e32d5afcf4a9..43f543768444 100644
--- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi
@@ -384,7 +384,7 @@
};
flexspi2: spi@29810000 {
- compatible = "nxp,imx8mm-fspi";
+ compatible = "nxp,imx8ulp-fspi";
reg = <0x29810000 0x10000>, <0x60000000 0x10000000>;
reg-names = "fspi_base", "fspi_mmap";
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi b/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
index 4676e3488f54..cb8d54895a77 100644
--- a/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
+++ b/arch/arm64/boot/dts/marvell/cn9130-sr-som.dtsi
@@ -136,7 +136,7 @@
};
cp0_mdio_pins: cp0-mdio-pins {
- marvell,pins = "mpp40", "mpp41";
+ marvell,pins = "mpp0", "mpp1";
marvell,function = "ge";
};
diff --git a/arch/arm64/boot/dts/qcom/msm8939.dtsi b/arch/arm64/boot/dts/qcom/msm8939.dtsi
index 28634789a8a9..7af210789879 100644
--- a/arch/arm64/boot/dts/qcom/msm8939.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8939.dtsi
@@ -248,7 +248,7 @@
smd-edge {
interrupts = <GIC_SPI 168 IRQ_TYPE_EDGE_RISING>;
- mboxes = <&apcs1_mbox 0>;
+ qcom,ipc = <&apcs1_mbox 8 0>;
qcom,smd-edge = <15>;
rpm_requests: rpm-requests {
diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi
index 9bafb3b350ff..38cb524cc568 100644
--- a/arch/arm64/boot/dts/qcom/sm8450.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi
@@ -1973,7 +1973,7 @@
clocks = <&gcc GCC_PCIE_1_PIPE_CLK>,
<&gcc GCC_PCIE_1_PIPE_CLK_SRC>,
- <&pcie1_phy>,
+ <&pcie1_phy QMP_PCIE_PIPE_CLK>,
<&rpmhcc RPMH_CXO_CLK>,
<&gcc GCC_PCIE_1_AUX_CLK>,
<&gcc GCC_PCIE_1_CFG_AHB_CLK>,
diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts
index 941dfddd6713..fdde988ae01e 100644
--- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts
+++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts
@@ -139,6 +139,8 @@
pinctrl-0 = <&nvme_reg_en>;
pinctrl-names = "default";
+
+ regulator-boot-on;
};
vph_pwr: regulator-vph-pwr {
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
index 20616bd4aa6c..fb4a48a1e2a8 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-asus-vivobook-s15.dts
@@ -134,6 +134,8 @@
pinctrl-0 = <&nvme_reg_en>;
pinctrl-names = "default";
+
+ regulator-boot-on;
};
};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
index 10b28d870f08..c6e0356ed9a2 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
@@ -177,9 +177,9 @@
compatible = "qcom,x1e80100-sndcard";
model = "X1E80100-CRD";
audio-routing = "WooferLeft IN", "WSA WSA_SPK1 OUT",
- "TwitterLeft IN", "WSA WSA_SPK2 OUT",
+ "TweeterLeft IN", "WSA WSA_SPK2 OUT",
"WooferRight IN", "WSA2 WSA_SPK2 OUT",
- "TwitterRight IN", "WSA2 WSA_SPK2 OUT",
+ "TweeterRight IN", "WSA2 WSA_SPK2 OUT",
"IN1_HPHL", "HPHL_OUT",
"IN2_HPHR", "HPHR_OUT",
"AMIC2", "MIC BIAS2",
@@ -300,6 +300,8 @@
pinctrl-names = "default";
pinctrl-0 = <&nvme_reg_en>;
+
+ regulator-boot-on;
};
vreg_wwan: regulator-wwan {
@@ -933,7 +935,7 @@
reg = <0 1>;
reset-gpios = <&lpass_tlmm 12 GPIO_ACTIVE_LOW>;
#sound-dai-cells = <0>;
- sound-name-prefix = "TwitterLeft";
+ sound-name-prefix = "TweeterLeft";
vdd-1p8-supply = <&vreg_l15b_1p8>;
vdd-io-supply = <&vreg_l12b_1p2>;
qcom,port-mapping = <4 5 6 7 11 13>;
@@ -986,7 +988,7 @@
reg = <0 1>;
reset-gpios = <&lpass_tlmm 13 GPIO_ACTIVE_LOW>;
#sound-dai-cells = <0>;
- sound-name-prefix = "TwitterRight";
+ sound-name-prefix = "TweeterRight";
vdd-1p8-supply = <&vreg_l15b_1p8>;
vdd-io-supply = <&vreg_l12b_1p2>;
qcom,port-mapping = <4 5 6 7 11 13>;
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
index 3c13331a9ef4..0cdaff9c8cf0 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-lenovo-yoga-slim7x.dts
@@ -205,6 +205,8 @@
pinctrl-0 = <&nvme_reg_en>;
pinctrl-names = "default";
+
+ regulator-boot-on;
};
};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi
index 42e02ad6a9c3..cdb401767c42 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100-microsoft-romulus.dtsi
@@ -164,6 +164,8 @@
pinctrl-0 = <&nvme_reg_en>;
pinctrl-names = "default";
+
+ regulator-boot-on;
};
};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
index 1c3a6a7b3ed6..5ef030c60abe 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
@@ -253,6 +253,8 @@
pinctrl-names = "default";
pinctrl-0 = <&nvme_reg_en>;
+
+ regulator-boot-on;
};
};
diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
index a36076e3c56b..0510abc0edf0 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -2924,14 +2924,14 @@
"mhi";
#address-cells = <3>;
#size-cells = <2>;
- ranges = <0x01000000 0 0x00000000 0 0x70200000 0 0x100000>,
- <0x02000000 0 0x70300000 0 0x70300000 0 0x3d00000>;
- bus-range = <0 0xff>;
+ ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>,
+ <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>;
+ bus-range = <0x00 0xff>;
dma-coherent;
linux,pci-domain = <6>;
- num-lanes = <2>;
+ num-lanes = <4>;
interrupts = <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 774 IRQ_TYPE_LEVEL_HIGH>,
@@ -2997,19 +2997,22 @@
};
pcie6a_phy: phy@1bfc000 {
- compatible = "qcom,x1e80100-qmp-gen4x2-pcie-phy";
- reg = <0 0x01bfc000 0 0x2000>;
+ compatible = "qcom,x1e80100-qmp-gen4x4-pcie-phy";
+ reg = <0 0x01bfc000 0 0x2000>,
+ <0 0x01bfe000 0 0x2000>;
clocks = <&gcc GCC_PCIE_6A_PHY_AUX_CLK>,
<&gcc GCC_PCIE_6A_CFG_AHB_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
+ <&tcsr TCSR_PCIE_4L_CLKREF_EN>,
<&gcc GCC_PCIE_6A_PHY_RCHNG_CLK>,
- <&gcc GCC_PCIE_6A_PIPE_CLK>;
+ <&gcc GCC_PCIE_6A_PIPE_CLK>,
+ <&gcc GCC_PCIE_6A_PIPEDIV2_CLK>;
clock-names = "aux",
"cfg_ahb",
"ref",
"rchng",
- "pipe";
+ "pipe",
+ "pipediv2";
resets = <&gcc GCC_PCIE_6A_PHY_BCR>,
<&gcc GCC_PCIE_6A_NOCSR_COM_PHY_BCR>;
@@ -3021,6 +3024,8 @@
power-domains = <&gcc GCC_PCIE_6_PHY_GDSC>;
+ qcom,4ln-config-sel = <&tcsr 0x1a000 0>;
+
#clock-cells = <0>;
clock-output-names = "pcie6a_pipe_clk";
@@ -3097,7 +3102,7 @@
assigned-clocks = <&gcc GCC_PCIE_5_AUX_CLK>;
assigned-clock-rates = <19200000>;
- interconnects = <&pcie_south_anoc MASTER_PCIE_5 QCOM_ICC_TAG_ALWAYS
+ interconnects = <&pcie_north_anoc MASTER_PCIE_5 QCOM_ICC_TAG_ALWAYS
&mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
&cnoc_main SLAVE_PCIE_5 QCOM_ICC_TAG_ALWAYS>;
@@ -3124,14 +3129,16 @@
clocks = <&gcc GCC_PCIE_5_AUX_CLK>,
<&gcc GCC_PCIE_5_CFG_AHB_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
+ <&tcsr TCSR_PCIE_2L_5_CLKREF_EN>,
<&gcc GCC_PCIE_5_PHY_RCHNG_CLK>,
- <&gcc GCC_PCIE_5_PIPE_CLK>;
+ <&gcc GCC_PCIE_5_PIPE_CLK>,
+ <&gcc GCC_PCIE_5_PIPEDIV2_CLK>;
clock-names = "aux",
"cfg_ahb",
"ref",
"rchng",
- "pipe";
+ "pipe",
+ "pipediv2";
resets = <&gcc GCC_PCIE_5_PHY_BCR>;
reset-names = "phy";
@@ -3166,8 +3173,8 @@
"mhi";
#address-cells = <3>;
#size-cells = <2>;
- ranges = <0x01000000 0 0x00000000 0 0x7c200000 0 0x100000>,
- <0x02000000 0 0x7c300000 0 0x7c300000 0 0x3d00000>;
+ ranges = <0x01000000 0x0 0x00000000 0x0 0x7c200000 0x0 0x100000>,
+ <0x02000000 0x0 0x7c300000 0x0 0x7c300000 0x0 0x1d00000>;
bus-range = <0x00 0xff>;
dma-coherent;
@@ -3217,7 +3224,7 @@
assigned-clocks = <&gcc GCC_PCIE_4_AUX_CLK>;
assigned-clock-rates = <19200000>;
- interconnects = <&pcie_south_anoc MASTER_PCIE_4 QCOM_ICC_TAG_ALWAYS
+ interconnects = <&pcie_north_anoc MASTER_PCIE_4 QCOM_ICC_TAG_ALWAYS
&mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
<&gem_noc MASTER_APPSS_PROC QCOM_ICC_TAG_ALWAYS
&cnoc_main SLAVE_PCIE_4 QCOM_ICC_TAG_ALWAYS>;
@@ -3254,14 +3261,16 @@
clocks = <&gcc GCC_PCIE_4_AUX_CLK>,
<&gcc GCC_PCIE_4_CFG_AHB_CLK>,
- <&rpmhcc RPMH_CXO_CLK>,
+ <&tcsr TCSR_PCIE_2L_4_CLKREF_EN>,
<&gcc GCC_PCIE_4_PHY_RCHNG_CLK>,
- <&gcc GCC_PCIE_4_PIPE_CLK>;
+ <&gcc GCC_PCIE_4_PIPE_CLK>,
+ <&gcc GCC_PCIE_4_PIPEDIV2_CLK>;
clock-names = "aux",
"cfg_ahb",
"ref",
"rchng",
- "pipe";
+ "pipe",
+ "pipediv2";
resets = <&gcc GCC_PCIE_4_PHY_BCR>;
reset-names = "phy";
@@ -6084,7 +6093,8 @@
<0 0x25a00000 0 0x200000>,
<0 0x25c00000 0 0x200000>,
<0 0x25e00000 0 0x200000>,
- <0 0x26000000 0 0x200000>;
+ <0 0x26000000 0 0x200000>,
+ <0 0x26200000 0 0x200000>;
reg-names = "llcc0_base",
"llcc1_base",
"llcc2_base",
@@ -6093,7 +6103,8 @@
"llcc5_base",
"llcc6_base",
"llcc7_base",
- "llcc_broadcast_base";
+ "llcc_broadcast_base",
+ "llcc_broadcast_and_base";
interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
};
diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
index 1ad5a1b6917f..abcdef3ba5bc 100644
--- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
+++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi
@@ -90,6 +90,95 @@
#size-cells = <2>;
ranges;
+ icu: interrupt-controller@10400000 {
+ compatible = "renesas,r9a09g057-icu";
+ reg = <0 0x10400000 0 0x10000>;
+ #interrupt-cells = <2>;
+ #address-cells = <0>;
+ interrupt-controller;
+ interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 419 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 420 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 426 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 427 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 428 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 429 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 430 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 431 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 432 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 433 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 434 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 436 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 437 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 439 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 440 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 441 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 442 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 443 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 444 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 445 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 446 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 447 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 448 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 449 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 450 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 262 IRQ_TYPE_EDGE_RISING>,
+ <GIC_SPI 263 IRQ_TYPE_EDGE_RISING>,
+ <GIC_SPI 264 IRQ_TYPE_EDGE_RISING>,
+ <GIC_SPI 265 IRQ_TYPE_EDGE_RISING>,
+ <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 451 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 452 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 453 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 454 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "nmi",
+ "port_irq0", "port_irq1", "port_irq2",
+ "port_irq3", "port_irq4", "port_irq5",
+ "port_irq6", "port_irq7", "port_irq8",
+ "port_irq9", "port_irq10", "port_irq11",
+ "port_irq12", "port_irq13", "port_irq14",
+ "port_irq15",
+ "tint0", "tint1", "tint2", "tint3",
+ "tint4", "tint5", "tint6", "tint7",
+ "tint8", "tint9", "tint10", "tint11",
+ "tint12", "tint13", "tint14", "tint15",
+ "tint16", "tint17", "tint18", "tint19",
+ "tint20", "tint21", "tint22", "tint23",
+ "tint24", "tint25", "tint26", "tint27",
+ "tint28", "tint29", "tint30", "tint31",
+ "int-ca55-0", "int-ca55-1",
+ "int-ca55-2", "int-ca55-3",
+ "icu-error-ca55",
+ "gpt-u0-gtciada", "gpt-u0-gtciadb",
+ "gpt-u1-gtciada", "gpt-u1-gtciadb";
+ clocks = <&cpg CPG_MOD 0x5>;
+ power-domains = <&cpg>;
+ resets = <&cpg 0x36>;
+ };
+
pinctrl: pinctrl@10410000 {
compatible = "renesas,r9a09g057-pinctrl";
reg = <0 0x10410000 0 0x10000>;
@@ -99,6 +188,7 @@
gpio-ranges = <&pinctrl 0 0 96>;
#interrupt-cells = <2>;
interrupt-controller;
+ interrupt-parent = <&icu>;
power-domains = <&cpg>;
resets = <&cpg 0xa5>, <&cpg 0xa6>;
};
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index bb1aea82e666..b7163ed74232 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -66,7 +66,6 @@
bus-width = <8>;
cap-mmc-highspeed;
mmc-hs200-1_8v;
- supports-emmc;
mmc-pwrseq = <&emmc_pwrseq>;
non-removable;
vmmc-supply = <&vcc_3v3>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
index 9232357f4fec..d9e191ad1d77 100644
--- a/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3308-roc-cc.dts
@@ -36,14 +36,14 @@
power_led: led-0 {
label = "firefly:red:power";
- linux,default-trigger = "ir-power-click";
+ linux,default-trigger = "default-on";
default-state = "on";
gpios = <&gpio0 RK_PA6 GPIO_ACTIVE_HIGH>;
};
user_led: led-1 {
label = "firefly:blue:user";
- linux,default-trigger = "ir-user-click";
+ linux,default-trigger = "rc-feedback";
default-state = "off";
gpios = <&gpio0 RK_PB2 GPIO_ACTIVE_HIGH>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts
index cb81ba3f23ff..4b9ced67742d 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s-plus.dts
@@ -24,9 +24,7 @@
disable-wp;
mmc-hs200-1_8v;
non-removable;
- num-slots = <1>;
pinctrl-names = "default";
pinctrl-0 = <&emmc_clk &emmc_cmd &emmc_bus8>;
- supports-emmc;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 16b4faa22e4f..c01a4cad48f3 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -754,8 +754,7 @@
compatible = "rockchip,rk3328-dw-hdmi";
reg = <0x0 0xff3c0000 0x0 0x20000>;
reg-io-width = <4>;
- interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 71 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cru PCLK_HDMI>,
<&cru SCLK_HDMI_SFC>,
<&cru SCLK_RTC32K>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
index 8ac8acf4082d..ab3fda69a1fb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3368-lion.dtsi
@@ -61,7 +61,6 @@
fan: fan@18 {
compatible = "ti,amc6821";
reg = <0x18>;
- #cooling-cells = <2>;
};
rtc_twi: rtc@6f {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
index 1489eb32e266..4feb78797982 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-eaidk-610.dts
@@ -541,7 +541,7 @@
status = "okay";
rt5651: audio-codec@1a {
- compatible = "rockchip,rt5651";
+ compatible = "realtek,rt5651";
reg = <0x1a>;
clocks = <&cru SCLK_I2S_8CH_OUT>;
clock-names = "mclk";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
index 1a44582a49fb..09a016ea8c76 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts
@@ -166,7 +166,6 @@
regulator-max-microvolt = <1800000>;
vin-supply = <&vcc3v3_sys>;
gpio = <&gpio3 RK_PA5 GPIO_ACTIVE_HIGH>;
- pinctrl-names = "default";
};
/* MIPI DSI panel 2.8v supply */
@@ -178,7 +177,6 @@
regulator-max-microvolt = <2800000>;
vin-supply = <&vcc3v3_sys>;
gpio = <&gpio3 RK_PA1 GPIO_ACTIVE_HIGH>;
- pinctrl-names = "default";
};
vibrator {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
index 7ba1c28f70a9..2f06bfdd70bf 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-roc-pc-plus.dts
@@ -114,7 +114,6 @@
es8388: es8388@11 {
compatible = "everest,es8388";
reg = <0x11>;
- clock-names = "mclk";
clocks = <&cru SCLK_I2S_8CH_OUT>;
#sound-dai-cells = <0>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi
index 8146f870d2bd..ab890e7b6c59 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi
@@ -576,7 +576,7 @@
bluetooth {
compatible = "brcm,bcm43438-bt";
clocks = <&rk808 1>;
- clock-names = "ext_clock";
+ clock-names = "txco";
device-wakeup-gpios = <&gpio2 RK_PD3 GPIO_ACTIVE_HIGH>;
host-wakeup-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_HIGH>;
shutdown-gpios = <&gpio0 RK_PB1 GPIO_ACTIVE_HIGH>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts
index dbec2b7173a0..31ea3d0182c0 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts
@@ -163,7 +163,7 @@
status = "okay";
rt5651: rt5651@1a {
- compatible = "rockchip,rt5651";
+ compatible = "realtek,rt5651";
reg = <0x1a>;
clocks = <&cru SCLK_I2S_8CH_OUT>;
clock-names = "mclk";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts
index a73cf30801ec..9816a4ed4599 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353p.dts
@@ -92,7 +92,7 @@
};
&i2c2 {
- pintctrl-names = "default";
+ pinctrl-names = "default";
pinctrl-0 = <&i2c2m1_xfer>;
status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts
index e9954a33e8cd..a79a5614bcc8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-anbernic-rg353v.dts
@@ -79,7 +79,7 @@
};
&i2c2 {
- pintctrl-names = "default";
+ pinctrl-names = "default";
pinctrl-0 = <&i2c2m1_xfer>;
status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts b/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts
index 0c18406e4c59..7d4680933823 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-box-demo.dts
@@ -449,9 +449,9 @@
bluetooth {
compatible = "brcm,bcm43438-bt";
clocks = <&pmucru CLK_RTC_32K>;
- clock-names = "ext_clock";
- device-wake-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>;
- host-wake-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>;
+ clock-names = "txco";
+ device-wakeup-gpios = <&gpio2 RK_PC1 GPIO_ACTIVE_HIGH>;
+ host-wakeup-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>;
shutdown-gpios = <&gpio2 RK_PB7 GPIO_ACTIVE_HIGH>;
pinctrl-names = "default";
pinctrl-0 = <&bt_host_wake_l &bt_wake_l &bt_enable_h>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
index c1194d1e438d..9a2f59a351de 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
@@ -507,7 +507,6 @@
non-removable;
pinctrl-names = "default";
pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>;
- supports-emmc;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
index ae2536c65a83..0131f2cdd312 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-pinenote.dtsi
@@ -684,11 +684,11 @@
compatible = "brcm,bcm43438-bt";
clocks = <&rk817 1>;
clock-names = "lpo";
- device-wake-gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>;
- host-wake-gpios = <&gpio0 RK_PC3 GPIO_ACTIVE_HIGH>;
- reset-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_LOW>;
+ device-wakeup-gpios = <&gpio0 RK_PC2 GPIO_ACTIVE_HIGH>;
+ host-wakeup-gpios = <&gpio0 RK_PC3 GPIO_ACTIVE_HIGH>;
pinctrl-0 = <&bt_enable_h>, <&bt_host_wake_l>, <&bt_wake_h>;
pinctrl-names = "default";
+ shutdown-gpios = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
vbat-supply = <&vcc_wl>;
vddio-supply = <&vcca_1v8_pmu>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi
index 45de2630bb50..1e36f73840da 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3566-radxa-cm3.dtsi
@@ -402,9 +402,9 @@
clock-names = "lpo";
device-wakeup-gpios = <&gpio2 RK_PB2 GPIO_ACTIVE_HIGH>;
host-wakeup-gpios = <&gpio2 RK_PB1 GPIO_ACTIVE_HIGH>;
- reset-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_LOW>;
pinctrl-names = "default";
pinctrl-0 = <&bt_host_wake_h &bt_reg_on_h &bt_wake_host_h>;
+ shutdown-gpios = <&gpio2 RK_PC0 GPIO_ACTIVE_HIGH>;
vbat-supply = <&vcc_3v3>;
vddio-supply = <&vcc_1v8>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
index a3112d5df200..b505a4537ee8 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-lubancat-2.dts
@@ -589,7 +589,6 @@
non-removable;
pinctrl-names = "default";
pinctrl-0 = <&emmc_bus8 &emmc_clk &emmc_cmd>;
- supports-emmc;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts
index e333449ead04..2fa89a0eeafc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3568-roc-pc.dts
@@ -272,7 +272,6 @@
regulator-name = "vdd_logic";
regulator-always-on;
regulator-boot-on;
- regulator-init-microvolt = <900000>;
regulator-initial-mode = <0x2>;
regulator-min-microvolt = <500000>;
regulator-max-microvolt = <1350000>;
@@ -285,7 +284,6 @@
vdd_gpu: DCDC_REG2 {
regulator-name = "vdd_gpu";
- regulator-init-microvolt = <900000>;
regulator-initial-mode = <0x2>;
regulator-min-microvolt = <500000>;
regulator-max-microvolt = <1350000>;
@@ -309,7 +307,6 @@
vdd_npu: DCDC_REG4 {
regulator-name = "vdd_npu";
- regulator-init-microvolt = <900000>;
regulator-initial-mode = <0x2>;
regulator-min-microvolt = <500000>;
regulator-max-microvolt = <1350000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index d97d84b88837..fc67585b64b7 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -337,15 +337,19 @@
cache-unified;
next-level-cache = <&l3_cache>;
};
+ };
- l3_cache: l3-cache {
- compatible = "cache";
- cache-size = <3145728>;
- cache-line-size = <64>;
- cache-sets = <4096>;
- cache-level = <3>;
- cache-unified;
- };
+ /*
+ * The L3 cache belongs to the DynamIQ Shared Unit (DSU),
+ * so it's represented here, outside the "cpus" node
+ */
+ l3_cache: l3-cache {
+ compatible = "cache";
+ cache-size = <3145728>;
+ cache-line-size = <64>;
+ cache-sets = <4096>;
+ cache-level = <3>;
+ cache-unified;
};
display_subsystem: display-subsystem {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
index c3a6812cc93a..dd4c79bcad87 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts
@@ -328,7 +328,6 @@
compatible = "everest,es8388";
reg = <0x11>;
clocks = <&cru I2S0_8CH_MCLKOUT>;
- clock-names = "mclk";
AVDD-supply = <&vcc_1v8_s0>;
DVDD-supply = <&vcc_1v8_s0>;
HPVDD-supply = <&vcc_3v3_s0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
index e4a20cda65ed..b38dab009ccc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-quartzpro64.dts
@@ -316,7 +316,6 @@
assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
assigned-clock-rates = <12288000>;
clocks = <&cru I2S0_8CH_MCLKOUT>;
- clock-names = "mclk";
AVDD-supply = <&avcc_1v8_codec_s0>;
DVDD-supply = <&avcc_1v8_codec_s0>;
HPVDD-supply = <&vcc_3v3_s0>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
index 966bbc582d89..6bd06e46a101 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts
@@ -304,12 +304,12 @@
};
cooling-maps {
- map1 {
+ map0 {
trip = <&package_fan0>;
cooling-device = <&fan THERMAL_NO_LIMIT 1>;
};
- map2 {
+ map1 {
trip = <&package_fan1>;
cooling-device = <&fan 2 THERMAL_NO_LIMIT>;
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
index d0021524e7f9..328dcb894ccb 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-toybrick-x0.dts
@@ -428,7 +428,6 @@
regulator-boot-on;
regulator-min-microvolt = <550000>;
regulator-max-microvolt = <950000>;
- regulator-init-microvolt = <750000>;
regulator-ramp-delay = <12500>;
regulator-state-mem {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
index dbaa94ca69f4..432133251e31 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-turing-rk1.dtsi
@@ -296,6 +296,7 @@
pinctrl-names = "default";
pinctrl-0 = <&pmic_pins>, <&rk806_dvs1_null>,
<&rk806_dvs2_null>, <&rk806_dvs3_null>;
+ system-power-controller;
vcc1-supply = <&vcc5v0_sys>;
vcc2-supply = <&vcc5v0_sys>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
index d8c50fdcca3b..8ba111d9283f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588s-indiedroid-nova.dts
@@ -377,7 +377,6 @@
assigned-clock-rates = <12288000>;
assigned-clocks = <&cru I2S0_8CH_MCLKOUT>;
AVDD-supply = <&vcc_3v3_s3>;
- clock-names = "mclk";
clocks = <&cru I2S0_8CH_MCLKOUT>;
DVDD-supply = <&vcc_1v8_s3>;
HPVDD-supply = <&vcc_3v3_s3>;
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index ce9b28e3c7d6..a523b519700f 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -9,7 +9,7 @@
*/
#include <asm/neon.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/aes.h>
#include <crypto/scatterwalk.h>
#include <crypto/internal/aead.h>
diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c
index e921823ca103..00b8749013c5 100644
--- a/arch/arm64/crypto/aes-ce-glue.c
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/aes.h>
#include <crypto/algapi.h>
#include <crypto/internal/simd.h>
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index 5604de61d06d..87dd6d46224d 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -1,8 +1,11 @@
//
// Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
//
-// Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
-// Copyright (C) 2019 Google LLC <ebiggers@google.com>
+// Copyright (C) 2016 Linaro Ltd
+// Copyright (C) 2019-2024 Google LLC
+//
+// Authors: Ard Biesheuvel <ardb@google.com>
+// Eric Biggers <ebiggers@google.com>
//
// 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
@@ -71,161 +74,117 @@
init_crc .req w0
buf .req x1
len .req x2
- fold_consts_ptr .req x3
+ fold_consts_ptr .req x5
fold_consts .req v10
- ad .req v14
-
- k00_16 .req v15
- k32_48 .req v16
-
t3 .req v17
t4 .req v18
t5 .req v19
t6 .req v20
t7 .req v21
t8 .req v22
- t9 .req v23
- perm1 .req v24
- perm2 .req v25
- perm3 .req v26
- perm4 .req v27
-
- bd1 .req v28
- bd2 .req v29
- bd3 .req v30
- bd4 .req v31
-
- .macro __pmull_init_p64
- .endm
+ perm .req v27
- .macro __pmull_pre_p64, bd
+ .macro pmull16x64_p64, a16, b64, c64
+ pmull2 \c64\().1q, \a16\().2d, \b64\().2d
+ pmull \b64\().1q, \a16\().1d, \b64\().1d
.endm
- .macro __pmull_init_p8
- // k00_16 := 0x0000000000000000_000000000000ffff
- // k32_48 := 0x00000000ffffffff_0000ffffffffffff
- movi k32_48.2d, #0xffffffff
- mov k32_48.h[2], k32_48.h[0]
- ushr k00_16.2d, k32_48.2d, #32
-
- // prepare the permutation vectors
- mov_q x5, 0x080f0e0d0c0b0a09
- movi perm4.8b, #8
- dup perm1.2d, x5
- eor perm1.16b, perm1.16b, perm4.16b
- ushr perm2.2d, perm1.2d, #8
- ushr perm3.2d, perm1.2d, #16
- ushr perm4.2d, perm1.2d, #24
- sli perm2.2d, perm1.2d, #56
- sli perm3.2d, perm1.2d, #48
- sli perm4.2d, perm1.2d, #40
+ /*
+ * Pairwise long polynomial multiplication of two 16-bit values
+ *
+ * { w0, w1 }, { y0, y1 }
+ *
+ * by two 64-bit values
+ *
+ * { x0, x1, x2, x3, x4, x5, x6, x7 }, { z0, z1, z2, z3, z4, z5, z6, z7 }
+ *
+ * where each vector element is a byte, ordered from least to most
+ * significant.
+ *
+ * This can be implemented using 8x8 long polynomial multiplication, by
+ * reorganizing the input so that each pairwise 8x8 multiplication
+ * produces one of the terms from the decomposition below, and
+ * combining the results of each rank and shifting them into place.
+ *
+ * Rank
+ * 0 w0*x0 ^ | y0*z0 ^
+ * 1 (w0*x1 ^ w1*x0) << 8 ^ | (y0*z1 ^ y1*z0) << 8 ^
+ * 2 (w0*x2 ^ w1*x1) << 16 ^ | (y0*z2 ^ y1*z1) << 16 ^
+ * 3 (w0*x3 ^ w1*x2) << 24 ^ | (y0*z3 ^ y1*z2) << 24 ^
+ * 4 (w0*x4 ^ w1*x3) << 32 ^ | (y0*z4 ^ y1*z3) << 32 ^
+ * 5 (w0*x5 ^ w1*x4) << 40 ^ | (y0*z5 ^ y1*z4) << 40 ^
+ * 6 (w0*x6 ^ w1*x5) << 48 ^ | (y0*z6 ^ y1*z5) << 48 ^
+ * 7 (w0*x7 ^ w1*x6) << 56 ^ | (y0*z7 ^ y1*z6) << 56 ^
+ * 8 w1*x7 << 64 | y1*z7 << 64
+ *
+ * The inputs can be reorganized into
+ *
+ * { w0, w0, w0, w0, y0, y0, y0, y0 }, { w1, w1, w1, w1, y1, y1, y1, y1 }
+ * { x0, x2, x4, x6, z0, z2, z4, z6 }, { x1, x3, x5, x7, z1, z3, z5, z7 }
+ *
+ * and after performing 8x8->16 bit long polynomial multiplication of
+ * each of the halves of the first vector with those of the second one,
+ * we obtain the following four vectors of 16-bit elements:
+ *
+ * a := { w0*x0, w0*x2, w0*x4, w0*x6 }, { y0*z0, y0*z2, y0*z4, y0*z6 }
+ * b := { w0*x1, w0*x3, w0*x5, w0*x7 }, { y0*z1, y0*z3, y0*z5, y0*z7 }
+ * c := { w1*x0, w1*x2, w1*x4, w1*x6 }, { y1*z0, y1*z2, y1*z4, y1*z6 }
+ * d := { w1*x1, w1*x3, w1*x5, w1*x7 }, { y1*z1, y1*z3, y1*z5, y1*z7 }
+ *
+ * Results b and c can be XORed together, as the vector elements have
+ * matching ranks. Then, the final XOR (*) can be pulled forward, and
+ * applied between the halves of each of the remaining three vectors,
+ * which are then shifted into place, and combined to produce two
+ * 80-bit results.
+ *
+ * (*) NOTE: the 16x64 bit polynomial multiply below is not equivalent
+ * to the 64x64 bit one above, but XOR'ing the outputs together will
+ * produce the expected result, and this is sufficient in the context of
+ * this algorithm.
+ */
+ .macro pmull16x64_p8, a16, b64, c64
+ ext t7.16b, \b64\().16b, \b64\().16b, #1
+ tbl t5.16b, {\a16\().16b}, perm.16b
+ uzp1 t7.16b, \b64\().16b, t7.16b
+ bl __pmull_p8_16x64
+ ext \b64\().16b, t4.16b, t4.16b, #15
+ eor \c64\().16b, t8.16b, t5.16b
.endm
- .macro __pmull_pre_p8, bd
- tbl bd1.16b, {\bd\().16b}, perm1.16b
- tbl bd2.16b, {\bd\().16b}, perm2.16b
- tbl bd3.16b, {\bd\().16b}, perm3.16b
- tbl bd4.16b, {\bd\().16b}, perm4.16b
- .endm
-
-SYM_FUNC_START_LOCAL(__pmull_p8_core)
-.L__pmull_p8_core:
- ext t4.8b, ad.8b, ad.8b, #1 // A1
- ext t5.8b, ad.8b, ad.8b, #2 // A2
- ext t6.8b, ad.8b, ad.8b, #3 // A3
-
- pmull t4.8h, t4.8b, fold_consts.8b // F = A1*B
- pmull t8.8h, ad.8b, bd1.8b // E = A*B1
- pmull t5.8h, t5.8b, fold_consts.8b // H = A2*B
- pmull t7.8h, ad.8b, bd2.8b // G = A*B2
- pmull t6.8h, t6.8b, fold_consts.8b // J = A3*B
- pmull t9.8h, ad.8b, bd3.8b // I = A*B3
- pmull t3.8h, ad.8b, bd4.8b // K = A*B4
- b 0f
-
-.L__pmull_p8_core2:
- tbl t4.16b, {ad.16b}, perm1.16b // A1
- tbl t5.16b, {ad.16b}, perm2.16b // A2
- tbl t6.16b, {ad.16b}, perm3.16b // A3
-
- pmull2 t4.8h, t4.16b, fold_consts.16b // F = A1*B
- pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1
- pmull2 t5.8h, t5.16b, fold_consts.16b // H = A2*B
- pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2
- pmull2 t6.8h, t6.16b, fold_consts.16b // J = A3*B
- pmull2 t9.8h, ad.16b, bd3.16b // I = A*B3
- pmull2 t3.8h, ad.16b, bd4.16b // K = A*B4
-
-0: eor t4.16b, t4.16b, t8.16b // L = E + F
- eor t5.16b, t5.16b, t7.16b // M = G + H
- eor t6.16b, t6.16b, t9.16b // N = I + J
-
- uzp1 t8.2d, t4.2d, t5.2d
- uzp2 t4.2d, t4.2d, t5.2d
- uzp1 t7.2d, t6.2d, t3.2d
- uzp2 t6.2d, t6.2d, t3.2d
-
- // t4 = (L) (P0 + P1) << 8
- // t5 = (M) (P2 + P3) << 16
- eor t8.16b, t8.16b, t4.16b
- and t4.16b, t4.16b, k32_48.16b
-
- // t6 = (N) (P4 + P5) << 24
- // t7 = (K) (P6 + P7) << 32
- eor t7.16b, t7.16b, t6.16b
- and t6.16b, t6.16b, k00_16.16b
-
- eor t8.16b, t8.16b, t4.16b
- eor t7.16b, t7.16b, t6.16b
-
- zip2 t5.2d, t8.2d, t4.2d
- zip1 t4.2d, t8.2d, t4.2d
- zip2 t3.2d, t7.2d, t6.2d
- zip1 t6.2d, t7.2d, t6.2d
-
- ext t4.16b, t4.16b, t4.16b, #15
+SYM_FUNC_START_LOCAL(__pmull_p8_16x64)
+ ext t6.16b, t5.16b, t5.16b, #8
+
+ pmull t3.8h, t7.8b, t5.8b
+ pmull t4.8h, t7.8b, t6.8b
+ pmull2 t5.8h, t7.16b, t5.16b
+ pmull2 t6.8h, t7.16b, t6.16b
+
+ ext t8.16b, t3.16b, t3.16b, #8
+ eor t4.16b, t4.16b, t6.16b
+ ext t7.16b, t5.16b, t5.16b, #8
+ ext t6.16b, t4.16b, t4.16b, #8
+ eor t8.8b, t8.8b, t3.8b
+ eor t5.8b, t5.8b, t7.8b
+ eor t4.8b, t4.8b, t6.8b
ext t5.16b, t5.16b, t5.16b, #14
- ext t6.16b, t6.16b, t6.16b, #13
- ext t3.16b, t3.16b, t3.16b, #12
-
- eor t4.16b, t4.16b, t5.16b
- eor t6.16b, t6.16b, t3.16b
ret
-SYM_FUNC_END(__pmull_p8_core)
+SYM_FUNC_END(__pmull_p8_16x64)
- .macro __pmull_p8, rq, ad, bd, i
- .ifnc \bd, fold_consts
- .err
- .endif
- mov ad.16b, \ad\().16b
- .ifb \i
- pmull \rq\().8h, \ad\().8b, \bd\().8b // D = A*B
- .else
- pmull2 \rq\().8h, \ad\().16b, \bd\().16b // D = A*B
- .endif
-
- bl .L__pmull_p8_core\i
-
- eor \rq\().16b, \rq\().16b, t4.16b
- eor \rq\().16b, \rq\().16b, t6.16b
- .endm
// Fold reg1, reg2 into the next 32 data bytes, storing the result back
// into reg1, reg2.
.macro fold_32_bytes, p, reg1, reg2
ldp q11, q12, [buf], #0x20
- __pmull_\p v8, \reg1, fold_consts, 2
- __pmull_\p \reg1, \reg1, fold_consts
+ pmull16x64_\p fold_consts, \reg1, v8
CPU_LE( rev64 v11.16b, v11.16b )
CPU_LE( rev64 v12.16b, v12.16b )
- __pmull_\p v9, \reg2, fold_consts, 2
- __pmull_\p \reg2, \reg2, fold_consts
+ pmull16x64_\p fold_consts, \reg2, v9
CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
@@ -238,26 +197,15 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
// Fold src_reg into dst_reg, optionally loading the next fold constants
.macro fold_16_bytes, p, src_reg, dst_reg, load_next_consts
- __pmull_\p v8, \src_reg, fold_consts
- __pmull_\p \src_reg, \src_reg, fold_consts, 2
+ pmull16x64_\p fold_consts, \src_reg, v8
.ifnb \load_next_consts
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
- __pmull_pre_\p fold_consts
.endif
eor \dst_reg\().16b, \dst_reg\().16b, v8.16b
eor \dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b
.endm
- .macro __pmull_p64, rd, rn, rm, n
- .ifb \n
- pmull \rd\().1q, \rn\().1d, \rm\().1d
- .else
- pmull2 \rd\().1q, \rn\().2d, \rm\().2d
- .endif
- .endm
-
.macro crc_t10dif_pmull, p
- __pmull_init_\p
// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
cmp len, #256
@@ -296,7 +244,6 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// Load the constants for folding across 128 bytes.
ld1 {fold_consts.2d}, [fold_consts_ptr]
- __pmull_pre_\p fold_consts
// Subtract 128 for the 128 data bytes just consumed. Subtract another
// 128 to simplify the termination condition of the following loop.
@@ -318,7 +265,6 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// Fold across 64 bytes.
add fold_consts_ptr, fold_consts_ptr, #16
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
- __pmull_pre_\p fold_consts
fold_16_bytes \p, v0, v4
fold_16_bytes \p, v1, v5
fold_16_bytes \p, v2, v6
@@ -339,8 +285,7 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// into them, storing the result back into v7.
b.lt .Lfold_16_bytes_loop_done_\@
.Lfold_16_bytes_loop_\@:
- __pmull_\p v8, v7, fold_consts
- __pmull_\p v7, v7, fold_consts, 2
+ pmull16x64_\p fold_consts, v7, v8
eor v7.16b, v7.16b, v8.16b
ldr q0, [buf], #16
CPU_LE( rev64 v0.16b, v0.16b )
@@ -387,51 +332,10 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
bsl v2.16b, v1.16b, v0.16b
// Fold the first chunk into the second chunk, storing the result in v7.
- __pmull_\p v0, v3, fold_consts
- __pmull_\p v7, v3, fold_consts, 2
- eor v7.16b, v7.16b, v0.16b
+ pmull16x64_\p fold_consts, v3, v0
+ eor v7.16b, v3.16b, v0.16b
eor v7.16b, v7.16b, v2.16b
-
-.Lreduce_final_16_bytes_\@:
- // Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
-
- movi v2.16b, #0 // init zero register
-
- // Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
- ld1 {fold_consts.2d}, [fold_consts_ptr], #16
- __pmull_pre_\p fold_consts
-
- // Fold the high 64 bits into the low 64 bits, while also multiplying by
- // x^64. This produces a 128-bit value congruent to x^64 * M(x) and
- // whose low 48 bits are 0.
- ext v0.16b, v2.16b, v7.16b, #8
- __pmull_\p v7, v7, fold_consts, 2 // high bits * x^48 * (x^80 mod G(x))
- eor v0.16b, v0.16b, v7.16b // + low bits * x^64
-
- // Fold the high 32 bits into the low 96 bits. This produces a 96-bit
- // value congruent to x^64 * M(x) and whose low 48 bits are 0.
- ext v1.16b, v0.16b, v2.16b, #12 // extract high 32 bits
- mov v0.s[3], v2.s[0] // zero high 32 bits
- __pmull_\p v1, v1, fold_consts // high 32 bits * x^48 * (x^48 mod G(x))
- eor v0.16b, v0.16b, v1.16b // + low bits
-
- // Load G(x) and floor(x^48 / G(x)).
- ld1 {fold_consts.2d}, [fold_consts_ptr]
- __pmull_pre_\p fold_consts
-
- // Use Barrett reduction to compute the final CRC value.
- __pmull_\p v1, v0, fold_consts, 2 // high 32 bits * floor(x^48 / G(x))
- ushr v1.2d, v1.2d, #32 // /= x^32
- __pmull_\p v1, v1, fold_consts // *= G(x)
- ushr v0.2d, v0.2d, #48
- eor v0.16b, v0.16b, v1.16b // + low 16 nonzero bits
- // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
-
- umov w0, v0.h[0]
- .ifc \p, p8
- frame_pop
- .endif
- ret
+ b .Lreduce_final_16_bytes_\@
.Lless_than_256_bytes_\@:
// Checksumming a buffer of length 16...255 bytes
@@ -450,7 +354,6 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// Load the fold-across-16-bytes constants.
ld1 {fold_consts.2d}, [fold_consts_ptr], #16
- __pmull_pre_\p fold_consts
cmp len, #16
b.eq .Lreduce_final_16_bytes_\@ // len == 16
@@ -458,6 +361,8 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
b.ge .Lfold_16_bytes_loop_\@ // 32 <= len <= 255
add len, len, #16
b .Lhandle_partial_segment_\@ // 17 <= len <= 31
+
+.Lreduce_final_16_bytes_\@:
.endm
//
@@ -467,7 +372,22 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
//
SYM_FUNC_START(crc_t10dif_pmull_p8)
frame_push 1
+
+ // Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
+ movi perm.4h, #8, lsl #8
+ orr perm.2s, #1, lsl #16
+ orr perm.2s, #1, lsl #24
+ zip1 perm.16b, perm.16b, perm.16b
+ zip1 perm.16b, perm.16b, perm.16b
+
crc_t10dif_pmull p8
+
+CPU_LE( rev64 v7.16b, v7.16b )
+CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
+ str q7, [x3]
+
+ frame_pop
+ ret
SYM_FUNC_END(crc_t10dif_pmull_p8)
.align 5
@@ -478,6 +398,41 @@ SYM_FUNC_END(crc_t10dif_pmull_p8)
//
SYM_FUNC_START(crc_t10dif_pmull_p64)
crc_t10dif_pmull p64
+
+ // Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
+
+ movi v2.16b, #0 // init zero register
+
+ // Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
+ ld1 {fold_consts.2d}, [fold_consts_ptr], #16
+
+ // Fold the high 64 bits into the low 64 bits, while also multiplying by
+ // x^64. This produces a 128-bit value congruent to x^64 * M(x) and
+ // whose low 48 bits are 0.
+ ext v0.16b, v2.16b, v7.16b, #8
+ pmull2 v7.1q, v7.2d, fold_consts.2d // high bits * x^48 * (x^80 mod G(x))
+ eor v0.16b, v0.16b, v7.16b // + low bits * x^64
+
+ // Fold the high 32 bits into the low 96 bits. This produces a 96-bit
+ // value congruent to x^64 * M(x) and whose low 48 bits are 0.
+ ext v1.16b, v0.16b, v2.16b, #12 // extract high 32 bits
+ mov v0.s[3], v2.s[0] // zero high 32 bits
+ pmull v1.1q, v1.1d, fold_consts.1d // high 32 bits * x^48 * (x^48 mod G(x))
+ eor v0.16b, v0.16b, v1.16b // + low bits
+
+ // Load G(x) and floor(x^48 / G(x)).
+ ld1 {fold_consts.2d}, [fold_consts_ptr]
+
+ // Use Barrett reduction to compute the final CRC value.
+ pmull2 v1.1q, v0.2d, fold_consts.2d // high 32 bits * floor(x^48 / G(x))
+ ushr v1.2d, v1.2d, #32 // /= x^32
+ pmull v1.1q, v1.1d, fold_consts.1d // *= G(x)
+ ushr v0.2d, v0.2d, #48
+ eor v0.16b, v0.16b, v1.16b // + low 16 nonzero bits
+ // Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
+
+ umov w0, v0.h[0]
+ ret
SYM_FUNC_END(crc_t10dif_pmull_p64)
.section ".rodata", "a"
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index 606d25c559ed..08bcbd884395 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -20,7 +20,8 @@
#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
-asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage void crc_t10dif_pmull_p8(u16 init_crc, const u8 *buf, size_t len,
+ u8 out[16]);
asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 *buf, size_t len);
static int crct10dif_init(struct shash_desc *desc)
@@ -34,25 +35,21 @@ static int crct10dif_init(struct shash_desc *desc)
static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
unsigned int length)
{
- u16 *crc = shash_desc_ctx(desc);
-
- if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
- do {
- unsigned int chunk = length;
-
- if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE)
- chunk = SZ_4K;
-
- kernel_neon_begin();
- *crc = crc_t10dif_pmull_p8(*crc, data, chunk);
- kernel_neon_end();
- data += chunk;
- length -= chunk;
- } while (length);
- } else {
- *crc = crc_t10dif_generic(*crc, data, length);
+ u16 *crcp = shash_desc_ctx(desc);
+ u16 crc = *crcp;
+ u8 buf[16];
+
+ if (length > CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
+ kernel_neon_begin();
+ crc_t10dif_pmull_p8(crc, data, length, buf);
+ kernel_neon_end();
+
+ crc = 0;
+ data = buf;
+ length = sizeof(buf);
}
+ *crcp = crc_t10dif_generic(crc, data, length);
return 0;
}
@@ -62,18 +59,9 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
u16 *crc = shash_desc_ctx(desc);
if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
- do {
- unsigned int chunk = length;
-
- if (chunk > SZ_4K + CRC_T10DIF_PMULL_CHUNK_SIZE)
- chunk = SZ_4K;
-
- kernel_neon_begin();
- *crc = crc_t10dif_pmull_p64(*crc, data, chunk);
- kernel_neon_end();
- data += chunk;
- length -= chunk;
- } while (length);
+ kernel_neon_begin();
+ *crc = crc_t10dif_pmull_p64(*crc, data, length);
+ kernel_neon_end();
} else {
*crc = crc_t10dif_generic(*crc, data, length);
}
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 97331b454ea8..da7b7ec1a664 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/aes.h>
#include <crypto/gcm.h>
#include <crypto/algapi.h>
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
index 9c4bfd62e789..18883ea438f3 100644
--- a/arch/arm64/crypto/poly1305-glue.c
+++ b/arch/arm64/crypto/poly1305-glue.c
@@ -8,7 +8,7 @@
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/algapi.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/poly1305.h>
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 1dd93e1fcb39..cbd14f208f83 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sha1.h>
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 0a44d2e7ee1f..6b4866a88ded 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sha2.h>
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index 250e1377c481..5662c3ac49e9 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -12,7 +12,7 @@
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sha3.h>
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index f3431fc62315..071f64293227 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -11,7 +11,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sha2.h>
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
index 54bf6ebcfffb..1a71788c4cda 100644
--- a/arch/arm64/crypto/sm3-ce-glue.c
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sm3.h>
diff --git a/arch/arm64/crypto/sm3-neon-glue.c b/arch/arm64/crypto/sm3-neon-glue.c
index 7182ee683f14..8dd71ce79b69 100644
--- a/arch/arm64/crypto/sm3-neon-glue.c
+++ b/arch/arm64/crypto/sm3-neon-glue.c
@@ -7,7 +7,7 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sm3.h>
diff --git a/arch/arm64/include/asm/arm_pmuv3.h b/arch/arm64/include/asm/arm_pmuv3.h
index 468a049bc63b..8a777dec8d88 100644
--- a/arch/arm64/include/asm/arm_pmuv3.h
+++ b/arch/arm64/include/asm/arm_pmuv3.h
@@ -152,6 +152,11 @@ static inline void write_pmuserenr(u32 val)
write_sysreg(val, pmuserenr_el0);
}
+static inline void write_pmuacr(u64 val)
+{
+ write_sysreg_s(val, SYS_PMUACR_EL1);
+}
+
static inline u64 read_pmceid0(void)
{
return read_sysreg(pmceid0_el0);
@@ -178,4 +183,9 @@ static inline bool is_pmuv3p5(int pmuver)
return pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P5;
}
+static inline bool is_pmuv3p9(int pmuver)
+{
+ return pmuver >= ID_AA64DFR0_EL1_PMUVer_V3P9;
+}
+
#endif
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index bc0b0d75acef..3d8d534a7a77 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -249,13 +249,6 @@ alternative_endif
.endm
/*
- * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
- */
- .macro vma_vm_mm, rd, rn
- ldr \rd, [\rn, #VMA_VM_MM]
- .endm
-
-/*
* read_ctr - read CTR_EL0. If the system has mismatched register fields,
* provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val
*/
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index a6e5b07b64fd..a08a1212ffbb 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -42,6 +42,8 @@ cpucap_is_possible(const unsigned int cap)
return IS_ENABLED(CONFIG_ARM64_BTI);
case ARM64_HAS_TLB_RANGE:
return IS_ENABLED(CONFIG_ARM64_TLB_RANGE);
+ case ARM64_HAS_S1POE:
+ return IS_ENABLED(CONFIG_ARM64_POE);
case ARM64_UNMAP_KERNEL_AT_EL0:
return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0);
case ARM64_WORKAROUND_843419:
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 3d261cc123c1..3d63c20ccefc 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -12,7 +12,7 @@
#include <asm/hwcap.h>
#include <asm/sysreg.h>
-#define MAX_CPU_FEATURES 128
+#define MAX_CPU_FEATURES 192
#define cpu_feature(x) KERNEL_HWCAP_ ## x
#define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0
@@ -438,6 +438,7 @@ void cpu_set_feature(unsigned int num);
bool cpu_have_feature(unsigned int num);
unsigned long cpu_get_elf_hwcap(void);
unsigned long cpu_get_elf_hwcap2(void);
+unsigned long cpu_get_elf_hwcap3(void);
#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
@@ -834,8 +835,19 @@ static inline bool system_supports_lpa2(void)
static inline bool system_supports_poe(void)
{
- return IS_ENABLED(CONFIG_ARM64_POE) &&
- alternative_has_cap_unlikely(ARM64_HAS_S1POE);
+ return alternative_has_cap_unlikely(ARM64_HAS_S1POE);
+}
+
+static inline bool system_supports_gcs(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_GCS) &&
+ alternative_has_cap_unlikely(ARM64_HAS_GCS);
+}
+
+static inline bool system_supports_haft(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_HAFT) &&
+ cpus_have_final_cap(ARM64_HAFT);
}
int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5a7dfeb8e8eb..488f8e751349 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -94,6 +94,7 @@
#define ARM_CPU_PART_NEOVERSE_V3 0xD84
#define ARM_CPU_PART_CORTEX_X925 0xD85
#define ARM_CPU_PART_CORTEX_A725 0xD87
+#define ARM_CPU_PART_NEOVERSE_N3 0xD8E
#define APM_CPU_PART_XGENE 0x000
#define APM_CPU_VAR_POTENZA 0x00
@@ -176,6 +177,7 @@
#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925)
#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)
+#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 55f57dfa8e2f..fbb5c99eb2f9 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -132,7 +132,7 @@ static inline void local_daif_inherit(struct pt_regs *regs)
trace_hardirqs_on();
if (system_uses_irq_prio_masking())
- gic_write_pmr(regs->pmr_save);
+ gic_write_pmr(regs->pmr);
/*
* We can't use local_daif_restore(regs->pstate) here as
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 13d437bcbf58..8f6ba31b8658 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -105,6 +105,7 @@ void kernel_enable_single_step(struct pt_regs *regs);
void kernel_disable_single_step(void);
int kernel_active_single_step(void);
void kernel_rewind_single_step(struct pt_regs *regs);
+void kernel_fastforward_single_step(struct pt_regs *regs);
#ifdef CONFIG_HAVE_HW_BREAKPOINT
int reinstall_suspended_bps(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index e0ffdf13a18b..27086a81eae3 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -27,6 +27,14 @@
ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4
cbz x0, .Lskip_hcrx_\@
mov_q x0, HCRX_HOST_FLAGS
+
+ /* Enable GCS if supported */
+ mrs_s x1, SYS_ID_AA64PFR1_EL1
+ ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
+ cbz x1, .Lset_hcrx_\@
+ orr x0, x0, #HCRX_EL2_GCSEn
+
+.Lset_hcrx_\@:
msr_s SYS_HCRX_EL2, x0
.Lskip_hcrx_\@:
.endm
@@ -200,6 +208,16 @@
orr x0, x0, #HFGxTR_EL2_nPOR_EL0
.Lskip_poe_fgt_\@:
+ /* GCS depends on PIE so we don't check it if PIE is absent */
+ mrs_s x1, SYS_ID_AA64PFR1_EL1
+ ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
+ cbz x1, .Lset_fgt_\@
+
+ /* Disable traps of access to GCS registers at EL0 and EL1 */
+ orr x0, x0, #HFGxTR_EL2_nGCS_EL1_MASK
+ orr x0, x0, #HFGxTR_EL2_nGCS_EL0_MASK
+
+.Lset_fgt_\@:
msr_s SYS_HFGRTR_EL2, x0
msr_s SYS_HFGWTR_EL2, x0
msr_s SYS_HFGITR_EL2, xzr
@@ -215,6 +233,17 @@
.Lskip_fgt_\@:
.endm
+.macro __init_el2_gcs
+ mrs_s x1, SYS_ID_AA64PFR1_EL1
+ ubfx x1, x1, #ID_AA64PFR1_EL1_GCS_SHIFT, #4
+ cbz x1, .Lskip_gcs_\@
+
+ /* Ensure GCS is not enabled when we start trying to do BLs */
+ msr_s SYS_GCSCR_EL1, xzr
+ msr_s SYS_GCSCRE0_EL1, xzr
+.Lskip_gcs_\@:
+.endm
+
.macro __init_el2_nvhe_prepare_eret
mov x0, #INIT_PSTATE_EL1
msr spsr_el2, x0
@@ -240,6 +269,7 @@
__init_el2_nvhe_idregs
__init_el2_cptr
__init_el2_fgt
+ __init_el2_gcs
.endm
#ifndef __KVM_NVHE_HYPERVISOR__
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index da6d2c1c0b03..d1b1a33f9a8b 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -51,7 +51,8 @@
#define ESR_ELx_EC_FP_EXC32 UL(0x28)
/* Unallocated EC: 0x29 - 0x2B */
#define ESR_ELx_EC_FP_EXC64 UL(0x2C)
-/* Unallocated EC: 0x2D - 0x2E */
+#define ESR_ELx_EC_GCS UL(0x2D)
+/* Unallocated EC: 0x2E */
#define ESR_ELx_EC_SERROR UL(0x2F)
#define ESR_ELx_EC_BREAKPT_LOW UL(0x30)
#define ESR_ELx_EC_BREAKPT_CUR UL(0x31)
@@ -386,6 +387,31 @@
#define ESR_ELx_MOPS_ISS_SRCREG(esr) (((esr) & (UL(0x1f) << 5)) >> 5)
#define ESR_ELx_MOPS_ISS_SIZEREG(esr) (((esr) & (UL(0x1f) << 0)) >> 0)
+/* ISS field definitions for GCS */
+#define ESR_ELx_ExType_SHIFT (20)
+#define ESR_ELx_ExType_MASK GENMASK(23, 20)
+#define ESR_ELx_Raddr_SHIFT (10)
+#define ESR_ELx_Raddr_MASK GENMASK(14, 10)
+#define ESR_ELx_Rn_SHIFT (5)
+#define ESR_ELx_Rn_MASK GENMASK(9, 5)
+#define ESR_ELx_Rvalue_SHIFT 5
+#define ESR_ELx_Rvalue_MASK GENMASK(9, 5)
+#define ESR_ELx_IT_SHIFT (0)
+#define ESR_ELx_IT_MASK GENMASK(4, 0)
+
+#define ESR_ELx_ExType_DATA_CHECK 0
+#define ESR_ELx_ExType_EXLOCK 1
+#define ESR_ELx_ExType_STR 2
+
+#define ESR_ELx_IT_RET 0
+#define ESR_ELx_IT_GCSPOPM 1
+#define ESR_ELx_IT_RET_KEYA 2
+#define ESR_ELx_IT_RET_KEYB 3
+#define ESR_ELx_IT_GCSSS1 4
+#define ESR_ELx_IT_GCSSS2 5
+#define ESR_ELx_IT_GCSPOPCX 6
+#define ESR_ELx_IT_GCSPOPX 7
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h
index f296662590c7..d48fc16584cd 100644
--- a/arch/arm64/include/asm/exception.h
+++ b/arch/arm64/include/asm/exception.h
@@ -57,6 +57,8 @@ void do_el0_undef(struct pt_regs *regs, unsigned long esr);
void do_el1_undef(struct pt_regs *regs, unsigned long esr);
void do_el0_bti(struct pt_regs *regs);
void do_el1_bti(struct pt_regs *regs, unsigned long esr);
+void do_el0_gcs(struct pt_regs *regs, unsigned long esr);
+void do_el1_gcs(struct pt_regs *regs, unsigned long esr);
void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr,
struct pt_regs *regs);
void do_fpsimd_acc(unsigned long esr, struct pt_regs *regs);
@@ -73,6 +75,7 @@ void do_el0_svc_compat(struct pt_regs *regs);
void do_el0_fpac(struct pt_regs *regs, unsigned long esr);
void do_el1_fpac(struct pt_regs *regs, unsigned long esr);
void do_el0_mops(struct pt_regs *regs, unsigned long esr);
+void do_el1_mops(struct pt_regs *regs, unsigned long esr);
void do_serror(struct pt_regs *regs, unsigned long esr);
void do_signal(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index dc9cf0bd2a4c..5ccff4de7f09 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -54,8 +54,11 @@ extern void return_to_handler(void);
unsigned long ftrace_call_adjust(unsigned long addr);
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+#define HAVE_ARCH_FTRACE_REGS
struct dyn_ftrace;
struct ftrace_ops;
+struct ftrace_regs;
+#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs))
#define arch_ftrace_get_regs(regs) NULL
@@ -63,7 +66,7 @@ struct ftrace_ops;
* Note: sizeof(struct ftrace_regs) must be a multiple of 16 to ensure correct
* stack alignment
*/
-struct ftrace_regs {
+struct __arch_ftrace_regs {
/* x0 - x8 */
unsigned long regs[9];
@@ -83,47 +86,47 @@ struct ftrace_regs {
static __always_inline unsigned long
ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
{
- return fregs->pc;
+ return arch_ftrace_regs(fregs)->pc;
}
static __always_inline void
ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
unsigned long pc)
{
- fregs->pc = pc;
+ arch_ftrace_regs(fregs)->pc = pc;
}
static __always_inline unsigned long
ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
{
- return fregs->sp;
+ return arch_ftrace_regs(fregs)->sp;
}
static __always_inline unsigned long
ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n)
{
if (n < 8)
- return fregs->regs[n];
+ return arch_ftrace_regs(fregs)->regs[n];
return 0;
}
static __always_inline unsigned long
ftrace_regs_get_return_value(const struct ftrace_regs *fregs)
{
- return fregs->regs[0];
+ return arch_ftrace_regs(fregs)->regs[0];
}
static __always_inline void
ftrace_regs_set_return_value(struct ftrace_regs *fregs,
unsigned long ret)
{
- fregs->regs[0] = ret;
+ arch_ftrace_regs(fregs)->regs[0] = ret;
}
static __always_inline void
ftrace_override_function_with_return(struct ftrace_regs *fregs)
{
- fregs->pc = fregs->lr;
+ arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr;
}
int ftrace_regs_query_register_offset(const char *name);
@@ -143,7 +146,7 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
* The ftrace trampoline will return to this address instead of the
* instrumented function.
*/
- fregs->direct_tramp = addr;
+ arch_ftrace_regs(fregs)->direct_tramp = addr;
}
#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/arm64/include/asm/gcs.h b/arch/arm64/include/asm/gcs.h
new file mode 100644
index 000000000000..f50660603ecf
--- /dev/null
+++ b/arch/arm64/include/asm/gcs.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+#ifndef __ASM_GCS_H
+#define __ASM_GCS_H
+
+#include <asm/types.h>
+#include <asm/uaccess.h>
+
+struct kernel_clone_args;
+struct ksignal;
+
+static inline void gcsb_dsync(void)
+{
+ asm volatile(".inst 0xd503227f" : : : "memory");
+}
+
+static inline void gcsstr(u64 *addr, u64 val)
+{
+ register u64 *_addr __asm__ ("x0") = addr;
+ register long _val __asm__ ("x1") = val;
+
+ /* GCSSTTR x1, x0 */
+ asm volatile(
+ ".inst 0xd91f1c01\n"
+ :
+ : "rZ" (_val), "r" (_addr)
+ : "memory");
+}
+
+static inline void gcsss1(u64 Xt)
+{
+ asm volatile (
+ "sys #3, C7, C7, #2, %0\n"
+ :
+ : "rZ" (Xt)
+ : "memory");
+}
+
+static inline u64 gcsss2(void)
+{
+ u64 Xt;
+
+ asm volatile(
+ "SYSL %0, #3, C7, C7, #3\n"
+ : "=r" (Xt)
+ :
+ : "memory");
+
+ return Xt;
+}
+
+#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK \
+ (PR_SHADOW_STACK_ENABLE | PR_SHADOW_STACK_WRITE | PR_SHADOW_STACK_PUSH)
+
+#ifdef CONFIG_ARM64_GCS
+
+static inline bool task_gcs_el0_enabled(struct task_struct *task)
+{
+ return current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE;
+}
+
+void gcs_set_el0_mode(struct task_struct *task);
+void gcs_free(struct task_struct *task);
+void gcs_preserve_current_state(void);
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args);
+
+static inline int gcs_check_locked(struct task_struct *task,
+ unsigned long new_val)
+{
+ unsigned long cur_val = task->thread.gcs_el0_mode;
+
+ cur_val &= task->thread.gcs_el0_locked;
+ new_val &= task->thread.gcs_el0_locked;
+
+ if (cur_val != new_val)
+ return -EBUSY;
+
+ return 0;
+}
+
+#else
+
+static inline bool task_gcs_el0_enabled(struct task_struct *task)
+{
+ return false;
+}
+
+static inline void gcs_set_el0_mode(struct task_struct *task) { }
+static inline void gcs_free(struct task_struct *task) { }
+static inline void gcs_preserve_current_state(void) { }
+static inline unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args)
+{
+ return -ENOTSUPP;
+}
+static inline int gcs_check_locked(struct task_struct *task,
+ unsigned long new_val)
+{
+ return 0;
+}
+
+#endif
+
+#endif
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 293f880865e8..c6dff3e69539 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -11,6 +11,7 @@
#define __ASM_HUGETLB_H
#include <asm/cacheflush.h>
+#include <asm/mte.h>
#include <asm/page.h>
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
@@ -21,6 +22,13 @@ extern bool arch_hugetlb_migration_supported(struct hstate *h);
static inline void arch_clear_hugetlb_flags(struct folio *folio)
{
clear_bit(PG_dcache_clean, &folio->flags);
+
+#ifdef CONFIG_ARM64_MTE
+ if (system_supports_mte()) {
+ clear_bit(PG_mte_tagged, &folio->flags);
+ clear_bit(PG_mte_lock, &folio->flags);
+ }
+#endif
}
#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index a775adddecf2..2b6c61c608e2 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -92,6 +92,7 @@
#define KERNEL_HWCAP_SB __khwcap_feature(SB)
#define KERNEL_HWCAP_PACA __khwcap_feature(PACA)
#define KERNEL_HWCAP_PACG __khwcap_feature(PACG)
+#define KERNEL_HWCAP_GCS __khwcap_feature(GCS)
#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 64)
#define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP)
@@ -159,17 +160,21 @@
#define KERNEL_HWCAP_SME_SF8DP2 __khwcap2_feature(SME_SF8DP2)
#define KERNEL_HWCAP_POE __khwcap2_feature(POE)
+#define __khwcap3_feature(x) (const_ilog2(HWCAP3_ ## x) + 128)
+
/*
* This yields a mask that user programs can use to figure out what
* instruction set this cpu supports.
*/
#define ELF_HWCAP cpu_get_elf_hwcap()
#define ELF_HWCAP2 cpu_get_elf_hwcap2()
+#define ELF_HWCAP3 cpu_get_elf_hwcap3()
#ifdef CONFIG_COMPAT
#define COMPAT_ELF_HWCAP (compat_elf_hwcap)
#define COMPAT_ELF_HWCAP2 (compat_elf_hwcap2)
-extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
+#define COMPAT_ELF_HWCAP3 (compat_elf_hwcap3)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2, compat_elf_hwcap3;
#endif
enum {
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 8c0a36f72d6f..e390c432f546 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -353,6 +353,7 @@ __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000)
__AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000)
__AARCH64_INSN_FUNCS(load_ex, 0x3F400000, 0x08400000)
__AARCH64_INSN_FUNCS(store_ex, 0x3F400000, 0x08000000)
+__AARCH64_INSN_FUNCS(mops, 0x3B200C00, 0x19000400)
__AARCH64_INSN_FUNCS(stp, 0x7FC00000, 0x29000000)
__AARCH64_INSN_FUNCS(ldp, 0x7FC00000, 0x29400000)
__AARCH64_INSN_FUNCS(stp_post, 0x7FC00000, 0x28800000)
@@ -575,6 +576,11 @@ static __always_inline u32 aarch64_insn_gen_nop(void)
return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP);
}
+static __always_inline bool aarch64_insn_is_nop(u32 insn)
+{
+ return insn == aarch64_insn_gen_nop();
+}
+
u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg,
enum aarch64_insn_branch_type type);
u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg,
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 1ada23a6ec19..8688343b71f2 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -17,6 +17,7 @@
#include <asm/early_ioremap.h>
#include <asm/alternative.h>
#include <asm/cpufeature.h>
+#include <asm/rsi.h>
/*
* Generic IO read/write. These perform native-endian accesses.
@@ -318,4 +319,11 @@ extern bool arch_memremap_can_ram_remap(resource_size_t offset, size_t size,
unsigned long flags);
#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap
+static inline bool arm64_is_protected_mmio(phys_addr_t phys_addr, size_t size)
+{
+ if (unlikely(is_realm_world()))
+ return __arm64_is_protected_mmio(phys_addr, size);
+ return false;
+}
+
#endif /* __ASM_IO_H */
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index bf05a77873a4..fd5a08450b12 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -26,7 +26,6 @@
#define SWAPPER_SKIP_LEVEL 0
#endif
#define SWAPPER_BLOCK_SIZE (UL(1) << SWAPPER_BLOCK_SHIFT)
-#define SWAPPER_TABLE_SHIFT (SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3)
#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL)
#define INIT_IDMAP_PGTABLE_LEVELS (IDMAP_LEVELS - SWAPPER_SKIP_LEVEL)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index b36a3b6cc011..67afac659231 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
unsigned long hcr_el2;
unsigned long vttbr;
unsigned long vtcr;
+ unsigned long tmp;
};
/*
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 329619c6fa96..bf64fed9820e 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -51,6 +51,7 @@
#define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5)
#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6)
#define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7)
+#define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
@@ -212,6 +213,12 @@ struct kvm_s2_mmu {
bool nested_stage2_enabled;
/*
+ * true when this MMU needs to be unmapped before being used for a new
+ * purpose.
+ */
+ bool pending_unmap;
+
+ /*
* 0: Nobody is currently using this, check vttbr for validity
* >0: Somebody is actively using this.
*/
@@ -1441,11 +1448,6 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
sign_extend64(__val, id##_##fld##_WIDTH - 1); \
})
-#define expand_field_sign(id, fld, val) \
- (id##_##fld##_SIGNED ? \
- __expand_field_sign_signed(id, fld, val) : \
- __expand_field_sign_unsigned(id, fld, val))
-
#define get_idreg_field_unsigned(kvm, id, fld) \
({ \
u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id); \
@@ -1461,20 +1463,26 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
#define get_idreg_field_enum(kvm, id, fld) \
get_idreg_field_unsigned(kvm, id, fld)
-#define get_idreg_field(kvm, id, fld) \
+#define kvm_cmp_feat_signed(kvm, id, fld, op, limit) \
+ (get_idreg_field_signed((kvm), id, fld) op __expand_field_sign_signed(id, fld, limit))
+
+#define kvm_cmp_feat_unsigned(kvm, id, fld, op, limit) \
+ (get_idreg_field_unsigned((kvm), id, fld) op __expand_field_sign_unsigned(id, fld, limit))
+
+#define kvm_cmp_feat(kvm, id, fld, op, limit) \
(id##_##fld##_SIGNED ? \
- get_idreg_field_signed(kvm, id, fld) : \
- get_idreg_field_unsigned(kvm, id, fld))
+ kvm_cmp_feat_signed(kvm, id, fld, op, limit) : \
+ kvm_cmp_feat_unsigned(kvm, id, fld, op, limit))
#define kvm_has_feat(kvm, id, fld, limit) \
- (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit))
+ kvm_cmp_feat(kvm, id, fld, >=, limit)
#define kvm_has_feat_enum(kvm, id, fld, val) \
- (get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val))
+ kvm_cmp_feat_unsigned(kvm, id, fld, ==, val)
#define kvm_has_feat_range(kvm, id, fld, min, max) \
- (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \
- get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max))
+ (kvm_cmp_feat(kvm, id, fld, >=, min) && \
+ kvm_cmp_feat(kvm, id, fld, <=, max))
/* Check for a given level of PAuth support */
#define kvm_has_pauth(k, l) \
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index cd4087fbda9a..66d93e320ec8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
void __init free_hyp_pgds(void);
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+ u64 size, bool may_block);
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index e8bc6d67aba2..233e65522716 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
+extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
+
struct kvm_s2_trans {
phys_addr_t output;
unsigned long block_size;
@@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
struct kvm_s2_trans *trans);
extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
extern void kvm_nested_s2_wp(struct kvm *kvm);
-extern void kvm_nested_s2_unmap(struct kvm *kvm);
+extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
extern void kvm_nested_s2_flush(struct kvm *kvm);
unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
diff --git a/arch/arm64/include/asm/mem_encrypt.h b/arch/arm64/include/asm/mem_encrypt.h
index b0c9a86b13a4..f8f78f622dd2 100644
--- a/arch/arm64/include/asm/mem_encrypt.h
+++ b/arch/arm64/include/asm/mem_encrypt.h
@@ -2,6 +2,8 @@
#ifndef __ASM_MEM_ENCRYPT_H
#define __ASM_MEM_ENCRYPT_H
+#include <asm/rsi.h>
+
struct arm64_mem_crypt_ops {
int (*encrypt)(unsigned long addr, int numpages);
int (*decrypt)(unsigned long addr, int numpages);
@@ -12,4 +14,11 @@ int arm64_mem_crypt_ops_register(const struct arm64_mem_crypt_ops *ops);
int set_memory_encrypted(unsigned long addr, int numpages);
int set_memory_decrypted(unsigned long addr, int numpages);
+int realm_register_memory_enc_ops(void);
+
+static inline bool force_dma_unencrypted(struct device *dev)
+{
+ return is_realm_world();
+}
+
#endif /* __ASM_MEM_ENCRYPT_H */
diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h
index 9e39217b4afb..1d53022fc7e1 100644
--- a/arch/arm64/include/asm/mman.h
+++ b/arch/arm64/include/asm/mman.h
@@ -6,6 +6,8 @@
#ifndef BUILD_VDSO
#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/shmem_fs.h>
#include <linux/types.h>
static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
@@ -31,19 +33,24 @@ static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
}
#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
-static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags)
+static inline unsigned long arch_calc_vm_flag_bits(struct file *file,
+ unsigned long flags)
{
/*
* Only allow MTE on anonymous mappings as these are guaranteed to be
* backed by tags-capable memory. The vm_flags may be overridden by a
* filesystem supporting MTE (RAM-based).
*/
- if (system_supports_mte() && (flags & MAP_ANONYMOUS))
- return VM_MTE_ALLOWED;
+ if (system_supports_mte()) {
+ if (flags & (MAP_ANONYMOUS | MAP_HUGETLB))
+ return VM_MTE_ALLOWED;
+ if (shmem_file(file))
+ return VM_MTE_ALLOWED;
+ }
return 0;
}
-#define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags)
+#define arch_calc_vm_flag_bits(file, flags) arch_calc_vm_flag_bits(file, flags)
static inline bool arch_validate_prot(unsigned long prot,
unsigned long addr __always_unused)
@@ -62,11 +69,26 @@ static inline bool arch_validate_prot(unsigned long prot,
static inline bool arch_validate_flags(unsigned long vm_flags)
{
- if (!system_supports_mte())
- return true;
+ if (system_supports_mte()) {
+ /*
+ * only allow VM_MTE if VM_MTE_ALLOWED has been set
+ * previously
+ */
+ if ((vm_flags & VM_MTE) && !(vm_flags & VM_MTE_ALLOWED))
+ return false;
+ }
+
+ if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
+ /* An executable GCS isn't a good idea. */
+ if (vm_flags & VM_EXEC)
+ return false;
+
+ /* The memory management core should prevent this */
+ VM_WARN_ON(vm_flags & VM_SHARED);
+ }
+
+ return true;
- /* only allow VM_MTE if VM_MTE_ALLOWED has been set previously */
- return !(vm_flags & VM_MTE) || (vm_flags & VM_MTE_ALLOWED);
}
#define arch_validate_flags(vm_flags) arch_validate_flags(vm_flags)
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 7c09d47e09cb..48b3d9553b67 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -20,6 +20,7 @@
#include <asm/cacheflush.h>
#include <asm/cpufeature.h>
#include <asm/daifflags.h>
+#include <asm/gcs.h>
#include <asm/proc-fns.h>
#include <asm/cputype.h>
#include <asm/sysreg.h>
@@ -311,6 +312,14 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
return por_el0_allows_pkey(vma_pkey(vma), write, execute);
}
+#define deactivate_mm deactivate_mm
+static inline void deactivate_mm(struct task_struct *tsk,
+ struct mm_struct *mm)
+{
+ gcs_free(tsk);
+}
+
+
#include <asm-generic/mmu_context.h>
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/mte.h b/arch/arm64/include/asm/mte.h
index 0f84518632b4..6567df8ec8ca 100644
--- a/arch/arm64/include/asm/mte.h
+++ b/arch/arm64/include/asm/mte.h
@@ -41,6 +41,8 @@ void mte_free_tag_storage(char *storage);
static inline void set_page_mte_tagged(struct page *page)
{
+ VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page)));
+
/*
* Ensure that the tags written prior to this function are visible
* before the page flags update.
@@ -53,6 +55,8 @@ static inline bool page_mte_tagged(struct page *page)
{
bool ret = test_bit(PG_mte_tagged, &page->flags);
+ VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page)));
+
/*
* If the page is tagged, ensure ordering with a likely subsequent
* read of the tags.
@@ -76,6 +80,8 @@ static inline bool page_mte_tagged(struct page *page)
*/
static inline bool try_page_mte_tagging(struct page *page)
{
+ VM_WARN_ON_ONCE(folio_test_hugetlb(page_folio(page)));
+
if (!test_and_set_bit(PG_mte_lock, &page->flags))
return true;
@@ -157,6 +163,67 @@ static inline int mte_ptrace_copy_tags(struct task_struct *child,
#endif /* CONFIG_ARM64_MTE */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_ARM64_MTE)
+static inline void folio_set_hugetlb_mte_tagged(struct folio *folio)
+{
+ VM_WARN_ON_ONCE(!folio_test_hugetlb(folio));
+
+ /*
+ * Ensure that the tags written prior to this function are visible
+ * before the folio flags update.
+ */
+ smp_wmb();
+ set_bit(PG_mte_tagged, &folio->flags);
+
+}
+
+static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio)
+{
+ bool ret = test_bit(PG_mte_tagged, &folio->flags);
+
+ VM_WARN_ON_ONCE(!folio_test_hugetlb(folio));
+
+ /*
+ * If the folio is tagged, ensure ordering with a likely subsequent
+ * read of the tags.
+ */
+ if (ret)
+ smp_rmb();
+ return ret;
+}
+
+static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio)
+{
+ VM_WARN_ON_ONCE(!folio_test_hugetlb(folio));
+
+ if (!test_and_set_bit(PG_mte_lock, &folio->flags))
+ return true;
+
+ /*
+ * The tags are either being initialised or may have been initialised
+ * already. Check if the PG_mte_tagged flag has been set or wait
+ * otherwise.
+ */
+ smp_cond_load_acquire(&folio->flags, VAL & (1UL << PG_mte_tagged));
+
+ return false;
+}
+#else
+static inline void folio_set_hugetlb_mte_tagged(struct folio *folio)
+{
+}
+
+static inline bool folio_test_hugetlb_mte_tagged(struct folio *folio)
+{
+ return false;
+}
+
+static inline bool folio_try_hugetlb_mte_tagging(struct folio *folio)
+{
+ return false;
+}
+#endif
+
static inline void mte_disable_tco_entry(struct task_struct *task)
{
if (!system_supports_mte())
diff --git a/arch/arm64/include/asm/page-def.h b/arch/arm64/include/asm/page-def.h
index 792e9fe881dc..d402e08442ee 100644
--- a/arch/arm64/include/asm/page-def.h
+++ b/arch/arm64/include/asm/page-def.h
@@ -10,9 +10,6 @@
#include <linux/const.h>
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT CONFIG_PAGE_SHIFT
-#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
+#include <vdso/page.h>
#endif /* __ASM_PAGE_DEF_H */
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index eb7071c9eb34..ee45b4e77347 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -10,10 +10,6 @@
#include <asm/ptrace.h>
#ifdef CONFIG_PERF_EVENTS
-struct pt_regs;
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs) perf_misc_flags(regs)
#define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
#endif
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 8ff5f2a2579e..e75422864d1b 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -28,7 +28,7 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
{
- pudval_t pudval = PUD_TYPE_TABLE;
+ pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_AF;
pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN;
__pud_populate(pudp, __pa(pmdp), pudval);
@@ -50,7 +50,7 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
{
- p4dval_t p4dval = P4D_TYPE_TABLE;
+ p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_AF;
p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
__p4d_populate(p4dp, __pa(pudp), p4dval);
@@ -79,7 +79,7 @@ static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot)
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp)
{
- pgdval_t pgdval = PGD_TYPE_TABLE;
+ pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_AF;
pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN;
__pgd_populate(pgdp, __pa(p4dp), pgdval);
@@ -127,14 +127,16 @@ static inline void
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
{
VM_BUG_ON(mm && mm != &init_mm);
- __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
+ __pmd_populate(pmdp, __pa(ptep),
+ PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_UXN);
}
static inline void
pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
{
VM_BUG_ON(mm == &init_mm);
- __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN);
+ __pmd_populate(pmdp, page_to_phys(ptep),
+ PMD_TYPE_TABLE | PMD_TABLE_AF | PMD_TABLE_PXN);
}
#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index fd330c1db289..c78a988cca93 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -99,6 +99,7 @@
#define PGD_TYPE_TABLE (_AT(pgdval_t, 3) << 0)
#define PGD_TABLE_BIT (_AT(pgdval_t, 1) << 1)
#define PGD_TYPE_MASK (_AT(pgdval_t, 3) << 0)
+#define PGD_TABLE_AF (_AT(pgdval_t, 1) << 10) /* Ignored if no FEAT_HAFT */
#define PGD_TABLE_PXN (_AT(pgdval_t, 1) << 59)
#define PGD_TABLE_UXN (_AT(pgdval_t, 1) << 60)
@@ -110,6 +111,7 @@
#define P4D_TYPE_MASK (_AT(p4dval_t, 3) << 0)
#define P4D_TYPE_SECT (_AT(p4dval_t, 1) << 0)
#define P4D_SECT_RDONLY (_AT(p4dval_t, 1) << 7) /* AP[2] */
+#define P4D_TABLE_AF (_AT(p4dval_t, 1) << 10) /* Ignored if no FEAT_HAFT */
#define P4D_TABLE_PXN (_AT(p4dval_t, 1) << 59)
#define P4D_TABLE_UXN (_AT(p4dval_t, 1) << 60)
@@ -121,6 +123,7 @@
#define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0)
#define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0)
#define PUD_SECT_RDONLY (_AT(pudval_t, 1) << 7) /* AP[2] */
+#define PUD_TABLE_AF (_AT(pudval_t, 1) << 10) /* Ignored if no FEAT_HAFT */
#define PUD_TABLE_PXN (_AT(pudval_t, 1) << 59)
#define PUD_TABLE_UXN (_AT(pudval_t, 1) << 60)
@@ -131,6 +134,7 @@
#define PMD_TYPE_TABLE (_AT(pmdval_t, 3) << 0)
#define PMD_TYPE_SECT (_AT(pmdval_t, 1) << 0)
#define PMD_TABLE_BIT (_AT(pmdval_t, 1) << 1)
+#define PMD_TABLE_AF (_AT(pmdval_t, 1) << 10) /* Ignored if no FEAT_HAFT */
/*
* Section
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2a11d0c10760..9f9cf13bbd95 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -35,7 +35,6 @@
#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
#define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
-#define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF)
#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF)
@@ -68,8 +67,12 @@
#include <asm/cpufeature.h>
#include <asm/pgtable-types.h>
+#include <asm/rsi.h>
extern bool arm64_use_ng_mappings;
+extern unsigned long prot_ns_shared;
+
+#define PROT_NS_SHARED (is_realm_world() ? prot_ns_shared : 0)
#define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0)
#define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0)
@@ -144,15 +147,23 @@ static inline bool __pure lpa2_is_enabled(void)
/* 6: PTE_PXN | PTE_WRITE */
/* 7: PAGE_SHARED_EXEC PTE_PXN | PTE_WRITE | PTE_USER */
/* 8: PAGE_KERNEL_ROX PTE_UXN */
-/* 9: PTE_UXN | PTE_USER */
+/* 9: PAGE_GCS_RO PTE_UXN | PTE_USER */
/* a: PAGE_KERNEL_EXEC PTE_UXN | PTE_WRITE */
-/* b: PTE_UXN | PTE_WRITE | PTE_USER */
+/* b: PAGE_GCS PTE_UXN | PTE_WRITE | PTE_USER */
/* c: PAGE_KERNEL_RO PTE_UXN | PTE_PXN */
/* d: PAGE_READONLY PTE_UXN | PTE_PXN | PTE_USER */
/* e: PAGE_KERNEL PTE_UXN | PTE_PXN | PTE_WRITE */
/* f: PAGE_SHARED PTE_UXN | PTE_PXN | PTE_WRITE | PTE_USER */
+#define _PAGE_GCS (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER)
+#define _PAGE_GCS_RO (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER)
+
+#define PAGE_GCS __pgprot(_PAGE_GCS)
+#define PAGE_GCS_RO __pgprot(_PAGE_GCS_RO)
+
#define PIE_E0 ( \
+ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_GCS) | \
+ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_R) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX_O) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX_O) | \
@@ -160,6 +171,8 @@ static inline bool __pure lpa2_is_enabled(void)
PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW_O))
#define PIE_E1 ( \
+ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS), PIE_NONE_O) | \
+ PIRx_ELx_PERM(pte_pi_index(_PAGE_GCS_RO), PIE_NONE_O) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R) | \
PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RW) | \
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c329ea061dc9..6986345b537a 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -265,8 +265,7 @@ static inline pte_t pte_mkspecial(pte_t pte)
static inline pte_t pte_mkcont(pte_t pte)
{
- pte = set_pte_bit(pte, __pgprot(PTE_CONT));
- return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE));
+ return set_pte_bit(pte, __pgprot(PTE_CONT));
}
static inline pte_t pte_mknoncont(pte_t pte)
@@ -338,7 +337,7 @@ static inline pte_t __ptep_get(pte_t *ptep)
}
extern void __sync_icache_dcache(pte_t pteval);
-bool pgattr_change_is_safe(u64 old, u64 new);
+bool pgattr_change_is_safe(pteval_t old, pteval_t new);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
@@ -439,11 +438,6 @@ static inline void __set_ptes(struct mm_struct *mm,
}
/*
- * Huge pte definitions.
- */
-#define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT))
-
-/*
* Hugetlb definitions.
*/
#define HUGE_MAX_HSTATE 4
@@ -684,6 +678,11 @@ static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
#define pgprot_nx(prot) \
__pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN)
+#define pgprot_decrypted(prot) \
+ __pgprot_modify(prot, PROT_NS_SHARED, PROT_NS_SHARED)
+#define pgprot_encrypted(prot) \
+ __pgprot_modify(prot, PROT_NS_SHARED, 0)
+
/*
* Mark the prot value as uncacheable and unbufferable.
*/
@@ -927,6 +926,9 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d)
static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr)
{
+ /* Ensure that 'p4dp' indexes a page table according to 'addr' */
+ VM_BUG_ON(((addr >> P4D_SHIFT) ^ ((u64)p4dp >> 3)) % PTRS_PER_P4D);
+
return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr);
}
@@ -1051,6 +1053,9 @@ static inline phys_addr_t pgd_page_paddr(pgd_t pgd)
static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr)
{
+ /* Ensure that 'pgdp' indexes a page table according to 'addr' */
+ VM_BUG_ON(((addr >> PGDIR_SHIFT) ^ ((u64)pgdp >> 3)) % PTRS_PER_PGD);
+
return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr);
}
@@ -1259,15 +1264,17 @@ static inline int __ptep_clear_flush_young(struct vm_area_struct *vma,
return young;
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address,
pmd_t *pmdp)
{
+ /* Operation applies to PMD table entry only if FEAT_HAFT is enabled */
+ VM_WARN_ON(pmd_table(READ_ONCE(*pmdp)) && !system_supports_haft());
return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp);
}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
@@ -1502,6 +1509,10 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
*/
#define arch_has_hw_pte_young cpu_has_hw_af
+#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
+#define arch_has_hw_nonleaf_pmd_young system_supports_haft
+#endif
+
/*
* Experimentally, it's cheap to set the access flag in hardware and we
* benefit from prefaulting mappings as 'old' to start with.
diff --git a/arch/arm64/include/asm/probes.h b/arch/arm64/include/asm/probes.h
index 006946745352..d49368886309 100644
--- a/arch/arm64/include/asm/probes.h
+++ b/arch/arm64/include/asm/probes.h
@@ -9,21 +9,18 @@
#include <asm/insn.h>
-typedef u32 probe_opcode_t;
typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
-/* architecture specific copy of original instruction */
struct arch_probe_insn {
- probe_opcode_t *insn;
- pstate_check_t *pstate_cc;
probes_handler_t *handler;
- /* restore address after step xol */
- unsigned long restore;
};
#ifdef CONFIG_KPROBES
-typedef u32 kprobe_opcode_t;
+typedef __le32 kprobe_opcode_t;
struct arch_specific_insn {
struct arch_probe_insn api;
+ kprobe_opcode_t *xol_insn;
+ /* restore address after step xol */
+ unsigned long xol_restore;
};
#endif
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 1438424f0064..1bf1a3b16e88 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -185,6 +185,13 @@ struct thread_struct {
u64 svcr;
u64 tpidr2_el0;
u64 por_el0;
+#ifdef CONFIG_ARM64_GCS
+ unsigned int gcs_el0_mode;
+ unsigned int gcs_el0_locked;
+ u64 gcspr_el0;
+ u64 gcs_base;
+ u64 gcs_size;
+#endif
};
static inline unsigned int thread_get_vl(struct thread_struct *thread,
@@ -285,22 +292,44 @@ void tls_preserve_current_state(void);
.fpsimd_cpu = NR_CPUS, \
}
-static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
+static inline void start_thread_common(struct pt_regs *regs, unsigned long pc,
+ unsigned long pstate)
{
- s32 previous_syscall = regs->syscallno;
- memset(regs, 0, sizeof(*regs));
- regs->syscallno = previous_syscall;
- regs->pc = pc;
+ /*
+ * Ensure all GPRs are zeroed, and initialize PC + PSTATE.
+ * The SP (or compat SP) will be initialized later.
+ */
+ regs->user_regs = (struct user_pt_regs) {
+ .pc = pc,
+ .pstate = pstate,
+ };
+ /*
+ * To allow the syscalls:sys_exit_execve tracepoint we need to preserve
+ * syscallno, but do not need orig_x0 or the original GPRs.
+ */
+ regs->orig_x0 = 0;
+
+ /*
+ * An exec from a kernel thread won't have an existing PMR value.
+ */
if (system_uses_irq_prio_masking())
- regs->pmr_save = GIC_PRIO_IRQON;
+ regs->pmr = GIC_PRIO_IRQON;
+
+ /*
+ * The pt_regs::stackframe field must remain valid throughout this
+ * function as a stacktrace can be taken at any time. Any user or
+ * kernel task should have a valid final frame.
+ */
+ WARN_ON_ONCE(regs->stackframe.record.fp != 0);
+ WARN_ON_ONCE(regs->stackframe.record.lr != 0);
+ WARN_ON_ONCE(regs->stackframe.type != FRAME_META_TYPE_FINAL);
}
static inline void start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
- start_thread_common(regs, pc);
- regs->pstate = PSR_MODE_EL0t;
+ start_thread_common(regs, pc, PSR_MODE_EL0t);
spectre_v4_enable_task_mitigation(current);
regs->sp = sp;
}
@@ -309,15 +338,13 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc,
static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
unsigned long sp)
{
- start_thread_common(regs, pc);
- regs->pstate = PSR_AA32_MODE_USR;
+ unsigned long pstate = PSR_AA32_MODE_USR;
if (pc & 1)
- regs->pstate |= PSR_AA32_T_BIT;
-
-#ifdef __AARCH64EB__
- regs->pstate |= PSR_AA32_E_BIT;
-#endif
+ pstate |= PSR_AA32_T_BIT;
+ if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
+ pstate |= PSR_AA32_E_BIT;
+ start_thread_common(regs, pc, pstate);
spectre_v4_enable_task_mitigation(current);
regs->compat_sp = sp;
}
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 0abe975d68a8..47ff8654c5ec 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -98,6 +98,8 @@
#include <linux/bug.h>
#include <linux/types.h>
+#include <asm/stacktrace/frame.h>
+
/* sizeof(struct user) for AArch32 */
#define COMPAT_USER_SZ 296
@@ -149,8 +151,7 @@ static inline unsigned long pstate_to_compat_psr(const unsigned long pstate)
/*
* This struct defines the way the registers are stored on the stack during an
- * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for
- * stack alignment). struct user_pt_regs must form a prefix of struct pt_regs.
+ * exception. struct user_pt_regs must form a prefix of struct pt_regs.
*/
struct pt_regs {
union {
@@ -163,23 +164,20 @@ struct pt_regs {
};
};
u64 orig_x0;
-#ifdef __AARCH64EB__
- u32 unused2;
- s32 syscallno;
-#else
s32 syscallno;
- u32 unused2;
-#endif
+ u32 pmr;
+
u64 sdei_ttbr1;
- /* Only valid when ARM64_HAS_GIC_PRIO_MASKING is enabled. */
- u64 pmr_save;
- u64 stackframe[2];
+ struct frame_record_meta stackframe;
/* Only valid for some EL1 exceptions. */
u64 lockdep_hardirqs;
u64 exit_rcu;
};
+/* For correct stack alignment, pt_regs has to be a multiple of 16 bytes. */
+static_assert(IS_ALIGNED(sizeof(struct pt_regs), 16));
+
static inline bool in_syscall(struct pt_regs const *regs)
{
return regs->syscallno != NO_SYSCALL;
@@ -213,7 +211,7 @@ static inline void forget_syscall(struct pt_regs *regs)
#define irqs_priority_unmasked(regs) \
(system_uses_irq_prio_masking() ? \
- (regs)->pmr_save == GIC_PRIO_IRQON : \
+ (regs)->pmr == GIC_PRIO_IRQON : \
true)
#define interrupts_enabled(regs) \
diff --git a/arch/arm64/include/asm/rsi.h b/arch/arm64/include/asm/rsi.h
new file mode 100644
index 000000000000..188cbb9b23f5
--- /dev/null
+++ b/arch/arm64/include/asm/rsi.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2024 ARM Ltd.
+ */
+
+#ifndef __ASM_RSI_H_
+#define __ASM_RSI_H_
+
+#include <linux/errno.h>
+#include <linux/jump_label.h>
+#include <asm/rsi_cmds.h>
+
+DECLARE_STATIC_KEY_FALSE(rsi_present);
+
+void __init arm64_rsi_init(void);
+
+bool __arm64_is_protected_mmio(phys_addr_t base, size_t size);
+
+static inline bool is_realm_world(void)
+{
+ return static_branch_unlikely(&rsi_present);
+}
+
+static inline int rsi_set_memory_range(phys_addr_t start, phys_addr_t end,
+ enum ripas state, unsigned long flags)
+{
+ unsigned long ret;
+ phys_addr_t top;
+
+ while (start != end) {
+ ret = rsi_set_addr_range_state(start, end, state, flags, &top);
+ if (ret || top < start || top > end)
+ return -EINVAL;
+ start = top;
+ }
+
+ return 0;
+}
+
+/*
+ * Convert the specified range to RAM. Do not use this if you rely on the
+ * contents of a page that may already be in RAM state.
+ */
+static inline int rsi_set_memory_range_protected(phys_addr_t start,
+ phys_addr_t end)
+{
+ return rsi_set_memory_range(start, end, RSI_RIPAS_RAM,
+ RSI_CHANGE_DESTROYED);
+}
+
+/*
+ * Convert the specified range to RAM. Do not convert any pages that may have
+ * been DESTROYED, without our permission.
+ */
+static inline int rsi_set_memory_range_protected_safe(phys_addr_t start,
+ phys_addr_t end)
+{
+ return rsi_set_memory_range(start, end, RSI_RIPAS_RAM,
+ RSI_NO_CHANGE_DESTROYED);
+}
+
+static inline int rsi_set_memory_range_shared(phys_addr_t start,
+ phys_addr_t end)
+{
+ return rsi_set_memory_range(start, end, RSI_RIPAS_EMPTY,
+ RSI_CHANGE_DESTROYED);
+}
+#endif /* __ASM_RSI_H_ */
diff --git a/arch/arm64/include/asm/rsi_cmds.h b/arch/arm64/include/asm/rsi_cmds.h
new file mode 100644
index 000000000000..e6a211001bd3
--- /dev/null
+++ b/arch/arm64/include/asm/rsi_cmds.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+
+#ifndef __ASM_RSI_CMDS_H
+#define __ASM_RSI_CMDS_H
+
+#include <linux/arm-smccc.h>
+
+#include <asm/rsi_smc.h>
+
+#define RSI_GRANULE_SHIFT 12
+#define RSI_GRANULE_SIZE (_AC(1, UL) << RSI_GRANULE_SHIFT)
+
+enum ripas {
+ RSI_RIPAS_EMPTY = 0,
+ RSI_RIPAS_RAM = 1,
+ RSI_RIPAS_DESTROYED = 2,
+ RSI_RIPAS_DEV = 3,
+};
+
+static inline unsigned long rsi_request_version(unsigned long req,
+ unsigned long *out_lower,
+ unsigned long *out_higher)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_smc(SMC_RSI_ABI_VERSION, req, 0, 0, 0, 0, 0, 0, &res);
+
+ if (out_lower)
+ *out_lower = res.a1;
+ if (out_higher)
+ *out_higher = res.a2;
+
+ return res.a0;
+}
+
+static inline unsigned long rsi_get_realm_config(struct realm_config *cfg)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_smc(SMC_RSI_REALM_CONFIG, virt_to_phys(cfg),
+ 0, 0, 0, 0, 0, 0, &res);
+ return res.a0;
+}
+
+static inline unsigned long rsi_ipa_state_get(phys_addr_t start,
+ phys_addr_t end,
+ enum ripas *state,
+ phys_addr_t *top)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_smc(SMC_RSI_IPA_STATE_GET,
+ start, end, 0, 0, 0, 0, 0,
+ &res);
+
+ if (res.a0 == RSI_SUCCESS) {
+ if (top)
+ *top = res.a1;
+ if (state)
+ *state = res.a2;
+ }
+
+ return res.a0;
+}
+
+static inline long rsi_set_addr_range_state(phys_addr_t start,
+ phys_addr_t end,
+ enum ripas state,
+ unsigned long flags,
+ phys_addr_t *top)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_smc(SMC_RSI_IPA_STATE_SET, start, end, state,
+ flags, 0, 0, 0, &res);
+
+ if (top)
+ *top = res.a1;
+
+ if (res.a2 != RSI_ACCEPT)
+ return -EPERM;
+
+ return res.a0;
+}
+
+/**
+ * rsi_attestation_token_init - Initialise the operation to retrieve an
+ * attestation token.
+ *
+ * @challenge: The challenge data to be used in the attestation token
+ * generation.
+ * @size: Size of the challenge data in bytes.
+ *
+ * Initialises the attestation token generation and returns an upper bound
+ * on the attestation token size that can be used to allocate an adequate
+ * buffer. The caller is expected to subsequently call
+ * rsi_attestation_token_continue() to retrieve the attestation token data on
+ * the same CPU.
+ *
+ * Returns:
+ * On success, returns the upper limit of the attestation report size.
+ * Otherwise, -EINVAL
+ */
+static inline long
+rsi_attestation_token_init(const u8 *challenge, unsigned long size)
+{
+ struct arm_smccc_1_2_regs regs = { 0 };
+
+ /* The challenge must be at least 32bytes and at most 64bytes */
+ if (!challenge || size < 32 || size > 64)
+ return -EINVAL;
+
+ regs.a0 = SMC_RSI_ATTESTATION_TOKEN_INIT;
+ memcpy(&regs.a1, challenge, size);
+ arm_smccc_1_2_smc(&regs, &regs);
+
+ if (regs.a0 == RSI_SUCCESS)
+ return regs.a1;
+
+ return -EINVAL;
+}
+
+/**
+ * rsi_attestation_token_continue - Continue the operation to retrieve an
+ * attestation token.
+ *
+ * @granule: {I}PA of the Granule to which the token will be written.
+ * @offset: Offset within Granule to start of buffer in bytes.
+ * @size: The size of the buffer.
+ * @len: The number of bytes written to the buffer.
+ *
+ * Retrieves up to a RSI_GRANULE_SIZE worth of token data per call. The caller
+ * is expected to call rsi_attestation_token_init() before calling this
+ * function to retrieve the attestation token.
+ *
+ * Return:
+ * * %RSI_SUCCESS - Attestation token retrieved successfully.
+ * * %RSI_INCOMPLETE - Token generation is not complete.
+ * * %RSI_ERROR_INPUT - A parameter was not valid.
+ * * %RSI_ERROR_STATE - Attestation not in progress.
+ */
+static inline unsigned long rsi_attestation_token_continue(phys_addr_t granule,
+ unsigned long offset,
+ unsigned long size,
+ unsigned long *len)
+{
+ struct arm_smccc_res res;
+
+ arm_smccc_1_1_invoke(SMC_RSI_ATTESTATION_TOKEN_CONTINUE,
+ granule, offset, size, 0, &res);
+
+ if (len)
+ *len = res.a1;
+ return res.a0;
+}
+
+#endif /* __ASM_RSI_CMDS_H */
diff --git a/arch/arm64/include/asm/rsi_smc.h b/arch/arm64/include/asm/rsi_smc.h
new file mode 100644
index 000000000000..6cb070eca9e9
--- /dev/null
+++ b/arch/arm64/include/asm/rsi_smc.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+
+#ifndef __ASM_RSI_SMC_H_
+#define __ASM_RSI_SMC_H_
+
+#include <linux/arm-smccc.h>
+
+/*
+ * This file describes the Realm Services Interface (RSI) Application Binary
+ * Interface (ABI) for SMC calls made from within the Realm to the RMM and
+ * serviced by the RMM.
+ */
+
+/*
+ * The major version number of the RSI implementation. This is increased when
+ * the binary format or semantics of the SMC calls change.
+ */
+#define RSI_ABI_VERSION_MAJOR UL(1)
+
+/*
+ * The minor version number of the RSI implementation. This is increased when
+ * a bug is fixed, or a feature is added without breaking binary compatibility.
+ */
+#define RSI_ABI_VERSION_MINOR UL(0)
+
+#define RSI_ABI_VERSION ((RSI_ABI_VERSION_MAJOR << 16) | \
+ RSI_ABI_VERSION_MINOR)
+
+#define RSI_ABI_VERSION_GET_MAJOR(_version) ((_version) >> 16)
+#define RSI_ABI_VERSION_GET_MINOR(_version) ((_version) & 0xFFFF)
+
+#define RSI_SUCCESS UL(0)
+#define RSI_ERROR_INPUT UL(1)
+#define RSI_ERROR_STATE UL(2)
+#define RSI_INCOMPLETE UL(3)
+#define RSI_ERROR_UNKNOWN UL(4)
+
+#define SMC_RSI_FID(n) ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_64, \
+ ARM_SMCCC_OWNER_STANDARD, \
+ n)
+
+/*
+ * Returns RSI version.
+ *
+ * arg1 == Requested interface revision
+ * ret0 == Status / error
+ * ret1 == Lower implemented interface revision
+ * ret2 == Higher implemented interface revision
+ */
+#define SMC_RSI_ABI_VERSION SMC_RSI_FID(0x190)
+
+/*
+ * Read feature register.
+ *
+ * arg1 == Feature register index
+ * ret0 == Status / error
+ * ret1 == Feature register value
+ */
+#define SMC_RSI_FEATURES SMC_RSI_FID(0x191)
+
+/*
+ * Read measurement for the current Realm.
+ *
+ * arg1 == Index, which measurements slot to read
+ * ret0 == Status / error
+ * ret1 == Measurement value, bytes: 0 - 7
+ * ret2 == Measurement value, bytes: 8 - 15
+ * ret3 == Measurement value, bytes: 16 - 23
+ * ret4 == Measurement value, bytes: 24 - 31
+ * ret5 == Measurement value, bytes: 32 - 39
+ * ret6 == Measurement value, bytes: 40 - 47
+ * ret7 == Measurement value, bytes: 48 - 55
+ * ret8 == Measurement value, bytes: 56 - 63
+ */
+#define SMC_RSI_MEASUREMENT_READ SMC_RSI_FID(0x192)
+
+/*
+ * Extend Realm Extensible Measurement (REM) value.
+ *
+ * arg1 == Index, which measurements slot to extend
+ * arg2 == Size of realm measurement in bytes, max 64 bytes
+ * arg3 == Measurement value, bytes: 0 - 7
+ * arg4 == Measurement value, bytes: 8 - 15
+ * arg5 == Measurement value, bytes: 16 - 23
+ * arg6 == Measurement value, bytes: 24 - 31
+ * arg7 == Measurement value, bytes: 32 - 39
+ * arg8 == Measurement value, bytes: 40 - 47
+ * arg9 == Measurement value, bytes: 48 - 55
+ * arg10 == Measurement value, bytes: 56 - 63
+ * ret0 == Status / error
+ */
+#define SMC_RSI_MEASUREMENT_EXTEND SMC_RSI_FID(0x193)
+
+/*
+ * Initialize the operation to retrieve an attestation token.
+ *
+ * arg1 == Challenge value, bytes: 0 - 7
+ * arg2 == Challenge value, bytes: 8 - 15
+ * arg3 == Challenge value, bytes: 16 - 23
+ * arg4 == Challenge value, bytes: 24 - 31
+ * arg5 == Challenge value, bytes: 32 - 39
+ * arg6 == Challenge value, bytes: 40 - 47
+ * arg7 == Challenge value, bytes: 48 - 55
+ * arg8 == Challenge value, bytes: 56 - 63
+ * ret0 == Status / error
+ * ret1 == Upper bound of token size in bytes
+ */
+#define SMC_RSI_ATTESTATION_TOKEN_INIT SMC_RSI_FID(0x194)
+
+/*
+ * Continue the operation to retrieve an attestation token.
+ *
+ * arg1 == The IPA of token buffer
+ * arg2 == Offset within the granule of the token buffer
+ * arg3 == Size of the granule buffer
+ * ret0 == Status / error
+ * ret1 == Length of token bytes copied to the granule buffer
+ */
+#define SMC_RSI_ATTESTATION_TOKEN_CONTINUE SMC_RSI_FID(0x195)
+
+#ifndef __ASSEMBLY__
+
+struct realm_config {
+ union {
+ struct {
+ unsigned long ipa_bits; /* Width of IPA in bits */
+ unsigned long hash_algo; /* Hash algorithm */
+ };
+ u8 pad[0x200];
+ };
+ union {
+ u8 rpv[64]; /* Realm Personalization Value */
+ u8 pad2[0xe00];
+ };
+ /*
+ * The RMM requires the configuration structure to be aligned to a 4k
+ * boundary, ensure this happens by aligning this structure.
+ */
+} __aligned(0x1000);
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * Read configuration for the current Realm.
+ *
+ * arg1 == struct realm_config addr
+ * ret0 == Status / error
+ */
+#define SMC_RSI_REALM_CONFIG SMC_RSI_FID(0x196)
+
+/*
+ * Request RIPAS of a target IPA range to be changed to a specified value.
+ *
+ * arg1 == Base IPA address of target region
+ * arg2 == Top of the region
+ * arg3 == RIPAS value
+ * arg4 == flags
+ * ret0 == Status / error
+ * ret1 == Top of modified IPA range
+ * ret2 == Whether the Host accepted or rejected the request
+ */
+#define SMC_RSI_IPA_STATE_SET SMC_RSI_FID(0x197)
+
+#define RSI_NO_CHANGE_DESTROYED UL(0)
+#define RSI_CHANGE_DESTROYED UL(1)
+
+#define RSI_ACCEPT UL(0)
+#define RSI_REJECT UL(1)
+
+/*
+ * Get RIPAS of a target IPA range.
+ *
+ * arg1 == Base IPA of target region
+ * arg2 == End of target IPA region
+ * ret0 == Status / error
+ * ret1 == Top of IPA region which has the reported RIPAS value
+ * ret2 == RIPAS value
+ */
+#define SMC_RSI_IPA_STATE_GET SMC_RSI_FID(0x198)
+
+/*
+ * Make a Host call.
+ *
+ * arg1 == IPA of host call structure
+ * ret0 == Status / error
+ */
+#define SMC_RSI_HOST_CALL SMC_RSI_FID(0x199)
+
+#endif /* __ASM_RSI_SMC_H_ */
diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h
index 2e010ea76be2..a76f9b387a26 100644
--- a/arch/arm64/include/asm/scs.h
+++ b/arch/arm64/include/asm/scs.h
@@ -46,8 +46,14 @@ static inline void dynamic_scs_init(void)
static inline void dynamic_scs_init(void) {}
#endif
+enum {
+ EDYNSCS_INVALID_CIE_HEADER = 1,
+ EDYNSCS_INVALID_CIE_SDATA_SIZE = 2,
+ EDYNSCS_INVALID_FDE_AUGM_DATA_SIZE = 3,
+ EDYNSCS_INVALID_CFA_OPCODE = 4,
+};
+
int __pi_scs_patch(const u8 eh_frame[], int size);
-asmlinkage void __pi_scs_patch_vmlinux(void);
#endif /* __ASSEMBLY __ */
diff --git a/arch/arm64/include/asm/set_memory.h b/arch/arm64/include/asm/set_memory.h
index 917761feeffd..37774c793006 100644
--- a/arch/arm64/include/asm/set_memory.h
+++ b/arch/arm64/include/asm/set_memory.h
@@ -15,4 +15,7 @@ int set_direct_map_invalid_noflush(struct page *page);
int set_direct_map_default_noflush(struct page *page);
bool kernel_page_present(struct page *page);
+int set_memory_encrypted(unsigned long addr, int numpages);
+int set_memory_decrypted(unsigned long addr, int numpages);
+
#endif /* _ASM_ARM64_SET_MEMORY_H */
diff --git a/arch/arm64/include/asm/stacktrace/common.h b/arch/arm64/include/asm/stacktrace/common.h
index f63dc654e545..821a8fdd31af 100644
--- a/arch/arm64/include/asm/stacktrace/common.h
+++ b/arch/arm64/include/asm/stacktrace/common.h
@@ -60,13 +60,27 @@ static inline void unwind_init_common(struct unwind_state *state)
state->stack = stackinfo_get_unknown();
}
-static struct stack_info *unwind_find_next_stack(const struct unwind_state *state,
- unsigned long sp,
- unsigned long size)
+/**
+ * unwind_find_stack() - Find the accessible stack which entirely contains an
+ * object.
+ *
+ * @state: the current unwind state.
+ * @sp: the base address of the object.
+ * @size: the size of the object.
+ *
+ * Return: a pointer to the relevant stack_info if found; NULL otherwise.
+ */
+static struct stack_info *unwind_find_stack(struct unwind_state *state,
+ unsigned long sp,
+ unsigned long size)
{
- for (int i = 0; i < state->nr_stacks; i++) {
- struct stack_info *info = &state->stacks[i];
+ struct stack_info *info = &state->stack;
+ if (stackinfo_on_stack(info, sp, size))
+ return info;
+
+ for (int i = 0; i < state->nr_stacks; i++) {
+ info = &state->stacks[i];
if (stackinfo_on_stack(info, sp, size))
return info;
}
@@ -75,36 +89,31 @@ static struct stack_info *unwind_find_next_stack(const struct unwind_state *stat
}
/**
- * unwind_consume_stack() - Check if an object is on an accessible stack,
- * updating stack boundaries so that future unwind steps cannot consume this
- * object again.
+ * unwind_consume_stack() - Update stack boundaries so that future unwind steps
+ * cannot consume this object again.
*
* @state: the current unwind state.
+ * @info: the stack_info of the stack containing the object.
* @sp: the base address of the object.
* @size: the size of the object.
*
* Return: 0 upon success, an error code otherwise.
*/
-static inline int unwind_consume_stack(struct unwind_state *state,
- unsigned long sp,
- unsigned long size)
+static inline void unwind_consume_stack(struct unwind_state *state,
+ struct stack_info *info,
+ unsigned long sp,
+ unsigned long size)
{
- struct stack_info *next;
-
- if (stackinfo_on_stack(&state->stack, sp, size))
- goto found;
-
- next = unwind_find_next_stack(state, sp, size);
- if (!next)
- return -EINVAL;
+ struct stack_info tmp;
/*
* Stack transitions are strictly one-way, and once we've
* transitioned from one stack to another, it's never valid to
* unwind back to the old stack.
*
- * Remove the current stack from the list of stacks so that it cannot
- * be found on a subsequent transition.
+ * Destroy the old stack info so that it cannot be found upon a
+ * subsequent transition. If the stack has not changed, we'll
+ * immediately restore the current stack info.
*
* Note that stacks can nest in several valid orders, e.g.
*
@@ -115,16 +124,15 @@ static inline int unwind_consume_stack(struct unwind_state *state,
* ... so we do not check the specific order of stack
* transitions.
*/
- state->stack = *next;
- *next = stackinfo_get_unknown();
+ tmp = *info;
+ *info = stackinfo_get_unknown();
+ state->stack = tmp;
-found:
/*
* Future unwind steps can only consume stack above this frame record.
* Update the current stack to start immediately above it.
*/
state->stack.low = sp + size;
- return 0;
}
/**
@@ -137,21 +145,25 @@ found:
static inline int
unwind_next_frame_record(struct unwind_state *state)
{
+ struct stack_info *info;
+ struct frame_record *record;
unsigned long fp = state->fp;
- int err;
if (fp & 0x7)
return -EINVAL;
- err = unwind_consume_stack(state, fp, 16);
- if (err)
- return err;
+ info = unwind_find_stack(state, fp, sizeof(*record));
+ if (!info)
+ return -EINVAL;
+
+ unwind_consume_stack(state, info, fp, sizeof(*record));
/*
* Record this frame record's values.
*/
- state->fp = READ_ONCE(*(unsigned long *)(fp));
- state->pc = READ_ONCE(*(unsigned long *)(fp + 8));
+ record = (struct frame_record *)fp;
+ state->fp = READ_ONCE(record->fp);
+ state->pc = READ_ONCE(record->lr);
return 0;
}
diff --git a/arch/arm64/include/asm/stacktrace/frame.h b/arch/arm64/include/asm/stacktrace/frame.h
new file mode 100644
index 000000000000..0ee0f6ba0fd8
--- /dev/null
+++ b/arch/arm64/include/asm/stacktrace/frame.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_STACKTRACE_FRAME_H
+#define __ASM_STACKTRACE_FRAME_H
+
+/*
+ * - FRAME_META_TYPE_NONE
+ *
+ * This value is reserved.
+ *
+ * - FRAME_META_TYPE_FINAL
+ *
+ * The record is the last entry on the stack.
+ * Unwinding should terminate successfully.
+ *
+ * - FRAME_META_TYPE_PT_REGS
+ *
+ * The record is embedded within a struct pt_regs, recording the registers at
+ * an arbitrary point in time.
+ * Unwinding should consume pt_regs::pc, followed by pt_regs::lr.
+ *
+ * Note: all other values are reserved and should result in unwinding
+ * terminating with an error.
+ */
+#define FRAME_META_TYPE_NONE 0
+#define FRAME_META_TYPE_FINAL 1
+#define FRAME_META_TYPE_PT_REGS 2
+
+#ifndef __ASSEMBLY__
+/*
+ * A standard AAPCS64 frame record.
+ */
+struct frame_record {
+ u64 fp;
+ u64 lr;
+};
+
+/*
+ * A metadata frame record indicating a special unwind.
+ * The record::{fp,lr} fields must be zero to indicate the presence of
+ * metadata.
+ */
+struct frame_record_meta {
+ struct frame_record record;
+ u64 type;
+};
+#endif /* __ASSEMBLY */
+
+#endif /* __ASM_STACKTRACE_FRAME_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 9ea97dddefc4..9c98ff448bd9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1101,6 +1101,26 @@
/* Initial value for Permission Overlay Extension for EL0 */
#define POR_EL0_INIT POE_RXW
+/*
+ * Definitions for Guarded Control Stack
+ */
+
+#define GCS_CAP_ADDR_MASK GENMASK(63, 12)
+#define GCS_CAP_ADDR_SHIFT 12
+#define GCS_CAP_ADDR_WIDTH 52
+#define GCS_CAP_ADDR(x) FIELD_GET(GCS_CAP_ADDR_MASK, x)
+
+#define GCS_CAP_TOKEN_MASK GENMASK(11, 0)
+#define GCS_CAP_TOKEN_SHIFT 0
+#define GCS_CAP_TOKEN_WIDTH 12
+#define GCS_CAP_TOKEN(x) FIELD_GET(GCS_CAP_TOKEN_MASK, x)
+
+#define GCS_CAP_VALID_TOKEN 0x1
+#define GCS_CAP_IN_PROGRESS_TOKEN 0x5
+
+#define GCS_CAP(x) ((((unsigned long)x) & GCS_CAP_ADDR_MASK) | \
+ GCS_CAP_VALID_TOKEN)
+
#define ARM64_FEATURE_FIELD_BITS 4
/* Defined for compatibility only, do not add new users. */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 95fbc8c05607..bc94e036a26b 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -431,6 +431,23 @@ do { \
#define __flush_s2_tlb_range_op(op, start, pages, stride, tlb_level) \
__flush_tlb_range_op(op, start, pages, stride, 0, tlb_level, false, kvm_lpa2_is_enabled());
+static inline bool __flush_tlb_range_limit_excess(unsigned long start,
+ unsigned long end, unsigned long pages, unsigned long stride)
+{
+ /*
+ * When the system does not support TLB range based flush
+ * operation, (MAX_DVM_OPS - 1) pages can be handled. But
+ * with TLB range based operation, MAX_TLBI_RANGE_PAGES
+ * pages can be handled.
+ */
+ if ((!system_supports_tlb_range() &&
+ (end - start) >= (MAX_DVM_OPS * stride)) ||
+ pages > MAX_TLBI_RANGE_PAGES)
+ return true;
+
+ return false;
+}
+
static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
unsigned long stride, bool last_level,
@@ -442,15 +459,7 @@ static inline void __flush_tlb_range_nosync(struct vm_area_struct *vma,
end = round_up(end, stride);
pages = (end - start) >> PAGE_SHIFT;
- /*
- * When not uses TLB range ops, we can handle up to
- * (MAX_DVM_OPS - 1) pages;
- * When uses TLB range ops, we can handle up to
- * MAX_TLBI_RANGE_PAGES pages.
- */
- if ((!system_supports_tlb_range() &&
- (end - start) >= (MAX_DVM_OPS * stride)) ||
- pages > MAX_TLBI_RANGE_PAGES) {
+ if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
flush_tlb_mm(vma->vm_mm);
return;
}
@@ -492,19 +501,21 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- unsigned long addr;
+ const unsigned long stride = PAGE_SIZE;
+ unsigned long pages;
- if ((end - start) > (MAX_DVM_OPS * PAGE_SIZE)) {
+ start = round_down(start, stride);
+ end = round_up(end, stride);
+ pages = (end - start) >> PAGE_SHIFT;
+
+ if (__flush_tlb_range_limit_excess(start, end, pages, stride)) {
flush_tlb_all();
return;
}
- start = __TLBI_VADDR(start, 0);
- end = __TLBI_VADDR(end, 0);
-
dsb(ishst);
- for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
- __tlbi(vaale1is, addr);
+ __flush_tlb_range_op(vaale1is, start, pages, stride, 0,
+ TLBI_TTL_UNKNOWN, false, lpa2_is_enabled());
dsb(ish);
isb();
}
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 5fc3af9f8f29..341174bf9106 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -26,10 +26,6 @@ void update_freq_counters_refs(void);
#define arch_scale_freq_invariant topology_scale_freq_invariant
#define arch_scale_freq_ref topology_get_freq_ref
-#ifdef CONFIG_ACPI_CPPC_LIB
-#define arch_init_invariance_cppc topology_init_cpu_capacity_cppc
-#endif
-
/* Replace task scheduler's default cpu-invariant accounting */
#define arch_scale_cpu_capacity topology_get_cpu_scale
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 1aa4ecb73429..5b91803201ef 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -502,4 +502,44 @@ static inline size_t probe_subpage_writeable(const char __user *uaddr,
#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
+#ifdef CONFIG_ARM64_GCS
+
+static inline int gcssttr(unsigned long __user *addr, unsigned long val)
+{
+ register unsigned long __user *_addr __asm__ ("x0") = addr;
+ register unsigned long _val __asm__ ("x1") = val;
+ int err = 0;
+
+ /* GCSSTTR x1, x0 */
+ asm volatile(
+ "1: .inst 0xd91f1c01\n"
+ "2: \n"
+ _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %w0)
+ : "+r" (err)
+ : "rZ" (_val), "r" (_addr)
+ : "memory");
+
+ return err;
+}
+
+static inline void put_user_gcs(unsigned long val, unsigned long __user *addr,
+ int *err)
+{
+ int ret;
+
+ if (!access_ok((char __user *)addr, sizeof(u64))) {
+ *err = -EFAULT;
+ return;
+ }
+
+ uaccess_ttbr0_enable();
+ ret = gcssttr(addr, val);
+ if (ret != 0)
+ *err = ret;
+ uaccess_ttbr0_disable();
+}
+
+
+#endif /* CONFIG_ARM64_GCS */
+
#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h
index 2b09495499c6..014b02897f8e 100644
--- a/arch/arm64/include/asm/uprobes.h
+++ b/arch/arm64/include/asm/uprobes.h
@@ -10,11 +10,9 @@
#include <asm/insn.h>
#include <asm/probes.h>
-#define MAX_UINSN_BYTES AARCH64_INSN_SIZE
-
#define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES)
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
-#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
+#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE
typedef __le32 uprobe_opcode_t;
@@ -23,8 +21,8 @@ struct arch_uprobe_task {
struct arch_uprobe {
union {
- u8 insn[MAX_UINSN_BYTES];
- u8 ixol[MAX_UINSN_BYTES];
+ __le32 insn;
+ __le32 ixol;
};
struct arch_probe_insn api;
bool simulate;
diff --git a/arch/arm64/include/asm/vdso.h b/arch/arm64/include/asm/vdso.h
index 4305995c8f82..3e3c3fdb1842 100644
--- a/arch/arm64/include/asm/vdso.h
+++ b/arch/arm64/include/asm/vdso.h
@@ -5,13 +5,6 @@
#ifndef __ASM_VDSO_H
#define __ASM_VDSO_H
-/*
- * Default link address for the vDSO.
- * Since we randomise the VDSO mapping, there's little point in trying
- * to prelink this.
- */
-#define VDSO_LBASE 0x0
-
#define __VVAR_PAGES 2
#ifndef __ASSEMBLY__
@@ -20,7 +13,7 @@
#define VDSO_SYMBOL(base, name) \
({ \
- (void *)(vdso_offset_##name - VDSO_LBASE + (unsigned long)(base)); \
+ (void *)(vdso_offset_##name + (unsigned long)(base)); \
})
extern char vdso_start[], vdso_end[];
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index 5b6d0dd3cef5..eea51946d45a 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -6,7 +6,6 @@
#ifndef __ASSEMBLY__
-#include <linux/timekeeper_internal.h>
#include <vdso/datapage.h>
enum vvar_pages {
@@ -37,7 +36,7 @@ struct vdso_rng_data *__arm64_get_k_vdso_rnd_data(void)
#define __arch_get_k_vdso_rng_data __arm64_get_k_vdso_rnd_data
static __always_inline
-void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
+void __arm64_update_vsyscall(struct vdso_data *vdata)
{
vdata[CS_HRES_COARSE].mask = VDSO_PRECISION_MASK;
vdata[CS_RAW].mask = VDSO_PRECISION_MASK;
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 055381b2c615..48d46b768eae 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -21,7 +21,7 @@
* HWCAP flags - for AT_HWCAP
*
* Bits 62 and 63 are reserved for use by libc.
- * Bits 32-61 are unallocated for potential use by libc.
+ * Bits 33-61 are unallocated for potential use by libc.
*/
#define HWCAP_FP (1 << 0)
#define HWCAP_ASIMD (1 << 1)
@@ -55,6 +55,7 @@
#define HWCAP_SB (1 << 29)
#define HWCAP_PACA (1 << 30)
#define HWCAP_PACG (1UL << 31)
+#define HWCAP_GCS (1UL << 32)
/*
* HWCAP2 flags - for AT_HWCAP2
@@ -124,4 +125,8 @@
#define HWCAP2_SME_SF8DP2 (1UL << 62)
#define HWCAP2_POE (1UL << 63)
+/*
+ * HWCAP3 flags - for AT_HWCAP3
+ */
+
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 7fa2f7036aa7..0f39ba4f3efd 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -324,6 +324,14 @@ struct user_za_header {
#define ZA_PT_SIZE(vq) \
(ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq))
+/* GCS state (NT_ARM_GCS) */
+
+struct user_gcs {
+ __u64 features_enabled;
+ __u64 features_locked;
+ __u64 gcspr_el0;
+};
+
#endif /* __ASSEMBLY__ */
#endif /* _UAPI__ASM_PTRACE_H */
diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
index bb7af77a30a7..d42f7a92238b 100644
--- a/arch/arm64/include/uapi/asm/sigcontext.h
+++ b/arch/arm64/include/uapi/asm/sigcontext.h
@@ -183,6 +183,15 @@ struct zt_context {
__u16 __reserved[3];
};
+#define GCS_MAGIC 0x47435300
+
+struct gcs_context {
+ struct _aarch64_ctx head;
+ __u64 gcspr;
+ __u64 features_enabled;
+ __u64 reserved;
+};
+
#endif /* !__ASSEMBLY__ */
#include <asm/sve_context.h>
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2b112f3b7510..71c29a2a2f19 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -33,7 +33,8 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
return_address.o cpuinfo.o cpu_errata.o \
cpufeature.o alternative.o cacheinfo.o \
smp.o smp_spin_table.o topology.o smccc-call.o \
- syscall.o proton-pack.o idle.o patching.o pi/
+ syscall.o proton-pack.o idle.o patching.o pi/ \
+ rsi.o
obj-$(CONFIG_COMPAT) += sys32.o signal32.o \
sys_compat.o
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 27de1dddb0ab..29bf85dacffe 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -12,15 +12,12 @@
#include <linux/ftrace.h>
#include <linux/kexec.h>
#include <linux/mm.h>
-#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
-#include <linux/preempt.h>
#include <linux/suspend.h>
#include <asm/cpufeature.h>
#include <asm/fixmap.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
-#include <asm/signal32.h>
#include <asm/smp_plat.h>
#include <asm/suspend.h>
#include <linux/kbuild.h>
@@ -28,8 +25,6 @@
int main(void)
{
- DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm));
- BLANK();
DEFINE(TSK_TI_CPU, offsetof(struct task_struct, thread_info.cpu));
DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags));
DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count));
@@ -79,45 +74,27 @@ int main(void)
DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate));
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1));
- DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save));
+ DEFINE(S_PMR, offsetof(struct pt_regs, pmr));
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
+ DEFINE(S_STACKFRAME_TYPE, offsetof(struct pt_regs, stackframe.type));
DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
BLANK();
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
- DEFINE(FREGS_X0, offsetof(struct ftrace_regs, regs[0]));
- DEFINE(FREGS_X2, offsetof(struct ftrace_regs, regs[2]));
- DEFINE(FREGS_X4, offsetof(struct ftrace_regs, regs[4]));
- DEFINE(FREGS_X6, offsetof(struct ftrace_regs, regs[6]));
- DEFINE(FREGS_X8, offsetof(struct ftrace_regs, regs[8]));
- DEFINE(FREGS_FP, offsetof(struct ftrace_regs, fp));
- DEFINE(FREGS_LR, offsetof(struct ftrace_regs, lr));
- DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp));
- DEFINE(FREGS_PC, offsetof(struct ftrace_regs, pc));
+ DEFINE(FREGS_X0, offsetof(struct __arch_ftrace_regs, regs[0]));
+ DEFINE(FREGS_X2, offsetof(struct __arch_ftrace_regs, regs[2]));
+ DEFINE(FREGS_X4, offsetof(struct __arch_ftrace_regs, regs[4]));
+ DEFINE(FREGS_X6, offsetof(struct __arch_ftrace_regs, regs[6]));
+ DEFINE(FREGS_X8, offsetof(struct __arch_ftrace_regs, regs[8]));
+ DEFINE(FREGS_FP, offsetof(struct __arch_ftrace_regs, fp));
+ DEFINE(FREGS_LR, offsetof(struct __arch_ftrace_regs, lr));
+ DEFINE(FREGS_SP, offsetof(struct __arch_ftrace_regs, sp));
+ DEFINE(FREGS_PC, offsetof(struct __arch_ftrace_regs, pc));
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
- DEFINE(FREGS_DIRECT_TRAMP, offsetof(struct ftrace_regs, direct_tramp));
-#endif
- DEFINE(FREGS_SIZE, sizeof(struct ftrace_regs));
- BLANK();
+ DEFINE(FREGS_DIRECT_TRAMP, offsetof(struct __arch_ftrace_regs, direct_tramp));
#endif
-#ifdef CONFIG_COMPAT
- DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
- DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0));
+ DEFINE(FREGS_SIZE, sizeof(struct __arch_ftrace_regs));
BLANK();
#endif
- DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
- BLANK();
- DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm));
- DEFINE(VMA_VM_FLAGS, offsetof(struct vm_area_struct, vm_flags));
- BLANK();
- DEFINE(VM_EXEC, VM_EXEC);
- BLANK();
- DEFINE(PAGE_SZ, PAGE_SIZE);
- BLANK();
- DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE);
- DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE);
- BLANK();
- DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
- BLANK();
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
BLANK();
DEFINE(FTR_OVR_VAL_OFFSET, offsetof(struct arm64_ftr_override, val));
@@ -146,6 +123,7 @@ int main(void)
DEFINE(NVHE_INIT_HCR_EL2, offsetof(struct kvm_nvhe_init_params, hcr_el2));
DEFINE(NVHE_INIT_VTTBR, offsetof(struct kvm_nvhe_init_params, vttbr));
DEFINE(NVHE_INIT_VTCR, offsetof(struct kvm_nvhe_init_params, vtcr));
+ DEFINE(NVHE_INIT_TMP, offsetof(struct kvm_nvhe_init_params, tmp));
#endif
#ifdef CONFIG_CPU_PM
DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index dfefbdf4073a..a78f247029ae 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -439,6 +439,7 @@ static const struct midr_range erratum_spec_ssbs_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A715),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
MIDR_ALL_VERSIONS(MIDR_CORTEX_A725),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
@@ -447,8 +448,10 @@ static const struct midr_range erratum_spec_ssbs_list[] = {
MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X4),
MIDR_ALL_VERSIONS(MIDR_CORTEX_X925),
+ MIDR_ALL_VERSIONS(MIDR_MICROSOFT_AZURE_COBALT_100),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N3),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3),
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 718728a85430..351aa825ec40 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -103,6 +103,7 @@ static DECLARE_BITMAP(elf_hwcap, MAX_CPU_FEATURES) __read_mostly;
COMPAT_HWCAP_LPAE)
unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
unsigned int compat_elf_hwcap2 __read_mostly;
+unsigned int compat_elf_hwcap3 __read_mostly;
#endif
DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS);
@@ -228,6 +229,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_XS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_I8MM_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_DGH_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_EL1_BF16_SHIFT, 4, 0),
@@ -291,6 +293,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
};
static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_GCS),
+ FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_GCS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_SME_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MPAM_frac_SHIFT, 4, 0),
@@ -2358,6 +2362,14 @@ static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused)
}
#endif
+#ifdef CONFIG_ARM64_GCS
+static void cpu_enable_gcs(const struct arm64_cpu_capabilities *__unused)
+{
+ /* GCSPR_EL0 is always readable */
+ write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1);
+}
+#endif
+
/* Internal helper functions to match cpu capability type */
static bool
cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap)
@@ -2591,6 +2603,21 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, DBM)
},
#endif
+#ifdef CONFIG_ARM64_HAFT
+ {
+ .desc = "Hardware managed Access Flag for Table Descriptors",
+ /*
+ * Contrary to the page/block access flag, the table access flag
+ * cannot be emulated in software (no access fault will occur).
+ * Therefore this should be used only if it's supported system
+ * wide.
+ */
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_HAFT,
+ .matches = has_cpuid_feature,
+ ARM64_CPUID_FIELDS(ID_AA64MMFR1_EL1, HAFDBS, HAFT)
+ },
+#endif
{
.desc = "CRC32 instructions",
.capability = ARM64_HAS_CRC32,
@@ -2890,6 +2917,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
ARM64_CPUID_FIELDS(ID_AA64MMFR3_EL1, S1POE, IMP)
},
#endif
+#ifdef CONFIG_ARM64_GCS
+ {
+ .desc = "Guarded Control Stack (GCS)",
+ .capability = ARM64_HAS_GCS,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .cpu_enable = cpu_enable_gcs,
+ .matches = has_cpuid_feature,
+ ARM64_CPUID_FIELDS(ID_AA64PFR1_EL1, GCS, IMP)
+ },
+#endif
{},
};
@@ -3006,6 +3043,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
#endif
+#ifdef CONFIG_ARM64_GCS
+ HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS),
+#endif
HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
#ifdef CONFIG_ARM64_BTI
HWCAP_CAP(ID_AA64PFR1_EL1, BT, IMP, CAP_HWCAP, KERNEL_HWCAP_BTI),
@@ -3499,6 +3539,11 @@ unsigned long cpu_get_elf_hwcap2(void)
return elf_hwcap[1];
}
+unsigned long cpu_get_elf_hwcap3(void)
+{
+ return elf_hwcap[2];
+}
+
static void __init setup_boot_cpu_capabilities(void)
{
/*
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 44718d0482b3..f2f92c6b1c85 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -80,6 +80,7 @@ static const char *const hwcap_str[] = {
[KERNEL_HWCAP_SB] = "sb",
[KERNEL_HWCAP_PACA] = "paca",
[KERNEL_HWCAP_PACG] = "pacg",
+ [KERNEL_HWCAP_GCS] = "gcs",
[KERNEL_HWCAP_DCPODP] = "dcpodp",
[KERNEL_HWCAP_SVE2] = "sve2",
[KERNEL_HWCAP_SVEAES] = "sveaes",
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 024a7b245056..58f047de3e1c 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -303,7 +303,6 @@ static int call_break_hook(struct pt_regs *regs, unsigned long esr)
{
struct break_hook *hook;
struct list_head *list;
- int (*fn)(struct pt_regs *regs, unsigned long esr) = NULL;
list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
@@ -313,10 +312,10 @@ static int call_break_hook(struct pt_regs *regs, unsigned long esr)
*/
list_for_each_entry_rcu(hook, list, node) {
if ((esr_brk_comment(esr) & ~hook->mask) == hook->imm)
- fn = hook->fn;
+ return hook->fn(regs, esr);
}
- return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
+ return DBG_HOOK_ERROR;
}
NOKPROBE_SYMBOL(call_break_hook);
@@ -441,6 +440,11 @@ void kernel_rewind_single_step(struct pt_regs *regs)
set_regs_spsr_ss(regs);
}
+void kernel_fastforward_single_step(struct pt_regs *regs)
+{
+ clear_regs_spsr_ss(regs);
+}
+
/* ptrace API */
void user_enable_single_step(struct task_struct *task)
{
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 712718aed5dd..1d25d8899dbf 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -34,8 +34,16 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md)
u64 attr = md->attribute;
u32 type = md->type;
- if (type == EFI_MEMORY_MAPPED_IO)
- return PROT_DEVICE_nGnRE;
+ if (type == EFI_MEMORY_MAPPED_IO) {
+ pgprot_t prot = __pgprot(PROT_DEVICE_nGnRE);
+
+ if (arm64_is_protected_mmio(md->phys_addr,
+ md->num_pages << EFI_PAGE_SHIFT))
+ prot = pgprot_encrypted(prot);
+ else
+ prot = pgprot_decrypted(prot);
+ return pgprot_val(prot);
+ }
if (region_is_misaligned(md)) {
static bool __initdata code_is_misaligned;
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 3fcd9d080bf2..b260ddc4d3e9 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -463,6 +463,24 @@ static void noinstr el1_bti(struct pt_regs *regs, unsigned long esr)
exit_to_kernel_mode(regs);
}
+static void noinstr el1_gcs(struct pt_regs *regs, unsigned long esr)
+{
+ enter_from_kernel_mode(regs);
+ local_daif_inherit(regs);
+ do_el1_gcs(regs, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
+}
+
+static void noinstr el1_mops(struct pt_regs *regs, unsigned long esr)
+{
+ enter_from_kernel_mode(regs);
+ local_daif_inherit(regs);
+ do_el1_mops(regs, esr);
+ local_daif_mask();
+ exit_to_kernel_mode(regs);
+}
+
static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr)
{
unsigned long far = read_sysreg(far_el1);
@@ -505,6 +523,12 @@ asmlinkage void noinstr el1h_64_sync_handler(struct pt_regs *regs)
case ESR_ELx_EC_BTI:
el1_bti(regs, esr);
break;
+ case ESR_ELx_EC_GCS:
+ el1_gcs(regs, esr);
+ break;
+ case ESR_ELx_EC_MOPS:
+ el1_mops(regs, esr);
+ break;
case ESR_ELx_EC_BREAKPT_CUR:
case ESR_ELx_EC_SOFTSTP_CUR:
case ESR_ELx_EC_WATCHPT_CUR:
@@ -684,6 +708,14 @@ static void noinstr el0_mops(struct pt_regs *regs, unsigned long esr)
exit_to_user_mode(regs);
}
+static void noinstr el0_gcs(struct pt_regs *regs, unsigned long esr)
+{
+ enter_from_user_mode(regs);
+ local_daif_restore(DAIF_PROCCTX);
+ do_el0_gcs(regs, esr);
+ exit_to_user_mode(regs);
+}
+
static void noinstr el0_inv(struct pt_regs *regs, unsigned long esr)
{
enter_from_user_mode(regs);
@@ -766,6 +798,9 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
case ESR_ELx_EC_MOPS:
el0_mops(regs, esr);
break;
+ case ESR_ELx_EC_GCS:
+ el0_gcs(regs, esr);
+ break;
case ESR_ELx_EC_BREAKPT_LOW:
case ESR_ELx_EC_SOFTSTP_LOW:
case ESR_ELx_EC_WATCHPT_LOW:
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 7ef0e127b149..5ae2a34b50bd 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -25,6 +25,7 @@
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/scs.h>
+#include <asm/stacktrace/frame.h>
#include <asm/thread_info.h>
#include <asm/asm-uaccess.h>
#include <asm/unistd.h>
@@ -284,15 +285,16 @@ alternative_else_nop_endif
stp lr, x21, [sp, #S_LR]
/*
- * For exceptions from EL0, create a final frame record.
- * For exceptions from EL1, create a synthetic frame record so the
- * interrupted code shows up in the backtrace.
+ * Create a metadata frame record. The unwinder will use this to
+ * identify and unwind exception boundaries.
*/
- .if \el == 0
stp xzr, xzr, [sp, #S_STACKFRAME]
+ .if \el == 0
+ mov x0, #FRAME_META_TYPE_FINAL
.else
- stp x29, x22, [sp, #S_STACKFRAME]
+ mov x0, #FRAME_META_TYPE_PT_REGS
.endif
+ str x0, [sp, #S_STACKFRAME_TYPE]
add x29, sp, #S_STACKFRAME
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
@@ -315,7 +317,7 @@ alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
alternative_else_nop_endif
mrs_s x20, SYS_ICC_PMR_EL1
- str x20, [sp, #S_PMR_SAVE]
+ str w20, [sp, #S_PMR]
mov x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET
msr_s SYS_ICC_PMR_EL1, x20
@@ -342,7 +344,7 @@ alternative_if_not ARM64_HAS_GIC_PRIO_MASKING
b .Lskip_pmr_restore\@
alternative_else_nop_endif
- ldr x20, [sp, #S_PMR_SAVE]
+ ldr w20, [sp, #S_PMR]
msr_s SYS_ICC_PMR_EL1, x20
/* Ensure priority change is seen by redistributor */
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 77006df20a75..8c4c1a2186cc 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -386,7 +386,7 @@ static void task_fpsimd_load(void)
* fpsimd_save_user_state() or memory corruption, we
* should always record an explicit format
* when we save. We always at least have the
- * memory allocated for FPSMID registers so
+ * memory allocated for FPSIMD registers so
* try that and hope for the best.
*/
WARN_ON_ONCE(1);
@@ -1367,6 +1367,7 @@ static void sve_init_regs(void)
} else {
fpsimd_to_sve(current);
current->thread.fp_type = FP_STATE_SVE;
+ fpsimd_flush_task_state(current);
}
}
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index a650f5e11fc5..b2d947175cbe 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -23,10 +23,10 @@ struct fregs_offset {
int offset;
};
-#define FREGS_OFFSET(n, field) \
-{ \
- .name = n, \
- .offset = offsetof(struct ftrace_regs, field), \
+#define FREGS_OFFSET(n, field) \
+{ \
+ .name = n, \
+ .offset = offsetof(struct __arch_ftrace_regs, field), \
}
static const struct fregs_offset fregs_offsets[] = {
@@ -481,7 +481,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op, struct ftrace_regs *fregs)
{
- prepare_ftrace_return(ip, &fregs->lr, fregs->fp);
+ prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp);
}
#else
/*
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index cb68adcabe07..5ab1970ee543 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -32,6 +32,7 @@
#include <asm/scs.h>
#include <asm/smp.h>
#include <asm/sysreg.h>
+#include <asm/stacktrace/frame.h>
#include <asm/thread_info.h>
#include <asm/virt.h>
@@ -199,6 +200,8 @@ SYM_CODE_END(preserve_boot_args)
sub sp, sp, #PT_REGS_SIZE
stp xzr, xzr, [sp, #S_STACKFRAME]
+ mov \tmp1, #FRAME_META_TYPE_FINAL
+ str \tmp1, [sp, #S_STACKFRAME_TYPE]
add x29, sp, #S_STACKFRAME
scs_load_current
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 7b11d84f533c..18749e9a6c2d 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -266,9 +266,15 @@ static int swsusp_mte_save_tags(void)
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
struct page *page = pfn_to_online_page(pfn);
+ struct folio *folio;
if (!page)
continue;
+ folio = page_folio(page);
+
+ if (folio_test_hugetlb(folio) &&
+ !folio_test_hugetlb_mte_tagged(folio))
+ continue;
if (!page_mte_tagged(page))
continue;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 36b25af56324..06bb680bfe97 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -462,14 +462,20 @@ int module_finalize(const Elf_Ehdr *hdr,
struct module *me)
{
const Elf_Shdr *s;
+ int ret;
+
s = find_section(hdr, sechdrs, ".altinstructions");
if (s)
apply_alternatives_module((void *)s->sh_addr, s->sh_size);
if (scs_is_dynamic()) {
s = find_section(hdr, sechdrs, ".init.eh_frame");
- if (s)
- __pi_scs_patch((void *)s->sh_addr, s->sh_size);
+ if (s) {
+ ret = __pi_scs_patch((void *)s->sh_addr, s->sh_size);
+ if (ret)
+ pr_err("module %s: error occurred during dynamic SCS patching (%d)\n",
+ me->name, ret);
+ }
}
return module_init_ftrace_plt(hdr, sechdrs, me);
diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c
index 6174671be7c1..2fbfd27ff5f2 100644
--- a/arch/arm64/kernel/mte.c
+++ b/arch/arm64/kernel/mte.c
@@ -38,7 +38,24 @@ EXPORT_SYMBOL_GPL(mte_async_or_asymm_mode);
void mte_sync_tags(pte_t pte, unsigned int nr_pages)
{
struct page *page = pte_page(pte);
- unsigned int i;
+ struct folio *folio = page_folio(page);
+ unsigned long i;
+
+ if (folio_test_hugetlb(folio)) {
+ unsigned long nr = folio_nr_pages(folio);
+
+ /* Hugetlb MTE flags are set for head page only */
+ if (folio_try_hugetlb_mte_tagging(folio)) {
+ for (i = 0; i < nr; i++, page++)
+ mte_clear_page_tags(page_address(page));
+ folio_set_hugetlb_mte_tagged(folio);
+ }
+
+ /* ensure the tags are visible before the PTE is set */
+ smp_wmb();
+
+ return;
+ }
/* if PG_mte_tagged is set, tags have already been initialised */
for (i = 0; i < nr_pages; i++, page++) {
@@ -410,6 +427,7 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
void *maddr;
struct page *page = get_user_page_vma_remote(mm, addr,
gup_flags, &vma);
+ struct folio *folio;
if (IS_ERR(page)) {
err = PTR_ERR(page);
@@ -428,7 +446,12 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr,
put_page(page);
break;
}
- WARN_ON_ONCE(!page_mte_tagged(page));
+
+ folio = page_folio(page);
+ if (folio_test_hugetlb(folio))
+ WARN_ON_ONCE(!folio_test_hugetlb_mte_tagged(folio));
+ else
+ WARN_ON_ONCE(!page_mte_tagged(page));
/* limit access to the end of the page */
offset = offset_in_page(addr);
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index e8ed5673f481..9b7f26b128b5 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -38,31 +38,3 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
arch_stack_walk(callchain_trace, entry, current, regs);
}
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
- if (perf_guest_state())
- return perf_guest_get_ip();
-
- return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
- unsigned int guest_state = perf_guest_state();
- int misc = 0;
-
- if (guest_state) {
- if (guest_state & PERF_GUEST_USER)
- misc |= PERF_RECORD_MISC_GUEST_USER;
- else
- misc |= PERF_RECORD_MISC_GUEST_KERNEL;
- } else {
- if (user_mode(regs))
- misc |= PERF_RECORD_MISC_USER;
- else
- misc |= PERF_RECORD_MISC_KERNEL;
- }
-
- return misc;
-}
diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c
index 29d4b6244a6f..22159251eb3a 100644
--- a/arch/arm64/kernel/pi/idreg-override.c
+++ b/arch/arm64/kernel/pi/idreg-override.c
@@ -38,6 +38,15 @@ struct ftr_set_desc {
#define FIELD(n, s, f) { .name = n, .shift = s, .width = 4, .filter = f }
+static const struct ftr_set_desc mmfr0 __prel64_initconst = {
+ .name = "id_aa64mmfr0",
+ .override = &id_aa64mmfr0_override,
+ .fields = {
+ FIELD("ecv", ID_AA64MMFR0_EL1_ECV_SHIFT, NULL),
+ {}
+ },
+};
+
static bool __init mmfr1_vh_filter(u64 val)
{
/*
@@ -133,6 +142,7 @@ static const struct ftr_set_desc pfr1 __prel64_initconst = {
.override = &id_aa64pfr1_override,
.fields = {
FIELD("bt", ID_AA64PFR1_EL1_BT_SHIFT, NULL ),
+ FIELD("gcs", ID_AA64PFR1_EL1_GCS_SHIFT, NULL),
FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL),
FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter),
{}
@@ -196,6 +206,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = {
static const
PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = {
+ { &mmfr0 },
{ &mmfr1 },
{ &mmfr2 },
{ &pfr0 },
@@ -215,6 +226,7 @@ static const struct {
{ "arm64.nosve", "id_aa64pfr0.sve=0" },
{ "arm64.nosme", "id_aa64pfr1.sme=0" },
{ "arm64.nobti", "id_aa64pfr1.bt=0" },
+ { "arm64.nogcs", "id_aa64pfr1.gcs=0" },
{ "arm64.nopauth",
"id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 "
"id_aa64isar1.api=0 id_aa64isar1.apa=0 "
diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c
index 5410b2cac590..2b69e3beeef8 100644
--- a/arch/arm64/kernel/pi/map_range.c
+++ b/arch/arm64/kernel/pi/map_range.c
@@ -30,7 +30,7 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot,
int level, pte_t *tbl, bool may_use_cont, u64 va_offset)
{
u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX;
- u64 protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
+ pteval_t protval = pgprot_val(prot) & ~PTE_TYPE_MASK;
int lshift = (3 - level) * (PAGE_SHIFT - 3);
u64 lmask = (PAGE_SIZE << lshift) - 1;
diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c
index 49d8b40e61bc..55d0cd64ef71 100644
--- a/arch/arm64/kernel/pi/patch-scs.c
+++ b/arch/arm64/kernel/pi/patch-scs.c
@@ -50,6 +50,10 @@ bool dynamic_scs_is_enabled;
#define DW_CFA_GNU_negative_offset_extended 0x2f
#define DW_CFA_hi_user 0x3f
+#define DW_EH_PE_sdata4 0x0b
+#define DW_EH_PE_sdata8 0x0c
+#define DW_EH_PE_pcrel 0x10
+
enum {
PACIASP = 0xd503233f,
AUTIASP = 0xd50323bf,
@@ -120,7 +124,12 @@ struct eh_frame {
union {
struct { // CIE
u8 version;
- u8 augmentation_string[];
+ u8 augmentation_string[3];
+ u8 code_alignment_factor;
+ u8 data_alignment_factor;
+ u8 return_address_register;
+ u8 augmentation_data_size;
+ u8 fde_pointer_format;
};
struct { // FDE
@@ -128,29 +137,38 @@ struct eh_frame {
s32 range;
u8 opcodes[];
};
+
+ struct { // FDE
+ s64 initial_loc64;
+ s64 range64;
+ u8 opcodes64[];
+ };
};
};
static int scs_handle_fde_frame(const struct eh_frame *frame,
- bool fde_has_augmentation_data,
int code_alignment_factor,
+ bool use_sdata8,
bool dry_run)
{
int size = frame->size - offsetof(struct eh_frame, opcodes) + 4;
u64 loc = (u64)offset_to_ptr(&frame->initial_loc);
const u8 *opcode = frame->opcodes;
+ int l;
- if (fde_has_augmentation_data) {
- int l;
+ if (use_sdata8) {
+ loc = (u64)&frame->initial_loc64 + frame->initial_loc64;
+ opcode = frame->opcodes64;
+ size -= 8;
+ }
- // assume single byte uleb128_t
- if (WARN_ON(*opcode & BIT(7)))
- return -ENOEXEC;
+ // assume single byte uleb128_t for augmentation data size
+ if (*opcode & BIT(7))
+ return EDYNSCS_INVALID_FDE_AUGM_DATA_SIZE;
- l = *opcode++;
- opcode += l;
- size -= l + 1;
- }
+ l = *opcode++;
+ opcode += l;
+ size -= l + 1;
/*
* Starting from 'loc', apply the CFA opcodes that advance the location
@@ -201,7 +219,7 @@ static int scs_handle_fde_frame(const struct eh_frame *frame,
break;
default:
- return -ENOEXEC;
+ return EDYNSCS_INVALID_CFA_OPCODE;
}
}
return 0;
@@ -209,12 +227,12 @@ static int scs_handle_fde_frame(const struct eh_frame *frame,
int scs_patch(const u8 eh_frame[], int size)
{
+ int code_alignment_factor = 1;
+ bool fde_use_sdata8 = false;
const u8 *p = eh_frame;
while (size > 4) {
const struct eh_frame *frame = (const void *)p;
- bool fde_has_augmentation_data = true;
- int code_alignment_factor = 1;
int ret;
if (frame->size == 0 ||
@@ -223,28 +241,47 @@ int scs_patch(const u8 eh_frame[], int size)
break;
if (frame->cie_id_or_pointer == 0) {
- const u8 *p = frame->augmentation_string;
-
- /* a 'z' in the augmentation string must come first */
- fde_has_augmentation_data = *p == 'z';
+ /*
+ * Require presence of augmentation data (z) with a
+ * specifier for the size of the FDE initial_loc and
+ * range fields (R), and nothing else.
+ */
+ if (strcmp(frame->augmentation_string, "zR"))
+ return EDYNSCS_INVALID_CIE_HEADER;
/*
* The code alignment factor is a uleb128 encoded field
* but given that the only sensible values are 1 or 4,
- * there is no point in decoding the whole thing.
+ * there is no point in decoding the whole thing. Also
+ * sanity check the size of the data alignment factor
+ * field, and the values of the return address register
+ * and augmentation data size fields.
*/
- p += strlen(p) + 1;
- if (!WARN_ON(*p & BIT(7)))
- code_alignment_factor = *p;
+ if ((frame->code_alignment_factor & BIT(7)) ||
+ (frame->data_alignment_factor & BIT(7)) ||
+ frame->return_address_register != 30 ||
+ frame->augmentation_data_size != 1)
+ return EDYNSCS_INVALID_CIE_HEADER;
+
+ code_alignment_factor = frame->code_alignment_factor;
+
+ switch (frame->fde_pointer_format) {
+ case DW_EH_PE_pcrel | DW_EH_PE_sdata4:
+ fde_use_sdata8 = false;
+ break;
+ case DW_EH_PE_pcrel | DW_EH_PE_sdata8:
+ fde_use_sdata8 = true;
+ break;
+ default:
+ return EDYNSCS_INVALID_CIE_SDATA_SIZE;
+ }
} else {
- ret = scs_handle_fde_frame(frame,
- fde_has_augmentation_data,
- code_alignment_factor,
- true);
+ ret = scs_handle_fde_frame(frame, code_alignment_factor,
+ fde_use_sdata8, true);
if (ret)
return ret;
- scs_handle_fde_frame(frame, fde_has_augmentation_data,
- code_alignment_factor, false);
+ scs_handle_fde_frame(frame, code_alignment_factor,
+ fde_use_sdata8, false);
}
p += sizeof(frame->size) + frame->size;
diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c
index 968d5fffe233..6438bf62e753 100644
--- a/arch/arm64/kernel/probes/decode-insn.c
+++ b/arch/arm64/kernel/probes/decode-insn.c
@@ -58,10 +58,13 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
* Instructions which load PC relative literals are not going to work
* when executed from an XOL slot. Instructions doing an exclusive
* load/store are not going to complete successfully when single-step
- * exception handling happens in the middle of the sequence.
+ * exception handling happens in the middle of the sequence. Memory
+ * copy/set instructions require that all three instructions be placed
+ * consecutively in memory.
*/
if (aarch64_insn_uses_literal(insn) ||
- aarch64_insn_is_exclusive(insn))
+ aarch64_insn_is_exclusive(insn) ||
+ aarch64_insn_is_mops(insn))
return false;
return true;
@@ -73,9 +76,18 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
* INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
*/
enum probe_insn __kprobes
-arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api)
+arm_probe_decode_insn(u32 insn, struct arch_probe_insn *api)
{
/*
+ * While 'nop' instruction can execute in the out-of-line slot,
+ * simulating them in breakpoint handling offers better performance.
+ */
+ if (aarch64_insn_is_nop(insn)) {
+ api->handler = simulate_nop;
+ return INSN_GOOD_NO_SLOT;
+ }
+
+ /*
* Instructions reading or modifying the PC won't work from the XOL
* slot.
*/
@@ -99,10 +111,6 @@ arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api)
aarch64_insn_is_blr(insn) ||
aarch64_insn_is_ret(insn)) {
api->handler = simulate_br_blr_ret;
- } else if (aarch64_insn_is_ldr_lit(insn)) {
- api->handler = simulate_ldr_literal;
- } else if (aarch64_insn_is_ldrsw_lit(insn)) {
- api->handler = simulate_ldrsw_literal;
} else {
/*
* Instruction cannot be stepped out-of-line and we don't
@@ -137,9 +145,20 @@ enum probe_insn __kprobes
arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
{
enum probe_insn decoded;
- probe_opcode_t insn = le32_to_cpu(*addr);
- probe_opcode_t *scan_end = NULL;
+ u32 insn = le32_to_cpu(*addr);
+ kprobe_opcode_t *scan_end = NULL;
unsigned long size = 0, offset = 0;
+ struct arch_probe_insn *api = &asi->api;
+
+ if (aarch64_insn_is_ldr_lit(insn)) {
+ api->handler = simulate_ldr_literal;
+ decoded = INSN_GOOD_NO_SLOT;
+ } else if (aarch64_insn_is_ldrsw_lit(insn)) {
+ api->handler = simulate_ldrsw_literal;
+ decoded = INSN_GOOD_NO_SLOT;
+ } else {
+ decoded = arm_probe_decode_insn(insn, &asi->api);
+ }
/*
* If there's a symbol defined in front of and near enough to
@@ -157,7 +176,6 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
else
scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
}
- decoded = arm_probe_decode_insn(insn, &asi->api);
if (decoded != INSN_REJECTED && scan_end)
if (is_probed_address_atomic(addr - 1, scan_end))
diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h
index 8b758c5a2062..0e4195de8206 100644
--- a/arch/arm64/kernel/probes/decode-insn.h
+++ b/arch/arm64/kernel/probes/decode-insn.h
@@ -28,6 +28,6 @@ enum probe_insn __kprobes
arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi);
#endif
enum probe_insn __kprobes
-arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *asi);
+arm_probe_decode_insn(u32 insn, struct arch_probe_insn *asi);
#endif /* _ARM_KERNEL_KPROBES_ARM64_H */
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 4268678d0e86..48d88e07611d 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -43,7 +43,7 @@ post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *);
static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
{
- kprobe_opcode_t *addr = p->ainsn.api.insn;
+ kprobe_opcode_t *addr = p->ainsn.xol_insn;
/*
* Prepare insn slot, Mark Rutland points out it depends on a coupe of
@@ -64,20 +64,20 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
* the BRK exception handler, so it is unnecessary to generate
* Contex-Synchronization-Event via ISB again.
*/
- aarch64_insn_patch_text_nosync(addr, p->opcode);
+ aarch64_insn_patch_text_nosync(addr, le32_to_cpu(p->opcode));
aarch64_insn_patch_text_nosync(addr + 1, BRK64_OPCODE_KPROBES_SS);
/*
* Needs restoring of return address after stepping xol.
*/
- p->ainsn.api.restore = (unsigned long) p->addr +
+ p->ainsn.xol_restore = (unsigned long) p->addr +
sizeof(kprobe_opcode_t);
}
static void __kprobes arch_prepare_simulate(struct kprobe *p)
{
/* This instructions is not executed xol. No need to adjust the PC */
- p->ainsn.api.restore = 0;
+ p->ainsn.xol_restore = 0;
}
static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
@@ -85,7 +85,7 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
if (p->ainsn.api.handler)
- p->ainsn.api.handler((u32)p->opcode, (long)p->addr, regs);
+ p->ainsn.api.handler(le32_to_cpu(p->opcode), (long)p->addr, regs);
/* single step simulated, now go for post processing */
post_kprobe_handler(p, kcb, regs);
@@ -99,7 +99,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
return -EINVAL;
/* copy instruction */
- p->opcode = le32_to_cpu(*p->addr);
+ p->opcode = *p->addr;
if (search_exception_tables(probe_addr))
return -EINVAL;
@@ -110,18 +110,18 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
return -EINVAL;
case INSN_GOOD_NO_SLOT: /* insn need simulation */
- p->ainsn.api.insn = NULL;
+ p->ainsn.xol_insn = NULL;
break;
case INSN_GOOD: /* instruction uses slot */
- p->ainsn.api.insn = get_insn_slot();
- if (!p->ainsn.api.insn)
+ p->ainsn.xol_insn = get_insn_slot();
+ if (!p->ainsn.xol_insn)
return -ENOMEM;
break;
}
/* prepare the instruction */
- if (p->ainsn.api.insn)
+ if (p->ainsn.xol_insn)
arch_prepare_ss_slot(p);
else
arch_prepare_simulate(p);
@@ -142,15 +142,16 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
void __kprobes arch_disarm_kprobe(struct kprobe *p)
{
void *addr = p->addr;
+ u32 insn = le32_to_cpu(p->opcode);
- aarch64_insn_patch_text(&addr, &p->opcode, 1);
+ aarch64_insn_patch_text(&addr, &insn, 1);
}
void __kprobes arch_remove_kprobe(struct kprobe *p)
{
- if (p->ainsn.api.insn) {
- free_insn_slot(p->ainsn.api.insn, 0);
- p->ainsn.api.insn = NULL;
+ if (p->ainsn.xol_insn) {
+ free_insn_slot(p->ainsn.xol_insn, 0);
+ p->ainsn.xol_insn = NULL;
}
}
@@ -205,9 +206,9 @@ static void __kprobes setup_singlestep(struct kprobe *p,
}
- if (p->ainsn.api.insn) {
+ if (p->ainsn.xol_insn) {
/* prepare for single stepping */
- slot = (unsigned long)p->ainsn.api.insn;
+ slot = (unsigned long)p->ainsn.xol_insn;
kprobes_save_local_irqflag(kcb, regs);
instruction_pointer_set(regs, slot);
@@ -245,8 +246,8 @@ static void __kprobes
post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs)
{
/* return addr restore if non-branching insn */
- if (cur->ainsn.api.restore != 0)
- instruction_pointer_set(regs, cur->ainsn.api.restore);
+ if (cur->ainsn.xol_restore != 0)
+ instruction_pointer_set(regs, cur->ainsn.xol_restore);
/* restore back original saved kprobe variables and continue */
if (kcb->kprobe_status == KPROBE_REENTER) {
@@ -348,7 +349,7 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr)
struct kprobe *cur = kprobe_running();
if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) &&
- ((unsigned long)&cur->ainsn.api.insn[1] == addr)) {
+ ((unsigned long)&cur->ainsn.xol_insn[1] == addr)) {
kprobes_restore_local_irqflag(kcb, regs);
post_kprobe_handler(cur, kcb, regs);
diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c
index 22d0b3252476..4c6d2d712fbd 100644
--- a/arch/arm64/kernel/probes/simulate-insn.c
+++ b/arch/arm64/kernel/probes/simulate-insn.c
@@ -171,17 +171,15 @@ simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs)
void __kprobes
simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
{
- u64 *load_addr;
+ unsigned long load_addr;
int xn = opcode & 0x1f;
- int disp;
- disp = ldr_displacement(opcode);
- load_addr = (u64 *) (addr + disp);
+ load_addr = addr + ldr_displacement(opcode);
if (opcode & (1 << 30)) /* x0-x30 */
- set_x_reg(regs, xn, *load_addr);
+ set_x_reg(regs, xn, READ_ONCE(*(u64 *)load_addr));
else /* w0-w30 */
- set_w_reg(regs, xn, *load_addr);
+ set_w_reg(regs, xn, READ_ONCE(*(u32 *)load_addr));
instruction_pointer_set(regs, instruction_pointer(regs) + 4);
}
@@ -189,14 +187,18 @@ simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
void __kprobes
simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs)
{
- s32 *load_addr;
+ unsigned long load_addr;
int xn = opcode & 0x1f;
- int disp;
- disp = ldr_displacement(opcode);
- load_addr = (s32 *) (addr + disp);
+ load_addr = addr + ldr_displacement(opcode);
- set_x_reg(regs, xn, *load_addr);
+ set_x_reg(regs, xn, READ_ONCE(*(s32 *)load_addr));
instruction_pointer_set(regs, instruction_pointer(regs) + 4);
}
+
+void __kprobes
+simulate_nop(u32 opcode, long addr, struct pt_regs *regs)
+{
+ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+}
diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h
index e065dc92218e..efb2803ec943 100644
--- a/arch/arm64/kernel/probes/simulate-insn.h
+++ b/arch/arm64/kernel/probes/simulate-insn.h
@@ -16,5 +16,6 @@ void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs);
void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs);
void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs);
void simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs);
+void simulate_nop(u32 opcode, long addr, struct pt_regs *regs);
#endif /* _ARM_KERNEL_KPROBES_SIMULATE_INSN_H */
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index d49aef2657cd..cb3d05af36e3 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -17,12 +17,20 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
void *xol_page_kaddr = kmap_atomic(page);
void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK);
+ /*
+ * Initial cache maintenance of the xol page done via set_pte_at().
+ * Subsequent CMOs only needed if the xol slot changes.
+ */
+ if (!memcmp(dst, src, len))
+ goto done;
+
/* Initialize the slot */
memcpy(dst, src, len);
/* flush caches (dcache/icache) */
sync_icache_aliases((unsigned long)dst, (unsigned long)dst + len);
+done:
kunmap_atomic(xol_page_kaddr);
}
@@ -34,7 +42,7 @@ unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
unsigned long addr)
{
- probe_opcode_t insn;
+ u32 insn;
/* TODO: Currently we do not support AARCH32 instruction probing */
if (mm->context.flags & MMCF_AARCH32)
@@ -42,7 +50,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE))
return -EINVAL;
- insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+ insn = le32_to_cpu(auprobe->insn);
switch (arm_probe_decode_insn(insn, &auprobe->api)) {
case INSN_REJECTED:
@@ -102,13 +110,13 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *t)
bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
{
- probe_opcode_t insn;
+ u32 insn;
unsigned long addr;
if (!auprobe->simulate)
return false;
- insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+ insn = le32_to_cpu(auprobe->insn);
addr = instruction_pointer(regs);
if (auprobe->api.handler)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 0540653fbf38..2968a33bb3bc 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -49,6 +49,7 @@
#include <asm/cacheflush.h>
#include <asm/exec.h>
#include <asm/fpsimd.h>
+#include <asm/gcs.h>
#include <asm/mmu_context.h>
#include <asm/mte.h>
#include <asm/processor.h>
@@ -227,7 +228,7 @@ void __show_regs(struct pt_regs *regs)
printk("sp : %016llx\n", sp);
if (system_uses_irq_prio_masking())
- printk("pmr_save: %08llx\n", regs->pmr_save);
+ printk("pmr: %08x\n", regs->pmr);
i = top_reg;
@@ -280,6 +281,51 @@ static void flush_poe(void)
write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
}
+#ifdef CONFIG_ARM64_GCS
+
+static void flush_gcs(void)
+{
+ if (!system_supports_gcs())
+ return;
+
+ gcs_free(current);
+ current->thread.gcs_el0_mode = 0;
+ write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1);
+ write_sysreg_s(0, SYS_GCSPR_EL0);
+}
+
+static int copy_thread_gcs(struct task_struct *p,
+ const struct kernel_clone_args *args)
+{
+ unsigned long gcs;
+
+ if (!system_supports_gcs())
+ return 0;
+
+ p->thread.gcs_base = 0;
+ p->thread.gcs_size = 0;
+
+ gcs = gcs_alloc_thread_stack(p, args);
+ if (IS_ERR_VALUE(gcs))
+ return PTR_ERR((void *)gcs);
+
+ p->thread.gcs_el0_mode = current->thread.gcs_el0_mode;
+ p->thread.gcs_el0_locked = current->thread.gcs_el0_locked;
+
+ return 0;
+}
+
+#else
+
+static void flush_gcs(void) { }
+static int copy_thread_gcs(struct task_struct *p,
+ const struct kernel_clone_args *args)
+{
+ return 0;
+}
+
+#endif
+
void flush_thread(void)
{
fpsimd_flush_thread();
@@ -287,11 +333,13 @@ void flush_thread(void)
flush_ptrace_hw_breakpoint(current);
flush_tagged_addr_state();
flush_poe();
+ flush_gcs();
}
void arch_release_task_struct(struct task_struct *tsk)
{
fpsimd_release_task(tsk);
+ gcs_free(tsk);
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -355,6 +403,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
unsigned long stack_start = args->stack;
unsigned long tls = args->tls;
struct pt_regs *childregs = task_pt_regs(p);
+ int ret;
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
@@ -399,6 +448,10 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
p->thread.uw.tp_value = tls;
p->thread.tpidr2_el0 = 0;
}
+
+ ret = copy_thread_gcs(p, args);
+ if (ret != 0)
+ return ret;
} else {
/*
* A kthread has no context to ERET to, so ensure any buggy
@@ -409,9 +462,13 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
*/
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
+ childregs->stackframe.type = FRAME_META_TYPE_FINAL;
p->thread.cpu_context.x19 = (unsigned long)args->fn;
p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
+
+ if (system_supports_poe())
+ p->thread.por_el0 = POR_EL0_INIT;
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
@@ -419,7 +476,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
* For the benefit of the unwinder, set up childregs->stackframe
* as the final frame for the new task.
*/
- p->thread.cpu_context.fp = (unsigned long)childregs->stackframe;
+ p->thread.cpu_context.fp = (unsigned long)&childregs->stackframe;
ptrace_hw_copy_thread(p);
@@ -439,7 +496,7 @@ static void tls_thread_switch(struct task_struct *next)
if (is_compat_thread(task_thread_info(next)))
write_sysreg(next->thread.uw.tp_value, tpidrro_el0);
- else if (!arm64_kernel_unmapped_at_el0())
+ else
write_sysreg(0, tpidrro_el0);
write_sysreg(*task_user_tls(next), tpidr_el0);
@@ -484,6 +541,46 @@ static void entry_task_switch(struct task_struct *next)
__this_cpu_write(__entry_task, next);
}
+#ifdef CONFIG_ARM64_GCS
+
+void gcs_preserve_current_state(void)
+{
+ current->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+}
+
+static void gcs_thread_switch(struct task_struct *next)
+{
+ if (!system_supports_gcs())
+ return;
+
+ /* GCSPR_EL0 is always readable */
+ gcs_preserve_current_state();
+ write_sysreg_s(next->thread.gcspr_el0, SYS_GCSPR_EL0);
+
+ if (current->thread.gcs_el0_mode != next->thread.gcs_el0_mode)
+ gcs_set_el0_mode(next);
+
+ /*
+ * Ensure that GCS memory effects of the 'prev' thread are
+ * ordered before other memory accesses with release semantics
+ * (or preceded by a DMB) on the current PE. In addition, any
+ * memory accesses with acquire semantics (or succeeded by a
+ * DMB) are ordered before GCS memory effects of the 'next'
+ * thread. This will ensure that the GCS memory effects are
+ * visible to other PEs in case of migration.
+ */
+ if (task_gcs_el0_enabled(current) || task_gcs_el0_enabled(next))
+ gcsb_dsync();
+}
+
+#else
+
+static void gcs_thread_switch(struct task_struct *next)
+{
+}
+
+#endif
+
/*
* Handle sysreg updates for ARM erratum 1418040 which affects the 32bit view of
* CNTVCT, various other errata which require trapping all CNTVCT{,_EL0}
@@ -580,6 +677,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
cntkctl_thread_switch(prev, next);
ptrauth_thread_switch_user(next);
permission_overlay_switch(next);
+ gcs_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index b756578aeaee..e4437f62a2cd 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -34,6 +34,7 @@
#include <asm/cpufeature.h>
#include <asm/debug-monitors.h>
#include <asm/fpsimd.h>
+#include <asm/gcs.h>
#include <asm/mte.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
@@ -898,7 +899,11 @@ static int sve_set_common(struct task_struct *target,
if (ret)
goto out;
- /* Actual VL set may be less than the user asked for: */
+ /*
+ * Actual VL set may be different from what the user asked
+ * for, or we may have configured the _ONEXEC VL not the
+ * current VL:
+ */
vq = sve_vq_from_vl(task_get_vl(target, type));
/* Enter/exit streaming mode */
@@ -1125,7 +1130,11 @@ static int za_set(struct task_struct *target,
if (ret)
goto out;
- /* Actual VL set may be less than the user asked for: */
+ /*
+ * Actual VL set may be different from what the user asked
+ * for, or we may have configured the _ONEXEC rather than
+ * current VL:
+ */
vq = sve_vq_from_vl(task_get_sme_vl(target));
/* Ensure there is some SVE storage for streaming mode */
@@ -1473,6 +1482,52 @@ static int poe_set(struct task_struct *target, const struct
}
#endif
+#ifdef CONFIG_ARM64_GCS
+static int gcs_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ struct user_gcs user_gcs;
+
+ if (!system_supports_gcs())
+ return -EINVAL;
+
+ if (target == current)
+ gcs_preserve_current_state();
+
+ user_gcs.features_enabled = target->thread.gcs_el0_mode;
+ user_gcs.features_locked = target->thread.gcs_el0_locked;
+ user_gcs.gcspr_el0 = target->thread.gcspr_el0;
+
+ return membuf_write(&to, &user_gcs, sizeof(user_gcs));
+}
+
+static int gcs_set(struct task_struct *target, const struct
+ user_regset *regset, unsigned int pos,
+ unsigned int count, const void *kbuf, const
+ void __user *ubuf)
+{
+ int ret;
+ struct user_gcs user_gcs;
+
+ if (!system_supports_gcs())
+ return -EINVAL;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_gcs, 0, -1);
+ if (ret)
+ return ret;
+
+ if (user_gcs.features_enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
+ return -EINVAL;
+
+ target->thread.gcs_el0_mode = user_gcs.features_enabled;
+ target->thread.gcs_el0_locked = user_gcs.features_locked;
+ target->thread.gcspr_el0 = user_gcs.gcspr_el0;
+
+ return 0;
+}
+#endif
+
enum aarch64_regset {
REGSET_GPR,
REGSET_FPR,
@@ -1503,7 +1558,10 @@ enum aarch64_regset {
REGSET_TAGGED_ADDR_CTRL,
#endif
#ifdef CONFIG_ARM64_POE
- REGSET_POE
+ REGSET_POE,
+#endif
+#ifdef CONFIG_ARM64_GCS
+ REGSET_GCS,
#endif
};
@@ -1674,6 +1732,16 @@ static const struct user_regset aarch64_regsets[] = {
.set = poe_set,
},
#endif
+#ifdef CONFIG_ARM64_GCS
+ [REGSET_GCS] = {
+ .core_note_type = NT_ARM_GCS,
+ .n = sizeof(struct user_gcs) / sizeof(u64),
+ .size = sizeof(u64),
+ .align = sizeof(u64),
+ .regset_get = gcs_get,
+ .set = gcs_set,
+ },
+#endif
};
static const struct user_regset_view user_aarch64_view = {
diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c
new file mode 100644
index 000000000000..3031f25c32ef
--- /dev/null
+++ b/arch/arm64/kernel/rsi.c
@@ -0,0 +1,142 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+
+#include <linux/jump_label.h>
+#include <linux/memblock.h>
+#include <linux/psci.h>
+#include <linux/swiotlb.h>
+#include <linux/cc_platform.h>
+
+#include <asm/io.h>
+#include <asm/mem_encrypt.h>
+#include <asm/rsi.h>
+
+static struct realm_config config;
+
+unsigned long prot_ns_shared;
+EXPORT_SYMBOL(prot_ns_shared);
+
+DEFINE_STATIC_KEY_FALSE_RO(rsi_present);
+EXPORT_SYMBOL(rsi_present);
+
+bool cc_platform_has(enum cc_attr attr)
+{
+ switch (attr) {
+ case CC_ATTR_MEM_ENCRYPT:
+ return is_realm_world();
+ default:
+ return false;
+ }
+}
+EXPORT_SYMBOL_GPL(cc_platform_has);
+
+static bool rsi_version_matches(void)
+{
+ unsigned long ver_lower, ver_higher;
+ unsigned long ret = rsi_request_version(RSI_ABI_VERSION,
+ &ver_lower,
+ &ver_higher);
+
+ if (ret == SMCCC_RET_NOT_SUPPORTED)
+ return false;
+
+ if (ret != RSI_SUCCESS) {
+ pr_err("RME: RMM doesn't support RSI version %lu.%lu. Supported range: %lu.%lu-%lu.%lu\n",
+ RSI_ABI_VERSION_MAJOR, RSI_ABI_VERSION_MINOR,
+ RSI_ABI_VERSION_GET_MAJOR(ver_lower),
+ RSI_ABI_VERSION_GET_MINOR(ver_lower),
+ RSI_ABI_VERSION_GET_MAJOR(ver_higher),
+ RSI_ABI_VERSION_GET_MINOR(ver_higher));
+ return false;
+ }
+
+ pr_info("RME: Using RSI version %lu.%lu\n",
+ RSI_ABI_VERSION_GET_MAJOR(ver_lower),
+ RSI_ABI_VERSION_GET_MINOR(ver_lower));
+
+ return true;
+}
+
+static void __init arm64_rsi_setup_memory(void)
+{
+ u64 i;
+ phys_addr_t start, end;
+
+ /*
+ * Iterate over the available memory ranges and convert the state to
+ * protected memory. We should take extra care to ensure that we DO NOT
+ * permit any "DESTROYED" pages to be converted to "RAM".
+ *
+ * panic() is used because if the attempt to switch the memory to
+ * protected has failed here, then future accesses to the memory are
+ * simply going to be reflected as a SEA (Synchronous External Abort)
+ * which we can't handle. Bailing out early prevents the guest limping
+ * on and dying later.
+ */
+ for_each_mem_range(i, &start, &end) {
+ if (rsi_set_memory_range_protected_safe(start, end)) {
+ panic("Failed to set memory range to protected: %pa-%pa",
+ &start, &end);
+ }
+ }
+}
+
+bool __arm64_is_protected_mmio(phys_addr_t base, size_t size)
+{
+ enum ripas ripas;
+ phys_addr_t end, top;
+
+ /* Overflow ? */
+ if (WARN_ON(base + size <= base))
+ return false;
+
+ end = ALIGN(base + size, RSI_GRANULE_SIZE);
+ base = ALIGN_DOWN(base, RSI_GRANULE_SIZE);
+
+ while (base < end) {
+ if (WARN_ON(rsi_ipa_state_get(base, end, &ripas, &top)))
+ break;
+ if (WARN_ON(top <= base))
+ break;
+ if (ripas != RSI_RIPAS_DEV)
+ break;
+ base = top;
+ }
+
+ return base >= end;
+}
+EXPORT_SYMBOL(__arm64_is_protected_mmio);
+
+static int realm_ioremap_hook(phys_addr_t phys, size_t size, pgprot_t *prot)
+{
+ if (__arm64_is_protected_mmio(phys, size))
+ *prot = pgprot_encrypted(*prot);
+ else
+ *prot = pgprot_decrypted(*prot);
+
+ return 0;
+}
+
+void __init arm64_rsi_init(void)
+{
+ if (arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_SMC)
+ return;
+ if (!rsi_version_matches())
+ return;
+ if (WARN_ON(rsi_get_realm_config(&config)))
+ return;
+ prot_ns_shared = BIT(config.ipa_bits - 1);
+
+ if (arm64_ioremap_prot_hook_register(realm_ioremap_hook))
+ return;
+
+ if (realm_register_memory_enc_ops())
+ return;
+
+ arm64_rsi_setup_memory();
+
+ static_branch_enable(&rsi_present);
+}
+
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 87f61fd6783c..4f613e8e0745 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -43,6 +43,7 @@
#include <asm/cpu_ops.h>
#include <asm/kasan.h>
#include <asm/numa.h>
+#include <asm/rsi.h>
#include <asm/scs.h>
#include <asm/sections.h>
#include <asm/setup.h>
@@ -355,6 +356,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
else
psci_acpi_init();
+ arm64_rsi_init();
+
init_bootcpu_ops();
smp_init_cpus();
smp_build_mpidr_hash();
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 561986947530..14ac6fdb872b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -19,12 +19,14 @@
#include <linux/ratelimit.h>
#include <linux/rseq.h>
#include <linux/syscalls.h>
+#include <linux/pkeys.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
#include <asm/exception.h>
#include <asm/cacheflush.h>
+#include <asm/gcs.h>
#include <asm/ucontext.h>
#include <asm/unistd.h>
#include <asm/fpsimd.h>
@@ -34,6 +36,15 @@
#include <asm/traps.h>
#include <asm/vdso.h>
+#ifdef CONFIG_ARM64_GCS
+#define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK)
+
+static bool gcs_signal_cap_valid(u64 addr, u64 val)
+{
+ return val == GCS_SIGNAL_CAP(addr);
+}
+#endif
+
/*
* Do a signal return; undo the signal stack. These are aligned to 128-bit.
*/
@@ -42,11 +53,6 @@ struct rt_sigframe {
struct ucontext uc;
};
-struct frame_record {
- u64 fp;
- u64 lr;
-};
-
struct rt_sigframe_user_layout {
struct rt_sigframe __user *sigframe;
struct frame_record __user *next_frame;
@@ -56,6 +62,7 @@ struct rt_sigframe_user_layout {
unsigned long fpsimd_offset;
unsigned long esr_offset;
+ unsigned long gcs_offset;
unsigned long sve_offset;
unsigned long tpidr2_offset;
unsigned long za_offset;
@@ -66,10 +73,62 @@ struct rt_sigframe_user_layout {
unsigned long end_offset;
};
-#define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
+/*
+ * Holds any EL0-controlled state that influences unprivileged memory accesses.
+ * This includes both accesses done in userspace and uaccess done in the kernel.
+ *
+ * This state needs to be carefully managed to ensure that it doesn't cause
+ * uaccess to fail when setting up the signal frame, and the signal handler
+ * itself also expects a well-defined state when entered.
+ */
+struct user_access_state {
+ u64 por_el0;
+};
+
#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
+/*
+ * Save the user access state into ua_state and reset it to disable any
+ * restrictions.
+ */
+static void save_reset_user_access_state(struct user_access_state *ua_state)
+{
+ if (system_supports_poe()) {
+ u64 por_enable_all = 0;
+
+ for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
+ por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
+
+ ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
+ write_sysreg_s(por_enable_all, SYS_POR_EL0);
+ /* Ensure that any subsequent uaccess observes the updated value */
+ isb();
+ }
+}
+
+/*
+ * Set the user access state for invoking the signal handler.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void set_handler_user_access_state(void)
+{
+ if (system_supports_poe())
+ write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
+}
+
+/*
+ * Restore the user access state to the values saved in ua_state.
+ *
+ * No uaccess should be done after that function is called.
+ */
+static void restore_user_access_state(const struct user_access_state *ua_state)
+{
+ if (system_supports_poe())
+ write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
+}
+
static void init_user_layout(struct rt_sigframe_user_layout *user)
{
const size_t reserved_size =
@@ -188,6 +247,8 @@ struct user_ctxs {
u32 fpmr_size;
struct poe_context __user *poe;
u32 poe_size;
+ struct gcs_context __user *gcs;
+ u32 gcs_size;
};
static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
@@ -261,18 +322,20 @@ static int restore_fpmr_context(struct user_ctxs *user)
return err;
}
-static int preserve_poe_context(struct poe_context __user *ctx)
+static int preserve_poe_context(struct poe_context __user *ctx,
+ const struct user_access_state *ua_state)
{
int err = 0;
__put_user_error(POE_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
- __put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err);
+ __put_user_error(ua_state->por_el0, &ctx->por_el0, err);
return err;
}
-static int restore_poe_context(struct user_ctxs *user)
+static int restore_poe_context(struct user_ctxs *user,
+ struct user_access_state *ua_state)
{
u64 por_el0;
int err = 0;
@@ -282,7 +345,7 @@ static int restore_poe_context(struct user_ctxs *user)
__get_user_error(por_el0, &(user->poe->por_el0), err);
if (!err)
- write_sysreg_s(por_el0, SYS_POR_EL0);
+ ua_state->por_el0 = por_el0;
return err;
}
@@ -633,6 +696,82 @@ extern int restore_zt_context(struct user_ctxs *user);
#endif /* ! CONFIG_ARM64_SME */
+#ifdef CONFIG_ARM64_GCS
+
+static int preserve_gcs_context(struct gcs_context __user *ctx)
+{
+ int err = 0;
+ u64 gcspr = read_sysreg_s(SYS_GCSPR_EL0);
+
+ /*
+ * If GCS is enabled we will add a cap token to the frame,
+ * include it in the GCSPR_EL0 we report to support stack
+ * switching via sigreturn if GCS is enabled. We do not allow
+ * enabling via sigreturn so the token is only relevant for
+ * threads with GCS enabled.
+ */
+ if (task_gcs_el0_enabled(current))
+ gcspr -= 8;
+
+ __put_user_error(GCS_MAGIC, &ctx->head.magic, err);
+ __put_user_error(sizeof(*ctx), &ctx->head.size, err);
+ __put_user_error(gcspr, &ctx->gcspr, err);
+ __put_user_error(0, &ctx->reserved, err);
+ __put_user_error(current->thread.gcs_el0_mode,
+ &ctx->features_enabled, err);
+
+ return err;
+}
+
+static int restore_gcs_context(struct user_ctxs *user)
+{
+ u64 gcspr, enabled;
+ int err = 0;
+
+ if (user->gcs_size != sizeof(*user->gcs))
+ return -EINVAL;
+
+ __get_user_error(gcspr, &user->gcs->gcspr, err);
+ __get_user_error(enabled, &user->gcs->features_enabled, err);
+ if (err)
+ return err;
+
+ /* Don't allow unknown modes */
+ if (enabled & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
+ return -EINVAL;
+
+ err = gcs_check_locked(current, enabled);
+ if (err != 0)
+ return err;
+
+ /* Don't allow enabling */
+ if (!task_gcs_el0_enabled(current) &&
+ (enabled & PR_SHADOW_STACK_ENABLE))
+ return -EINVAL;
+
+ /* If we are disabling disable everything */
+ if (!(enabled & PR_SHADOW_STACK_ENABLE))
+ enabled = 0;
+
+ current->thread.gcs_el0_mode = enabled;
+
+ /*
+ * We let userspace set GCSPR_EL0 to anything here, we will
+ * validate later in gcs_restore_signal().
+ */
+ write_sysreg_s(gcspr, SYS_GCSPR_EL0);
+
+ return 0;
+}
+
+#else /* ! CONFIG_ARM64_GCS */
+
+/* Turn any non-optimised out attempts to use these into a link error: */
+extern int preserve_gcs_context(void __user *ctx);
+extern int restore_gcs_context(struct user_ctxs *user);
+
+#endif /* ! CONFIG_ARM64_GCS */
+
static int parse_user_sigframe(struct user_ctxs *user,
struct rt_sigframe __user *sf)
{
@@ -651,6 +790,7 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->zt = NULL;
user->fpmr = NULL;
user->poe = NULL;
+ user->gcs = NULL;
if (!IS_ALIGNED((unsigned long)base, 16))
goto invalid;
@@ -767,6 +907,17 @@ static int parse_user_sigframe(struct user_ctxs *user,
user->fpmr_size = size;
break;
+ case GCS_MAGIC:
+ if (!system_supports_gcs())
+ goto invalid;
+
+ if (user->gcs)
+ goto invalid;
+
+ user->gcs = (struct gcs_context __user *)head;
+ user->gcs_size = size;
+ break;
+
case EXTRA_MAGIC:
if (have_extra_context)
goto invalid;
@@ -850,7 +1001,8 @@ invalid:
}
static int restore_sigframe(struct pt_regs *regs,
- struct rt_sigframe __user *sf)
+ struct rt_sigframe __user *sf,
+ struct user_access_state *ua_state)
{
sigset_t set;
int i, err;
@@ -886,6 +1038,9 @@ static int restore_sigframe(struct pt_regs *regs,
err = restore_fpsimd_context(&user);
}
+ if (err == 0 && system_supports_gcs() && user.gcs)
+ err = restore_gcs_context(&user);
+
if (err == 0 && system_supports_tpidr2() && user.tpidr2)
err = restore_tpidr2_context(&user);
@@ -899,15 +1054,68 @@ static int restore_sigframe(struct pt_regs *regs,
err = restore_zt_context(&user);
if (err == 0 && system_supports_poe() && user.poe)
- err = restore_poe_context(&user);
+ err = restore_poe_context(&user, ua_state);
return err;
}
+#ifdef CONFIG_ARM64_GCS
+static int gcs_restore_signal(void)
+{
+ unsigned long __user *gcspr_el0;
+ u64 cap;
+ int ret;
+
+ if (!system_supports_gcs())
+ return 0;
+
+ if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE))
+ return 0;
+
+ gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0);
+
+ /*
+ * Ensure that any changes to the GCS done via GCS operations
+ * are visible to the normal reads we do to validate the
+ * token.
+ */
+ gcsb_dsync();
+
+ /*
+ * GCSPR_EL0 should be pointing at a capped GCS, read the cap.
+ * We don't enforce that this is in a GCS page, if it is not
+ * then faults will be generated on GCS operations - the main
+ * concern is to protect GCS pages.
+ */
+ ret = copy_from_user(&cap, gcspr_el0, sizeof(cap));
+ if (ret)
+ return -EFAULT;
+
+ /*
+ * Check that the cap is the actual GCS before replacing it.
+ */
+ if (!gcs_signal_cap_valid((u64)gcspr_el0, cap))
+ return -EINVAL;
+
+ /* Invalidate the token to prevent reuse */
+ put_user_gcs(0, (__user void*)gcspr_el0, &ret);
+ if (ret != 0)
+ return -EFAULT;
+
+ write_sysreg_s(gcspr_el0 + 1, SYS_GCSPR_EL0);
+
+ return 0;
+}
+
+#else
+static int gcs_restore_signal(void) { return 0; }
+#endif
+
SYSCALL_DEFINE0(rt_sigreturn)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
+ struct user_access_state ua_state;
/* Always make any pending restarted system calls return -EINTR */
current->restart_block.fn = do_no_restart_syscall;
@@ -924,12 +1132,17 @@ SYSCALL_DEFINE0(rt_sigreturn)
if (!access_ok(frame, sizeof (*frame)))
goto badframe;
- if (restore_sigframe(regs, frame))
+ if (restore_sigframe(regs, frame, &ua_state))
+ goto badframe;
+
+ if (gcs_restore_signal())
goto badframe;
if (restore_altstack(&frame->uc.uc_stack))
goto badframe;
+ restore_user_access_state(&ua_state);
+
return regs->regs[0];
badframe:
@@ -964,6 +1177,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
return err;
}
+#ifdef CONFIG_ARM64_GCS
+ if (system_supports_gcs() && (add_all || current->thread.gcspr_el0)) {
+ err = sigframe_alloc(user, &user->gcs_offset,
+ sizeof(struct gcs_context));
+ if (err)
+ return err;
+ }
+#endif
+
if (system_supports_sve() || system_supports_sme()) {
unsigned int vq = 0;
@@ -1035,7 +1257,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
}
static int setup_sigframe(struct rt_sigframe_user_layout *user,
- struct pt_regs *regs, sigset_t *set)
+ struct pt_regs *regs, sigset_t *set,
+ const struct user_access_state *ua_state)
{
int i, err = 0;
struct rt_sigframe __user *sf = user->sigframe;
@@ -1071,6 +1294,12 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
__put_user_error(current->thread.fault_code, &esr_ctx->esr, err);
}
+ if (system_supports_gcs() && err == 0 && user->gcs_offset) {
+ struct gcs_context __user *gcs_ctx =
+ apply_user_offset(user, user->gcs_offset);
+ err |= preserve_gcs_context(gcs_ctx);
+ }
+
/* Scalable Vector Extension state (including streaming), if present */
if ((system_supports_sve() || system_supports_sme()) &&
err == 0 && user->sve_offset) {
@@ -1093,14 +1322,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
err |= preserve_fpmr_context(fpmr_ctx);
}
- if (system_supports_poe() && err == 0 && user->poe_offset) {
+ if (system_supports_poe() && err == 0) {
struct poe_context __user *poe_ctx =
apply_user_offset(user, user->poe_offset);
- err |= preserve_poe_context(poe_ctx);
+ err |= preserve_poe_context(poe_ctx, ua_state);
}
-
/* ZA state if present */
if (system_supports_sme() && err == 0 && user->za_offset) {
struct za_context __user *za_ctx =
@@ -1189,7 +1417,48 @@ static int get_sigframe(struct rt_sigframe_user_layout *user,
return 0;
}
-static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
+#ifdef CONFIG_ARM64_GCS
+
+static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
+{
+ unsigned long __user *gcspr_el0;
+ int ret = 0;
+
+ if (!system_supports_gcs())
+ return 0;
+
+ if (!task_gcs_el0_enabled(current))
+ return 0;
+
+ /*
+ * We are entering a signal handler, current register state is
+ * active.
+ */
+ gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0);
+
+ /*
+ * Push a cap and the GCS entry for the trampoline onto the GCS.
+ */
+ put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret);
+ put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret);
+ if (ret != 0)
+ return ret;
+
+ gcspr_el0 -= 2;
+ write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0);
+
+ return 0;
+}
+#else
+
+static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig)
+{
+ return 0;
+}
+
+#endif
+
+static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
struct rt_sigframe_user_layout *user, int usig)
{
__sigrestore_t sigtramp;
@@ -1197,7 +1466,7 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
regs->regs[0] = usig;
regs->sp = (unsigned long)user->sigframe;
regs->regs[29] = (unsigned long)&user->next_frame->fp;
- regs->pc = (unsigned long)ka->sa.sa_handler;
+ regs->pc = (unsigned long)ksig->ka.sa.sa_handler;
/*
* Signal delivery is a (wacky) indirect function call in
@@ -1237,15 +1506,14 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
sme_smstop();
}
- if (system_supports_poe())
- write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
-
- if (ka->sa.sa_flags & SA_RESTORER)
- sigtramp = ka->sa.sa_restorer;
+ if (ksig->ka.sa.sa_flags & SA_RESTORER)
+ sigtramp = ksig->ka.sa.sa_restorer;
else
sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp);
regs->regs[30] = (unsigned long)sigtramp;
+
+ return gcs_signal_entry(sigtramp, ksig);
}
static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
@@ -1253,6 +1521,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
{
struct rt_sigframe_user_layout user;
struct rt_sigframe __user *frame;
+ struct user_access_state ua_state;
int err = 0;
fpsimd_signal_preserve_current_state();
@@ -1260,15 +1529,16 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
if (get_sigframe(&user, ksig, regs))
return 1;
+ save_reset_user_access_state(&ua_state);
frame = user.sigframe;
__put_user_error(0, &frame->uc.uc_flags, err);
__put_user_error(NULL, &frame->uc.uc_link, err);
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
- err |= setup_sigframe(&user, regs, set);
+ err |= setup_sigframe(&user, regs, set, &ua_state);
if (err == 0) {
- setup_return(regs, &ksig->ka, &user, usig);
+ err = setup_return(regs, ksig, &user, usig);
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
err |= copy_siginfo_to_user(&frame->info, &ksig->info);
regs->regs[1] = (unsigned long)&frame->info;
@@ -1276,6 +1546,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
}
}
+ if (err == 0)
+ set_handler_user_access_state();
+ else
+ restore_user_access_state(&ua_state);
+
return err;
}
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index 487381164ff6..2def9d0dd3dd 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -7,48 +7,19 @@
#include <asm/asm-offsets.h>
#include <asm/assembler.h>
-#include <asm/thread_info.h>
-
-/*
- * If we have SMCCC v1.3 and (as is likely) no SVE state in
- * the registers then set the SMCCC hint bit to say there's no
- * need to preserve it. Do this by directly adjusting the SMCCC
- * function value which is already stored in x0 ready to be called.
- */
-SYM_FUNC_START(__arm_smccc_sve_check)
-
- ldr_l x16, smccc_has_sve_hint
- cbz x16, 2f
-
- get_current_task x16
- ldr x16, [x16, #TSK_TI_FLAGS]
- tbnz x16, #TIF_FOREIGN_FPSTATE, 1f // Any live FP state?
- tbnz x16, #TIF_SVE, 2f // Does that state include SVE?
-
-1: orr x0, x0, ARM_SMCCC_1_3_SVE_HINT
-
-2: ret
-SYM_FUNC_END(__arm_smccc_sve_check)
-EXPORT_SYMBOL(__arm_smccc_sve_check)
.macro SMCCC instr
- stp x29, x30, [sp, #-16]!
- mov x29, sp
-alternative_if ARM64_SVE
- bl __arm_smccc_sve_check
-alternative_else_nop_endif
\instr #0
- ldr x4, [sp, #16]
+ ldr x4, [sp]
stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
- ldr x4, [sp, #24]
+ ldr x4, [sp, #8]
cbz x4, 1f /* no quirk structure */
ldr x9, [x4, #ARM_SMCCC_QUIRK_ID_OFFS]
cmp x9, #ARM_SMCCC_QUIRK_QCOM_A6
b.ne 1f
str x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS]
-1: ldp x29, x30, [sp], #16
- ret
+1: ret
.endm
/*
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 2729faaee4b4..caef85462acb 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -20,6 +20,23 @@
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
+enum kunwind_source {
+ KUNWIND_SOURCE_UNKNOWN,
+ KUNWIND_SOURCE_FRAME,
+ KUNWIND_SOURCE_CALLER,
+ KUNWIND_SOURCE_TASK,
+ KUNWIND_SOURCE_REGS_PC,
+ KUNWIND_SOURCE_REGS_LR,
+};
+
+union unwind_flags {
+ unsigned long all;
+ struct {
+ unsigned long fgraph : 1,
+ kretprobe : 1;
+ };
+};
+
/*
* Kernel unwind state
*
@@ -37,6 +54,9 @@ struct kunwind_state {
#ifdef CONFIG_KRETPROBES
struct llist_node *kr_cur;
#endif
+ enum kunwind_source source;
+ union unwind_flags flags;
+ struct pt_regs *regs;
};
static __always_inline void
@@ -45,6 +65,9 @@ kunwind_init(struct kunwind_state *state,
{
unwind_init_common(&state->common);
state->task = task;
+ state->source = KUNWIND_SOURCE_UNKNOWN;
+ state->flags.all = 0;
+ state->regs = NULL;
}
/*
@@ -60,8 +83,10 @@ kunwind_init_from_regs(struct kunwind_state *state,
{
kunwind_init(state, current);
+ state->regs = regs;
state->common.fp = regs->regs[29];
state->common.pc = regs->pc;
+ state->source = KUNWIND_SOURCE_REGS_PC;
}
/*
@@ -79,6 +104,7 @@ kunwind_init_from_caller(struct kunwind_state *state)
state->common.fp = (unsigned long)__builtin_frame_address(1);
state->common.pc = (unsigned long)__builtin_return_address(0);
+ state->source = KUNWIND_SOURCE_CALLER;
}
/*
@@ -99,6 +125,7 @@ kunwind_init_from_task(struct kunwind_state *state,
state->common.fp = thread_saved_fp(task);
state->common.pc = thread_saved_pc(task);
+ state->source = KUNWIND_SOURCE_TASK;
}
static __always_inline int
@@ -114,6 +141,7 @@ kunwind_recover_return_address(struct kunwind_state *state)
if (WARN_ON_ONCE(state->common.pc == orig_pc))
return -EINVAL;
state->common.pc = orig_pc;
+ state->flags.fgraph = 1;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -124,12 +152,110 @@ kunwind_recover_return_address(struct kunwind_state *state)
(void *)state->common.fp,
&state->kr_cur);
state->common.pc = orig_pc;
+ state->flags.kretprobe = 1;
}
#endif /* CONFIG_KRETPROBES */
return 0;
}
+static __always_inline
+int kunwind_next_regs_pc(struct kunwind_state *state)
+{
+ struct stack_info *info;
+ unsigned long fp = state->common.fp;
+ struct pt_regs *regs;
+
+ regs = container_of((u64 *)fp, struct pt_regs, stackframe.record.fp);
+
+ info = unwind_find_stack(&state->common, (unsigned long)regs, sizeof(*regs));
+ if (!info)
+ return -EINVAL;
+
+ unwind_consume_stack(&state->common, info, (unsigned long)regs,
+ sizeof(*regs));
+
+ state->regs = regs;
+ state->common.pc = regs->pc;
+ state->common.fp = regs->regs[29];
+ state->source = KUNWIND_SOURCE_REGS_PC;
+ return 0;
+}
+
+static __always_inline int
+kunwind_next_regs_lr(struct kunwind_state *state)
+{
+ /*
+ * The stack for the regs was consumed by kunwind_next_regs_pc(), so we
+ * cannot consume that again here, but we know the regs are safe to
+ * access.
+ */
+ state->common.pc = state->regs->regs[30];
+ state->common.fp = state->regs->regs[29];
+ state->regs = NULL;
+ state->source = KUNWIND_SOURCE_REGS_LR;
+
+ return 0;
+}
+
+static __always_inline int
+kunwind_next_frame_record_meta(struct kunwind_state *state)
+{
+ struct task_struct *tsk = state->task;
+ unsigned long fp = state->common.fp;
+ struct frame_record_meta *meta;
+ struct stack_info *info;
+
+ info = unwind_find_stack(&state->common, fp, sizeof(*meta));
+ if (!info)
+ return -EINVAL;
+
+ meta = (struct frame_record_meta *)fp;
+ switch (READ_ONCE(meta->type)) {
+ case FRAME_META_TYPE_FINAL:
+ if (meta == &task_pt_regs(tsk)->stackframe)
+ return -ENOENT;
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ case FRAME_META_TYPE_PT_REGS:
+ return kunwind_next_regs_pc(state);
+ default:
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+}
+
+static __always_inline int
+kunwind_next_frame_record(struct kunwind_state *state)
+{
+ unsigned long fp = state->common.fp;
+ struct frame_record *record;
+ struct stack_info *info;
+ unsigned long new_fp, new_pc;
+
+ if (fp & 0x7)
+ return -EINVAL;
+
+ info = unwind_find_stack(&state->common, fp, sizeof(*record));
+ if (!info)
+ return -EINVAL;
+
+ record = (struct frame_record *)fp;
+ new_fp = READ_ONCE(record->fp);
+ new_pc = READ_ONCE(record->lr);
+
+ if (!new_fp && !new_pc)
+ return kunwind_next_frame_record_meta(state);
+
+ unwind_consume_stack(&state->common, info, fp, sizeof(*record));
+
+ state->common.fp = new_fp;
+ state->common.pc = new_pc;
+ state->source = KUNWIND_SOURCE_FRAME;
+
+ return 0;
+}
+
/*
* Unwind from one frame record (A) to the next frame record (B).
*
@@ -140,15 +266,24 @@ kunwind_recover_return_address(struct kunwind_state *state)
static __always_inline int
kunwind_next(struct kunwind_state *state)
{
- struct task_struct *tsk = state->task;
- unsigned long fp = state->common.fp;
int err;
- /* Final frame; nothing to unwind */
- if (fp == (unsigned long)task_pt_regs(tsk)->stackframe)
- return -ENOENT;
+ state->flags.all = 0;
+
+ switch (state->source) {
+ case KUNWIND_SOURCE_FRAME:
+ case KUNWIND_SOURCE_CALLER:
+ case KUNWIND_SOURCE_TASK:
+ case KUNWIND_SOURCE_REGS_LR:
+ err = kunwind_next_frame_record(state);
+ break;
+ case KUNWIND_SOURCE_REGS_PC:
+ err = kunwind_next_regs_lr(state);
+ break;
+ default:
+ err = -EINVAL;
+ }
- err = unwind_next_frame_record(&state->common);
if (err)
return err;
@@ -294,10 +429,33 @@ noinline noinstr void arch_bpf_stack_walk(bool (*consume_entry)(void *cookie, u6
kunwind_stack_walk(arch_bpf_unwind_consume_entry, &data, current, NULL);
}
-static bool dump_backtrace_entry(void *arg, unsigned long where)
+static const char *state_source_string(const struct kunwind_state *state)
{
+ switch (state->source) {
+ case KUNWIND_SOURCE_FRAME: return NULL;
+ case KUNWIND_SOURCE_CALLER: return "C";
+ case KUNWIND_SOURCE_TASK: return "T";
+ case KUNWIND_SOURCE_REGS_PC: return "P";
+ case KUNWIND_SOURCE_REGS_LR: return "L";
+ default: return "U";
+ }
+}
+
+static bool dump_backtrace_entry(const struct kunwind_state *state, void *arg)
+{
+ const char *source = state_source_string(state);
+ union unwind_flags flags = state->flags;
+ bool has_info = source || flags.all;
char *loglvl = arg;
- printk("%s %pSb\n", loglvl, (void *)where);
+
+ printk("%s %pSb%s%s%s%s%s\n", loglvl,
+ (void *)state->common.pc,
+ has_info ? " (" : "",
+ source ? source : "",
+ flags.fgraph ? "F" : "",
+ flags.kretprobe ? "K" : "",
+ has_info ? ")" : "");
+
return true;
}
@@ -316,7 +474,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk,
return;
printk("%sCall trace:\n", loglvl);
- arch_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs);
+ kunwind_stack_walk(dump_backtrace_entry, (void *)loglvl, tsk, regs);
put_task_stack(tsk);
}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 563cbce11126..ee318f6df647 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -506,6 +506,16 @@ void do_el1_bti(struct pt_regs *regs, unsigned long esr)
die("Oops - BTI", regs, esr);
}
+void do_el0_gcs(struct pt_regs *regs, unsigned long esr)
+{
+ force_signal_inject(SIGSEGV, SEGV_CPERR, regs->pc, 0);
+}
+
+void do_el1_gcs(struct pt_regs *regs, unsigned long esr)
+{
+ die("Oops - GCS", regs, esr);
+}
+
void do_el0_fpac(struct pt_regs *regs, unsigned long esr)
{
force_signal_inject(SIGILL, ILL_ILLOPN, regs->pc, esr);
@@ -531,6 +541,13 @@ void do_el0_mops(struct pt_regs *regs, unsigned long esr)
user_fastforward_single_step(current);
}
+void do_el1_mops(struct pt_regs *regs, unsigned long esr)
+{
+ arm64_mops_reset_regs(&regs->user_regs, esr);
+
+ kernel_fastforward_single_step(regs);
+}
+
#define __user_cache_maint(insn, address, res) \
if (address >= TASK_SIZE_MAX) { \
res = -EFAULT; \
@@ -852,6 +869,7 @@ static const char *esr_class_str[] = {
[ESR_ELx_EC_MOPS] = "MOPS",
[ESR_ELx_EC_FP_EXC32] = "FP (AArch32)",
[ESR_ELx_EC_FP_EXC64] = "FP (AArch64)",
+ [ESR_ELx_EC_GCS] = "Guarded Control Stack",
[ESR_ELx_EC_SERROR] = "SError",
[ESR_ELx_EC_BREAKPT_LOW] = "Breakpoint (lower EL)",
[ESR_ELx_EC_BREAKPT_CUR] = "Breakpoint (current EL)",
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 706c9c3a7a50..e8ed8e5b713b 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -19,7 +19,6 @@
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/time_namespace.h>
-#include <linux/timekeeper_internal.h>
#include <linux/vmalloc.h>
#include <vdso/datapage.h>
#include <vdso/helpers.h>
@@ -39,8 +38,6 @@ struct vdso_abi_info {
const char *vdso_code_start;
const char *vdso_code_end;
unsigned long vdso_pages;
- /* Data Mapping */
- struct vm_special_mapping *dm;
/* Code Mapping */
struct vm_special_mapping *cm;
};
@@ -113,6 +110,8 @@ struct vdso_data *arch_get_vdso_data(void *vvar_page)
return (struct vdso_data *)(vvar_page);
}
+static const struct vm_special_mapping vvar_map;
+
/*
* The vvar mapping contains data for a specific time namespace, so when a task
* changes namespace we must unmap its vvar data for the old namespace.
@@ -129,12 +128,8 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
mmap_read_lock(mm);
for_each_vma(vmi, vma) {
- if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA64].dm))
- zap_vma_pages(vma);
-#ifdef CONFIG_COMPAT_VDSO
- if (vma_is_special_mapping(vma, vdso_info[VDSO_ABI_AA32].dm))
+ if (vma_is_special_mapping(vma, &vvar_map))
zap_vma_pages(vma);
-#endif
}
mmap_read_unlock(mm);
@@ -176,6 +171,11 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
return vmf_insert_pfn(vma, vmf->address, pfn);
}
+static const struct vm_special_mapping vvar_map = {
+ .name = "[vvar]",
+ .fault = vvar_fault,
+};
+
static int __setup_additional_pages(enum vdso_abi abi,
struct mm_struct *mm,
struct linux_binprm *bprm,
@@ -199,7 +199,7 @@ static int __setup_additional_pages(enum vdso_abi abi,
ret = _install_special_mapping(mm, vdso_base, VVAR_NR_PAGES * PAGE_SIZE,
VM_READ|VM_MAYREAD|VM_PFNMAP,
- vdso_info[abi].dm);
+ &vvar_map);
if (IS_ERR(ret))
goto up_fail;
@@ -229,7 +229,6 @@ up_fail:
enum aarch32_map {
AA32_MAP_VECTORS, /* kuser helpers */
AA32_MAP_SIGPAGE,
- AA32_MAP_VVAR,
AA32_MAP_VDSO,
};
@@ -254,10 +253,6 @@ static struct vm_special_mapping aarch32_vdso_maps[] = {
.pages = &aarch32_sig_page,
.mremap = aarch32_sigpage_mremap,
},
- [AA32_MAP_VVAR] = {
- .name = "[vvar]",
- .fault = vvar_fault,
- },
[AA32_MAP_VDSO] = {
.name = "[vdso]",
.mremap = vdso_mremap,
@@ -307,7 +302,6 @@ static int __init __aarch32_alloc_vdso_pages(void)
if (!IS_ENABLED(CONFIG_COMPAT_VDSO))
return 0;
- vdso_info[VDSO_ABI_AA32].dm = &aarch32_vdso_maps[AA32_MAP_VVAR];
vdso_info[VDSO_ABI_AA32].cm = &aarch32_vdso_maps[AA32_MAP_VDSO];
return __vdso_init(VDSO_ABI_AA32);
@@ -402,26 +396,14 @@ out:
}
#endif /* CONFIG_COMPAT */
-enum aarch64_map {
- AA64_MAP_VVAR,
- AA64_MAP_VDSO,
-};
-
-static struct vm_special_mapping aarch64_vdso_maps[] __ro_after_init = {
- [AA64_MAP_VVAR] = {
- .name = "[vvar]",
- .fault = vvar_fault,
- },
- [AA64_MAP_VDSO] = {
- .name = "[vdso]",
- .mremap = vdso_mremap,
- },
+static struct vm_special_mapping aarch64_vdso_map __ro_after_init = {
+ .name = "[vdso]",
+ .mremap = vdso_mremap,
};
static int __init vdso_init(void)
{
- vdso_info[VDSO_ABI_AA64].dm = &aarch64_vdso_maps[AA64_MAP_VVAR];
- vdso_info[VDSO_ABI_AA64].cm = &aarch64_vdso_maps[AA64_MAP_VDSO];
+ vdso_info[VDSO_ABI_AA64].cm = &aarch64_vdso_map;
return __vdso_init(VDSO_ABI_AA64);
}
diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S
index f204a9ddc833..4ec32e86a8da 100644
--- a/arch/arm64/kernel/vdso/vdso.lds.S
+++ b/arch/arm64/kernel/vdso/vdso.lds.S
@@ -25,7 +25,7 @@ SECTIONS
#ifdef CONFIG_TIME_NS
PROVIDE(_timens_data = _vdso_data + PAGE_SIZE);
#endif
- . = VDSO_LBASE + SIZEOF_HEADERS;
+ . = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
diff --git a/arch/arm64/kernel/vdso32/vdso.lds.S b/arch/arm64/kernel/vdso32/vdso.lds.S
index 8d95d7d35057..732702a187e9 100644
--- a/arch/arm64/kernel/vdso32/vdso.lds.S
+++ b/arch/arm64/kernel/vdso32/vdso.lds.S
@@ -22,7 +22,7 @@ SECTIONS
#ifdef CONFIG_TIME_NS
PROVIDE_HIDDEN(_timens_data = _vdso_data + PAGE_SIZE);
#endif
- . = VDSO_LBASE + SIZEOF_HEADERS;
+ . = SIZEOF_HEADERS;
.hash : { *(.hash) } :text
.gnu.hash : { *(.gnu.hash) }
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 58d89d997d05..f84c71f04d9e 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -287,6 +287,9 @@ SECTIONS
__initdata_end = .;
__init_end = .;
+ .data.rel.ro : { *(.data.rel.ro) }
+ ASSERT(SIZEOF(.data.rel.ro) == 0, "Unexpected RELRO detected!")
+
_data = .;
_sdata = .;
RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
@@ -343,9 +346,6 @@ SECTIONS
*(.plt) *(.plt.*) *(.iplt) *(.igot .igot.plt)
}
ASSERT(SIZEOF(.plt) == 0, "Unexpected run-time procedure linkages detected!")
-
- .data.rel.ro : { *(.data.rel.ro) }
- ASSERT(SIZEOF(.data.rel.ro) == 0, "Unexpected RELRO detected!")
}
#include "image-vars.h"
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a0d01c46e408..48cafb65d6ac 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
static int check_vcpu_requests(struct kvm_vcpu *vcpu)
{
if (kvm_request_pending(vcpu)) {
+ if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+ return -EIO;
+
if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
kvm_vcpu_sleep(vcpu);
@@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
if (kvm_dirty_ring_check_request(vcpu))
return 0;
+
+ check_nested_vcpu_requests(vcpu);
}
return 1;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 962f985977c2..e738a353b20e 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -1055,6 +1055,7 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
void *maddr;
unsigned long num_tags;
struct page *page;
+ struct folio *folio;
if (is_error_noslot_pfn(pfn)) {
ret = -EFAULT;
@@ -1068,10 +1069,13 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
ret = -EFAULT;
goto out;
}
+ folio = page_folio(page);
maddr = page_address(page);
if (!write) {
- if (page_mte_tagged(page))
+ if ((folio_test_hugetlb(folio) &&
+ folio_test_hugetlb_mte_tagged(folio)) ||
+ page_mte_tagged(page))
num_tags = mte_copy_tags_to_user(tags, maddr,
MTE_GRANULES_PER_PAGE);
else
@@ -1085,14 +1089,20 @@ int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
* __set_ptes() in the VMM but still overriding the
* tags, hence ignoring the return value.
*/
- try_page_mte_tagging(page);
+ if (folio_test_hugetlb(folio))
+ folio_try_hugetlb_mte_tagging(folio);
+ else
+ try_page_mte_tagging(page);
num_tags = mte_copy_tags_from_user(maddr, tags,
MTE_GRANULES_PER_PAGE);
/* uaccess failed, don't leave stale tags */
if (num_tags != MTE_GRANULES_PER_PAGE)
mte_clear_page_tags(maddr);
- set_page_mte_tagged(page);
+ if (folio_test_hugetlb(folio))
+ folio_set_hugetlb_mte_tagged(folio);
+ else
+ set_page_mte_tagged(page);
kvm_release_pfn_dirty(pfn);
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 46d52e8a3df3..5310fe1da616 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -338,7 +338,7 @@ static inline void __hyp_sve_save_host(void)
struct cpu_sve_state *sve_state = *host_data_ptr(sve_state);
sve_state->zcr_el1 = read_sysreg_el1(SYS_ZCR);
- write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+ write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2);
__sve_save_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
&sve_state->fpsr,
true);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 401af1835be6..fc1866226067 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -24,28 +24,25 @@
.align 11
SYM_CODE_START(__kvm_hyp_init)
- ventry __invalid // Synchronous EL2t
- ventry __invalid // IRQ EL2t
- ventry __invalid // FIQ EL2t
- ventry __invalid // Error EL2t
+ ventry . // Synchronous EL2t
+ ventry . // IRQ EL2t
+ ventry . // FIQ EL2t
+ ventry . // Error EL2t
- ventry __invalid // Synchronous EL2h
- ventry __invalid // IRQ EL2h
- ventry __invalid // FIQ EL2h
- ventry __invalid // Error EL2h
+ ventry . // Synchronous EL2h
+ ventry . // IRQ EL2h
+ ventry . // FIQ EL2h
+ ventry . // Error EL2h
ventry __do_hyp_init // Synchronous 64-bit EL1
- ventry __invalid // IRQ 64-bit EL1
- ventry __invalid // FIQ 64-bit EL1
- ventry __invalid // Error 64-bit EL1
+ ventry . // IRQ 64-bit EL1
+ ventry . // FIQ 64-bit EL1
+ ventry . // Error 64-bit EL1
- ventry __invalid // Synchronous 32-bit EL1
- ventry __invalid // IRQ 32-bit EL1
- ventry __invalid // FIQ 32-bit EL1
- ventry __invalid // Error 32-bit EL1
-
-__invalid:
- b .
+ ventry . // Synchronous 32-bit EL1
+ ventry . // IRQ 32-bit EL1
+ ventry . // FIQ 32-bit EL1
+ ventry . // Error 32-bit EL1
/*
* Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
@@ -76,6 +73,13 @@ __do_hyp_init:
eret
SYM_CODE_END(__kvm_hyp_init)
+SYM_CODE_START_LOCAL(__kvm_init_el2_state)
+ /* Initialize EL2 CPU state to sane values. */
+ init_el2_state // Clobbers x0..x2
+ finalise_el2_state
+ ret
+SYM_CODE_END(__kvm_init_el2_state)
+
/*
* Initialize the hypervisor in EL2.
*
@@ -102,9 +106,12 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
// TPIDR_EL2 is used to preserve x0 across the macro maze...
isb
msr tpidr_el2, x0
- init_el2_state
- finalise_el2_state
+ str lr, [x0, #NVHE_INIT_TMP]
+
+ bl __kvm_init_el2_state
+
mrs x0, tpidr_el2
+ ldr lr, [x0, #NVHE_INIT_TMP]
1:
ldr x1, [x0, #NVHE_INIT_TPIDR_EL2]
@@ -199,9 +206,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
2: msr SPsel, #1 // We want to use SP_EL{1,2}
- /* Initialize EL2 CPU state to sane values. */
- init_el2_state // Clobbers x0..x2
- finalise_el2_state
+ bl __kvm_init_el2_state
+
__init_el2_nvhe_prepare_eret
/* Enable MMU, set vectors and stack. */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 87692b566d90..fefc89209f9e 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -33,7 +33,7 @@ static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
*/
sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2);
__sve_save_state(vcpu_sve_pffr(vcpu), &vcpu->arch.ctxt.fp_regs.fpsr, true);
- write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+ write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2);
}
static void __hyp_sve_restore_host(void)
@@ -45,10 +45,11 @@ static void __hyp_sve_restore_host(void)
* the host. The layout of the data when saving the sve state depends
* on the VL, so use a consistent (i.e., the maximum) host VL.
*
- * Setting ZCR_EL2 to ZCR_ELx_LEN_MASK sets the effective length
- * supported by the system (or limited at EL3).
+ * Note that this constrains the PE to the maximum shared VL
+ * that was discovered, if we wish to use larger VLs this will
+ * need to be revisited.
*/
- write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+ write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2);
__sve_restore_state(sve_state->sve_regs + sve_ffr_offset(kvm_host_sve_max_vl),
&sve_state->fpsr,
true);
@@ -488,7 +489,8 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
case ESR_ELx_EC_SVE:
cpacr_clear_set(0, CPACR_ELx_ZEN);
isb();
- sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, SYS_ZCR_EL2);
+ sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1,
+ SYS_ZCR_EL2);
break;
case ESR_ELx_EC_IABT_LOW:
case ESR_ELx_EC_DABT_LOW:
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 187a5f4d56c0..077d4098548d 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -574,12 +574,14 @@ int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu,
unlock:
hyp_spin_unlock(&vm_table_lock);
- if (ret)
+ if (ret) {
unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu));
+ return ret;
+ }
hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu);
- return ret;
+ return 0;
}
static void
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index 5763d979d8ca..ee6573befb81 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
* to the guest, and hide SSBS so that the
* guest stays protected.
*/
- if (cpus_have_final_cap(ARM64_SSBS))
+ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
break;
fallthrough;
case SPECTRE_UNAFFECTED:
@@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
* Convert the workaround level into an easy-to-compare number, where higher
* values mean better protection.
*/
-static int get_kernel_wa_level(u64 regid)
+static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
{
switch (regid) {
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
@@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
* don't have any FW mitigation if SSBS is there at
* all times.
*/
- if (cpus_have_final_cap(ARM64_SSBS))
+ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
fallthrough;
case SPECTRE_UNAFFECTED:
@@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
- val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
+ val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
break;
case KVM_REG_ARM_STD_BMAP:
val = READ_ONCE(smccc_feat->std_bmap);
@@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
return -EINVAL;
- if (get_kernel_wa_level(reg->id) < val)
+ if (get_kernel_wa_level(vcpu, reg->id) < val)
return -EINVAL;
return 0;
@@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
* We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
* other way around.
*/
- if (get_kernel_wa_level(reg->id) < wa_level)
+ if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
return -EINVAL;
return 0;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index a509b63bd4dd..56d9a7f414fe 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
may_block));
}
-void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
+void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
+ u64 size, bool may_block)
{
- __unmap_stage2_range(mmu, start, size, true);
+ __unmap_stage2_range(mmu, start, size, may_block);
}
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
@@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
if (!(vma->vm_flags & VM_PFNMAP)) {
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
- kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
+ kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
}
hva = vm_end;
} while (hva < reg_end);
@@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
kvm_for_each_memslot(memslot, bkt, slots)
stage2_unmap_memslot(kvm, memslot);
- kvm_nested_s2_unmap(kvm);
+ kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
mmap_read_unlock(current->mm);
@@ -1401,10 +1402,21 @@ static void sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
{
unsigned long i, nr_pages = size >> PAGE_SHIFT;
struct page *page = pfn_to_page(pfn);
+ struct folio *folio = page_folio(page);
if (!kvm_has_mte(kvm))
return;
+ if (folio_test_hugetlb(folio)) {
+ /* Hugetlb has MTE flags set on head page only */
+ if (folio_try_hugetlb_mte_tagging(folio)) {
+ for (i = 0; i < nr_pages; i++, page++)
+ mte_clear_page_tags(page_address(page));
+ folio_set_hugetlb_mte_tagged(folio);
+ }
+ return;
+ }
+
for (i = 0; i < nr_pages; i++, page++) {
if (try_page_mte_tagging(page)) {
mte_clear_page_tags(page_address(page));
@@ -1912,7 +1924,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
(range->end - range->start) << PAGE_SHIFT,
range->may_block);
- kvm_nested_s2_unmap(kvm);
+ kvm_nested_s2_unmap(kvm, range->may_block);
return false;
}
@@ -2179,8 +2191,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
phys_addr_t size = slot->npages << PAGE_SHIFT;
write_lock(&kvm->mmu_lock);
- kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
- kvm_nested_s2_unmap(kvm);
+ kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
+ kvm_nested_s2_unmap(kvm, true);
write_unlock(&kvm->mmu_lock);
}
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index f9e30dd34c7a..c4b17d90fc49 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -632,9 +632,9 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
/* Set the scene for the next search */
kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
- /* Clear the old state */
+ /* Make sure we don't forget to do the laundry */
if (kvm_s2_mmu_valid(s2_mmu))
- kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
+ s2_mmu->pending_unmap = true;
/*
* The virtual VMID (modulo CnP) will be used as a key when matching
@@ -650,6 +650,16 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
out:
atomic_inc(&s2_mmu->refcnt);
+
+ /*
+ * Set the vCPU request to perform an unmap, even if the pending unmap
+ * originates from another vCPU. This guarantees that the MMU has been
+ * completely unmapped before any vCPU actually uses it, and allows
+ * multiple vCPUs to lend a hand with completing the unmap.
+ */
+ if (s2_mmu->pending_unmap)
+ kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
+
return s2_mmu;
}
@@ -663,6 +673,13 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
{
+ /*
+ * The vCPU kept its reference on the MMU after the last put, keep
+ * rolling with it.
+ */
+ if (vcpu->arch.hw_mmu)
+ return;
+
if (is_hyp_ctxt(vcpu)) {
vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
} else {
@@ -674,10 +691,18 @@ void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
{
- if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
+ /*
+ * Keep a reference on the associated stage-2 MMU if the vCPU is
+ * scheduling out and not in WFI emulation, suggesting it is likely to
+ * reuse the MMU sometime soon.
+ */
+ if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
+ return;
+
+ if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
atomic_dec(&vcpu->arch.hw_mmu->refcnt);
- vcpu->arch.hw_mmu = NULL;
- }
+
+ vcpu->arch.hw_mmu = NULL;
}
/*
@@ -730,7 +755,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
}
}
-void kvm_nested_s2_unmap(struct kvm *kvm)
+void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
{
int i;
@@ -740,7 +765,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
if (kvm_s2_mmu_valid(mmu))
- kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
+ kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
}
}
@@ -1184,3 +1209,17 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
return 0;
}
+
+void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
+{
+ if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
+ struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
+
+ write_lock(&vcpu->kvm->mmu_lock);
+ if (mmu->pending_unmap) {
+ kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
+ mmu->pending_unmap = false;
+ }
+ write_unlock(&vcpu->kvm->mmu_lock);
+ }
+}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index dad88e31f953..ff8c4e1b847e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1527,6 +1527,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
break;
case SYS_ID_AA64PFR2_EL1:
/* We only expose FPMR */
@@ -1550,7 +1558,8 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
break;
case SYS_ID_AA64MMFR3_EL1:
- val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE;
+ val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE |
+ ID_AA64MMFR3_EL1_S1PIE;
break;
case SYS_ID_MMFR4_EL1:
val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
@@ -1985,7 +1994,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
* one cache line.
*/
if (kvm_has_mte(vcpu->kvm))
- clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
+ clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
__vcpu_sys_reg(vcpu, r->reg) = clidr;
@@ -2376,7 +2385,19 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_AA64PFR0_EL1_RAS |
ID_AA64PFR0_EL1_AdvSIMD |
ID_AA64PFR0_EL1_FP), },
- ID_SANITISED(ID_AA64PFR1_EL1),
+ ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR |
+ ID_AA64PFR1_EL1_DF2 |
+ ID_AA64PFR1_EL1_MTEX |
+ ID_AA64PFR1_EL1_THE |
+ ID_AA64PFR1_EL1_GCS |
+ ID_AA64PFR1_EL1_MTE_frac |
+ ID_AA64PFR1_EL1_NMI |
+ ID_AA64PFR1_EL1_RNDR_trap |
+ ID_AA64PFR1_EL1_SME |
+ ID_AA64PFR1_EL1_RES0 |
+ ID_AA64PFR1_EL1_MPAM_frac |
+ ID_AA64PFR1_EL1_RAS_frac |
+ ID_AA64PFR1_EL1_MTE)),
ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
ID_UNALLOCATED(4,3),
ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
@@ -2390,7 +2411,21 @@ static const struct sys_reg_desc sys_reg_descs[] = {
.get_user = get_id_reg,
.set_user = set_id_aa64dfr0_el1,
.reset = read_sanitised_id_aa64dfr0_el1,
- .val = ID_AA64DFR0_EL1_PMUVer_MASK |
+ /*
+ * Prior to FEAT_Debugv8.9, the architecture defines context-aware
+ * breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs).
+ * KVM does not trap + emulate the breakpoint registers, and as such
+ * cannot support a layout that misaligns with the underlying hardware.
+ * While it may be possible to describe a subset that aligns with
+ * hardware, just prevent changes to BRPs and CTX_CMPs altogether for
+ * simplicity.
+ *
+ * See DDI0487K.a, section D2.8.3 Breakpoint types and linking
+ * of breakpoints for more details.
+ */
+ .val = ID_AA64DFR0_EL1_DoubleLock_MASK |
+ ID_AA64DFR0_EL1_WRPs_MASK |
+ ID_AA64DFR0_EL1_PMUVer_MASK |
ID_AA64DFR0_EL1_DebugVer_MASK, },
ID_SANITISED(ID_AA64DFR1_EL1),
ID_UNALLOCATED(5,2),
@@ -2433,6 +2468,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
ID_AA64MMFR2_EL1_NV |
ID_AA64MMFR2_EL1_CCIDX)),
ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX |
+ ID_AA64MMFR3_EL1_S1PIE |
ID_AA64MMFR3_EL1_S1POE)),
ID_SANITISED(ID_AA64MMFR4_EL1),
ID_UNALLOCATED(7,5),
@@ -2903,7 +2939,7 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
* Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
* corresponding VMIDs.
*/
- kvm_nested_s2_unmap(vcpu->kvm);
+ kvm_nested_s2_unmap(vcpu->kvm, true);
write_unlock(&vcpu->kvm->mmu_lock);
@@ -2955,7 +2991,30 @@ union tlbi_info {
static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
const union tlbi_info *info)
{
- kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
+ /*
+ * The unmap operation is allowed to drop the MMU lock and block, which
+ * means that @mmu could be used for a different context than the one
+ * currently being invalidated.
+ *
+ * This behavior is still safe, as:
+ *
+ * 1) The vCPU(s) that recycled the MMU are responsible for invalidating
+ * the entire MMU before reusing it, which still honors the intent
+ * of a TLBI.
+ *
+ * 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC
+ * and ERET to the guest), other vCPUs are allowed to use stale
+ * translations.
+ *
+ * 3) Accidentally unmapping an unrelated MMU context is nonfatal, and
+ * at worst may cause more aborts for shadow stage-2 fills.
+ *
+ * Dropping the MMU lock also implies that shadow stage-2 fills could
+ * happen behind the back of the TLBI. This is still safe, though, as
+ * the L1 needs to put its stage-2 in a consistent state before doing
+ * the TLBI.
+ */
+ kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
}
static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -3050,7 +3109,11 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
base_addr &= ~(max_size - 1);
- kvm_stage2_unmap_range(mmu, base_addr, max_size);
+ /*
+ * See comment in s2_mmu_unmap_range() for why this is allowed to
+ * reschedule.
+ */
+ kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
}
static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index e7c53e8af3d1..48c952563e85 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -417,8 +417,28 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
- if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+ /*
+ * If this vCPU is being destroyed because of a failed creation
+ * then unregister the redistributor to avoid leaving behind a
+ * dangling pointer to the vCPU struct.
+ *
+ * vCPUs that have been successfully created (i.e. added to
+ * kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
+ * this function gets called while holding kvm->arch.config_lock
+ * in the VM teardown path and would otherwise introduce a lock
+ * inversion w.r.t. kvm->srcu.
+ *
+ * vCPUs that failed creation are torn down outside of the
+ * kvm->arch.config_lock and do not get unregistered in
+ * kvm_vgic_destroy(), meaning it is both safe and necessary to
+ * do so here.
+ */
+ if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu)
+ vgic_unregister_redist_iodev(vcpu);
+
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
+ }
}
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
@@ -524,22 +544,31 @@ int kvm_vgic_map_resources(struct kvm *kvm)
if (ret)
goto out;
- dist->ready = true;
dist_base = dist->vgic_dist_base;
mutex_unlock(&kvm->arch.config_lock);
ret = vgic_register_dist_iodev(kvm, dist_base, type);
- if (ret)
+ if (ret) {
kvm_err("Unable to register VGIC dist MMIO regions\n");
+ goto out_slots;
+ }
+ /*
+ * kvm_io_bus_register_dev() guarantees all readers see the new MMIO
+ * registration before returning through synchronize_srcu(), which also
+ * implies a full memory barrier. As such, marking the distributor as
+ * 'ready' here is guaranteed to be ordered after all vCPUs having seen
+ * a completely configured distributor.
+ */
+ dist->ready = true;
goto out_slots;
out:
mutex_unlock(&kvm->arch.config_lock);
out_slots:
- mutex_unlock(&kvm->slots_lock);
-
if (ret)
- kvm_vgic_destroy(kvm);
+ kvm_vm_dead(kvm);
+
+ mutex_unlock(&kvm->slots_lock);
return ret;
}
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 1d26bb5b02f4..5f4f57aaa23e 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -236,7 +236,12 @@ static int vgic_set_common_attr(struct kvm_device *dev,
mutex_lock(&dev->kvm->arch.config_lock);
- if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
+ /*
+ * Either userspace has already configured NR_IRQS or
+ * the vgic has already been initialized and vgic_init()
+ * supplied a default amount of SPIs.
+ */
+ if (dev->kvm->arch.vgic.nr_spis)
ret = -EBUSY;
else
dev->kvm->arch.vgic.nr_spis =
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 13e6a2829116..8e882f479d98 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -13,7 +13,7 @@ endif
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
-obj-$(CONFIG_CRC32) += crc32.o
+obj-$(CONFIG_CRC32) += crc32.o crc32-glue.o
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/arm64/lib/clear_page.S b/arch/arm64/lib/clear_page.S
index ebde40e7fa2b..bd6f7d5eb6eb 100644
--- a/arch/arm64/lib/clear_page.S
+++ b/arch/arm64/lib/clear_page.S
@@ -15,6 +15,19 @@
* x0 - dest
*/
SYM_FUNC_START(__pi_clear_page)
+#ifdef CONFIG_AS_HAS_MOPS
+ .arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+ b .Lno_mops
+alternative_else_nop_endif
+
+ mov x1, #PAGE_SIZE
+ setpn [x0]!, x1!, xzr
+ setmn [x0]!, x1!, xzr
+ seten [x0]!, x1!, xzr
+ ret
+.Lno_mops:
+#endif
mrs x1, dczid_el0
tbnz x1, #4, 2f /* Branch if DC ZVA is prohibited */
and w1, w1, #0xf
diff --git a/arch/arm64/lib/copy_page.S b/arch/arm64/lib/copy_page.S
index 6a56d7cf309d..e6374e7e5511 100644
--- a/arch/arm64/lib/copy_page.S
+++ b/arch/arm64/lib/copy_page.S
@@ -18,6 +18,19 @@
* x1 - src
*/
SYM_FUNC_START(__pi_copy_page)
+#ifdef CONFIG_AS_HAS_MOPS
+ .arch_extension mops
+alternative_if_not ARM64_HAS_MOPS
+ b .Lno_mops
+alternative_else_nop_endif
+
+ mov x2, #PAGE_SIZE
+ cpypwn [x0]!, [x1]!, x2!
+ cpymwn [x0]!, [x1]!, x2!
+ cpyewn [x0]!, [x1]!, x2!
+ ret
+.Lno_mops:
+#endif
ldp x2, x3, [x1]
ldp x4, x5, [x1, #16]
ldp x6, x7, [x1, #32]
diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32-glue.c
new file mode 100644
index 000000000000..295ae3e6b997
--- /dev/null
+++ b/arch/arm64/lib/crc32-glue.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/crc32.h>
+#include <linux/linkage.h>
+
+#include <asm/alternative.h>
+#include <asm/cpufeature.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+#include <crypto/internal/simd.h>
+
+// The minimum input length to consider the 4-way interleaved code path
+static const size_t min_len = 1024;
+
+asmlinkage u32 crc32_le_arm64(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32c_le_arm64(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32_be_arm64(u32 crc, unsigned char const *p, size_t len);
+
+asmlinkage u32 crc32_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32c_le_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+asmlinkage u32 crc32_be_arm64_4way(u32 crc, unsigned char const *p, size_t len);
+
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+ if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+ return crc32_le_base(crc, p, len);
+
+ if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
+ kernel_neon_begin();
+ crc = crc32_le_arm64_4way(crc, p, len);
+ kernel_neon_end();
+
+ p += round_down(len, 64);
+ len %= 64;
+
+ if (!len)
+ return crc;
+ }
+
+ return crc32_le_arm64(crc, p, len);
+}
+
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+ if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+ return __crc32c_le_base(crc, p, len);
+
+ if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
+ kernel_neon_begin();
+ crc = crc32c_le_arm64_4way(crc, p, len);
+ kernel_neon_end();
+
+ p += round_down(len, 64);
+ len %= 64;
+
+ if (!len)
+ return crc;
+ }
+
+ return crc32c_le_arm64(crc, p, len);
+}
+
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+ if (!alternative_has_cap_likely(ARM64_HAS_CRC32))
+ return crc32_be_base(crc, p, len);
+
+ if (len >= min_len && cpu_have_named_feature(PMULL) && crypto_simd_usable()) {
+ kernel_neon_begin();
+ crc = crc32_be_arm64_4way(crc, p, len);
+ kernel_neon_end();
+
+ p += round_down(len, 64);
+ len %= 64;
+
+ if (!len)
+ return crc;
+ }
+
+ return crc32_be_arm64(crc, p, len);
+}
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 8340dccff46f..68825317460f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -1,54 +1,60 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * Accelerated CRC32(C) using AArch64 CRC instructions
+ * Accelerated CRC32(C) using AArch64 CRC and PMULL instructions
*
- * Copyright (C) 2016 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2016 - 2018 Linaro Ltd.
+ * Copyright (C) 2024 Google LLC
+ *
+ * Author: Ard Biesheuvel <ardb@kernel.org>
*/
#include <linux/linkage.h>
-#include <asm/alternative.h>
#include <asm/assembler.h>
- .arch armv8-a+crc
+ .cpu generic+crc+crypto
- .macro byteorder, reg, be
- .if \be
-CPU_LE( rev \reg, \reg )
- .else
-CPU_BE( rev \reg, \reg )
- .endif
+ .macro bitle, reg
.endm
- .macro byteorder16, reg, be
- .if \be
-CPU_LE( rev16 \reg, \reg )
- .else
-CPU_BE( rev16 \reg, \reg )
- .endif
+ .macro bitbe, reg
+ rbit \reg, \reg
.endm
- .macro bitorder, reg, be
- .if \be
- rbit \reg, \reg
- .endif
+ .macro bytele, reg
.endm
- .macro bitorder16, reg, be
- .if \be
+ .macro bytebe, reg
rbit \reg, \reg
- lsr \reg, \reg, #16
- .endif
+ lsr \reg, \reg, #24
.endm
- .macro bitorder8, reg, be
- .if \be
+ .macro hwordle, reg
+CPU_BE( rev16 \reg, \reg )
+ .endm
+
+ .macro hwordbe, reg
+CPU_LE( rev \reg, \reg )
rbit \reg, \reg
- lsr \reg, \reg, #24
- .endif
+CPU_BE( lsr \reg, \reg, #16 )
+ .endm
+
+ .macro le, regs:vararg
+ .irp r, \regs
+CPU_BE( rev \r, \r )
+ .endr
.endm
- .macro __crc32, c, be=0
- bitorder w0, \be
+ .macro be, regs:vararg
+ .irp r, \regs
+CPU_LE( rev \r, \r )
+ .endr
+ .irp r, \regs
+ rbit \r, \r
+ .endr
+ .endm
+
+ .macro __crc32, c, order=le
+ bit\order w0
cmp x2, #16
b.lt 8f // less than 16 bytes
@@ -61,14 +67,7 @@ CPU_BE( rev16 \reg, \reg )
add x8, x8, x1
add x1, x1, x7
ldp x5, x6, [x8]
- byteorder x3, \be
- byteorder x4, \be
- byteorder x5, \be
- byteorder x6, \be
- bitorder x3, \be
- bitorder x4, \be
- bitorder x5, \be
- bitorder x6, \be
+ \order x3, x4, x5, x6
tst x7, #8
crc32\c\()x w8, w0, x3
@@ -96,65 +95,268 @@ CPU_BE( rev16 \reg, \reg )
32: ldp x3, x4, [x1], #32
sub x2, x2, #32
ldp x5, x6, [x1, #-16]
- byteorder x3, \be
- byteorder x4, \be
- byteorder x5, \be
- byteorder x6, \be
- bitorder x3, \be
- bitorder x4, \be
- bitorder x5, \be
- bitorder x6, \be
+ \order x3, x4, x5, x6
crc32\c\()x w0, w0, x3
crc32\c\()x w0, w0, x4
crc32\c\()x w0, w0, x5
crc32\c\()x w0, w0, x6
cbnz x2, 32b
-0: bitorder w0, \be
+0: bit\order w0
ret
8: tbz x2, #3, 4f
ldr x3, [x1], #8
- byteorder x3, \be
- bitorder x3, \be
+ \order x3
crc32\c\()x w0, w0, x3
4: tbz x2, #2, 2f
ldr w3, [x1], #4
- byteorder w3, \be
- bitorder w3, \be
+ \order w3
crc32\c\()w w0, w0, w3
2: tbz x2, #1, 1f
ldrh w3, [x1], #2
- byteorder16 w3, \be
- bitorder16 w3, \be
+ hword\order w3
crc32\c\()h w0, w0, w3
1: tbz x2, #0, 0f
ldrb w3, [x1]
- bitorder8 w3, \be
+ byte\order w3
crc32\c\()b w0, w0, w3
-0: bitorder w0, \be
+0: bit\order w0
ret
.endm
.align 5
-SYM_FUNC_START(crc32_le)
-alternative_if_not ARM64_HAS_CRC32
- b crc32_le_base
-alternative_else_nop_endif
+SYM_FUNC_START(crc32_le_arm64)
__crc32
-SYM_FUNC_END(crc32_le)
+SYM_FUNC_END(crc32_le_arm64)
.align 5
-SYM_FUNC_START(__crc32c_le)
-alternative_if_not ARM64_HAS_CRC32
- b __crc32c_le_base
-alternative_else_nop_endif
+SYM_FUNC_START(crc32c_le_arm64)
__crc32 c
-SYM_FUNC_END(__crc32c_le)
+SYM_FUNC_END(crc32c_le_arm64)
.align 5
-SYM_FUNC_START(crc32_be)
-alternative_if_not ARM64_HAS_CRC32
- b crc32_be_base
-alternative_else_nop_endif
- __crc32 be=1
-SYM_FUNC_END(crc32_be)
+SYM_FUNC_START(crc32_be_arm64)
+ __crc32 order=be
+SYM_FUNC_END(crc32_be_arm64)
+
+ in .req x1
+ len .req x2
+
+ /*
+ * w0: input CRC at entry, output CRC at exit
+ * x1: pointer to input buffer
+ * x2: length of input in bytes
+ */
+ .macro crc4way, insn, table, order=le
+ bit\order w0
+ lsr len, len, #6 // len := # of 64-byte blocks
+
+ /* Process up to 64 blocks of 64 bytes at a time */
+.La\@: mov x3, #64
+ cmp len, #64
+ csel x3, x3, len, hi // x3 := min(len, 64)
+ sub len, len, x3
+
+ /* Divide the input into 4 contiguous blocks */
+ add x4, x3, x3, lsl #1 // x4 := 3 * x3
+ add x7, in, x3, lsl #4 // x7 := in + 16 * x3
+ add x8, in, x3, lsl #5 // x8 := in + 32 * x3
+ add x9, in, x4, lsl #4 // x9 := in + 16 * x4
+
+ /* Load the folding coefficients from the lookup table */
+ adr_l x5, \table - 12 // entry 0 omitted
+ add x5, x5, x4, lsl #2 // x5 += 12 * x3
+ ldp s0, s1, [x5]
+ ldr s2, [x5, #8]
+
+ /* Zero init partial CRCs for this iteration */
+ mov w4, wzr
+ mov w5, wzr
+ mov w6, wzr
+ mov x17, xzr
+
+.Lb\@: sub x3, x3, #1
+ \insn w6, w6, x17
+ ldp x10, x11, [in], #16
+ ldp x12, x13, [x7], #16
+ ldp x14, x15, [x8], #16
+ ldp x16, x17, [x9], #16
+
+ \order x10, x11, x12, x13, x14, x15, x16, x17
+
+ /* Apply the CRC transform to 4 16-byte blocks in parallel */
+ \insn w0, w0, x10
+ \insn w4, w4, x12
+ \insn w5, w5, x14
+ \insn w6, w6, x16
+ \insn w0, w0, x11
+ \insn w4, w4, x13
+ \insn w5, w5, x15
+ cbnz x3, .Lb\@
+
+ /* Combine the 4 partial results into w0 */
+ mov v3.d[0], x0
+ mov v4.d[0], x4
+ mov v5.d[0], x5
+ pmull v0.1q, v0.1d, v3.1d
+ pmull v1.1q, v1.1d, v4.1d
+ pmull v2.1q, v2.1d, v5.1d
+ eor v0.8b, v0.8b, v1.8b
+ eor v0.8b, v0.8b, v2.8b
+ mov x5, v0.d[0]
+ eor x5, x5, x17
+ \insn w0, w6, x5
+
+ mov in, x9
+ cbnz len, .La\@
+
+ bit\order w0
+ ret
+ .endm
+
+ .align 5
+SYM_FUNC_START(crc32c_le_arm64_4way)
+ crc4way crc32cx, .L0
+SYM_FUNC_END(crc32c_le_arm64_4way)
+
+ .align 5
+SYM_FUNC_START(crc32_le_arm64_4way)
+ crc4way crc32x, .L1
+SYM_FUNC_END(crc32_le_arm64_4way)
+
+ .align 5
+SYM_FUNC_START(crc32_be_arm64_4way)
+ crc4way crc32x, .L1, be
+SYM_FUNC_END(crc32_be_arm64_4way)
+
+ .section .rodata, "a", %progbits
+ .align 6
+.L0: .long 0xddc0152b, 0xba4fc28e, 0x493c7d27
+ .long 0x0715ce53, 0x9e4addf8, 0xba4fc28e
+ .long 0xc96cfdc0, 0x0715ce53, 0xddc0152b
+ .long 0xab7aff2a, 0x0d3b6092, 0x9e4addf8
+ .long 0x299847d5, 0x878a92a7, 0x39d3b296
+ .long 0xb6dd949b, 0xab7aff2a, 0x0715ce53
+ .long 0xa60ce07b, 0x83348832, 0x47db8317
+ .long 0xd270f1a2, 0xb9e02b86, 0x0d3b6092
+ .long 0x65863b64, 0xb6dd949b, 0xc96cfdc0
+ .long 0xb3e32c28, 0xbac2fd7b, 0x878a92a7
+ .long 0xf285651c, 0xce7f39f4, 0xdaece73e
+ .long 0x271d9844, 0xd270f1a2, 0xab7aff2a
+ .long 0x6cb08e5c, 0x2b3cac5d, 0x2162d385
+ .long 0xcec3662e, 0x1b03397f, 0x83348832
+ .long 0x8227bb8a, 0xb3e32c28, 0x299847d5
+ .long 0xd7a4825c, 0xdd7e3b0c, 0xb9e02b86
+ .long 0xf6076544, 0x10746f3c, 0x18b33a4e
+ .long 0x98d8d9cb, 0x271d9844, 0xb6dd949b
+ .long 0x57a3d037, 0x93a5f730, 0x78d9ccb7
+ .long 0x3771e98f, 0x6b749fb2, 0xbac2fd7b
+ .long 0xe0ac139e, 0xcec3662e, 0xa60ce07b
+ .long 0x6f345e45, 0xe6fc4e6a, 0xce7f39f4
+ .long 0xa2b73df1, 0xb0cd4768, 0x61d82e56
+ .long 0x86d8e4d2, 0xd7a4825c, 0xd270f1a2
+ .long 0xa90fd27a, 0x0167d312, 0xc619809d
+ .long 0xca6ef3ac, 0x26f6a60a, 0x2b3cac5d
+ .long 0x4597456a, 0x98d8d9cb, 0x65863b64
+ .long 0xc9c8b782, 0x68bce87a, 0x1b03397f
+ .long 0x62ec6c6d, 0x6956fc3b, 0xebb883bd
+ .long 0x2342001e, 0x3771e98f, 0xb3e32c28
+ .long 0xe8b6368b, 0x2178513a, 0x064f7f26
+ .long 0x9ef68d35, 0x170076fa, 0xdd7e3b0c
+ .long 0x0b0bf8ca, 0x6f345e45, 0xf285651c
+ .long 0x02ee03b2, 0xff0dba97, 0x10746f3c
+ .long 0x135c83fd, 0xf872e54c, 0xc7a68855
+ .long 0x00bcf5f6, 0x86d8e4d2, 0x271d9844
+ .long 0x58ca5f00, 0x5bb8f1bc, 0x8e766a0c
+ .long 0xded288f8, 0xb3af077a, 0x93a5f730
+ .long 0x37170390, 0xca6ef3ac, 0x6cb08e5c
+ .long 0xf48642e9, 0xdd66cbbb, 0x6b749fb2
+ .long 0xb25b29f2, 0xe9e28eb4, 0x1393e203
+ .long 0x45cddf4e, 0xc9c8b782, 0xcec3662e
+ .long 0xdfd94fb2, 0x93e106a4, 0x96c515bb
+ .long 0x021ac5ef, 0xd813b325, 0xe6fc4e6a
+ .long 0x8e1450f7, 0x2342001e, 0x8227bb8a
+ .long 0xe0cdcf86, 0x6d9a4957, 0xb0cd4768
+ .long 0x613eee91, 0xd2c3ed1a, 0x39c7ff35
+ .long 0xbedc6ba1, 0x9ef68d35, 0xd7a4825c
+ .long 0x0cd1526a, 0xf2271e60, 0x0ab3844b
+ .long 0xd6c3a807, 0x2664fd8b, 0x0167d312
+ .long 0x1d31175f, 0x02ee03b2, 0xf6076544
+ .long 0x4be7fd90, 0x363bd6b3, 0x26f6a60a
+ .long 0x6eeed1c9, 0x5fabe670, 0xa741c1bf
+ .long 0xb3a6da94, 0x00bcf5f6, 0x98d8d9cb
+ .long 0x2e7d11a7, 0x17f27698, 0x49c3cc9c
+ .long 0x889774e1, 0xaa7c7ad5, 0x68bce87a
+ .long 0x8a074012, 0xded288f8, 0x57a3d037
+ .long 0xbd0bb25f, 0x6d390dec, 0x6956fc3b
+ .long 0x3be3c09b, 0x6353c1cc, 0x42d98888
+ .long 0x465a4eee, 0xf48642e9, 0x3771e98f
+ .long 0x2e5f3c8c, 0xdd35bc8d, 0xb42ae3d9
+ .long 0xa52f58ec, 0x9a5ede41, 0x2178513a
+ .long 0x47972100, 0x45cddf4e, 0xe0ac139e
+ .long 0x359674f7, 0xa51b6135, 0x170076fa
+
+.L1: .long 0xaf449247, 0x81256527, 0xccaa009e
+ .long 0x57c54819, 0x1d9513d7, 0x81256527
+ .long 0x3f41287a, 0x57c54819, 0xaf449247
+ .long 0xf5e48c85, 0x910eeec1, 0x1d9513d7
+ .long 0x1f0c2cdd, 0x9026d5b1, 0xae0b5394
+ .long 0x71d54a59, 0xf5e48c85, 0x57c54819
+ .long 0x1c63267b, 0xfe807bbd, 0x0cbec0ed
+ .long 0xd31343ea, 0xe95c1271, 0x910eeec1
+ .long 0xf9d9c7ee, 0x71d54a59, 0x3f41287a
+ .long 0x9ee62949, 0xcec97417, 0x9026d5b1
+ .long 0xa55d1514, 0xf183c71b, 0xd1df2327
+ .long 0x21aa2b26, 0xd31343ea, 0xf5e48c85
+ .long 0x9d842b80, 0xeea395c4, 0x3c656ced
+ .long 0xd8110ff1, 0xcd669a40, 0xfe807bbd
+ .long 0x3f9e9356, 0x9ee62949, 0x1f0c2cdd
+ .long 0x1d6708a0, 0x0c30f51d, 0xe95c1271
+ .long 0xef82aa68, 0xdb3935ea, 0xb918a347
+ .long 0xd14bcc9b, 0x21aa2b26, 0x71d54a59
+ .long 0x99cce860, 0x356d209f, 0xff6f2fc2
+ .long 0xd8af8e46, 0xc352f6de, 0xcec97417
+ .long 0xf1996890, 0xd8110ff1, 0x1c63267b
+ .long 0x631bc508, 0xe95c7216, 0xf183c71b
+ .long 0x8511c306, 0x8e031a19, 0x9b9bdbd0
+ .long 0xdb3839f3, 0x1d6708a0, 0xd31343ea
+ .long 0x7a92fffb, 0xf7003835, 0x4470ac44
+ .long 0x6ce68f2a, 0x00eba0c8, 0xeea395c4
+ .long 0x4caaa263, 0xd14bcc9b, 0xf9d9c7ee
+ .long 0xb46f7cff, 0x9a1b53c8, 0xcd669a40
+ .long 0x60290934, 0x81b6f443, 0x6d40f445
+ .long 0x8e976a7d, 0xd8af8e46, 0x9ee62949
+ .long 0xdcf5088a, 0x9dbdc100, 0x145575d5
+ .long 0x1753ab84, 0xbbf2f6d6, 0x0c30f51d
+ .long 0x255b139e, 0x631bc508, 0xa55d1514
+ .long 0xd784eaa8, 0xce26786c, 0xdb3935ea
+ .long 0x6d2c864a, 0x8068c345, 0x2586d334
+ .long 0x02072e24, 0xdb3839f3, 0x21aa2b26
+ .long 0x06689b0a, 0x5efd72f5, 0xe0575528
+ .long 0x1e52f5ea, 0x4117915b, 0x356d209f
+ .long 0x1d3d1db6, 0x6ce68f2a, 0x9d842b80
+ .long 0x3796455c, 0xb8e0e4a8, 0xc352f6de
+ .long 0xdf3a4eb3, 0xc55a2330, 0xb84ffa9c
+ .long 0x28ae0976, 0xb46f7cff, 0xd8110ff1
+ .long 0x9764bc8d, 0xd7e7a22c, 0x712510f0
+ .long 0x13a13e18, 0x3e9a43cd, 0xe95c7216
+ .long 0xb8ee242e, 0x8e976a7d, 0x3f9e9356
+ .long 0x0c540e7b, 0x753c81ff, 0x8e031a19
+ .long 0x9924c781, 0xb9220208, 0x3edcde65
+ .long 0x3954de39, 0x1753ab84, 0x1d6708a0
+ .long 0xf32238b5, 0xbec81497, 0x9e70b943
+ .long 0xbbd2cd2c, 0x0925d861, 0xf7003835
+ .long 0xcc401304, 0xd784eaa8, 0xef82aa68
+ .long 0x4987e684, 0x6044fbb0, 0x00eba0c8
+ .long 0x3aa11427, 0x18fe3b4a, 0x87441142
+ .long 0x297aad60, 0x02072e24, 0xd14bcc9b
+ .long 0xf60c5e51, 0x6ef6f487, 0x5b7fdd0a
+ .long 0x632d78c5, 0x3fc33de4, 0x9a1b53c8
+ .long 0x25b8822a, 0x1e52f5ea, 0x99cce860
+ .long 0xd4fc84bc, 0x1af62fb8, 0x81b6f443
+ .long 0x5690aa32, 0xa91fdefb, 0x688a110e
+ .long 0x1357a093, 0x3796455c, 0xd8af8e46
+ .long 0x798fdd33, 0xaaa18a37, 0x357b9517
+ .long 0xc2815395, 0x54d42691, 0x9dbdc100
+ .long 0x21cfc0f7, 0x28ae0976, 0xf1996890
+ .long 0xa0decef3, 0x7b4aa8b7, 0xbbf2f6d6
diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
index 4ab48d49c451..9b99106fb95f 100644
--- a/arch/arm64/lib/memcpy.S
+++ b/arch/arm64/lib/memcpy.S
@@ -57,7 +57,7 @@
The loop tail is handled by always copying 64 bytes from the end.
*/
-SYM_FUNC_START(__pi_memcpy)
+SYM_FUNC_START_LOCAL(__pi_memcpy_generic)
add srcend, src, count
add dstend, dstin, count
cmp count, 128
@@ -238,7 +238,24 @@ L(copy64_from_start):
stp B_l, B_h, [dstin, 16]
stp C_l, C_h, [dstin]
ret
+SYM_FUNC_END(__pi_memcpy_generic)
+
+#ifdef CONFIG_AS_HAS_MOPS
+ .arch_extension mops
+SYM_FUNC_START(__pi_memcpy)
+alternative_if_not ARM64_HAS_MOPS
+ b __pi_memcpy_generic
+alternative_else_nop_endif
+
+ mov dst, dstin
+ cpyp [dst]!, [src]!, count!
+ cpym [dst]!, [src]!, count!
+ cpye [dst]!, [src]!, count!
+ ret
SYM_FUNC_END(__pi_memcpy)
+#else
+SYM_FUNC_ALIAS(__pi_memcpy, __pi_memcpy_generic)
+#endif
SYM_FUNC_ALIAS(__memcpy, __pi_memcpy)
EXPORT_SYMBOL(__memcpy)
diff --git a/arch/arm64/lib/memset.S b/arch/arm64/lib/memset.S
index a5aebe82ad73..97157da65ec6 100644
--- a/arch/arm64/lib/memset.S
+++ b/arch/arm64/lib/memset.S
@@ -26,6 +26,7 @@
*/
dstin .req x0
+val_x .req x1
val .req w1
count .req x2
tmp1 .req x3
@@ -42,7 +43,7 @@ dst .req x8
tmp3w .req w9
tmp3 .req x9
-SYM_FUNC_START(__pi_memset)
+SYM_FUNC_START_LOCAL(__pi_memset_generic)
mov dst, dstin /* Preserve return value. */
and A_lw, val, #255
orr A_lw, A_lw, A_lw, lsl #8
@@ -201,7 +202,24 @@ SYM_FUNC_START(__pi_memset)
ands count, count, zva_bits_x
b.ne .Ltail_maybe_long
ret
+SYM_FUNC_END(__pi_memset_generic)
+
+#ifdef CONFIG_AS_HAS_MOPS
+ .arch_extension mops
+SYM_FUNC_START(__pi_memset)
+alternative_if_not ARM64_HAS_MOPS
+ b __pi_memset_generic
+alternative_else_nop_endif
+
+ mov dst, dstin
+ setp [dst]!, count!, val_x
+ setm [dst]!, count!, val_x
+ sete [dst]!, count!, val_x
+ ret
SYM_FUNC_END(__pi_memset)
+#else
+SYM_FUNC_ALIAS(__pi_memset, __pi_memset_generic)
+#endif
SYM_FUNC_ALIAS(__memset, __pi_memset)
EXPORT_SYMBOL(__memset)
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 2fc8c6dd0407..fc92170a8f37 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_TRANS_TABLE) += trans_pgd.o
obj-$(CONFIG_TRANS_TABLE) += trans_pgd-asm.o
obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o
obj-$(CONFIG_ARM64_MTE) += mteswap.o
+obj-$(CONFIG_ARM64_GCS) += gcs.o
KASAN_SANITIZE_physaddr.o += n
obj-$(CONFIG_KASAN) += kasan_init.o
diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c
index a7bb20055ce0..87b3f1a25535 100644
--- a/arch/arm64/mm/copypage.c
+++ b/arch/arm64/mm/copypage.c
@@ -18,15 +18,40 @@ void copy_highpage(struct page *to, struct page *from)
{
void *kto = page_address(to);
void *kfrom = page_address(from);
+ struct folio *src = page_folio(from);
+ struct folio *dst = page_folio(to);
+ unsigned int i, nr_pages;
copy_page(kto, kfrom);
if (kasan_hw_tags_enabled())
page_kasan_tag_reset(to);
- if (system_supports_mte() && page_mte_tagged(from)) {
+ if (!system_supports_mte())
+ return;
+
+ if (folio_test_hugetlb(src) &&
+ folio_test_hugetlb_mte_tagged(src)) {
+ if (!folio_try_hugetlb_mte_tagging(dst))
+ return;
+
+ /*
+ * Populate tags for all subpages.
+ *
+ * Don't assume the first page is head page since
+ * huge page copy may start from any subpage.
+ */
+ nr_pages = folio_nr_pages(src);
+ for (i = 0; i < nr_pages; i++) {
+ kfrom = page_address(folio_page(src, i));
+ kto = page_address(folio_page(dst, i));
+ mte_copy_page_tags(kto, kfrom);
+ }
+ folio_set_hugetlb_mte_tagged(dst);
+ } else if (page_mte_tagged(from)) {
/* It's a new page, shouldn't have been tagged yet */
WARN_ON_ONCE(!try_page_mte_tagging(to));
+
mte_copy_page_tags(kto, kfrom);
set_page_mte_tagged(to);
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 8b281cf308b3..c2f89a678ac0 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -504,6 +504,14 @@ static bool fault_from_pkey(unsigned long esr, struct vm_area_struct *vma,
false);
}
+static bool is_gcs_fault(unsigned long esr)
+{
+ if (!esr_is_data_abort(esr))
+ return false;
+
+ return ESR_ELx_ISS2(esr) & ESR_ELx_GCS;
+}
+
static bool is_el0_instruction_abort(unsigned long esr)
{
return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
@@ -518,6 +526,23 @@ static bool is_write_abort(unsigned long esr)
return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM);
}
+static bool is_invalid_gcs_access(struct vm_area_struct *vma, u64 esr)
+{
+ if (!system_supports_gcs())
+ return false;
+
+ if (unlikely(is_gcs_fault(esr))) {
+ /* GCS accesses must be performed on a GCS page */
+ if (!(vma->vm_flags & VM_SHADOW_STACK))
+ return true;
+ } else if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) {
+ /* Only GCS operations can write to a GCS page */
+ return esr_is_data_abort(esr) && is_write_abort(esr);
+ }
+
+ return false;
+}
+
static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
struct pt_regs *regs)
{
@@ -554,6 +579,14 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
/* It was exec fault */
vm_flags = VM_EXEC;
mm_flags |= FAULT_FLAG_INSTRUCTION;
+ } else if (is_gcs_fault(esr)) {
+ /*
+ * The GCS permission on a page implies both read and
+ * write so always handle any GCS fault as a write fault,
+ * we need to trigger CoW even for GCS reads.
+ */
+ vm_flags = VM_WRITE;
+ mm_flags |= FAULT_FLAG_WRITE;
} else if (is_write_abort(esr)) {
/* It was write fault */
vm_flags = VM_WRITE;
@@ -587,6 +620,13 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
if (!vma)
goto lock_mmap;
+ if (is_invalid_gcs_access(vma, esr)) {
+ vma_end_read(vma);
+ fault = 0;
+ si_code = SEGV_ACCERR;
+ goto bad_area;
+ }
+
if (!(vma->vm_flags & vm_flags)) {
vma_end_read(vma);
fault = 0;
diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c
index de1e09d986ad..c5c5425791da 100644
--- a/arch/arm64/mm/fixmap.c
+++ b/arch/arm64/mm/fixmap.c
@@ -47,7 +47,8 @@ static void __init early_fixmap_init_pte(pmd_t *pmdp, unsigned long addr)
if (pmd_none(pmd)) {
ptep = bm_pte[BM_PTE_TABLE_IDX(addr)];
- __pmd_populate(pmdp, __pa_symbol(ptep), PMD_TYPE_TABLE);
+ __pmd_populate(pmdp, __pa_symbol(ptep),
+ PMD_TYPE_TABLE | PMD_TABLE_AF);
}
}
@@ -59,7 +60,8 @@ static void __init early_fixmap_init_pmd(pud_t *pudp, unsigned long addr,
pmd_t *pmdp;
if (pud_none(pud))
- __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE);
+ __pud_populate(pudp, __pa_symbol(bm_pmd),
+ PUD_TYPE_TABLE | PUD_TABLE_AF);
pmdp = pmd_offset_kimg(pudp, addr);
do {
@@ -86,7 +88,8 @@ static void __init early_fixmap_init_pud(p4d_t *p4dp, unsigned long addr,
}
if (p4d_none(p4d))
- __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE);
+ __p4d_populate(p4dp, __pa_symbol(bm_pud),
+ P4D_TYPE_TABLE | P4D_TABLE_AF);
pudp = pud_offset_kimg(p4dp, addr);
early_fixmap_init_pmd(pudp, addr, end);
diff --git a/arch/arm64/mm/gcs.c b/arch/arm64/mm/gcs.c
new file mode 100644
index 000000000000..5c46ec527b1c
--- /dev/null
+++ b/arch/arm64/mm/gcs.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/syscalls.h>
+#include <linux/types.h>
+
+#include <asm/cmpxchg.h>
+#include <asm/cpufeature.h>
+#include <asm/gcs.h>
+#include <asm/page.h>
+
+static unsigned long alloc_gcs(unsigned long addr, unsigned long size)
+{
+ int flags = MAP_ANONYMOUS | MAP_PRIVATE;
+ struct mm_struct *mm = current->mm;
+ unsigned long mapped_addr, unused;
+
+ if (addr)
+ flags |= MAP_FIXED_NOREPLACE;
+
+ mmap_write_lock(mm);
+ mapped_addr = do_mmap(NULL, addr, size, PROT_READ, flags,
+ VM_SHADOW_STACK | VM_WRITE, 0, &unused, NULL);
+ mmap_write_unlock(mm);
+
+ return mapped_addr;
+}
+
+static unsigned long gcs_size(unsigned long size)
+{
+ if (size)
+ return PAGE_ALIGN(size);
+
+ /* Allocate RLIMIT_STACK/2 with limits of PAGE_SIZE..2G */
+ size = PAGE_ALIGN(min_t(unsigned long long,
+ rlimit(RLIMIT_STACK) / 2, SZ_2G));
+ return max(PAGE_SIZE, size);
+}
+
+unsigned long gcs_alloc_thread_stack(struct task_struct *tsk,
+ const struct kernel_clone_args *args)
+{
+ unsigned long addr, size;
+
+ if (!system_supports_gcs())
+ return 0;
+
+ if (!task_gcs_el0_enabled(tsk))
+ return 0;
+
+ if ((args->flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM) {
+ tsk->thread.gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0);
+ return 0;
+ }
+
+ size = args->stack_size / 2;
+
+ size = gcs_size(size);
+ addr = alloc_gcs(0, size);
+ if (IS_ERR_VALUE(addr))
+ return addr;
+
+ tsk->thread.gcs_base = addr;
+ tsk->thread.gcs_size = size;
+ tsk->thread.gcspr_el0 = addr + size - sizeof(u64);
+
+ return addr;
+}
+
+SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags)
+{
+ unsigned long alloc_size;
+ unsigned long __user *cap_ptr;
+ unsigned long cap_val;
+ int ret = 0;
+ int cap_offset;
+
+ if (!system_supports_gcs())
+ return -EOPNOTSUPP;
+
+ if (flags & ~(SHADOW_STACK_SET_TOKEN | SHADOW_STACK_SET_MARKER))
+ return -EINVAL;
+
+ if (!PAGE_ALIGNED(addr))
+ return -EINVAL;
+
+ if (size == 8 || !IS_ALIGNED(size, 8))
+ return -EINVAL;
+
+ /*
+ * An overflow would result in attempting to write the restore token
+ * to the wrong location. Not catastrophic, but just return the right
+ * error code and block it.
+ */
+ alloc_size = PAGE_ALIGN(size);
+ if (alloc_size < size)
+ return -EOVERFLOW;
+
+ addr = alloc_gcs(addr, alloc_size);
+ if (IS_ERR_VALUE(addr))
+ return addr;
+
+ /*
+ * Put a cap token at the end of the allocated region so it
+ * can be switched to.
+ */
+ if (flags & SHADOW_STACK_SET_TOKEN) {
+ /* Leave an extra empty frame as a top of stack marker? */
+ if (flags & SHADOW_STACK_SET_MARKER)
+ cap_offset = 2;
+ else
+ cap_offset = 1;
+
+ cap_ptr = (unsigned long __user *)(addr + size -
+ (cap_offset * sizeof(unsigned long)));
+ cap_val = GCS_CAP(cap_ptr);
+
+ put_user_gcs(cap_val, cap_ptr, &ret);
+ if (ret != 0) {
+ vm_munmap(addr, size);
+ return -EFAULT;
+ }
+
+ /*
+ * Ensure the new cap is ordered before standard
+ * memory accesses to the same location.
+ */
+ gcsb_dsync();
+ }
+
+ return addr;
+}
+
+/*
+ * Apply the GCS mode configured for the specified task to the
+ * hardware.
+ */
+void gcs_set_el0_mode(struct task_struct *task)
+{
+ u64 gcscre0_el1 = GCSCRE0_EL1_nTR;
+
+ if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)
+ gcscre0_el1 |= GCSCRE0_EL1_RVCHKEN | GCSCRE0_EL1_PCRSEL;
+
+ if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_WRITE)
+ gcscre0_el1 |= GCSCRE0_EL1_STREn;
+
+ if (task->thread.gcs_el0_mode & PR_SHADOW_STACK_PUSH)
+ gcscre0_el1 |= GCSCRE0_EL1_PUSHMEn;
+
+ write_sysreg_s(gcscre0_el1, SYS_GCSCRE0_EL1);
+}
+
+void gcs_free(struct task_struct *task)
+{
+ if (!system_supports_gcs())
+ return;
+
+ /*
+ * When fork() with CLONE_VM fails, the child (tsk) already
+ * has a GCS allocated, and exit_thread() calls this function
+ * to free it. In this case the parent (current) and the
+ * child share the same mm struct.
+ */
+ if (!task->mm || task->mm != current->mm)
+ return;
+
+ if (task->thread.gcs_base)
+ vm_munmap(task->thread.gcs_base, task->thread.gcs_size);
+
+ task->thread.gcspr_el0 = 0;
+ task->thread.gcs_base = 0;
+ task->thread.gcs_size = 0;
+}
+
+int arch_set_shadow_stack_status(struct task_struct *task, unsigned long arg)
+{
+ unsigned long gcs, size;
+ int ret;
+
+ if (!system_supports_gcs())
+ return -EINVAL;
+
+ if (is_compat_thread(task_thread_info(task)))
+ return -EINVAL;
+
+ /* Reject unknown flags */
+ if (arg & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK)
+ return -EINVAL;
+
+ ret = gcs_check_locked(task, arg);
+ if (ret != 0)
+ return ret;
+
+ /* If we are enabling GCS then make sure we have a stack */
+ if (arg & PR_SHADOW_STACK_ENABLE &&
+ !task_gcs_el0_enabled(task)) {
+ /* Do not allow GCS to be reenabled */
+ if (task->thread.gcs_base || task->thread.gcspr_el0)
+ return -EINVAL;
+
+ if (task != current)
+ return -EBUSY;
+
+ size = gcs_size(0);
+ gcs = alloc_gcs(0, size);
+ if (!gcs)
+ return -ENOMEM;
+
+ task->thread.gcspr_el0 = gcs + size - sizeof(u64);
+ task->thread.gcs_base = gcs;
+ task->thread.gcs_size = size;
+ if (task == current)
+ write_sysreg_s(task->thread.gcspr_el0,
+ SYS_GCSPR_EL0);
+ }
+
+ task->thread.gcs_el0_mode = arg;
+ if (task == current)
+ gcs_set_el0_mode(task);
+
+ return 0;
+}
+
+int arch_get_shadow_stack_status(struct task_struct *task,
+ unsigned long __user *arg)
+{
+ if (!system_supports_gcs())
+ return -EINVAL;
+
+ if (is_compat_thread(task_thread_info(task)))
+ return -EINVAL;
+
+ return put_user(task->thread.gcs_el0_mode, arg);
+}
+
+int arch_lock_shadow_stack_status(struct task_struct *task,
+ unsigned long arg)
+{
+ if (!system_supports_gcs())
+ return -EINVAL;
+
+ if (is_compat_thread(task_thread_info(task)))
+ return -EINVAL;
+
+ /*
+ * We support locking unknown bits so applications can prevent
+ * any changes in a future proof manner.
+ */
+ task->thread.gcs_el0_locked |= arg;
+
+ return 0;
+}
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 5f1e2103888b..3215adf48a1b 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -361,14 +361,25 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
{
size_t pagesize = 1UL << shift;
- entry = pte_mkhuge(entry);
- if (pagesize == CONT_PTE_SIZE) {
- entry = pte_mkcont(entry);
- } else if (pagesize == CONT_PMD_SIZE) {
+ switch (pagesize) {
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SIZE:
+ entry = pud_pte(pud_mkhuge(pte_pud(entry)));
+ break;
+#endif
+ case CONT_PMD_SIZE:
entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
- } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
+ fallthrough;
+ case PMD_SIZE:
+ entry = pmd_pte(pmd_mkhuge(pte_pmd(entry)));
+ break;
+ case CONT_PTE_SIZE:
+ entry = pte_mkcont(entry);
+ break;
+ default:
pr_warn("%s: unrecognized huge page size 0x%lx\n",
__func__, pagesize);
+ break;
}
return entry;
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 27a32ff15412..d21f67d67cf5 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -41,6 +41,7 @@
#include <asm/kvm_host.h>
#include <asm/memory.h>
#include <asm/numa.h>
+#include <asm/rsi.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <linux/sizes.h>
@@ -366,8 +367,14 @@ void __init bootmem_init(void)
*/
void __init mem_init(void)
{
+ unsigned int flags = SWIOTLB_VERBOSE;
bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
+ if (is_realm_world()) {
+ swiotlb = true;
+ flags |= SWIOTLB_FORCE;
+ }
+
if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) {
/*
* If no bouncing needed for ZONE_DMA, reduce the swiotlb
@@ -379,7 +386,8 @@ void __init mem_init(void)
swiotlb = true;
}
- swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
+ swiotlb_init(swiotlb, flags);
+ swiotlb_update_mem_attributes();
/* this will put all unused low memory onto the freelists */
memblock_free_all();
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 7e3ad97e27d8..07aeab8a7606 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -83,8 +83,15 @@ arch_initcall(adjust_protection_map);
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
- pteval_t prot = pgprot_val(protection_map[vm_flags &
+ pteval_t prot;
+
+ /* Short circuit GCS to avoid bloating the table. */
+ if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) {
+ prot = _PAGE_GCS_RO;
+ } else {
+ prot = pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
+ }
if (vm_flags & VM_ARM64_BTI)
prot |= PTE_GP;
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e55b02fbddc8..e2739b69e11b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -119,7 +119,7 @@ static phys_addr_t __init early_pgtable_alloc(int shift)
return phys;
}
-bool pgattr_change_is_safe(u64 old, u64 new)
+bool pgattr_change_is_safe(pteval_t old, pteval_t new)
{
/*
* The following mapping attributes may be updated in live
@@ -201,7 +201,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
BUG_ON(pmd_sect(pmd));
if (pmd_none(pmd)) {
- pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
+ pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN | PMD_TABLE_AF;
phys_addr_t pte_phys;
if (flags & NO_EXEC_MAPPINGS)
@@ -288,7 +288,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
*/
BUG_ON(pud_sect(pud));
if (pud_none(pud)) {
- pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
+ pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN | PUD_TABLE_AF;
phys_addr_t pmd_phys;
if (flags & NO_EXEC_MAPPINGS)
@@ -333,7 +333,7 @@ static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end,
pud_t *pudp;
if (p4d_none(p4d)) {
- p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
+ p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN | P4D_TABLE_AF;
phys_addr_t pud_phys;
if (flags & NO_EXEC_MAPPINGS)
@@ -391,7 +391,7 @@ static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end,
p4d_t *p4dp;
if (pgd_none(pgd)) {
- pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN;
+ pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN | PGD_TABLE_AF;
phys_addr_t p4d_phys;
if (flags & NO_EXEC_MAPPINGS)
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 0e270a1c51e6..6ae6ae806454 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -5,10 +5,12 @@
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
+#include <linux/mem_encrypt.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <asm/cacheflush.h>
+#include <asm/pgtable-prot.h>
#include <asm/set_memory.h>
#include <asm/tlbflush.h>
#include <asm/kfence.h>
@@ -23,14 +25,16 @@ bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED
bool can_set_direct_map(void)
{
/*
- * rodata_full and DEBUG_PAGEALLOC require linear map to be
- * mapped at page granularity, so that it is possible to
+ * rodata_full, DEBUG_PAGEALLOC and a Realm guest all require linear
+ * map to be mapped at page granularity, so that it is possible to
* protect/unprotect single pages.
*
* KFENCE pool requires page-granular mapping if initialized late.
+ *
+ * Realms need to make pages shared/protected at page granularity.
*/
return rodata_full || debug_pagealloc_enabled() ||
- arm64_kfence_can_set_direct_map();
+ arm64_kfence_can_set_direct_map() || is_realm_world();
}
static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
@@ -60,7 +64,13 @@ static int __change_memory_common(unsigned long start, unsigned long size,
ret = apply_to_page_range(&init_mm, start, size, change_page_range,
&data);
- flush_tlb_kernel_range(start, start + size);
+ /*
+ * If the memory is being made valid without changing any other bits
+ * then a TLBI isn't required as a non-valid entry cannot be cached in
+ * the TLB.
+ */
+ if (pgprot_val(set_mask) != PTE_VALID || pgprot_val(clear_mask))
+ flush_tlb_kernel_range(start, start + size);
return ret;
}
@@ -192,6 +202,86 @@ int set_direct_map_default_noflush(struct page *page)
PAGE_SIZE, change_page_range, &data);
}
+static int __set_memory_enc_dec(unsigned long addr,
+ int numpages,
+ bool encrypt)
+{
+ unsigned long set_prot = 0, clear_prot = 0;
+ phys_addr_t start, end;
+ int ret;
+
+ if (!is_realm_world())
+ return 0;
+
+ if (!__is_lm_address(addr))
+ return -EINVAL;
+
+ start = __virt_to_phys(addr);
+ end = start + numpages * PAGE_SIZE;
+
+ if (encrypt)
+ clear_prot = PROT_NS_SHARED;
+ else
+ set_prot = PROT_NS_SHARED;
+
+ /*
+ * Break the mapping before we make any changes to avoid stale TLB
+ * entries or Synchronous External Aborts caused by RIPAS_EMPTY
+ */
+ ret = __change_memory_common(addr, PAGE_SIZE * numpages,
+ __pgprot(set_prot),
+ __pgprot(clear_prot | PTE_VALID));
+
+ if (ret)
+ return ret;
+
+ if (encrypt)
+ ret = rsi_set_memory_range_protected(start, end);
+ else
+ ret = rsi_set_memory_range_shared(start, end);
+
+ if (ret)
+ return ret;
+
+ return __change_memory_common(addr, PAGE_SIZE * numpages,
+ __pgprot(PTE_VALID),
+ __pgprot(0));
+}
+
+static int realm_set_memory_encrypted(unsigned long addr, int numpages)
+{
+ int ret = __set_memory_enc_dec(addr, numpages, true);
+
+ /*
+ * If the request to change state fails, then the only sensible cause
+ * of action for the caller is to leak the memory
+ */
+ WARN(ret, "Failed to encrypt memory, %d pages will be leaked",
+ numpages);
+
+ return ret;
+}
+
+static int realm_set_memory_decrypted(unsigned long addr, int numpages)
+{
+ int ret = __set_memory_enc_dec(addr, numpages, false);
+
+ WARN(ret, "Failed to decrypt memory, %d pages will be leaked",
+ numpages);
+
+ return ret;
+}
+
+static const struct arm64_mem_crypt_ops realm_crypt_ops = {
+ .encrypt = realm_set_memory_encrypted,
+ .decrypt = realm_set_memory_decrypted,
+};
+
+int realm_register_memory_enc_ops(void)
+{
+ return arm64_mem_crypt_ops_register(&realm_crypt_ops);
+}
+
#ifdef CONFIG_DEBUG_PAGEALLOC
void __kernel_map_pages(struct page *page, int numpages, int enable)
{
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 8abdc7fed321..b8edc5765441 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -465,10 +465,12 @@ SYM_FUNC_START(__cpu_setup)
*/
mair .req x17
tcr .req x16
+ tcr2 .req x15
mov_q mair, MAIR_EL1_SET
mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \
TCR_SHARED | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS
+ mov tcr2, xzr
tcr_clear_errata_bits tcr, x9, x5
@@ -493,9 +495,14 @@ alternative_else_nop_endif
* via capabilities.
*/
mrs x9, ID_AA64MMFR1_EL1
- and x9, x9, ID_AA64MMFR1_EL1_HAFDBS_MASK
+ ubfx x9, x9, ID_AA64MMFR1_EL1_HAFDBS_SHIFT, #4
cbz x9, 1f
orr tcr, tcr, #TCR_HA // hardware Access flag update
+#ifdef CONFIG_ARM64_HAFT
+ cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT
+ b.lt 1f
+ orr tcr2, tcr2, TCR2_EL1x_HAFT
+#endif /* CONFIG_ARM64_HAFT */
1:
#endif /* CONFIG_ARM64_HW_AFDBM */
msr mair_el1, mair
@@ -525,11 +532,16 @@ alternative_else_nop_endif
#undef PTE_MAYBE_NG
#undef PTE_MAYBE_SHARED
- mov x0, TCR2_EL1x_PIE
- msr REG_TCR2_EL1, x0
+ orr tcr2, tcr2, TCR2_EL1x_PIE
.Lskip_indirection:
+ mrs_s x1, SYS_ID_AA64MMFR3_EL1
+ ubfx x1, x1, #ID_AA64MMFR3_EL1_TCRX_SHIFT, #4
+ cbz x1, 1f
+ msr REG_TCR2_EL1, tcr2
+1:
+
/*
* Prepare SCTLR
*/
@@ -538,4 +550,5 @@ alternative_else_nop_endif
.unreq mair
.unreq tcr
+ .unreq tcr2
SYM_FUNC_END(__cpu_setup)
diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c
index 264c5f9b97d8..688fbe0271ca 100644
--- a/arch/arm64/mm/ptdump.c
+++ b/arch/arm64/mm/ptdump.c
@@ -80,10 +80,10 @@ static const struct ptdump_prot_bits pte_bits[] = {
.set = "CON",
.clear = " ",
}, {
- .mask = PTE_TABLE_BIT,
- .val = PTE_TABLE_BIT,
- .set = " ",
- .clear = "BLK",
+ .mask = PTE_TABLE_BIT | PTE_VALID,
+ .val = PTE_VALID,
+ .set = "BLK",
+ .clear = " ",
}, {
.mask = PTE_UXN,
.val = PTE_UXN,
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 8bbd0b20136a..5db82bfc9dc1 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2220,7 +2220,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ /* for the first pass, assume the worst case */
+ if (!ctx->image)
+ ctx->idx += 4;
+ else
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_enter, ctx);
}
@@ -2264,7 +2268,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
if (flags & BPF_TRAMP_F_CALL_ORIG) {
im->ip_epilogue = ctx->ro_image + ctx->idx;
- emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ /* for the first pass, assume the worst case */
+ if (!ctx->image)
+ ctx->idx += 4;
+ else
+ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
emit_call((const u64)__bpf_tramp_exit, ctx);
}
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index eedb5acc21ed..8dfb2fa51d12 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -29,6 +29,7 @@ HAS_EVT
HAS_FPMR
HAS_FGT
HAS_FPSIMD
+HAS_GCS
HAS_GENERIC_AUTH
HAS_GENERIC_AUTH_ARCH_QARMA3
HAS_GENERIC_AUTH_ARCH_QARMA5
@@ -56,6 +57,7 @@ HAS_TLB_RANGE
HAS_VA52
HAS_VIRT_HOST_EXTN
HAS_WFXT
+HAFT
HW_DBM
KVM_HVHE
KVM_PROTECTED_MODE
diff --git a/arch/arm64/tools/syscall_32.tbl b/arch/arm64/tools/syscall_32.tbl
index 9a37930d4e26..69a829912a05 100644
--- a/arch/arm64/tools/syscall_32.tbl
+++ b/arch/arm64/tools/syscall_32.tbl
@@ -474,3 +474,7 @@
460 common lsm_set_self_attr sys_lsm_set_self_attr
461 common lsm_list_modules sys_lsm_list_modules
462 common mseal sys_mseal
+463 common setxattrat sys_setxattrat
+464 common getxattrat sys_getxattrat
+465 common listxattrat sys_listxattrat
+466 common removexattrat sys_removexattrat
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 8d637ac4b7c6..283279af932c 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1238,6 +1238,7 @@ UnsignedEnum 11:8 PMUVer
0b0110 V3P5
0b0111 V3P7
0b1000 V3P8
+ 0b1001 V3P9
0b1111 IMP_DEF
EndEnum
UnsignedEnum 7:4 TraceVer
@@ -1648,6 +1649,8 @@ EndEnum
UnsignedEnum 39:36 ETS
0b0000 NI
0b0001 IMP
+ 0b0010 ETS2
+ 0b0011 ETS3
EndEnum
UnsignedEnum 35:32 TWED
0b0000 NI
@@ -1688,6 +1691,8 @@ UnsignedEnum 3:0 HAFDBS
0b0000 NI
0b0001 AF
0b0010 DBM
+ 0b0011 HAFT
+ 0b0100 HDBSS
EndEnum
EndSysreg
@@ -2178,6 +2183,13 @@ Field 4 P
Field 3:0 ALIGN
EndSysreg
+Sysreg PMUACR_EL1 3 0 9 14 4
+Res0 63:33
+Field 32 F0
+Field 31 C
+Field 30:0 P
+EndSysreg
+
Sysreg PMSELR_EL0 3 3 9 12 5
Res0 63:5
Field 4:0 SEL