summaryrefslogtreecommitdiff
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig26
-rw-r--r--arch/arm64/boot/dts/qcom/x1e80100.dtsi27
-rw-r--r--arch/arm64/configs/defconfig32
-rw-r--r--arch/arm64/crypto/Kconfig53
-rw-r--r--arch/arm64/crypto/Makefile20
-rw-r--r--arch/arm64/crypto/aes-glue.c124
-rw-r--r--arch/arm64/crypto/chacha-neon-glue.c237
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c143
-rw-r--r--arch/arm64/crypto/poly1305-glue.c232
-rw-r--r--arch/arm64/crypto/polyval-ce-glue.c73
-rw-r--r--arch/arm64/crypto/sha1-ce-glue.c70
-rw-r--r--arch/arm64/crypto/sha2-ce-glue.c192
-rw-r--r--arch/arm64/crypto/sha256-glue.c194
-rw-r--r--arch/arm64/crypto/sha3-ce-glue.c111
-rw-r--r--arch/arm64/crypto/sha512-ce-glue.c49
-rw-r--r--arch/arm64/crypto/sha512-glue.c35
-rw-r--r--arch/arm64/crypto/sm3-ce-glue.c48
-rw-r--r--arch/arm64/crypto/sm3-neon-glue.c48
-rw-r--r--arch/arm64/crypto/sm4-ce-glue.c100
-rw-r--r--arch/arm64/include/asm/cpu.h1
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/el2_setup.h26
-rw-r--r--arch/arm64/include/asm/esr.h29
-rw-r--r--arch/arm64/include/asm/fixmap.h6
-rw-r--r--arch/arm64/include/asm/fpsimd.h64
-rw-r--r--arch/arm64/include/asm/hardirq.h4
-rw-r--r--arch/arm64/include/asm/hugetlb.h29
-rw-r--r--arch/arm64/include/asm/kvm_arm.h186
-rw-r--r--arch/arm64/include/asm/kvm_host.h88
-rw-r--r--arch/arm64/include/asm/kvm_nested.h100
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h7
-rw-r--r--arch/arm64/include/asm/kvm_pkvm.h8
-rw-r--r--arch/arm64/include/asm/mem_encrypt.h2
-rw-r--r--arch/arm64/include/asm/pgtable.h236
-rw-r--r--arch/arm64/include/asm/rsi_cmds.h2
-rw-r--r--arch/arm64/include/asm/sections.h1
-rw-r--r--arch/arm64/include/asm/sysreg.h53
-rw-r--r--arch/arm64/include/asm/thread_info.h18
-rw-r--r--arch/arm64/include/asm/vdso/gettimeofday.h22
-rw-r--r--arch/arm64/include/asm/virt.h3
-rw-r--r--arch/arm64/include/asm/vmalloc.h45
-rw-r--r--arch/arm64/include/asm/vncr_mapping.h5
-rw-r--r--arch/arm64/include/uapi/asm/kvm.h9
-rw-r--r--arch/arm64/kernel/asm-offsets.c2
-rw-r--r--arch/arm64/kernel/cpu_errata.c14
-rw-r--r--arch/arm64/kernel/cpufeature.c30
-rw-r--r--arch/arm64/kernel/cpuinfo.c110
-rw-r--r--arch/arm64/kernel/efi.c4
-rw-r--r--arch/arm64/kernel/entry-common.c48
-rw-r--r--arch/arm64/kernel/fpsimd.c376
-rw-r--r--arch/arm64/kernel/head.S6
-rw-r--r--arch/arm64/kernel/hyp-stub.S2
-rw-r--r--arch/arm64/kernel/image-vars.h63
-rw-r--r--arch/arm64/kernel/kaslr.c2
-rw-r--r--arch/arm64/kernel/pi/kaslr_early.c4
-rw-r--r--arch/arm64/kernel/pi/pi.h1
-rw-r--r--arch/arm64/kernel/process.c124
-rw-r--r--arch/arm64/kernel/ptrace.c137
-rw-r--r--arch/arm64/kernel/setup.c10
-rw-r--r--arch/arm64/kernel/signal.c149
-rw-r--r--arch/arm64/kernel/signal32.c11
-rw-r--r--arch/arm64/kernel/traps.c4
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S28
-rw-r--r--arch/arm64/kvm/Makefile2
-rw-r--r--arch/arm64/kvm/arm.c30
-rw-r--r--arch/arm64/kvm/at.c186
-rw-r--r--arch/arm64/kvm/config.c1085
-rw-r--r--arch/arm64/kvm/emulate-nested.c590
-rw-r--r--arch/arm64/kvm/handle_exit.c84
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h160
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/mem_protect.h14
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/memory.h58
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/mm.h4
-rw-r--r--arch/arm64/kvm/hyp/nvhe/Makefile6
-rw-r--r--arch/arm64/kvm/hyp/nvhe/host.S2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-init.S4
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c20
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp.lds.S2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c510
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mm.c97
-rw-r--r--arch/arm64/kvm/hyp/nvhe/pkvm.c47
-rw-r--r--arch/arm64/kvm/hyp/nvhe/setup.c27
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c14
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c6
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c12
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c48
-rw-r--r--arch/arm64/kvm/hyp/vhe/tlb.c4
-rw-r--r--arch/arm64/kvm/mmu.c6
-rw-r--r--arch/arm64/kvm/nested.c846
-rw-r--r--arch/arm64/kvm/pkvm.c150
-rw-r--r--arch/arm64/kvm/pmu-emul.c60
-rw-r--r--arch/arm64/kvm/reset.c2
-rw-r--r--arch/arm64/kvm/sys_regs.c273
-rw-r--r--arch/arm64/kvm/trace_arm.h6
-rw-r--r--arch/arm64/kvm/vgic/vgic-debug.c224
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c39
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3-nested.c3
-rw-r--r--arch/arm64/kvm/vgic/vgic.h33
-rw-r--r--arch/arm64/lib/Makefile7
-rw-r--r--arch/arm64/lib/crc-t10dif.c (renamed from arch/arm64/lib/crc-t10dif-glue.c)6
-rw-r--r--arch/arm64/lib/crc32-core.S (renamed from arch/arm64/lib/crc32.S)0
-rw-r--r--arch/arm64/lib/crc32.c (renamed from arch/arm64/lib/crc32-glue.c)0
-rw-r--r--arch/arm64/lib/crypto/.gitignore3
-rw-r--r--arch/arm64/lib/crypto/Kconfig20
-rw-r--r--arch/arm64/lib/crypto/Makefile24
-rw-r--r--arch/arm64/lib/crypto/chacha-neon-core.S (renamed from arch/arm64/crypto/chacha-neon-core.S)2
-rw-r--r--arch/arm64/lib/crypto/chacha-neon-glue.c119
-rw-r--r--arch/arm64/lib/crypto/poly1305-armv8.pl (renamed from arch/arm64/crypto/poly1305-armv8.pl)0
-rw-r--r--arch/arm64/lib/crypto/poly1305-glue.c73
-rw-r--r--arch/arm64/lib/crypto/sha2-armv8.pl (renamed from arch/arm64/crypto/sha512-armv8.pl)2
-rw-r--r--arch/arm64/lib/crypto/sha256-ce.S (renamed from arch/arm64/crypto/sha2-ce-core.S)41
-rw-r--r--arch/arm64/lib/crypto/sha256.c75
-rw-r--r--arch/arm64/mm/hugetlbpage.c73
-rw-r--r--arch/arm64/mm/init.c20
-rw-r--r--arch/arm64/mm/pageattr.c6
-rw-r--r--arch/arm64/mm/proc.S19
-rw-r--r--arch/arm64/net/bpf_jit_comp.c242
-rw-r--r--arch/arm64/tools/cpucaps2
-rw-r--r--arch/arm64/tools/sysreg1012
-rw-r--r--arch/arm64/xen/hypercall.S21
120 files changed, 6735 insertions, 3571 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a182295e6f08..c314eb429b9f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -42,6 +42,7 @@ config ARM64
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_PREEMPT_LAZY
select ARCH_HAS_PTDUMP
select ARCH_HAS_PTE_DEVMAP
select ARCH_HAS_PTE_SPECIAL
@@ -134,7 +135,6 @@ config ARM64
select COMMON_CLK
select CPU_PM if (SUSPEND || CPU_IDLE)
select CPUMASK_OFFSTACK if NR_CPUS > 256
- select CRC32
select DCACHE_WORD_ACCESS
select DYNAMIC_FTRACE if FUNCTION_TRACER
select DMA_BOUNCE_UNALIGNED_KMALLOC
@@ -333,9 +333,9 @@ config ARCH_MMAP_RND_BITS_MAX
default 24 if ARM64_VA_BITS=39
default 27 if ARM64_VA_BITS=42
default 30 if ARM64_VA_BITS=47
- default 29 if ARM64_VA_BITS=48 && ARM64_64K_PAGES
- default 31 if ARM64_VA_BITS=48 && ARM64_16K_PAGES
- default 33 if ARM64_VA_BITS=48
+ default 29 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52) && ARM64_64K_PAGES
+ default 31 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52) && ARM64_16K_PAGES
+ default 33 if (ARM64_VA_BITS=48 || ARM64_VA_BITS=52)
default 14 if ARM64_64K_PAGES
default 16 if ARM64_16K_PAGES
default 18
@@ -464,6 +464,23 @@ config AMPERE_ERRATUM_AC03_CPU_38
If unsure, say Y.
+config AMPERE_ERRATUM_AC04_CPU_23
+ bool "AmpereOne: AC04_CPU_23: Failure to synchronize writes to HCR_EL2 may corrupt address translations."
+ default y
+ help
+ This option adds an alternative code sequence to work around Ampere
+ errata AC04_CPU_23 on AmpereOne.
+
+ Updates to HCR_EL2 can rarely corrupt simultaneous translations for
+ data addresses initiated by load/store instructions. Only
+ instruction initiated translations are vulnerable, not translations
+ from prefetches for example. A DSB before the store to HCR_EL2 is
+ sufficient to prevent older instructions from hitting the window
+ for corruption, and an ISB after is sufficient to prevent younger
+ instructions from hitting the window for corruption.
+
+ If unsure, say Y.
+
config ARM64_WORKAROUND_CLEAN_CACHE
bool
@@ -2285,7 +2302,6 @@ 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/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
index 4936fa5b98ff..8eddf0c96098 100644
--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
@@ -3752,60 +3752,83 @@
};
gpu_opp_table: opp-table {
- compatible = "operating-points-v2";
+ compatible = "operating-points-v2-adreno", "operating-points-v2";
+
+ opp-1250000000 {
+ opp-hz = /bits/ 64 <1250000000>;
+ opp-level = <RPMH_REGULATOR_LEVEL_TURBO_L3>;
+ opp-peak-kBps = <16500000>;
+ qcom,opp-acd-level = <0xa82a5ffd>;
+ };
+
+ opp-1175000000 {
+ opp-hz = /bits/ 64 <1175000000>;
+ opp-level = <RPMH_REGULATOR_LEVEL_TURBO_L2>;
+ opp-peak-kBps = <14398438>;
+ qcom,opp-acd-level = <0xa82a5ffd>;
+ };
opp-1100000000 {
opp-hz = /bits/ 64 <1100000000>;
opp-level = <RPMH_REGULATOR_LEVEL_TURBO_L1>;
- opp-peak-kBps = <16500000>;
+ opp-peak-kBps = <14398438>;
+ qcom,opp-acd-level = <0xa82a5ffd>;
};
opp-1000000000 {
opp-hz = /bits/ 64 <1000000000>;
opp-level = <RPMH_REGULATOR_LEVEL_TURBO>;
opp-peak-kBps = <14398438>;
+ qcom,opp-acd-level = <0xa82b5ffd>;
};
opp-925000000 {
opp-hz = /bits/ 64 <925000000>;
opp-level = <RPMH_REGULATOR_LEVEL_NOM_L1>;
opp-peak-kBps = <14398438>;
+ qcom,opp-acd-level = <0xa82b5ffd>;
};
opp-800000000 {
opp-hz = /bits/ 64 <800000000>;
opp-level = <RPMH_REGULATOR_LEVEL_NOM>;
opp-peak-kBps = <12449219>;
+ qcom,opp-acd-level = <0xa82c5ffd>;
};
opp-744000000 {
opp-hz = /bits/ 64 <744000000>;
opp-level = <RPMH_REGULATOR_LEVEL_SVS_L2>;
opp-peak-kBps = <10687500>;
+ qcom,opp-acd-level = <0x882e5ffd>;
};
opp-687000000 {
opp-hz = /bits/ 64 <687000000>;
opp-level = <RPMH_REGULATOR_LEVEL_SVS_L1>;
opp-peak-kBps = <8171875>;
+ qcom,opp-acd-level = <0x882e5ffd>;
};
opp-550000000 {
opp-hz = /bits/ 64 <550000000>;
opp-level = <RPMH_REGULATOR_LEVEL_SVS>;
opp-peak-kBps = <6074219>;
+ qcom,opp-acd-level = <0xc0285ffd>;
};
opp-390000000 {
opp-hz = /bits/ 64 <390000000>;
opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS>;
opp-peak-kBps = <3000000>;
+ qcom,opp-acd-level = <0xc0285ffd>;
};
opp-300000000 {
opp-hz = /bits/ 64 <300000000>;
opp-level = <RPMH_REGULATOR_LEVEL_LOW_SVS_D1>;
opp-peak-kBps = <2136719>;
+ qcom,opp-acd-level = <0xc02b5ffd>;
};
};
};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index c4ce2c67c0e0..a61154545c89 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1010,6 +1010,7 @@ CONFIG_SND_SOC_ROCKCHIP_RT5645=m
CONFIG_SND_SOC_RK3399_GRU_SOUND=m
CONFIG_SND_SOC_SAMSUNG=y
CONFIG_SND_SOC_RCAR=m
+CONFIG_SND_SOC_MSIOF=m
CONFIG_SND_SOC_RZ=m
CONFIG_SND_SOC_SOF_TOPLEVEL=y
CONFIG_SND_SOC_SOF_OF=y
@@ -1474,29 +1475,6 @@ CONFIG_QCOM_WCNSS_CTRL=m
CONFIG_QCOM_APR=m
CONFIG_QCOM_ICC_BWMON=m
CONFIG_QCOM_PBS=m
-CONFIG_ARCH_R8A77995=y
-CONFIG_ARCH_R8A77990=y
-CONFIG_ARCH_R8A77951=y
-CONFIG_ARCH_R8A77965=y
-CONFIG_ARCH_R8A77960=y
-CONFIG_ARCH_R8A77961=y
-CONFIG_ARCH_R8A779F0=y
-CONFIG_ARCH_R8A77980=y
-CONFIG_ARCH_R8A77970=y
-CONFIG_ARCH_R8A779A0=y
-CONFIG_ARCH_R8A779G0=y
-CONFIG_ARCH_R8A779H0=y
-CONFIG_ARCH_R8A774C0=y
-CONFIG_ARCH_R8A774E1=y
-CONFIG_ARCH_R8A774A1=y
-CONFIG_ARCH_R8A774B1=y
-CONFIG_ARCH_R9A07G043=y
-CONFIG_ARCH_R9A07G044=y
-CONFIG_ARCH_R9A07G054=y
-CONFIG_ARCH_R9A08G045=y
-CONFIG_ARCH_R9A09G011=y
-CONFIG_ARCH_R9A09G047=y
-CONFIG_ARCH_R9A09G057=y
CONFIG_ROCKCHIP_IODOMAIN=y
CONFIG_ARCH_TEGRA_132_SOC=y
CONFIG_ARCH_TEGRA_210_SOC=y
@@ -1550,10 +1528,11 @@ CONFIG_PWM_IMX27=m
CONFIG_PWM_MESON=m
CONFIG_PWM_MTK_DISP=m
CONFIG_PWM_MEDIATEK=m
-CONFIG_PWM_RCAR=m
+CONFIG_PWM_RENESAS_RCAR=m
+CONFIG_PWM_RENESAS_RZG2L_GPT=m
+CONFIG_PWM_RENESAS_RZ_MTU3=m
CONFIG_PWM_RENESAS_TPU=m
CONFIG_PWM_ROCKCHIP=y
-CONFIG_PWM_RZ_MTU3=m
CONFIG_PWM_SAMSUNG=y
CONFIG_PWM_SL28CPLD=m
CONFIG_PWM_SUN4I=m
@@ -1730,14 +1709,13 @@ CONFIG_NLS_ISO8859_1=y
CONFIG_SECURITY=y
CONFIG_CRYPTO_USER=y
CONFIG_CRYPTO_CHACHA20=m
-CONFIG_CRYPTO_TEST=m
+CONFIG_CRYPTO_BENCHMARK=m
CONFIG_CRYPTO_ECHAINIV=y
CONFIG_CRYPTO_MICHAEL_MIC=m
CONFIG_CRYPTO_ANSI_CPRNG=y
CONFIG_CRYPTO_USER_API_RNG=m
CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_SHA1_ARM64_CE=y
-CONFIG_CRYPTO_SHA2_ARM64_CE=y
CONFIG_CRYPTO_SHA512_ARM64_CE=m
CONFIG_CRYPTO_SHA3_ARM64=m
CONFIG_CRYPTO_SM3_ARM64_CE=m
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 3418c8d3c78d..c44b0f202a1f 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -25,18 +25,6 @@ config CRYPTO_NHPOLY1305_NEON
Architecture: arm64 using:
- NEON (Advanced SIMD) extensions
-config CRYPTO_POLY1305_NEON
- tristate
- depends on KERNEL_MODE_NEON
- select CRYPTO_HASH
- select CRYPTO_ARCH_HAVE_LIB_POLY1305
- default CRYPTO_LIB_POLY1305_INTERNAL
- help
- Poly1305 authenticator algorithm (RFC7539)
-
- Architecture: arm64 using:
- - NEON (Advanced SIMD) extensions
-
config CRYPTO_SHA1_ARM64_CE
tristate "Hash functions: SHA-1 (ARMv8 Crypto Extensions)"
depends on KERNEL_MODE_NEON
@@ -48,25 +36,6 @@ config CRYPTO_SHA1_ARM64_CE
Architecture: arm64 using:
- ARMv8 Crypto Extensions
-config CRYPTO_SHA256_ARM64
- tristate "Hash functions: SHA-224 and SHA-256"
- select CRYPTO_HASH
- help
- SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
- Architecture: arm64
-
-config CRYPTO_SHA2_ARM64_CE
- tristate "Hash functions: SHA-224 and SHA-256 (ARMv8 Crypto Extensions)"
- depends on KERNEL_MODE_NEON
- select CRYPTO_HASH
- select CRYPTO_SHA256_ARM64
- help
- SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
- Architecture: arm64 using:
- - ARMv8 Crypto Extensions
-
config CRYPTO_SHA512_ARM64
tristate "Hash functions: SHA-384 and SHA-512"
select CRYPTO_HASH
@@ -101,7 +70,7 @@ config CRYPTO_SM3_NEON
tristate "Hash functions: SM3 (NEON)"
depends on KERNEL_MODE_NEON
select CRYPTO_HASH
- select CRYPTO_SM3
+ select CRYPTO_LIB_SM3
help
SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
@@ -112,7 +81,7 @@ config CRYPTO_SM3_ARM64_CE
tristate "Hash functions: SM3 (ARMv8.2 Crypto Extensions)"
depends on KERNEL_MODE_NEON
select CRYPTO_HASH
- select CRYPTO_SM3
+ select CRYPTO_LIB_SM3
help
SM3 (ShangMi 3) secure hash function (OSCCA GM/T 0004-2012)
@@ -143,7 +112,7 @@ config CRYPTO_AES_ARM64
config CRYPTO_AES_ARM64_CE
tristate "Ciphers: AES (ARMv8 Crypto Extensions)"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_ALGAPI
select CRYPTO_LIB_AES
help
@@ -186,20 +155,6 @@ config CRYPTO_AES_ARM64_NEON_BLK
Architecture: arm64 using:
- NEON (Advanced SIMD) extensions
-config CRYPTO_CHACHA20_NEON
- tristate
- depends on KERNEL_MODE_NEON
- select CRYPTO_SKCIPHER
- select CRYPTO_LIB_CHACHA_GENERIC
- select CRYPTO_ARCH_HAVE_LIB_CHACHA
- default CRYPTO_LIB_CHACHA_INTERNAL
- help
- Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
- stream cipher algorithms
-
- Architecture: arm64 using:
- - NEON (Advanced SIMD) extensions
-
config CRYPTO_AES_ARM64_BS
tristate "Ciphers: AES, modes: ECB/CBC/CTR/XCTR/XTS modes (bit-sliced NEON)"
depends on KERNEL_MODE_NEON
@@ -267,7 +222,7 @@ config CRYPTO_SM4_ARM64_NEON_BLK
config CRYPTO_AES_ARM64_CE_CCM
tristate "AEAD cipher: AES in CCM mode (ARMv8 Crypto Extensions)"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_ALGAPI
select CRYPTO_AES_ARM64_CE
select CRYPTO_AES_ARM64_CE_BLK
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index e7139c4768ce..c231c980c514 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -8,9 +8,6 @@
obj-$(CONFIG_CRYPTO_SHA1_ARM64_CE) += sha1-ce.o
sha1-ce-y := sha1-ce-glue.o sha1-ce-core.o
-obj-$(CONFIG_CRYPTO_SHA2_ARM64_CE) += sha2-ce.o
-sha2-ce-y := sha2-ce-glue.o sha2-ce-core.o
-
obj-$(CONFIG_CRYPTO_SHA512_ARM64_CE) += sha512-ce.o
sha512-ce-y := sha512-ce-glue.o sha512-ce-core.o
@@ -56,19 +53,9 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
-obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
-sha256-arm64-y := sha256-glue.o sha256-core.o
-
obj-$(CONFIG_CRYPTO_SHA512_ARM64) += sha512-arm64.o
sha512-arm64-y := sha512-glue.o sha512-core.o
-obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
-chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
-
-obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
-poly1305-neon-y := poly1305-core.o poly1305-glue.o
-AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_init_arm64
-
obj-$(CONFIG_CRYPTO_NHPOLY1305_NEON) += nhpoly1305-neon.o
nhpoly1305-neon-y := nh-neon-core.o nhpoly1305-neon-glue.o
@@ -81,10 +68,7 @@ aes-neon-bs-y := aes-neonbs-core.o aes-neonbs-glue.o
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $(<) void $(@)
-$(obj)/%-core.S: $(src)/%-armv8.pl
- $(call cmd,perlasm)
-
-$(obj)/sha256-core.S: $(src)/sha512-armv8.pl
+$(obj)/sha512-core.S: $(src)/../lib/crypto/sha2-armv8.pl
$(call cmd,perlasm)
-clean-files += poly1305-core.S sha256-core.S sha512-core.S
+clean-files += sha512-core.S
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index b0150999743f..81560f722b9d 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -5,19 +5,20 @@
* Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*/
-#include <asm/neon.h>
#include <asm/hwcap.h>
-#include <asm/simd.h>
+#include <asm/neon.h>
#include <crypto/aes.h>
#include <crypto/ctr.h>
-#include <crypto/sha2.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
-#include <linux/module.h>
-#include <linux/cpufeature.h>
+#include <crypto/sha2.h>
+#include <crypto/utils.h>
#include <crypto/xts.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
#include "aes-ce-setkey.h"
@@ -130,7 +131,6 @@ struct mac_tfm_ctx {
};
struct mac_desc_ctx {
- unsigned int len;
u8 dg[AES_BLOCK_SIZE];
};
@@ -869,109 +869,64 @@ static int mac_init(struct shash_desc *desc)
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
memset(ctx->dg, 0, AES_BLOCK_SIZE);
- ctx->len = 0;
-
return 0;
}
static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
- u8 dg[], int enc_before, int enc_after)
+ u8 dg[], int enc_before)
{
int rounds = 6 + ctx->key_length / 4;
+ int rem;
- if (crypto_simd_usable()) {
- int rem;
-
- do {
- kernel_neon_begin();
- rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
- dg, enc_before, enc_after);
- kernel_neon_end();
- in += (blocks - rem) * AES_BLOCK_SIZE;
- blocks = rem;
- enc_before = 0;
- } while (blocks);
- } else {
- if (enc_before)
- aes_encrypt(ctx, dg, dg);
-
- while (blocks--) {
- crypto_xor(dg, in, AES_BLOCK_SIZE);
- in += AES_BLOCK_SIZE;
-
- if (blocks || enc_after)
- aes_encrypt(ctx, dg, dg);
- }
- }
+ do {
+ kernel_neon_begin();
+ rem = aes_mac_update(in, ctx->key_enc, rounds, blocks,
+ dg, enc_before, !enc_before);
+ kernel_neon_end();
+ in += (blocks - rem) * AES_BLOCK_SIZE;
+ blocks = rem;
+ } while (blocks);
}
static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
+ int blocks = len / AES_BLOCK_SIZE;
- while (len > 0) {
- unsigned int l;
-
- if ((ctx->len % AES_BLOCK_SIZE) == 0 &&
- (ctx->len + len) > AES_BLOCK_SIZE) {
-
- int blocks = len / AES_BLOCK_SIZE;
-
- len %= AES_BLOCK_SIZE;
-
- mac_do_update(&tctx->key, p, blocks, ctx->dg,
- (ctx->len != 0), (len != 0));
-
- p += blocks * AES_BLOCK_SIZE;
-
- if (!len) {
- ctx->len = AES_BLOCK_SIZE;
- break;
- }
- ctx->len = 0;
- }
-
- l = min(len, AES_BLOCK_SIZE - ctx->len);
-
- if (l <= AES_BLOCK_SIZE) {
- crypto_xor(ctx->dg + ctx->len, p, l);
- ctx->len += l;
- len -= l;
- p += l;
- }
- }
-
- return 0;
+ len %= AES_BLOCK_SIZE;
+ mac_do_update(&tctx->key, p, blocks, ctx->dg, 0);
+ return len;
}
-static int cbcmac_final(struct shash_desc *desc, u8 *out)
+static int cbcmac_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *out)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
- mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0);
-
+ if (len) {
+ crypto_xor(ctx->dg, src, len);
+ mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1);
+ }
memcpy(out, ctx->dg, AES_BLOCK_SIZE);
-
return 0;
}
-static int cmac_final(struct shash_desc *desc, u8 *out)
+static int cmac_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+ u8 *out)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
u8 *consts = tctx->consts;
- if (ctx->len != AES_BLOCK_SIZE) {
- ctx->dg[ctx->len] ^= 0x80;
+ crypto_xor(ctx->dg, src, len);
+ if (len != AES_BLOCK_SIZE) {
+ ctx->dg[len] ^= 0x80;
consts += AES_BLOCK_SIZE;
}
-
- mac_do_update(&tctx->key, consts, 1, ctx->dg, 0, 1);
-
+ mac_do_update(&tctx->key, consts, 1, ctx->dg, 0);
memcpy(out, ctx->dg, AES_BLOCK_SIZE);
-
return 0;
}
@@ -979,6 +934,8 @@ static struct shash_alg mac_algs[] = { {
.base.cra_name = "cmac(aes)",
.base.cra_driver_name = "cmac-aes-" MODE,
.base.cra_priority = PRIO,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINAL_NONZERO,
.base.cra_blocksize = AES_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct mac_tfm_ctx) +
2 * AES_BLOCK_SIZE,
@@ -987,13 +944,15 @@ static struct shash_alg mac_algs[] = { {
.digestsize = AES_BLOCK_SIZE,
.init = mac_init,
.update = mac_update,
- .final = cmac_final,
+ .finup = cmac_finup,
.setkey = cmac_setkey,
.descsize = sizeof(struct mac_desc_ctx),
}, {
.base.cra_name = "xcbc(aes)",
.base.cra_driver_name = "xcbc-aes-" MODE,
.base.cra_priority = PRIO,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINAL_NONZERO,
.base.cra_blocksize = AES_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct mac_tfm_ctx) +
2 * AES_BLOCK_SIZE,
@@ -1002,21 +961,22 @@ static struct shash_alg mac_algs[] = { {
.digestsize = AES_BLOCK_SIZE,
.init = mac_init,
.update = mac_update,
- .final = cmac_final,
+ .finup = cmac_finup,
.setkey = xcbc_setkey,
.descsize = sizeof(struct mac_desc_ctx),
}, {
.base.cra_name = "cbcmac(aes)",
.base.cra_driver_name = "cbcmac-aes-" MODE,
.base.cra_priority = PRIO,
- .base.cra_blocksize = 1,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
+ .base.cra_blocksize = AES_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct mac_tfm_ctx),
.base.cra_module = THIS_MODULE,
.digestsize = AES_BLOCK_SIZE,
.init = mac_init,
.update = mac_update,
- .final = cbcmac_final,
+ .finup = cbcmac_finup,
.setkey = cbcmac_setkey,
.descsize = sizeof(struct mac_desc_ctx),
} };
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
deleted file mode 100644
index 229876acfc58..000000000000
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ /dev/null
@@ -1,237 +0,0 @@
-/*
- * ARM NEON and scalar accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Based on:
- * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
- *
- * Copyright (C) 2015 Martin Willi
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_neon(u32 *state, u8 *dst, const u8 *src,
- int nrounds);
-asmlinkage void chacha_4block_xor_neon(u32 *state, u8 *dst, const u8 *src,
- int nrounds, int bytes);
-asmlinkage void hchacha_block_neon(const u32 *state, u32 *out, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-static void chacha_doneon(u32 *state, u8 *dst, const u8 *src,
- int bytes, int nrounds)
-{
- while (bytes > 0) {
- int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
-
- if (l <= CHACHA_BLOCK_SIZE) {
- u8 buf[CHACHA_BLOCK_SIZE];
-
- memcpy(buf, src, l);
- chacha_block_xor_neon(state, buf, buf, nrounds);
- memcpy(dst, buf, l);
- state[12] += 1;
- break;
- }
- chacha_4block_xor_neon(state, dst, src, nrounds, l);
- bytes -= l;
- src += l;
- dst += l;
- state[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
- }
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
- if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
- hchacha_block_generic(state, stream, nrounds);
- } else {
- kernel_neon_begin();
- hchacha_block_neon(state, stream, nrounds);
- kernel_neon_end();
- }
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
- int nrounds)
-{
- if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
- !crypto_simd_usable())
- return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
- do {
- unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
- kernel_neon_begin();
- chacha_doneon(state, dst, src, todo, nrounds);
- kernel_neon_end();
-
- bytes -= todo;
- src += todo;
- dst += todo;
- } while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_neon_stream_xor(struct skcipher_request *req,
- const struct chacha_ctx *ctx, const u8 *iv)
-{
- struct skcipher_walk walk;
- u32 state[16];
- int err;
-
- err = skcipher_walk_virt(&walk, req, false);
-
- chacha_init(state, ctx->key, iv);
-
- while (walk.nbytes > 0) {
- unsigned int nbytes = walk.nbytes;
-
- if (nbytes < walk.total)
- nbytes = rounddown(nbytes, walk.stride);
-
- if (!static_branch_likely(&have_neon) ||
- !crypto_simd_usable()) {
- chacha_crypt_generic(state, walk.dst.virt.addr,
- walk.src.virt.addr, nbytes,
- ctx->nrounds);
- } else {
- kernel_neon_begin();
- chacha_doneon(state, walk.dst.virt.addr,
- walk.src.virt.addr, nbytes, ctx->nrounds);
- kernel_neon_end();
- }
- err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
- }
-
- return err;
-}
-
-static int chacha_neon(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
- return chacha_neon_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_neon(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct chacha_ctx subctx;
- u32 state[16];
- u8 real_iv[16];
-
- chacha_init(state, ctx->key, req->iv);
- hchacha_block_arch(state, subctx.key, ctx->nrounds);
- subctx.nrounds = ctx->nrounds;
-
- memcpy(&real_iv[0], req->iv + 24, 8);
- memcpy(&real_iv[8], req->iv + 16, 8);
- return chacha_neon_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
- {
- .base.cra_name = "chacha20",
- .base.cra_driver_name = "chacha20-neon",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = CHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .walksize = 5 * CHACHA_BLOCK_SIZE,
- .setkey = chacha20_setkey,
- .encrypt = chacha_neon,
- .decrypt = chacha_neon,
- }, {
- .base.cra_name = "xchacha20",
- .base.cra_driver_name = "xchacha20-neon",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = XCHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .walksize = 5 * CHACHA_BLOCK_SIZE,
- .setkey = chacha20_setkey,
- .encrypt = xchacha_neon,
- .decrypt = xchacha_neon,
- }, {
- .base.cra_name = "xchacha12",
- .base.cra_driver_name = "xchacha12-neon",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = XCHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .walksize = 5 * CHACHA_BLOCK_SIZE,
- .setkey = chacha12_setkey,
- .encrypt = xchacha_neon,
- .decrypt = xchacha_neon,
- }
-};
-
-static int __init chacha_simd_mod_init(void)
-{
- if (!cpu_have_named_feature(ASIMD))
- return 0;
-
- static_branch_enable(&have_neon);
-
- return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
- crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
- if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && cpu_have_named_feature(ASIMD))
- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (NEON accelerated)");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-neon");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-neon");
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 071e122f9c37..4995b6e22335 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -6,30 +6,27 @@
*/
#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/aes.h>
-#include <crypto/gcm.h>
-#include <crypto/algapi.h>
#include <crypto/b128ops.h>
+#include <crypto/gcm.h>
+#include <crypto/ghash.h>
#include <crypto/gf128mul.h>
#include <crypto/internal/aead.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_CRYPTO("ghash");
-#define GHASH_BLOCK_SIZE 16
-#define GHASH_DIGEST_SIZE 16
-
#define RFC4106_NONCE_SIZE 4
struct ghash_key {
@@ -37,10 +34,8 @@ struct ghash_key {
u64 h[][2];
};
-struct ghash_desc_ctx {
+struct arm_ghash_desc_ctx {
u64 digest[GHASH_DIGEST_SIZE/sizeof(u64)];
- u8 buf[GHASH_BLOCK_SIZE];
- u32 count;
};
struct gcm_aes_ctx {
@@ -65,36 +60,12 @@ asmlinkage int pmull_gcm_decrypt(int bytes, u8 dst[], const u8 src[],
static int ghash_init(struct shash_desc *desc)
{
- struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
- *ctx = (struct ghash_desc_ctx){};
+ *ctx = (struct arm_ghash_desc_ctx){};
return 0;
}
-static void ghash_do_update(int blocks, u64 dg[], const char *src,
- struct ghash_key *key, const char *head)
-{
- be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
-
- do {
- const u8 *in = src;
-
- if (head) {
- in = head;
- blocks++;
- head = NULL;
- } else {
- src += GHASH_BLOCK_SIZE;
- }
-
- crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
- gf128mul_lle(&dst, &key->k);
- } while (--blocks);
-
- dg[0] = be64_to_cpu(dst.b);
- dg[1] = be64_to_cpu(dst.a);
-}
-
static __always_inline
void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
struct ghash_key *key, const char *head,
@@ -103,13 +74,9 @@ void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
u64 const h[][2],
const char *head))
{
- if (likely(crypto_simd_usable())) {
- kernel_neon_begin();
- simd_update(blocks, dg, src, key->h, head);
- kernel_neon_end();
- } else {
- ghash_do_update(blocks, dg, src, key, head);
- }
+ kernel_neon_begin();
+ simd_update(blocks, dg, src, key->h, head);
+ kernel_neon_end();
}
/* avoid hogging the CPU for too long */
@@ -118,61 +85,59 @@ void ghash_do_simd_update(int blocks, u64 dg[], const char *src,
static int ghash_update(struct shash_desc *desc, const u8 *src,
unsigned int len)
{
- struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
- unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
+ struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+ int blocks;
- ctx->count += len;
+ blocks = len / GHASH_BLOCK_SIZE;
+ len -= blocks * GHASH_BLOCK_SIZE;
- if ((partial + len) >= GHASH_BLOCK_SIZE) {
- struct ghash_key *key = crypto_shash_ctx(desc->tfm);
- int blocks;
-
- if (partial) {
- int p = GHASH_BLOCK_SIZE - partial;
+ do {
+ int chunk = min(blocks, MAX_BLOCKS);
- memcpy(ctx->buf + partial, src, p);
- src += p;
- len -= p;
- }
+ ghash_do_simd_update(chunk, ctx->digest, src, key, NULL,
+ pmull_ghash_update_p8);
+ blocks -= chunk;
+ src += chunk * GHASH_BLOCK_SIZE;
+ } while (unlikely(blocks > 0));
+ return len;
+}
- blocks = len / GHASH_BLOCK_SIZE;
- len %= GHASH_BLOCK_SIZE;
+static int ghash_export(struct shash_desc *desc, void *out)
+{
+ struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ u8 *dst = out;
- do {
- int chunk = min(blocks, MAX_BLOCKS);
+ put_unaligned_be64(ctx->digest[1], dst);
+ put_unaligned_be64(ctx->digest[0], dst + 8);
+ return 0;
+}
- ghash_do_simd_update(chunk, ctx->digest, src, key,
- partial ? ctx->buf : NULL,
- pmull_ghash_update_p8);
+static int ghash_import(struct shash_desc *desc, const void *in)
+{
+ struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ const u8 *src = in;
- blocks -= chunk;
- src += chunk * GHASH_BLOCK_SIZE;
- partial = 0;
- } while (unlikely(blocks > 0));
- }
- if (len)
- memcpy(ctx->buf + partial, src, len);
+ ctx->digest[1] = get_unaligned_be64(src);
+ ctx->digest[0] = get_unaligned_be64(src + 8);
return 0;
}
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *dst)
{
- struct ghash_desc_ctx *ctx = shash_desc_ctx(desc);
- unsigned int partial = ctx->count % GHASH_BLOCK_SIZE;
-
- if (partial) {
- struct ghash_key *key = crypto_shash_ctx(desc->tfm);
+ struct arm_ghash_desc_ctx *ctx = shash_desc_ctx(desc);
+ struct ghash_key *key = crypto_shash_ctx(desc->tfm);
- memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
+ if (len) {
+ u8 buf[GHASH_BLOCK_SIZE] = {};
- ghash_do_simd_update(1, ctx->digest, ctx->buf, key, NULL,
+ memcpy(buf, src, len);
+ ghash_do_simd_update(1, ctx->digest, src, key, NULL,
pmull_ghash_update_p8);
+ memzero_explicit(buf, sizeof(buf));
}
- put_unaligned_be64(ctx->digest[1], dst);
- put_unaligned_be64(ctx->digest[0], dst + 8);
-
- memzero_explicit(ctx, sizeof(*ctx));
- return 0;
+ return ghash_export(desc, dst);
}
static void ghash_reflect(u64 h[], const be128 *k)
@@ -205,6 +170,7 @@ static struct shash_alg ghash_alg = {
.base.cra_name = "ghash",
.base.cra_driver_name = "ghash-neon",
.base.cra_priority = 150,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.base.cra_blocksize = GHASH_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct ghash_key) + sizeof(u64[2]),
.base.cra_module = THIS_MODULE,
@@ -212,9 +178,12 @@ static struct shash_alg ghash_alg = {
.digestsize = GHASH_DIGEST_SIZE,
.init = ghash_init,
.update = ghash_update,
- .final = ghash_final,
+ .finup = ghash_finup,
.setkey = ghash_setkey,
- .descsize = sizeof(struct ghash_desc_ctx),
+ .export = ghash_export,
+ .import = ghash_import,
+ .descsize = sizeof(struct arm_ghash_desc_ctx),
+ .statesize = sizeof(struct ghash_desc_ctx),
};
static int num_rounds(struct crypto_aes_ctx *ctx)
diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c
deleted file mode 100644
index 18883ea438f3..000000000000
--- a/arch/arm64/crypto/poly1305-glue.c
+++ /dev/null
@@ -1,232 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
- *
- * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/jump_label.h>
-#include <linux/module.h>
-
-asmlinkage void poly1305_init_arm64(void *state, const u8 *key);
-asmlinkage void poly1305_blocks(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit);
-asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
- poly1305_init_arm64(&dctx->h, key);
- dctx->s[0] = get_unaligned_le32(key + 16);
- dctx->s[1] = get_unaligned_le32(key + 20);
- dctx->s[2] = get_unaligned_le32(key + 24);
- dctx->s[3] = get_unaligned_le32(key + 28);
- dctx->buflen = 0;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static int neon_poly1305_init(struct shash_desc *desc)
-{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- dctx->buflen = 0;
- dctx->rset = 0;
- dctx->sset = false;
-
- return 0;
-}
-
-static void neon_poly1305_blocks(struct poly1305_desc_ctx *dctx, const u8 *src,
- u32 len, u32 hibit, bool do_neon)
-{
- if (unlikely(!dctx->sset)) {
- if (!dctx->rset) {
- poly1305_init_arm64(&dctx->h, src);
- src += POLY1305_BLOCK_SIZE;
- len -= POLY1305_BLOCK_SIZE;
- dctx->rset = 1;
- }
- if (len >= POLY1305_BLOCK_SIZE) {
- dctx->s[0] = get_unaligned_le32(src + 0);
- dctx->s[1] = get_unaligned_le32(src + 4);
- dctx->s[2] = get_unaligned_le32(src + 8);
- dctx->s[3] = get_unaligned_le32(src + 12);
- src += POLY1305_BLOCK_SIZE;
- len -= POLY1305_BLOCK_SIZE;
- dctx->sset = true;
- }
- if (len < POLY1305_BLOCK_SIZE)
- return;
- }
-
- len &= ~(POLY1305_BLOCK_SIZE - 1);
-
- if (static_branch_likely(&have_neon) && likely(do_neon))
- poly1305_blocks_neon(&dctx->h, src, len, hibit);
- else
- poly1305_blocks(&dctx->h, src, len, hibit);
-}
-
-static void neon_poly1305_do_update(struct poly1305_desc_ctx *dctx,
- const u8 *src, u32 len, bool do_neon)
-{
- if (unlikely(dctx->buflen)) {
- u32 bytes = min(len, POLY1305_BLOCK_SIZE - dctx->buflen);
-
- memcpy(dctx->buf + dctx->buflen, src, bytes);
- src += bytes;
- len -= bytes;
- dctx->buflen += bytes;
-
- if (dctx->buflen == POLY1305_BLOCK_SIZE) {
- neon_poly1305_blocks(dctx, dctx->buf,
- POLY1305_BLOCK_SIZE, 1, false);
- dctx->buflen = 0;
- }
- }
-
- if (likely(len >= POLY1305_BLOCK_SIZE)) {
- neon_poly1305_blocks(dctx, src, len, 1, do_neon);
- src += round_down(len, POLY1305_BLOCK_SIZE);
- len %= POLY1305_BLOCK_SIZE;
- }
-
- if (unlikely(len)) {
- dctx->buflen = len;
- memcpy(dctx->buf, src, len);
- }
-}
-
-static int neon_poly1305_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
-{
- bool do_neon = crypto_simd_usable() && srclen > 128;
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- if (static_branch_likely(&have_neon) && do_neon)
- kernel_neon_begin();
- neon_poly1305_do_update(dctx, src, srclen, do_neon);
- if (static_branch_likely(&have_neon) && do_neon)
- kernel_neon_end();
- return 0;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
- unsigned int nbytes)
-{
- if (unlikely(dctx->buflen)) {
- u32 bytes = min(nbytes, POLY1305_BLOCK_SIZE - dctx->buflen);
-
- memcpy(dctx->buf + dctx->buflen, src, bytes);
- src += bytes;
- nbytes -= bytes;
- dctx->buflen += bytes;
-
- if (dctx->buflen == POLY1305_BLOCK_SIZE) {
- poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
- dctx->buflen = 0;
- }
- }
-
- if (likely(nbytes >= POLY1305_BLOCK_SIZE)) {
- unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE);
-
- if (static_branch_likely(&have_neon) && crypto_simd_usable()) {
- do {
- unsigned int todo = min_t(unsigned int, len, SZ_4K);
-
- kernel_neon_begin();
- poly1305_blocks_neon(&dctx->h, src, todo, 1);
- kernel_neon_end();
-
- len -= todo;
- src += todo;
- } while (len);
- } else {
- poly1305_blocks(&dctx->h, src, len, 1);
- src += len;
- }
- nbytes %= POLY1305_BLOCK_SIZE;
- }
-
- if (unlikely(nbytes)) {
- dctx->buflen = nbytes;
- memcpy(dctx->buf, src, nbytes);
- }
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
- if (unlikely(dctx->buflen)) {
- dctx->buf[dctx->buflen++] = 1;
- memset(dctx->buf + dctx->buflen, 0,
- POLY1305_BLOCK_SIZE - dctx->buflen);
- poly1305_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
- }
-
- poly1305_emit(&dctx->h, dst, dctx->s);
- memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int neon_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- if (unlikely(!dctx->sset))
- return -ENOKEY;
-
- poly1305_final_arch(dctx, dst);
- return 0;
-}
-
-static struct shash_alg neon_poly1305_alg = {
- .init = neon_poly1305_init,
- .update = neon_poly1305_update,
- .final = neon_poly1305_final,
- .digestsize = POLY1305_DIGEST_SIZE,
- .descsize = sizeof(struct poly1305_desc_ctx),
-
- .base.cra_name = "poly1305",
- .base.cra_driver_name = "poly1305-neon",
- .base.cra_priority = 200,
- .base.cra_blocksize = POLY1305_BLOCK_SIZE,
- .base.cra_module = THIS_MODULE,
-};
-
-static int __init neon_poly1305_mod_init(void)
-{
- if (!cpu_have_named_feature(ASIMD))
- return 0;
-
- static_branch_enable(&have_neon);
-
- return IS_REACHABLE(CONFIG_CRYPTO_HASH) ?
- crypto_register_shash(&neon_poly1305_alg) : 0;
-}
-
-static void __exit neon_poly1305_mod_exit(void)
-{
- if (IS_REACHABLE(CONFIG_CRYPTO_HASH) && cpu_have_named_feature(ASIMD))
- crypto_unregister_shash(&neon_poly1305_alg);
-}
-
-module_init(neon_poly1305_mod_init);
-module_exit(neon_poly1305_mod_exit);
-
-MODULE_DESCRIPTION("Poly1305 transform using NEON instructions");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-neon");
diff --git a/arch/arm64/crypto/polyval-ce-glue.c b/arch/arm64/crypto/polyval-ce-glue.c
index 0a3b5718df85..c4e653688ea0 100644
--- a/arch/arm64/crypto/polyval-ce-glue.c
+++ b/arch/arm64/crypto/polyval-ce-glue.c
@@ -15,17 +15,15 @@
* ARMv8 Crypto Extensions instructions to implement the finite field operations.
*/
-#include <crypto/algapi.h>
+#include <asm/neon.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/polyval.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
+#include <crypto/utils.h>
+#include <linux/cpufeature.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <linux/cpufeature.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
+#include <linux/string.h>
#define NUM_KEY_POWERS 8
@@ -38,7 +36,6 @@ struct polyval_tfm_ctx {
struct polyval_desc_ctx {
u8 buffer[POLYVAL_BLOCK_SIZE];
- u32 bytes;
};
asmlinkage void pmull_polyval_update(const struct polyval_tfm_ctx *keys,
@@ -48,25 +45,16 @@ asmlinkage void pmull_polyval_mul(u8 *op1, const u8 *op2);
static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator)
{
- if (likely(crypto_simd_usable())) {
- kernel_neon_begin();
- pmull_polyval_update(keys, in, nblocks, accumulator);
- kernel_neon_end();
- } else {
- polyval_update_non4k(keys->key_powers[NUM_KEY_POWERS-1], in,
- nblocks, accumulator);
- }
+ kernel_neon_begin();
+ pmull_polyval_update(keys, in, nblocks, accumulator);
+ kernel_neon_end();
}
static void internal_polyval_mul(u8 *op1, const u8 *op2)
{
- if (likely(crypto_simd_usable())) {
- kernel_neon_begin();
- pmull_polyval_mul(op1, op2);
- kernel_neon_end();
- } else {
- polyval_mul_non4k(op1, op2);
- }
+ kernel_neon_begin();
+ pmull_polyval_mul(op1, op2);
+ kernel_neon_end();
}
static int polyval_arm64_setkey(struct crypto_shash *tfm,
@@ -103,49 +91,27 @@ static int polyval_arm64_update(struct shash_desc *desc,
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
- u8 *pos;
unsigned int nblocks;
- unsigned int n;
-
- if (dctx->bytes) {
- n = min(srclen, dctx->bytes);
- pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes;
-
- dctx->bytes -= n;
- srclen -= n;
- while (n--)
- *pos++ ^= *src++;
-
- if (!dctx->bytes)
- internal_polyval_mul(dctx->buffer,
- tctx->key_powers[NUM_KEY_POWERS-1]);
- }
-
- while (srclen >= POLYVAL_BLOCK_SIZE) {
+ do {
/* allow rescheduling every 4K bytes */
nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
internal_polyval_update(tctx, src, nblocks, dctx->buffer);
srclen -= nblocks * POLYVAL_BLOCK_SIZE;
src += nblocks * POLYVAL_BLOCK_SIZE;
- }
+ } while (srclen >= POLYVAL_BLOCK_SIZE);
- if (srclen) {
- dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
- pos = dctx->buffer;
- while (srclen--)
- *pos++ ^= *src++;
- }
-
- return 0;
+ return srclen;
}
-static int polyval_arm64_final(struct shash_desc *desc, u8 *dst)
+static int polyval_arm64_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *dst)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
- if (dctx->bytes) {
+ if (len) {
+ crypto_xor(dctx->buffer, src, len);
internal_polyval_mul(dctx->buffer,
tctx->key_powers[NUM_KEY_POWERS-1]);
}
@@ -159,13 +125,14 @@ static struct shash_alg polyval_alg = {
.digestsize = POLYVAL_DIGEST_SIZE,
.init = polyval_arm64_init,
.update = polyval_arm64_update,
- .final = polyval_arm64_final,
+ .finup = polyval_arm64_finup,
.setkey = polyval_arm64_setkey,
.descsize = sizeof(struct polyval_desc_ctx),
.base = {
.cra_name = "polyval",
.cra_driver_name = "polyval-ce",
.cra_priority = 200,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.cra_blocksize = POLYVAL_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct polyval_tfm_ctx),
.cra_module = THIS_MODULE,
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index cbd14f208f83..65b6980817e5 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -7,14 +7,14 @@
#include <asm/neon.h>
#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
#include <crypto/sha1.h>
#include <crypto/sha1_base.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/string.h>
MODULE_DESCRIPTION("SHA1 secure hash using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
@@ -56,79 +56,49 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
{
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
- if (!crypto_simd_usable())
- return crypto_sha1_update(desc, data, len);
-
sctx->finalize = 0;
- sha1_base_do_update(desc, data, len, sha1_ce_transform);
-
- return 0;
+ return sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
}
static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
- bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE) && len;
-
- if (!crypto_simd_usable())
- return crypto_sha1_finup(desc, data, len, out);
+ bool finalized = false;
/*
* Allow the asm code to perform the finalization if there is no
* partial data and the input is a round multiple of the block size.
*/
- sctx->finalize = finalize;
-
- sha1_base_do_update(desc, data, len, sha1_ce_transform);
- if (!finalize)
- sha1_base_do_finalize(desc, sha1_ce_transform);
- return sha1_base_finish(desc, out);
-}
-
-static int sha1_ce_final(struct shash_desc *desc, u8 *out)
-{
- struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable())
- return crypto_sha1_finup(desc, NULL, 0, out);
-
- sctx->finalize = 0;
- sha1_base_do_finalize(desc, sha1_ce_transform);
+ if (len >= SHA1_BLOCK_SIZE) {
+ unsigned int remain = len - round_down(len, SHA1_BLOCK_SIZE);
+
+ finalized = !remain;
+ sctx->finalize = finalized;
+ sha1_base_do_update_blocks(desc, data, len, sha1_ce_transform);
+ data += len - remain;
+ len = remain;
+ }
+ if (!finalized) {
+ sctx->finalize = 0;
+ sha1_base_do_finup(desc, data, len, sha1_ce_transform);
+ }
return sha1_base_finish(desc, out);
}
-static int sha1_ce_export(struct shash_desc *desc, void *out)
-{
- struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
- memcpy(out, &sctx->sst, sizeof(struct sha1_state));
- return 0;
-}
-
-static int sha1_ce_import(struct shash_desc *desc, const void *in)
-{
- struct sha1_ce_state *sctx = shash_desc_ctx(desc);
-
- memcpy(&sctx->sst, in, sizeof(struct sha1_state));
- sctx->finalize = 0;
- return 0;
-}
-
static struct shash_alg alg = {
.init = sha1_base_init,
.update = sha1_ce_update,
- .final = sha1_ce_final,
.finup = sha1_ce_finup,
- .import = sha1_ce_import,
- .export = sha1_ce_export,
.descsize = sizeof(struct sha1_ce_state),
- .statesize = sizeof(struct sha1_state),
+ .statesize = SHA1_STATE_SIZE,
.digestsize = SHA1_DIGEST_SIZE,
.base = {
.cra_name = "sha1",
.cra_driver_name = "sha1-ce",
.cra_priority = 200,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.cra_blocksize = SHA1_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
deleted file mode 100644
index 6b4866a88ded..000000000000
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ /dev/null
@@ -1,192 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
- *
- * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/cpufeature.h>
-#include <linux/crypto.h>
-#include <linux/module.h>
-
-MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash using ARMv8 Crypto Extensions");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha256");
-
-struct sha256_ce_state {
- struct sha256_state sst;
- u32 finalize;
-};
-
-extern const u32 sha256_ce_offsetof_count;
-extern const u32 sha256_ce_offsetof_finalize;
-
-asmlinkage int __sha256_ce_transform(struct sha256_ce_state *sst, u8 const *src,
- int blocks);
-
-static void sha256_ce_transform(struct sha256_state *sst, u8 const *src,
- int blocks)
-{
- while (blocks) {
- int rem;
-
- kernel_neon_begin();
- rem = __sha256_ce_transform(container_of(sst,
- struct sha256_ce_state,
- sst), src, blocks);
- kernel_neon_end();
- src += (blocks - rem) * SHA256_BLOCK_SIZE;
- blocks = rem;
- }
-}
-
-const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
- sst.count);
-const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
- finalize);
-
-asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks);
-
-static void sha256_arm64_transform(struct sha256_state *sst, u8 const *src,
- int blocks)
-{
- sha256_block_data_order(sst->state, src, blocks);
-}
-
-static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable())
- return sha256_base_do_update(desc, data, len,
- sha256_arm64_transform);
-
- sctx->finalize = 0;
- sha256_base_do_update(desc, data, len, sha256_ce_transform);
-
- return 0;
-}
-
-static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- struct sha256_ce_state *sctx = shash_desc_ctx(desc);
- bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE) && len;
-
- if (!crypto_simd_usable()) {
- if (len)
- sha256_base_do_update(desc, data, len,
- sha256_arm64_transform);
- sha256_base_do_finalize(desc, sha256_arm64_transform);
- return sha256_base_finish(desc, out);
- }
-
- /*
- * Allow the asm code to perform the finalization if there is no
- * partial data and the input is a round multiple of the block size.
- */
- sctx->finalize = finalize;
-
- sha256_base_do_update(desc, data, len, sha256_ce_transform);
- if (!finalize)
- sha256_base_do_finalize(desc, sha256_ce_transform);
- return sha256_base_finish(desc, out);
-}
-
-static int sha256_ce_final(struct shash_desc *desc, u8 *out)
-{
- struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable()) {
- sha256_base_do_finalize(desc, sha256_arm64_transform);
- return sha256_base_finish(desc, out);
- }
-
- sctx->finalize = 0;
- sha256_base_do_finalize(desc, sha256_ce_transform);
- return sha256_base_finish(desc, out);
-}
-
-static int sha256_ce_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- sha256_base_init(desc);
- return sha256_ce_finup(desc, data, len, out);
-}
-
-static int sha256_ce_export(struct shash_desc *desc, void *out)
-{
- struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
- memcpy(out, &sctx->sst, sizeof(struct sha256_state));
- return 0;
-}
-
-static int sha256_ce_import(struct shash_desc *desc, const void *in)
-{
- struct sha256_ce_state *sctx = shash_desc_ctx(desc);
-
- memcpy(&sctx->sst, in, sizeof(struct sha256_state));
- sctx->finalize = 0;
- return 0;
-}
-
-static struct shash_alg algs[] = { {
- .init = sha224_base_init,
- .update = sha256_ce_update,
- .final = sha256_ce_final,
- .finup = sha256_ce_finup,
- .export = sha256_ce_export,
- .import = sha256_ce_import,
- .descsize = sizeof(struct sha256_ce_state),
- .statesize = sizeof(struct sha256_state),
- .digestsize = SHA224_DIGEST_SIZE,
- .base = {
- .cra_name = "sha224",
- .cra_driver_name = "sha224-ce",
- .cra_priority = 200,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .init = sha256_base_init,
- .update = sha256_ce_update,
- .final = sha256_ce_final,
- .finup = sha256_ce_finup,
- .digest = sha256_ce_digest,
- .export = sha256_ce_export,
- .import = sha256_ce_import,
- .descsize = sizeof(struct sha256_ce_state),
- .statesize = sizeof(struct sha256_state),
- .digestsize = SHA256_DIGEST_SIZE,
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256-ce",
- .cra_priority = 200,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int __init sha2_ce_mod_init(void)
-{
- return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha2_ce_mod_fini(void)
-{
- crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_cpu_feature_match(SHA2, sha2_ce_mod_init);
-module_exit(sha2_ce_mod_fini);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
deleted file mode 100644
index 35356987cc1e..000000000000
--- a/arch/arm64/crypto/sha256-glue.c
+++ /dev/null
@@ -1,194 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Linux/arm64 port of the OpenSSL SHA256 implementation for AArch64
- *
- * Copyright (c) 2016 Linaro Ltd. <ard.biesheuvel@linaro.org>
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/types.h>
-
-MODULE_DESCRIPTION("SHA-224/SHA-256 secure hash for arm64");
-MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha256");
-
-asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
- unsigned int num_blks);
-EXPORT_SYMBOL(sha256_block_data_order);
-
-static void sha256_arm64_transform(struct sha256_state *sst, u8 const *src,
- int blocks)
-{
- sha256_block_data_order(sst->state, src, blocks);
-}
-
-asmlinkage void sha256_block_neon(u32 *digest, const void *data,
- unsigned int num_blks);
-
-static void sha256_neon_transform(struct sha256_state *sst, u8 const *src,
- int blocks)
-{
- sha256_block_neon(sst->state, src, blocks);
-}
-
-static int crypto_sha256_arm64_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha256_base_do_update(desc, data, len, sha256_arm64_transform);
-}
-
-static int crypto_sha256_arm64_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- if (len)
- sha256_base_do_update(desc, data, len, sha256_arm64_transform);
- sha256_base_do_finalize(desc, sha256_arm64_transform);
-
- return sha256_base_finish(desc, out);
-}
-
-static int crypto_sha256_arm64_final(struct shash_desc *desc, u8 *out)
-{
- return crypto_sha256_arm64_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = crypto_sha256_arm64_update,
- .final = crypto_sha256_arm64_final,
- .finup = crypto_sha256_arm64_finup,
- .descsize = sizeof(struct sha256_state),
- .base.cra_name = "sha256",
- .base.cra_driver_name = "sha256-arm64",
- .base.cra_priority = 125,
- .base.cra_blocksize = SHA256_BLOCK_SIZE,
- .base.cra_module = THIS_MODULE,
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = crypto_sha256_arm64_update,
- .final = crypto_sha256_arm64_final,
- .finup = crypto_sha256_arm64_finup,
- .descsize = sizeof(struct sha256_state),
- .base.cra_name = "sha224",
- .base.cra_driver_name = "sha224-arm64",
- .base.cra_priority = 125,
- .base.cra_blocksize = SHA224_BLOCK_SIZE,
- .base.cra_module = THIS_MODULE,
-} };
-
-static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- struct sha256_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable())
- return sha256_base_do_update(desc, data, len,
- sha256_arm64_transform);
-
- while (len > 0) {
- unsigned int chunk = len;
-
- /*
- * Don't hog the CPU for the entire time it takes to process all
- * input when running on a preemptible kernel, but process the
- * data block by block instead.
- */
- if (IS_ENABLED(CONFIG_PREEMPTION) &&
- chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
- chunk = SHA256_BLOCK_SIZE -
- sctx->count % SHA256_BLOCK_SIZE;
-
- kernel_neon_begin();
- sha256_base_do_update(desc, data, chunk, sha256_neon_transform);
- kernel_neon_end();
- data += chunk;
- len -= chunk;
- }
- return 0;
-}
-
-static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- if (!crypto_simd_usable()) {
- if (len)
- sha256_base_do_update(desc, data, len,
- sha256_arm64_transform);
- sha256_base_do_finalize(desc, sha256_arm64_transform);
- } else {
- if (len)
- sha256_update_neon(desc, data, len);
- kernel_neon_begin();
- sha256_base_do_finalize(desc, sha256_neon_transform);
- kernel_neon_end();
- }
- return sha256_base_finish(desc, out);
-}
-
-static int sha256_final_neon(struct shash_desc *desc, u8 *out)
-{
- return sha256_finup_neon(desc, NULL, 0, out);
-}
-
-static struct shash_alg neon_algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = sha256_update_neon,
- .final = sha256_final_neon,
- .finup = sha256_finup_neon,
- .descsize = sizeof(struct sha256_state),
- .base.cra_name = "sha256",
- .base.cra_driver_name = "sha256-arm64-neon",
- .base.cra_priority = 150,
- .base.cra_blocksize = SHA256_BLOCK_SIZE,
- .base.cra_module = THIS_MODULE,
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = sha256_update_neon,
- .final = sha256_final_neon,
- .finup = sha256_finup_neon,
- .descsize = sizeof(struct sha256_state),
- .base.cra_name = "sha224",
- .base.cra_driver_name = "sha224-arm64-neon",
- .base.cra_priority = 150,
- .base.cra_blocksize = SHA224_BLOCK_SIZE,
- .base.cra_module = THIS_MODULE,
-} };
-
-static int __init sha256_mod_init(void)
-{
- int ret = crypto_register_shashes(algs, ARRAY_SIZE(algs));
- if (ret)
- return ret;
-
- if (cpu_have_named_feature(ASIMD)) {
- ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
- if (ret)
- crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
- }
- return ret;
-}
-
-static void __exit sha256_mod_fini(void)
-{
- if (cpu_have_named_feature(ASIMD))
- crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
- crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha256_mod_init);
-module_exit(sha256_mod_fini);
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index 5662c3ac49e9..b4f1001046c9 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -12,13 +12,13 @@
#include <asm/hwcap.h>
#include <asm/neon.h>
#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/sha3.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/unaligned.h>
MODULE_DESCRIPTION("SHA3 secure hash using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
@@ -35,74 +35,55 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha3_state *sctx = shash_desc_ctx(desc);
- unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
-
- if (!crypto_simd_usable())
- return crypto_sha3_update(desc, data, len);
-
- if ((sctx->partial + len) >= sctx->rsiz) {
- int blocks;
-
- if (sctx->partial) {
- int p = sctx->rsiz - sctx->partial;
-
- memcpy(sctx->buf + sctx->partial, data, p);
- kernel_neon_begin();
- sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
- kernel_neon_end();
-
- data += p;
- len -= p;
- sctx->partial = 0;
- }
-
- blocks = len / sctx->rsiz;
- len %= sctx->rsiz;
-
- while (blocks) {
- int rem;
-
- kernel_neon_begin();
- rem = sha3_ce_transform(sctx->st, data, blocks,
- digest_size);
- kernel_neon_end();
- data += (blocks - rem) * sctx->rsiz;
- blocks = rem;
- }
- }
-
- if (len) {
- memcpy(sctx->buf + sctx->partial, data, len);
- sctx->partial += len;
- }
- return 0;
+ struct crypto_shash *tfm = desc->tfm;
+ unsigned int bs, ds;
+ int blocks;
+
+ ds = crypto_shash_digestsize(tfm);
+ bs = crypto_shash_blocksize(tfm);
+ blocks = len / bs;
+ len -= blocks * bs;
+ do {
+ int rem;
+
+ kernel_neon_begin();
+ rem = sha3_ce_transform(sctx->st, data, blocks, ds);
+ kernel_neon_end();
+ data += (blocks - rem) * bs;
+ blocks = rem;
+ } while (blocks);
+ return len;
}
-static int sha3_final(struct shash_desc *desc, u8 *out)
+static int sha3_finup(struct shash_desc *desc, const u8 *src, unsigned int len,
+ u8 *out)
{
struct sha3_state *sctx = shash_desc_ctx(desc);
- unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
+ struct crypto_shash *tfm = desc->tfm;
__le64 *digest = (__le64 *)out;
+ u8 block[SHA3_224_BLOCK_SIZE];
+ unsigned int bs, ds;
int i;
- if (!crypto_simd_usable())
- return crypto_sha3_final(desc, out);
+ ds = crypto_shash_digestsize(tfm);
+ bs = crypto_shash_blocksize(tfm);
+ memcpy(block, src, len);
- sctx->buf[sctx->partial++] = 0x06;
- memset(sctx->buf + sctx->partial, 0, sctx->rsiz - sctx->partial);
- sctx->buf[sctx->rsiz - 1] |= 0x80;
+ block[len++] = 0x06;
+ memset(block + len, 0, bs - len);
+ block[bs - 1] |= 0x80;
kernel_neon_begin();
- sha3_ce_transform(sctx->st, sctx->buf, 1, digest_size);
+ sha3_ce_transform(sctx->st, block, 1, ds);
kernel_neon_end();
+ memzero_explicit(block , sizeof(block));
- for (i = 0; i < digest_size / 8; i++)
+ for (i = 0; i < ds / 8; i++)
put_unaligned_le64(sctx->st[i], digest++);
- if (digest_size & 4)
+ if (ds & 4)
put_unaligned_le32(sctx->st[i], (__le32 *)digest);
- memzero_explicit(sctx, sizeof(*sctx));
return 0;
}
@@ -110,10 +91,11 @@ static struct shash_alg algs[] = { {
.digestsize = SHA3_224_DIGEST_SIZE,
.init = crypto_sha3_init,
.update = sha3_update,
- .final = sha3_final,
- .descsize = sizeof(struct sha3_state),
+ .finup = sha3_finup,
+ .descsize = SHA3_STATE_SIZE,
.base.cra_name = "sha3-224",
.base.cra_driver_name = "sha3-224-ce",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.base.cra_blocksize = SHA3_224_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 200,
@@ -121,10 +103,11 @@ static struct shash_alg algs[] = { {
.digestsize = SHA3_256_DIGEST_SIZE,
.init = crypto_sha3_init,
.update = sha3_update,
- .final = sha3_final,
- .descsize = sizeof(struct sha3_state),
+ .finup = sha3_finup,
+ .descsize = SHA3_STATE_SIZE,
.base.cra_name = "sha3-256",
.base.cra_driver_name = "sha3-256-ce",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.base.cra_blocksize = SHA3_256_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 200,
@@ -132,10 +115,11 @@ static struct shash_alg algs[] = { {
.digestsize = SHA3_384_DIGEST_SIZE,
.init = crypto_sha3_init,
.update = sha3_update,
- .final = sha3_final,
- .descsize = sizeof(struct sha3_state),
+ .finup = sha3_finup,
+ .descsize = SHA3_STATE_SIZE,
.base.cra_name = "sha3-384",
.base.cra_driver_name = "sha3-384-ce",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.base.cra_blocksize = SHA3_384_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 200,
@@ -143,10 +127,11 @@ static struct shash_alg algs[] = { {
.digestsize = SHA3_512_DIGEST_SIZE,
.init = crypto_sha3_init,
.update = sha3_update,
- .final = sha3_final,
- .descsize = sizeof(struct sha3_state),
+ .finup = sha3_finup,
+ .descsize = SHA3_STATE_SIZE,
.base.cra_name = "sha3-512",
.base.cra_driver_name = "sha3-512-ce",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.base.cra_blocksize = SHA3_512_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 200,
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index 071f64293227..6fb3001fa2c9 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -10,14 +10,11 @@
*/
#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/sha2.h>
#include <crypto/sha512_base.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
#include <linux/module.h>
MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash using ARMv8 Crypto Extensions");
@@ -29,12 +26,10 @@ MODULE_ALIAS_CRYPTO("sha512");
asmlinkage int __sha512_ce_transform(struct sha512_state *sst, u8 const *src,
int blocks);
-asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
-
static void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
int blocks)
{
- while (blocks) {
+ do {
int rem;
kernel_neon_begin();
@@ -42,67 +37,47 @@ static void sha512_ce_transform(struct sha512_state *sst, u8 const *src,
kernel_neon_end();
src += (blocks - rem) * SHA512_BLOCK_SIZE;
blocks = rem;
- }
-}
-
-static void sha512_arm64_transform(struct sha512_state *sst, u8 const *src,
- int blocks)
-{
- sha512_block_data_order(sst->state, src, blocks);
+ } while (blocks);
}
static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
- sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
- : sha512_arm64_transform;
-
- sha512_base_do_update(desc, data, len, fn);
- return 0;
+ return sha512_base_do_update_blocks(desc, data, len,
+ sha512_ce_transform);
}
static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
- sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
- : sha512_arm64_transform;
-
- sha512_base_do_update(desc, data, len, fn);
- sha512_base_do_finalize(desc, fn);
- return sha512_base_finish(desc, out);
-}
-
-static int sha512_ce_final(struct shash_desc *desc, u8 *out)
-{
- sha512_block_fn *fn = crypto_simd_usable() ? sha512_ce_transform
- : sha512_arm64_transform;
-
- sha512_base_do_finalize(desc, fn);
+ sha512_base_do_finup(desc, data, len, sha512_ce_transform);
return sha512_base_finish(desc, out);
}
static struct shash_alg algs[] = { {
.init = sha384_base_init,
.update = sha512_ce_update,
- .final = sha512_ce_final,
.finup = sha512_ce_finup,
- .descsize = sizeof(struct sha512_state),
+ .descsize = SHA512_STATE_SIZE,
.digestsize = SHA384_DIGEST_SIZE,
.base.cra_name = "sha384",
.base.cra_driver_name = "sha384-ce",
.base.cra_priority = 200,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SHA512_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
}, {
.init = sha512_base_init,
.update = sha512_ce_update,
- .final = sha512_ce_final,
.finup = sha512_ce_finup,
- .descsize = sizeof(struct sha512_state),
+ .descsize = SHA512_STATE_SIZE,
.digestsize = SHA512_DIGEST_SIZE,
.base.cra_name = "sha512",
.base.cra_driver_name = "sha512-ce",
.base.cra_priority = 200,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SHA512_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
} };
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index 62f129dea83d..15aa9d8b7b2c 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -6,11 +6,10 @@
*/
#include <crypto/internal/hash.h>
-#include <linux/types.h>
-#include <linux/string.h>
#include <crypto/sha2.h>
#include <crypto/sha512_base.h>
-#include <asm/neon.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
MODULE_DESCRIPTION("SHA-384/SHA-512 secure hash for arm64");
MODULE_AUTHOR("Andy Polyakov <appro@openssl.org>");
@@ -19,59 +18,53 @@ MODULE_LICENSE("GPL v2");
MODULE_ALIAS_CRYPTO("sha384");
MODULE_ALIAS_CRYPTO("sha512");
-asmlinkage void sha512_block_data_order(u64 *digest, const void *data,
- unsigned int num_blks);
-EXPORT_SYMBOL(sha512_block_data_order);
+asmlinkage void sha512_blocks_arch(u64 *digest, const void *data,
+ unsigned int num_blks);
static void sha512_arm64_transform(struct sha512_state *sst, u8 const *src,
int blocks)
{
- sha512_block_data_order(sst->state, src, blocks);
+ sha512_blocks_arch(sst->state, src, blocks);
}
static int sha512_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
- return sha512_base_do_update(desc, data, len, sha512_arm64_transform);
+ return sha512_base_do_update_blocks(desc, data, len,
+ sha512_arm64_transform);
}
static int sha512_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
- if (len)
- sha512_base_do_update(desc, data, len, sha512_arm64_transform);
- sha512_base_do_finalize(desc, sha512_arm64_transform);
-
+ sha512_base_do_finup(desc, data, len, sha512_arm64_transform);
return sha512_base_finish(desc, out);
}
-static int sha512_final(struct shash_desc *desc, u8 *out)
-{
- return sha512_finup(desc, NULL, 0, out);
-}
-
static struct shash_alg algs[] = { {
.digestsize = SHA512_DIGEST_SIZE,
.init = sha512_base_init,
.update = sha512_update,
- .final = sha512_final,
.finup = sha512_finup,
- .descsize = sizeof(struct sha512_state),
+ .descsize = SHA512_STATE_SIZE,
.base.cra_name = "sha512",
.base.cra_driver_name = "sha512-arm64",
.base.cra_priority = 150,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SHA512_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
}, {
.digestsize = SHA384_DIGEST_SIZE,
.init = sha384_base_init,
.update = sha512_update,
- .final = sha512_final,
.finup = sha512_finup,
- .descsize = sizeof(struct sha512_state),
+ .descsize = SHA512_STATE_SIZE,
.base.cra_name = "sha384",
.base.cra_driver_name = "sha384-arm64",
.base.cra_priority = 150,
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SHA384_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
} };
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
index 1a71788c4cda..eac6f5fa0abe 100644
--- a/arch/arm64/crypto/sm3-ce-glue.c
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -6,14 +6,11 @@
*/
#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/sm3.h>
#include <crypto/sm3_base.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
#include <linux/module.h>
MODULE_DESCRIPTION("SM3 secure hash using ARMv8 Crypto Extensions");
@@ -26,50 +23,20 @@ asmlinkage void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
- if (!crypto_simd_usable()) {
- sm3_update(shash_desc_ctx(desc), data, len);
- return 0;
- }
+ int remain;
kernel_neon_begin();
- sm3_base_do_update(desc, data, len, sm3_ce_transform);
+ remain = sm3_base_do_update_blocks(desc, data, len, sm3_ce_transform);
kernel_neon_end();
-
- return 0;
-}
-
-static int sm3_ce_final(struct shash_desc *desc, u8 *out)
-{
- if (!crypto_simd_usable()) {
- sm3_final(shash_desc_ctx(desc), out);
- return 0;
- }
-
- kernel_neon_begin();
- sm3_base_do_finalize(desc, sm3_ce_transform);
- kernel_neon_end();
-
- return sm3_base_finish(desc, out);
+ return remain;
}
static int sm3_ce_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
- if (!crypto_simd_usable()) {
- struct sm3_state *sctx = shash_desc_ctx(desc);
-
- if (len)
- sm3_update(sctx, data, len);
- sm3_final(sctx, out);
- return 0;
- }
-
kernel_neon_begin();
- if (len)
- sm3_base_do_update(desc, data, len, sm3_ce_transform);
- sm3_base_do_finalize(desc, sm3_ce_transform);
+ sm3_base_do_finup(desc, data, len, sm3_ce_transform);
kernel_neon_end();
-
return sm3_base_finish(desc, out);
}
@@ -77,11 +44,12 @@ static struct shash_alg sm3_alg = {
.digestsize = SM3_DIGEST_SIZE,
.init = sm3_base_init,
.update = sm3_ce_update,
- .final = sm3_ce_final,
.finup = sm3_ce_finup,
- .descsize = sizeof(struct sm3_state),
+ .descsize = SM3_STATE_SIZE,
.base.cra_name = "sm3",
.base.cra_driver_name = "sm3-ce",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SM3_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 400,
diff --git a/arch/arm64/crypto/sm3-neon-glue.c b/arch/arm64/crypto/sm3-neon-glue.c
index 8dd71ce79b69..6c4611a503a3 100644
--- a/arch/arm64/crypto/sm3-neon-glue.c
+++ b/arch/arm64/crypto/sm3-neon-glue.c
@@ -6,14 +6,11 @@
*/
#include <asm/neon.h>
-#include <asm/simd.h>
-#include <linux/unaligned.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/sm3.h>
#include <crypto/sm3_base.h>
#include <linux/cpufeature.h>
-#include <linux/crypto.h>
+#include <linux/kernel.h>
#include <linux/module.h>
@@ -23,50 +20,20 @@ asmlinkage void sm3_neon_transform(struct sm3_state *sst, u8 const *src,
static int sm3_neon_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
- if (!crypto_simd_usable()) {
- sm3_update(shash_desc_ctx(desc), data, len);
- return 0;
- }
+ int remain;
kernel_neon_begin();
- sm3_base_do_update(desc, data, len, sm3_neon_transform);
+ remain = sm3_base_do_update_blocks(desc, data, len, sm3_neon_transform);
kernel_neon_end();
-
- return 0;
-}
-
-static int sm3_neon_final(struct shash_desc *desc, u8 *out)
-{
- if (!crypto_simd_usable()) {
- sm3_final(shash_desc_ctx(desc), out);
- return 0;
- }
-
- kernel_neon_begin();
- sm3_base_do_finalize(desc, sm3_neon_transform);
- kernel_neon_end();
-
- return sm3_base_finish(desc, out);
+ return remain;
}
static int sm3_neon_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
- if (!crypto_simd_usable()) {
- struct sm3_state *sctx = shash_desc_ctx(desc);
-
- if (len)
- sm3_update(sctx, data, len);
- sm3_final(sctx, out);
- return 0;
- }
-
kernel_neon_begin();
- if (len)
- sm3_base_do_update(desc, data, len, sm3_neon_transform);
- sm3_base_do_finalize(desc, sm3_neon_transform);
+ sm3_base_do_finup(desc, data, len, sm3_neon_transform);
kernel_neon_end();
-
return sm3_base_finish(desc, out);
}
@@ -74,11 +41,12 @@ static struct shash_alg sm3_alg = {
.digestsize = SM3_DIGEST_SIZE,
.init = sm3_base_init,
.update = sm3_neon_update,
- .final = sm3_neon_final,
.finup = sm3_neon_finup,
- .descsize = sizeof(struct sm3_state),
+ .descsize = SM3_STATE_SIZE,
.base.cra_name = "sm3",
.base.cra_driver_name = "sm3-neon",
+ .base.cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.base.cra_blocksize = SM3_BLOCK_SIZE,
.base.cra_module = THIS_MODULE,
.base.cra_priority = 200,
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index 43741bed874e..7a60e7b559dc 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -8,19 +8,18 @@
* Copyright (C) 2022 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
*/
-#include <linux/module.h>
-#include <linux/crypto.h>
-#include <linux/kernel.h>
-#include <linux/cpufeature.h>
#include <asm/neon.h>
-#include <asm/simd.h>
#include <crypto/b128ops.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
-#include <crypto/xts.h>
#include <crypto/sm4.h>
+#include <crypto/utils.h>
+#include <crypto/xts.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
#define BYTES2BLKS(nbytes) ((nbytes) >> 4)
@@ -64,7 +63,6 @@ struct sm4_mac_tfm_ctx {
};
struct sm4_mac_desc_ctx {
- unsigned int len;
u8 digest[SM4_BLOCK_SIZE];
};
@@ -591,8 +589,6 @@ static int sm4_mac_init(struct shash_desc *desc)
struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
memset(ctx->digest, 0, SM4_BLOCK_SIZE);
- ctx->len = 0;
-
return 0;
}
@@ -601,87 +597,50 @@ static int sm4_mac_update(struct shash_desc *desc, const u8 *p,
{
struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
- unsigned int l, nblocks;
-
- if (len == 0)
- return 0;
-
- if (ctx->len || ctx->len + len < SM4_BLOCK_SIZE) {
- l = min(len, SM4_BLOCK_SIZE - ctx->len);
-
- crypto_xor(ctx->digest + ctx->len, p, l);
- ctx->len += l;
- len -= l;
- p += l;
- }
-
- if (len && (ctx->len % SM4_BLOCK_SIZE) == 0) {
- kernel_neon_begin();
-
- if (len < SM4_BLOCK_SIZE && ctx->len == SM4_BLOCK_SIZE) {
- sm4_ce_crypt_block(tctx->key.rkey_enc,
- ctx->digest, ctx->digest);
- ctx->len = 0;
- } else {
- nblocks = len / SM4_BLOCK_SIZE;
- len %= SM4_BLOCK_SIZE;
+ unsigned int nblocks = len / SM4_BLOCK_SIZE;
- sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, p,
- nblocks, (ctx->len == SM4_BLOCK_SIZE),
- (len != 0));
-
- p += nblocks * SM4_BLOCK_SIZE;
-
- if (len == 0)
- ctx->len = SM4_BLOCK_SIZE;
- }
-
- kernel_neon_end();
-
- if (len) {
- crypto_xor(ctx->digest, p, len);
- ctx->len = len;
- }
- }
-
- return 0;
+ len %= SM4_BLOCK_SIZE;
+ kernel_neon_begin();
+ sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, p,
+ nblocks, false, true);
+ kernel_neon_end();
+ return len;
}
-static int sm4_cmac_final(struct shash_desc *desc, u8 *out)
+static int sm4_cmac_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *out)
{
struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
const u8 *consts = tctx->consts;
- if (ctx->len != SM4_BLOCK_SIZE) {
- ctx->digest[ctx->len] ^= 0x80;
+ crypto_xor(ctx->digest, src, len);
+ if (len != SM4_BLOCK_SIZE) {
+ ctx->digest[len] ^= 0x80;
consts += SM4_BLOCK_SIZE;
}
-
kernel_neon_begin();
sm4_ce_mac_update(tctx->key.rkey_enc, ctx->digest, consts, 1,
false, true);
kernel_neon_end();
-
memcpy(out, ctx->digest, SM4_BLOCK_SIZE);
-
return 0;
}
-static int sm4_cbcmac_final(struct shash_desc *desc, u8 *out)
+static int sm4_cbcmac_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *out)
{
struct sm4_mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct sm4_mac_desc_ctx *ctx = shash_desc_ctx(desc);
- if (ctx->len) {
+ if (len) {
+ crypto_xor(ctx->digest, src, len);
kernel_neon_begin();
sm4_ce_crypt_block(tctx->key.rkey_enc, ctx->digest,
ctx->digest);
kernel_neon_end();
}
-
memcpy(out, ctx->digest, SM4_BLOCK_SIZE);
-
return 0;
}
@@ -691,6 +650,8 @@ static struct shash_alg sm4_mac_algs[] = {
.cra_name = "cmac(sm4)",
.cra_driver_name = "cmac-sm4-ce",
.cra_priority = 400,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINAL_NONZERO,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_mac_tfm_ctx)
+ SM4_BLOCK_SIZE * 2,
@@ -699,7 +660,7 @@ static struct shash_alg sm4_mac_algs[] = {
.digestsize = SM4_BLOCK_SIZE,
.init = sm4_mac_init,
.update = sm4_mac_update,
- .final = sm4_cmac_final,
+ .finup = sm4_cmac_finup,
.setkey = sm4_cmac_setkey,
.descsize = sizeof(struct sm4_mac_desc_ctx),
}, {
@@ -707,6 +668,8 @@ static struct shash_alg sm4_mac_algs[] = {
.cra_name = "xcbc(sm4)",
.cra_driver_name = "xcbc-sm4-ce",
.cra_priority = 400,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINAL_NONZERO,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_mac_tfm_ctx)
+ SM4_BLOCK_SIZE * 2,
@@ -715,7 +678,7 @@ static struct shash_alg sm4_mac_algs[] = {
.digestsize = SM4_BLOCK_SIZE,
.init = sm4_mac_init,
.update = sm4_mac_update,
- .final = sm4_cmac_final,
+ .finup = sm4_cmac_finup,
.setkey = sm4_xcbc_setkey,
.descsize = sizeof(struct sm4_mac_desc_ctx),
}, {
@@ -723,14 +686,15 @@ static struct shash_alg sm4_mac_algs[] = {
.cra_name = "cbcmac(sm4)",
.cra_driver_name = "cbcmac-sm4-ce",
.cra_priority = 400,
- .cra_blocksize = 1,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
+ .cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_mac_tfm_ctx),
.cra_module = THIS_MODULE,
},
.digestsize = SM4_BLOCK_SIZE,
.init = sm4_mac_init,
.update = sm4_mac_update,
- .final = sm4_cbcmac_final,
+ .finup = sm4_cbcmac_finup,
.setkey = sm4_cbcmac_setkey,
.descsize = sizeof(struct sm4_mac_desc_ctx),
}
diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h
index 81e4157f92b7..71493b760b83 100644
--- a/arch/arm64/include/asm/cpu.h
+++ b/arch/arm64/include/asm/cpu.h
@@ -44,6 +44,7 @@ struct cpuinfo_arm64 {
u64 reg_dczid;
u64 reg_midr;
u64 reg_revidr;
+ u64 reg_aidr;
u64 reg_gmid;
u64 reg_smidr;
u64 reg_mpamidr;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index dffff6763812..661735616787 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -134,6 +134,7 @@
#define HISI_CPU_PART_TSV110 0xD01
#define HISI_CPU_PART_HIP09 0xD02
+#define HISI_CPU_PART_HIP12 0xD06
#define APPLE_CPU_PART_M1_ICESTORM 0x022
#define APPLE_CPU_PART_M1_FIRESTORM 0x023
@@ -222,6 +223,7 @@
#define MIDR_FUJITSU_A64FX MIDR_CPU_MODEL(ARM_CPU_IMP_FUJITSU, FUJITSU_CPU_PART_A64FX)
#define MIDR_HISI_TSV110 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_TSV110)
#define MIDR_HISI_HIP09 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP09)
+#define MIDR_HISI_HIP12 MIDR_CPU_MODEL(ARM_CPU_IMP_HISI, HISI_CPU_PART_HIP12)
#define MIDR_APPLE_M1_ICESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM)
#define MIDR_APPLE_M1_FIRESTORM MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM)
#define MIDR_APPLE_M1_ICESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_PRO)
diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index d40e427ddad9..1e7c7475e43f 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -38,7 +38,7 @@
orr x0, x0, #HCR_E2H
.LnVHE_\@:
- msr hcr_el2, x0
+ msr_hcr_el2 x0
isb
.endm
@@ -204,26 +204,28 @@
orr x0, x0, #(1 << 62)
.Lskip_spe_fgt_\@:
+
+.Lset_debug_fgt_\@:
msr_s SYS_HDFGRTR_EL2, x0
msr_s SYS_HDFGWTR_EL2, x0
mov x0, xzr
mrs x1, id_aa64pfr1_el1
ubfx x1, x1, #ID_AA64PFR1_EL1_SME_SHIFT, #4
- cbz x1, .Lskip_debug_fgt_\@
+ cbz x1, .Lskip_sme_fgt_\@
/* Disable nVHE traps of TPIDR2 and SMPRI */
- orr x0, x0, #HFGxTR_EL2_nSMPRI_EL1_MASK
- orr x0, x0, #HFGxTR_EL2_nTPIDR2_EL0_MASK
+ orr x0, x0, #HFGRTR_EL2_nSMPRI_EL1_MASK
+ orr x0, x0, #HFGRTR_EL2_nTPIDR2_EL0_MASK
-.Lskip_debug_fgt_\@:
+.Lskip_sme_fgt_\@:
mrs_s x1, SYS_ID_AA64MMFR3_EL1
ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4
cbz x1, .Lskip_pie_fgt_\@
/* Disable trapping of PIR_EL1 / PIRE0_EL1 */
- orr x0, x0, #HFGxTR_EL2_nPIR_EL1
- orr x0, x0, #HFGxTR_EL2_nPIRE0_EL1
+ orr x0, x0, #HFGRTR_EL2_nPIR_EL1
+ orr x0, x0, #HFGRTR_EL2_nPIRE0_EL1
.Lskip_pie_fgt_\@:
mrs_s x1, SYS_ID_AA64MMFR3_EL1
@@ -231,17 +233,19 @@
cbz x1, .Lskip_poe_fgt_\@
/* Disable trapping of POR_EL0 */
- orr x0, x0, #HFGxTR_EL2_nPOR_EL0
+ orr x0, x0, #HFGRTR_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_\@
+ cbz x1, .Lskip_gce_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
+ orr x0, x0, #HFGRTR_EL2_nGCS_EL1_MASK
+ orr x0, x0, #HFGRTR_EL2_nGCS_EL0_MASK
+
+.Lskip_gce_fgt_\@:
.Lset_fgt_\@:
msr_s SYS_HFGRTR_EL2, x0
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index e4f77757937e..e1deed824464 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -20,7 +20,8 @@
#define ESR_ELx_EC_FP_ASIMD UL(0x07)
#define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */
#define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */
-/* Unallocated EC: 0x0A - 0x0B */
+#define ESR_ELx_EC_OTHER UL(0x0A)
+/* Unallocated EC: 0x0B */
#define ESR_ELx_EC_CP14_64 UL(0x0C)
#define ESR_ELx_EC_BTI UL(0x0D)
#define ESR_ELx_EC_ILL UL(0x0E)
@@ -99,6 +100,8 @@
#define ESR_ELx_AET_CE (UL(6) << ESR_ELx_AET_SHIFT)
/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_VNCR_SHIFT (13)
+#define ESR_ELx_VNCR (UL(1) << ESR_ELx_VNCR_SHIFT)
#define ESR_ELx_SET_SHIFT (11)
#define ESR_ELx_SET_MASK (UL(3) << ESR_ELx_SET_SHIFT)
#define ESR_ELx_FnV_SHIFT (10)
@@ -181,6 +184,13 @@
#define ESR_ELx_WFx_ISS_WFE (UL(1) << 0)
#define ESR_ELx_xVC_IMM_MASK ((UL(1) << 16) - 1)
+/* ISS definitions for LD64B/ST64B/{T,P}SBCSYNC instructions */
+#define ESR_ELx_ISS_OTHER_ST64BV (0)
+#define ESR_ELx_ISS_OTHER_ST64BV0 (1)
+#define ESR_ELx_ISS_OTHER_LDST64B (2)
+#define ESR_ELx_ISS_OTHER_TSBCSYNC (3)
+#define ESR_ELx_ISS_OTHER_PSBCSYNC (4)
+
#define DISR_EL1_IDS (UL(1) << 24)
/*
* DISR_EL1 and ESR_ELx share the bottom 13 bits, but the RES0 bits may mean
@@ -378,12 +388,14 @@
/*
* ISS values for SME traps
*/
+#define ESR_ELx_SME_ISS_SMTC_MASK GENMASK(2, 0)
+#define ESR_ELx_SME_ISS_SMTC(esr) ((esr) & ESR_ELx_SME_ISS_SMTC_MASK)
-#define ESR_ELx_SME_ISS_SME_DISABLED 0
-#define ESR_ELx_SME_ISS_ILL 1
-#define ESR_ELx_SME_ISS_SM_DISABLED 2
-#define ESR_ELx_SME_ISS_ZA_DISABLED 3
-#define ESR_ELx_SME_ISS_ZT_DISABLED 4
+#define ESR_ELx_SME_ISS_SMTC_SME_DISABLED 0
+#define ESR_ELx_SME_ISS_SMTC_ILL 1
+#define ESR_ELx_SME_ISS_SMTC_SM_DISABLED 2
+#define ESR_ELx_SME_ISS_SMTC_ZA_DISABLED 3
+#define ESR_ELx_SME_ISS_SMTC_ZT_DISABLED 4
/* ISS field definitions for MOPS exceptions */
#define ESR_ELx_MOPS_ISS_MEM_INST (UL(1) << 24)
@@ -440,6 +452,11 @@ static inline bool esr_is_cfi_brk(unsigned long esr)
(esr_brk_comment(esr) & ~CFI_BRK_IMM_MASK) == CFI_BRK_IMM_BASE;
}
+static inline bool esr_is_ubsan_brk(unsigned long esr)
+{
+ return (esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM;
+}
+
static inline bool esr_fsc_is_translation_fault(unsigned long esr)
{
esr = esr & ESR_ELx_FSC;
diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h
index 87e307804b99..635a43c4ec85 100644
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -48,6 +48,12 @@ enum fixed_addresses {
FIX_EARLYCON_MEM_BASE,
FIX_TEXT_POKE0,
+#ifdef CONFIG_KVM
+ /* One slot per CPU, mapping the guest's VNCR page at EL2. */
+ FIX_VNCR_END,
+ FIX_VNCR = FIX_VNCR_END + NR_CPUS,
+#endif
+
#ifdef CONFIG_ACPI_APEI_GHES
/* Used for GHES mapping from assorted contexts */
FIX_APEI_GHES_IRQ,
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 564bc09b3e06..b8cf0ea43cc0 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -6,6 +6,7 @@
#define __ASM_FP_H
#include <asm/errno.h>
+#include <asm/percpu.h>
#include <asm/ptrace.h>
#include <asm/processor.h>
#include <asm/sigcontext.h>
@@ -76,7 +77,6 @@ extern void fpsimd_load_state(struct user_fpsimd_state *state);
extern void fpsimd_thread_switch(struct task_struct *next);
extern void fpsimd_flush_thread(void);
-extern void fpsimd_signal_preserve_current_state(void);
extern void fpsimd_preserve_current_state(void);
extern void fpsimd_restore_current_state(void);
extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
@@ -93,9 +93,12 @@ struct cpu_fp_state {
enum fp_type to_save;
};
+DECLARE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+
extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state);
extern void fpsimd_flush_task_state(struct task_struct *target);
+extern void fpsimd_save_and_flush_current_state(void);
extern void fpsimd_save_and_flush_cpu_state(void);
static inline bool thread_sm_enabled(struct thread_struct *thread)
@@ -108,6 +111,8 @@ static inline bool thread_za_enabled(struct thread_struct *thread)
return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK);
}
+extern void task_smstop_sm(struct task_struct *task);
+
/* Maximum VL that SVE/SME VL-agnostic software can transparently support */
#define VL_ARCH_MAX 0x100
@@ -195,10 +200,8 @@ struct vl_info {
extern void sve_alloc(struct task_struct *task, bool flush);
extern void fpsimd_release_task(struct task_struct *task);
-extern void fpsimd_sync_to_sve(struct task_struct *task);
-extern void fpsimd_force_sync_to_sve(struct task_struct *task);
-extern void sve_sync_to_fpsimd(struct task_struct *task);
-extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task);
+extern void fpsimd_sync_from_effective_state(struct task_struct *task);
+extern void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task);
extern int vec_set_vector_length(struct task_struct *task, enum vec_type type,
unsigned long vl, unsigned long flags);
@@ -292,14 +295,29 @@ static inline bool sve_vq_available(unsigned int vq)
return vq_available(ARM64_VEC_SVE, vq);
}
-size_t sve_state_size(struct task_struct const *task);
+static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl)
+{
+ unsigned int vl = max(sve_vl, sme_vl);
+ return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+}
+
+/*
+ * Return how many bytes of memory are required to store the full SVE
+ * state for task, given task's currently configured vector length.
+ */
+static inline size_t sve_state_size(struct task_struct const *task)
+{
+ unsigned int sve_vl = task_get_sve_vl(task);
+ unsigned int sme_vl = task_get_sme_vl(task);
+ return __sve_state_size(sve_vl, sme_vl);
+}
#else /* ! CONFIG_ARM64_SVE */
static inline void sve_alloc(struct task_struct *task, bool flush) { }
static inline void fpsimd_release_task(struct task_struct *task) { }
-static inline void sve_sync_to_fpsimd(struct task_struct *task) { }
-static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { }
+static inline void fpsimd_sync_from_effective_state(struct task_struct *task) { }
+static inline void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task) { }
static inline int sve_max_virtualisable_vl(void)
{
@@ -333,6 +351,11 @@ static inline void vec_update_vq_map(enum vec_type t) { }
static inline int vec_verify_vq_map(enum vec_type t) { return 0; }
static inline void sve_setup(void) { }
+static inline size_t __sve_state_size(unsigned int sve_vl, unsigned int sme_vl)
+{
+ return 0;
+}
+
static inline size_t sve_state_size(struct task_struct const *task)
{
return 0;
@@ -385,6 +408,16 @@ extern int sme_set_current_vl(unsigned long arg);
extern int sme_get_current_vl(void);
extern void sme_suspend_exit(void);
+static inline size_t __sme_state_size(unsigned int sme_vl)
+{
+ size_t size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(sme_vl));
+
+ if (system_supports_sme2())
+ size += ZT_SIG_REG_SIZE;
+
+ return size;
+}
+
/*
* Return how many bytes of memory are required to store the full SME
* specific state for task, given task's currently configured vector
@@ -392,15 +425,7 @@ extern void sme_suspend_exit(void);
*/
static inline size_t sme_state_size(struct task_struct const *task)
{
- unsigned int vl = task_get_sme_vl(task);
- size_t size;
-
- size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl));
-
- if (system_supports_sme2())
- size += ZT_SIG_REG_SIZE;
-
- return size;
+ return __sme_state_size(task_get_sme_vl(task));
}
#else
@@ -421,6 +446,11 @@ static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; }
static inline int sme_get_current_vl(void) { return -EINVAL; }
static inline void sme_suspend_exit(void) { }
+static inline size_t __sme_state_size(unsigned int sme_vl)
+{
+ return 0;
+}
+
static inline size_t sme_state_size(struct task_struct const *task)
{
return 0;
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index cbfa7b6f2e09..77d6b8c63d4e 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -41,7 +41,7 @@ do { \
\
___hcr = read_sysreg(hcr_el2); \
if (!(___hcr & HCR_TGE)) { \
- write_sysreg(___hcr | HCR_TGE, hcr_el2); \
+ write_sysreg_hcr(___hcr | HCR_TGE); \
isb(); \
} \
/* \
@@ -82,7 +82,7 @@ do { \
*/ \
barrier(); \
if (!___ctx->cnt && !(___hcr & HCR_TGE)) \
- write_sysreg(___hcr, hcr_el2); \
+ write_sysreg_hcr(___hcr); \
} while (0)
static inline void ack_bad_irq(unsigned int irq)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 07fbf5bf85a7..2a8155c4a882 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -69,29 +69,38 @@ extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
#include <asm-generic/hugetlb.h>
-#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
-static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
- unsigned long start,
- unsigned long end)
+static inline void __flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end,
+ unsigned long stride,
+ bool last_level)
{
- unsigned long stride = huge_page_size(hstate_vma(vma));
-
switch (stride) {
#ifndef __PAGETABLE_PMD_FOLDED
case PUD_SIZE:
- __flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+ __flush_tlb_range(vma, start, end, PUD_SIZE, last_level, 1);
break;
#endif
case CONT_PMD_SIZE:
case PMD_SIZE:
- __flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+ __flush_tlb_range(vma, start, end, PMD_SIZE, last_level, 2);
break;
case CONT_PTE_SIZE:
- __flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+ __flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, 3);
break;
default:
- __flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+ __flush_tlb_range(vma, start, end, PAGE_SIZE, last_level, TLBI_TTL_UNKNOWN);
}
}
+#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+ unsigned long start,
+ unsigned long end)
+{
+ unsigned long stride = huge_page_size(hstate_vma(vma));
+
+ __flush_hugetlb_tlb_range(vma, start, end, stride, false);
+}
+
#endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index e9c8a581e16f..1da290aeedce 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -12,67 +12,70 @@
#include <asm/sysreg.h>
#include <asm/types.h>
-/* Hyp Configuration Register (HCR) bits */
-
-#define HCR_TID5 (UL(1) << 58)
-#define HCR_DCT (UL(1) << 57)
-#define HCR_ATA_SHIFT 56
-#define HCR_ATA (UL(1) << HCR_ATA_SHIFT)
-#define HCR_TTLBOS (UL(1) << 55)
-#define HCR_TTLBIS (UL(1) << 54)
-#define HCR_ENSCXT (UL(1) << 53)
-#define HCR_TOCU (UL(1) << 52)
-#define HCR_AMVOFFEN (UL(1) << 51)
-#define HCR_TICAB (UL(1) << 50)
-#define HCR_TID4 (UL(1) << 49)
-#define HCR_FIEN (UL(1) << 47)
-#define HCR_FWB (UL(1) << 46)
-#define HCR_NV2 (UL(1) << 45)
-#define HCR_AT (UL(1) << 44)
-#define HCR_NV1 (UL(1) << 43)
-#define HCR_NV (UL(1) << 42)
-#define HCR_API (UL(1) << 41)
-#define HCR_APK (UL(1) << 40)
-#define HCR_TEA (UL(1) << 37)
-#define HCR_TERR (UL(1) << 36)
-#define HCR_TLOR (UL(1) << 35)
-#define HCR_E2H (UL(1) << 34)
-#define HCR_ID (UL(1) << 33)
-#define HCR_CD (UL(1) << 32)
-#define HCR_RW_SHIFT 31
-#define HCR_RW (UL(1) << HCR_RW_SHIFT)
-#define HCR_TRVM (UL(1) << 30)
-#define HCR_HCD (UL(1) << 29)
-#define HCR_TDZ (UL(1) << 28)
-#define HCR_TGE (UL(1) << 27)
-#define HCR_TVM (UL(1) << 26)
-#define HCR_TTLB (UL(1) << 25)
-#define HCR_TPU (UL(1) << 24)
-#define HCR_TPC (UL(1) << 23) /* HCR_TPCP if FEAT_DPB */
-#define HCR_TSW (UL(1) << 22)
-#define HCR_TACR (UL(1) << 21)
-#define HCR_TIDCP (UL(1) << 20)
-#define HCR_TSC (UL(1) << 19)
-#define HCR_TID3 (UL(1) << 18)
-#define HCR_TID2 (UL(1) << 17)
-#define HCR_TID1 (UL(1) << 16)
-#define HCR_TID0 (UL(1) << 15)
-#define HCR_TWE (UL(1) << 14)
-#define HCR_TWI (UL(1) << 13)
-#define HCR_DC (UL(1) << 12)
-#define HCR_BSU (3 << 10)
-#define HCR_BSU_IS (UL(1) << 10)
-#define HCR_FB (UL(1) << 9)
-#define HCR_VSE (UL(1) << 8)
-#define HCR_VI (UL(1) << 7)
-#define HCR_VF (UL(1) << 6)
-#define HCR_AMO (UL(1) << 5)
-#define HCR_IMO (UL(1) << 4)
-#define HCR_FMO (UL(1) << 3)
-#define HCR_PTW (UL(1) << 2)
-#define HCR_SWIO (UL(1) << 1)
-#define HCR_VM (UL(1) << 0)
-#define HCR_RES0 ((UL(1) << 48) | (UL(1) << 39))
+/*
+ * Because I'm terribly lazy and that repainting the whole of the KVM
+ * code with the proper names is a pain, use a helper to map the names
+ * inherited from AArch32 with the new fancy nomenclature. One day...
+ */
+#define __HCR(x) HCR_EL2_##x
+
+#define HCR_TID5 __HCR(TID5)
+#define HCR_DCT __HCR(DCT)
+#define HCR_ATA_SHIFT __HCR(ATA_SHIFT)
+#define HCR_ATA __HCR(ATA)
+#define HCR_TTLBOS __HCR(TTLBOS)
+#define HCR_TTLBIS __HCR(TTLBIS)
+#define HCR_ENSCXT __HCR(EnSCXT)
+#define HCR_TOCU __HCR(TOCU)
+#define HCR_AMVOFFEN __HCR(AMVOFFEN)
+#define HCR_TICAB __HCR(TICAB)
+#define HCR_TID4 __HCR(TID4)
+#define HCR_FIEN __HCR(FIEN)
+#define HCR_FWB __HCR(FWB)
+#define HCR_NV2 __HCR(NV2)
+#define HCR_AT __HCR(AT)
+#define HCR_NV1 __HCR(NV1)
+#define HCR_NV __HCR(NV)
+#define HCR_API __HCR(API)
+#define HCR_APK __HCR(APK)
+#define HCR_TEA __HCR(TEA)
+#define HCR_TERR __HCR(TERR)
+#define HCR_TLOR __HCR(TLOR)
+#define HCR_E2H __HCR(E2H)
+#define HCR_ID __HCR(ID)
+#define HCR_CD __HCR(CD)
+#define HCR_RW __HCR(RW)
+#define HCR_TRVM __HCR(TRVM)
+#define HCR_HCD __HCR(HCD)
+#define HCR_TDZ __HCR(TDZ)
+#define HCR_TGE __HCR(TGE)
+#define HCR_TVM __HCR(TVM)
+#define HCR_TTLB __HCR(TTLB)
+#define HCR_TPU __HCR(TPU)
+#define HCR_TPC __HCR(TPCP)
+#define HCR_TSW __HCR(TSW)
+#define HCR_TACR __HCR(TACR)
+#define HCR_TIDCP __HCR(TIDCP)
+#define HCR_TSC __HCR(TSC)
+#define HCR_TID3 __HCR(TID3)
+#define HCR_TID2 __HCR(TID2)
+#define HCR_TID1 __HCR(TID1)
+#define HCR_TID0 __HCR(TID0)
+#define HCR_TWE __HCR(TWE)
+#define HCR_TWI __HCR(TWI)
+#define HCR_DC __HCR(DC)
+#define HCR_BSU __HCR(BSU)
+#define HCR_BSU_IS __HCR(BSU_IS)
+#define HCR_FB __HCR(FB)
+#define HCR_VSE __HCR(VSE)
+#define HCR_VI __HCR(VI)
+#define HCR_VF __HCR(VF)
+#define HCR_AMO __HCR(AMO)
+#define HCR_IMO __HCR(IMO)
+#define HCR_FMO __HCR(FMO)
+#define HCR_PTW __HCR(PTW)
+#define HCR_SWIO __HCR(SWIO)
+#define HCR_VM __HCR(VM)
/*
* The bits we set in HCR:
@@ -312,56 +315,19 @@
GENMASK(15, 0))
/*
- * FGT register definitions
- *
- * RES0 and polarity masks as of DDI0487J.a, to be updated as needed.
- * We're not using the generated masks as they are usually ahead of
- * the published ARM ARM, which we use as a reference.
- *
- * Once we get to a point where the two describe the same thing, we'll
- * merge the definitions. One day.
- */
-#define __HFGRTR_EL2_RES0 HFGxTR_EL2_RES0
-#define __HFGRTR_EL2_MASK GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK ~(__HFGRTR_EL2_RES0 | __HFGRTR_EL2_MASK)
-
-/*
- * The HFGWTR bits are a subset of HFGRTR bits. To ensure we don't miss any
- * future additions, define __HFGWTR* macros relative to __HFGRTR* ones.
+ * Polarity masks for HCRX_EL2, limited to the bits that we know about
+ * at this point in time. It doesn't mean that we actually *handle*
+ * them, but that at least those that are not advertised to a guest
+ * will be RES0 for that guest.
*/
-#define __HFGRTR_ONLY_MASK (BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
- GENMASK(26, 25) | BIT(21) | BIT(18) | \
- GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
-#define __HFGWTR_EL2_RES0 (__HFGRTR_EL2_RES0 | __HFGRTR_ONLY_MASK)
-#define __HFGWTR_EL2_MASK (__HFGRTR_EL2_MASK & ~__HFGRTR_ONLY_MASK)
-#define __HFGWTR_EL2_nMASK ~(__HFGWTR_EL2_RES0 | __HFGWTR_EL2_MASK)
-
-#define __HFGITR_EL2_RES0 HFGITR_EL2_RES0
-#define __HFGITR_EL2_MASK (BIT(62) | BIT(60) | GENMASK(54, 0))
-#define __HFGITR_EL2_nMASK ~(__HFGITR_EL2_RES0 | __HFGITR_EL2_MASK)
-
-#define __HDFGRTR_EL2_RES0 HDFGRTR_EL2_RES0
-#define __HDFGRTR_EL2_MASK (BIT(63) | GENMASK(58, 50) | GENMASK(48, 43) | \
- GENMASK(41, 40) | GENMASK(37, 22) | \
- GENMASK(19, 9) | GENMASK(7, 0))
-#define __HDFGRTR_EL2_nMASK ~(__HDFGRTR_EL2_RES0 | __HDFGRTR_EL2_MASK)
-
-#define __HDFGWTR_EL2_RES0 HDFGWTR_EL2_RES0
-#define __HDFGWTR_EL2_MASK (GENMASK(57, 52) | GENMASK(50, 48) | \
- GENMASK(46, 44) | GENMASK(42, 41) | \
- GENMASK(37, 35) | GENMASK(33, 31) | \
- GENMASK(29, 23) | GENMASK(21, 10) | \
- GENMASK(8, 7) | GENMASK(5, 0))
-#define __HDFGWTR_EL2_nMASK ~(__HDFGWTR_EL2_RES0 | __HDFGWTR_EL2_MASK)
-
-#define __HAFGRTR_EL2_RES0 HAFGRTR_EL2_RES0
-#define __HAFGRTR_EL2_MASK (GENMASK(49, 17) | GENMASK(4, 0))
-#define __HAFGRTR_EL2_nMASK ~(__HAFGRTR_EL2_RES0 | __HAFGRTR_EL2_MASK)
-
-/* Similar definitions for HCRX_EL2 */
-#define __HCRX_EL2_RES0 HCRX_EL2_RES0
-#define __HCRX_EL2_MASK (BIT(6))
-#define __HCRX_EL2_nMASK ~(__HCRX_EL2_RES0 | __HCRX_EL2_MASK)
+#define __HCRX_EL2_MASK (BIT_ULL(6))
+#define __HCRX_EL2_nMASK (GENMASK_ULL(24, 14) | \
+ GENMASK_ULL(11, 7) | \
+ GENMASK_ULL(5, 0))
+#define __HCRX_EL2_RES0 ~(__HCRX_EL2_nMASK | __HCRX_EL2_MASK)
+#define __HCRX_EL2_RES1 ~(__HCRX_EL2_nMASK | \
+ __HCRX_EL2_MASK | \
+ __HCRX_EL2_RES0)
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 08ba91e6fb03..d941abc6b5ee 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -39,7 +39,7 @@
#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
-#define KVM_VCPU_MAX_FEATURES 7
+#define KVM_VCPU_MAX_FEATURES 9
#define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1)
#define KVM_REQ_SLEEP \
@@ -53,6 +53,7 @@
#define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7)
#define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8)
#define KVM_REQ_GUEST_HYP_IRQ_PENDING KVM_ARCH_REQ(9)
+#define KVM_REQ_MAP_L1_VNCR_EL2 KVM_ARCH_REQ(10)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
@@ -273,11 +274,17 @@ struct kvm_sysreg_masks;
enum fgt_group_id {
__NO_FGT_GROUP__,
- HFGxTR_GROUP,
+ HFGRTR_GROUP,
+ HFGWTR_GROUP = HFGRTR_GROUP,
HDFGRTR_GROUP,
HDFGWTR_GROUP = HDFGRTR_GROUP,
HFGITR_GROUP,
HAFGRTR_GROUP,
+ HFGRTR2_GROUP,
+ HFGWTR2_GROUP = HFGRTR2_GROUP,
+ HDFGRTR2_GROUP,
+ HDFGWTR2_GROUP = HDFGRTR2_GROUP,
+ HFGITR2_GROUP,
/* Must be last */
__NR_FGT_GROUP_IDS__
@@ -359,8 +366,8 @@ struct kvm_arch {
cpumask_var_t supported_cpus;
- /* PMCR_EL0.N value for the guest */
- u8 pmcr_n;
+ /* Maximum number of counters for the guest */
+ u8 nr_pmu_counters;
/* Iterator for idreg debugfs */
u8 idreg_debugfs_iter;
@@ -389,6 +396,9 @@ struct kvm_arch {
/* Masks for VNCR-backed and general EL2 sysregs */
struct kvm_sysreg_masks *sysreg_masks;
+ /* Count the number of VNCR_EL2 currently mapped */
+ atomic_t vncr_map_count;
+
/*
* For an untrusted host VM, 'pkvm.handle' is used to lookup
* the associated pKVM instance in the hypervisor.
@@ -561,6 +571,13 @@ enum vcpu_sysreg {
VNCR(HDFGRTR_EL2),
VNCR(HDFGWTR_EL2),
VNCR(HAFGRTR_EL2),
+ VNCR(HFGRTR2_EL2),
+ VNCR(HFGWTR2_EL2),
+ VNCR(HFGITR2_EL2),
+ VNCR(HDFGRTR2_EL2),
+ VNCR(HDFGWTR2_EL2),
+
+ VNCR(VNCR_EL2),
VNCR(CNTVOFF_EL2),
VNCR(CNTV_CVAL_EL0),
@@ -606,6 +623,37 @@ struct kvm_sysreg_masks {
} mask[NR_SYS_REGS - __SANITISED_REG_START__];
};
+struct fgt_masks {
+ const char *str;
+ u64 mask;
+ u64 nmask;
+ u64 res0;
+};
+
+extern struct fgt_masks hfgrtr_masks;
+extern struct fgt_masks hfgwtr_masks;
+extern struct fgt_masks hfgitr_masks;
+extern struct fgt_masks hdfgrtr_masks;
+extern struct fgt_masks hdfgwtr_masks;
+extern struct fgt_masks hafgrtr_masks;
+extern struct fgt_masks hfgrtr2_masks;
+extern struct fgt_masks hfgwtr2_masks;
+extern struct fgt_masks hfgitr2_masks;
+extern struct fgt_masks hdfgrtr2_masks;
+extern struct fgt_masks hdfgwtr2_masks;
+
+extern struct fgt_masks kvm_nvhe_sym(hfgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgwtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgitr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgwtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hafgrtr_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgrtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgwtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hfgitr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgrtr2_masks);
+extern struct fgt_masks kvm_nvhe_sym(hdfgwtr2_masks);
+
struct kvm_cpu_context {
struct user_pt_regs regs; /* sp = sp_el0 */
@@ -654,6 +702,8 @@ struct kvm_host_data {
#define KVM_HOST_DATA_FLAG_HAS_TRBE 1
#define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4
#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5
+#define KVM_HOST_DATA_FLAG_VCPU_IN_HYP_CONTEXT 6
+#define KVM_HOST_DATA_FLAG_L1_VNCR_MAPPED 7
unsigned long flags;
struct kvm_cpu_context host_ctxt;
@@ -730,6 +780,8 @@ struct vcpu_reset_state {
bool reset;
};
+struct vncr_tlb;
+
struct kvm_vcpu_arch {
struct kvm_cpu_context ctxt;
@@ -824,6 +876,9 @@ struct kvm_vcpu_arch {
/* Per-vcpu CCSIDR override or NULL */
u32 *ccsidr;
+
+ /* Per-vcpu TLB for VNCR_EL2 -- NULL when !NV */
+ struct vncr_tlb *vncr_tlb;
};
/*
@@ -971,20 +1026,22 @@ struct kvm_vcpu_arch {
#define vcpu_sve_zcr_elx(vcpu) \
(unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1)
-#define vcpu_sve_state_size(vcpu) ({ \
+#define sve_state_size_from_vl(sve_max_vl) ({ \
size_t __size_ret; \
- unsigned int __vcpu_vq; \
+ unsigned int __vq; \
\
- if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) { \
+ if (WARN_ON(!sve_vl_valid(sve_max_vl))) { \
__size_ret = 0; \
} else { \
- __vcpu_vq = vcpu_sve_max_vq(vcpu); \
- __size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq); \
+ __vq = sve_vq_from_vl(sve_max_vl); \
+ __size_ret = SVE_SIG_REGS_SIZE(__vq); \
} \
\
__size_ret; \
})
+#define vcpu_sve_state_size(vcpu) sve_state_size_from_vl((vcpu)->arch.sve_max_vl)
+
#define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \
KVM_GUESTDBG_USE_SW_BP | \
KVM_GUESTDBG_USE_HW | \
@@ -1550,12 +1607,16 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val);
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) \
+#define __kvm_has_feat(kvm, id, fld, limit) \
kvm_cmp_feat(kvm, id, fld, >=, limit)
-#define kvm_has_feat_enum(kvm, id, fld, val) \
+#define kvm_has_feat(kvm, ...) __kvm_has_feat(kvm, __VA_ARGS__)
+
+#define __kvm_has_feat_enum(kvm, id, fld, val) \
kvm_cmp_feat_unsigned(kvm, id, fld, ==, val)
+#define kvm_has_feat_enum(kvm, ...) __kvm_has_feat_enum(kvm, __VA_ARGS__)
+
#define kvm_has_feat_range(kvm, id, fld, min, max) \
(kvm_cmp_feat(kvm, id, fld, >=, min) && \
kvm_cmp_feat(kvm, id, fld, <=, max))
@@ -1593,4 +1654,9 @@ static inline bool kvm_arch_has_irq_bypass(void)
return true;
}
+void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt);
+void get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg, u64 *res0, u64 *res1);
+void check_feature_map(void);
+
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h
index 692f403c1896..0bd07ea068a1 100644
--- a/arch/arm64/include/asm/kvm_nested.h
+++ b/arch/arm64/include/asm/kvm_nested.h
@@ -231,6 +231,38 @@ static inline u64 kvm_encode_nested_level(struct kvm_s2_trans *trans)
shift; \
})
+static inline u64 decode_range_tlbi(u64 val, u64 *range, u16 *asid)
+{
+ u64 base, tg, num, scale;
+ int shift;
+
+ tg = FIELD_GET(GENMASK(47, 46), val);
+
+ switch(tg) {
+ case 1:
+ shift = 12;
+ break;
+ case 2:
+ shift = 14;
+ break;
+ case 3:
+ default: /* IMPDEF: handle tg==0 as 64k */
+ shift = 16;
+ break;
+ }
+
+ base = (val & GENMASK(36, 0)) << shift;
+
+ if (asid)
+ *asid = FIELD_GET(TLBIR_ASID_MASK, val);
+
+ scale = FIELD_GET(GENMASK(45, 44), val);
+ num = FIELD_GET(GENMASK(43, 39), val);
+ *range = __TLBI_RANGE_PAGES(num, scale) << shift;
+
+ return base;
+}
+
static inline unsigned int ps_to_output_size(unsigned int ps)
{
switch (ps) {
@@ -245,4 +277,72 @@ static inline unsigned int ps_to_output_size(unsigned int ps)
}
}
+enum trans_regime {
+ TR_EL10,
+ TR_EL20,
+ TR_EL2,
+};
+
+struct s1_walk_info {
+ u64 baddr;
+ enum trans_regime regime;
+ unsigned int max_oa_bits;
+ unsigned int pgshift;
+ unsigned int txsz;
+ int sl;
+ bool as_el0;
+ bool hpd;
+ bool e0poe;
+ bool poe;
+ bool pan;
+ bool be;
+ bool s2;
+};
+
+struct s1_walk_result {
+ union {
+ struct {
+ u64 desc;
+ u64 pa;
+ s8 level;
+ u8 APTable;
+ bool nG;
+ u16 asid;
+ bool UXNTable;
+ bool PXNTable;
+ bool uwxn;
+ bool uov;
+ bool ur;
+ bool uw;
+ bool ux;
+ bool pwxn;
+ bool pov;
+ bool pr;
+ bool pw;
+ bool px;
+ };
+ struct {
+ u8 fst;
+ bool ptw;
+ bool s2;
+ };
+ };
+ bool failed;
+};
+
+int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
+ struct s1_walk_result *wr, u64 va);
+
+/* VNCR management */
+int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu);
+int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu);
+void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val);
+
+#define vncr_fixmap(c) \
+ ({ \
+ u32 __c = (c); \
+ BUG_ON(__c >= NR_CPUS); \
+ (FIX_VNCR - __c); \
+ })
+
#endif /* __ARM64_KVM_NESTED_H */
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index 6b9d274052c7..2888b5d03757 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -59,6 +59,11 @@ typedef u64 kvm_pte_t;
#define KVM_PHYS_INVALID (-1ULL)
+#define KVM_PTE_TYPE BIT(1)
+#define KVM_PTE_TYPE_BLOCK 0
+#define KVM_PTE_TYPE_PAGE 1
+#define KVM_PTE_TYPE_TABLE 1
+
#define KVM_PTE_LEAF_ATTR_LO GENMASK(11, 2)
#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX GENMASK(4, 2)
@@ -413,7 +418,7 @@ static inline bool kvm_pgtable_walk_lock_held(void)
*/
struct kvm_pgtable {
union {
- struct rb_root pkvm_mappings;
+ struct rb_root_cached pkvm_mappings;
struct {
u32 ia_bits;
s8 start_level;
diff --git a/arch/arm64/include/asm/kvm_pkvm.h b/arch/arm64/include/asm/kvm_pkvm.h
index abd693ce5b93..ea58282f59bb 100644
--- a/arch/arm64/include/asm/kvm_pkvm.h
+++ b/arch/arm64/include/asm/kvm_pkvm.h
@@ -135,6 +135,12 @@ static inline unsigned long host_s2_pgtable_pages(void)
return res;
}
+#ifdef CONFIG_NVHE_EL2_DEBUG
+static inline unsigned long pkvm_selftest_pages(void) { return 32; }
+#else
+static inline unsigned long pkvm_selftest_pages(void) { return 0; }
+#endif
+
#define KVM_FFA_MBOX_NR_PAGES 1
static inline unsigned long hyp_ffa_proxy_pages(void)
@@ -167,6 +173,8 @@ struct pkvm_mapping {
struct rb_node node;
u64 gfn;
u64 pfn;
+ u64 nr_pages;
+ u64 __subtree_last; /* Internal member for interval tree */
};
int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
diff --git a/arch/arm64/include/asm/mem_encrypt.h b/arch/arm64/include/asm/mem_encrypt.h
index a2a1eeb36d4b..314b2b52025f 100644
--- a/arch/arm64/include/asm/mem_encrypt.h
+++ b/arch/arm64/include/asm/mem_encrypt.h
@@ -4,6 +4,8 @@
#include <asm/rsi.h>
+struct device;
+
struct arm64_mem_crypt_ops {
int (*encrypt)(unsigned long addr, int numpages);
int (*decrypt)(unsigned long addr, int numpages);
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index d3b538be1500..5285757ee0c1 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -40,6 +40,85 @@
#include <linux/sched.h>
#include <linux/page_table_check.h>
+static inline void emit_pte_barriers(void)
+{
+ /*
+ * These barriers are emitted under certain conditions after a pte entry
+ * was modified (see e.g. __set_pte_complete()). The dsb makes the store
+ * visible to the table walker. The isb ensures that any previous
+ * speculative "invalid translation" marker that is in the CPU's
+ * pipeline gets cleared, so that any access to that address after
+ * setting the pte to valid won't cause a spurious fault. If the thread
+ * gets preempted after storing to the pgtable but before emitting these
+ * barriers, __switch_to() emits a dsb which ensure the walker gets to
+ * see the store. There is no guarantee of an isb being issued though.
+ * This is safe because it will still get issued (albeit on a
+ * potentially different CPU) when the thread starts running again,
+ * before any access to the address.
+ */
+ dsb(ishst);
+ isb();
+}
+
+static inline void queue_pte_barriers(void)
+{
+ unsigned long flags;
+
+ if (in_interrupt()) {
+ emit_pte_barriers();
+ return;
+ }
+
+ flags = read_thread_flags();
+
+ if (flags & BIT(TIF_LAZY_MMU)) {
+ /* Avoid the atomic op if already set. */
+ if (!(flags & BIT(TIF_LAZY_MMU_PENDING)))
+ set_thread_flag(TIF_LAZY_MMU_PENDING);
+ } else {
+ emit_pte_barriers();
+ }
+}
+
+#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+ /*
+ * lazy_mmu_mode is not supposed to permit nesting. But in practice this
+ * does happen with CONFIG_DEBUG_PAGEALLOC, where a page allocation
+ * inside a lazy_mmu_mode section (such as zap_pte_range()) will change
+ * permissions on the linear map with apply_to_page_range(), which
+ * re-enters lazy_mmu_mode. So we tolerate nesting in our
+ * implementation. The first call to arch_leave_lazy_mmu_mode() will
+ * flush and clear the flag such that the remainder of the work in the
+ * outer nest behaves as if outside of lazy mmu mode. This is safe and
+ * keeps tracking simple.
+ */
+
+ if (in_interrupt())
+ return;
+
+ set_thread_flag(TIF_LAZY_MMU);
+}
+
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+ if (in_interrupt())
+ return;
+
+ if (test_and_clear_thread_flag(TIF_LAZY_MMU_PENDING))
+ emit_pte_barriers();
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+ if (in_interrupt())
+ return;
+
+ arch_flush_lazy_mmu_mode();
+ clear_thread_flag(TIF_LAZY_MMU);
+}
+
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
@@ -320,18 +399,20 @@ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
WRITE_ONCE(*ptep, pte);
}
-static inline void __set_pte(pte_t *ptep, pte_t pte)
+static inline void __set_pte_complete(pte_t pte)
{
- __set_pte_nosync(ptep, pte);
-
/*
* Only if the new pte is valid and kernel, otherwise TLB maintenance
- * or update_mmu_cache() have the necessary barriers.
+ * has the necessary barriers.
*/
- if (pte_valid_not_user(pte)) {
- dsb(ishst);
- isb();
- }
+ if (pte_valid_not_user(pte))
+ queue_pte_barriers();
+}
+
+static inline void __set_pte(pte_t *ptep, pte_t pte)
+{
+ __set_pte_nosync(ptep, pte);
+ __set_pte_complete(pte);
}
static inline pte_t __ptep_get(pte_t *ptep)
@@ -423,23 +504,6 @@ static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte));
}
-static inline void __set_ptes(struct mm_struct *mm,
- unsigned long __always_unused addr,
- pte_t *ptep, pte_t pte, unsigned int nr)
-{
- page_table_check_ptes_set(mm, ptep, pte, nr);
- __sync_cache_and_tags(pte, nr);
-
- for (;;) {
- __check_safe_pte_update(mm, ptep, pte);
- __set_pte(ptep, pte);
- if (--nr == 0)
- break;
- ptep++;
- pte = pte_advance_pfn(pte, 1);
- }
-}
-
/*
* Hugetlb definitions.
*/
@@ -649,30 +713,64 @@ static inline pgprot_t pud_pgprot(pud_t pud)
return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud));
}
-static inline void __set_pte_at(struct mm_struct *mm,
- unsigned long __always_unused addr,
- pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void __set_ptes_anysz(struct mm_struct *mm, pte_t *ptep,
+ pte_t pte, unsigned int nr,
+ unsigned long pgsize)
{
- __sync_cache_and_tags(pte, nr);
- __check_safe_pte_update(mm, ptep, pte);
- __set_pte(ptep, pte);
+ unsigned long stride = pgsize >> PAGE_SHIFT;
+
+ switch (pgsize) {
+ case PAGE_SIZE:
+ page_table_check_ptes_set(mm, ptep, pte, nr);
+ break;
+ case PMD_SIZE:
+ page_table_check_pmds_set(mm, (pmd_t *)ptep, pte_pmd(pte), nr);
+ break;
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SIZE:
+ page_table_check_puds_set(mm, (pud_t *)ptep, pte_pud(pte), nr);
+ break;
+#endif
+ default:
+ VM_WARN_ON(1);
+ }
+
+ __sync_cache_and_tags(pte, nr * stride);
+
+ for (;;) {
+ __check_safe_pte_update(mm, ptep, pte);
+ __set_pte_nosync(ptep, pte);
+ if (--nr == 0)
+ break;
+ ptep++;
+ pte = pte_advance_pfn(pte, stride);
+ }
+
+ __set_pte_complete(pte);
}
-static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp, pmd_t pmd)
+static inline void __set_ptes(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pte_t *ptep, pte_t pte, unsigned int nr)
{
- page_table_check_pmd_set(mm, pmdp, pmd);
- return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
- PMD_SIZE >> PAGE_SHIFT);
+ __set_ptes_anysz(mm, ptep, pte, nr, PAGE_SIZE);
}
-static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
- pud_t *pudp, pud_t pud)
+static inline void __set_pmds(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pmd_t *pmdp, pmd_t pmd, unsigned int nr)
+{
+ __set_ptes_anysz(mm, (pte_t *)pmdp, pmd_pte(pmd), nr, PMD_SIZE);
+}
+#define set_pmd_at(mm, addr, pmdp, pmd) __set_pmds(mm, addr, pmdp, pmd, 1)
+
+static inline void __set_puds(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pud_t *pudp, pud_t pud, unsigned int nr)
{
- page_table_check_pud_set(mm, pudp, pud);
- return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
- PUD_SIZE >> PAGE_SHIFT);
+ __set_ptes_anysz(mm, (pte_t *)pudp, pud_pte(pud), nr, PUD_SIZE);
}
+#define set_pud_at(mm, addr, pudp, pud) __set_puds(mm, addr, pudp, pud, 1)
#define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d))
#define __phys_to_p4d_val(phys) __phys_to_pte_val(phys)
@@ -739,8 +837,7 @@ static inline int pmd_trans_huge(pmd_t pmd)
* If pmd is present-invalid, pmd_table() won't detect it
* as a table, so force the valid bit for the comparison.
*/
- return pmd_val(pmd) && pmd_present(pmd) &&
- !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
+ return pmd_present(pmd) && !pmd_table(__pmd(pmd_val(pmd) | PTE_VALID));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -754,8 +851,6 @@ static inline bool pud_table(pud_t pud) { return true; }
PUD_TYPE_TABLE)
#endif
-extern pgd_t init_pg_dir[];
-extern pgd_t init_pg_end[];
extern pgd_t swapper_pg_dir[];
extern pgd_t idmap_pg_dir[];
extern pgd_t tramp_pg_dir[];
@@ -780,10 +875,8 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
WRITE_ONCE(*pmdp, pmd);
- if (pmd_valid(pmd)) {
- dsb(ishst);
- isb();
- }
+ if (pmd_valid(pmd))
+ queue_pte_barriers();
}
static inline void pmd_clear(pmd_t *pmdp)
@@ -848,10 +941,8 @@ static inline void set_pud(pud_t *pudp, pud_t pud)
WRITE_ONCE(*pudp, pud);
- if (pud_valid(pud)) {
- dsb(ishst);
- isb();
- }
+ if (pud_valid(pud))
+ queue_pte_barriers();
}
static inline void pud_clear(pud_t *pudp)
@@ -930,8 +1021,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
}
WRITE_ONCE(*p4dp, p4d);
- dsb(ishst);
- isb();
+ queue_pte_barriers();
}
static inline void p4d_clear(p4d_t *p4dp)
@@ -1059,8 +1149,7 @@ static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
}
WRITE_ONCE(*pgdp, pgd);
- dsb(ishst);
- isb();
+ queue_pte_barriers();
}
static inline void pgd_clear(pgd_t *pgdp)
@@ -1301,16 +1390,37 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
}
#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)
+static inline pte_t __ptep_get_and_clear_anysz(struct mm_struct *mm,
+ pte_t *ptep,
+ unsigned long pgsize)
{
pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
- page_table_check_pte_clear(mm, pte);
+ switch (pgsize) {
+ case PAGE_SIZE:
+ page_table_check_pte_clear(mm, pte);
+ break;
+ case PMD_SIZE:
+ page_table_check_pmd_clear(mm, pte_pmd(pte));
+ break;
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SIZE:
+ page_table_check_pud_clear(mm, pte_pud(pte));
+ break;
+#endif
+ default:
+ VM_WARN_ON(1);
+ }
return pte;
}
+static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pte_t *ptep)
+{
+ return __ptep_get_and_clear_anysz(mm, ptep, PAGE_SIZE);
+}
+
static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned int nr, int full)
{
@@ -1347,11 +1457,7 @@ static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm,
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
unsigned long address, pmd_t *pmdp)
{
- pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
-
- page_table_check_pmd_clear(mm, pmd);
-
- return pmd;
+ return pte_pmd(__ptep_get_and_clear_anysz(mm, (pte_t *)pmdp, PMD_SIZE));
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/arch/arm64/include/asm/rsi_cmds.h b/arch/arm64/include/asm/rsi_cmds.h
index e6a211001bd3..2c8763876dfb 100644
--- a/arch/arm64/include/asm/rsi_cmds.h
+++ b/arch/arm64/include/asm/rsi_cmds.h
@@ -7,6 +7,8 @@
#define __ASM_RSI_CMDS_H
#include <linux/arm-smccc.h>
+#include <linux/string.h>
+#include <asm/memory.h>
#include <asm/rsi_smc.h>
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 40971ac1303f..51b0d594239e 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -11,6 +11,7 @@ extern char __alt_instructions[], __alt_instructions_end[];
extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
extern char __hyp_text_start[], __hyp_text_end[];
+extern char __hyp_data_start[], __hyp_data_end[];
extern char __hyp_rodata_start[], __hyp_rodata_end[];
extern char __hyp_reloc_begin[], __hyp_reloc_end[];
extern char __hyp_bss_start[], __hyp_bss_end[];
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 2639d3633073..cd853801a8f7 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -117,6 +117,7 @@
#define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31)
+/* Data cache zero operations */
#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2)
#define SYS_DC_IGSW sys_insn(1, 0, 7, 6, 4)
#define SYS_DC_IGDSW sys_insn(1, 0, 7, 6, 6)
@@ -153,11 +154,13 @@
#define SYS_DC_CIGVAC sys_insn(1, 3, 7, 14, 3)
#define SYS_DC_CIGDVAC sys_insn(1, 3, 7, 14, 5)
-/* Data cache zero operations */
#define SYS_DC_ZVA sys_insn(1, 3, 7, 4, 1)
#define SYS_DC_GVA sys_insn(1, 3, 7, 4, 3)
#define SYS_DC_GZVA sys_insn(1, 3, 7, 4, 4)
+#define SYS_DC_CIVAPS sys_insn(1, 0, 7, 15, 1)
+#define SYS_DC_CIGDVAPS sys_insn(1, 0, 7, 15, 5)
+
/*
* Automatically generated definitions for system registers, the
* manual encodings below are in the process of being converted to
@@ -497,12 +500,22 @@
#define __PMEV_op2(n) ((n) & 0x7)
#define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTSVRn_EL1(n) sys_reg(2, 0, 14, __CNTR_CRm(n), __PMEV_op2(n))
#define SYS_PMEVCNTRn_EL0(n) sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
#define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3))
#define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7)
+#define SYS_SPMCGCRn_EL1(n) sys_reg(2, 0, 9, 13, ((n) & 1))
+
+#define __SPMEV_op2(n) ((n) & 0x7)
+#define __SPMEV_crm(p, n) ((((p) & 7) << 1) | (((n) >> 3) & 1))
+#define SYS_SPMEVCNTRn_EL0(n) sys_reg(2, 3, 14, __SPMEV_crm(0b000, n), __SPMEV_op2(n))
+#define SYS_SPMEVFILT2Rn_EL0(n) sys_reg(2, 3, 14, __SPMEV_crm(0b011, n), __SPMEV_op2(n))
+#define SYS_SPMEVFILTRn_EL0(n) sys_reg(2, 3, 14, __SPMEV_crm(0b010, n), __SPMEV_op2(n))
+#define SYS_SPMEVTYPERn_EL0(n) sys_reg(2, 3, 14, __SPMEV_crm(0b001, n), __SPMEV_op2(n))
+
#define SYS_VPIDR_EL2 sys_reg(3, 4, 0, 0, 0)
#define SYS_VMPIDR_EL2 sys_reg(3, 4, 0, 0, 5)
@@ -521,7 +534,6 @@
#define SYS_VTTBR_EL2 sys_reg(3, 4, 2, 1, 0)
#define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2)
-#define SYS_VNCR_EL2 sys_reg(3, 4, 2, 2, 0)
#define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6)
#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0)
#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1)
@@ -608,28 +620,18 @@
/* VHE encodings for architectural EL0/1 system registers */
#define SYS_BRBCR_EL12 sys_reg(2, 5, 9, 0, 0)
-#define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0)
-#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2)
-#define SYS_SCTLR2_EL12 sys_reg(3, 5, 1, 0, 3)
-#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0)
-#define SYS_TRFCR_EL12 sys_reg(3, 5, 1, 2, 1)
-#define SYS_SMCR_EL12 sys_reg(3, 5, 1, 2, 6)
#define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0)
#define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1)
-#define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2)
-#define SYS_TCR2_EL12 sys_reg(3, 5, 2, 0, 3)
#define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0)
#define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1)
#define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0)
#define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1)
#define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0)
#define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0)
-#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0)
#define SYS_PMSCR_EL12 sys_reg(3, 5, 9, 9, 0)
#define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0)
#define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0)
#define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0)
-#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1)
#define SYS_SCXTNUM_EL12 sys_reg(3, 5, 13, 0, 7)
#define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0)
#define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0)
@@ -1091,6 +1093,15 @@
__emit_inst(0xd5000000|(\sreg)|(.L__gpr_num_\rt))
.endm
+ .macro msr_hcr_el2, reg
+#if IS_ENABLED(CONFIG_AMPERE_ERRATUM_AC04_CPU_23)
+ dsb nsh
+ msr hcr_el2, \reg
+ isb
+#else
+ msr hcr_el2, \reg
+#endif
+ .endm
#else
#include <linux/bitfield.h>
@@ -1178,6 +1189,13 @@
write_sysreg(__scs_new, sysreg); \
} while (0)
+#define sysreg_clear_set_hcr(clear, set) do { \
+ u64 __scs_val = read_sysreg(hcr_el2); \
+ u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
+ if (__scs_new != __scs_val) \
+ write_sysreg_hcr(__scs_new); \
+} while (0)
+
#define sysreg_clear_set_s(sysreg, clear, set) do { \
u64 __scs_val = read_sysreg_s(sysreg); \
u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
@@ -1185,6 +1203,17 @@
write_sysreg_s(__scs_new, sysreg); \
} while (0)
+#define write_sysreg_hcr(__val) do { \
+ if (IS_ENABLED(CONFIG_AMPERE_ERRATUM_AC04_CPU_23) && \
+ (!system_capabilities_finalized() || \
+ alternative_has_cap_unlikely(ARM64_WORKAROUND_AMPERE_AC04_CPU_23))) \
+ asm volatile("dsb nsh; msr hcr_el2, %x0; isb" \
+ : : "rZ" (__val)); \
+ else \
+ asm volatile("msr hcr_el2, %x0" \
+ : : "rZ" (__val)); \
+} while (0)
+
#define read_sysreg_par() ({ \
u64 par; \
asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 1114c1c3300a..1269c2487574 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -59,11 +59,12 @@ void arch_setup_new_exec(void);
#define TIF_SIGPENDING 0 /* signal pending */
#define TIF_NEED_RESCHED 1 /* rescheduling necessary */
-#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
-#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
-#define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */
-#define TIF_MTE_ASYNC_FAULT 5 /* MTE Asynchronous Tag Check Fault */
-#define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */
+#define TIF_NEED_RESCHED_LAZY 2 /* Lazy rescheduling needed */
+#define TIF_NOTIFY_RESUME 3 /* callback before returning to user */
+#define TIF_FOREIGN_FPSTATE 4 /* CPU's FP state is not current's */
+#define TIF_UPROBE 5 /* uprobe breakpoint or singlestep */
+#define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */
+#define TIF_NOTIFY_SIGNAL 7 /* signal notifications exist */
#define TIF_SYSCALL_TRACE 8 /* syscall trace active */
#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */
#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */
@@ -82,9 +83,12 @@ void arch_setup_new_exec(void);
#define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */
#define TIF_KERNEL_FPSTATE 29 /* Task is in a kernel mode FPSIMD section */
#define TIF_TSC_SIGSEGV 30 /* SIGSEGV on counter-timer access */
+#define TIF_LAZY_MMU 31 /* Task in lazy mmu mode */
+#define TIF_LAZY_MMU_PENDING 32 /* Ops pending for lazy mmu mode exit */
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING)
#define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED)
+#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY)
#define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME)
#define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE)
#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE)
@@ -100,10 +104,10 @@ void arch_setup_new_exec(void);
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
#define _TIF_TSC_SIGSEGV (1 << TIF_TSC_SIGSEGV)
-#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \
_TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
_TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
- _TIF_NOTIFY_SIGNAL)
+ _TIF_NOTIFY_SIGNAL | _TIF_SIGPENDING)
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h
index 3322c7047d84..da1ab8759592 100644
--- a/arch/arm64/include/asm/vdso/gettimeofday.h
+++ b/arch/arm64/include/asm/vdso/gettimeofday.h
@@ -8,6 +8,7 @@
#ifndef __ASSEMBLY__
#include <asm/alternative.h>
+#include <asm/arch_timer.h>
#include <asm/barrier.h>
#include <asm/unistd.h>
#include <asm/sysreg.h>
@@ -69,8 +70,6 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
const struct vdso_time_data *vd)
{
- u64 res;
-
/*
* Core checks for mode already, so this raced against a concurrent
* update. Return something. Core will do another round and then
@@ -79,24 +78,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode,
if (clock_mode == VDSO_CLOCKMODE_NONE)
return 0;
- /*
- * If FEAT_ECV is available, use the self-synchronizing counter.
- * Otherwise the isb is required to prevent that the counter value
- * is speculated.
- */
- asm volatile(
- ALTERNATIVE("isb\n"
- "mrs %0, cntvct_el0",
- "nop\n"
- __mrs_s("%0", SYS_CNTVCTSS_EL0),
- ARM64_HAS_ECV)
- : "=r" (res)
- :
- : "memory");
-
- arch_counter_enforce_ordering(res);
-
- return res;
+ return __arch_counter_get_cntvct();
}
#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB)
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index ebf4a9f943ed..aa280f356b96 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -67,7 +67,8 @@
* __boot_cpu_mode records what mode CPUs were booted in.
* A correctly-implemented bootloader must start all CPUs in the same mode:
* In this case, both 32bit halves of __boot_cpu_mode will contain the
- * same value (either 0 if booted in EL1, BOOT_CPU_MODE_EL2 if booted in EL2).
+ * same value (either BOOT_CPU_MODE_EL1 if booted in EL1, BOOT_CPU_MODE_EL2 if
+ * booted in EL2).
*
* Should the bootloader fail to do this, the two values will be different.
* This allows the kernel to flag an error when the secondaries have come up.
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index 38fafffe699f..12f534e8f3ed 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -23,6 +23,51 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot)
return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
+#define arch_vmap_pte_range_map_size arch_vmap_pte_range_map_size
+static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr,
+ unsigned long end, u64 pfn,
+ unsigned int max_page_shift)
+{
+ /*
+ * If the block is at least CONT_PTE_SIZE in size, and is naturally
+ * aligned in both virtual and physical space, then we can pte-map the
+ * block using the PTE_CONT bit for more efficient use of the TLB.
+ */
+ if (max_page_shift < CONT_PTE_SHIFT)
+ return PAGE_SIZE;
+
+ if (end - addr < CONT_PTE_SIZE)
+ return PAGE_SIZE;
+
+ if (!IS_ALIGNED(addr, CONT_PTE_SIZE))
+ return PAGE_SIZE;
+
+ if (!IS_ALIGNED(PFN_PHYS(pfn), CONT_PTE_SIZE))
+ return PAGE_SIZE;
+
+ return CONT_PTE_SIZE;
+}
+
+#define arch_vmap_pte_range_unmap_size arch_vmap_pte_range_unmap_size
+static inline unsigned long arch_vmap_pte_range_unmap_size(unsigned long addr,
+ pte_t *ptep)
+{
+ /*
+ * The caller handles alignment so it's sufficient just to check
+ * PTE_CONT.
+ */
+ return pte_valid_cont(__ptep_get(ptep)) ? CONT_PTE_SIZE : PAGE_SIZE;
+}
+
+#define arch_vmap_pte_supported_shift arch_vmap_pte_supported_shift
+static inline int arch_vmap_pte_supported_shift(unsigned long size)
+{
+ if (size >= CONT_PTE_SIZE)
+ return CONT_PTE_SHIFT;
+
+ return PAGE_SHIFT;
+}
+
#endif
#define arch_vmap_pgprot_tagged arch_vmap_pgprot_tagged
diff --git a/arch/arm64/include/asm/vncr_mapping.h b/arch/arm64/include/asm/vncr_mapping.h
index 4f9bbd4d6c26..6f556e993644 100644
--- a/arch/arm64/include/asm/vncr_mapping.h
+++ b/arch/arm64/include/asm/vncr_mapping.h
@@ -35,6 +35,8 @@
#define VNCR_CNTP_CTL_EL0 0x180
#define VNCR_SCXTNUM_EL1 0x188
#define VNCR_TFSR_EL1 0x190
+#define VNCR_HDFGRTR2_EL2 0x1A0
+#define VNCR_HDFGWTR2_EL2 0x1B0
#define VNCR_HFGRTR_EL2 0x1B8
#define VNCR_HFGWTR_EL2 0x1C0
#define VNCR_HFGITR_EL2 0x1C8
@@ -52,6 +54,9 @@
#define VNCR_PIRE0_EL1 0x290
#define VNCR_PIR_EL1 0x2A0
#define VNCR_POR_EL1 0x2A8
+#define VNCR_HFGRTR2_EL2 0x2C0
+#define VNCR_HFGWTR2_EL2 0x2C8
+#define VNCR_HFGITR2_EL2 0x310
#define VNCR_ICH_LR0_EL2 0x400
#define VNCR_ICH_LR1_EL2 0x408
#define VNCR_ICH_LR2_EL2 0x410
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index af9d9acaf997..ed5f3892674c 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -431,10 +431,11 @@ enum {
/* Device Control API on vcpu fd */
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
-#define KVM_ARM_VCPU_PMU_V3_IRQ 0
-#define KVM_ARM_VCPU_PMU_V3_INIT 1
-#define KVM_ARM_VCPU_PMU_V3_FILTER 2
-#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3
+#define KVM_ARM_VCPU_PMU_V3_IRQ 0
+#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_PMU_V3_FILTER 2
+#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3
+#define KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS 4
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index eb1a840e4110..30d4bbe68661 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -182,5 +182,7 @@ int main(void)
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call));
#endif
+ DEFINE(PIE_E0_ASM, PIE_E0);
+ DEFINE(PIE_E1_ASM, PIE_E1);
return 0;
}
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6b0ad5070d3e..59d723c9ab8f 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -557,6 +557,13 @@ static const struct midr_range erratum_ac03_cpu_38_list[] = {
};
#endif
+#ifdef CONFIG_AMPERE_ERRATUM_AC04_CPU_23
+static const struct midr_range erratum_ac04_cpu_23_list[] = {
+ MIDR_ALL_VERSIONS(MIDR_AMPERE1A),
+ {},
+};
+#endif
+
const struct arm64_cpu_capabilities arm64_errata[] = {
#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
{
@@ -876,6 +883,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
ERRATA_MIDR_RANGE_LIST(erratum_ac03_cpu_38_list),
},
#endif
+#ifdef CONFIG_AMPERE_ERRATUM_AC04_CPU_23
+ {
+ .desc = "AmpereOne erratum AC04_CPU_23",
+ .capability = ARM64_WORKAROUND_AMPERE_AC04_CPU_23,
+ ERRATA_MIDR_RANGE_LIST(erratum_ac04_cpu_23_list),
+ },
+#endif
{
.desc = "Broken CNTVOFF_EL2",
.capability = ARM64_WORKAROUND_QCOM_ORYON_CNTVOFF,
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4c46d80aa64b..45ea79cacf46 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -305,6 +305,7 @@ 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),
+ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_EL1_MTE_frac_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),
@@ -765,17 +766,17 @@ static const struct arm64_ftr_bits ftr_raz[] = {
#define ARM64_FTR_REG(id, table) \
__ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override)
-struct arm64_ftr_override id_aa64mmfr0_override;
-struct arm64_ftr_override id_aa64mmfr1_override;
-struct arm64_ftr_override id_aa64mmfr2_override;
-struct arm64_ftr_override id_aa64pfr0_override;
-struct arm64_ftr_override id_aa64pfr1_override;
-struct arm64_ftr_override id_aa64zfr0_override;
-struct arm64_ftr_override id_aa64smfr0_override;
-struct arm64_ftr_override id_aa64isar1_override;
-struct arm64_ftr_override id_aa64isar2_override;
+struct arm64_ftr_override __read_mostly id_aa64mmfr0_override;
+struct arm64_ftr_override __read_mostly id_aa64mmfr1_override;
+struct arm64_ftr_override __read_mostly id_aa64mmfr2_override;
+struct arm64_ftr_override __read_mostly id_aa64pfr0_override;
+struct arm64_ftr_override __read_mostly id_aa64pfr1_override;
+struct arm64_ftr_override __read_mostly id_aa64zfr0_override;
+struct arm64_ftr_override __read_mostly id_aa64smfr0_override;
+struct arm64_ftr_override __read_mostly id_aa64isar1_override;
+struct arm64_ftr_override __read_mostly id_aa64isar2_override;
-struct arm64_ftr_override arm64_sw_feature_override;
+struct arm64_ftr_override __read_mostly arm64_sw_feature_override;
static const struct __ftr_reg_entry {
u32 sys_id;
@@ -1410,6 +1411,8 @@ void update_cpu_features(int cpu,
info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2);
taint |= check_update_ftr_reg(SYS_ID_AA64MMFR3_EL1, cpu,
info->reg_id_aa64mmfr3, boot->reg_id_aa64mmfr3);
+ taint |= check_update_ftr_reg(SYS_ID_AA64MMFR4_EL1, cpu,
+ info->reg_id_aa64mmfr4, boot->reg_id_aa64mmfr4);
taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
@@ -2883,6 +2886,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = has_cpuid_feature,
ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, IMP)
},
+ {
+ .desc = "Fine Grained Traps 2",
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .capability = ARM64_HAS_FGT2,
+ .matches = has_cpuid_feature,
+ ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, FGT, FGT2)
+ },
#ifdef CONFIG_ARM64_SME
{
.desc = "Scalable Matrix Extension",
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 285d7d538342..94525abd1c22 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -209,80 +209,79 @@ static const char *const compat_hwcap2_str[] = {
static int c_show(struct seq_file *m, void *v)
{
- int i, j;
+ int j;
+ int cpu = m->index;
bool compat = personality(current->personality) == PER_LINUX32;
+ struct cpuinfo_arm64 *cpuinfo = v;
+ u32 midr = cpuinfo->reg_midr;
- for_each_online_cpu(i) {
- struct cpuinfo_arm64 *cpuinfo = &per_cpu(cpu_data, i);
- u32 midr = cpuinfo->reg_midr;
-
- /*
- * glibc reads /proc/cpuinfo to determine the number of
- * online processors, looking for lines beginning with
- * "processor". Give glibc what it expects.
- */
- seq_printf(m, "processor\t: %d\n", i);
- if (compat)
- seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
- MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
+ /*
+ * glibc reads /proc/cpuinfo to determine the number of
+ * online processors, looking for lines beginning with
+ * "processor". Give glibc what it expects.
+ */
+ seq_printf(m, "processor\t: %d\n", cpu);
+ if (compat)
+ seq_printf(m, "model name\t: ARMv8 Processor rev %d (%s)\n",
+ MIDR_REVISION(midr), COMPAT_ELF_PLATFORM);
- seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
- loops_per_jiffy / (500000UL/HZ),
- loops_per_jiffy / (5000UL/HZ) % 100);
+ seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+ loops_per_jiffy / (500000UL/HZ),
+ loops_per_jiffy / (5000UL/HZ) % 100);
- /*
- * Dump out the common processor features in a single line.
- * Userspace should read the hwcaps with getauxval(AT_HWCAP)
- * rather than attempting to parse this, but there's a body of
- * software which does already (at least for 32-bit).
- */
- seq_puts(m, "Features\t:");
- if (compat) {
+ /*
+ * Dump out the common processor features in a single line.
+ * Userspace should read the hwcaps with getauxval(AT_HWCAP)
+ * rather than attempting to parse this, but there's a body of
+ * software which does already (at least for 32-bit).
+ */
+ seq_puts(m, "Features\t:");
+ if (compat) {
#ifdef CONFIG_COMPAT
- for (j = 0; j < ARRAY_SIZE(compat_hwcap_str); j++) {
- if (compat_elf_hwcap & (1 << j)) {
- /*
- * Warn once if any feature should not
- * have been present on arm64 platform.
- */
- if (WARN_ON_ONCE(!compat_hwcap_str[j]))
- continue;
-
- seq_printf(m, " %s", compat_hwcap_str[j]);
- }
+ for (j = 0; j < ARRAY_SIZE(compat_hwcap_str); j++) {
+ if (compat_elf_hwcap & (1 << j)) {
+ /*
+ * Warn once if any feature should not
+ * have been present on arm64 platform.
+ */
+ if (WARN_ON_ONCE(!compat_hwcap_str[j]))
+ continue;
+
+ seq_printf(m, " %s", compat_hwcap_str[j]);
}
+ }
- for (j = 0; j < ARRAY_SIZE(compat_hwcap2_str); j++)
- if (compat_elf_hwcap2 & (1 << j))
- seq_printf(m, " %s", compat_hwcap2_str[j]);
+ for (j = 0; j < ARRAY_SIZE(compat_hwcap2_str); j++)
+ if (compat_elf_hwcap2 & (1 << j))
+ seq_printf(m, " %s", compat_hwcap2_str[j]);
#endif /* CONFIG_COMPAT */
- } else {
- for (j = 0; j < ARRAY_SIZE(hwcap_str); j++)
- if (cpu_have_feature(j))
- seq_printf(m, " %s", hwcap_str[j]);
- }
- seq_puts(m, "\n");
-
- seq_printf(m, "CPU implementer\t: 0x%02x\n",
- MIDR_IMPLEMENTOR(midr));
- seq_printf(m, "CPU architecture: 8\n");
- seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
- seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
- seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
+ } else {
+ for (j = 0; j < ARRAY_SIZE(hwcap_str); j++)
+ if (cpu_have_feature(j))
+ seq_printf(m, " %s", hwcap_str[j]);
}
+ seq_puts(m, "\n");
+
+ seq_printf(m, "CPU implementer\t: 0x%02x\n",
+ MIDR_IMPLEMENTOR(midr));
+ seq_puts(m, "CPU architecture: 8\n");
+ seq_printf(m, "CPU variant\t: 0x%x\n", MIDR_VARIANT(midr));
+ seq_printf(m, "CPU part\t: 0x%03x\n", MIDR_PARTNUM(midr));
+ seq_printf(m, "CPU revision\t: %d\n\n", MIDR_REVISION(midr));
return 0;
}
static void *c_start(struct seq_file *m, loff_t *pos)
{
- return *pos < 1 ? (void *)1 : NULL;
+ *pos = cpumask_next(*pos - 1, cpu_online_mask);
+ return *pos < nr_cpu_ids ? &per_cpu(cpu_data, *pos) : NULL;
}
static void *c_next(struct seq_file *m, void *v, loff_t *pos)
{
++*pos;
- return NULL;
+ return c_start(m, pos);
}
static void c_stop(struct seq_file *m, void *v)
@@ -328,11 +327,13 @@ static const struct kobj_type cpuregs_kobj_type = {
CPUREGS_ATTR_RO(midr_el1, midr);
CPUREGS_ATTR_RO(revidr_el1, revidr);
+CPUREGS_ATTR_RO(aidr_el1, aidr);
CPUREGS_ATTR_RO(smidr_el1, smidr);
static struct attribute *cpuregs_id_attrs[] = {
&cpuregs_attr_midr_el1.attr,
&cpuregs_attr_revidr_el1.attr,
+ &cpuregs_attr_aidr_el1.attr,
NULL
};
@@ -469,6 +470,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
info->reg_dczid = read_cpuid(DCZID_EL0);
info->reg_midr = read_cpuid_id();
info->reg_revidr = read_cpuid(REVIDR_EL1);
+ info->reg_aidr = read_cpuid(AIDR_EL1);
info->reg_id_aa64dfr0 = read_cpuid(ID_AA64DFR0_EL1);
info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1);
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 1d25d8899dbf..250e9d7c08a7 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -169,14 +169,14 @@ static DEFINE_RAW_SPINLOCK(efi_rt_lock);
void arch_efi_call_virt_setup(void)
{
efi_virtmap_load();
- __efi_fpsimd_begin();
raw_spin_lock(&efi_rt_lock);
+ __efi_fpsimd_begin();
}
void arch_efi_call_virt_teardown(void)
{
- raw_spin_unlock(&efi_rt_lock);
__efi_fpsimd_end();
+ raw_spin_unlock(&efi_rt_lock);
efi_virtmap_unload();
}
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index b260ddc4d3e9..7c1970b341b8 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -132,7 +132,7 @@ static void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
do {
local_irq_enable();
- if (thread_flags & _TIF_NEED_RESCHED)
+ if (thread_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY))
schedule();
if (thread_flags & _TIF_UPROBE)
@@ -393,20 +393,16 @@ static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
* As per the ABI exit SME streaming mode and clear the SVE state not
* shared with FPSIMD on syscall entry.
*/
-static inline void fp_user_discard(void)
+static inline void fpsimd_syscall_enter(void)
{
- /*
- * If SME is active then exit streaming mode. If ZA is active
- * then flush the SVE registers but leave userspace access to
- * both SVE and SME enabled, otherwise disable SME for the
- * task and fall through to disabling SVE too. This means
- * that after a syscall we never have any streaming mode
- * register state to track, if this changes the KVM code will
- * need updating.
- */
+ /* Ensure PSTATE.SM is clear, but leave PSTATE.ZA as-is. */
if (system_supports_sme())
sme_smstop_sm();
+ /*
+ * The CPU is not in streaming mode. If non-streaming SVE is not
+ * supported, there is no SVE state that needs to be discarded.
+ */
if (!system_supports_sve())
return;
@@ -416,6 +412,33 @@ static inline void fp_user_discard(void)
sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1;
sve_flush_live(true, sve_vq_minus_one);
}
+
+ /*
+ * Any live non-FPSIMD SVE state has been zeroed. Allow
+ * fpsimd_save_user_state() to lazily discard SVE state until either
+ * the live state is unbound or fpsimd_syscall_exit() is called.
+ */
+ __this_cpu_write(fpsimd_last_state.to_save, FP_STATE_FPSIMD);
+}
+
+static __always_inline void fpsimd_syscall_exit(void)
+{
+ if (!system_supports_sve())
+ return;
+
+ /*
+ * The current task's user FPSIMD/SVE/SME state is now bound to this
+ * CPU. The fpsimd_last_state.to_save value is either:
+ *
+ * - FP_STATE_FPSIMD, if the state has not been reloaded on this CPU
+ * since fpsimd_syscall_enter().
+ *
+ * - FP_STATE_CURRENT, if the state has been reloaded on this CPU at
+ * any point.
+ *
+ * Reset this to FP_STATE_CURRENT to stop lazy discarding.
+ */
+ __this_cpu_write(fpsimd_last_state.to_save, FP_STATE_CURRENT);
}
UNHANDLED(el1t, 64, sync)
@@ -739,10 +762,11 @@ static void noinstr el0_svc(struct pt_regs *regs)
{
enter_from_user_mode(regs);
cortex_a76_erratum_1463225_svc_handler();
- fp_user_discard();
+ fpsimd_syscall_enter();
local_daif_restore(DAIF_PROCCTX);
do_el0_svc(regs);
exit_to_user_mode(regs);
+ fpsimd_syscall_exit();
}
static void noinstr el0_fpac(struct pt_regs *regs, unsigned long esr)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 8370d55f0353..c37f02d7194e 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -119,7 +119,7 @@
* whatever is in the FPSIMD registers is not saved to memory, but discarded.
*/
-static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
+DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state);
__ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = {
#ifdef CONFIG_ARM64_SVE
@@ -180,12 +180,12 @@ static inline void set_sve_default_vl(int val)
set_default_vl(ARM64_VEC_SVE, val);
}
-static void __percpu *efi_sve_state;
+static u8 *efi_sve_state;
#else /* ! CONFIG_ARM64_SVE */
/* Dummy declaration for code that will be optimised out: */
-extern void __percpu *efi_sve_state;
+extern u8 *efi_sve_state;
#endif /* ! CONFIG_ARM64_SVE */
@@ -359,20 +359,15 @@ static void task_fpsimd_load(void)
WARN_ON(preemptible());
WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE));
- if (system_supports_fpmr())
- write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
-
if (system_supports_sve() || system_supports_sme()) {
switch (current->thread.fp_type) {
case FP_STATE_FPSIMD:
/* Stop tracking SVE for this task until next use. */
- if (test_and_clear_thread_flag(TIF_SVE))
- sve_user_disable();
+ clear_thread_flag(TIF_SVE);
break;
case FP_STATE_SVE:
- if (!thread_sm_enabled(&current->thread) &&
- !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE)))
- sve_user_enable();
+ if (!thread_sm_enabled(&current->thread))
+ WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE));
if (test_thread_flag(TIF_SVE))
sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1);
@@ -413,6 +408,9 @@ static void task_fpsimd_load(void)
restore_ffr = system_supports_fa64();
}
+ if (system_supports_fpmr())
+ write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR);
+
if (restore_sve_regs) {
WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE);
sve_load_state(sve_pffr(&current->thread),
@@ -453,12 +451,15 @@ static void fpsimd_save_user_state(void)
*(last->fpmr) = read_sysreg_s(SYS_FPMR);
/*
- * If a task is in a syscall the ABI allows us to only
- * preserve the state shared with FPSIMD so don't bother
- * saving the full SVE state in that case.
+ * Save SVE state if it is live.
+ *
+ * The syscall ABI discards live SVE state at syscall entry. When
+ * entering a syscall, fpsimd_syscall_enter() sets to_save to
+ * FP_STATE_FPSIMD to allow the SVE state to be lazily discarded until
+ * either new SVE state is loaded+bound or fpsimd_syscall_exit() is
+ * called prior to a return to userspace.
*/
- if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) &&
- !in_syscall(current_pt_regs())) ||
+ if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE)) ||
last->to_save == FP_STATE_SVE) {
save_sve_regs = true;
save_ffr = true;
@@ -651,7 +652,7 @@ static void __fpsimd_to_sve(void *sst, struct user_fpsimd_state const *fst,
* task->thread.uw.fpsimd_state must be up to date before calling this
* function.
*/
-static void fpsimd_to_sve(struct task_struct *task)
+static inline void fpsimd_to_sve(struct task_struct *task)
{
unsigned int vq;
void *sst = task->thread.sve_state;
@@ -675,7 +676,7 @@ static void fpsimd_to_sve(struct task_struct *task)
* bytes of allocated kernel memory.
* task->thread.sve_state must be up to date before calling this function.
*/
-static void sve_to_fpsimd(struct task_struct *task)
+static inline void sve_to_fpsimd(struct task_struct *task)
{
unsigned int vq, vl;
void const *sst = task->thread.sve_state;
@@ -694,44 +695,39 @@ static void sve_to_fpsimd(struct task_struct *task)
}
}
-void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
+static inline void __fpsimd_zero_vregs(struct user_fpsimd_state *fpsimd)
{
- write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
- SYS_SCTLR_EL1);
+ memset(&fpsimd->vregs, 0, sizeof(fpsimd->vregs));
}
-#ifdef CONFIG_ARM64_SVE
/*
- * Call __sve_free() directly only if you know task can't be scheduled
- * or preempted.
+ * Simulate the effects of an SMSTOP SM instruction.
*/
-static void __sve_free(struct task_struct *task)
+void task_smstop_sm(struct task_struct *task)
{
- kfree(task->thread.sve_state);
- task->thread.sve_state = NULL;
-}
+ if (!thread_sm_enabled(&task->thread))
+ return;
-static void sve_free(struct task_struct *task)
-{
- WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+ __fpsimd_zero_vregs(&task->thread.uw.fpsimd_state);
+ task->thread.uw.fpsimd_state.fpsr = 0x0800009f;
+ if (system_supports_fpmr())
+ task->thread.uw.fpmr = 0;
- __sve_free(task);
+ task->thread.svcr &= ~SVCR_SM_MASK;
+ task->thread.fp_type = FP_STATE_FPSIMD;
}
-/*
- * Return how many bytes of memory are required to store the full SVE
- * state for task, given task's currently configured vector length.
- */
-size_t sve_state_size(struct task_struct const *task)
+void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p)
{
- unsigned int vl = 0;
-
- if (system_supports_sve())
- vl = task_get_sve_vl(task);
- if (system_supports_sme())
- vl = max(vl, task_get_sme_vl(task));
+ write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK,
+ SYS_SCTLR_EL1);
+}
- return SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl));
+#ifdef CONFIG_ARM64_SVE
+static void sve_free(struct task_struct *task)
+{
+ kfree(task->thread.sve_state);
+ task->thread.sve_state = NULL;
}
/*
@@ -758,69 +754,34 @@ void sve_alloc(struct task_struct *task, bool flush)
kzalloc(sve_state_size(task), GFP_KERNEL);
}
-
-/*
- * Force the FPSIMD state shared with SVE to be updated in the SVE state
- * even if the SVE state is the current active state.
- *
- * This should only be called by ptrace. task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- */
-void fpsimd_force_sync_to_sve(struct task_struct *task)
-{
- fpsimd_to_sve(task);
-}
-
-/*
- * Ensure that task->thread.sve_state is up to date with respect to
- * the user task, irrespective of when SVE is in use or not.
- *
- * This should only be called by ptrace. task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- */
-void fpsimd_sync_to_sve(struct task_struct *task)
-{
- if (!test_tsk_thread_flag(task, TIF_SVE) &&
- !thread_sm_enabled(&task->thread))
- fpsimd_to_sve(task);
-}
-
/*
- * Ensure that task->thread.uw.fpsimd_state is up to date with respect to
- * the user task, irrespective of whether SVE is in use or not.
+ * Ensure that task->thread.uw.fpsimd_state is up to date with respect to the
+ * task's currently effective FPSIMD/SVE state.
*
- * This should only be called by ptrace. task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
+ * The task's FPSIMD/SVE/SME state must not be subject to concurrent
+ * manipulation.
*/
-void sve_sync_to_fpsimd(struct task_struct *task)
+void fpsimd_sync_from_effective_state(struct task_struct *task)
{
if (task->thread.fp_type == FP_STATE_SVE)
sve_to_fpsimd(task);
}
/*
- * Ensure that task->thread.sve_state is up to date with respect to
- * the task->thread.uw.fpsimd_state.
+ * Ensure that the task's currently effective FPSIMD/SVE state is up to date
+ * with respect to task->thread.uw.fpsimd_state, zeroing any effective
+ * non-FPSIMD (S)SVE state.
*
- * This should only be called by ptrace to merge new FPSIMD register
- * values into a task for which SVE is currently active.
- * task must be non-runnable.
- * task->thread.sve_state must point to at least sve_state_size(task)
- * bytes of allocated kernel memory.
- * task->thread.uw.fpsimd_state must already have been initialised with
- * the new FPSIMD register values to be merged in.
+ * The task's FPSIMD/SVE/SME state must not be subject to concurrent
+ * manipulation.
*/
-void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
+void fpsimd_sync_to_effective_state_zeropad(struct task_struct *task)
{
unsigned int vq;
void *sst = task->thread.sve_state;
struct user_fpsimd_state const *fst = &task->thread.uw.fpsimd_state;
- if (!test_tsk_thread_flag(task, TIF_SVE) &&
- !thread_sm_enabled(&task->thread))
+ if (task->thread.fp_type != FP_STATE_SVE)
return;
vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread));
@@ -829,10 +790,73 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task)
__fpsimd_to_sve(sst, fst, vq);
}
+static int change_live_vector_length(struct task_struct *task,
+ enum vec_type type,
+ unsigned long vl)
+{
+ unsigned int sve_vl = task_get_sve_vl(task);
+ unsigned int sme_vl = task_get_sme_vl(task);
+ void *sve_state = NULL, *sme_state = NULL;
+
+ if (type == ARM64_VEC_SME)
+ sme_vl = vl;
+ else
+ sve_vl = vl;
+
+ /*
+ * Allocate the new sve_state and sme_state before freeing the old
+ * copies so that allocation failure can be handled without needing to
+ * mutate the task's state in any way.
+ *
+ * Changes to the SVE vector length must not discard live ZA state or
+ * clear PSTATE.ZA, as userspace code which is unaware of the AAPCS64
+ * ZA lazy saving scheme may attempt to change the SVE vector length
+ * while unsaved/dormant ZA state exists.
+ */
+ sve_state = kzalloc(__sve_state_size(sve_vl, sme_vl), GFP_KERNEL);
+ if (!sve_state)
+ goto out_mem;
+
+ if (type == ARM64_VEC_SME) {
+ sme_state = kzalloc(__sme_state_size(sme_vl), GFP_KERNEL);
+ if (!sme_state)
+ goto out_mem;
+ }
+
+ if (task == current)
+ fpsimd_save_and_flush_current_state();
+ else
+ fpsimd_flush_task_state(task);
+
+ /*
+ * Always preserve PSTATE.SM and the effective FPSIMD state, zeroing
+ * other SVE state.
+ */
+ fpsimd_sync_from_effective_state(task);
+ task_set_vl(task, type, vl);
+ kfree(task->thread.sve_state);
+ task->thread.sve_state = sve_state;
+ fpsimd_sync_to_effective_state_zeropad(task);
+
+ if (type == ARM64_VEC_SME) {
+ task->thread.svcr &= ~SVCR_ZA_MASK;
+ kfree(task->thread.sme_state);
+ task->thread.sme_state = sme_state;
+ }
+
+ return 0;
+
+out_mem:
+ kfree(sve_state);
+ kfree(sme_state);
+ return -ENOMEM;
+}
+
int vec_set_vector_length(struct task_struct *task, enum vec_type type,
unsigned long vl, unsigned long flags)
{
- bool free_sme = false;
+ bool onexec = flags & PR_SVE_SET_VL_ONEXEC;
+ bool inherit = flags & PR_SVE_VL_INHERIT;
if (flags & ~(unsigned long)(PR_SVE_VL_INHERIT |
PR_SVE_SET_VL_ONEXEC))
@@ -852,71 +876,17 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type,
vl = find_supported_vector_length(type, vl);
- if (flags & (PR_SVE_VL_INHERIT |
- PR_SVE_SET_VL_ONEXEC))
+ if (!onexec && vl != task_get_vl(task, type)) {
+ if (change_live_vector_length(task, type, vl))
+ return -ENOMEM;
+ }
+
+ if (onexec || inherit)
task_set_vl_onexec(task, type, vl);
else
/* Reset VL to system default on next exec: */
task_set_vl_onexec(task, type, 0);
- /* Only actually set the VL if not deferred: */
- if (flags & PR_SVE_SET_VL_ONEXEC)
- goto out;
-
- if (vl == task_get_vl(task, type))
- goto out;
-
- /*
- * To ensure the FPSIMD bits of the SVE vector registers are preserved,
- * write any live register state back to task_struct, and convert to a
- * regular FPSIMD thread.
- */
- if (task == current) {
- get_cpu_fpsimd_context();
-
- fpsimd_save_user_state();
- }
-
- fpsimd_flush_task_state(task);
- if (test_and_clear_tsk_thread_flag(task, TIF_SVE) ||
- thread_sm_enabled(&task->thread)) {
- sve_to_fpsimd(task);
- task->thread.fp_type = FP_STATE_FPSIMD;
- }
-
- if (system_supports_sme()) {
- if (type == ARM64_VEC_SME ||
- !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) {
- /*
- * We are changing the SME VL or weren't using
- * SME anyway, discard the state and force a
- * reallocation.
- */
- task->thread.svcr &= ~(SVCR_SM_MASK |
- SVCR_ZA_MASK);
- clear_tsk_thread_flag(task, TIF_SME);
- free_sme = true;
- }
- }
-
- if (task == current)
- put_cpu_fpsimd_context();
-
- task_set_vl(task, type, vl);
-
- /*
- * Free the changed states if they are not in use, SME will be
- * reallocated to the correct size on next use and we just
- * allocate SVE now in case it is needed for use in streaming
- * mode.
- */
- sve_free(task);
- sve_alloc(task, true);
-
- if (free_sme)
- sme_free(task);
-
-out:
update_tsk_thread_flag(task, vec_vl_inherit_flag(type),
flags & PR_SVE_VL_INHERIT);
@@ -1131,15 +1101,15 @@ static void __init sve_efi_setup(void)
if (!sve_vl_valid(max_vl))
goto fail;
- efi_sve_state = __alloc_percpu(
- SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)), SVE_VQ_BYTES);
+ efi_sve_state = kmalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(max_vl)),
+ GFP_KERNEL);
if (!efi_sve_state)
goto fail;
return;
fail:
- panic("Cannot allocate percpu memory for EFI SVE save/restore");
+ panic("Cannot allocate memory for EFI SVE save/restore");
}
void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p)
@@ -1212,7 +1182,7 @@ void __init sve_setup(void)
*/
void fpsimd_release_task(struct task_struct *dead_task)
{
- __sve_free(dead_task);
+ sve_free(dead_task);
sme_free(dead_task);
}
@@ -1436,7 +1406,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
* If this not a trap due to SME being disabled then something
* is being used in the wrong mode, report as SIGILL.
*/
- if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) {
+ if (ESR_ELx_SME_ISS_SMTC(esr) != ESR_ELx_SME_ISS_SMTC_SME_DISABLED) {
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0);
return;
}
@@ -1460,6 +1430,8 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs)
sme_set_vq(vq_minus_one);
fpsimd_bind_task_to_cpu();
+ } else {
+ fpsimd_flush_task_state(current);
}
put_cpu_fpsimd_context();
@@ -1573,8 +1545,8 @@ void fpsimd_thread_switch(struct task_struct *next)
fpsimd_save_user_state();
if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) {
- fpsimd_load_kernel_state(next);
fpsimd_flush_cpu_state();
+ fpsimd_load_kernel_state(next);
} else {
/*
* Fix up TIF_FOREIGN_FPSTATE to correctly describe next's
@@ -1661,6 +1633,9 @@ void fpsimd_flush_thread(void)
current->thread.svcr = 0;
}
+ if (system_supports_fpmr())
+ current->thread.uw.fpmr = 0;
+
current->thread.fp_type = FP_STATE_FPSIMD;
put_cpu_fpsimd_context();
@@ -1683,18 +1658,6 @@ void fpsimd_preserve_current_state(void)
}
/*
- * Like fpsimd_preserve_current_state(), but ensure that
- * current->thread.uw.fpsimd_state is updated so that it can be copied to
- * the signal frame.
- */
-void fpsimd_signal_preserve_current_state(void)
-{
- fpsimd_preserve_current_state();
- if (current->thread.fp_type == FP_STATE_SVE)
- sve_to_fpsimd(current);
-}
-
-/*
* Associate current's FPSIMD context with this cpu
* The caller must have ownership of the cpu FPSIMD context before calling
* this function.
@@ -1786,30 +1749,14 @@ void fpsimd_restore_current_state(void)
put_cpu_fpsimd_context();
}
-/*
- * Load an updated userland FPSIMD state for 'current' from memory and set the
- * flag that indicates that the FPSIMD register contents are the most recent
- * FPSIMD state of 'current'. This is used by the signal code to restore the
- * register state when returning from a signal handler in FPSIMD only cases,
- * any SVE context will be discarded.
- */
void fpsimd_update_current_state(struct user_fpsimd_state const *state)
{
if (WARN_ON(!system_supports_fpsimd()))
return;
- get_cpu_fpsimd_context();
-
current->thread.uw.fpsimd_state = *state;
- if (test_thread_flag(TIF_SVE))
+ if (current->thread.fp_type == FP_STATE_SVE)
fpsimd_to_sve(current);
-
- task_fpsimd_load();
- fpsimd_bind_task_to_cpu();
-
- clear_thread_flag(TIF_FOREIGN_FPSTATE);
-
- put_cpu_fpsimd_context();
}
/*
@@ -1839,6 +1786,17 @@ void fpsimd_flush_task_state(struct task_struct *t)
barrier();
}
+void fpsimd_save_and_flush_current_state(void)
+{
+ if (!system_supports_fpsimd())
+ return;
+
+ get_cpu_fpsimd_context();
+ fpsimd_save_user_state();
+ fpsimd_flush_task_state(current);
+ put_cpu_fpsimd_context();
+}
+
/*
* Save the FPSIMD state to memory and invalidate cpu view.
* This function must be called with preemption disabled.
@@ -1948,10 +1906,10 @@ EXPORT_SYMBOL_GPL(kernel_neon_end);
#ifdef CONFIG_EFI
-static DEFINE_PER_CPU(struct user_fpsimd_state, efi_fpsimd_state);
-static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
-static DEFINE_PER_CPU(bool, efi_sve_state_used);
-static DEFINE_PER_CPU(bool, efi_sm_state);
+static struct user_fpsimd_state efi_fpsimd_state;
+static bool efi_fpsimd_state_used;
+static bool efi_sve_state_used;
+static bool efi_sm_state;
/*
* EFI runtime services support functions
@@ -1984,18 +1942,16 @@ void __efi_fpsimd_begin(void)
* If !efi_sve_state, SVE can't be in use yet and doesn't need
* preserving:
*/
- if (system_supports_sve() && likely(efi_sve_state)) {
- char *sve_state = this_cpu_ptr(efi_sve_state);
+ if (system_supports_sve() && efi_sve_state != NULL) {
bool ffr = true;
u64 svcr;
- __this_cpu_write(efi_sve_state_used, true);
+ efi_sve_state_used = true;
if (system_supports_sme()) {
svcr = read_sysreg_s(SYS_SVCR);
- __this_cpu_write(efi_sm_state,
- svcr & SVCR_SM_MASK);
+ efi_sm_state = svcr & SVCR_SM_MASK;
/*
* Unless we have FA64 FFR does not
@@ -2005,19 +1961,18 @@ void __efi_fpsimd_begin(void)
ffr = !(svcr & SVCR_SM_MASK);
}
- sve_save_state(sve_state + sve_ffr_offset(sve_max_vl()),
- &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
- ffr);
+ sve_save_state(efi_sve_state + sve_ffr_offset(sve_max_vl()),
+ &efi_fpsimd_state.fpsr, ffr);
if (system_supports_sme())
sysreg_clear_set_s(SYS_SVCR,
SVCR_SM_MASK, 0);
} else {
- fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+ fpsimd_save_state(&efi_fpsimd_state);
}
- __this_cpu_write(efi_fpsimd_state_used, true);
+ efi_fpsimd_state_used = true;
}
}
@@ -2029,12 +1984,10 @@ void __efi_fpsimd_end(void)
if (!system_supports_fpsimd())
return;
- if (!__this_cpu_xchg(efi_fpsimd_state_used, false)) {
+ if (!efi_fpsimd_state_used) {
kernel_neon_end();
} else {
- if (system_supports_sve() &&
- likely(__this_cpu_read(efi_sve_state_used))) {
- char const *sve_state = this_cpu_ptr(efi_sve_state);
+ if (system_supports_sve() && efi_sve_state_used) {
bool ffr = true;
/*
@@ -2043,7 +1996,7 @@ void __efi_fpsimd_end(void)
* streaming mode.
*/
if (system_supports_sme()) {
- if (__this_cpu_read(efi_sm_state)) {
+ if (efi_sm_state) {
sysreg_clear_set_s(SYS_SVCR,
0,
SVCR_SM_MASK);
@@ -2057,14 +2010,15 @@ void __efi_fpsimd_end(void)
}
}
- sve_load_state(sve_state + sve_ffr_offset(sve_max_vl()),
- &this_cpu_ptr(&efi_fpsimd_state)->fpsr,
- ffr);
+ sve_load_state(efi_sve_state + sve_ffr_offset(sve_max_vl()),
+ &efi_fpsimd_state.fpsr, ffr);
- __this_cpu_write(efi_sve_state_used, false);
+ efi_sve_state_used = false;
} else {
- fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
+ fpsimd_load_state(&efi_fpsimd_state);
}
+
+ efi_fpsimd_state_used = false;
}
}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2ce73525de2c..ca04b338cb0d 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -89,7 +89,7 @@ SYM_CODE_START(primary_entry)
adrp x1, early_init_stack
mov sp, x1
mov x29, xzr
- adrp x0, init_idmap_pg_dir
+ adrp x0, __pi_init_idmap_pg_dir
mov x1, xzr
bl __pi_create_init_idmap
@@ -101,7 +101,7 @@ SYM_CODE_START(primary_entry)
cbnz x19, 0f
dmb sy
mov x1, x0 // end of used region
- adrp x0, init_idmap_pg_dir
+ adrp x0, __pi_init_idmap_pg_dir
adr_l x2, dcache_inval_poc
blr x2
b 1f
@@ -507,7 +507,7 @@ SYM_FUNC_END(__no_granule_support)
SYM_FUNC_START_LOCAL(__primary_switch)
adrp x1, reserved_pg_dir
- adrp x2, init_idmap_pg_dir
+ adrp x2, __pi_init_idmap_pg_dir
bl __enable_mmu
adrp x1, early_init_stack
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index ae990da1eae5..36e2d26b54f5 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -97,7 +97,7 @@ SYM_CODE_START_LOCAL(__finalise_el2)
2:
// Engage the VHE magic!
mov_q x0, HCR_HOST_VHE_FLAGS
- msr hcr_el2, x0
+ msr_hcr_el2 x0
isb
// Use the EL1 allocated stack, per-cpu offset
diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h
index 2004b4f41ade..5a69b6eb4090 100644
--- a/arch/arm64/kernel/image-vars.h
+++ b/arch/arm64/kernel/image-vars.h
@@ -10,6 +10,12 @@
#error This file should only be included in vmlinux.lds.S
#endif
+#define PI_EXPORT_SYM(sym) \
+ __PI_EXPORT_SYM(sym, __pi_ ## sym, Cannot export BSS symbol sym to startup code)
+#define __PI_EXPORT_SYM(sym, pisym, msg)\
+ PROVIDE(pisym = sym); \
+ ASSERT((sym - KIMAGE_VADDR) < (__bss_start - KIMAGE_VADDR), #msg)
+
PROVIDE(__efistub_primary_entry = primary_entry);
/*
@@ -36,37 +42,30 @@ PROVIDE(__pi___memcpy = __pi_memcpy);
PROVIDE(__pi___memmove = __pi_memmove);
PROVIDE(__pi___memset = __pi_memset);
-PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override);
-PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override);
-PROVIDE(__pi_id_aa64mmfr0_override = id_aa64mmfr0_override);
-PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override);
-PROVIDE(__pi_id_aa64mmfr2_override = id_aa64mmfr2_override);
-PROVIDE(__pi_id_aa64pfr0_override = id_aa64pfr0_override);
-PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override);
-PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override);
-PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override);
-PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override);
-PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings);
-PROVIDE(__pi__ctype = _ctype);
-PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed);
-
-PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir);
-PROVIDE(__pi_init_idmap_pg_end = init_idmap_pg_end);
-PROVIDE(__pi_init_pg_dir = init_pg_dir);
-PROVIDE(__pi_init_pg_end = init_pg_end);
-PROVIDE(__pi_swapper_pg_dir = swapper_pg_dir);
-
-PROVIDE(__pi__text = _text);
-PROVIDE(__pi__stext = _stext);
-PROVIDE(__pi__etext = _etext);
-PROVIDE(__pi___start_rodata = __start_rodata);
-PROVIDE(__pi___inittext_begin = __inittext_begin);
-PROVIDE(__pi___inittext_end = __inittext_end);
-PROVIDE(__pi___initdata_begin = __initdata_begin);
-PROVIDE(__pi___initdata_end = __initdata_end);
-PROVIDE(__pi__data = _data);
-PROVIDE(__pi___bss_start = __bss_start);
-PROVIDE(__pi__end = _end);
+PI_EXPORT_SYM(id_aa64isar1_override);
+PI_EXPORT_SYM(id_aa64isar2_override);
+PI_EXPORT_SYM(id_aa64mmfr0_override);
+PI_EXPORT_SYM(id_aa64mmfr1_override);
+PI_EXPORT_SYM(id_aa64mmfr2_override);
+PI_EXPORT_SYM(id_aa64pfr0_override);
+PI_EXPORT_SYM(id_aa64pfr1_override);
+PI_EXPORT_SYM(id_aa64smfr0_override);
+PI_EXPORT_SYM(id_aa64zfr0_override);
+PI_EXPORT_SYM(arm64_sw_feature_override);
+PI_EXPORT_SYM(arm64_use_ng_mappings);
+PI_EXPORT_SYM(_ctype);
+
+PI_EXPORT_SYM(swapper_pg_dir);
+
+PI_EXPORT_SYM(_text);
+PI_EXPORT_SYM(_stext);
+PI_EXPORT_SYM(_etext);
+PI_EXPORT_SYM(__start_rodata);
+PI_EXPORT_SYM(__inittext_begin);
+PI_EXPORT_SYM(__inittext_end);
+PI_EXPORT_SYM(__initdata_begin);
+PI_EXPORT_SYM(__initdata_end);
+PI_EXPORT_SYM(_data);
#ifdef CONFIG_KVM
@@ -127,6 +126,8 @@ KVM_NVHE_ALIAS(__hyp_text_start);
KVM_NVHE_ALIAS(__hyp_text_end);
KVM_NVHE_ALIAS(__hyp_bss_start);
KVM_NVHE_ALIAS(__hyp_bss_end);
+KVM_NVHE_ALIAS(__hyp_data_start);
+KVM_NVHE_ALIAS(__hyp_data_end);
KVM_NVHE_ALIAS(__hyp_rodata_start);
KVM_NVHE_ALIAS(__hyp_rodata_end);
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 1da3e25f9d9e..c9503ed45a6c 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -10,8 +10,6 @@
#include <asm/cpufeature.h>
#include <asm/memory.h>
-u16 __initdata memstart_offset_seed;
-
bool __ro_after_init __kaslr_is_enabled = false;
void __init kaslr_init(void)
diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c
index 0257b43819db..e0e018046a46 100644
--- a/arch/arm64/kernel/pi/kaslr_early.c
+++ b/arch/arm64/kernel/pi/kaslr_early.c
@@ -18,8 +18,6 @@
#include "pi.h"
-extern u16 memstart_offset_seed;
-
static u64 __init get_kaslr_seed(void *fdt, int node)
{
static char const seed_str[] __initconst = "kaslr-seed";
@@ -53,8 +51,6 @@ u64 __init kaslr_early_init(void *fdt, int chosen)
return 0;
}
- memstart_offset_seed = seed & U16_MAX;
-
/*
* OK, so we are proceeding with KASLR enabled. Calculate a suitable
* kernel image offset from the seed. Let's place the kernel in the
diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h
index c91e5e965cd3..1f4731a4e17e 100644
--- a/arch/arm64/kernel/pi/pi.h
+++ b/arch/arm64/kernel/pi/pi.h
@@ -22,6 +22,7 @@ static inline void *prel64_to_pointer(const prel64_t *offset)
extern bool dynamic_scs_is_enabled;
extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[];
+extern pgd_t init_pg_dir[], init_pg_end[];
void init_feature_override(u64 boot_status, const void *fdt, int chosen);
u64 kaslr_early_init(void *fdt, int chosen);
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 42faebb7b712..a5ca15daeb8a 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -344,50 +344,34 @@ void arch_release_task_struct(struct task_struct *tsk)
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- if (current->mm)
- fpsimd_preserve_current_state();
+ /*
+ * The current/src task's FPSIMD state may or may not be live, and may
+ * have been altered by ptrace after entry to the kernel. Save the
+ * effective FPSIMD state so that this will be copied into dst.
+ */
+ fpsimd_save_and_flush_current_state();
+ fpsimd_sync_from_effective_state(src);
+
*dst = *src;
/*
- * Detach src's sve_state (if any) from dst so that it does not
- * get erroneously used or freed prematurely. dst's copies
- * will be allocated on demand later on if dst uses SVE.
- * For consistency, also clear TIF_SVE here: this could be done
- * later in copy_process(), but to avoid tripping up future
- * maintainers it is best not to leave TIF flags and buffers in
- * an inconsistent state, even temporarily.
+ * Drop stale reference to src's sve_state and convert dst to
+ * non-streaming FPSIMD mode.
*/
+ dst->thread.fp_type = FP_STATE_FPSIMD;
dst->thread.sve_state = NULL;
clear_tsk_thread_flag(dst, TIF_SVE);
+ task_smstop_sm(dst);
/*
- * In the unlikely event that we create a new thread with ZA
- * enabled we should retain the ZA and ZT state so duplicate
- * it here. This may be shortly freed if we exec() or if
- * CLONE_SETTLS but it's simpler to do it here. To avoid
- * confusing the rest of the code ensure that we have a
- * sve_state allocated whenever sme_state is allocated.
+ * Drop stale reference to src's sme_state and ensure dst has ZA
+ * disabled.
+ *
+ * When necessary, ZA will be inherited later in copy_thread_za().
*/
- if (thread_za_enabled(&src->thread)) {
- dst->thread.sve_state = kzalloc(sve_state_size(src),
- GFP_KERNEL);
- if (!dst->thread.sve_state)
- return -ENOMEM;
-
- dst->thread.sme_state = kmemdup(src->thread.sme_state,
- sme_state_size(src),
- GFP_KERNEL);
- if (!dst->thread.sme_state) {
- kfree(dst->thread.sve_state);
- dst->thread.sve_state = NULL;
- return -ENOMEM;
- }
- } else {
- dst->thread.sme_state = NULL;
- clear_tsk_thread_flag(dst, TIF_SME);
- }
-
- dst->thread.fp_type = FP_STATE_FPSIMD;
+ dst->thread.sme_state = NULL;
+ clear_tsk_thread_flag(dst, TIF_SME);
+ dst->thread.svcr &= ~SVCR_ZA_MASK;
/* clear any pending asynchronous tag fault raised by the parent */
clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
@@ -395,6 +379,31 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
return 0;
}
+static int copy_thread_za(struct task_struct *dst, struct task_struct *src)
+{
+ if (!thread_za_enabled(&src->thread))
+ return 0;
+
+ dst->thread.sve_state = kzalloc(sve_state_size(src),
+ GFP_KERNEL);
+ if (!dst->thread.sve_state)
+ return -ENOMEM;
+
+ dst->thread.sme_state = kmemdup(src->thread.sme_state,
+ sme_state_size(src),
+ GFP_KERNEL);
+ if (!dst->thread.sme_state) {
+ kfree(dst->thread.sve_state);
+ dst->thread.sve_state = NULL;
+ return -ENOMEM;
+ }
+
+ set_tsk_thread_flag(dst, TIF_SME);
+ dst->thread.svcr |= SVCR_ZA_MASK;
+
+ return 0;
+}
+
asmlinkage void ret_from_fork(void) asm("ret_from_fork");
int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
@@ -427,8 +436,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
* out-of-sync with the saved value.
*/
*task_user_tls(p) = read_sysreg(tpidr_el0);
- if (system_supports_tpidr2())
- p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
if (system_supports_poe())
p->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
@@ -441,13 +448,39 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
}
/*
+ * Due to the AAPCS64 "ZA lazy saving scheme", PSTATE.ZA and
+ * TPIDR2 need to be manipulated as a pair, and either both
+ * need to be inherited or both need to be reset.
+ *
+ * Within a process, child threads must not inherit their
+ * parent's TPIDR2 value or they may clobber their parent's
+ * stack at some later point.
+ *
+ * When a process is fork()'d, the child must inherit ZA and
+ * TPIDR2 from its parent in case there was dormant ZA state.
+ *
+ * Use CLONE_VM to determine when the child will share the
+ * address space with the parent, and cannot safely inherit the
+ * state.
+ */
+ if (system_supports_sme()) {
+ if (!(clone_flags & CLONE_VM)) {
+ p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+ ret = copy_thread_za(p, current);
+ if (ret)
+ return ret;
+ } else {
+ p->thread.tpidr2_el0 = 0;
+ WARN_ON_ONCE(p->thread.svcr & SVCR_ZA_MASK);
+ }
+ }
+
+ /*
* If a TLS pointer was passed to clone, use it for the new
- * thread. We also reset TPIDR2 if it's in use.
+ * thread.
*/
- if (clone_flags & CLONE_SETTLS) {
+ if (clone_flags & CLONE_SETTLS)
p->thread.uw.tp_value = tls;
- p->thread.tpidr2_el0 = 0;
- }
ret = copy_thread_gcs(p, args);
if (ret != 0)
@@ -680,10 +713,11 @@ struct task_struct *__switch_to(struct task_struct *prev,
gcs_thread_switch(next);
/*
- * Complete any pending TLB or cache maintenance on this CPU in case
- * the thread migrates to a different CPU.
- * This full barrier is also required by the membarrier system
- * call.
+ * Complete any pending TLB or cache maintenance on this CPU in case the
+ * thread migrates to a different CPU. This full barrier is also
+ * required by the membarrier system call. Additionally it makes any
+ * in-progress pgtable writes visible to the table walker; See
+ * emit_pte_barriers().
*/
dsb(ish);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index f79b0d5f71ac..a360e52db02f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -594,7 +594,7 @@ static int __fpr_get(struct task_struct *target,
{
struct user_fpsimd_state *uregs;
- sve_sync_to_fpsimd(target);
+ fpsimd_sync_from_effective_state(target);
uregs = &target->thread.uw.fpsimd_state;
@@ -626,7 +626,7 @@ static int __fpr_set(struct task_struct *target,
* Ensure target->thread.uw.fpsimd_state is up to date, so that a
* short copyin can't resurrect stale data.
*/
- sve_sync_to_fpsimd(target);
+ fpsimd_sync_from_effective_state(target);
newstate = target->thread.uw.fpsimd_state;
@@ -653,7 +653,7 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
if (ret)
return ret;
- sve_sync_from_fpsimd_zeropad(target);
+ fpsimd_sync_to_effective_state_zeropad(target);
fpsimd_flush_task_state(target);
return ret;
@@ -775,6 +775,11 @@ static void sve_init_header_from_task(struct user_sve_header *header,
task_type = ARM64_VEC_SVE;
active = (task_type == type);
+ if (active && target->thread.fp_type == FP_STATE_SVE)
+ header->flags = SVE_PT_REGS_SVE;
+ else
+ header->flags = SVE_PT_REGS_FPSIMD;
+
switch (type) {
case ARM64_VEC_SVE:
if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
@@ -789,19 +794,14 @@ static void sve_init_header_from_task(struct user_sve_header *header,
return;
}
- if (active) {
- if (target->thread.fp_type == FP_STATE_FPSIMD) {
- header->flags |= SVE_PT_REGS_FPSIMD;
- } else {
- header->flags |= SVE_PT_REGS_SVE;
- }
- }
-
header->vl = task_get_vl(target, type);
vq = sve_vq_from_vl(header->vl);
header->max_vl = vec_max_vl(type);
- header->size = SVE_PT_SIZE(vq, header->flags);
+ if (active)
+ header->size = SVE_PT_SIZE(vq, header->flags);
+ else
+ header->size = sizeof(header);
header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl),
SVE_PT_REGS_SVE);
}
@@ -820,18 +820,25 @@ static int sve_get_common(struct task_struct *target,
unsigned int vq;
unsigned long start, end;
+ if (target == current)
+ fpsimd_preserve_current_state();
+
/* Header */
sve_init_header_from_task(&header, target, type);
vq = sve_vq_from_vl(header.vl);
membuf_write(&to, &header, sizeof(header));
- if (target == current)
- fpsimd_preserve_current_state();
-
BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
+ /*
+ * When the requested vector type is not active, do not present data
+ * from the other mode to userspace.
+ */
+ if (header.size == sizeof(header))
+ return 0;
+
switch ((header.flags & SVE_PT_REGS_MASK)) {
case SVE_PT_REGS_FPSIMD:
return __fpr_get(target, regset, to);
@@ -859,7 +866,7 @@ static int sve_get_common(struct task_struct *target,
return membuf_zero(&to, end - start);
default:
- return 0;
+ BUILD_BUG();
}
}
@@ -883,6 +890,9 @@ static int sve_set_common(struct task_struct *target,
struct user_sve_header header;
unsigned int vq;
unsigned long start, end;
+ bool fpsimd;
+
+ fpsimd_flush_task_state(target);
/* Header */
if (count < sizeof(header))
@@ -890,7 +900,16 @@ static int sve_set_common(struct task_struct *target,
ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header,
0, sizeof(header));
if (ret)
- goto out;
+ return ret;
+
+ /*
+ * Streaming SVE data is always stored and presented in SVE format.
+ * Require the user to provide SVE formatted data for consistency, and
+ * to avoid the risk that we configure the task into an invalid state.
+ */
+ fpsimd = (header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD;
+ if (fpsimd && type == ARM64_VEC_SME)
+ return -EINVAL;
/*
* Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by
@@ -899,7 +918,21 @@ static int sve_set_common(struct task_struct *target,
ret = vec_set_vector_length(target, type, header.vl,
((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16);
if (ret)
- goto out;
+ return ret;
+
+ /* Allocate SME storage if necessary, preserving any existing ZA/ZT state */
+ if (type == ARM64_VEC_SME) {
+ sme_alloc(target, false);
+ if (!target->thread.sme_state)
+ return -ENOMEM;
+ }
+
+ /* Allocate SVE storage if necessary, zeroing any existing SVE state */
+ if (!fpsimd) {
+ sve_alloc(target, true);
+ if (!target->thread.sve_state)
+ return -ENOMEM;
+ }
/*
* Actual VL set may be different from what the user asked
@@ -910,81 +943,47 @@ static int sve_set_common(struct task_struct *target,
/* Enter/exit streaming mode */
if (system_supports_sme()) {
- u64 old_svcr = target->thread.svcr;
-
switch (type) {
case ARM64_VEC_SVE:
target->thread.svcr &= ~SVCR_SM_MASK;
+ set_tsk_thread_flag(target, TIF_SVE);
break;
case ARM64_VEC_SME:
target->thread.svcr |= SVCR_SM_MASK;
-
- /*
- * Disable traps and ensure there is SME storage but
- * preserve any currently set values in ZA/ZT.
- */
- sme_alloc(target, false);
set_tsk_thread_flag(target, TIF_SME);
break;
default:
WARN_ON_ONCE(1);
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
-
- /*
- * If we switched then invalidate any existing SVE
- * state and ensure there's storage.
- */
- if (target->thread.svcr != old_svcr)
- sve_alloc(target, true);
}
+ /* Always zero V regs, FPSR, and FPCR */
+ memset(&current->thread.uw.fpsimd_state, 0,
+ sizeof(current->thread.uw.fpsimd_state));
+
/* Registers: FPSIMD-only case */
BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header));
- if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) {
- ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
- SVE_PT_FPSIMD_OFFSET);
+ if (fpsimd) {
clear_tsk_thread_flag(target, TIF_SVE);
target->thread.fp_type = FP_STATE_FPSIMD;
- goto out;
+ ret = __fpr_set(target, regset, pos, count, kbuf, ubuf,
+ SVE_PT_FPSIMD_OFFSET);
+ return ret;
}
- /*
- * Otherwise: no registers or full SVE case. For backwards
- * compatibility reasons we treat empty flags as SVE registers.
- */
+ /* Otherwise: no registers or full SVE case. */
+
+ target->thread.fp_type = FP_STATE_SVE;
/*
* If setting a different VL from the requested VL and there is
* register data, the data layout will be wrong: don't even
* try to set the registers in this case.
*/
- if (count && vq != sve_vq_from_vl(header.vl)) {
- ret = -EIO;
- goto out;
- }
-
- sve_alloc(target, true);
- if (!target->thread.sve_state) {
- ret = -ENOMEM;
- clear_tsk_thread_flag(target, TIF_SVE);
- target->thread.fp_type = FP_STATE_FPSIMD;
- goto out;
- }
-
- /*
- * Ensure target->thread.sve_state is up to date with target's
- * FPSIMD regs, so that a short copyin leaves trailing
- * registers unmodified. Only enable SVE if we are
- * configuring normal SVE, a system with streaming SVE may not
- * have normal SVE.
- */
- fpsimd_sync_to_sve(target);
- if (type == ARM64_VEC_SVE)
- set_tsk_thread_flag(target, TIF_SVE);
- target->thread.fp_type = FP_STATE_SVE;
+ if (count && vq != sve_vq_from_vl(header.vl))
+ return -EIO;
BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header));
start = SVE_PT_SVE_OFFSET;
@@ -993,7 +992,7 @@ static int sve_set_common(struct task_struct *target,
target->thread.sve_state,
start, end);
if (ret)
- goto out;
+ return ret;
start = end;
end = SVE_PT_SVE_FPSR_OFFSET(vq);
@@ -1009,8 +1008,6 @@ static int sve_set_common(struct task_struct *target,
&target->thread.uw.fpsimd_state.fpsr,
start, end);
-out:
- fpsimd_flush_task_state(target);
return ret;
}
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 85104587f849..77c7926a4df6 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -169,7 +169,7 @@ static void __init smp_build_mpidr_hash(void)
static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
- int size;
+ int size = 0;
void *dt_virt = fixmap_remap_fdt(dt_phys, &size, PAGE_KERNEL);
const char *name;
@@ -182,10 +182,10 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
*/
if (!early_init_dt_scan(dt_virt, dt_phys)) {
pr_crit("\n"
- "Error: invalid device tree blob at physical address %pa (virtual address 0x%px)\n"
- "The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
- "\nPlease check your bootloader.",
- &dt_phys, dt_virt);
+ "Error: invalid device tree blob: PA=%pa, VA=%px, size=%d bytes\n"
+ "The dtb must be 8-byte aligned and must not exceed 2 MB in size.\n"
+ "\nPlease check your bootloader.\n",
+ &dt_phys, dt_virt, size);
/*
* Note that in this _really_ early stage we cannot even BUG()
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index a7c37afb4ebe..417140cd399b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -250,6 +250,8 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
&current->thread.uw.fpsimd_state;
int err;
+ fpsimd_sync_from_effective_state(current);
+
/* copy the FP and status/control registers */
err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs));
__put_user_error(fpsimd->fpsr, &ctx->fpsr, err);
@@ -262,37 +264,46 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx)
return err ? -EFAULT : 0;
}
-static int restore_fpsimd_context(struct user_ctxs *user)
+static int read_fpsimd_context(struct user_fpsimd_state *fpsimd,
+ struct user_ctxs *user)
{
- struct user_fpsimd_state fpsimd;
- int err = 0;
+ int err;
/* check the size information */
if (user->fpsimd_size != sizeof(struct fpsimd_context))
return -EINVAL;
/* copy the FP and status/control registers */
- err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs),
- sizeof(fpsimd.vregs));
- __get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err);
- __get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err);
+ err = __copy_from_user(fpsimd->vregs, &(user->fpsimd->vregs),
+ sizeof(fpsimd->vregs));
+ __get_user_error(fpsimd->fpsr, &(user->fpsimd->fpsr), err);
+ __get_user_error(fpsimd->fpcr, &(user->fpsimd->fpcr), err);
+
+ return err ? -EFAULT : 0;
+}
+
+static int restore_fpsimd_context(struct user_ctxs *user)
+{
+ struct user_fpsimd_state fpsimd;
+ int err;
+
+ err = read_fpsimd_context(&fpsimd, user);
+ if (err)
+ return err;
clear_thread_flag(TIF_SVE);
+ current->thread.svcr &= ~SVCR_SM_MASK;
current->thread.fp_type = FP_STATE_FPSIMD;
/* load the hardware registers from the fpsimd_state structure */
- if (!err)
- fpsimd_update_current_state(&fpsimd);
-
- return err ? -EFAULT : 0;
+ fpsimd_update_current_state(&fpsimd);
+ return 0;
}
static int preserve_fpmr_context(struct fpmr_context __user *ctx)
{
int err = 0;
- current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR);
-
__put_user_error(FPMR_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
__put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err);
@@ -310,7 +321,7 @@ static int restore_fpmr_context(struct user_ctxs *user)
__get_user_error(fpmr, &user->fpmr->fpmr, err);
if (!err)
- write_sysreg_s(fpmr, SYS_FPMR);
+ current->thread.uw.fpmr = fpmr;
return err;
}
@@ -372,11 +383,6 @@ static int preserve_sve_context(struct sve_context __user *ctx)
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
if (vq) {
- /*
- * This assumes that the SVE state has already been saved to
- * the task struct by calling the function
- * fpsimd_signal_preserve_current_state().
- */
err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET,
current->thread.sve_state,
SVE_SIG_REGS_SIZE(vq));
@@ -391,6 +397,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
unsigned int vl, vq;
struct user_fpsimd_state fpsimd;
u16 user_vl, flags;
+ bool sm;
if (user->sve_size < sizeof(*user->sve))
return -EINVAL;
@@ -400,7 +407,8 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
if (err)
return err;
- if (flags & SVE_SIG_FLAG_SM) {
+ sm = flags & SVE_SIG_FLAG_SM;
+ if (sm) {
if (!system_supports_sme())
return -EINVAL;
@@ -420,28 +428,23 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
if (user_vl != vl)
return -EINVAL;
- if (user->sve_size == sizeof(*user->sve)) {
- clear_thread_flag(TIF_SVE);
- current->thread.svcr &= ~SVCR_SM_MASK;
- current->thread.fp_type = FP_STATE_FPSIMD;
- goto fpsimd_only;
- }
+ /*
+ * Non-streaming SVE state may be preserved without an SVE payload, in
+ * which case the SVE context only has a header with VL==0, and all
+ * state can be restored from the FPSIMD context.
+ *
+ * Streaming SVE state is always preserved with an SVE payload. For
+ * consistency and robustness, reject restoring streaming SVE state
+ * without an SVE payload.
+ */
+ if (!sm && user->sve_size == sizeof(*user->sve))
+ return restore_fpsimd_context(user);
vq = sve_vq_from_vl(vl);
if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
- /*
- * Careful: we are about __copy_from_user() directly into
- * thread.sve_state with preemption enabled, so protection is
- * needed to prevent a racing context switch from writing stale
- * registers back over the new data.
- */
-
- fpsimd_flush_task_state(current);
- /* From now, fpsimd_thread_switch() won't touch thread.sve_state */
-
sve_alloc(current, true);
if (!current->thread.sve_state) {
clear_thread_flag(TIF_SVE);
@@ -461,19 +464,14 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user)
set_thread_flag(TIF_SVE);
current->thread.fp_type = FP_STATE_SVE;
-fpsimd_only:
- /* copy the FP and status/control registers */
- /* restore_sigframe() already checked that user->fpsimd != NULL. */
- err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs,
- sizeof(fpsimd.vregs));
- __get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err);
- __get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err);
+ err = read_fpsimd_context(&fpsimd, user);
+ if (err)
+ return err;
- /* load the hardware registers from the fpsimd_state structure */
- if (!err)
- fpsimd_update_current_state(&fpsimd);
+ /* Merge the FPSIMD registers into the SVE state */
+ fpsimd_update_current_state(&fpsimd);
- return err ? -EFAULT : 0;
+ return 0;
}
#else /* ! CONFIG_ARM64_SVE */
@@ -493,13 +491,12 @@ extern int preserve_sve_context(void __user *ctx);
static int preserve_tpidr2_context(struct tpidr2_context __user *ctx)
{
+ u64 tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
int err = 0;
- current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
-
__put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err);
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
- __put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err);
+ __put_user_error(tpidr2_el0, &ctx->tpidr2, err);
return err;
}
@@ -541,11 +538,6 @@ static int preserve_za_context(struct za_context __user *ctx)
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
if (vq) {
- /*
- * This assumes that the ZA state has already been saved to
- * the task struct by calling the function
- * fpsimd_signal_preserve_current_state().
- */
err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET,
current->thread.sme_state,
ZA_SIG_REGS_SIZE(vq));
@@ -580,16 +572,6 @@ static int restore_za_context(struct user_ctxs *user)
if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq))
return -EINVAL;
- /*
- * Careful: we are about __copy_from_user() directly into
- * thread.sme_state with preemption enabled, so protection is
- * needed to prevent a racing context switch from writing stale
- * registers back over the new data.
- */
-
- fpsimd_flush_task_state(current);
- /* From now, fpsimd_thread_switch() won't touch thread.sve_state */
-
sme_alloc(current, true);
if (!current->thread.sme_state) {
current->thread.svcr &= ~SVCR_ZA_MASK;
@@ -627,11 +609,6 @@ static int preserve_zt_context(struct zt_context __user *ctx)
BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved));
err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved));
- /*
- * This assumes that the ZT state has already been saved to
- * the task struct by calling the function
- * fpsimd_signal_preserve_current_state().
- */
err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET,
thread_zt_state(&current->thread),
ZT_SIG_REGS_SIZE(1));
@@ -657,16 +634,6 @@ static int restore_zt_context(struct user_ctxs *user)
if (nregs != 1)
return -EINVAL;
- /*
- * Careful: we are about __copy_from_user() directly into
- * thread.zt_state with preemption enabled, so protection is
- * needed to prevent a racing context switch from writing stale
- * registers back over the new data.
- */
-
- fpsimd_flush_task_state(current);
- /* From now, fpsimd_thread_switch() won't touch ZT in thread state */
-
err = __copy_from_user(thread_zt_state(&current->thread),
(char __user const *)user->zt +
ZT_SIG_REGS_OFFSET,
@@ -1017,6 +984,8 @@ static int restore_sigframe(struct pt_regs *regs,
*/
forget_syscall(regs);
+ fpsimd_save_and_flush_current_state();
+
err |= !valid_user_regs(&regs->user_regs, current);
if (err == 0)
err = parse_user_sigframe(&user, sf);
@@ -1507,21 +1476,9 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig,
/* Signal handlers are invoked with ZA and streaming mode disabled */
if (system_supports_sme()) {
- /*
- * If we were in streaming mode the saved register
- * state was SVE but we will exit SM and use the
- * FPSIMD register state - flush the saved FPSIMD
- * register state in case it gets loaded.
- */
- if (current->thread.svcr & SVCR_SM_MASK) {
- memset(&current->thread.uw.fpsimd_state, 0,
- sizeof(current->thread.uw.fpsimd_state));
- current->thread.fp_type = FP_STATE_FPSIMD;
- }
-
- current->thread.svcr &= ~(SVCR_ZA_MASK |
- SVCR_SM_MASK);
- sme_smstop();
+ task_smstop_sm(current);
+ current->thread.svcr &= ~SVCR_ZA_MASK;
+ write_sysreg_s(0, SYS_TPIDR2_EL0);
}
return 0;
@@ -1535,7 +1492,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct user_access_state ua_state;
int err = 0;
- fpsimd_signal_preserve_current_state();
+ fpsimd_save_and_flush_current_state();
if (get_sigframe(&user, ksig, regs))
return 1;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 81e798b6dada..bb3b526ff43f 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -103,7 +103,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
* Note that this also saves V16-31, which aren't visible
* in AArch32.
*/
- fpsimd_signal_preserve_current_state();
+ fpsimd_save_and_flush_current_state();
/* Place structure header on the stack */
__put_user_error(magic, &frame->magic, err);
@@ -169,14 +169,17 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame)
fpsimd.fpsr = fpscr & VFP_FPSCR_STAT_MASK;
fpsimd.fpcr = fpscr & VFP_FPSCR_CTRL_MASK;
+ if (err)
+ return -EFAULT;
+
/*
* We don't need to touch the exception register, so
* reload the hardware state.
*/
- if (!err)
- fpsimd_update_current_state(&fpsimd);
+ fpsimd_save_and_flush_current_state();
+ current->thread.uw.fpsimd_state = fpsimd;
- return err ? -EFAULT : 0;
+ return 0;
}
static int compat_restore_sigframe(struct pt_regs *regs,
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 529cff825531..9bfa5c944379 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -1118,7 +1118,7 @@ static struct break_hook kasan_break_hook = {
#ifdef CONFIG_UBSAN_TRAP
static int ubsan_handler(struct pt_regs *regs, unsigned long esr)
{
- die(report_ubsan_failure(regs, esr & UBSAN_BRK_MASK), regs, esr);
+ die(report_ubsan_failure(esr & UBSAN_BRK_MASK), regs, esr);
return DBG_HOOK_HANDLED;
}
@@ -1145,7 +1145,7 @@ int __init early_brk64(unsigned long addr, unsigned long esr,
return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
#endif
#ifdef CONFIG_UBSAN_TRAP
- if ((esr_brk_comment(esr) & ~UBSAN_BRK_MASK) == UBSAN_BRK_IMM)
+ if (esr_is_ubsan_brk(esr))
return ubsan_handler(regs, esr) != DBG_HOOK_HANDLED;
#endif
return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index e73326bd3ff7..ad6133b89e7a 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -13,7 +13,7 @@
*(__kvm_ex_table) \
__stop___kvm_ex_table = .;
-#define HYPERVISOR_DATA_SECTIONS \
+#define HYPERVISOR_RODATA_SECTIONS \
HYP_SECTION_NAME(.rodata) : { \
. = ALIGN(PAGE_SIZE); \
__hyp_rodata_start = .; \
@@ -23,6 +23,15 @@
__hyp_rodata_end = .; \
}
+#define HYPERVISOR_DATA_SECTION \
+ HYP_SECTION_NAME(.data) : { \
+ . = ALIGN(PAGE_SIZE); \
+ __hyp_data_start = .; \
+ *(HYP_SECTION_NAME(.data)) \
+ . = ALIGN(PAGE_SIZE); \
+ __hyp_data_end = .; \
+ }
+
#define HYPERVISOR_PERCPU_SECTION \
. = ALIGN(PAGE_SIZE); \
HYP_SECTION_NAME(.data..percpu) : { \
@@ -51,7 +60,8 @@
#define SBSS_ALIGN PAGE_SIZE
#else /* CONFIG_KVM */
#define HYPERVISOR_EXTABLE
-#define HYPERVISOR_DATA_SECTIONS
+#define HYPERVISOR_RODATA_SECTIONS
+#define HYPERVISOR_DATA_SECTION
#define HYPERVISOR_PERCPU_SECTION
#define HYPERVISOR_RELOC_SECTION
#define SBSS_ALIGN 0
@@ -190,7 +200,7 @@ SECTIONS
/* everything from this point to __init_begin will be marked RO NX */
RO_DATA(PAGE_SIZE)
- HYPERVISOR_DATA_SECTIONS
+ HYPERVISOR_RODATA_SECTIONS
.got : { *(.got) }
/*
@@ -249,9 +259,9 @@ SECTIONS
__inittext_end = .;
__initdata_begin = .;
- init_idmap_pg_dir = .;
+ __pi_init_idmap_pg_dir = .;
. += INIT_IDMAP_DIR_SIZE;
- init_idmap_pg_end = .;
+ __pi_init_idmap_pg_end = .;
.init.data : {
INIT_DATA
@@ -295,6 +305,8 @@ SECTIONS
_sdata = .;
RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
+ HYPERVISOR_DATA_SECTION
+
/*
* Data written with the MMU off but read with the MMU on requires
* cache lines to be invalidated, discarding up to a Cache Writeback
@@ -319,11 +331,12 @@ SECTIONS
/* start of zero-init region */
BSS_SECTION(SBSS_ALIGN, 0, 0)
+ __pi___bss_start = __bss_start;
. = ALIGN(PAGE_SIZE);
- init_pg_dir = .;
+ __pi_init_pg_dir = .;
. += INIT_DIR_SIZE;
- init_pg_end = .;
+ __pi_init_pg_end = .;
/* end of zero-init region */
. += SZ_4K; /* stack for the early C runtime */
@@ -332,6 +345,7 @@ SECTIONS
. = ALIGN(SEGMENT_ALIGN);
__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
_end = .;
+ __pi__end = .;
STABS_DEBUG
DWARF_DEBUG
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 209bc76263f1..7c329e01c557 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -14,7 +14,7 @@ CFLAGS_sys_regs.o += -Wno-override-init
CFLAGS_handle_exit.o += -Wno-override-init
kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \
- inject_fault.o va_layout.o handle_exit.o \
+ inject_fault.o va_layout.o handle_exit.o config.o \
guest.o debug.o reset.o sys_regs.o stacktrace.o \
vgic-sys-reg-v3.o fpsimd.o pkvm.o \
arch_timer.o trng.o vmid.o emulate-nested.o nested.o at.o \
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 19ca57def629..36cfcffb40d8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -368,6 +368,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_ARM_EL1_32BIT:
r = cpus_have_final_cap(ARM64_HAS_32BIT_EL1);
break;
+ case KVM_CAP_ARM_EL2:
+ r = cpus_have_final_cap(ARM64_HAS_NESTED_VIRT);
+ break;
+ case KVM_CAP_ARM_EL2_E2H0:
+ r = cpus_have_final_cap(ARM64_HAS_HCR_NV1);
+ break;
case KVM_CAP_GUEST_DEBUG_HW_BPS:
r = get_num_brps();
break;
@@ -843,6 +849,10 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
return ret;
if (vcpu_has_nv(vcpu)) {
+ ret = kvm_vcpu_allocate_vncr_tlb(vcpu);
+ if (ret)
+ return ret;
+
ret = kvm_vgic_vcpu_nv_init(vcpu);
if (ret)
return ret;
@@ -2450,6 +2460,19 @@ static void kvm_hyp_init_symbols(void)
kvm_nvhe_sym(__icache_flags) = __icache_flags;
kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
+ /* Propagate the FGT state to the the nVHE side */
+ kvm_nvhe_sym(hfgrtr_masks) = hfgrtr_masks;
+ kvm_nvhe_sym(hfgwtr_masks) = hfgwtr_masks;
+ kvm_nvhe_sym(hfgitr_masks) = hfgitr_masks;
+ kvm_nvhe_sym(hdfgrtr_masks) = hdfgrtr_masks;
+ kvm_nvhe_sym(hdfgwtr_masks) = hdfgwtr_masks;
+ kvm_nvhe_sym(hafgrtr_masks) = hafgrtr_masks;
+ kvm_nvhe_sym(hfgrtr2_masks) = hfgrtr2_masks;
+ kvm_nvhe_sym(hfgwtr2_masks) = hfgwtr2_masks;
+ kvm_nvhe_sym(hfgitr2_masks) = hfgitr2_masks;
+ kvm_nvhe_sym(hdfgrtr2_masks)= hdfgrtr2_masks;
+ kvm_nvhe_sym(hdfgwtr2_masks)= hdfgwtr2_masks;
+
/*
* Flush entire BSS since part of its data containing init symbols is read
* while the MMU is off.
@@ -2604,6 +2627,13 @@ static int __init init_hyp_mode(void)
goto out_err;
}
+ err = create_hyp_mappings(kvm_ksym_ref(__hyp_data_start),
+ kvm_ksym_ref(__hyp_data_end), PAGE_HYP);
+ if (err) {
+ kvm_err("Cannot map .hyp.data section\n");
+ goto out_err;
+ }
+
err = create_hyp_mappings(kvm_ksym_ref(__hyp_rodata_start),
kvm_ksym_ref(__hyp_rodata_end), PAGE_HYP_RO);
if (err) {
diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c
index f74a66ce3064..a25be111cd8f 100644
--- a/arch/arm64/kvm/at.c
+++ b/arch/arm64/kvm/at.c
@@ -10,61 +10,11 @@
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
-enum trans_regime {
- TR_EL10,
- TR_EL20,
- TR_EL2,
-};
-
-struct s1_walk_info {
- u64 baddr;
- enum trans_regime regime;
- unsigned int max_oa_bits;
- unsigned int pgshift;
- unsigned int txsz;
- int sl;
- bool hpd;
- bool e0poe;
- bool poe;
- bool pan;
- bool be;
- bool s2;
-};
-
-struct s1_walk_result {
- union {
- struct {
- u64 desc;
- u64 pa;
- s8 level;
- u8 APTable;
- bool UXNTable;
- bool PXNTable;
- bool uwxn;
- bool uov;
- bool ur;
- bool uw;
- bool ux;
- bool pwxn;
- bool pov;
- bool pr;
- bool pw;
- bool px;
- };
- struct {
- u8 fst;
- bool ptw;
- bool s2;
- };
- };
- bool failed;
-};
-
-static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool ptw, bool s2)
+static void fail_s1_walk(struct s1_walk_result *wr, u8 fst, bool s1ptw)
{
wr->fst = fst;
- wr->ptw = ptw;
- wr->s2 = s2;
+ wr->ptw = s1ptw;
+ wr->s2 = s1ptw;
wr->failed = true;
}
@@ -145,20 +95,15 @@ static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi)
}
}
-static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
+static int setup_s1_walk(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
struct s1_walk_result *wr, u64 va)
{
u64 hcr, sctlr, tcr, tg, ps, ia_bits, ttbr;
unsigned int stride, x;
- bool va55, tbi, lva, as_el0;
+ bool va55, tbi, lva;
hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
- wi->regime = compute_translation_regime(vcpu, op);
- as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W);
- wi->pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) &&
- (*vcpu_cpsr(vcpu) & PSR_PAN_BIT);
-
va55 = va & BIT(55);
if (wi->regime == TR_EL2 && va55)
@@ -319,7 +264,7 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
/* R_BNDVG and following statements */
if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR2_EL1, E0PD, IMP) &&
- as_el0 && (tcr & (va55 ? TCR_E0PD1 : TCR_E0PD0)))
+ wi->as_el0 && (tcr & (va55 ? TCR_E0PD1 : TCR_E0PD0)))
goto transfault_l0;
/* AArch64.S1StartLevel() */
@@ -345,11 +290,11 @@ static int setup_s1_walk(struct kvm_vcpu *vcpu, u32 op, struct s1_walk_info *wi,
return 0;
addrsz: /* Address Size Fault level 0 */
- fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(0), false, false);
+ fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(0), false);
return -EFAULT;
transfault_l0: /* Translation Fault level 0 */
- fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(0), false, false);
+ fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(0), false);
return -EFAULT;
}
@@ -380,13 +325,13 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
if (ret) {
fail_s1_walk(wr,
(s2_trans.esr & ~ESR_ELx_FSC_LEVEL) | level,
- true, true);
+ true);
return ret;
}
if (!kvm_s2_trans_readable(&s2_trans)) {
fail_s1_walk(wr, ESR_ELx_FSC_PERM_L(level),
- true, true);
+ true);
return -EPERM;
}
@@ -396,8 +341,7 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
ret = kvm_read_guest(vcpu->kvm, ipa, &desc, sizeof(desc));
if (ret) {
- fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level),
- true, false);
+ fail_s1_walk(wr, ESR_ELx_FSC_SEA_TTW(level), false);
return ret;
}
@@ -457,6 +401,11 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
if (check_output_size(desc & GENMASK(47, va_bottom), wi))
goto addrsz;
+ if (!(desc & PTE_AF)) {
+ fail_s1_walk(wr, ESR_ELx_FSC_ACCESS_L(level), false);
+ return -EACCES;
+ }
+
va_bottom += contiguous_bit_shift(desc, wi, level);
wr->failed = false;
@@ -465,13 +414,40 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
wr->pa = desc & GENMASK(47, va_bottom);
wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0);
+ wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG);
+ if (wr->nG) {
+ u64 asid_ttbr, tcr;
+
+ switch (wi->regime) {
+ case TR_EL10:
+ tcr = vcpu_read_sys_reg(vcpu, TCR_EL1);
+ asid_ttbr = ((tcr & TCR_A1) ?
+ vcpu_read_sys_reg(vcpu, TTBR1_EL1) :
+ vcpu_read_sys_reg(vcpu, TTBR0_EL1));
+ break;
+ case TR_EL20:
+ tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+ asid_ttbr = ((tcr & TCR_A1) ?
+ vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
+ vcpu_read_sys_reg(vcpu, TTBR0_EL2));
+ break;
+ default:
+ BUG();
+ }
+
+ wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr);
+ if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+ !(tcr & TCR_ASID16))
+ wr->asid &= GENMASK(7, 0);
+ }
+
return 0;
addrsz:
- fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(level), true, false);
+ fail_s1_walk(wr, ESR_ELx_FSC_ADDRSZ_L(level), false);
return -EINVAL;
transfault:
- fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(level), true, false);
+ fail_s1_walk(wr, ESR_ELx_FSC_FAULT_L(level), false);
return -ENOENT;
}
@@ -488,7 +464,6 @@ struct mmu_config {
u64 sctlr;
u64 vttbr;
u64 vtcr;
- u64 hcr;
};
static void __mmu_config_save(struct mmu_config *config)
@@ -511,13 +486,10 @@ static void __mmu_config_save(struct mmu_config *config)
config->sctlr = read_sysreg_el1(SYS_SCTLR);
config->vttbr = read_sysreg(vttbr_el2);
config->vtcr = read_sysreg(vtcr_el2);
- config->hcr = read_sysreg(hcr_el2);
}
static void __mmu_config_restore(struct mmu_config *config)
{
- write_sysreg(config->hcr, hcr_el2);
-
/*
* ARM errata 1165522 and 1530923 require TGE to be 1 before
* we update the guest state.
@@ -1155,7 +1127,12 @@ static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
bool perm_fail = false;
int ret, idx;
- ret = setup_s1_walk(vcpu, op, &wi, &wr, vaddr);
+ wi.regime = compute_translation_regime(vcpu, op);
+ wi.as_el0 = (op == OP_AT_S1E0R || op == OP_AT_S1E0W);
+ wi.pan = (op == OP_AT_S1E1RP || op == OP_AT_S1E1WP) &&
+ (*vcpu_cpsr(vcpu) & PSR_PAN_BIT);
+
+ ret = setup_s1_walk(vcpu, &wi, &wr, vaddr);
if (ret)
goto compute_par;
@@ -1198,7 +1175,7 @@ static u64 handle_at_slow(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
}
if (perm_fail)
- fail_s1_walk(&wr, ESR_ELx_FSC_PERM_L(wr.level), false, false);
+ fail_s1_walk(&wr, ESR_ELx_FSC_PERM_L(wr.level), false);
compute_par:
return compute_par_s1(vcpu, &wr, wi.regime);
@@ -1210,7 +1187,8 @@ compute_par:
* If the translation is unsuccessful, the value may only contain
* PAR_EL1.F, and cannot be taken at face value. It isn't an
* indication of the translation having failed, only that the fast
- * path did not succeed, *unless* it indicates a S1 permission fault.
+ * path did not succeed, *unless* it indicates a S1 permission or
+ * access fault.
*/
static u64 __kvm_at_s1e01_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
{
@@ -1266,8 +1244,8 @@ static u64 __kvm_at_s1e01_fast(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
__load_stage2(mmu, mmu->arch);
skip_mmu_switch:
- /* Clear TGE, enable S2 translation, we're rolling */
- write_sysreg((config.hcr & ~HCR_TGE) | HCR_VM, hcr_el2);
+ /* Temporarily switch back to guest context */
+ write_sysreg_hcr(vcpu->arch.hcr_el2);
isb();
switch (op) {
@@ -1299,6 +1277,8 @@ skip_mmu_switch:
if (!fail)
par = read_sysreg_par();
+ write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
+
if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
__mmu_config_restore(&config);
@@ -1313,19 +1293,29 @@ static bool par_check_s1_perm_fault(u64 par)
!(par & SYS_PAR_EL1_S));
}
+static bool par_check_s1_access_fault(u64 par)
+{
+ u8 fst = FIELD_GET(SYS_PAR_EL1_FST, par);
+
+ return ((fst & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_ACCESS &&
+ !(par & SYS_PAR_EL1_S));
+}
+
void __kvm_at_s1e01(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
{
u64 par = __kvm_at_s1e01_fast(vcpu, op, vaddr);
/*
- * If PAR_EL1 reports that AT failed on a S1 permission fault, we
- * know for sure that the PTW was able to walk the S1 tables and
- * there's nothing else to do.
+ * If PAR_EL1 reports that AT failed on a S1 permission or access
+ * fault, we know for sure that the PTW was able to walk the S1
+ * tables and there's nothing else to do.
*
* If AT failed for any other reason, then we must walk the guest S1
* to emulate the instruction.
*/
- if ((par & SYS_PAR_EL1_F) && !par_check_s1_perm_fault(par))
+ if ((par & SYS_PAR_EL1_F) &&
+ !par_check_s1_perm_fault(par) &&
+ !par_check_s1_access_fault(par))
par = handle_at_slow(vcpu, op, vaddr);
vcpu_write_sys_reg(vcpu, par, PAR_EL1);
@@ -1350,7 +1340,7 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
if (!vcpu_el2_e2h_is_set(vcpu))
val |= HCR_NV | HCR_NV1;
- write_sysreg(val, hcr_el2);
+ write_sysreg_hcr(val);
isb();
par = SYS_PAR_EL1_F;
@@ -1375,7 +1365,7 @@ void __kvm_at_s1e2(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
if (!fail)
par = read_sysreg_par();
- write_sysreg(hcr, hcr_el2);
+ write_sysreg_hcr(hcr);
isb();
}
@@ -1444,3 +1434,31 @@ void __kvm_at_s12(struct kvm_vcpu *vcpu, u32 op, u64 vaddr)
par = compute_par_s12(vcpu, par, &out);
vcpu_write_sys_reg(vcpu, par, PAR_EL1);
}
+
+/*
+ * Translate a VA for a given EL in a given translation regime, with
+ * or without PAN. This requires wi->{regime, as_el0, pan} to be
+ * set. The rest of the wi and wr should be 0-initialised.
+ */
+int __kvm_translate_va(struct kvm_vcpu *vcpu, struct s1_walk_info *wi,
+ struct s1_walk_result *wr, u64 va)
+{
+ int ret;
+
+ ret = setup_s1_walk(vcpu, wi, wr, va);
+ if (ret)
+ return ret;
+
+ if (wr->level == S1_MMU_DISABLED) {
+ wr->ur = wr->uw = wr->ux = true;
+ wr->pr = wr->pw = wr->px = true;
+ } else {
+ ret = walk_s1(vcpu, wi, wr, va);
+ if (ret)
+ return ret;
+
+ compute_s1_permissions(vcpu, wi, wr);
+ }
+
+ return 0;
+}
diff --git a/arch/arm64/kvm/config.c b/arch/arm64/kvm/config.c
new file mode 100644
index 000000000000..54911a93b001
--- /dev/null
+++ b/arch/arm64/kvm/config.c
@@ -0,0 +1,1085 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Google LLC
+ * Author: Marc Zyngier <maz@kernel.org>
+ */
+
+#include <linux/kvm_host.h>
+#include <asm/sysreg.h>
+
+struct reg_bits_to_feat_map {
+ u64 bits;
+
+#define NEVER_FGU BIT(0) /* Can trap, but never UNDEF */
+#define CALL_FUNC BIT(1) /* Needs to evaluate tons of crap */
+#define FIXED_VALUE BIT(2) /* RAZ/WI or RAO/WI in KVM */
+ unsigned long flags;
+
+ union {
+ struct {
+ u8 regidx;
+ u8 shift;
+ u8 width;
+ bool sign;
+ s8 lo_lim;
+ };
+ bool (*match)(struct kvm *);
+ bool (*fval)(struct kvm *, u64 *);
+ };
+};
+
+#define __NEEDS_FEAT_3(m, f, id, fld, lim) \
+ { \
+ .bits = (m), \
+ .flags = (f), \
+ .regidx = IDREG_IDX(SYS_ ## id), \
+ .shift = id ##_## fld ## _SHIFT, \
+ .width = id ##_## fld ## _WIDTH, \
+ .sign = id ##_## fld ## _SIGNED, \
+ .lo_lim = id ##_## fld ##_## lim \
+ }
+
+#define __NEEDS_FEAT_2(m, f, fun, dummy) \
+ { \
+ .bits = (m), \
+ .flags = (f) | CALL_FUNC, \
+ .fval = (fun), \
+ }
+
+#define __NEEDS_FEAT_1(m, f, fun) \
+ { \
+ .bits = (m), \
+ .flags = (f) | CALL_FUNC, \
+ .match = (fun), \
+ }
+
+#define NEEDS_FEAT_FLAG(m, f, ...) \
+ CONCATENATE(__NEEDS_FEAT_, COUNT_ARGS(__VA_ARGS__))(m, f, __VA_ARGS__)
+
+#define NEEDS_FEAT_FIXED(m, ...) \
+ NEEDS_FEAT_FLAG(m, FIXED_VALUE, __VA_ARGS__, 0)
+
+#define NEEDS_FEAT(m, ...) NEEDS_FEAT_FLAG(m, 0, __VA_ARGS__)
+
+#define FEAT_SPE ID_AA64DFR0_EL1, PMSVer, IMP
+#define FEAT_SPE_FnE ID_AA64DFR0_EL1, PMSVer, V1P2
+#define FEAT_BRBE ID_AA64DFR0_EL1, BRBE, IMP
+#define FEAT_TRC_SR ID_AA64DFR0_EL1, TraceVer, IMP
+#define FEAT_PMUv3 ID_AA64DFR0_EL1, PMUVer, IMP
+#define FEAT_PMUv3p9 ID_AA64DFR0_EL1, PMUVer, V3P9
+#define FEAT_TRBE ID_AA64DFR0_EL1, TraceBuffer, IMP
+#define FEAT_TRBEv1p1 ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1
+#define FEAT_DoubleLock ID_AA64DFR0_EL1, DoubleLock, IMP
+#define FEAT_TRF ID_AA64DFR0_EL1, TraceFilt, IMP
+#define FEAT_AA32EL0 ID_AA64PFR0_EL1, EL0, AARCH32
+#define FEAT_AA32EL1 ID_AA64PFR0_EL1, EL1, AARCH32
+#define FEAT_AA64EL1 ID_AA64PFR0_EL1, EL1, IMP
+#define FEAT_AA64EL3 ID_AA64PFR0_EL1, EL3, IMP
+#define FEAT_AIE ID_AA64MMFR3_EL1, AIE, IMP
+#define FEAT_S2POE ID_AA64MMFR3_EL1, S2POE, IMP
+#define FEAT_S1POE ID_AA64MMFR3_EL1, S1POE, IMP
+#define FEAT_S1PIE ID_AA64MMFR3_EL1, S1PIE, IMP
+#define FEAT_THE ID_AA64PFR1_EL1, THE, IMP
+#define FEAT_SME ID_AA64PFR1_EL1, SME, IMP
+#define FEAT_GCS ID_AA64PFR1_EL1, GCS, IMP
+#define FEAT_LS64 ID_AA64ISAR1_EL1, LS64, LS64
+#define FEAT_LS64_V ID_AA64ISAR1_EL1, LS64, LS64_V
+#define FEAT_LS64_ACCDATA ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA
+#define FEAT_RAS ID_AA64PFR0_EL1, RAS, IMP
+#define FEAT_RASv2 ID_AA64PFR0_EL1, RAS, V2
+#define FEAT_GICv3 ID_AA64PFR0_EL1, GIC, IMP
+#define FEAT_LOR ID_AA64MMFR1_EL1, LO, IMP
+#define FEAT_SPEv1p4 ID_AA64DFR0_EL1, PMSVer, V1P4
+#define FEAT_SPEv1p5 ID_AA64DFR0_EL1, PMSVer, V1P5
+#define FEAT_ATS1A ID_AA64ISAR2_EL1, ATS1A, IMP
+#define FEAT_SPECRES2 ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX
+#define FEAT_SPECRES ID_AA64ISAR1_EL1, SPECRES, IMP
+#define FEAT_TLBIRANGE ID_AA64ISAR0_EL1, TLB, RANGE
+#define FEAT_TLBIOS ID_AA64ISAR0_EL1, TLB, OS
+#define FEAT_PAN2 ID_AA64MMFR1_EL1, PAN, PAN2
+#define FEAT_DPB2 ID_AA64ISAR1_EL1, DPB, DPB2
+#define FEAT_AMUv1 ID_AA64PFR0_EL1, AMU, IMP
+#define FEAT_AMUv1p1 ID_AA64PFR0_EL1, AMU, V1P1
+#define FEAT_CMOW ID_AA64MMFR1_EL1, CMOW, IMP
+#define FEAT_D128 ID_AA64MMFR3_EL1, D128, IMP
+#define FEAT_DoubleFault2 ID_AA64PFR1_EL1, DF2, IMP
+#define FEAT_FPMR ID_AA64PFR2_EL1, FPMR, IMP
+#define FEAT_MOPS ID_AA64ISAR2_EL1, MOPS, IMP
+#define FEAT_NMI ID_AA64PFR1_EL1, NMI, IMP
+#define FEAT_SCTLR2 ID_AA64MMFR3_EL1, SCTLRX, IMP
+#define FEAT_SYSREG128 ID_AA64ISAR2_EL1, SYSREG_128, IMP
+#define FEAT_TCR2 ID_AA64MMFR3_EL1, TCRX, IMP
+#define FEAT_XS ID_AA64ISAR1_EL1, XS, IMP
+#define FEAT_EVT ID_AA64MMFR2_EL1, EVT, IMP
+#define FEAT_EVT_TTLBxS ID_AA64MMFR2_EL1, EVT, TTLBxS
+#define FEAT_MTE2 ID_AA64PFR1_EL1, MTE, MTE2
+#define FEAT_RME ID_AA64PFR0_EL1, RME, IMP
+#define FEAT_MPAM ID_AA64PFR0_EL1, MPAM, 1
+#define FEAT_S2FWB ID_AA64MMFR2_EL1, FWB, IMP
+#define FEAT_TME ID_AA64ISAR0_EL1, TME, IMP
+#define FEAT_TWED ID_AA64MMFR1_EL1, TWED, IMP
+#define FEAT_E2H0 ID_AA64MMFR4_EL1, E2H0, IMP
+#define FEAT_SRMASK ID_AA64MMFR4_EL1, SRMASK, IMP
+#define FEAT_PoPS ID_AA64MMFR4_EL1, PoPS, IMP
+#define FEAT_PFAR ID_AA64PFR1_EL1, PFAR, IMP
+#define FEAT_Debugv8p9 ID_AA64DFR0_EL1, PMUVer, V3P9
+#define FEAT_PMUv3_SS ID_AA64DFR0_EL1, PMSS, IMP
+#define FEAT_SEBEP ID_AA64DFR0_EL1, SEBEP, IMP
+#define FEAT_EBEP ID_AA64DFR1_EL1, EBEP, IMP
+#define FEAT_ITE ID_AA64DFR1_EL1, ITE, IMP
+#define FEAT_PMUv3_ICNTR ID_AA64DFR1_EL1, PMICNTR, IMP
+#define FEAT_SPMU ID_AA64DFR1_EL1, SPMU, IMP
+#define FEAT_SPE_nVM ID_AA64DFR2_EL1, SPE_nVM, IMP
+#define FEAT_STEP2 ID_AA64DFR2_EL1, STEP, IMP
+
+static bool not_feat_aa64el3(struct kvm *kvm)
+{
+ return !kvm_has_feat(kvm, FEAT_AA64EL3);
+}
+
+static bool feat_nv2(struct kvm *kvm)
+{
+ return ((kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY) &&
+ kvm_has_feat_enum(kvm, ID_AA64MMFR2_EL1, NV, NI)) ||
+ kvm_has_feat(kvm, ID_AA64MMFR2_EL1, NV, NV2));
+}
+
+static bool feat_nv2_e2h0_ni(struct kvm *kvm)
+{
+ return feat_nv2(kvm) && !kvm_has_feat(kvm, FEAT_E2H0);
+}
+
+static bool feat_rasv1p1(struct kvm *kvm)
+{
+ return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1) ||
+ (kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, RAS, IMP) &&
+ kvm_has_feat(kvm, ID_AA64PFR1_EL1, RAS_frac, RASv1p1)));
+}
+
+static bool feat_csv2_2_csv2_1p2(struct kvm *kvm)
+{
+ return (kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) ||
+ (kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2) &&
+ kvm_has_feat_enum(kvm, ID_AA64PFR0_EL1, CSV2, IMP)));
+}
+
+static bool feat_pauth(struct kvm *kvm)
+{
+ return kvm_has_pauth(kvm, PAuth);
+}
+
+static bool feat_pauth_lr(struct kvm *kvm)
+{
+ return kvm_has_pauth(kvm, PAuth_LR);
+}
+
+static bool feat_aderr(struct kvm *kvm)
+{
+ return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, FEAT_ADERR) &&
+ kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SDERR, FEAT_ADERR));
+}
+
+static bool feat_anerr(struct kvm *kvm)
+{
+ return (kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ANERR, FEAT_ANERR) &&
+ kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SNERR, FEAT_ANERR));
+}
+
+static bool feat_sme_smps(struct kvm *kvm)
+{
+ /*
+ * Revists this if KVM ever supports SME -- this really should
+ * look at the guest's view of SMIDR_EL1. Funnily enough, this
+ * is not captured in the JSON file, but only as a note in the
+ * ARM ARM.
+ */
+ return (kvm_has_feat(kvm, FEAT_SME) &&
+ (read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS));
+}
+
+static bool feat_spe_fds(struct kvm *kvm)
+{
+ /*
+ * Revists this if KVM ever supports SPE -- this really should
+ * look at the guest's view of PMSIDR_EL1.
+ */
+ return (kvm_has_feat(kvm, FEAT_SPEv1p4) &&
+ (read_sysreg_s(SYS_PMSIDR_EL1) & PMSIDR_EL1_FDS));
+}
+
+static bool feat_trbe_mpam(struct kvm *kvm)
+{
+ /*
+ * Revists this if KVM ever supports both MPAM and TRBE --
+ * this really should look at the guest's view of TRBIDR_EL1.
+ */
+ return (kvm_has_feat(kvm, FEAT_TRBE) &&
+ kvm_has_feat(kvm, FEAT_MPAM) &&
+ (read_sysreg_s(SYS_TRBIDR_EL1) & TRBIDR_EL1_MPAM));
+}
+
+static bool feat_ebep_pmuv3_ss(struct kvm *kvm)
+{
+ return kvm_has_feat(kvm, FEAT_EBEP) || kvm_has_feat(kvm, FEAT_PMUv3_SS);
+}
+
+static bool compute_hcr_rw(struct kvm *kvm, u64 *bits)
+{
+ /* This is purely academic: AArch32 and NV are mutually exclusive */
+ if (bits) {
+ if (kvm_has_feat(kvm, FEAT_AA32EL1))
+ *bits &= ~HCR_EL2_RW;
+ else
+ *bits |= HCR_EL2_RW;
+ }
+
+ return true;
+}
+
+static bool compute_hcr_e2h(struct kvm *kvm, u64 *bits)
+{
+ if (bits) {
+ if (kvm_has_feat(kvm, FEAT_E2H0))
+ *bits &= ~HCR_EL2_E2H;
+ else
+ *bits |= HCR_EL2_E2H;
+ }
+
+ return true;
+}
+
+static const struct reg_bits_to_feat_map hfgrtr_feat_map[] = {
+ NEEDS_FEAT(HFGRTR_EL2_nAMAIR2_EL1 |
+ HFGRTR_EL2_nMAIR2_EL1,
+ FEAT_AIE),
+ NEEDS_FEAT(HFGRTR_EL2_nS2POR_EL1, FEAT_S2POE),
+ NEEDS_FEAT(HFGRTR_EL2_nPOR_EL1 |
+ HFGRTR_EL2_nPOR_EL0,
+ FEAT_S1POE),
+ NEEDS_FEAT(HFGRTR_EL2_nPIR_EL1 |
+ HFGRTR_EL2_nPIRE0_EL1,
+ FEAT_S1PIE),
+ NEEDS_FEAT(HFGRTR_EL2_nRCWMASK_EL1, FEAT_THE),
+ NEEDS_FEAT(HFGRTR_EL2_nTPIDR2_EL0 |
+ HFGRTR_EL2_nSMPRI_EL1,
+ FEAT_SME),
+ NEEDS_FEAT(HFGRTR_EL2_nGCS_EL1 |
+ HFGRTR_EL2_nGCS_EL0,
+ FEAT_GCS),
+ NEEDS_FEAT(HFGRTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA),
+ NEEDS_FEAT(HFGRTR_EL2_ERXADDR_EL1 |
+ HFGRTR_EL2_ERXMISCn_EL1 |
+ HFGRTR_EL2_ERXSTATUS_EL1 |
+ HFGRTR_EL2_ERXCTLR_EL1 |
+ HFGRTR_EL2_ERXFR_EL1 |
+ HFGRTR_EL2_ERRSELR_EL1 |
+ HFGRTR_EL2_ERRIDR_EL1,
+ FEAT_RAS),
+ NEEDS_FEAT(HFGRTR_EL2_ERXPFGCDN_EL1 |
+ HFGRTR_EL2_ERXPFGCTL_EL1 |
+ HFGRTR_EL2_ERXPFGF_EL1,
+ feat_rasv1p1),
+ NEEDS_FEAT(HFGRTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3),
+ NEEDS_FEAT(HFGRTR_EL2_SCXTNUM_EL0 |
+ HFGRTR_EL2_SCXTNUM_EL1,
+ feat_csv2_2_csv2_1p2),
+ NEEDS_FEAT(HFGRTR_EL2_LORSA_EL1 |
+ HFGRTR_EL2_LORN_EL1 |
+ HFGRTR_EL2_LORID_EL1 |
+ HFGRTR_EL2_LOREA_EL1 |
+ HFGRTR_EL2_LORC_EL1,
+ FEAT_LOR),
+ NEEDS_FEAT(HFGRTR_EL2_APIBKey |
+ HFGRTR_EL2_APIAKey |
+ HFGRTR_EL2_APGAKey |
+ HFGRTR_EL2_APDBKey |
+ HFGRTR_EL2_APDAKey,
+ feat_pauth),
+ NEEDS_FEAT_FLAG(HFGRTR_EL2_VBAR_EL1 |
+ HFGRTR_EL2_TTBR1_EL1 |
+ HFGRTR_EL2_TTBR0_EL1 |
+ HFGRTR_EL2_TPIDR_EL0 |
+ HFGRTR_EL2_TPIDRRO_EL0 |
+ HFGRTR_EL2_TPIDR_EL1 |
+ HFGRTR_EL2_TCR_EL1 |
+ HFGRTR_EL2_SCTLR_EL1 |
+ HFGRTR_EL2_REVIDR_EL1 |
+ HFGRTR_EL2_PAR_EL1 |
+ HFGRTR_EL2_MPIDR_EL1 |
+ HFGRTR_EL2_MIDR_EL1 |
+ HFGRTR_EL2_MAIR_EL1 |
+ HFGRTR_EL2_ISR_EL1 |
+ HFGRTR_EL2_FAR_EL1 |
+ HFGRTR_EL2_ESR_EL1 |
+ HFGRTR_EL2_DCZID_EL0 |
+ HFGRTR_EL2_CTR_EL0 |
+ HFGRTR_EL2_CSSELR_EL1 |
+ HFGRTR_EL2_CPACR_EL1 |
+ HFGRTR_EL2_CONTEXTIDR_EL1|
+ HFGRTR_EL2_CLIDR_EL1 |
+ HFGRTR_EL2_CCSIDR_EL1 |
+ HFGRTR_EL2_AMAIR_EL1 |
+ HFGRTR_EL2_AIDR_EL1 |
+ HFGRTR_EL2_AFSR1_EL1 |
+ HFGRTR_EL2_AFSR0_EL1,
+ NEVER_FGU, FEAT_AA64EL1),
+};
+
+static const struct reg_bits_to_feat_map hfgwtr_feat_map[] = {
+ NEEDS_FEAT(HFGWTR_EL2_nAMAIR2_EL1 |
+ HFGWTR_EL2_nMAIR2_EL1,
+ FEAT_AIE),
+ NEEDS_FEAT(HFGWTR_EL2_nS2POR_EL1, FEAT_S2POE),
+ NEEDS_FEAT(HFGWTR_EL2_nPOR_EL1 |
+ HFGWTR_EL2_nPOR_EL0,
+ FEAT_S1POE),
+ NEEDS_FEAT(HFGWTR_EL2_nPIR_EL1 |
+ HFGWTR_EL2_nPIRE0_EL1,
+ FEAT_S1PIE),
+ NEEDS_FEAT(HFGWTR_EL2_nRCWMASK_EL1, FEAT_THE),
+ NEEDS_FEAT(HFGWTR_EL2_nTPIDR2_EL0 |
+ HFGWTR_EL2_nSMPRI_EL1,
+ FEAT_SME),
+ NEEDS_FEAT(HFGWTR_EL2_nGCS_EL1 |
+ HFGWTR_EL2_nGCS_EL0,
+ FEAT_GCS),
+ NEEDS_FEAT(HFGWTR_EL2_nACCDATA_EL1, FEAT_LS64_ACCDATA),
+ NEEDS_FEAT(HFGWTR_EL2_ERXADDR_EL1 |
+ HFGWTR_EL2_ERXMISCn_EL1 |
+ HFGWTR_EL2_ERXSTATUS_EL1 |
+ HFGWTR_EL2_ERXCTLR_EL1 |
+ HFGWTR_EL2_ERRSELR_EL1,
+ FEAT_RAS),
+ NEEDS_FEAT(HFGWTR_EL2_ERXPFGCDN_EL1 |
+ HFGWTR_EL2_ERXPFGCTL_EL1,
+ feat_rasv1p1),
+ NEEDS_FEAT(HFGWTR_EL2_ICC_IGRPENn_EL1, FEAT_GICv3),
+ NEEDS_FEAT(HFGWTR_EL2_SCXTNUM_EL0 |
+ HFGWTR_EL2_SCXTNUM_EL1,
+ feat_csv2_2_csv2_1p2),
+ NEEDS_FEAT(HFGWTR_EL2_LORSA_EL1 |
+ HFGWTR_EL2_LORN_EL1 |
+ HFGWTR_EL2_LOREA_EL1 |
+ HFGWTR_EL2_LORC_EL1,
+ FEAT_LOR),
+ NEEDS_FEAT(HFGWTR_EL2_APIBKey |
+ HFGWTR_EL2_APIAKey |
+ HFGWTR_EL2_APGAKey |
+ HFGWTR_EL2_APDBKey |
+ HFGWTR_EL2_APDAKey,
+ feat_pauth),
+ NEEDS_FEAT_FLAG(HFGWTR_EL2_VBAR_EL1 |
+ HFGWTR_EL2_TTBR1_EL1 |
+ HFGWTR_EL2_TTBR0_EL1 |
+ HFGWTR_EL2_TPIDR_EL0 |
+ HFGWTR_EL2_TPIDRRO_EL0 |
+ HFGWTR_EL2_TPIDR_EL1 |
+ HFGWTR_EL2_TCR_EL1 |
+ HFGWTR_EL2_SCTLR_EL1 |
+ HFGWTR_EL2_PAR_EL1 |
+ HFGWTR_EL2_MAIR_EL1 |
+ HFGWTR_EL2_FAR_EL1 |
+ HFGWTR_EL2_ESR_EL1 |
+ HFGWTR_EL2_CSSELR_EL1 |
+ HFGWTR_EL2_CPACR_EL1 |
+ HFGWTR_EL2_CONTEXTIDR_EL1|
+ HFGWTR_EL2_AMAIR_EL1 |
+ HFGWTR_EL2_AFSR1_EL1 |
+ HFGWTR_EL2_AFSR0_EL1,
+ NEVER_FGU, FEAT_AA64EL1),
+};
+
+static const struct reg_bits_to_feat_map hdfgrtr_feat_map[] = {
+ NEEDS_FEAT(HDFGRTR_EL2_PMBIDR_EL1 |
+ HDFGRTR_EL2_PMSLATFR_EL1 |
+ HDFGRTR_EL2_PMSIRR_EL1 |
+ HDFGRTR_EL2_PMSIDR_EL1 |
+ HDFGRTR_EL2_PMSICR_EL1 |
+ HDFGRTR_EL2_PMSFCR_EL1 |
+ HDFGRTR_EL2_PMSEVFR_EL1 |
+ HDFGRTR_EL2_PMSCR_EL1 |
+ HDFGRTR_EL2_PMBSR_EL1 |
+ HDFGRTR_EL2_PMBPTR_EL1 |
+ HDFGRTR_EL2_PMBLIMITR_EL1,
+ FEAT_SPE),
+ NEEDS_FEAT(HDFGRTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE),
+ NEEDS_FEAT(HDFGRTR_EL2_nBRBDATA |
+ HDFGRTR_EL2_nBRBCTL |
+ HDFGRTR_EL2_nBRBIDR,
+ FEAT_BRBE),
+ NEEDS_FEAT(HDFGRTR_EL2_TRCVICTLR |
+ HDFGRTR_EL2_TRCSTATR |
+ HDFGRTR_EL2_TRCSSCSRn |
+ HDFGRTR_EL2_TRCSEQSTR |
+ HDFGRTR_EL2_TRCPRGCTLR |
+ HDFGRTR_EL2_TRCOSLSR |
+ HDFGRTR_EL2_TRCIMSPECn |
+ HDFGRTR_EL2_TRCID |
+ HDFGRTR_EL2_TRCCNTVRn |
+ HDFGRTR_EL2_TRCCLAIM |
+ HDFGRTR_EL2_TRCAUXCTLR |
+ HDFGRTR_EL2_TRCAUTHSTATUS |
+ HDFGRTR_EL2_TRC,
+ FEAT_TRC_SR),
+ NEEDS_FEAT(HDFGRTR_EL2_PMCEIDn_EL0 |
+ HDFGRTR_EL2_PMUSERENR_EL0 |
+ HDFGRTR_EL2_PMMIR_EL1 |
+ HDFGRTR_EL2_PMSELR_EL0 |
+ HDFGRTR_EL2_PMOVS |
+ HDFGRTR_EL2_PMINTEN |
+ HDFGRTR_EL2_PMCNTEN |
+ HDFGRTR_EL2_PMCCNTR_EL0 |
+ HDFGRTR_EL2_PMCCFILTR_EL0 |
+ HDFGRTR_EL2_PMEVTYPERn_EL0 |
+ HDFGRTR_EL2_PMEVCNTRn_EL0,
+ FEAT_PMUv3),
+ NEEDS_FEAT(HDFGRTR_EL2_TRBTRG_EL1 |
+ HDFGRTR_EL2_TRBSR_EL1 |
+ HDFGRTR_EL2_TRBPTR_EL1 |
+ HDFGRTR_EL2_TRBMAR_EL1 |
+ HDFGRTR_EL2_TRBLIMITR_EL1 |
+ HDFGRTR_EL2_TRBIDR_EL1 |
+ HDFGRTR_EL2_TRBBASER_EL1,
+ FEAT_TRBE),
+ NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSDLR_EL1, NEVER_FGU,
+ FEAT_DoubleLock),
+ NEEDS_FEAT_FLAG(HDFGRTR_EL2_OSECCR_EL1 |
+ HDFGRTR_EL2_OSLSR_EL1 |
+ HDFGRTR_EL2_DBGPRCR_EL1 |
+ HDFGRTR_EL2_DBGAUTHSTATUS_EL1|
+ HDFGRTR_EL2_DBGCLAIM |
+ HDFGRTR_EL2_MDSCR_EL1 |
+ HDFGRTR_EL2_DBGWVRn_EL1 |
+ HDFGRTR_EL2_DBGWCRn_EL1 |
+ HDFGRTR_EL2_DBGBVRn_EL1 |
+ HDFGRTR_EL2_DBGBCRn_EL1,
+ NEVER_FGU, FEAT_AA64EL1)
+};
+
+static const struct reg_bits_to_feat_map hdfgwtr_feat_map[] = {
+ NEEDS_FEAT(HDFGWTR_EL2_PMSLATFR_EL1 |
+ HDFGWTR_EL2_PMSIRR_EL1 |
+ HDFGWTR_EL2_PMSICR_EL1 |
+ HDFGWTR_EL2_PMSFCR_EL1 |
+ HDFGWTR_EL2_PMSEVFR_EL1 |
+ HDFGWTR_EL2_PMSCR_EL1 |
+ HDFGWTR_EL2_PMBSR_EL1 |
+ HDFGWTR_EL2_PMBPTR_EL1 |
+ HDFGWTR_EL2_PMBLIMITR_EL1,
+ FEAT_SPE),
+ NEEDS_FEAT(HDFGWTR_EL2_nPMSNEVFR_EL1, FEAT_SPE_FnE),
+ NEEDS_FEAT(HDFGWTR_EL2_nBRBDATA |
+ HDFGWTR_EL2_nBRBCTL,
+ FEAT_BRBE),
+ NEEDS_FEAT(HDFGWTR_EL2_TRCVICTLR |
+ HDFGWTR_EL2_TRCSSCSRn |
+ HDFGWTR_EL2_TRCSEQSTR |
+ HDFGWTR_EL2_TRCPRGCTLR |
+ HDFGWTR_EL2_TRCOSLAR |
+ HDFGWTR_EL2_TRCIMSPECn |
+ HDFGWTR_EL2_TRCCNTVRn |
+ HDFGWTR_EL2_TRCCLAIM |
+ HDFGWTR_EL2_TRCAUXCTLR |
+ HDFGWTR_EL2_TRC,
+ FEAT_TRC_SR),
+ NEEDS_FEAT(HDFGWTR_EL2_PMUSERENR_EL0 |
+ HDFGWTR_EL2_PMCR_EL0 |
+ HDFGWTR_EL2_PMSWINC_EL0 |
+ HDFGWTR_EL2_PMSELR_EL0 |
+ HDFGWTR_EL2_PMOVS |
+ HDFGWTR_EL2_PMINTEN |
+ HDFGWTR_EL2_PMCNTEN |
+ HDFGWTR_EL2_PMCCNTR_EL0 |
+ HDFGWTR_EL2_PMCCFILTR_EL0 |
+ HDFGWTR_EL2_PMEVTYPERn_EL0 |
+ HDFGWTR_EL2_PMEVCNTRn_EL0,
+ FEAT_PMUv3),
+ NEEDS_FEAT(HDFGWTR_EL2_TRBTRG_EL1 |
+ HDFGWTR_EL2_TRBSR_EL1 |
+ HDFGWTR_EL2_TRBPTR_EL1 |
+ HDFGWTR_EL2_TRBMAR_EL1 |
+ HDFGWTR_EL2_TRBLIMITR_EL1 |
+ HDFGWTR_EL2_TRBBASER_EL1,
+ FEAT_TRBE),
+ NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSDLR_EL1,
+ NEVER_FGU, FEAT_DoubleLock),
+ NEEDS_FEAT_FLAG(HDFGWTR_EL2_OSECCR_EL1 |
+ HDFGWTR_EL2_OSLAR_EL1 |
+ HDFGWTR_EL2_DBGPRCR_EL1 |
+ HDFGWTR_EL2_DBGCLAIM |
+ HDFGWTR_EL2_MDSCR_EL1 |
+ HDFGWTR_EL2_DBGWVRn_EL1 |
+ HDFGWTR_EL2_DBGWCRn_EL1 |
+ HDFGWTR_EL2_DBGBVRn_EL1 |
+ HDFGWTR_EL2_DBGBCRn_EL1,
+ NEVER_FGU, FEAT_AA64EL1),
+ NEEDS_FEAT(HDFGWTR_EL2_TRFCR_EL1, FEAT_TRF),
+};
+
+
+static const struct reg_bits_to_feat_map hfgitr_feat_map[] = {
+ NEEDS_FEAT(HFGITR_EL2_PSBCSYNC, FEAT_SPEv1p5),
+ NEEDS_FEAT(HFGITR_EL2_ATS1E1A, FEAT_ATS1A),
+ NEEDS_FEAT(HFGITR_EL2_COSPRCTX, FEAT_SPECRES2),
+ NEEDS_FEAT(HFGITR_EL2_nGCSEPP |
+ HFGITR_EL2_nGCSSTR_EL1 |
+ HFGITR_EL2_nGCSPUSHM_EL1,
+ FEAT_GCS),
+ NEEDS_FEAT(HFGITR_EL2_nBRBIALL |
+ HFGITR_EL2_nBRBINJ,
+ FEAT_BRBE),
+ NEEDS_FEAT(HFGITR_EL2_CPPRCTX |
+ HFGITR_EL2_DVPRCTX |
+ HFGITR_EL2_CFPRCTX,
+ FEAT_SPECRES),
+ NEEDS_FEAT(HFGITR_EL2_TLBIRVAALE1 |
+ HFGITR_EL2_TLBIRVALE1 |
+ HFGITR_EL2_TLBIRVAAE1 |
+ HFGITR_EL2_TLBIRVAE1 |
+ HFGITR_EL2_TLBIRVAALE1IS |
+ HFGITR_EL2_TLBIRVALE1IS |
+ HFGITR_EL2_TLBIRVAAE1IS |
+ HFGITR_EL2_TLBIRVAE1IS |
+ HFGITR_EL2_TLBIRVAALE1OS |
+ HFGITR_EL2_TLBIRVALE1OS |
+ HFGITR_EL2_TLBIRVAAE1OS |
+ HFGITR_EL2_TLBIRVAE1OS,
+ FEAT_TLBIRANGE),
+ NEEDS_FEAT(HFGITR_EL2_TLBIVAALE1OS |
+ HFGITR_EL2_TLBIVALE1OS |
+ HFGITR_EL2_TLBIVAAE1OS |
+ HFGITR_EL2_TLBIASIDE1OS |
+ HFGITR_EL2_TLBIVAE1OS |
+ HFGITR_EL2_TLBIVMALLE1OS,
+ FEAT_TLBIOS),
+ NEEDS_FEAT(HFGITR_EL2_ATS1E1WP |
+ HFGITR_EL2_ATS1E1RP,
+ FEAT_PAN2),
+ NEEDS_FEAT(HFGITR_EL2_DCCVADP, FEAT_DPB2),
+ NEEDS_FEAT_FLAG(HFGITR_EL2_DCCVAC |
+ HFGITR_EL2_SVC_EL1 |
+ HFGITR_EL2_SVC_EL0 |
+ HFGITR_EL2_ERET |
+ HFGITR_EL2_TLBIVAALE1 |
+ HFGITR_EL2_TLBIVALE1 |
+ HFGITR_EL2_TLBIVAAE1 |
+ HFGITR_EL2_TLBIASIDE1 |
+ HFGITR_EL2_TLBIVAE1 |
+ HFGITR_EL2_TLBIVMALLE1 |
+ HFGITR_EL2_TLBIVAALE1IS |
+ HFGITR_EL2_TLBIVALE1IS |
+ HFGITR_EL2_TLBIVAAE1IS |
+ HFGITR_EL2_TLBIASIDE1IS |
+ HFGITR_EL2_TLBIVAE1IS |
+ HFGITR_EL2_TLBIVMALLE1IS|
+ HFGITR_EL2_ATS1E0W |
+ HFGITR_EL2_ATS1E0R |
+ HFGITR_EL2_ATS1E1W |
+ HFGITR_EL2_ATS1E1R |
+ HFGITR_EL2_DCZVA |
+ HFGITR_EL2_DCCIVAC |
+ HFGITR_EL2_DCCVAP |
+ HFGITR_EL2_DCCVAU |
+ HFGITR_EL2_DCCISW |
+ HFGITR_EL2_DCCSW |
+ HFGITR_EL2_DCISW |
+ HFGITR_EL2_DCIVAC |
+ HFGITR_EL2_ICIVAU |
+ HFGITR_EL2_ICIALLU |
+ HFGITR_EL2_ICIALLUIS,
+ NEVER_FGU, FEAT_AA64EL1),
+};
+
+static const struct reg_bits_to_feat_map hafgrtr_feat_map[] = {
+ NEEDS_FEAT(HAFGRTR_EL2_AMEVTYPER115_EL0 |
+ HAFGRTR_EL2_AMEVTYPER114_EL0 |
+ HAFGRTR_EL2_AMEVTYPER113_EL0 |
+ HAFGRTR_EL2_AMEVTYPER112_EL0 |
+ HAFGRTR_EL2_AMEVTYPER111_EL0 |
+ HAFGRTR_EL2_AMEVTYPER110_EL0 |
+ HAFGRTR_EL2_AMEVTYPER19_EL0 |
+ HAFGRTR_EL2_AMEVTYPER18_EL0 |
+ HAFGRTR_EL2_AMEVTYPER17_EL0 |
+ HAFGRTR_EL2_AMEVTYPER16_EL0 |
+ HAFGRTR_EL2_AMEVTYPER15_EL0 |
+ HAFGRTR_EL2_AMEVTYPER14_EL0 |
+ HAFGRTR_EL2_AMEVTYPER13_EL0 |
+ HAFGRTR_EL2_AMEVTYPER12_EL0 |
+ HAFGRTR_EL2_AMEVTYPER11_EL0 |
+ HAFGRTR_EL2_AMEVTYPER10_EL0 |
+ HAFGRTR_EL2_AMEVCNTR115_EL0 |
+ HAFGRTR_EL2_AMEVCNTR114_EL0 |
+ HAFGRTR_EL2_AMEVCNTR113_EL0 |
+ HAFGRTR_EL2_AMEVCNTR112_EL0 |
+ HAFGRTR_EL2_AMEVCNTR111_EL0 |
+ HAFGRTR_EL2_AMEVCNTR110_EL0 |
+ HAFGRTR_EL2_AMEVCNTR19_EL0 |
+ HAFGRTR_EL2_AMEVCNTR18_EL0 |
+ HAFGRTR_EL2_AMEVCNTR17_EL0 |
+ HAFGRTR_EL2_AMEVCNTR16_EL0 |
+ HAFGRTR_EL2_AMEVCNTR15_EL0 |
+ HAFGRTR_EL2_AMEVCNTR14_EL0 |
+ HAFGRTR_EL2_AMEVCNTR13_EL0 |
+ HAFGRTR_EL2_AMEVCNTR12_EL0 |
+ HAFGRTR_EL2_AMEVCNTR11_EL0 |
+ HAFGRTR_EL2_AMEVCNTR10_EL0 |
+ HAFGRTR_EL2_AMCNTEN1 |
+ HAFGRTR_EL2_AMCNTEN0 |
+ HAFGRTR_EL2_AMEVCNTR03_EL0 |
+ HAFGRTR_EL2_AMEVCNTR02_EL0 |
+ HAFGRTR_EL2_AMEVCNTR01_EL0 |
+ HAFGRTR_EL2_AMEVCNTR00_EL0,
+ FEAT_AMUv1),
+};
+
+static const struct reg_bits_to_feat_map hfgitr2_feat_map[] = {
+ NEEDS_FEAT(HFGITR2_EL2_nDCCIVAPS, FEAT_PoPS),
+ NEEDS_FEAT(HFGITR2_EL2_TSBCSYNC, FEAT_TRBEv1p1)
+};
+
+static const struct reg_bits_to_feat_map hfgrtr2_feat_map[] = {
+ NEEDS_FEAT(HFGRTR2_EL2_nPFAR_EL1, FEAT_PFAR),
+ NEEDS_FEAT(HFGRTR2_EL2_nERXGSR_EL1, FEAT_RASv2),
+ NEEDS_FEAT(HFGRTR2_EL2_nACTLRALIAS_EL1 |
+ HFGRTR2_EL2_nACTLRMASK_EL1 |
+ HFGRTR2_EL2_nCPACRALIAS_EL1 |
+ HFGRTR2_EL2_nCPACRMASK_EL1 |
+ HFGRTR2_EL2_nSCTLR2MASK_EL1 |
+ HFGRTR2_EL2_nSCTLRALIAS2_EL1 |
+ HFGRTR2_EL2_nSCTLRALIAS_EL1 |
+ HFGRTR2_EL2_nSCTLRMASK_EL1 |
+ HFGRTR2_EL2_nTCR2ALIAS_EL1 |
+ HFGRTR2_EL2_nTCR2MASK_EL1 |
+ HFGRTR2_EL2_nTCRALIAS_EL1 |
+ HFGRTR2_EL2_nTCRMASK_EL1,
+ FEAT_SRMASK),
+ NEEDS_FEAT(HFGRTR2_EL2_nRCWSMASK_EL1, FEAT_THE),
+};
+
+static const struct reg_bits_to_feat_map hfgwtr2_feat_map[] = {
+ NEEDS_FEAT(HFGWTR2_EL2_nPFAR_EL1, FEAT_PFAR),
+ NEEDS_FEAT(HFGWTR2_EL2_nACTLRALIAS_EL1 |
+ HFGWTR2_EL2_nACTLRMASK_EL1 |
+ HFGWTR2_EL2_nCPACRALIAS_EL1 |
+ HFGWTR2_EL2_nCPACRMASK_EL1 |
+ HFGWTR2_EL2_nSCTLR2MASK_EL1 |
+ HFGWTR2_EL2_nSCTLRALIAS2_EL1 |
+ HFGWTR2_EL2_nSCTLRALIAS_EL1 |
+ HFGWTR2_EL2_nSCTLRMASK_EL1 |
+ HFGWTR2_EL2_nTCR2ALIAS_EL1 |
+ HFGWTR2_EL2_nTCR2MASK_EL1 |
+ HFGWTR2_EL2_nTCRALIAS_EL1 |
+ HFGWTR2_EL2_nTCRMASK_EL1,
+ FEAT_SRMASK),
+ NEEDS_FEAT(HFGWTR2_EL2_nRCWSMASK_EL1, FEAT_THE),
+};
+
+static const struct reg_bits_to_feat_map hdfgrtr2_feat_map[] = {
+ NEEDS_FEAT(HDFGRTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss),
+ NEEDS_FEAT(HDFGRTR2_EL2_nTRCITECR_EL1, FEAT_ITE),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMICFILTR_EL0 |
+ HDFGRTR2_EL2_nPMICNTR_EL0,
+ FEAT_PMUv3_ICNTR),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMUACR_EL1, FEAT_PMUv3p9),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMSSCR_EL1 |
+ HDFGRTR2_EL2_nPMSSDATA,
+ FEAT_PMUv3_SS),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMIAR_EL1, FEAT_SEBEP),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMSDSFR_EL1, feat_spe_fds),
+ NEEDS_FEAT(HDFGRTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM),
+ NEEDS_FEAT(HDFGRTR2_EL2_nSPMACCESSR_EL1 |
+ HDFGRTR2_EL2_nSPMCNTEN |
+ HDFGRTR2_EL2_nSPMCR_EL0 |
+ HDFGRTR2_EL2_nSPMDEVAFF_EL1 |
+ HDFGRTR2_EL2_nSPMEVCNTRn_EL0 |
+ HDFGRTR2_EL2_nSPMEVTYPERn_EL0|
+ HDFGRTR2_EL2_nSPMID |
+ HDFGRTR2_EL2_nSPMINTEN |
+ HDFGRTR2_EL2_nSPMOVS |
+ HDFGRTR2_EL2_nSPMSCR_EL1 |
+ HDFGRTR2_EL2_nSPMSELR_EL0,
+ FEAT_SPMU),
+ NEEDS_FEAT(HDFGRTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2),
+ NEEDS_FEAT(HDFGRTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam),
+};
+
+static const struct reg_bits_to_feat_map hdfgwtr2_feat_map[] = {
+ NEEDS_FEAT(HDFGWTR2_EL2_nMDSELR_EL1, FEAT_Debugv8p9),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMECR_EL1, feat_ebep_pmuv3_ss),
+ NEEDS_FEAT(HDFGWTR2_EL2_nTRCITECR_EL1, FEAT_ITE),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMICFILTR_EL0 |
+ HDFGWTR2_EL2_nPMICNTR_EL0,
+ FEAT_PMUv3_ICNTR),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMUACR_EL1 |
+ HDFGWTR2_EL2_nPMZR_EL0,
+ FEAT_PMUv3p9),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMSSCR_EL1, FEAT_PMUv3_SS),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMIAR_EL1, FEAT_SEBEP),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMSDSFR_EL1, feat_spe_fds),
+ NEEDS_FEAT(HDFGWTR2_EL2_nPMBMAR_EL1, FEAT_SPE_nVM),
+ NEEDS_FEAT(HDFGWTR2_EL2_nSPMACCESSR_EL1 |
+ HDFGWTR2_EL2_nSPMCNTEN |
+ HDFGWTR2_EL2_nSPMCR_EL0 |
+ HDFGWTR2_EL2_nSPMEVCNTRn_EL0 |
+ HDFGWTR2_EL2_nSPMEVTYPERn_EL0|
+ HDFGWTR2_EL2_nSPMINTEN |
+ HDFGWTR2_EL2_nSPMOVS |
+ HDFGWTR2_EL2_nSPMSCR_EL1 |
+ HDFGWTR2_EL2_nSPMSELR_EL0,
+ FEAT_SPMU),
+ NEEDS_FEAT(HDFGWTR2_EL2_nMDSTEPOP_EL1, FEAT_STEP2),
+ NEEDS_FEAT(HDFGWTR2_EL2_nTRBMPAM_EL1, feat_trbe_mpam),
+};
+
+static const struct reg_bits_to_feat_map hcrx_feat_map[] = {
+ NEEDS_FEAT(HCRX_EL2_PACMEn, feat_pauth_lr),
+ NEEDS_FEAT(HCRX_EL2_EnFPM, FEAT_FPMR),
+ NEEDS_FEAT(HCRX_EL2_GCSEn, FEAT_GCS),
+ NEEDS_FEAT(HCRX_EL2_EnIDCP128, FEAT_SYSREG128),
+ NEEDS_FEAT(HCRX_EL2_EnSDERR, feat_aderr),
+ NEEDS_FEAT(HCRX_EL2_TMEA, FEAT_DoubleFault2),
+ NEEDS_FEAT(HCRX_EL2_EnSNERR, feat_anerr),
+ NEEDS_FEAT(HCRX_EL2_D128En, FEAT_D128),
+ NEEDS_FEAT(HCRX_EL2_PTTWI, FEAT_THE),
+ NEEDS_FEAT(HCRX_EL2_SCTLR2En, FEAT_SCTLR2),
+ NEEDS_FEAT(HCRX_EL2_TCR2En, FEAT_TCR2),
+ NEEDS_FEAT(HCRX_EL2_MSCEn |
+ HCRX_EL2_MCE2,
+ FEAT_MOPS),
+ NEEDS_FEAT(HCRX_EL2_CMOW, FEAT_CMOW),
+ NEEDS_FEAT(HCRX_EL2_VFNMI |
+ HCRX_EL2_VINMI |
+ HCRX_EL2_TALLINT,
+ FEAT_NMI),
+ NEEDS_FEAT(HCRX_EL2_SMPME, feat_sme_smps),
+ NEEDS_FEAT(HCRX_EL2_FGTnXS |
+ HCRX_EL2_FnXS,
+ FEAT_XS),
+ NEEDS_FEAT(HCRX_EL2_EnASR, FEAT_LS64_V),
+ NEEDS_FEAT(HCRX_EL2_EnALS, FEAT_LS64),
+ NEEDS_FEAT(HCRX_EL2_EnAS0, FEAT_LS64_ACCDATA),
+};
+
+static const struct reg_bits_to_feat_map hcr_feat_map[] = {
+ NEEDS_FEAT(HCR_EL2_TID0, FEAT_AA32EL0),
+ NEEDS_FEAT_FIXED(HCR_EL2_RW, compute_hcr_rw),
+ NEEDS_FEAT(HCR_EL2_HCD, not_feat_aa64el3),
+ NEEDS_FEAT(HCR_EL2_AMO |
+ HCR_EL2_BSU |
+ HCR_EL2_CD |
+ HCR_EL2_DC |
+ HCR_EL2_FB |
+ HCR_EL2_FMO |
+ HCR_EL2_ID |
+ HCR_EL2_IMO |
+ HCR_EL2_MIOCNCE |
+ HCR_EL2_PTW |
+ HCR_EL2_SWIO |
+ HCR_EL2_TACR |
+ HCR_EL2_TDZ |
+ HCR_EL2_TGE |
+ HCR_EL2_TID1 |
+ HCR_EL2_TID2 |
+ HCR_EL2_TID3 |
+ HCR_EL2_TIDCP |
+ HCR_EL2_TPCP |
+ HCR_EL2_TPU |
+ HCR_EL2_TRVM |
+ HCR_EL2_TSC |
+ HCR_EL2_TSW |
+ HCR_EL2_TTLB |
+ HCR_EL2_TVM |
+ HCR_EL2_TWE |
+ HCR_EL2_TWI |
+ HCR_EL2_VF |
+ HCR_EL2_VI |
+ HCR_EL2_VM |
+ HCR_EL2_VSE,
+ FEAT_AA64EL1),
+ NEEDS_FEAT(HCR_EL2_AMVOFFEN, FEAT_AMUv1p1),
+ NEEDS_FEAT(HCR_EL2_EnSCXT, feat_csv2_2_csv2_1p2),
+ NEEDS_FEAT(HCR_EL2_TICAB |
+ HCR_EL2_TID4 |
+ HCR_EL2_TOCU,
+ FEAT_EVT),
+ NEEDS_FEAT(HCR_EL2_TTLBIS |
+ HCR_EL2_TTLBOS,
+ FEAT_EVT_TTLBxS),
+ NEEDS_FEAT(HCR_EL2_TLOR, FEAT_LOR),
+ NEEDS_FEAT(HCR_EL2_ATA |
+ HCR_EL2_DCT |
+ HCR_EL2_TID5,
+ FEAT_MTE2),
+ NEEDS_FEAT(HCR_EL2_AT | /* Ignore the original FEAT_NV */
+ HCR_EL2_NV2 |
+ HCR_EL2_NV,
+ feat_nv2),
+ NEEDS_FEAT(HCR_EL2_NV1, feat_nv2_e2h0_ni), /* Missing from JSON */
+ NEEDS_FEAT(HCR_EL2_API |
+ HCR_EL2_APK,
+ feat_pauth),
+ NEEDS_FEAT(HCR_EL2_TEA |
+ HCR_EL2_TERR,
+ FEAT_RAS),
+ NEEDS_FEAT(HCR_EL2_FIEN, feat_rasv1p1),
+ NEEDS_FEAT(HCR_EL2_GPF, FEAT_RME),
+ NEEDS_FEAT(HCR_EL2_FWB, FEAT_S2FWB),
+ NEEDS_FEAT(HCR_EL2_TME, FEAT_TME),
+ NEEDS_FEAT(HCR_EL2_TWEDEL |
+ HCR_EL2_TWEDEn,
+ FEAT_TWED),
+ NEEDS_FEAT_FIXED(HCR_EL2_E2H, compute_hcr_e2h),
+};
+
+static void __init check_feat_map(const struct reg_bits_to_feat_map *map,
+ int map_size, u64 res0, const char *str)
+{
+ u64 mask = 0;
+
+ for (int i = 0; i < map_size; i++)
+ mask |= map[i].bits;
+
+ if (mask != ~res0)
+ kvm_err("Undefined %s behaviour, bits %016llx\n",
+ str, mask ^ ~res0);
+}
+
+void __init check_feature_map(void)
+{
+ check_feat_map(hfgrtr_feat_map, ARRAY_SIZE(hfgrtr_feat_map),
+ hfgrtr_masks.res0, hfgrtr_masks.str);
+ check_feat_map(hfgwtr_feat_map, ARRAY_SIZE(hfgwtr_feat_map),
+ hfgwtr_masks.res0, hfgwtr_masks.str);
+ check_feat_map(hfgitr_feat_map, ARRAY_SIZE(hfgitr_feat_map),
+ hfgitr_masks.res0, hfgitr_masks.str);
+ check_feat_map(hdfgrtr_feat_map, ARRAY_SIZE(hdfgrtr_feat_map),
+ hdfgrtr_masks.res0, hdfgrtr_masks.str);
+ check_feat_map(hdfgwtr_feat_map, ARRAY_SIZE(hdfgwtr_feat_map),
+ hdfgwtr_masks.res0, hdfgwtr_masks.str);
+ check_feat_map(hafgrtr_feat_map, ARRAY_SIZE(hafgrtr_feat_map),
+ hafgrtr_masks.res0, hafgrtr_masks.str);
+ check_feat_map(hcrx_feat_map, ARRAY_SIZE(hcrx_feat_map),
+ __HCRX_EL2_RES0, "HCRX_EL2");
+ check_feat_map(hcr_feat_map, ARRAY_SIZE(hcr_feat_map),
+ HCR_EL2_RES0, "HCR_EL2");
+}
+
+static bool idreg_feat_match(struct kvm *kvm, const struct reg_bits_to_feat_map *map)
+{
+ u64 regval = kvm->arch.id_regs[map->regidx];
+ u64 regfld = (regval >> map->shift) & GENMASK(map->width - 1, 0);
+
+ if (map->sign) {
+ s64 sfld = sign_extend64(regfld, map->width - 1);
+ s64 slim = sign_extend64(map->lo_lim, map->width - 1);
+ return sfld >= slim;
+ } else {
+ return regfld >= map->lo_lim;
+ }
+}
+
+static u64 __compute_fixed_bits(struct kvm *kvm,
+ const struct reg_bits_to_feat_map *map,
+ int map_size,
+ u64 *fixed_bits,
+ unsigned long require,
+ unsigned long exclude)
+{
+ u64 val = 0;
+
+ for (int i = 0; i < map_size; i++) {
+ bool match;
+
+ if ((map[i].flags & require) != require)
+ continue;
+
+ if (map[i].flags & exclude)
+ continue;
+
+ if (map[i].flags & CALL_FUNC)
+ match = (map[i].flags & FIXED_VALUE) ?
+ map[i].fval(kvm, fixed_bits) :
+ map[i].match(kvm);
+ else
+ match = idreg_feat_match(kvm, &map[i]);
+
+ if (!match || (map[i].flags & FIXED_VALUE))
+ val |= map[i].bits;
+ }
+
+ return val;
+}
+
+static u64 compute_res0_bits(struct kvm *kvm,
+ const struct reg_bits_to_feat_map *map,
+ int map_size,
+ unsigned long require,
+ unsigned long exclude)
+{
+ return __compute_fixed_bits(kvm, map, map_size, NULL,
+ require, exclude | FIXED_VALUE);
+}
+
+static u64 compute_fixed_bits(struct kvm *kvm,
+ const struct reg_bits_to_feat_map *map,
+ int map_size,
+ u64 *fixed_bits,
+ unsigned long require,
+ unsigned long exclude)
+{
+ return __compute_fixed_bits(kvm, map, map_size, fixed_bits,
+ require | FIXED_VALUE, exclude);
+}
+
+void compute_fgu(struct kvm *kvm, enum fgt_group_id fgt)
+{
+ u64 val = 0;
+
+ switch (fgt) {
+ case HFGRTR_GROUP:
+ val |= compute_res0_bits(kvm, hfgrtr_feat_map,
+ ARRAY_SIZE(hfgrtr_feat_map),
+ 0, NEVER_FGU);
+ val |= compute_res0_bits(kvm, hfgwtr_feat_map,
+ ARRAY_SIZE(hfgwtr_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HFGITR_GROUP:
+ val |= compute_res0_bits(kvm, hfgitr_feat_map,
+ ARRAY_SIZE(hfgitr_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HDFGRTR_GROUP:
+ val |= compute_res0_bits(kvm, hdfgrtr_feat_map,
+ ARRAY_SIZE(hdfgrtr_feat_map),
+ 0, NEVER_FGU);
+ val |= compute_res0_bits(kvm, hdfgwtr_feat_map,
+ ARRAY_SIZE(hdfgwtr_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HAFGRTR_GROUP:
+ val |= compute_res0_bits(kvm, hafgrtr_feat_map,
+ ARRAY_SIZE(hafgrtr_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HFGRTR2_GROUP:
+ val |= compute_res0_bits(kvm, hfgrtr2_feat_map,
+ ARRAY_SIZE(hfgrtr2_feat_map),
+ 0, NEVER_FGU);
+ val |= compute_res0_bits(kvm, hfgwtr2_feat_map,
+ ARRAY_SIZE(hfgwtr2_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HFGITR2_GROUP:
+ val |= compute_res0_bits(kvm, hfgitr2_feat_map,
+ ARRAY_SIZE(hfgitr2_feat_map),
+ 0, NEVER_FGU);
+ break;
+ case HDFGRTR2_GROUP:
+ val |= compute_res0_bits(kvm, hdfgrtr2_feat_map,
+ ARRAY_SIZE(hdfgrtr2_feat_map),
+ 0, NEVER_FGU);
+ val |= compute_res0_bits(kvm, hdfgwtr2_feat_map,
+ ARRAY_SIZE(hdfgwtr2_feat_map),
+ 0, NEVER_FGU);
+ break;
+ default:
+ BUG();
+ }
+
+ kvm->arch.fgu[fgt] = val;
+}
+
+void get_reg_fixed_bits(struct kvm *kvm, enum vcpu_sysreg reg, u64 *res0, u64 *res1)
+{
+ u64 fixed = 0, mask;
+
+ switch (reg) {
+ case HFGRTR_EL2:
+ *res0 = compute_res0_bits(kvm, hfgrtr_feat_map,
+ ARRAY_SIZE(hfgrtr_feat_map), 0, 0);
+ *res0 |= hfgrtr_masks.res0;
+ *res1 = HFGRTR_EL2_RES1;
+ break;
+ case HFGWTR_EL2:
+ *res0 = compute_res0_bits(kvm, hfgwtr_feat_map,
+ ARRAY_SIZE(hfgwtr_feat_map), 0, 0);
+ *res0 |= hfgwtr_masks.res0;
+ *res1 = HFGWTR_EL2_RES1;
+ break;
+ case HFGITR_EL2:
+ *res0 = compute_res0_bits(kvm, hfgitr_feat_map,
+ ARRAY_SIZE(hfgitr_feat_map), 0, 0);
+ *res0 |= hfgitr_masks.res0;
+ *res1 = HFGITR_EL2_RES1;
+ break;
+ case HDFGRTR_EL2:
+ *res0 = compute_res0_bits(kvm, hdfgrtr_feat_map,
+ ARRAY_SIZE(hdfgrtr_feat_map), 0, 0);
+ *res0 |= hdfgrtr_masks.res0;
+ *res1 = HDFGRTR_EL2_RES1;
+ break;
+ case HDFGWTR_EL2:
+ *res0 = compute_res0_bits(kvm, hdfgwtr_feat_map,
+ ARRAY_SIZE(hdfgwtr_feat_map), 0, 0);
+ *res0 |= hdfgwtr_masks.res0;
+ *res1 = HDFGWTR_EL2_RES1;
+ break;
+ case HAFGRTR_EL2:
+ *res0 = compute_res0_bits(kvm, hafgrtr_feat_map,
+ ARRAY_SIZE(hafgrtr_feat_map), 0, 0);
+ *res0 |= hafgrtr_masks.res0;
+ *res1 = HAFGRTR_EL2_RES1;
+ break;
+ case HFGRTR2_EL2:
+ *res0 = compute_res0_bits(kvm, hfgrtr2_feat_map,
+ ARRAY_SIZE(hfgrtr2_feat_map), 0, 0);
+ *res0 |= hfgrtr2_masks.res0;
+ *res1 = HFGRTR2_EL2_RES1;
+ break;
+ case HFGWTR2_EL2:
+ *res0 = compute_res0_bits(kvm, hfgwtr2_feat_map,
+ ARRAY_SIZE(hfgwtr2_feat_map), 0, 0);
+ *res0 |= hfgwtr2_masks.res0;
+ *res1 = HFGWTR2_EL2_RES1;
+ break;
+ case HFGITR2_EL2:
+ *res0 = compute_res0_bits(kvm, hfgitr2_feat_map,
+ ARRAY_SIZE(hfgitr2_feat_map), 0, 0);
+ *res0 |= hfgitr2_masks.res0;
+ *res1 = HFGITR2_EL2_RES1;
+ break;
+ case HDFGRTR2_EL2:
+ *res0 = compute_res0_bits(kvm, hdfgrtr2_feat_map,
+ ARRAY_SIZE(hdfgrtr2_feat_map), 0, 0);
+ *res0 |= hdfgrtr2_masks.res0;
+ *res1 = HDFGRTR2_EL2_RES1;
+ break;
+ case HDFGWTR2_EL2:
+ *res0 = compute_res0_bits(kvm, hdfgwtr2_feat_map,
+ ARRAY_SIZE(hdfgwtr2_feat_map), 0, 0);
+ *res0 |= hdfgwtr2_masks.res0;
+ *res1 = HDFGWTR2_EL2_RES1;
+ break;
+ case HCRX_EL2:
+ *res0 = compute_res0_bits(kvm, hcrx_feat_map,
+ ARRAY_SIZE(hcrx_feat_map), 0, 0);
+ *res0 |= __HCRX_EL2_RES0;
+ *res1 = __HCRX_EL2_RES1;
+ break;
+ case HCR_EL2:
+ mask = compute_fixed_bits(kvm, hcr_feat_map,
+ ARRAY_SIZE(hcr_feat_map), &fixed,
+ 0, 0);
+ *res0 = compute_res0_bits(kvm, hcr_feat_map,
+ ARRAY_SIZE(hcr_feat_map), 0, 0);
+ *res0 |= HCR_EL2_RES0 | (mask & ~fixed);
+ *res1 = HCR_EL2_RES1 | (mask & fixed);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ *res0 = *res1 = 0;
+ break;
+ }
+}
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 0fcfcc0478f9..3a384e9660b8 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -622,6 +622,11 @@ struct encoding_to_trap_config {
const unsigned int line;
};
+/*
+ * WARNING: using ranges is a treacherous endeavour, as sysregs that
+ * are part of an architectural range are not necessarily contiguous
+ * in the [Op0,Op1,CRn,CRm,Ops] space. Tread carefully.
+ */
#define SR_RANGE_TRAP(sr_start, sr_end, trap_id) \
{ \
.encoding = sr_start, \
@@ -1279,98 +1284,128 @@ enum fg_filter_id {
__NR_FG_FILTER_IDS__
};
-#define SR_FGF(sr, g, b, p, f) \
- { \
- .encoding = sr, \
- .end = sr, \
- .tc = { \
+#define __FGT(g, b, p, f) \
+ { \
.fgt = g ## _GROUP, \
.bit = g ## _EL2_ ## b ## _SHIFT, \
.pol = p, \
.fgf = f, \
- }, \
+ }
+
+#define FGT(g, b, p) __FGT(g, b, p, __NO_FGF__)
+
+/*
+ * See the warning next to SR_RANGE_TRAP(), and apply the same
+ * level of caution.
+ */
+#define SR_FGF_RANGE(sr, e, g, b, p, f) \
+ { \
+ .encoding = sr, \
+ .end = e, \
+ .tc = __FGT(g, b, p, f), \
.line = __LINE__, \
}
-#define SR_FGT(sr, g, b, p) SR_FGF(sr, g, b, p, __NO_FGF__)
+#define SR_FGF(sr, g, b, p, f) SR_FGF_RANGE(sr, sr, g, b, p, f)
+#define SR_FGT(sr, g, b, p) SR_FGF_RANGE(sr, sr, g, b, p, __NO_FGF__)
+#define SR_FGT_RANGE(sr, end, g, b, p) \
+ SR_FGF_RANGE(sr, end, g, b, p, __NO_FGF__)
static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
/* HFGRTR_EL2, HFGWTR_EL2 */
- SR_FGT(SYS_AMAIR2_EL1, HFGxTR, nAMAIR2_EL1, 0),
- SR_FGT(SYS_MAIR2_EL1, HFGxTR, nMAIR2_EL1, 0),
- SR_FGT(SYS_S2POR_EL1, HFGxTR, nS2POR_EL1, 0),
- SR_FGT(SYS_POR_EL1, HFGxTR, nPOR_EL1, 0),
- SR_FGT(SYS_POR_EL0, HFGxTR, nPOR_EL0, 0),
- SR_FGT(SYS_PIR_EL1, HFGxTR, nPIR_EL1, 0),
- SR_FGT(SYS_PIRE0_EL1, HFGxTR, nPIRE0_EL1, 0),
- SR_FGT(SYS_RCWMASK_EL1, HFGxTR, nRCWMASK_EL1, 0),
- SR_FGT(SYS_TPIDR2_EL0, HFGxTR, nTPIDR2_EL0, 0),
- SR_FGT(SYS_SMPRI_EL1, HFGxTR, nSMPRI_EL1, 0),
- SR_FGT(SYS_GCSCR_EL1, HFGxTR, nGCS_EL1, 0),
- SR_FGT(SYS_GCSPR_EL1, HFGxTR, nGCS_EL1, 0),
- SR_FGT(SYS_GCSCRE0_EL1, HFGxTR, nGCS_EL0, 0),
- SR_FGT(SYS_GCSPR_EL0, HFGxTR, nGCS_EL0, 0),
- SR_FGT(SYS_ACCDATA_EL1, HFGxTR, nACCDATA_EL1, 0),
- SR_FGT(SYS_ERXADDR_EL1, HFGxTR, ERXADDR_EL1, 1),
- SR_FGT(SYS_ERXPFGCDN_EL1, HFGxTR, ERXPFGCDN_EL1, 1),
- SR_FGT(SYS_ERXPFGCTL_EL1, HFGxTR, ERXPFGCTL_EL1, 1),
- SR_FGT(SYS_ERXPFGF_EL1, HFGxTR, ERXPFGF_EL1, 1),
- SR_FGT(SYS_ERXMISC0_EL1, HFGxTR, ERXMISCn_EL1, 1),
- SR_FGT(SYS_ERXMISC1_EL1, HFGxTR, ERXMISCn_EL1, 1),
- SR_FGT(SYS_ERXMISC2_EL1, HFGxTR, ERXMISCn_EL1, 1),
- SR_FGT(SYS_ERXMISC3_EL1, HFGxTR, ERXMISCn_EL1, 1),
- SR_FGT(SYS_ERXSTATUS_EL1, HFGxTR, ERXSTATUS_EL1, 1),
- SR_FGT(SYS_ERXCTLR_EL1, HFGxTR, ERXCTLR_EL1, 1),
- SR_FGT(SYS_ERXFR_EL1, HFGxTR, ERXFR_EL1, 1),
- SR_FGT(SYS_ERRSELR_EL1, HFGxTR, ERRSELR_EL1, 1),
- SR_FGT(SYS_ERRIDR_EL1, HFGxTR, ERRIDR_EL1, 1),
- SR_FGT(SYS_ICC_IGRPEN0_EL1, HFGxTR, ICC_IGRPENn_EL1, 1),
- SR_FGT(SYS_ICC_IGRPEN1_EL1, HFGxTR, ICC_IGRPENn_EL1, 1),
- SR_FGT(SYS_VBAR_EL1, HFGxTR, VBAR_EL1, 1),
- SR_FGT(SYS_TTBR1_EL1, HFGxTR, TTBR1_EL1, 1),
- SR_FGT(SYS_TTBR0_EL1, HFGxTR, TTBR0_EL1, 1),
- SR_FGT(SYS_TPIDR_EL0, HFGxTR, TPIDR_EL0, 1),
- SR_FGT(SYS_TPIDRRO_EL0, HFGxTR, TPIDRRO_EL0, 1),
- SR_FGT(SYS_TPIDR_EL1, HFGxTR, TPIDR_EL1, 1),
- SR_FGT(SYS_TCR_EL1, HFGxTR, TCR_EL1, 1),
- SR_FGT(SYS_TCR2_EL1, HFGxTR, TCR_EL1, 1),
- SR_FGT(SYS_SCXTNUM_EL0, HFGxTR, SCXTNUM_EL0, 1),
- SR_FGT(SYS_SCXTNUM_EL1, HFGxTR, SCXTNUM_EL1, 1),
- SR_FGT(SYS_SCTLR_EL1, HFGxTR, SCTLR_EL1, 1),
- SR_FGT(SYS_REVIDR_EL1, HFGxTR, REVIDR_EL1, 1),
- SR_FGT(SYS_PAR_EL1, HFGxTR, PAR_EL1, 1),
- SR_FGT(SYS_MPIDR_EL1, HFGxTR, MPIDR_EL1, 1),
- SR_FGT(SYS_MIDR_EL1, HFGxTR, MIDR_EL1, 1),
- SR_FGT(SYS_MAIR_EL1, HFGxTR, MAIR_EL1, 1),
- SR_FGT(SYS_LORSA_EL1, HFGxTR, LORSA_EL1, 1),
- SR_FGT(SYS_LORN_EL1, HFGxTR, LORN_EL1, 1),
- SR_FGT(SYS_LORID_EL1, HFGxTR, LORID_EL1, 1),
- SR_FGT(SYS_LOREA_EL1, HFGxTR, LOREA_EL1, 1),
- SR_FGT(SYS_LORC_EL1, HFGxTR, LORC_EL1, 1),
- SR_FGT(SYS_ISR_EL1, HFGxTR, ISR_EL1, 1),
- SR_FGT(SYS_FAR_EL1, HFGxTR, FAR_EL1, 1),
- SR_FGT(SYS_ESR_EL1, HFGxTR, ESR_EL1, 1),
- SR_FGT(SYS_DCZID_EL0, HFGxTR, DCZID_EL0, 1),
- SR_FGT(SYS_CTR_EL0, HFGxTR, CTR_EL0, 1),
- SR_FGT(SYS_CSSELR_EL1, HFGxTR, CSSELR_EL1, 1),
- SR_FGT(SYS_CPACR_EL1, HFGxTR, CPACR_EL1, 1),
- SR_FGT(SYS_CONTEXTIDR_EL1, HFGxTR, CONTEXTIDR_EL1, 1),
- SR_FGT(SYS_CLIDR_EL1, HFGxTR, CLIDR_EL1, 1),
- SR_FGT(SYS_CCSIDR_EL1, HFGxTR, CCSIDR_EL1, 1),
- SR_FGT(SYS_APIBKEYLO_EL1, HFGxTR, APIBKey, 1),
- SR_FGT(SYS_APIBKEYHI_EL1, HFGxTR, APIBKey, 1),
- SR_FGT(SYS_APIAKEYLO_EL1, HFGxTR, APIAKey, 1),
- SR_FGT(SYS_APIAKEYHI_EL1, HFGxTR, APIAKey, 1),
- SR_FGT(SYS_APGAKEYLO_EL1, HFGxTR, APGAKey, 1),
- SR_FGT(SYS_APGAKEYHI_EL1, HFGxTR, APGAKey, 1),
- SR_FGT(SYS_APDBKEYLO_EL1, HFGxTR, APDBKey, 1),
- SR_FGT(SYS_APDBKEYHI_EL1, HFGxTR, APDBKey, 1),
- SR_FGT(SYS_APDAKEYLO_EL1, HFGxTR, APDAKey, 1),
- SR_FGT(SYS_APDAKEYHI_EL1, HFGxTR, APDAKey, 1),
- SR_FGT(SYS_AMAIR_EL1, HFGxTR, AMAIR_EL1, 1),
- SR_FGT(SYS_AIDR_EL1, HFGxTR, AIDR_EL1, 1),
- SR_FGT(SYS_AFSR1_EL1, HFGxTR, AFSR1_EL1, 1),
- SR_FGT(SYS_AFSR0_EL1, HFGxTR, AFSR0_EL1, 1),
+ SR_FGT(SYS_AMAIR2_EL1, HFGRTR, nAMAIR2_EL1, 0),
+ SR_FGT(SYS_MAIR2_EL1, HFGRTR, nMAIR2_EL1, 0),
+ SR_FGT(SYS_S2POR_EL1, HFGRTR, nS2POR_EL1, 0),
+ SR_FGT(SYS_POR_EL1, HFGRTR, nPOR_EL1, 0),
+ SR_FGT(SYS_POR_EL0, HFGRTR, nPOR_EL0, 0),
+ SR_FGT(SYS_PIR_EL1, HFGRTR, nPIR_EL1, 0),
+ SR_FGT(SYS_PIRE0_EL1, HFGRTR, nPIRE0_EL1, 0),
+ SR_FGT(SYS_RCWMASK_EL1, HFGRTR, nRCWMASK_EL1, 0),
+ SR_FGT(SYS_TPIDR2_EL0, HFGRTR, nTPIDR2_EL0, 0),
+ SR_FGT(SYS_SMPRI_EL1, HFGRTR, nSMPRI_EL1, 0),
+ SR_FGT(SYS_GCSCR_EL1, HFGRTR, nGCS_EL1, 0),
+ SR_FGT(SYS_GCSPR_EL1, HFGRTR, nGCS_EL1, 0),
+ SR_FGT(SYS_GCSCRE0_EL1, HFGRTR, nGCS_EL0, 0),
+ SR_FGT(SYS_GCSPR_EL0, HFGRTR, nGCS_EL0, 0),
+ SR_FGT(SYS_ACCDATA_EL1, HFGRTR, nACCDATA_EL1, 0),
+ SR_FGT(SYS_ERXADDR_EL1, HFGRTR, ERXADDR_EL1, 1),
+ SR_FGT(SYS_ERXPFGCDN_EL1, HFGRTR, ERXPFGCDN_EL1, 1),
+ SR_FGT(SYS_ERXPFGCTL_EL1, HFGRTR, ERXPFGCTL_EL1, 1),
+ SR_FGT(SYS_ERXPFGF_EL1, HFGRTR, ERXPFGF_EL1, 1),
+ SR_FGT(SYS_ERXMISC0_EL1, HFGRTR, ERXMISCn_EL1, 1),
+ SR_FGT(SYS_ERXMISC1_EL1, HFGRTR, ERXMISCn_EL1, 1),
+ SR_FGT(SYS_ERXMISC2_EL1, HFGRTR, ERXMISCn_EL1, 1),
+ SR_FGT(SYS_ERXMISC3_EL1, HFGRTR, ERXMISCn_EL1, 1),
+ SR_FGT(SYS_ERXSTATUS_EL1, HFGRTR, ERXSTATUS_EL1, 1),
+ SR_FGT(SYS_ERXCTLR_EL1, HFGRTR, ERXCTLR_EL1, 1),
+ SR_FGT(SYS_ERXFR_EL1, HFGRTR, ERXFR_EL1, 1),
+ SR_FGT(SYS_ERRSELR_EL1, HFGRTR, ERRSELR_EL1, 1),
+ SR_FGT(SYS_ERRIDR_EL1, HFGRTR, ERRIDR_EL1, 1),
+ SR_FGT(SYS_ICC_IGRPEN0_EL1, HFGRTR, ICC_IGRPENn_EL1, 1),
+ SR_FGT(SYS_ICC_IGRPEN1_EL1, HFGRTR, ICC_IGRPENn_EL1, 1),
+ SR_FGT(SYS_VBAR_EL1, HFGRTR, VBAR_EL1, 1),
+ SR_FGT(SYS_TTBR1_EL1, HFGRTR, TTBR1_EL1, 1),
+ SR_FGT(SYS_TTBR0_EL1, HFGRTR, TTBR0_EL1, 1),
+ SR_FGT(SYS_TPIDR_EL0, HFGRTR, TPIDR_EL0, 1),
+ SR_FGT(SYS_TPIDRRO_EL0, HFGRTR, TPIDRRO_EL0, 1),
+ SR_FGT(SYS_TPIDR_EL1, HFGRTR, TPIDR_EL1, 1),
+ SR_FGT(SYS_TCR_EL1, HFGRTR, TCR_EL1, 1),
+ SR_FGT(SYS_TCR2_EL1, HFGRTR, TCR_EL1, 1),
+ SR_FGT(SYS_SCXTNUM_EL0, HFGRTR, SCXTNUM_EL0, 1),
+ SR_FGT(SYS_SCXTNUM_EL1, HFGRTR, SCXTNUM_EL1, 1),
+ SR_FGT(SYS_SCTLR_EL1, HFGRTR, SCTLR_EL1, 1),
+ SR_FGT(SYS_REVIDR_EL1, HFGRTR, REVIDR_EL1, 1),
+ SR_FGT(SYS_PAR_EL1, HFGRTR, PAR_EL1, 1),
+ SR_FGT(SYS_MPIDR_EL1, HFGRTR, MPIDR_EL1, 1),
+ SR_FGT(SYS_MIDR_EL1, HFGRTR, MIDR_EL1, 1),
+ SR_FGT(SYS_MAIR_EL1, HFGRTR, MAIR_EL1, 1),
+ SR_FGT(SYS_LORSA_EL1, HFGRTR, LORSA_EL1, 1),
+ SR_FGT(SYS_LORN_EL1, HFGRTR, LORN_EL1, 1),
+ SR_FGT(SYS_LORID_EL1, HFGRTR, LORID_EL1, 1),
+ SR_FGT(SYS_LOREA_EL1, HFGRTR, LOREA_EL1, 1),
+ SR_FGT(SYS_LORC_EL1, HFGRTR, LORC_EL1, 1),
+ SR_FGT(SYS_ISR_EL1, HFGRTR, ISR_EL1, 1),
+ SR_FGT(SYS_FAR_EL1, HFGRTR, FAR_EL1, 1),
+ SR_FGT(SYS_ESR_EL1, HFGRTR, ESR_EL1, 1),
+ SR_FGT(SYS_DCZID_EL0, HFGRTR, DCZID_EL0, 1),
+ SR_FGT(SYS_CTR_EL0, HFGRTR, CTR_EL0, 1),
+ SR_FGT(SYS_CSSELR_EL1, HFGRTR, CSSELR_EL1, 1),
+ SR_FGT(SYS_CPACR_EL1, HFGRTR, CPACR_EL1, 1),
+ SR_FGT(SYS_CONTEXTIDR_EL1, HFGRTR, CONTEXTIDR_EL1, 1),
+ SR_FGT(SYS_CLIDR_EL1, HFGRTR, CLIDR_EL1, 1),
+ SR_FGT(SYS_CCSIDR_EL1, HFGRTR, CCSIDR_EL1, 1),
+ SR_FGT(SYS_APIBKEYLO_EL1, HFGRTR, APIBKey, 1),
+ SR_FGT(SYS_APIBKEYHI_EL1, HFGRTR, APIBKey, 1),
+ SR_FGT(SYS_APIAKEYLO_EL1, HFGRTR, APIAKey, 1),
+ SR_FGT(SYS_APIAKEYHI_EL1, HFGRTR, APIAKey, 1),
+ SR_FGT(SYS_APGAKEYLO_EL1, HFGRTR, APGAKey, 1),
+ SR_FGT(SYS_APGAKEYHI_EL1, HFGRTR, APGAKey, 1),
+ SR_FGT(SYS_APDBKEYLO_EL1, HFGRTR, APDBKey, 1),
+ SR_FGT(SYS_APDBKEYHI_EL1, HFGRTR, APDBKey, 1),
+ SR_FGT(SYS_APDAKEYLO_EL1, HFGRTR, APDAKey, 1),
+ SR_FGT(SYS_APDAKEYHI_EL1, HFGRTR, APDAKey, 1),
+ SR_FGT(SYS_AMAIR_EL1, HFGRTR, AMAIR_EL1, 1),
+ SR_FGT(SYS_AIDR_EL1, HFGRTR, AIDR_EL1, 1),
+ SR_FGT(SYS_AFSR1_EL1, HFGRTR, AFSR1_EL1, 1),
+ SR_FGT(SYS_AFSR0_EL1, HFGRTR, AFSR0_EL1, 1),
+
+ /* HFGRTR2_EL2, HFGWTR2_EL2 */
+ SR_FGT(SYS_ACTLRALIAS_EL1, HFGRTR2, nACTLRALIAS_EL1, 0),
+ SR_FGT(SYS_ACTLRMASK_EL1, HFGRTR2, nACTLRMASK_EL1, 0),
+ SR_FGT(SYS_CPACRALIAS_EL1, HFGRTR2, nCPACRALIAS_EL1, 0),
+ SR_FGT(SYS_CPACRMASK_EL1, HFGRTR2, nCPACRMASK_EL1, 0),
+ SR_FGT(SYS_PFAR_EL1, HFGRTR2, nPFAR_EL1, 0),
+ SR_FGT(SYS_RCWSMASK_EL1, HFGRTR2, nRCWSMASK_EL1, 0),
+ SR_FGT(SYS_SCTLR2ALIAS_EL1, HFGRTR2, nSCTLRALIAS2_EL1, 0),
+ SR_FGT(SYS_SCTLR2MASK_EL1, HFGRTR2, nSCTLR2MASK_EL1, 0),
+ SR_FGT(SYS_SCTLRALIAS_EL1, HFGRTR2, nSCTLRALIAS_EL1, 0),
+ SR_FGT(SYS_SCTLRMASK_EL1, HFGRTR2, nSCTLRMASK_EL1, 0),
+ SR_FGT(SYS_TCR2ALIAS_EL1, HFGRTR2, nTCR2ALIAS_EL1, 0),
+ SR_FGT(SYS_TCR2MASK_EL1, HFGRTR2, nTCR2MASK_EL1, 0),
+ SR_FGT(SYS_TCRALIAS_EL1, HFGRTR2, nTCRALIAS_EL1, 0),
+ SR_FGT(SYS_TCRMASK_EL1, HFGRTR2, nTCRMASK_EL1, 0),
+ SR_FGT(SYS_ERXGSR_EL1, HFGRTR2, nERXGSR_EL1, 0),
+
/* HFGITR_EL2 */
SR_FGT(OP_AT_S1E1A, HFGITR, ATS1E1A, 1),
SR_FGT(OP_COSP_RCTX, HFGITR, COSPRCTX, 1),
@@ -1480,6 +1515,11 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
SR_FGT(SYS_IC_IVAU, HFGITR, ICIVAU, 1),
SR_FGT(SYS_IC_IALLU, HFGITR, ICIALLU, 1),
SR_FGT(SYS_IC_IALLUIS, HFGITR, ICIALLUIS, 1),
+
+ /* HFGITR2_EL2 */
+ SR_FGT(SYS_DC_CIGDVAPS, HFGITR2, nDCCIVAPS, 0),
+ SR_FGT(SYS_DC_CIVAPS, HFGITR2, nDCCIVAPS, 0),
+
/* HDFGRTR_EL2 */
SR_FGT(SYS_PMBIDR_EL1, HDFGRTR, PMBIDR_EL1, 1),
SR_FGT(SYS_PMSNEVFR_EL1, HDFGRTR, nPMSNEVFR_EL1, 0),
@@ -1789,68 +1829,12 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
SR_FGT(SYS_PMCNTENSET_EL0, HDFGRTR, PMCNTEN, 1),
SR_FGT(SYS_PMCCNTR_EL0, HDFGRTR, PMCCNTR_EL0, 1),
SR_FGT(SYS_PMCCFILTR_EL0, HDFGRTR, PMCCFILTR_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(0), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(1), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(2), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(3), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(4), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(5), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(6), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(7), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(8), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(9), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(10), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(11), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(12), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(13), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(14), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(15), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(16), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(17), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(18), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(19), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(20), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(21), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(22), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(23), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(24), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(25), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(26), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(27), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(28), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(29), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVTYPERn_EL0(30), HDFGRTR, PMEVTYPERn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(0), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(1), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(2), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(3), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(4), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(5), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(6), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(7), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(8), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(9), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(10), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(11), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(12), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(13), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(14), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(15), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(16), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(17), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(18), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(19), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(20), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(21), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(22), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(23), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(24), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(25), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(26), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(27), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(28), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(29), HDFGRTR, PMEVCNTRn_EL0, 1),
- SR_FGT(SYS_PMEVCNTRn_EL0(30), HDFGRTR, PMEVCNTRn_EL0, 1),
+ SR_FGT_RANGE(SYS_PMEVTYPERn_EL0(0),
+ SYS_PMEVTYPERn_EL0(30),
+ HDFGRTR, PMEVTYPERn_EL0, 1),
+ SR_FGT_RANGE(SYS_PMEVCNTRn_EL0(0),
+ SYS_PMEVCNTRn_EL0(30),
+ HDFGRTR, PMEVCNTRn_EL0, 1),
SR_FGT(SYS_OSDLR_EL1, HDFGRTR, OSDLR_EL1, 1),
SR_FGT(SYS_OSECCR_EL1, HDFGRTR, OSECCR_EL1, 1),
SR_FGT(SYS_OSLSR_EL1, HDFGRTR, OSLSR_EL1, 1),
@@ -1928,6 +1912,59 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
SR_FGT(SYS_DBGBCRn_EL1(13), HDFGRTR, DBGBCRn_EL1, 1),
SR_FGT(SYS_DBGBCRn_EL1(14), HDFGRTR, DBGBCRn_EL1, 1),
SR_FGT(SYS_DBGBCRn_EL1(15), HDFGRTR, DBGBCRn_EL1, 1),
+
+ /* HDFGRTR2_EL2 */
+ SR_FGT(SYS_MDSELR_EL1, HDFGRTR2, nMDSELR_EL1, 0),
+ SR_FGT(SYS_MDSTEPOP_EL1, HDFGRTR2, nMDSTEPOP_EL1, 0),
+ SR_FGT(SYS_PMCCNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0),
+ SR_FGT_RANGE(SYS_PMEVCNTSVRn_EL1(0),
+ SYS_PMEVCNTSVRn_EL1(30),
+ HDFGRTR2, nPMSSDATA, 0),
+ SR_FGT(SYS_PMICNTSVR_EL1, HDFGRTR2, nPMSSDATA, 0),
+ SR_FGT(SYS_PMECR_EL1, HDFGRTR2, nPMECR_EL1, 0),
+ SR_FGT(SYS_PMIAR_EL1, HDFGRTR2, nPMIAR_EL1, 0),
+ SR_FGT(SYS_PMICFILTR_EL0, HDFGRTR2, nPMICFILTR_EL0, 0),
+ SR_FGT(SYS_PMICNTR_EL0, HDFGRTR2, nPMICNTR_EL0, 0),
+ SR_FGT(SYS_PMSSCR_EL1, HDFGRTR2, nPMSSCR_EL1, 0),
+ SR_FGT(SYS_PMUACR_EL1, HDFGRTR2, nPMUACR_EL1, 0),
+ SR_FGT(SYS_SPMACCESSR_EL1, HDFGRTR2, nSPMACCESSR_EL1, 0),
+ SR_FGT(SYS_SPMCFGR_EL1, HDFGRTR2, nSPMID, 0),
+ SR_FGT(SYS_SPMDEVARCH_EL1, HDFGRTR2, nSPMID, 0),
+ SR_FGT(SYS_SPMCGCRn_EL1(0), HDFGRTR2, nSPMID, 0),
+ SR_FGT(SYS_SPMCGCRn_EL1(1), HDFGRTR2, nSPMID, 0),
+ SR_FGT(SYS_SPMIIDR_EL1, HDFGRTR2, nSPMID, 0),
+ SR_FGT(SYS_SPMCNTENCLR_EL0, HDFGRTR2, nSPMCNTEN, 0),
+ SR_FGT(SYS_SPMCNTENSET_EL0, HDFGRTR2, nSPMCNTEN, 0),
+ SR_FGT(SYS_SPMCR_EL0, HDFGRTR2, nSPMCR_EL0, 0),
+ SR_FGT(SYS_SPMDEVAFF_EL1, HDFGRTR2, nSPMDEVAFF_EL1, 0),
+ /*
+ * We have up to 64 of these registers in ranges of 16, banked via
+ * SPMSELR_EL0.BANK. We're only concerned with the accessors here,
+ * not the architectural registers.
+ */
+ SR_FGT_RANGE(SYS_SPMEVCNTRn_EL0(0),
+ SYS_SPMEVCNTRn_EL0(15),
+ HDFGRTR2, nSPMEVCNTRn_EL0, 0),
+ SR_FGT_RANGE(SYS_SPMEVFILT2Rn_EL0(0),
+ SYS_SPMEVFILT2Rn_EL0(15),
+ HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+ SR_FGT_RANGE(SYS_SPMEVFILTRn_EL0(0),
+ SYS_SPMEVFILTRn_EL0(15),
+ HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+ SR_FGT_RANGE(SYS_SPMEVTYPERn_EL0(0),
+ SYS_SPMEVTYPERn_EL0(15),
+ HDFGRTR2, nSPMEVTYPERn_EL0, 0),
+ SR_FGT(SYS_SPMINTENCLR_EL1, HDFGRTR2, nSPMINTEN, 0),
+ SR_FGT(SYS_SPMINTENSET_EL1, HDFGRTR2, nSPMINTEN, 0),
+ SR_FGT(SYS_SPMOVSCLR_EL0, HDFGRTR2, nSPMOVS, 0),
+ SR_FGT(SYS_SPMOVSSET_EL0, HDFGRTR2, nSPMOVS, 0),
+ SR_FGT(SYS_SPMSCR_EL1, HDFGRTR2, nSPMSCR_EL1, 0),
+ SR_FGT(SYS_SPMSELR_EL0, HDFGRTR2, nSPMSELR_EL0, 0),
+ SR_FGT(SYS_TRCITECR_EL1, HDFGRTR2, nTRCITECR_EL1, 0),
+ SR_FGT(SYS_PMBMAR_EL1, HDFGRTR2, nPMBMAR_EL1, 0),
+ SR_FGT(SYS_PMSDSFR_EL1, HDFGRTR2, nPMSDSFR_EL1, 0),
+ SR_FGT(SYS_TRBMPAM_EL1, HDFGRTR2, nTRBMPAM_EL1, 0),
+
/*
* HDFGWTR_EL2
*
@@ -1938,12 +1975,19 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
* read-side mappings, and only the write-side mappings that
* differ from the read side, and the trap handler will pick
* the correct shadow register based on the access type.
+ *
+ * Same model applies to the FEAT_FGT2 registers.
*/
SR_FGT(SYS_TRFCR_EL1, HDFGWTR, TRFCR_EL1, 1),
SR_FGT(SYS_TRCOSLAR, HDFGWTR, TRCOSLAR, 1),
SR_FGT(SYS_PMCR_EL0, HDFGWTR, PMCR_EL0, 1),
SR_FGT(SYS_PMSWINC_EL0, HDFGWTR, PMSWINC_EL0, 1),
SR_FGT(SYS_OSLAR_EL1, HDFGWTR, OSLAR_EL1, 1),
+
+ /* HDFGWTR2_EL2 */
+ SR_FGT(SYS_PMZR_EL0, HDFGWTR2, nPMZR_EL0, 0),
+ SR_FGT(SYS_SPMZR_EL0, HDFGWTR2, nSPMEVCNTRn_EL0, 0),
+
/*
* HAFGRTR_EL2
*/
@@ -1989,6 +2033,20 @@ static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
SR_FGT(SYS_AMEVCNTR0_EL0(0), HAFGRTR, AMEVCNTR00_EL0, 1),
};
+/*
+ * Additional FGTs that do not fire with ESR_EL2.EC==0x18. This table
+ * isn't used for exception routing, but only as a promise that the
+ * trap is handled somewhere else.
+ */
+static const union trap_config non_0x18_fgt[] __initconst = {
+ FGT(HFGITR, PSBCSYNC, 1),
+ FGT(HFGITR, nGCSSTR_EL1, 0),
+ FGT(HFGITR, SVC_EL1, 1),
+ FGT(HFGITR, SVC_EL0, 1),
+ FGT(HFGITR, ERET, 1),
+ FGT(HFGITR2, TSBCSYNC, 1),
+};
+
static union trap_config get_trap_config(u32 sysreg)
{
return (union trap_config) {
@@ -2033,6 +2091,130 @@ static u32 encoding_next(u32 encoding)
return sys_reg(op0 + 1, 0, 0, 0, 0);
}
+#define FGT_MASKS(__n, __m) \
+ struct fgt_masks __n = { .str = #__m, .res0 = __m, }
+
+FGT_MASKS(hfgrtr_masks, HFGRTR_EL2_RES0);
+FGT_MASKS(hfgwtr_masks, HFGWTR_EL2_RES0);
+FGT_MASKS(hfgitr_masks, HFGITR_EL2_RES0);
+FGT_MASKS(hdfgrtr_masks, HDFGRTR_EL2_RES0);
+FGT_MASKS(hdfgwtr_masks, HDFGWTR_EL2_RES0);
+FGT_MASKS(hafgrtr_masks, HAFGRTR_EL2_RES0);
+FGT_MASKS(hfgrtr2_masks, HFGRTR2_EL2_RES0);
+FGT_MASKS(hfgwtr2_masks, HFGWTR2_EL2_RES0);
+FGT_MASKS(hfgitr2_masks, HFGITR2_EL2_RES0);
+FGT_MASKS(hdfgrtr2_masks, HDFGRTR2_EL2_RES0);
+FGT_MASKS(hdfgwtr2_masks, HDFGWTR2_EL2_RES0);
+
+static __init bool aggregate_fgt(union trap_config tc)
+{
+ struct fgt_masks *rmasks, *wmasks;
+
+ switch (tc.fgt) {
+ case HFGRTR_GROUP:
+ rmasks = &hfgrtr_masks;
+ wmasks = &hfgwtr_masks;
+ break;
+ case HDFGRTR_GROUP:
+ rmasks = &hdfgrtr_masks;
+ wmasks = &hdfgwtr_masks;
+ break;
+ case HAFGRTR_GROUP:
+ rmasks = &hafgrtr_masks;
+ wmasks = NULL;
+ break;
+ case HFGITR_GROUP:
+ rmasks = &hfgitr_masks;
+ wmasks = NULL;
+ break;
+ case HFGRTR2_GROUP:
+ rmasks = &hfgrtr2_masks;
+ wmasks = &hfgwtr2_masks;
+ break;
+ case HDFGRTR2_GROUP:
+ rmasks = &hdfgrtr2_masks;
+ wmasks = &hdfgwtr2_masks;
+ break;
+ case HFGITR2_GROUP:
+ rmasks = &hfgitr2_masks;
+ wmasks = NULL;
+ break;
+ }
+
+ /*
+ * A bit can be reserved in either the R or W register, but
+ * not both.
+ */
+ if ((BIT(tc.bit) & rmasks->res0) &&
+ (!wmasks || (BIT(tc.bit) & wmasks->res0)))
+ return false;
+
+ if (tc.pol)
+ rmasks->mask |= BIT(tc.bit) & ~rmasks->res0;
+ else
+ rmasks->nmask |= BIT(tc.bit) & ~rmasks->res0;
+
+ if (wmasks) {
+ if (tc.pol)
+ wmasks->mask |= BIT(tc.bit) & ~wmasks->res0;
+ else
+ wmasks->nmask |= BIT(tc.bit) & ~wmasks->res0;
+ }
+
+ return true;
+}
+
+static __init int check_fgt_masks(struct fgt_masks *masks)
+{
+ unsigned long duplicate = masks->mask & masks->nmask;
+ u64 res0 = masks->res0;
+ int ret = 0;
+
+ if (duplicate) {
+ int i;
+
+ for_each_set_bit(i, &duplicate, 64) {
+ kvm_err("%s[%d] bit has both polarities\n",
+ masks->str, i);
+ }
+
+ ret = -EINVAL;
+ }
+
+ masks->res0 = ~(masks->mask | masks->nmask);
+ if (masks->res0 != res0)
+ kvm_info("Implicit %s = %016llx, expecting %016llx\n",
+ masks->str, masks->res0, res0);
+
+ return ret;
+}
+
+static __init int check_all_fgt_masks(int ret)
+{
+ static struct fgt_masks * const masks[] __initconst = {
+ &hfgrtr_masks,
+ &hfgwtr_masks,
+ &hfgitr_masks,
+ &hdfgrtr_masks,
+ &hdfgwtr_masks,
+ &hafgrtr_masks,
+ &hfgrtr2_masks,
+ &hfgwtr2_masks,
+ &hfgitr2_masks,
+ &hdfgrtr2_masks,
+ &hdfgwtr2_masks,
+ };
+ int err = 0;
+
+ for (int i = 0; i < ARRAY_SIZE(masks); i++)
+ err |= check_fgt_masks(masks[i]);
+
+ return ret ?: err;
+}
+
+#define for_each_encoding_in(__x, __s, __e) \
+ for (u32 __x = __s; __x <= __e; __x = encoding_next(__x))
+
int __init populate_nv_trap_config(void)
{
int ret = 0;
@@ -2041,6 +2223,7 @@ int __init populate_nv_trap_config(void)
BUILD_BUG_ON(__NR_CGT_GROUP_IDS__ > BIT(TC_CGT_BITS));
BUILD_BUG_ON(__NR_FGT_GROUP_IDS__ > BIT(TC_FGT_BITS));
BUILD_BUG_ON(__NR_FG_FILTER_IDS__ > BIT(TC_FGF_BITS));
+ BUILD_BUG_ON(__HCRX_EL2_MASK & __HCRX_EL2_nMASK);
for (int i = 0; i < ARRAY_SIZE(encoding_to_cgt); i++) {
const struct encoding_to_trap_config *cgt = &encoding_to_cgt[i];
@@ -2051,7 +2234,7 @@ int __init populate_nv_trap_config(void)
ret = -EINVAL;
}
- for (u32 enc = cgt->encoding; enc <= cgt->end; enc = encoding_next(enc)) {
+ for_each_encoding_in(enc, cgt->encoding, cgt->end) {
prev = xa_store(&sr_forward_xa, enc,
xa_mk_value(cgt->tc.val), GFP_KERNEL);
if (prev && !xa_is_err(prev)) {
@@ -2066,6 +2249,10 @@ int __init populate_nv_trap_config(void)
}
}
+ if (__HCRX_EL2_RES0 != HCRX_EL2_RES0)
+ kvm_info("Sanitised HCR_EL2_RES0 = %016llx, expecting %016llx\n",
+ __HCRX_EL2_RES0, HCRX_EL2_RES0);
+
kvm_info("nv: %ld coarse grained trap handlers\n",
ARRAY_SIZE(encoding_to_cgt));
@@ -2082,23 +2269,39 @@ int __init populate_nv_trap_config(void)
print_nv_trap_error(fgt, "Invalid FGT", ret);
}
- tc = get_trap_config(fgt->encoding);
+ for_each_encoding_in(enc, fgt->encoding, fgt->end) {
+ tc = get_trap_config(enc);
- if (tc.fgt) {
- ret = -EINVAL;
- print_nv_trap_error(fgt, "Duplicate FGT", ret);
- }
+ if (tc.fgt) {
+ ret = -EINVAL;
+ print_nv_trap_error(fgt, "Duplicate FGT", ret);
+ }
+
+ tc.val |= fgt->tc.val;
+ prev = xa_store(&sr_forward_xa, enc,
+ xa_mk_value(tc.val), GFP_KERNEL);
+
+ if (xa_is_err(prev)) {
+ ret = xa_err(prev);
+ print_nv_trap_error(fgt, "Failed FGT insertion", ret);
+ }
- tc.val |= fgt->tc.val;
- prev = xa_store(&sr_forward_xa, fgt->encoding,
- xa_mk_value(tc.val), GFP_KERNEL);
+ if (!aggregate_fgt(tc)) {
+ ret = -EINVAL;
+ print_nv_trap_error(fgt, "FGT bit is reserved", ret);
+ }
+ }
+ }
- if (xa_is_err(prev)) {
- ret = xa_err(prev);
- print_nv_trap_error(fgt, "Failed FGT insertion", ret);
+ for (int i = 0; i < ARRAY_SIZE(non_0x18_fgt); i++) {
+ if (!aggregate_fgt(non_0x18_fgt[i])) {
+ ret = -EINVAL;
+ kvm_err("non_0x18_fgt[%d] is reserved\n", i);
}
}
+ ret = check_all_fgt_masks(ret);
+
kvm_info("nv: %ld fine grained trap handlers\n",
ARRAY_SIZE(encoding_to_fgt));
@@ -2215,11 +2418,11 @@ static u64 kvm_get_sysreg_res0(struct kvm *kvm, enum vcpu_sysreg sr)
return masks->mask[sr - __VNCR_START__].res0;
}
-static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
- u64 val, const union trap_config tc)
+static bool check_fgt_bit(struct kvm_vcpu *vcpu, enum vcpu_sysreg sr,
+ const union trap_config tc)
{
struct kvm *kvm = vcpu->kvm;
- enum vcpu_sysreg sr;
+ u64 val;
/*
* KVM doesn't know about any FGTs that apply to the host, and hopefully
@@ -2228,6 +2431,8 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
if (is_hyp_ctxt(vcpu))
return false;
+ val = __vcpu_sys_reg(vcpu, sr);
+
if (tc.pol)
return (val & BIT(tc.bit));
@@ -2242,38 +2447,17 @@ static bool check_fgt_bit(struct kvm_vcpu *vcpu, bool is_read,
if (val & BIT(tc.bit))
return false;
- switch ((enum fgt_group_id)tc.fgt) {
- case HFGxTR_GROUP:
- sr = is_read ? HFGRTR_EL2 : HFGWTR_EL2;
- break;
-
- case HDFGRTR_GROUP:
- sr = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2;
- break;
-
- case HAFGRTR_GROUP:
- sr = HAFGRTR_EL2;
- break;
-
- case HFGITR_GROUP:
- sr = HFGITR_EL2;
- break;
-
- default:
- WARN_ONCE(1, "Unhandled FGT group");
- return false;
- }
-
return !(kvm_get_sysreg_res0(kvm, sr) & BIT(tc.bit));
}
bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
{
+ enum vcpu_sysreg fgtreg;
union trap_config tc;
enum trap_behaviour b;
bool is_read;
u32 sysreg;
- u64 esr, val;
+ u64 esr;
esr = kvm_vcpu_get_esr(vcpu);
sysreg = esr_sys64_to_sysreg(esr);
@@ -2319,26 +2503,20 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
case __NO_FGT_GROUP__:
break;
- case HFGxTR_GROUP:
- if (is_read)
- val = __vcpu_sys_reg(vcpu, HFGRTR_EL2);
- else
- val = __vcpu_sys_reg(vcpu, HFGWTR_EL2);
+ case HFGRTR_GROUP:
+ fgtreg = is_read ? HFGRTR_EL2 : HFGWTR_EL2;
break;
case HDFGRTR_GROUP:
- if (is_read)
- val = __vcpu_sys_reg(vcpu, HDFGRTR_EL2);
- else
- val = __vcpu_sys_reg(vcpu, HDFGWTR_EL2);
+ fgtreg = is_read ? HDFGRTR_EL2 : HDFGWTR_EL2;
break;
case HAFGRTR_GROUP:
- val = __vcpu_sys_reg(vcpu, HAFGRTR_EL2);
+ fgtreg = HAFGRTR_EL2;
break;
case HFGITR_GROUP:
- val = __vcpu_sys_reg(vcpu, HFGITR_EL2);
+ fgtreg = HFGITR_EL2;
switch (tc.fgf) {
u64 tmp;
@@ -2352,13 +2530,26 @@ bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index)
}
break;
- case __NR_FGT_GROUP_IDS__:
+ case HFGRTR2_GROUP:
+ fgtreg = is_read ? HFGRTR2_EL2 : HFGWTR2_EL2;
+ break;
+
+ case HDFGRTR2_GROUP:
+ fgtreg = is_read ? HDFGRTR2_EL2 : HDFGWTR2_EL2;
+ break;
+
+ case HFGITR2_GROUP:
+ fgtreg = HFGITR2_EL2;
+ break;
+
+ default:
/* Something is really wrong, bail out */
- WARN_ONCE(1, "__NR_FGT_GROUP_IDS__");
+ WARN_ONCE(1, "Bad FGT group (encoding %08x, config %016llx)\n",
+ sysreg, tc.val);
goto local;
}
- if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, is_read, val, tc))
+ if (tc.fgt != __NO_FGT_GROUP__ && check_fgt_bit(vcpu, fgtreg, tc))
goto inject;
b = compute_trap_behaviour(vcpu, tc);
@@ -2471,13 +2662,6 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu)
{
u64 spsr, elr, esr;
- /*
- * Forward this trap to the virtual EL2 if the virtual
- * HCR_EL2.NV bit is set and this is coming from !EL2.
- */
- if (forward_hcr_traps(vcpu, HCR_NV))
- return;
-
spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2);
spsr = kvm_check_illegal_exception_return(vcpu, spsr);
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index b73dc26bc44b..453266c96481 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -10,6 +10,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <linux/ubsan.h>
#include <asm/esr.h>
#include <asm/exception.h>
@@ -298,6 +299,81 @@ static int handle_svc(struct kvm_vcpu *vcpu)
return 1;
}
+static int kvm_handle_gcs(struct kvm_vcpu *vcpu)
+{
+ /* We don't expect GCS, so treat it with contempt */
+ if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, GCS, IMP))
+ WARN_ON_ONCE(1);
+
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
+static int handle_other(struct kvm_vcpu *vcpu)
+{
+ bool is_l2 = vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu);
+ u64 hcrx = __vcpu_sys_reg(vcpu, HCRX_EL2);
+ u64 esr = kvm_vcpu_get_esr(vcpu);
+ u64 iss = ESR_ELx_ISS(esr);
+ struct kvm *kvm = vcpu->kvm;
+ bool allowed, fwd = false;
+
+ /*
+ * We only trap for two reasons:
+ *
+ * - the feature is disabled, and the only outcome is to
+ * generate an UNDEF.
+ *
+ * - the feature is enabled, but a NV guest wants to trap the
+ * feature used by its L2 guest. We forward the exception in
+ * this case.
+ *
+ * What we don't expect is to end-up here if the guest is
+ * expected be be able to directly use the feature, hence the
+ * WARN_ON below.
+ */
+ switch (iss) {
+ case ESR_ELx_ISS_OTHER_ST64BV:
+ allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V);
+ if (is_l2)
+ fwd = !(hcrx & HCRX_EL2_EnASR);
+ break;
+ case ESR_ELx_ISS_OTHER_ST64BV0:
+ allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA);
+ if (is_l2)
+ fwd = !(hcrx & HCRX_EL2_EnAS0);
+ break;
+ case ESR_ELx_ISS_OTHER_LDST64B:
+ allowed = kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64);
+ if (is_l2)
+ fwd = !(hcrx & HCRX_EL2_EnALS);
+ break;
+ case ESR_ELx_ISS_OTHER_TSBCSYNC:
+ allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, TRBE_V1P1);
+ if (is_l2)
+ fwd = (__vcpu_sys_reg(vcpu, HFGITR2_EL2) & HFGITR2_EL2_TSBCSYNC);
+ break;
+ case ESR_ELx_ISS_OTHER_PSBCSYNC:
+ allowed = kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P5);
+ if (is_l2)
+ fwd = (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_PSBCSYNC);
+ break;
+ default:
+ /* Clearly, we're missing something. */
+ WARN_ON_ONCE(1);
+ allowed = false;
+ }
+
+ WARN_ON_ONCE(allowed && !fwd);
+
+ if (allowed && fwd)
+ kvm_inject_nested_sync(vcpu, esr);
+ else
+ kvm_inject_undefined(vcpu);
+
+ return 1;
+}
+
static exit_handle_fn arm_exit_handlers[] = {
[0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec,
[ESR_ELx_EC_WFx] = kvm_handle_wfx,
@@ -307,6 +383,7 @@ static exit_handle_fn arm_exit_handlers[] = {
[ESR_ELx_EC_CP14_LS] = kvm_handle_cp14_load_store,
[ESR_ELx_EC_CP10_ID] = kvm_handle_cp10_id,
[ESR_ELx_EC_CP14_64] = kvm_handle_cp14_64,
+ [ESR_ELx_EC_OTHER] = handle_other,
[ESR_ELx_EC_HVC32] = handle_hvc,
[ESR_ELx_EC_SMC32] = handle_smc,
[ESR_ELx_EC_HVC64] = handle_hvc,
@@ -317,6 +394,7 @@ static exit_handle_fn arm_exit_handlers[] = {
[ESR_ELx_EC_ERET] = kvm_handle_eret,
[ESR_ELx_EC_IABT_LOW] = kvm_handle_guest_abort,
[ESR_ELx_EC_DABT_LOW] = kvm_handle_guest_abort,
+ [ESR_ELx_EC_DABT_CUR] = kvm_handle_vncr_abort,
[ESR_ELx_EC_SOFTSTP_LOW]= kvm_handle_guest_debug,
[ESR_ELx_EC_WATCHPT_LOW]= kvm_handle_guest_debug,
[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
@@ -324,6 +402,7 @@ static exit_handle_fn arm_exit_handlers[] = {
[ESR_ELx_EC_BRK64] = kvm_handle_guest_debug,
[ESR_ELx_EC_FP_ASIMD] = kvm_handle_fpasimd,
[ESR_ELx_EC_PAC] = kvm_handle_ptrauth,
+ [ESR_ELx_EC_GCS] = kvm_handle_gcs,
};
static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
@@ -474,6 +553,11 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
print_nvhe_hyp_panic("BUG", panic_addr);
} else if (IS_ENABLED(CONFIG_CFI_CLANG) && esr_is_cfi_brk(esr)) {
kvm_nvhe_report_cfi_failure(panic_addr);
+ } else if (IS_ENABLED(CONFIG_UBSAN_KVM_EL2) &&
+ ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
+ esr_is_ubsan_brk(esr)) {
+ print_nvhe_hyp_panic(report_ubsan_failure(esr & UBSAN_BRK_MASK),
+ panic_addr);
} else {
print_nvhe_hyp_panic("panic", panic_addr);
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 96f625dc7256..bb9f2eecfb67 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -65,12 +65,56 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
}
}
+#define reg_to_fgt_masks(reg) \
+ ({ \
+ struct fgt_masks *m; \
+ switch(reg) { \
+ case HFGRTR_EL2: \
+ m = &hfgrtr_masks; \
+ break; \
+ case HFGWTR_EL2: \
+ m = &hfgwtr_masks; \
+ break; \
+ case HFGITR_EL2: \
+ m = &hfgitr_masks; \
+ break; \
+ case HDFGRTR_EL2: \
+ m = &hdfgrtr_masks; \
+ break; \
+ case HDFGWTR_EL2: \
+ m = &hdfgwtr_masks; \
+ break; \
+ case HAFGRTR_EL2: \
+ m = &hafgrtr_masks; \
+ break; \
+ case HFGRTR2_EL2: \
+ m = &hfgrtr2_masks; \
+ break; \
+ case HFGWTR2_EL2: \
+ m = &hfgwtr2_masks; \
+ break; \
+ case HFGITR2_EL2: \
+ m = &hfgitr2_masks; \
+ break; \
+ case HDFGRTR2_EL2: \
+ m = &hdfgrtr2_masks; \
+ break; \
+ case HDFGWTR2_EL2: \
+ m = &hdfgwtr2_masks; \
+ break; \
+ default: \
+ BUILD_BUG_ON(1); \
+ } \
+ \
+ m; \
+ })
+
#define compute_clr_set(vcpu, reg, clr, set) \
do { \
- u64 hfg; \
- hfg = __vcpu_sys_reg(vcpu, reg) & ~__ ## reg ## _RES0; \
- set |= hfg & __ ## reg ## _MASK; \
- clr |= ~hfg & __ ## reg ## _nMASK; \
+ u64 hfg = __vcpu_sys_reg(vcpu, reg); \
+ struct fgt_masks *m = reg_to_fgt_masks(reg); \
+ set |= hfg & m->mask; \
+ clr |= ~hfg & m->nmask; \
} while(0)
#define reg_to_fgt_group_id(reg) \
@@ -79,7 +123,7 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
switch(reg) { \
case HFGRTR_EL2: \
case HFGWTR_EL2: \
- id = HFGxTR_GROUP; \
+ id = HFGRTR_GROUP; \
break; \
case HFGITR_EL2: \
id = HFGITR_GROUP; \
@@ -91,6 +135,17 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
case HAFGRTR_EL2: \
id = HAFGRTR_GROUP; \
break; \
+ case HFGRTR2_EL2: \
+ case HFGWTR2_EL2: \
+ id = HFGRTR2_GROUP; \
+ break; \
+ case HFGITR2_EL2: \
+ id = HFGITR2_GROUP; \
+ break; \
+ case HDFGRTR2_EL2: \
+ case HDFGWTR2_EL2: \
+ id = HDFGRTR2_GROUP; \
+ break; \
default: \
BUILD_BUG_ON(1); \
} \
@@ -101,13 +156,16 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
#define compute_undef_clr_set(vcpu, kvm, reg, clr, set) \
do { \
u64 hfg = kvm->arch.fgu[reg_to_fgt_group_id(reg)]; \
- set |= hfg & __ ## reg ## _MASK; \
- clr |= hfg & __ ## reg ## _nMASK; \
+ struct fgt_masks *m = reg_to_fgt_masks(reg); \
+ set |= hfg & m->mask; \
+ clr |= hfg & m->nmask; \
} while(0)
#define update_fgt_traps_cs(hctxt, vcpu, kvm, reg, clr, set) \
do { \
- u64 c = 0, s = 0; \
+ struct fgt_masks *m = reg_to_fgt_masks(reg); \
+ u64 c = clr, s = set; \
+ u64 val; \
\
ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg); \
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) \
@@ -115,30 +173,15 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
\
compute_undef_clr_set(vcpu, kvm, reg, c, s); \
\
- s |= set; \
- c |= clr; \
- if (c || s) { \
- u64 val = __ ## reg ## _nMASK; \
- val |= s; \
- val &= ~c; \
- write_sysreg_s(val, SYS_ ## reg); \
- } \
+ val = m->nmask; \
+ val |= s; \
+ val &= ~c; \
+ write_sysreg_s(val, SYS_ ## reg); \
} while(0)
#define update_fgt_traps(hctxt, vcpu, kvm, reg) \
update_fgt_traps_cs(hctxt, vcpu, kvm, reg, 0, 0)
-/*
- * Validate the fine grain trap masks.
- * Check that the masks do not overlap and that all bits are accounted for.
- */
-#define CHECK_FGT_MASKS(reg) \
- do { \
- BUILD_BUG_ON((__ ## reg ## _MASK) & (__ ## reg ## _nMASK)); \
- BUILD_BUG_ON(~((__ ## reg ## _RES0) ^ (__ ## reg ## _MASK) ^ \
- (__ ## reg ## _nMASK))); \
- } while(0)
-
static inline bool cpu_has_amu(void)
{
u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1);
@@ -152,56 +195,60 @@ static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu)
struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
struct kvm *kvm = kern_hyp_va(vcpu->kvm);
- CHECK_FGT_MASKS(HFGRTR_EL2);
- CHECK_FGT_MASKS(HFGWTR_EL2);
- CHECK_FGT_MASKS(HFGITR_EL2);
- CHECK_FGT_MASKS(HDFGRTR_EL2);
- CHECK_FGT_MASKS(HDFGWTR_EL2);
- CHECK_FGT_MASKS(HAFGRTR_EL2);
- CHECK_FGT_MASKS(HCRX_EL2);
-
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
update_fgt_traps(hctxt, vcpu, kvm, HFGRTR_EL2);
update_fgt_traps_cs(hctxt, vcpu, kvm, HFGWTR_EL2, 0,
cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) ?
- HFGxTR_EL2_TCR_EL1_MASK : 0);
+ HFGWTR_EL2_TCR_EL1_MASK : 0);
update_fgt_traps(hctxt, vcpu, kvm, HFGITR_EL2);
update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR_EL2);
update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR_EL2);
if (cpu_has_amu())
update_fgt_traps(hctxt, vcpu, kvm, HAFGRTR_EL2);
+
+ if (!cpus_have_final_cap(ARM64_HAS_FGT2))
+ return;
+
+ update_fgt_traps(hctxt, vcpu, kvm, HFGRTR2_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HFGWTR2_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HFGITR2_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HDFGRTR2_EL2);
+ update_fgt_traps(hctxt, vcpu, kvm, HDFGWTR2_EL2);
}
-#define __deactivate_fgt(htcxt, vcpu, kvm, reg) \
+#define __deactivate_fgt(htcxt, vcpu, reg) \
do { \
- if ((vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) || \
- kvm->arch.fgu[reg_to_fgt_group_id(reg)]) \
- write_sysreg_s(ctxt_sys_reg(hctxt, reg), \
- SYS_ ## reg); \
+ write_sysreg_s(ctxt_sys_reg(hctxt, reg), \
+ SYS_ ## reg); \
} while(0)
static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt);
- struct kvm *kvm = kern_hyp_va(vcpu->kvm);
if (!cpus_have_final_cap(ARM64_HAS_FGT))
return;
- __deactivate_fgt(hctxt, vcpu, kvm, HFGRTR_EL2);
- if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38))
- write_sysreg_s(ctxt_sys_reg(hctxt, HFGWTR_EL2), SYS_HFGWTR_EL2);
- else
- __deactivate_fgt(hctxt, vcpu, kvm, HFGWTR_EL2);
- __deactivate_fgt(hctxt, vcpu, kvm, HFGITR_EL2);
- __deactivate_fgt(hctxt, vcpu, kvm, HDFGRTR_EL2);
- __deactivate_fgt(hctxt, vcpu, kvm, HDFGWTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HFGRTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HFGWTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HFGITR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HDFGRTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HDFGWTR_EL2);
if (cpu_has_amu())
- __deactivate_fgt(hctxt, vcpu, kvm, HAFGRTR_EL2);
+ __deactivate_fgt(hctxt, vcpu, HAFGRTR_EL2);
+
+ if (!cpus_have_final_cap(ARM64_HAS_FGT2))
+ return;
+
+ __deactivate_fgt(hctxt, vcpu, HFGRTR2_EL2);
+ __deactivate_fgt(hctxt, vcpu, HFGWTR2_EL2);
+ __deactivate_fgt(hctxt, vcpu, HFGITR2_EL2);
+ __deactivate_fgt(hctxt, vcpu, HDFGRTR2_EL2);
+ __deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2);
}
static inline void __activate_traps_mpam(struct kvm_vcpu *vcpu)
@@ -260,12 +307,9 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
if (cpus_have_final_cap(ARM64_HAS_HCX)) {
u64 hcrx = vcpu->arch.hcrx_el2;
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) {
- u64 clr = 0, set = 0;
-
- compute_clr_set(vcpu, HCRX_EL2, clr, set);
-
- hcrx |= set;
- hcrx &= ~clr;
+ u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2);
+ hcrx |= val & __HCRX_EL2_MASK;
+ hcrx &= ~(~val & __HCRX_EL2_nMASK);
}
ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2);
@@ -300,7 +344,7 @@ static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr)
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM))
hcr |= HCR_TVM;
- write_sysreg(hcr, hcr_el2);
+ write_sysreg_hcr(hcr);
if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index ea0a704da9b8..5f9d56754e39 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -39,12 +39,12 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages);
int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages);
-int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
enum kvm_pgtable_prot prot);
-int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);
int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot);
-int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *hyp_vm);
-int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm);
+int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm);
+int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm);
int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu);
bool addr_is_memory(phys_addr_t phys);
@@ -67,4 +67,10 @@ static __always_inline void __load_host_stage2(void)
else
write_sysreg(0, vttbr_el2);
}
+
+#ifdef CONFIG_NVHE_EL2_DEBUG
+void pkvm_ownership_selftest(void *base);
+#else
+static inline void pkvm_ownership_selftest(void *base) { }
+#endif
#endif /* __KVM_NVHE_MEM_PROTECT__ */
diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h
index 34233d586060..dee1a406b0c2 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/memory.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h
@@ -8,23 +8,30 @@
#include <linux/types.h>
/*
- * Bits 0-1 are reserved to track the memory ownership state of each page:
- * 00: The page is owned exclusively by the page-table owner.
- * 01: The page is owned by the page-table owner, but is shared
- * with another entity.
- * 10: The page is shared with, but not owned by the page-table owner.
- * 11: Reserved for future use (lending).
+ * Bits 0-1 are used to encode the memory ownership state of each page from the
+ * point of view of a pKVM "component" (host, hyp, guest, ... see enum
+ * pkvm_component_id):
+ * 00: The page is owned and exclusively accessible by the component;
+ * 01: The page is owned and accessible by the component, but is also
+ * accessible by another component;
+ * 10: The page is accessible but not owned by the component;
+ * The storage of this state depends on the component: either in the
+ * hyp_vmemmap for the host and hyp states or in PTE software bits for guests.
*/
enum pkvm_page_state {
PKVM_PAGE_OWNED = 0ULL,
PKVM_PAGE_SHARED_OWNED = BIT(0),
PKVM_PAGE_SHARED_BORROWED = BIT(1),
- __PKVM_PAGE_RESERVED = BIT(0) | BIT(1),
- /* Meta-states which aren't encoded directly in the PTE's SW bits */
- PKVM_NOPAGE = BIT(2),
+ /*
+ * 'Meta-states' are not stored directly in PTE SW bits for guest
+ * states, but inferred from the context (e.g. invalid PTE entries).
+ * For the host and hyp, meta-states are stored directly in the
+ * struct hyp_page.
+ */
+ PKVM_NOPAGE = BIT(0) | BIT(1),
};
-#define PKVM_PAGE_META_STATES_MASK (~__PKVM_PAGE_RESERVED)
+#define PKVM_PAGE_STATE_MASK (BIT(0) | BIT(1))
#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
@@ -44,8 +51,15 @@ struct hyp_page {
u16 refcount;
u8 order;
- /* Host (non-meta) state. Guarded by the host stage-2 lock. */
- enum pkvm_page_state host_state : 8;
+ /* Host state. Guarded by the host stage-2 lock. */
+ unsigned __host_state : 4;
+
+ /*
+ * Complement of the hyp state. Guarded by the hyp stage-1 lock. We use
+ * the complement so that the initial 0 in __hyp_state_comp (due to the
+ * entire vmemmap starting off zeroed) encodes PKVM_NOPAGE.
+ */
+ unsigned __hyp_state_comp : 4;
u32 host_share_guest_count;
};
@@ -82,6 +96,26 @@ static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys)
#define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page))
#define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool)
+static inline enum pkvm_page_state get_host_state(struct hyp_page *p)
+{
+ return p->__host_state;
+}
+
+static inline void set_host_state(struct hyp_page *p, enum pkvm_page_state state)
+{
+ p->__host_state = state;
+}
+
+static inline enum pkvm_page_state get_hyp_state(struct hyp_page *p)
+{
+ return p->__hyp_state_comp ^ PKVM_PAGE_STATE_MASK;
+}
+
+static inline void set_hyp_state(struct hyp_page *p, enum pkvm_page_state state)
+{
+ p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_MASK;
+}
+
/*
* Refcounting for 'struct hyp_page'.
* hyp_pool::lock must be held if atomic access to the refcount is required.
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index 230e4f2527de..6e83ce35c2f2 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -13,9 +13,11 @@
extern struct kvm_pgtable pkvm_pgtable;
extern hyp_spinlock_t pkvm_pgd_lock;
-int hyp_create_pcpu_fixmap(void);
+int hyp_create_fixmap(void);
void *hyp_fixmap_map(phys_addr_t phys);
void hyp_fixmap_unmap(void);
+void *hyp_fixblock_map(phys_addr_t phys, size_t *size);
+void hyp_fixblock_unmap(void);
int hyp_create_idmap(u32 hyp_va_bits);
int hyp_map_vectors(void);
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index b43426a493df..a76522d63c3e 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -99,3 +99,9 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAG
# causes a build failure. Remove profile optimization flags.
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS))
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables
+
+ifeq ($(CONFIG_UBSAN_KVM_EL2),y)
+UBSAN_SANITIZE := y
+# Always use brk and not hooks
+ccflags-y += $(CFLAGS_UBSAN_TRAP)
+endif
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 58f0cb2298cc..eef15b374abb 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -124,7 +124,7 @@ SYM_FUNC_START(__hyp_do_panic)
/* Ensure host stage-2 is disabled */
mrs x0, hcr_el2
bic x0, x0, #HCR_VM
- msr hcr_el2, x0
+ msr_hcr_el2 x0
isb
tlbi vmalls12e1
dsb nsh
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index f8af11189572..aada42522e7b 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -100,7 +100,7 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
msr mair_el2, x1
ldr x1, [x0, #NVHE_INIT_HCR_EL2]
- msr hcr_el2, x1
+ msr_hcr_el2 x1
mov x2, #HCR_E2H
and x2, x1, x2
@@ -262,7 +262,7 @@ reset:
alternative_if ARM64_KVM_PROTECTED_MODE
mov_q x5, HCR_HOST_NVHE_FLAGS
- msr hcr_el2, x5
+ msr_hcr_el2 x5
alternative_else_nop_endif
/* Install stub vectors */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 2c37680d954c..8e8848de4d47 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -123,10 +123,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt;
- hyp_vcpu->vcpu.arch.sve_state = kern_hyp_va(host_vcpu->arch.sve_state);
- /* Limit guest vector length to the maximum supported by the host. */
- hyp_vcpu->vcpu.arch.sve_max_vl = min(host_vcpu->arch.sve_max_vl, kvm_host_sve_max_vl);
-
hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2;
hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE);
hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) &
@@ -249,7 +245,8 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(u64, pfn, host_ctxt, 1);
DECLARE_REG(u64, gfn, host_ctxt, 2);
- DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3);
+ DECLARE_REG(u64, nr_pages, host_ctxt, 3);
+ DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4);
struct pkvm_hyp_vcpu *hyp_vcpu;
int ret = -EINVAL;
@@ -264,7 +261,7 @@ static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt)
if (ret)
goto out;
- ret = __pkvm_host_share_guest(pfn, gfn, hyp_vcpu, prot);
+ ret = __pkvm_host_share_guest(pfn, gfn, nr_pages, hyp_vcpu, prot);
out:
cpu_reg(host_ctxt, 1) = ret;
}
@@ -273,6 +270,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
DECLARE_REG(u64, gfn, host_ctxt, 2);
+ DECLARE_REG(u64, nr_pages, host_ctxt, 3);
struct pkvm_hyp_vm *hyp_vm;
int ret = -EINVAL;
@@ -283,7 +281,7 @@ static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt)
if (!hyp_vm)
goto out;
- ret = __pkvm_host_unshare_guest(gfn, hyp_vm);
+ ret = __pkvm_host_unshare_guest(gfn, nr_pages, hyp_vm);
put_pkvm_hyp_vm(hyp_vm);
out:
cpu_reg(host_ctxt, 1) = ret;
@@ -312,6 +310,7 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt
{
DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
DECLARE_REG(u64, gfn, host_ctxt, 2);
+ DECLARE_REG(u64, nr_pages, host_ctxt, 3);
struct pkvm_hyp_vm *hyp_vm;
int ret = -EINVAL;
@@ -322,7 +321,7 @@ static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt
if (!hyp_vm)
goto out;
- ret = __pkvm_host_wrprotect_guest(gfn, hyp_vm);
+ ret = __pkvm_host_wrprotect_guest(gfn, nr_pages, hyp_vm);
put_pkvm_hyp_vm(hyp_vm);
out:
cpu_reg(host_ctxt, 1) = ret;
@@ -332,7 +331,8 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho
{
DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1);
DECLARE_REG(u64, gfn, host_ctxt, 2);
- DECLARE_REG(bool, mkold, host_ctxt, 3);
+ DECLARE_REG(u64, nr_pages, host_ctxt, 3);
+ DECLARE_REG(bool, mkold, host_ctxt, 4);
struct pkvm_hyp_vm *hyp_vm;
int ret = -EINVAL;
@@ -343,7 +343,7 @@ static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *ho
if (!hyp_vm)
goto out;
- ret = __pkvm_host_test_clear_young_guest(gfn, mkold, hyp_vm);
+ ret = __pkvm_host_test_clear_young_guest(gfn, nr_pages, mkold, hyp_vm);
put_pkvm_hyp_vm(hyp_vm);
out:
cpu_reg(host_ctxt, 1) = ret;
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
index f4562f417d3f..d724f6d69302 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S
@@ -25,5 +25,7 @@ SECTIONS {
BEGIN_HYP_SECTION(.data..percpu)
PERCPU_INPUT(L1_CACHE_BYTES)
END_HYP_SECTION
+
HYP_SECTION(.bss)
+ HYP_SECTION(.data)
}
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index e80f3ebd3e2a..95d7534c9679 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -60,6 +60,11 @@ static void hyp_unlock_component(void)
hyp_spin_unlock(&pkvm_pgd_lock);
}
+#define for_each_hyp_page(__p, __st, __sz) \
+ for (struct hyp_page *__p = hyp_phys_to_page(__st), \
+ *__e = __p + ((__sz) >> PAGE_SHIFT); \
+ __p < __e; __p++)
+
static void *host_s2_zalloc_pages_exact(size_t size)
{
void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
@@ -161,12 +166,6 @@ int kvm_host_prepare_stage2(void *pgt_pool_base)
return 0;
}
-static bool guest_stage2_force_pte_cb(u64 addr, u64 end,
- enum kvm_pgtable_prot prot)
-{
- return true;
-}
-
static void *guest_s2_zalloc_pages_exact(size_t size)
{
void *addr = hyp_alloc_pages(&current_vm->pool, get_order(size));
@@ -217,16 +216,42 @@ static void guest_s2_put_page(void *addr)
hyp_put_page(&current_vm->pool, addr);
}
+static void __apply_guest_page(void *va, size_t size,
+ void (*func)(void *addr, size_t size))
+{
+ size += va - PTR_ALIGN_DOWN(va, PAGE_SIZE);
+ va = PTR_ALIGN_DOWN(va, PAGE_SIZE);
+ size = PAGE_ALIGN(size);
+
+ while (size) {
+ size_t map_size = PAGE_SIZE;
+ void *map;
+
+ if (IS_ALIGNED((unsigned long)va, PMD_SIZE) && size >= PMD_SIZE)
+ map = hyp_fixblock_map(__hyp_pa(va), &map_size);
+ else
+ map = hyp_fixmap_map(__hyp_pa(va));
+
+ func(map, map_size);
+
+ if (map_size == PMD_SIZE)
+ hyp_fixblock_unmap();
+ else
+ hyp_fixmap_unmap();
+
+ size -= map_size;
+ va += map_size;
+ }
+}
+
static void clean_dcache_guest_page(void *va, size_t size)
{
- __clean_dcache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size);
- hyp_fixmap_unmap();
+ __apply_guest_page(va, size, __clean_dcache_guest_page);
}
static void invalidate_icache_guest_page(void *va, size_t size)
{
- __invalidate_icache_guest_page(hyp_fixmap_map(__hyp_pa(va)), size);
- hyp_fixmap_unmap();
+ __apply_guest_page(va, size, __invalidate_icache_guest_page);
}
int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
@@ -255,8 +280,7 @@ int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd)
};
guest_lock_component(vm);
- ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0,
- guest_stage2_force_pte_cb);
+ ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, NULL);
guest_unlock_component(vm);
if (ret)
return ret;
@@ -309,7 +333,7 @@ int __pkvm_prot_finalize(void)
*/
kvm_flush_dcache_to_poc(params, sizeof(*params));
- write_sysreg(params->hcr_el2, hcr_el2);
+ write_sysreg_hcr(params->hcr_el2);
__load_stage2(&host_mmu.arch.mmu, &host_mmu.arch);
/*
@@ -467,7 +491,8 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
return -EAGAIN;
if (pte) {
- WARN_ON(addr_is_memory(addr) && hyp_phys_to_page(addr)->host_state != PKVM_NOPAGE);
+ WARN_ON(addr_is_memory(addr) &&
+ get_host_state(hyp_phys_to_page(addr)) != PKVM_NOPAGE);
return -EPERM;
}
@@ -493,10 +518,8 @@ int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state)
{
- phys_addr_t end = addr + size;
-
- for (; addr < end; addr += PAGE_SIZE)
- hyp_phys_to_page(addr)->host_state = state;
+ for_each_hyp_page(page, addr, size)
+ set_host_state(page, state);
}
int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
@@ -618,16 +641,16 @@ static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size,
static int __host_check_page_state_range(u64 addr, u64 size,
enum pkvm_page_state state)
{
- u64 end = addr + size;
int ret;
- ret = check_range_allowed_memory(addr, end);
+ ret = check_range_allowed_memory(addr, addr + size);
if (ret)
return ret;
hyp_assert_lock_held(&host_mmu.lock);
- for (; addr < end; addr += PAGE_SIZE) {
- if (hyp_phys_to_page(addr)->host_state != state)
+
+ for_each_hyp_page(page, addr, size) {
+ if (get_host_state(page) != state)
return -EPERM;
}
@@ -637,7 +660,7 @@ static int __host_check_page_state_range(u64 addr, u64 size,
static int __host_set_page_state_range(u64 addr, u64 size,
enum pkvm_page_state state)
{
- if (hyp_phys_to_page(addr)->host_state == PKVM_NOPAGE) {
+ if (get_host_state(hyp_phys_to_page(addr)) == PKVM_NOPAGE) {
int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT);
if (ret)
@@ -649,24 +672,20 @@ static int __host_set_page_state_range(u64 addr, u64 size,
return 0;
}
-static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte, u64 addr)
+static void __hyp_set_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state)
{
- if (!kvm_pte_valid(pte))
- return PKVM_NOPAGE;
-
- return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
+ for_each_hyp_page(page, phys, size)
+ set_hyp_state(page, state);
}
-static int __hyp_check_page_state_range(u64 addr, u64 size,
- enum pkvm_page_state state)
+static int __hyp_check_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state)
{
- struct check_walk_data d = {
- .desired = state,
- .get_page_state = hyp_get_page_state,
- };
+ for_each_hyp_page(page, phys, size) {
+ if (get_hyp_state(page) != state)
+ return -EPERM;
+ }
- hyp_assert_lock_held(&pkvm_pgd_lock);
- return check_page_state_range(&pkvm_pgtable, addr, size, &d);
+ return 0;
}
static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
@@ -677,10 +696,9 @@ static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr)
return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
}
-static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr,
+static int __guest_check_page_state_range(struct pkvm_hyp_vm *vm, u64 addr,
u64 size, enum pkvm_page_state state)
{
- struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
struct check_walk_data d = {
.desired = state,
.get_page_state = guest_get_page_state,
@@ -693,8 +711,6 @@ static int __guest_check_page_state_range(struct pkvm_hyp_vcpu *vcpu, u64 addr,
int __pkvm_host_share_hyp(u64 pfn)
{
u64 phys = hyp_pfn_to_phys(pfn);
- void *virt = __hyp_va(phys);
- enum kvm_pgtable_prot prot;
u64 size = PAGE_SIZE;
int ret;
@@ -704,14 +720,11 @@ int __pkvm_host_share_hyp(u64 pfn)
ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
if (ret)
goto unlock;
- if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
- ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE);
- if (ret)
- goto unlock;
- }
+ ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE);
+ if (ret)
+ goto unlock;
- prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
- WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot));
+ __hyp_set_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED));
unlock:
@@ -734,7 +747,7 @@ int __pkvm_host_unshare_hyp(u64 pfn)
ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
if (ret)
goto unlock;
- ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_SHARED_BORROWED);
+ ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
if (ret)
goto unlock;
if (hyp_page_count((void *)virt)) {
@@ -742,7 +755,7 @@ int __pkvm_host_unshare_hyp(u64 pfn)
goto unlock;
}
- WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size);
+ __hyp_set_page_state_range(phys, size, PKVM_NOPAGE);
WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED));
unlock:
@@ -757,7 +770,6 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
u64 phys = hyp_pfn_to_phys(pfn);
u64 size = PAGE_SIZE * nr_pages;
void *virt = __hyp_va(phys);
- enum kvm_pgtable_prot prot;
int ret;
host_lock_component();
@@ -766,14 +778,12 @@ int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
if (ret)
goto unlock;
- if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
- ret = __hyp_check_page_state_range((u64)virt, size, PKVM_NOPAGE);
- if (ret)
- goto unlock;
- }
+ ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE);
+ if (ret)
+ goto unlock;
- prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
- WARN_ON(pkvm_create_mappings_locked(virt, virt + size, prot));
+ __hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED);
+ WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP));
WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP));
unlock:
@@ -793,15 +803,14 @@ int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
host_lock_component();
hyp_lock_component();
- ret = __hyp_check_page_state_range(virt, size, PKVM_PAGE_OWNED);
+ ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_OWNED);
+ if (ret)
+ goto unlock;
+ ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE);
if (ret)
goto unlock;
- if (IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
- ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE);
- if (ret)
- goto unlock;
- }
+ __hyp_set_page_state_range(phys, size, PKVM_NOPAGE);
WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size);
WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST));
@@ -816,24 +825,30 @@ int hyp_pin_shared_mem(void *from, void *to)
{
u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
u64 end = PAGE_ALIGN((u64)to);
+ u64 phys = __hyp_pa(start);
u64 size = end - start;
+ struct hyp_page *p;
int ret;
host_lock_component();
hyp_lock_component();
- ret = __host_check_page_state_range(__hyp_pa(start), size,
- PKVM_PAGE_SHARED_OWNED);
+ ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED);
if (ret)
goto unlock;
- ret = __hyp_check_page_state_range(start, size,
- PKVM_PAGE_SHARED_BORROWED);
+ ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED);
if (ret)
goto unlock;
- for (cur = start; cur < end; cur += PAGE_SIZE)
- hyp_page_ref_inc(hyp_virt_to_page(cur));
+ for (cur = start; cur < end; cur += PAGE_SIZE) {
+ p = hyp_virt_to_page(cur);
+ hyp_page_ref_inc(p);
+ if (p->refcount == 1)
+ WARN_ON(pkvm_create_mappings_locked((void *)cur,
+ (void *)cur + PAGE_SIZE,
+ PAGE_HYP));
+ }
unlock:
hyp_unlock_component();
@@ -846,12 +861,17 @@ void hyp_unpin_shared_mem(void *from, void *to)
{
u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE);
u64 end = PAGE_ALIGN((u64)to);
+ struct hyp_page *p;
host_lock_component();
hyp_lock_component();
- for (cur = start; cur < end; cur += PAGE_SIZE)
- hyp_page_ref_dec(hyp_virt_to_page(cur));
+ for (cur = start; cur < end; cur += PAGE_SIZE) {
+ p = hyp_virt_to_page(cur);
+ if (p->refcount == 1)
+ WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, cur, PAGE_SIZE) != PAGE_SIZE);
+ hyp_page_ref_dec(p);
+ }
hyp_unlock_component();
host_unlock_component();
@@ -887,49 +907,84 @@ int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages)
return ret;
}
-int __pkvm_host_share_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu,
+static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *size)
+{
+ size_t block_size;
+
+ if (nr_pages == 1) {
+ *size = PAGE_SIZE;
+ return 0;
+ }
+
+ /* We solely support second to last level huge mapping */
+ block_size = kvm_granule_size(KVM_PGTABLE_LAST_LEVEL - 1);
+
+ if (nr_pages != block_size >> PAGE_SHIFT)
+ return -EINVAL;
+
+ if (!IS_ALIGNED(phys | ipa, block_size))
+ return -EINVAL;
+
+ *size = block_size;
+ return 0;
+}
+
+int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu,
enum kvm_pgtable_prot prot)
{
struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
u64 phys = hyp_pfn_to_phys(pfn);
u64 ipa = hyp_pfn_to_phys(gfn);
- struct hyp_page *page;
+ u64 size;
int ret;
if (prot & ~KVM_PGTABLE_PROT_RWX)
return -EINVAL;
- ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+ ret = __guest_check_transition_size(phys, ipa, nr_pages, &size);
+ if (ret)
+ return ret;
+
+ ret = check_range_allowed_memory(phys, phys + size);
if (ret)
return ret;
host_lock_component();
guest_lock_component(vm);
- ret = __guest_check_page_state_range(vcpu, ipa, PAGE_SIZE, PKVM_NOPAGE);
+ ret = __guest_check_page_state_range(vm, ipa, size, PKVM_NOPAGE);
if (ret)
goto unlock;
- page = hyp_phys_to_page(phys);
- switch (page->host_state) {
- case PKVM_PAGE_OWNED:
- WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_OWNED));
- break;
- case PKVM_PAGE_SHARED_OWNED:
- if (page->host_share_guest_count)
- break;
- /* Only host to np-guest multi-sharing is tolerated */
- WARN_ON(1);
- fallthrough;
- default:
- ret = -EPERM;
- goto unlock;
+ for_each_hyp_page(page, phys, size) {
+ switch (get_host_state(page)) {
+ case PKVM_PAGE_OWNED:
+ continue;
+ case PKVM_PAGE_SHARED_OWNED:
+ if (page->host_share_guest_count == U32_MAX) {
+ ret = -EBUSY;
+ goto unlock;
+ }
+
+ /* Only host to np-guest multi-sharing is tolerated */
+ if (page->host_share_guest_count)
+ continue;
+
+ fallthrough;
+ default:
+ ret = -EPERM;
+ goto unlock;
+ }
}
- WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys,
+ for_each_hyp_page(page, phys, size) {
+ set_host_state(page, PKVM_PAGE_SHARED_OWNED);
+ page->host_share_guest_count++;
+ }
+
+ WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, size, phys,
pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED),
&vcpu->vcpu.arch.pkvm_memcache, 0));
- page->host_share_guest_count++;
unlock:
guest_unlock_component(vm);
@@ -938,10 +993,9 @@ unlock:
return ret;
}
-static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa)
+static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa, u64 size)
{
enum pkvm_page_state state;
- struct hyp_page *page;
kvm_pte_t pte;
u64 phys;
s8 level;
@@ -952,7 +1006,7 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
return ret;
if (!kvm_pte_valid(pte))
return -ENOENT;
- if (level != KVM_PGTABLE_LAST_LEVEL)
+ if (kvm_granule_size(level) != size)
return -E2BIG;
state = guest_get_page_state(pte, ipa);
@@ -960,43 +1014,49 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
return -EPERM;
phys = kvm_pte_to_phys(pte);
- ret = check_range_allowed_memory(phys, phys + PAGE_SIZE);
+ ret = check_range_allowed_memory(phys, phys + size);
if (WARN_ON(ret))
return ret;
- page = hyp_phys_to_page(phys);
- if (page->host_state != PKVM_PAGE_SHARED_OWNED)
- return -EPERM;
- if (WARN_ON(!page->host_share_guest_count))
- return -EINVAL;
+ for_each_hyp_page(page, phys, size) {
+ if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED)
+ return -EPERM;
+ if (WARN_ON(!page->host_share_guest_count))
+ return -EINVAL;
+ }
*__phys = phys;
return 0;
}
-int __pkvm_host_unshare_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm)
{
u64 ipa = hyp_pfn_to_phys(gfn);
- struct hyp_page *page;
- u64 phys;
+ u64 size, phys;
int ret;
+ ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
+ if (ret)
+ return ret;
+
host_lock_component();
guest_lock_component(vm);
- ret = __check_host_shared_guest(vm, &phys, ipa);
+ ret = __check_host_shared_guest(vm, &phys, ipa, size);
if (ret)
goto unlock;
- ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE);
+ ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, size);
if (ret)
goto unlock;
- page = hyp_phys_to_page(phys);
- page->host_share_guest_count--;
- if (!page->host_share_guest_count)
- WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED));
+ for_each_hyp_page(page, phys, size) {
+ /* __check_host_shared_guest() protects against underflow */
+ page->host_share_guest_count--;
+ if (!page->host_share_guest_count)
+ set_host_state(page, PKVM_PAGE_OWNED);
+ }
unlock:
guest_unlock_component(vm);
@@ -1005,7 +1065,7 @@ unlock:
return ret;
}
-static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa)
+static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa, u64 size)
{
u64 phys;
int ret;
@@ -1016,7 +1076,7 @@ static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa)
host_lock_component();
guest_lock_component(vm);
- ret = __check_host_shared_guest(vm, &phys, ipa);
+ ret = __check_host_shared_guest(vm, &phys, ipa, size);
guest_unlock_component(vm);
host_unlock_component();
@@ -1036,7 +1096,7 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_
if (prot & ~KVM_PGTABLE_PROT_RWX)
return -EINVAL;
- assert_host_shared_guest(vm, ipa);
+ assert_host_shared_guest(vm, ipa, PAGE_SIZE);
guest_lock_component(vm);
ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
guest_unlock_component(vm);
@@ -1044,33 +1104,41 @@ int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_
return ret;
}
-int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
+int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm)
{
- u64 ipa = hyp_pfn_to_phys(gfn);
+ u64 size, ipa = hyp_pfn_to_phys(gfn);
int ret;
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
- assert_host_shared_guest(vm, ipa);
+ ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
+ if (ret)
+ return ret;
+
+ assert_host_shared_guest(vm, ipa, size);
guest_lock_component(vm);
- ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
+ ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, size);
guest_unlock_component(vm);
return ret;
}
-int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
+int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm)
{
- u64 ipa = hyp_pfn_to_phys(gfn);
+ u64 size, ipa = hyp_pfn_to_phys(gfn);
int ret;
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
- assert_host_shared_guest(vm, ipa);
+ ret = __guest_check_transition_size(0, ipa, nr_pages, &size);
+ if (ret)
+ return ret;
+
+ assert_host_shared_guest(vm, ipa, size);
guest_lock_component(vm);
- ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
+ ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, size, mkold);
guest_unlock_component(vm);
return ret;
@@ -1084,10 +1152,210 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
- assert_host_shared_guest(vm, ipa);
+ assert_host_shared_guest(vm, ipa, PAGE_SIZE);
guest_lock_component(vm);
kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
guest_unlock_component(vm);
return 0;
}
+
+#ifdef CONFIG_NVHE_EL2_DEBUG
+struct pkvm_expected_state {
+ enum pkvm_page_state host;
+ enum pkvm_page_state hyp;
+ enum pkvm_page_state guest[2]; /* [ gfn, gfn + 1 ] */
+};
+
+static struct pkvm_expected_state selftest_state;
+static struct hyp_page *selftest_page;
+
+static struct pkvm_hyp_vm selftest_vm = {
+ .kvm = {
+ .arch = {
+ .mmu = {
+ .arch = &selftest_vm.kvm.arch,
+ .pgt = &selftest_vm.pgt,
+ },
+ },
+ },
+};
+
+static struct pkvm_hyp_vcpu selftest_vcpu = {
+ .vcpu = {
+ .arch = {
+ .hw_mmu = &selftest_vm.kvm.arch.mmu,
+ },
+ .kvm = &selftest_vm.kvm,
+ },
+};
+
+static void init_selftest_vm(void *virt)
+{
+ struct hyp_page *p = hyp_virt_to_page(virt);
+ int i;
+
+ selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr;
+ WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt));
+
+ for (i = 0; i < pkvm_selftest_pages(); i++) {
+ if (p[i].refcount)
+ continue;
+ p[i].refcount = 1;
+ hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i]));
+ }
+}
+
+static u64 selftest_ipa(void)
+{
+ return BIT(selftest_vm.pgt.ia_bits - 1);
+}
+
+static void assert_page_state(void)
+{
+ void *virt = hyp_page_to_virt(selftest_page);
+ u64 size = PAGE_SIZE << selftest_page->order;
+ struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu;
+ u64 phys = hyp_virt_to_phys(virt);
+ u64 ipa[2] = { selftest_ipa(), selftest_ipa() + PAGE_SIZE };
+ struct pkvm_hyp_vm *vm;
+
+ vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
+
+ host_lock_component();
+ WARN_ON(__host_check_page_state_range(phys, size, selftest_state.host));
+ host_unlock_component();
+
+ hyp_lock_component();
+ WARN_ON(__hyp_check_page_state_range(phys, size, selftest_state.hyp));
+ hyp_unlock_component();
+
+ guest_lock_component(&selftest_vm);
+ WARN_ON(__guest_check_page_state_range(vm, ipa[0], size, selftest_state.guest[0]));
+ WARN_ON(__guest_check_page_state_range(vm, ipa[1], size, selftest_state.guest[1]));
+ guest_unlock_component(&selftest_vm);
+}
+
+#define assert_transition_res(res, fn, ...) \
+ do { \
+ WARN_ON(fn(__VA_ARGS__) != res); \
+ assert_page_state(); \
+ } while (0)
+
+void pkvm_ownership_selftest(void *base)
+{
+ enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_RWX;
+ void *virt = hyp_alloc_pages(&host_s2_pool, 0);
+ struct pkvm_hyp_vcpu *vcpu = &selftest_vcpu;
+ struct pkvm_hyp_vm *vm = &selftest_vm;
+ u64 phys, size, pfn, gfn;
+
+ WARN_ON(!virt);
+ selftest_page = hyp_virt_to_page(virt);
+ selftest_page->refcount = 0;
+ init_selftest_vm(base);
+
+ size = PAGE_SIZE << selftest_page->order;
+ phys = hyp_virt_to_phys(virt);
+ pfn = hyp_phys_to_pfn(phys);
+ gfn = hyp_phys_to_pfn(selftest_ipa());
+
+ selftest_state.host = PKVM_NOPAGE;
+ selftest_state.hyp = PKVM_PAGE_OWNED;
+ selftest_state.guest[0] = selftest_state.guest[1] = PKVM_NOPAGE;
+ assert_page_state();
+ assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1);
+ assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size);
+ assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm);
+
+ selftest_state.host = PKVM_PAGE_OWNED;
+ selftest_state.hyp = PKVM_NOPAGE;
+ assert_transition_res(0, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1);
+ assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm);
+ assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size);
+
+ selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+ selftest_state.hyp = PKVM_PAGE_SHARED_BORROWED;
+ assert_transition_res(0, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm);
+
+ assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size);
+ assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size);
+ hyp_unpin_shared_mem(virt, virt + size);
+ WARN_ON(hyp_page_count(virt) != 1);
+ assert_transition_res(-EBUSY, __pkvm_host_unshare_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm);
+
+ hyp_unpin_shared_mem(virt, virt + size);
+ assert_page_state();
+ WARN_ON(hyp_page_count(virt));
+
+ selftest_state.host = PKVM_PAGE_OWNED;
+ selftest_state.hyp = PKVM_NOPAGE;
+ assert_transition_res(0, __pkvm_host_unshare_hyp, pfn);
+
+ selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+ selftest_state.hyp = PKVM_NOPAGE;
+ assert_transition_res(0, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm);
+ assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size);
+
+ selftest_state.host = PKVM_PAGE_OWNED;
+ selftest_state.hyp = PKVM_NOPAGE;
+ assert_transition_res(0, __pkvm_host_unshare_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1);
+
+ selftest_state.host = PKVM_PAGE_SHARED_OWNED;
+ selftest_state.guest[0] = PKVM_PAGE_SHARED_BORROWED;
+ assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot);
+ assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1);
+ assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn);
+ assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1);
+ assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size);
+
+ selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED;
+ assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot);
+ WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2);
+
+ selftest_state.guest[0] = PKVM_NOPAGE;
+ assert_transition_res(0, __pkvm_host_unshare_guest, gfn, 1, vm);
+
+ selftest_state.guest[1] = PKVM_NOPAGE;
+ selftest_state.host = PKVM_PAGE_OWNED;
+ assert_transition_res(0, __pkvm_host_unshare_guest, gfn + 1, 1, vm);
+
+ selftest_state.host = PKVM_NOPAGE;
+ selftest_state.hyp = PKVM_PAGE_OWNED;
+ assert_transition_res(0, __pkvm_host_donate_hyp, pfn, 1);
+
+ selftest_page->refcount = 1;
+ hyp_put_page(&host_s2_pool, virt);
+}
+#endif
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index f41c7440b34b..ae8391baebc3 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -229,9 +229,8 @@ int hyp_map_vectors(void)
return 0;
}
-void *hyp_fixmap_map(phys_addr_t phys)
+static void *fixmap_map_slot(struct hyp_fixmap_slot *slot, phys_addr_t phys)
{
- struct hyp_fixmap_slot *slot = this_cpu_ptr(&fixmap_slots);
kvm_pte_t pte, *ptep = slot->ptep;
pte = *ptep;
@@ -243,10 +242,21 @@ void *hyp_fixmap_map(phys_addr_t phys)
return (void *)slot->addr;
}
+void *hyp_fixmap_map(phys_addr_t phys)
+{
+ return fixmap_map_slot(this_cpu_ptr(&fixmap_slots), phys);
+}
+
static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
{
kvm_pte_t *ptep = slot->ptep;
u64 addr = slot->addr;
+ u32 level;
+
+ if (FIELD_GET(KVM_PTE_TYPE, *ptep) == KVM_PTE_TYPE_PAGE)
+ level = KVM_PGTABLE_LAST_LEVEL;
+ else
+ level = KVM_PGTABLE_LAST_LEVEL - 1; /* create_fixblock() guarantees PMD level */
WRITE_ONCE(*ptep, *ptep & ~KVM_PTE_VALID);
@@ -260,7 +270,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot)
* https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03
*/
dsb(ishst);
- __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), KVM_PGTABLE_LAST_LEVEL);
+ __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level);
dsb(ish);
isb();
}
@@ -273,9 +283,9 @@ void hyp_fixmap_unmap(void)
static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx,
enum kvm_pgtable_walk_flags visit)
{
- struct hyp_fixmap_slot *slot = per_cpu_ptr(&fixmap_slots, (u64)ctx->arg);
+ struct hyp_fixmap_slot *slot = (struct hyp_fixmap_slot *)ctx->arg;
- if (!kvm_pte_valid(ctx->old) || ctx->level != KVM_PGTABLE_LAST_LEVEL)
+ if (!kvm_pte_valid(ctx->old) || (ctx->end - ctx->start) != kvm_granule_size(ctx->level))
return -EINVAL;
slot->addr = ctx->addr;
@@ -296,13 +306,84 @@ static int create_fixmap_slot(u64 addr, u64 cpu)
struct kvm_pgtable_walker walker = {
.cb = __create_fixmap_slot_cb,
.flags = KVM_PGTABLE_WALK_LEAF,
- .arg = (void *)cpu,
+ .arg = per_cpu_ptr(&fixmap_slots, cpu),
};
return kvm_pgtable_walk(&pkvm_pgtable, addr, PAGE_SIZE, &walker);
}
-int hyp_create_pcpu_fixmap(void)
+#if PAGE_SHIFT < 16
+#define HAS_FIXBLOCK
+static struct hyp_fixmap_slot hyp_fixblock_slot;
+static DEFINE_HYP_SPINLOCK(hyp_fixblock_lock);
+#endif
+
+static int create_fixblock(void)
+{
+#ifdef HAS_FIXBLOCK
+ struct kvm_pgtable_walker walker = {
+ .cb = __create_fixmap_slot_cb,
+ .flags = KVM_PGTABLE_WALK_LEAF,
+ .arg = &hyp_fixblock_slot,
+ };
+ unsigned long addr;
+ phys_addr_t phys;
+ int ret, i;
+
+ /* Find a RAM phys address, PMD aligned */
+ for (i = 0; i < hyp_memblock_nr; i++) {
+ phys = ALIGN(hyp_memory[i].base, PMD_SIZE);
+ if (phys + PMD_SIZE < (hyp_memory[i].base + hyp_memory[i].size))
+ break;
+ }
+
+ if (i >= hyp_memblock_nr)
+ return -EINVAL;
+
+ hyp_spin_lock(&pkvm_pgd_lock);
+ addr = ALIGN(__io_map_base, PMD_SIZE);
+ ret = __pkvm_alloc_private_va_range(addr, PMD_SIZE);
+ if (ret)
+ goto unlock;
+
+ ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PMD_SIZE, phys, PAGE_HYP);
+ if (ret)
+ goto unlock;
+
+ ret = kvm_pgtable_walk(&pkvm_pgtable, addr, PMD_SIZE, &walker);
+
+unlock:
+ hyp_spin_unlock(&pkvm_pgd_lock);
+
+ return ret;
+#else
+ return 0;
+#endif
+}
+
+void *hyp_fixblock_map(phys_addr_t phys, size_t *size)
+{
+#ifdef HAS_FIXBLOCK
+ *size = PMD_SIZE;
+ hyp_spin_lock(&hyp_fixblock_lock);
+ return fixmap_map_slot(&hyp_fixblock_slot, phys);
+#else
+ *size = PAGE_SIZE;
+ return hyp_fixmap_map(phys);
+#endif
+}
+
+void hyp_fixblock_unmap(void)
+{
+#ifdef HAS_FIXBLOCK
+ fixmap_clear_slot(&hyp_fixblock_slot);
+ hyp_spin_unlock(&hyp_fixblock_lock);
+#else
+ hyp_fixmap_unmap();
+#endif
+}
+
+int hyp_create_fixmap(void)
{
unsigned long addr, i;
int ret;
@@ -322,7 +403,7 @@ int hyp_create_pcpu_fixmap(void)
return ret;
}
- return 0;
+ return create_fixblock();
}
int hyp_create_idmap(u32 hyp_va_bits)
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
index 5a335a51deca..338505cb0171 100644
--- a/arch/arm64/kvm/hyp/nvhe/pkvm.c
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -372,6 +372,18 @@ static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu)
hyp_unpin_shared_mem(host_vcpu, host_vcpu + 1);
}
+static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu)
+{
+ void *sve_state;
+
+ if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE))
+ return;
+
+ sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state);
+ hyp_unpin_shared_mem(sve_state,
+ sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu));
+}
+
static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],
unsigned int nr_vcpus)
{
@@ -384,6 +396,7 @@ static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[],
continue;
unpin_host_vcpu(hyp_vcpu->host_vcpu);
+ unpin_host_sve_state(hyp_vcpu);
}
}
@@ -398,12 +411,40 @@ static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm,
pkvm_init_features_from_host(hyp_vm, host_kvm);
}
-static void pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu)
+static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu)
{
struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu;
+ unsigned int sve_max_vl;
+ size_t sve_state_size;
+ void *sve_state;
+ int ret = 0;
- if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE))
+ if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) {
vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED);
+ return 0;
+ }
+
+ /* Limit guest vector length to the maximum supported by the host. */
+ sve_max_vl = min(READ_ONCE(host_vcpu->arch.sve_max_vl), kvm_host_sve_max_vl);
+ sve_state_size = sve_state_size_from_vl(sve_max_vl);
+ sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state));
+
+ if (!sve_state || !sve_state_size) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ ret = hyp_pin_shared_mem(sve_state, sve_state + sve_state_size);
+ if (ret)
+ goto err;
+
+ vcpu->arch.sve_state = sve_state;
+ vcpu->arch.sve_max_vl = sve_max_vl;
+
+ return 0;
+err:
+ clear_bit(KVM_ARM_VCPU_SVE, vcpu->kvm->arch.vcpu_features);
+ return ret;
}
static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
@@ -432,7 +473,7 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu,
if (ret)
goto done;
- pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
+ ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu);
done:
if (ret)
unpin_host_vcpu(host_vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index d62bcb5634a2..a48d3f5a5afb 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -28,6 +28,7 @@ static void *vmemmap_base;
static void *vm_table_base;
static void *hyp_pgt_base;
static void *host_s2_pgt_base;
+static void *selftest_base;
static void *ffa_proxy_pages;
static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
static struct hyp_pool hpool;
@@ -38,6 +39,11 @@ static int divide_memory_pool(void *virt, unsigned long size)
hyp_early_alloc_init(virt, size);
+ nr_pages = pkvm_selftest_pages();
+ selftest_base = hyp_early_alloc_contig(nr_pages);
+ if (nr_pages && !selftest_base)
+ return -ENOMEM;
+
nr_pages = hyp_vmemmap_pages(sizeof(struct hyp_page));
vmemmap_base = hyp_early_alloc_contig(nr_pages);
if (!vmemmap_base)
@@ -119,6 +125,10 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
+ ret = pkvm_create_mappings(__hyp_data_start, __hyp_data_end, PAGE_HYP);
+ if (ret)
+ return ret;
+
ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO);
if (ret)
return ret;
@@ -180,6 +190,7 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
enum kvm_pgtable_walk_flags visit)
{
enum pkvm_page_state state;
+ struct hyp_page *page;
phys_addr_t phys;
if (!kvm_pte_valid(ctx->old))
@@ -192,19 +203,25 @@ static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx,
if (!addr_is_memory(phys))
return -EINVAL;
+ page = hyp_phys_to_page(phys);
+
/*
* Adjust the host stage-2 mappings to match the ownership attributes
- * configured in the hypervisor stage-1.
+ * configured in the hypervisor stage-1, and make sure to propagate them
+ * to the hyp_vmemmap state.
*/
state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(ctx->old));
switch (state) {
case PKVM_PAGE_OWNED:
+ set_hyp_state(page, PKVM_PAGE_OWNED);
return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP);
case PKVM_PAGE_SHARED_OWNED:
- hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_BORROWED;
+ set_hyp_state(page, PKVM_PAGE_SHARED_OWNED);
+ set_host_state(page, PKVM_PAGE_SHARED_BORROWED);
break;
case PKVM_PAGE_SHARED_BORROWED:
- hyp_phys_to_page(phys)->host_state = PKVM_PAGE_SHARED_OWNED;
+ set_hyp_state(page, PKVM_PAGE_SHARED_BORROWED);
+ set_host_state(page, PKVM_PAGE_SHARED_OWNED);
break;
default:
return -EINVAL;
@@ -295,7 +312,7 @@ void __noreturn __pkvm_init_finalise(void)
if (ret)
goto out;
- ret = hyp_create_pcpu_fixmap();
+ ret = hyp_create_fixmap();
if (ret)
goto out;
@@ -304,6 +321,8 @@ void __noreturn __pkvm_init_finalise(void)
goto out;
pkvm_hyp_vm_table_init(vm_table_base);
+
+ pkvm_ownership_selftest(selftest_base);
out:
/*
* We tail-called to here from handle___pkvm_init() and will not return,
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 7d2ba6ef0261..73affe1333a4 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -33,6 +33,18 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
+struct fgt_masks hfgrtr_masks;
+struct fgt_masks hfgwtr_masks;
+struct fgt_masks hfgitr_masks;
+struct fgt_masks hdfgrtr_masks;
+struct fgt_masks hdfgwtr_masks;
+struct fgt_masks hafgrtr_masks;
+struct fgt_masks hfgrtr2_masks;
+struct fgt_masks hfgwtr2_masks;
+struct fgt_masks hfgitr2_masks;
+struct fgt_masks hdfgrtr2_masks;
+struct fgt_masks hdfgwtr2_masks;
+
extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
@@ -142,7 +154,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
__deactivate_traps_common(vcpu);
- write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
+ write_sysreg_hcr(this_cpu_ptr(&kvm_init_params)->hcr_el2);
__deactivate_cptr_traps(vcpu);
write_sysreg(__kvm_hyp_host_vector, vbar_el2);
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index df5cc74a7dd0..c351b4abd5db 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -11,12 +11,6 @@
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
-
-#define KVM_PTE_TYPE BIT(1)
-#define KVM_PTE_TYPE_BLOCK 0
-#define KVM_PTE_TYPE_PAGE 1
-#define KVM_PTE_TYPE_TABLE 1
-
struct kvm_pgtable_walk_data {
struct kvm_pgtable_walker *walker;
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 50aa8dbcae75..f162b0df5cae 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -446,7 +446,7 @@ u64 __vgic_v3_get_gic_config(void)
if (has_vhe()) {
flags = local_daif_save();
} else {
- sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+ sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO);
isb();
}
@@ -461,7 +461,7 @@ u64 __vgic_v3_get_gic_config(void)
if (has_vhe()) {
local_daif_restore(flags);
} else {
- sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+ sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0);
isb();
}
@@ -1058,11 +1058,11 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
switch (sysreg) {
case SYS_ICC_IGRPEN0_EL1:
if (is_read &&
- (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+ (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
return true;
if (!is_read &&
- (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+ (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
return true;
fallthrough;
@@ -1079,11 +1079,11 @@ static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu,
case SYS_ICC_IGRPEN1_EL1:
if (is_read &&
- (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+ (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1))
return true;
if (!is_read &&
- (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGxTR_EL2_ICC_IGRPENn_EL1))
+ (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1))
return true;
fallthrough;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 731a0378ed13..c9b330dc2066 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -48,21 +48,46 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
static u64 __compute_hcr(struct kvm_vcpu *vcpu)
{
+ u64 guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
u64 hcr = vcpu->arch.hcr_el2;
if (!vcpu_has_nv(vcpu))
return hcr;
+ /*
+ * We rely on the invariant that a vcpu entered from HYP
+ * context must also exit in the same context, as only an ERET
+ * instruction can kick us out of it, and we obviously trap
+ * that sucker. PSTATE.M will get fixed-up on exit.
+ */
if (is_hyp_ctxt(vcpu)) {
+ host_data_set_flag(VCPU_IN_HYP_CONTEXT);
+
hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB;
if (!vcpu_el2_e2h_is_set(vcpu))
hcr |= HCR_NV1;
write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2);
+ } else {
+ host_data_clear_flag(VCPU_IN_HYP_CONTEXT);
+
+ if (guest_hcr & HCR_NV) {
+ u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id()));
+
+ /* Inherit the low bits from the actual register */
+ va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0);
+ write_sysreg_s(va, SYS_VNCR_EL2);
+
+ /* Force NV2 in case the guest is forgetful... */
+ guest_hcr |= HCR_NV2;
+ }
}
- return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE);
+ BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) &&
+ host_data_test_flag(L1_VNCR_MAPPED));
+
+ return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE);
}
static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
@@ -184,7 +209,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
___deactivate_traps(vcpu);
- write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+ write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
if (has_cntpoff()) {
struct timer_map map;
@@ -459,6 +484,14 @@ static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
if (ret)
return false;
+ /*
+ * If we have to check for any VNCR mapping being invalidated,
+ * go back to the slow path for further processing.
+ */
+ if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) &&
+ atomic_read(&vcpu->kvm->arch.vncr_map_count))
+ return false;
+
__kvm_skip_instr(vcpu);
return true;
@@ -568,9 +601,12 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
/*
* If we were in HYP context on entry, adjust the PSTATE view
- * so that the usual helpers work correctly.
+ * so that the usual helpers work correctly. This enforces our
+ * invariant that the guest's HYP context status is preserved
+ * across a run.
*/
- if (vcpu_has_nv(vcpu) && (read_sysreg(hcr_el2) & HCR_NV)) {
+ if (vcpu_has_nv(vcpu) &&
+ unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) {
u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
switch (mode) {
@@ -586,6 +622,10 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
*vcpu_cpsr(vcpu) |= mode;
}
+ /* Apply extreme paranoia! */
+ BUG_ON(vcpu_has_nv(vcpu) &&
+ !!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu));
+
return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers);
}
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 3d50a1bd2bdb..ec2569818629 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -63,7 +63,7 @@ static void enter_vmid_context(struct kvm_s2_mmu *mmu,
__load_stage2(mmu, mmu->arch);
val = read_sysreg(hcr_el2);
val &= ~HCR_TGE;
- write_sysreg(val, hcr_el2);
+ write_sysreg_hcr(val);
isb();
}
@@ -73,7 +73,7 @@ static void exit_vmid_context(struct tlb_inv_context *cxt)
* We're done with the TLB operation, let's restore the host's
* view of HCR_EL2.
*/
- write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+ write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
isb();
/* ... and the stage-2 MMU context that we switched away from */
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index eeda92330ade..2942ec92c5a4 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1304,6 +1304,10 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
if (map_size == PAGE_SIZE)
return true;
+ /* pKVM only supports PMD_SIZE huge-mappings */
+ if (is_protected_kvm_enabled() && map_size != PMD_SIZE)
+ return false;
+
size = memslot->npages * PAGE_SIZE;
gpa_start = memslot->base_gfn << PAGE_SHIFT;
@@ -1540,7 +1544,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* logging_active is guaranteed to never be true for VM_PFNMAP
* memslots.
*/
- if (logging_active || is_protected_kvm_enabled()) {
+ if (logging_active) {
force_pte = true;
vma_shift = PAGE_SHIFT;
} else {
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 4a3fc11f7ecf..291dbe38eb5c 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -8,6 +8,7 @@
#include <linux/kvm.h>
#include <linux/kvm_host.h>
+#include <asm/fixmap.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_mmu.h>
@@ -16,6 +17,24 @@
#include "sys_regs.h"
+struct vncr_tlb {
+ /* The guest's VNCR_EL2 */
+ u64 gva;
+ struct s1_walk_info wi;
+ struct s1_walk_result wr;
+
+ u64 hpa;
+
+ /* -1 when not mapped on a CPU */
+ int cpu;
+
+ /*
+ * true if the TLB is valid. Can only be changed with the
+ * mmu_lock held.
+ */
+ bool valid;
+};
+
/*
* Ratio of live shadow S2 MMU per vcpu. This is a trade-off between
* memory usage and potential number of different sets of S2 PTs in
@@ -28,6 +47,7 @@ void kvm_init_nested(struct kvm *kvm)
{
kvm->arch.nested_mmus = NULL;
kvm->arch.nested_mmus_size = 0;
+ atomic_set(&kvm->arch.vncr_map_count, 0);
}
static int init_nested_s2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
@@ -55,6 +75,13 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
return -EINVAL;
+ if (!vcpu->arch.ctxt.vncr_array)
+ vcpu->arch.ctxt.vncr_array = (u64 *)__get_free_page(GFP_KERNEL_ACCOUNT |
+ __GFP_ZERO);
+
+ if (!vcpu->arch.ctxt.vncr_array)
+ return -ENOMEM;
+
/*
* Let's treat memory allocation failures as benign: If we fail to
* allocate anything, return an error and keep the allocated array
@@ -85,6 +112,9 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]);
+ free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
+ vcpu->arch.ctxt.vncr_array = NULL;
+
return ret;
}
@@ -405,6 +435,30 @@ static unsigned int ttl_to_size(u8 ttl)
return max_size;
}
+static u8 pgshift_level_to_ttl(u16 shift, u8 level)
+{
+ u8 ttl;
+
+ switch(shift) {
+ case 12:
+ ttl = TLBI_TTL_TG_4K;
+ break;
+ case 14:
+ ttl = TLBI_TTL_TG_16K;
+ break;
+ case 16:
+ ttl = TLBI_TTL_TG_64K;
+ break;
+ default:
+ BUG();
+ }
+
+ ttl <<= 2;
+ ttl |= level & 3;
+
+ return ttl;
+}
+
/*
* Compute the equivalent of the TTL field by parsing the shadow PT. The
* granule size is extracted from the cached VTCR_EL2.TG0 while the level is
@@ -676,23 +730,36 @@ 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 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;
+ if (!vcpu->arch.hw_mmu)
+ vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
} else {
- write_lock(&vcpu->kvm->mmu_lock);
- vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
- write_unlock(&vcpu->kvm->mmu_lock);
+ if (!vcpu->arch.hw_mmu) {
+ scoped_guard(write_lock, &vcpu->kvm->mmu_lock)
+ vcpu->arch.hw_mmu = get_s2_mmu_nested(vcpu);
+ }
+
+ if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV)
+ kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
}
}
void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
{
+ /* Unconditionally drop the VNCR mapping if we have one */
+ if (host_data_test_flag(L1_VNCR_MAPPED)) {
+ BUG_ON(vcpu->arch.vncr_tlb->cpu != smp_processor_id());
+ BUG_ON(is_hyp_ctxt(vcpu));
+
+ clear_fixmap(vncr_fixmap(vcpu->arch.vncr_tlb->cpu));
+ vcpu->arch.vncr_tlb->cpu = -1;
+ host_data_clear_flag(L1_VNCR_MAPPED);
+ atomic_dec(&vcpu->kvm->arch.vncr_map_count);
+ }
+
/*
* 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
@@ -743,6 +810,245 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2)
return kvm_inject_nested_sync(vcpu, esr_el2);
}
+static void invalidate_vncr(struct vncr_tlb *vt)
+{
+ vt->valid = false;
+ if (vt->cpu != -1)
+ clear_fixmap(vncr_fixmap(vt->cpu));
+}
+
+static void kvm_invalidate_vncr_ipa(struct kvm *kvm, u64 start, u64 end)
+{
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
+ return;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+ u64 ipa_start, ipa_end, ipa_size;
+
+ /*
+ * Careful here: We end-up here from an MMU notifier,
+ * and this can race against a vcpu not being onlined
+ * yet, without the pseudo-TLB being allocated.
+ *
+ * Skip those, as they obviously don't participate in
+ * the invalidation at this stage.
+ */
+ if (!vt)
+ continue;
+
+ if (!vt->valid)
+ continue;
+
+ ipa_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
+ vt->wr.level));
+ ipa_start = vt->wr.pa & (ipa_size - 1);
+ ipa_end = ipa_start + ipa_size;
+
+ if (ipa_end <= start || ipa_start >= end)
+ continue;
+
+ invalidate_vncr(vt);
+ }
+}
+
+struct s1e2_tlbi_scope {
+ enum {
+ TLBI_ALL,
+ TLBI_VA,
+ TLBI_VAA,
+ TLBI_ASID,
+ } type;
+
+ u16 asid;
+ u64 va;
+ u64 size;
+};
+
+static void invalidate_vncr_va(struct kvm *kvm,
+ struct s1e2_tlbi_scope *scope)
+{
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+ u64 va_start, va_end, va_size;
+
+ if (!vt->valid)
+ continue;
+
+ va_size = ttl_to_size(pgshift_level_to_ttl(vt->wi.pgshift,
+ vt->wr.level));
+ va_start = vt->gva & (va_size - 1);
+ va_end = va_start + va_size;
+
+ switch (scope->type) {
+ case TLBI_ALL:
+ break;
+
+ case TLBI_VA:
+ if (va_end <= scope->va ||
+ va_start >= (scope->va + scope->size))
+ continue;
+ if (vt->wr.nG && vt->wr.asid != scope->asid)
+ continue;
+ break;
+
+ case TLBI_VAA:
+ if (va_end <= scope->va ||
+ va_start >= (scope->va + scope->size))
+ continue;
+ break;
+
+ case TLBI_ASID:
+ if (!vt->wr.nG || vt->wr.asid != scope->asid)
+ continue;
+ break;
+ }
+
+ invalidate_vncr(vt);
+ }
+}
+
+static void compute_s1_tlbi_range(struct kvm_vcpu *vcpu, u32 inst, u64 val,
+ struct s1e2_tlbi_scope *scope)
+{
+ switch (inst) {
+ case OP_TLBI_ALLE2:
+ case OP_TLBI_ALLE2IS:
+ case OP_TLBI_ALLE2OS:
+ case OP_TLBI_VMALLE1:
+ case OP_TLBI_VMALLE1IS:
+ case OP_TLBI_VMALLE1OS:
+ case OP_TLBI_ALLE2NXS:
+ case OP_TLBI_ALLE2ISNXS:
+ case OP_TLBI_ALLE2OSNXS:
+ case OP_TLBI_VMALLE1NXS:
+ case OP_TLBI_VMALLE1ISNXS:
+ case OP_TLBI_VMALLE1OSNXS:
+ scope->type = TLBI_ALL;
+ break;
+ case OP_TLBI_VAE2:
+ case OP_TLBI_VAE2IS:
+ case OP_TLBI_VAE2OS:
+ case OP_TLBI_VAE1:
+ case OP_TLBI_VAE1IS:
+ case OP_TLBI_VAE1OS:
+ case OP_TLBI_VAE2NXS:
+ case OP_TLBI_VAE2ISNXS:
+ case OP_TLBI_VAE2OSNXS:
+ case OP_TLBI_VAE1NXS:
+ case OP_TLBI_VAE1ISNXS:
+ case OP_TLBI_VAE1OSNXS:
+ case OP_TLBI_VALE2:
+ case OP_TLBI_VALE2IS:
+ case OP_TLBI_VALE2OS:
+ case OP_TLBI_VALE1:
+ case OP_TLBI_VALE1IS:
+ case OP_TLBI_VALE1OS:
+ case OP_TLBI_VALE2NXS:
+ case OP_TLBI_VALE2ISNXS:
+ case OP_TLBI_VALE2OSNXS:
+ case OP_TLBI_VALE1NXS:
+ case OP_TLBI_VALE1ISNXS:
+ case OP_TLBI_VALE1OSNXS:
+ scope->type = TLBI_VA;
+ scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
+ if (!scope->size)
+ scope->size = SZ_1G;
+ scope->va = (val << 12) & ~(scope->size - 1);
+ scope->asid = FIELD_GET(TLBIR_ASID_MASK, val);
+ break;
+ case OP_TLBI_ASIDE1:
+ case OP_TLBI_ASIDE1IS:
+ case OP_TLBI_ASIDE1OS:
+ case OP_TLBI_ASIDE1NXS:
+ case OP_TLBI_ASIDE1ISNXS:
+ case OP_TLBI_ASIDE1OSNXS:
+ scope->type = TLBI_ASID;
+ scope->asid = FIELD_GET(TLBIR_ASID_MASK, val);
+ break;
+ case OP_TLBI_VAAE1:
+ case OP_TLBI_VAAE1IS:
+ case OP_TLBI_VAAE1OS:
+ case OP_TLBI_VAAE1NXS:
+ case OP_TLBI_VAAE1ISNXS:
+ case OP_TLBI_VAAE1OSNXS:
+ case OP_TLBI_VAALE1:
+ case OP_TLBI_VAALE1IS:
+ case OP_TLBI_VAALE1OS:
+ case OP_TLBI_VAALE1NXS:
+ case OP_TLBI_VAALE1ISNXS:
+ case OP_TLBI_VAALE1OSNXS:
+ scope->type = TLBI_VAA;
+ scope->size = ttl_to_size(FIELD_GET(TLBI_TTL_MASK, val));
+ if (!scope->size)
+ scope->size = SZ_1G;
+ scope->va = (val << 12) & ~(scope->size - 1);
+ break;
+ case OP_TLBI_RVAE2:
+ case OP_TLBI_RVAE2IS:
+ case OP_TLBI_RVAE2OS:
+ case OP_TLBI_RVAE1:
+ case OP_TLBI_RVAE1IS:
+ case OP_TLBI_RVAE1OS:
+ case OP_TLBI_RVAE2NXS:
+ case OP_TLBI_RVAE2ISNXS:
+ case OP_TLBI_RVAE2OSNXS:
+ case OP_TLBI_RVAE1NXS:
+ case OP_TLBI_RVAE1ISNXS:
+ case OP_TLBI_RVAE1OSNXS:
+ case OP_TLBI_RVALE2:
+ case OP_TLBI_RVALE2IS:
+ case OP_TLBI_RVALE2OS:
+ case OP_TLBI_RVALE1:
+ case OP_TLBI_RVALE1IS:
+ case OP_TLBI_RVALE1OS:
+ case OP_TLBI_RVALE2NXS:
+ case OP_TLBI_RVALE2ISNXS:
+ case OP_TLBI_RVALE2OSNXS:
+ case OP_TLBI_RVALE1NXS:
+ case OP_TLBI_RVALE1ISNXS:
+ case OP_TLBI_RVALE1OSNXS:
+ scope->type = TLBI_VA;
+ scope->va = decode_range_tlbi(val, &scope->size, &scope->asid);
+ break;
+ case OP_TLBI_RVAAE1:
+ case OP_TLBI_RVAAE1IS:
+ case OP_TLBI_RVAAE1OS:
+ case OP_TLBI_RVAAE1NXS:
+ case OP_TLBI_RVAAE1ISNXS:
+ case OP_TLBI_RVAAE1OSNXS:
+ case OP_TLBI_RVAALE1:
+ case OP_TLBI_RVAALE1IS:
+ case OP_TLBI_RVAALE1OS:
+ case OP_TLBI_RVAALE1NXS:
+ case OP_TLBI_RVAALE1ISNXS:
+ case OP_TLBI_RVAALE1OSNXS:
+ scope->type = TLBI_VAA;
+ scope->va = decode_range_tlbi(val, &scope->size, NULL);
+ break;
+ }
+}
+
+void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val)
+{
+ struct s1e2_tlbi_scope scope = {};
+
+ compute_s1_tlbi_range(vcpu, inst, val, &scope);
+
+ guard(write_lock)(&vcpu->kvm->mmu_lock);
+ invalidate_vncr_va(vcpu->kvm, &scope);
+}
+
void kvm_nested_s2_wp(struct kvm *kvm)
{
int i;
@@ -755,6 +1061,8 @@ void kvm_nested_s2_wp(struct kvm *kvm)
if (kvm_s2_mmu_valid(mmu))
kvm_stage2_wp_range(mmu, 0, kvm_phys_size(mmu));
}
+
+ kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits));
}
void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
@@ -769,6 +1077,8 @@ void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
if (kvm_s2_mmu_valid(mmu))
kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
}
+
+ kvm_invalidate_vncr_ipa(kvm, 0, BIT(kvm->arch.mmu.pgt->ia_bits));
}
void kvm_nested_s2_flush(struct kvm *kvm)
@@ -802,6 +1112,295 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm)
}
/*
+ * Dealing with VNCR_EL2 exposed by the *guest* is a complicated matter:
+ *
+ * - We introduce an internal representation of a vcpu-private TLB,
+ * representing the mapping between the guest VA contained in VNCR_EL2,
+ * the IPA the guest's EL2 PTs point to, and the actual PA this lives at.
+ *
+ * - On translation fault from a nested VNCR access, we create such a TLB.
+ * If there is no mapping to describe, the guest inherits the fault.
+ * Crucially, no actual mapping is done at this stage.
+ *
+ * - On vcpu_load() in a non-HYP context with HCR_EL2.NV==1, if the above
+ * TLB exists, we map it in the fixmap for this CPU, and run with it. We
+ * have to respect the permissions dictated by the guest, but not the
+ * memory type (FWB is a must).
+ *
+ * - Note that we usually don't do a vcpu_load() on the back of a fault
+ * (unless we are preempted), so the resolution of a translation fault
+ * must go via a request that will map the VNCR page in the fixmap.
+ * vcpu_load() might as well use the same mechanism.
+ *
+ * - On vcpu_put() in a non-HYP context with HCR_EL2.NV==1, if the TLB was
+ * mapped, we unmap it. Yes it is that simple. The TLB still exists
+ * though, and may be reused at a later load.
+ *
+ * - On permission fault, we simply forward the fault to the guest's EL2.
+ * Get out of my way.
+ *
+ * - On any TLBI for the EL2&0 translation regime, we must find any TLB that
+ * intersects with the TLBI request, invalidate it, and unmap the page
+ * from the fixmap. Because we need to look at all the vcpu-private TLBs,
+ * this requires some wide-ranging locking to ensure that nothing races
+ * against it. This may require some refcounting to avoid the search when
+ * no such TLB is present.
+ *
+ * - On MMU notifiers, we must invalidate our TLB in a similar way, but
+ * looking at the IPA instead. The funny part is that there may not be a
+ * stage-2 mapping for this page if L1 hasn't accessed it using LD/ST
+ * instructions.
+ */
+
+int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu)
+{
+ if (!kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
+ return 0;
+
+ vcpu->arch.vncr_tlb = kzalloc(sizeof(*vcpu->arch.vncr_tlb),
+ GFP_KERNEL_ACCOUNT);
+ if (!vcpu->arch.vncr_tlb)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static u64 read_vncr_el2(struct kvm_vcpu *vcpu)
+{
+ return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48);
+}
+
+static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
+{
+ bool write_fault, writable;
+ unsigned long mmu_seq;
+ struct vncr_tlb *vt;
+ struct page *page;
+ u64 va, pfn, gfn;
+ int ret;
+
+ vt = vcpu->arch.vncr_tlb;
+
+ /*
+ * If we're about to walk the EL2 S1 PTs, we must invalidate the
+ * current TLB, as it could be sampled from another vcpu doing a
+ * TLBI *IS. A real CPU wouldn't do that, but we only keep a single
+ * translation, so not much of a choice.
+ *
+ * We also prepare the next walk wilst we're at it.
+ */
+ scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
+ invalidate_vncr(vt);
+
+ vt->wi = (struct s1_walk_info) {
+ .regime = TR_EL20,
+ .as_el0 = false,
+ .pan = false,
+ };
+ vt->wr = (struct s1_walk_result){};
+ }
+
+ guard(srcu)(&vcpu->kvm->srcu);
+
+ va = read_vncr_el2(vcpu);
+
+ ret = __kvm_translate_va(vcpu, &vt->wi, &vt->wr, va);
+ if (ret)
+ return ret;
+
+ write_fault = kvm_is_write_fault(vcpu);
+
+ mmu_seq = vcpu->kvm->mmu_invalidate_seq;
+ smp_rmb();
+
+ gfn = vt->wr.pa >> PAGE_SHIFT;
+ pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writable, &page);
+ if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+ return -EFAULT;
+
+ scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
+ if (mmu_invalidate_retry(vcpu->kvm, mmu_seq))
+ return -EAGAIN;
+
+ vt->gva = va;
+ vt->hpa = pfn << PAGE_SHIFT;
+ vt->valid = true;
+ vt->cpu = -1;
+
+ kvm_make_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu);
+ kvm_release_faultin_page(vcpu->kvm, page, false, vt->wr.pw);
+ }
+
+ if (vt->wr.pw)
+ mark_page_dirty(vcpu->kvm, gfn);
+
+ return 0;
+}
+
+static void inject_vncr_perm(struct kvm_vcpu *vcpu)
+{
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+ u64 esr = kvm_vcpu_get_esr(vcpu);
+
+ /* Adjust the fault level to reflect that of the guest's */
+ esr &= ~ESR_ELx_FSC;
+ esr |= FIELD_PREP(ESR_ELx_FSC,
+ ESR_ELx_FSC_PERM_L(vt->wr.level));
+
+ kvm_inject_nested_sync(vcpu, esr);
+}
+
+static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu)
+{
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+
+ lockdep_assert_held_read(&vcpu->kvm->mmu_lock);
+
+ if (!vt->valid)
+ return false;
+
+ if (read_vncr_el2(vcpu) != vt->gva)
+ return false;
+
+ if (vt->wr.nG) {
+ u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+ u64 ttbr = ((tcr & TCR_A1) ?
+ vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
+ vcpu_read_sys_reg(vcpu, TTBR0_EL2));
+ u16 asid;
+
+ asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
+ if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+ !(tcr & TCR_ASID16))
+ asid &= GENMASK(7, 0);
+
+ return asid != vt->wr.asid;
+ }
+
+ return true;
+}
+
+int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
+{
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+ u64 esr = kvm_vcpu_get_esr(vcpu);
+
+ BUG_ON(!(esr & ESR_ELx_VNCR_SHIFT));
+
+ if (esr_fsc_is_permission_fault(esr)) {
+ inject_vncr_perm(vcpu);
+ } else if (esr_fsc_is_translation_fault(esr)) {
+ bool valid;
+ int ret;
+
+ scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
+ valid = kvm_vncr_tlb_lookup(vcpu);
+
+ if (!valid)
+ ret = kvm_translate_vncr(vcpu);
+ else
+ ret = -EPERM;
+
+ switch (ret) {
+ case -EAGAIN:
+ case -ENOMEM:
+ /* Let's try again... */
+ break;
+ case -EFAULT:
+ case -EINVAL:
+ case -ENOENT:
+ case -EACCES:
+ /*
+ * Translation failed, inject the corresponding
+ * exception back to EL2.
+ */
+ BUG_ON(!vt->wr.failed);
+
+ esr &= ~ESR_ELx_FSC;
+ esr |= FIELD_PREP(ESR_ELx_FSC, vt->wr.fst);
+
+ kvm_inject_nested_sync(vcpu, esr);
+ break;
+ case -EPERM:
+ /* Hack to deal with POE until we get kernel support */
+ inject_vncr_perm(vcpu);
+ break;
+ case 0:
+ break;
+ }
+ } else {
+ WARN_ONCE(1, "Unhandled VNCR abort, ESR=%llx\n", esr);
+ }
+
+ return 1;
+}
+
+static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu)
+{
+ struct vncr_tlb *vt = vcpu->arch.vncr_tlb;
+ pgprot_t prot;
+
+ guard(preempt)();
+ guard(read_lock)(&vcpu->kvm->mmu_lock);
+
+ /*
+ * The request to map VNCR may have raced against some other
+ * event, such as an interrupt, and may not be valid anymore.
+ */
+ if (is_hyp_ctxt(vcpu))
+ return;
+
+ /*
+ * Check that the pseudo-TLB is valid and that VNCR_EL2 still
+ * contains the expected value. If it doesn't, we simply bail out
+ * without a mapping -- a transformed MSR/MRS will generate the
+ * fault and allows us to populate the pseudo-TLB.
+ */
+ if (!vt->valid)
+ return;
+
+ if (read_vncr_el2(vcpu) != vt->gva)
+ return;
+
+ if (vt->wr.nG) {
+ u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2);
+ u64 ttbr = ((tcr & TCR_A1) ?
+ vcpu_read_sys_reg(vcpu, TTBR1_EL2) :
+ vcpu_read_sys_reg(vcpu, TTBR0_EL2));
+ u16 asid;
+
+ asid = FIELD_GET(TTBR_ASID_MASK, ttbr);
+ if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) ||
+ !(tcr & TCR_ASID16))
+ asid &= GENMASK(7, 0);
+
+ if (asid != vt->wr.asid)
+ return;
+ }
+
+ vt->cpu = smp_processor_id();
+
+ if (vt->wr.pw && vt->wr.pr)
+ prot = PAGE_KERNEL;
+ else if (vt->wr.pr)
+ prot = PAGE_KERNEL_RO;
+ else
+ prot = PAGE_NONE;
+
+ /*
+ * We can't map write-only (or no permission at all) in the kernel,
+ * but the guest can do it if using POE, so we'll have to turn a
+ * translation fault into a permission fault at runtime.
+ * FIXME: WO doesn't work at all, need POE support in the kernel.
+ */
+ if (pgprot_val(prot) != pgprot_val(PAGE_NONE)) {
+ __set_fixmap(vncr_fixmap(vt->cpu), vt->hpa, prot);
+ host_data_set_flag(L1_VNCR_MAPPED);
+ atomic_inc(&vcpu->kvm->arch.vncr_map_count);
+ }
+}
+
+/*
* Our emulated CPU doesn't support all the possible features. For the
* sake of simplicity (and probably mental sanity), wipe out a number
* of feature bits we don't intend to support for the time being.
@@ -1018,216 +1617,49 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
set_sysreg_masks(kvm, VMPIDR_EL2, res0, res1);
/* HCR_EL2 */
- res0 = BIT(48);
- res1 = HCR_RW;
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, TWED, IMP))
- res0 |= GENMASK(63, 59);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, MTE, MTE2))
- res0 |= (HCR_TID5 | HCR_DCT | HCR_ATA);
- if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, TTLBxS))
- res0 |= (HCR_TTLBIS | HCR_TTLBOS);
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
- !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
- res0 |= HCR_ENSCXT;
- if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, EVT, IMP))
- res0 |= (HCR_TOCU | HCR_TICAB | HCR_TID4);
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
- res0 |= HCR_AMVOFFEN;
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, V1P1))
- res0 |= HCR_FIEN;
- if (!kvm_has_feat(kvm, ID_AA64MMFR2_EL1, FWB, IMP))
- res0 |= HCR_FWB;
- /* Implementation choice: NV2 is the only supported config */
- if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
- res0 |= (HCR_NV2 | HCR_NV | HCR_AT);
- if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, NI))
- res0 |= HCR_NV1;
- if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
- kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
- res0 |= (HCR_API | HCR_APK);
- if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TME, IMP))
- res0 |= BIT(39);
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
- res0 |= (HCR_TEA | HCR_TERR);
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
- res0 |= HCR_TLOR;
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, VH, IMP))
- res0 |= HCR_E2H;
- if (!kvm_has_feat(kvm, ID_AA64MMFR4_EL1, E2H0, IMP))
- res1 |= HCR_E2H;
+ get_reg_fixed_bits(kvm, HCR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HCR_EL2, res0, res1);
/* HCRX_EL2 */
- res0 = HCRX_EL2_RES0;
- res1 = HCRX_EL2_RES1;
- if (!kvm_has_feat(kvm, ID_AA64ISAR3_EL1, PACM, TRIVIAL_IMP))
- res0 |= HCRX_EL2_PACMEn;
- if (!kvm_has_feat(kvm, ID_AA64PFR2_EL1, FPMR, IMP))
- res0 |= HCRX_EL2_EnFPM;
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
- res0 |= HCRX_EL2_GCSEn;
- if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, SYSREG_128, IMP))
- res0 |= HCRX_EL2_EnIDCP128;
- if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, ADERR, DEV_ASYNC))
- res0 |= (HCRX_EL2_EnSDERR | HCRX_EL2_EnSNERR);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, DF2, IMP))
- res0 |= HCRX_EL2_TMEA;
- if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, D128, IMP))
- res0 |= HCRX_EL2_D128En;
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
- res0 |= HCRX_EL2_PTTWI;
- if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, SCTLRX, IMP))
- res0 |= HCRX_EL2_SCTLR2En;
- if (!kvm_has_tcr2(kvm))
- res0 |= HCRX_EL2_TCR2En;
- if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, MOPS, IMP))
- res0 |= (HCRX_EL2_MSCEn | HCRX_EL2_MCE2);
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, CMOW, IMP))
- res0 |= HCRX_EL2_CMOW;
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, NMI, IMP))
- res0 |= (HCRX_EL2_VFNMI | HCRX_EL2_VINMI | HCRX_EL2_TALLINT);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP) ||
- !(read_sysreg_s(SYS_SMIDR_EL1) & SMIDR_EL1_SMPS))
- res0 |= HCRX_EL2_SMPME;
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, XS, IMP))
- res0 |= (HCRX_EL2_FGTnXS | HCRX_EL2_FnXS);
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_V))
- res0 |= HCRX_EL2_EnASR;
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64))
- res0 |= HCRX_EL2_EnALS;
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
- res0 |= HCRX_EL2_EnAS0;
+ get_reg_fixed_bits(kvm, HCRX_EL2, &res0, &res1);
set_sysreg_masks(kvm, HCRX_EL2, res0, res1);
/* HFG[RW]TR_EL2 */
- res0 = res1 = 0;
- if (!(kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_ADDRESS) &&
- kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC)))
- res0 |= (HFGxTR_EL2_APDAKey | HFGxTR_EL2_APDBKey |
- HFGxTR_EL2_APGAKey | HFGxTR_EL2_APIAKey |
- HFGxTR_EL2_APIBKey);
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP))
- res0 |= (HFGxTR_EL2_LORC_EL1 | HFGxTR_EL2_LOREA_EL1 |
- HFGxTR_EL2_LORID_EL1 | HFGxTR_EL2_LORN_EL1 |
- HFGxTR_EL2_LORSA_EL1);
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, CSV2, CSV2_2) &&
- !kvm_has_feat(kvm, ID_AA64PFR1_EL1, CSV2_frac, CSV2_1p2))
- res0 |= (HFGxTR_EL2_SCXTNUM_EL1 | HFGxTR_EL2_SCXTNUM_EL0);
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, GIC, IMP))
- res0 |= HFGxTR_EL2_ICC_IGRPENn_EL1;
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP))
- res0 |= (HFGxTR_EL2_ERRIDR_EL1 | HFGxTR_EL2_ERRSELR_EL1 |
- HFGxTR_EL2_ERXFR_EL1 | HFGxTR_EL2_ERXCTLR_EL1 |
- HFGxTR_EL2_ERXSTATUS_EL1 | HFGxTR_EL2_ERXMISCn_EL1 |
- HFGxTR_EL2_ERXPFGF_EL1 | HFGxTR_EL2_ERXPFGCTL_EL1 |
- HFGxTR_EL2_ERXPFGCDN_EL1 | HFGxTR_EL2_ERXADDR_EL1);
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, LS64, LS64_ACCDATA))
- res0 |= HFGxTR_EL2_nACCDATA_EL1;
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
- res0 |= (HFGxTR_EL2_nGCS_EL0 | HFGxTR_EL2_nGCS_EL1);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP))
- res0 |= (HFGxTR_EL2_nSMPRI_EL1 | HFGxTR_EL2_nTPIDR2_EL0);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, THE, IMP))
- res0 |= HFGxTR_EL2_nRCWMASK_EL1;
- if (!kvm_has_s1pie(kvm))
- res0 |= (HFGxTR_EL2_nPIRE0_EL1 | HFGxTR_EL2_nPIR_EL1);
- if (!kvm_has_s1poe(kvm))
- res0 |= (HFGxTR_EL2_nPOR_EL0 | HFGxTR_EL2_nPOR_EL1);
- if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
- res0 |= HFGxTR_EL2_nS2POR_EL1;
- if (!kvm_has_feat(kvm, ID_AA64MMFR3_EL1, AIE, IMP))
- res0 |= (HFGxTR_EL2_nMAIR2_EL1 | HFGxTR_EL2_nAMAIR2_EL1);
- set_sysreg_masks(kvm, HFGRTR_EL2, res0 | __HFGRTR_EL2_RES0, res1);
- set_sysreg_masks(kvm, HFGWTR_EL2, res0 | __HFGWTR_EL2_RES0, res1);
+ get_reg_fixed_bits(kvm, HFGRTR_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HFGRTR_EL2, res0, res1);
+ get_reg_fixed_bits(kvm, HFGWTR_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HFGWTR_EL2, res0, res1);
/* HDFG[RW]TR_EL2 */
- res0 = res1 = 0;
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP))
- res0 |= HDFGRTR_EL2_OSDLR_EL1;
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
- res0 |= (HDFGRTR_EL2_PMEVCNTRn_EL0 | HDFGRTR_EL2_PMEVTYPERn_EL0 |
- HDFGRTR_EL2_PMCCFILTR_EL0 | HDFGRTR_EL2_PMCCNTR_EL0 |
- HDFGRTR_EL2_PMCNTEN | HDFGRTR_EL2_PMINTEN |
- HDFGRTR_EL2_PMOVS | HDFGRTR_EL2_PMSELR_EL0 |
- HDFGRTR_EL2_PMMIR_EL1 | HDFGRTR_EL2_PMUSERENR_EL0 |
- HDFGRTR_EL2_PMCEIDn_EL0);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP))
- res0 |= (HDFGRTR_EL2_PMBLIMITR_EL1 | HDFGRTR_EL2_PMBPTR_EL1 |
- HDFGRTR_EL2_PMBSR_EL1 | HDFGRTR_EL2_PMSCR_EL1 |
- HDFGRTR_EL2_PMSEVFR_EL1 | HDFGRTR_EL2_PMSFCR_EL1 |
- HDFGRTR_EL2_PMSICR_EL1 | HDFGRTR_EL2_PMSIDR_EL1 |
- HDFGRTR_EL2_PMSIRR_EL1 | HDFGRTR_EL2_PMSLATFR_EL1 |
- HDFGRTR_EL2_PMBIDR_EL1);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
- res0 |= (HDFGRTR_EL2_TRC | HDFGRTR_EL2_TRCAUTHSTATUS |
- HDFGRTR_EL2_TRCAUXCTLR | HDFGRTR_EL2_TRCCLAIM |
- HDFGRTR_EL2_TRCCNTVRn | HDFGRTR_EL2_TRCID |
- HDFGRTR_EL2_TRCIMSPECn | HDFGRTR_EL2_TRCOSLSR |
- HDFGRTR_EL2_TRCPRGCTLR | HDFGRTR_EL2_TRCSEQSTR |
- HDFGRTR_EL2_TRCSSCSRn | HDFGRTR_EL2_TRCSTATR |
- HDFGRTR_EL2_TRCVICTLR);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP))
- res0 |= (HDFGRTR_EL2_TRBBASER_EL1 | HDFGRTR_EL2_TRBIDR_EL1 |
- HDFGRTR_EL2_TRBLIMITR_EL1 | HDFGRTR_EL2_TRBMAR_EL1 |
- HDFGRTR_EL2_TRBPTR_EL1 | HDFGRTR_EL2_TRBSR_EL1 |
- HDFGRTR_EL2_TRBTRG_EL1);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
- res0 |= (HDFGRTR_EL2_nBRBIDR | HDFGRTR_EL2_nBRBCTL |
- HDFGRTR_EL2_nBRBDATA);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, V1P2))
- res0 |= HDFGRTR_EL2_nPMSNEVFR_EL1;
- set_sysreg_masks(kvm, HDFGRTR_EL2, res0 | HDFGRTR_EL2_RES0, res1);
-
- /* Reuse the bits from the read-side and add the write-specific stuff */
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP))
- res0 |= (HDFGWTR_EL2_PMCR_EL0 | HDFGWTR_EL2_PMSWINC_EL0);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceVer, IMP))
- res0 |= HDFGWTR_EL2_TRCOSLAR;
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP))
- res0 |= HDFGWTR_EL2_TRFCR_EL1;
- set_sysreg_masks(kvm, HFGWTR_EL2, res0 | HDFGWTR_EL2_RES0, res1);
+ get_reg_fixed_bits(kvm, HDFGRTR_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HDFGRTR_EL2, res0, res1);
+ get_reg_fixed_bits(kvm, HDFGWTR_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HDFGWTR_EL2, res0, res1);
/* HFGITR_EL2 */
- res0 = HFGITR_EL2_RES0;
- res1 = HFGITR_EL2_RES1;
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, DPB, DPB2))
- res0 |= HFGITR_EL2_DCCVADP;
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2))
- res0 |= (HFGITR_EL2_ATS1E1RP | HFGITR_EL2_ATS1E1WP);
- if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
- res0 |= (HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
- HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS |
- HFGITR_EL2_TLBIVAALE1OS | HFGITR_EL2_TLBIVALE1OS |
- HFGITR_EL2_TLBIVAAE1OS | HFGITR_EL2_TLBIASIDE1OS |
- HFGITR_EL2_TLBIVAE1OS | HFGITR_EL2_TLBIVMALLE1OS);
- if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
- res0 |= (HFGITR_EL2_TLBIRVAALE1 | HFGITR_EL2_TLBIRVALE1 |
- HFGITR_EL2_TLBIRVAAE1 | HFGITR_EL2_TLBIRVAE1 |
- HFGITR_EL2_TLBIRVAALE1IS | HFGITR_EL2_TLBIRVALE1IS |
- HFGITR_EL2_TLBIRVAAE1IS | HFGITR_EL2_TLBIRVAE1IS |
- HFGITR_EL2_TLBIRVAALE1OS | HFGITR_EL2_TLBIRVALE1OS |
- HFGITR_EL2_TLBIRVAAE1OS | HFGITR_EL2_TLBIRVAE1OS);
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, IMP))
- res0 |= (HFGITR_EL2_CFPRCTX | HFGITR_EL2_DVPRCTX |
- HFGITR_EL2_CPPRCTX);
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP))
- res0 |= (HFGITR_EL2_nBRBINJ | HFGITR_EL2_nBRBIALL);
- if (!kvm_has_feat(kvm, ID_AA64PFR1_EL1, GCS, IMP))
- res0 |= (HFGITR_EL2_nGCSPUSHM_EL1 | HFGITR_EL2_nGCSSTR_EL1 |
- HFGITR_EL2_nGCSEPP);
- if (!kvm_has_feat(kvm, ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX))
- res0 |= HFGITR_EL2_COSPRCTX;
- if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP))
- res0 |= HFGITR_EL2_ATS1E1A;
+ get_reg_fixed_bits(kvm, HFGITR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HFGITR_EL2, res0, res1);
/* HAFGRTR_EL2 - not a lot to see here */
- res0 = HAFGRTR_EL2_RES0;
- res1 = HAFGRTR_EL2_RES1;
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, V1P1))
- res0 |= ~(res0 | res1);
+ get_reg_fixed_bits(kvm, HAFGRTR_EL2, &res0, &res1);
set_sysreg_masks(kvm, HAFGRTR_EL2, res0, res1);
+ /* HFG[RW]TR2_EL2 */
+ get_reg_fixed_bits(kvm, HFGRTR2_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HFGRTR2_EL2, res0, res1);
+ get_reg_fixed_bits(kvm, HFGWTR2_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HFGWTR2_EL2, res0, res1);
+
+ /* HDFG[RW]TR2_EL2 */
+ get_reg_fixed_bits(kvm, HDFGRTR2_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HDFGRTR2_EL2, res0, res1);
+ get_reg_fixed_bits(kvm, HDFGWTR2_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HDFGWTR2_EL2, res0, res1);
+
+ /* HFGITR2_EL2 */
+ get_reg_fixed_bits(kvm, HFGITR2_EL2, &res0, &res1);
+ set_sysreg_masks(kvm, HFGITR2_EL2, res0, res1);
+
/* TCR2_EL2 */
res0 = TCR2_EL2_RES0;
res1 = TCR2_EL2_RES1;
@@ -1318,6 +1750,9 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
res0 |= ICH_HCR_EL2_DVIM | ICH_HCR_EL2_vSGIEOICount;
set_sysreg_masks(kvm, ICH_HCR_EL2, res0, res1);
+ /* VNCR_EL2 */
+ set_sysreg_masks(kvm, VNCR_EL2, VNCR_EL2_RES0, VNCR_EL2_RES1);
+
out:
for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
(void)__vcpu_sys_reg(vcpu, sr);
@@ -1338,6 +1773,9 @@ void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
write_unlock(&vcpu->kvm->mmu_lock);
}
+ if (kvm_check_request(KVM_REQ_MAP_L1_VNCR_EL2, vcpu))
+ kvm_map_l1_vncr(vcpu);
+
/* Must be last, as may switch context! */
if (kvm_check_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu))
kvm_inject_nested_irq(vcpu);
diff --git a/arch/arm64/kvm/pkvm.c b/arch/arm64/kvm/pkvm.c
index 0f89157d31fd..fcd70bfe44fb 100644
--- a/arch/arm64/kvm/pkvm.c
+++ b/arch/arm64/kvm/pkvm.c
@@ -5,12 +5,12 @@
*/
#include <linux/init.h>
+#include <linux/interval_tree_generic.h>
#include <linux/kmemleak.h>
#include <linux/kvm_host.h>
#include <asm/kvm_mmu.h>
#include <linux/memblock.h>
#include <linux/mutex.h>
-#include <linux/sort.h>
#include <asm/kvm_pkvm.h>
@@ -24,23 +24,6 @@ static unsigned int *hyp_memblock_nr_ptr = &kvm_nvhe_sym(hyp_memblock_nr);
phys_addr_t hyp_mem_base;
phys_addr_t hyp_mem_size;
-static int cmp_hyp_memblock(const void *p1, const void *p2)
-{
- const struct memblock_region *r1 = p1;
- const struct memblock_region *r2 = p2;
-
- return r1->base < r2->base ? -1 : (r1->base > r2->base);
-}
-
-static void __init sort_memblock_regions(void)
-{
- sort(hyp_memory,
- *hyp_memblock_nr_ptr,
- sizeof(struct memblock_region),
- cmp_hyp_memblock,
- NULL);
-}
-
static int __init register_memblock_regions(void)
{
struct memblock_region *reg;
@@ -52,7 +35,6 @@ static int __init register_memblock_regions(void)
hyp_memory[*hyp_memblock_nr_ptr] = *reg;
(*hyp_memblock_nr_ptr)++;
}
- sort_memblock_regions();
return 0;
}
@@ -79,6 +61,7 @@ void __init kvm_hyp_reserve(void)
hyp_mem_pages += host_s2_pgtable_pages();
hyp_mem_pages += hyp_vm_table_pages();
hyp_mem_pages += hyp_vmemmap_pages(STRUCT_HYP_PAGE_SIZE);
+ hyp_mem_pages += pkvm_selftest_pages();
hyp_mem_pages += hyp_ffa_proxy_pages();
/*
@@ -262,6 +245,7 @@ static int __init finalize_pkvm(void)
* at, which would end badly once inaccessible.
*/
kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
+ kmemleak_free_part(__hyp_data_start, __hyp_data_end - __hyp_data_start);
kmemleak_free_part(__hyp_rodata_start, __hyp_rodata_end - __hyp_rodata_start);
kmemleak_free_part_phys(hyp_mem_base, hyp_mem_size);
@@ -273,80 +257,68 @@ static int __init finalize_pkvm(void)
}
device_initcall_sync(finalize_pkvm);
-static int cmp_mappings(struct rb_node *node, const struct rb_node *parent)
+static u64 __pkvm_mapping_start(struct pkvm_mapping *m)
{
- struct pkvm_mapping *a = rb_entry(node, struct pkvm_mapping, node);
- struct pkvm_mapping *b = rb_entry(parent, struct pkvm_mapping, node);
-
- if (a->gfn < b->gfn)
- return -1;
- if (a->gfn > b->gfn)
- return 1;
- return 0;
+ return m->gfn * PAGE_SIZE;
}
-static struct rb_node *find_first_mapping_node(struct rb_root *root, u64 gfn)
+static u64 __pkvm_mapping_end(struct pkvm_mapping *m)
{
- struct rb_node *node = root->rb_node, *prev = NULL;
- struct pkvm_mapping *mapping;
-
- while (node) {
- mapping = rb_entry(node, struct pkvm_mapping, node);
- if (mapping->gfn == gfn)
- return node;
- prev = node;
- node = (gfn < mapping->gfn) ? node->rb_left : node->rb_right;
- }
-
- return prev;
+ return (m->gfn + m->nr_pages) * PAGE_SIZE - 1;
}
+INTERVAL_TREE_DEFINE(struct pkvm_mapping, node, u64, __subtree_last,
+ __pkvm_mapping_start, __pkvm_mapping_end, static,
+ pkvm_mapping);
+
/*
- * __tmp is updated to rb_next(__tmp) *before* entering the body of the loop to allow freeing
- * of __map inline.
+ * __tmp is updated to iter_first(pkvm_mappings) *before* entering the body of the loop to allow
+ * freeing of __map inline.
*/
#define for_each_mapping_in_range_safe(__pgt, __start, __end, __map) \
- for (struct rb_node *__tmp = find_first_mapping_node(&(__pgt)->pkvm_mappings, \
- ((__start) >> PAGE_SHIFT)); \
+ for (struct pkvm_mapping *__tmp = pkvm_mapping_iter_first(&(__pgt)->pkvm_mappings, \
+ __start, __end - 1); \
__tmp && ({ \
- __map = rb_entry(__tmp, struct pkvm_mapping, node); \
- __tmp = rb_next(__tmp); \
+ __map = __tmp; \
+ __tmp = pkvm_mapping_iter_next(__map, __start, __end - 1); \
true; \
}); \
- ) \
- if (__map->gfn < ((__start) >> PAGE_SHIFT)) \
- continue; \
- else if (__map->gfn >= ((__end) >> PAGE_SHIFT)) \
- break; \
- else
+ )
int pkvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu,
struct kvm_pgtable_mm_ops *mm_ops)
{
- pgt->pkvm_mappings = RB_ROOT;
+ pgt->pkvm_mappings = RB_ROOT_CACHED;
pgt->mmu = mmu;
return 0;
}
-void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+static int __pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 start, u64 end)
{
struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
pkvm_handle_t handle = kvm->arch.pkvm.handle;
struct pkvm_mapping *mapping;
- struct rb_node *node;
+ int ret;
if (!handle)
- return;
+ return 0;
- node = rb_first(&pgt->pkvm_mappings);
- while (node) {
- mapping = rb_entry(node, struct pkvm_mapping, node);
- kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
- node = rb_next(node);
- rb_erase(&mapping->node, &pgt->pkvm_mappings);
+ for_each_mapping_in_range_safe(pgt, start, end, mapping) {
+ ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn,
+ mapping->nr_pages);
+ if (WARN_ON(ret))
+ return ret;
+ pkvm_mapping_remove(mapping, &pgt->pkvm_mappings);
kfree(mapping);
}
+
+ return 0;
+}
+
+void pkvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
+{
+ __pkvm_pgtable_stage2_unmap(pgt, 0, ~(0ULL));
}
int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
@@ -360,42 +332,46 @@ int pkvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
u64 pfn = phys >> PAGE_SHIFT;
int ret;
- if (size != PAGE_SIZE)
+ if (size != PAGE_SIZE && size != PMD_SIZE)
return -EINVAL;
lockdep_assert_held_write(&kvm->mmu_lock);
- ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, prot);
- if (ret) {
- /* Is the gfn already mapped due to a racing vCPU? */
- if (ret == -EPERM)
+
+ /*
+ * Calling stage2_map() on top of existing mappings is either happening because of a race
+ * with another vCPU, or because we're changing between page and block mappings. As per
+ * user_mem_abort(), same-size permission faults are handled in the relax_perms() path.
+ */
+ mapping = pkvm_mapping_iter_first(&pgt->pkvm_mappings, addr, addr + size - 1);
+ if (mapping) {
+ if (size == (mapping->nr_pages * PAGE_SIZE))
return -EAGAIN;
+
+ /* Remove _any_ pkvm_mapping overlapping with the range, bigger or smaller. */
+ ret = __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
+ if (ret)
+ return ret;
+ mapping = NULL;
}
+ ret = kvm_call_hyp_nvhe(__pkvm_host_share_guest, pfn, gfn, size / PAGE_SIZE, prot);
+ if (WARN_ON(ret))
+ return ret;
+
swap(mapping, cache->mapping);
mapping->gfn = gfn;
mapping->pfn = pfn;
- WARN_ON(rb_find_add(&mapping->node, &pgt->pkvm_mappings, cmp_mappings));
+ mapping->nr_pages = size / PAGE_SIZE;
+ pkvm_mapping_insert(mapping, &pgt->pkvm_mappings);
return ret;
}
int pkvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
{
- struct kvm *kvm = kvm_s2_mmu_to_kvm(pgt->mmu);
- pkvm_handle_t handle = kvm->arch.pkvm.handle;
- struct pkvm_mapping *mapping;
- int ret = 0;
-
- lockdep_assert_held_write(&kvm->mmu_lock);
- for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
- ret = kvm_call_hyp_nvhe(__pkvm_host_unshare_guest, handle, mapping->gfn);
- if (WARN_ON(ret))
- break;
- rb_erase(&mapping->node, &pgt->pkvm_mappings);
- kfree(mapping);
- }
+ lockdep_assert_held_write(&kvm_s2_mmu_to_kvm(pgt->mmu)->mmu_lock);
- return ret;
+ return __pkvm_pgtable_stage2_unmap(pgt, addr, addr + size);
}
int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
@@ -407,7 +383,8 @@ int pkvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size)
lockdep_assert_held(&kvm->mmu_lock);
for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping) {
- ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn);
+ ret = kvm_call_hyp_nvhe(__pkvm_host_wrprotect_guest, handle, mapping->gfn,
+ mapping->nr_pages);
if (WARN_ON(ret))
break;
}
@@ -422,7 +399,8 @@ int pkvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
lockdep_assert_held(&kvm->mmu_lock);
for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
- __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn), PAGE_SIZE);
+ __clean_dcache_guest_page(pfn_to_kaddr(mapping->pfn),
+ PAGE_SIZE * mapping->nr_pages);
return 0;
}
@@ -437,7 +415,7 @@ bool pkvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64
lockdep_assert_held(&kvm->mmu_lock);
for_each_mapping_in_range_safe(pgt, addr, addr + size, mapping)
young |= kvm_call_hyp_nvhe(__pkvm_host_test_clear_young_guest, handle, mapping->gfn,
- mkold);
+ mapping->nr_pages, mkold);
return young;
}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index a1bc10d7116a..25c29107f13f 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -280,7 +280,7 @@ static u64 kvm_pmu_hyp_counter_mask(struct kvm_vcpu *vcpu)
return 0;
hpmn = SYS_FIELD_GET(MDCR_EL2, HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
- n = vcpu->kvm->arch.pmcr_n;
+ n = vcpu->kvm->arch.nr_pmu_counters;
/*
* Programming HPMN to a value greater than PMCR_EL0.N is
@@ -608,14 +608,12 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
if (val & ARMV8_PMU_PMCR_P) {
- /*
- * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply
- * to the 'guest' range of counters and never the 'hyp' range.
- */
unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) &
- ~kvm_pmu_hyp_counter_mask(vcpu) &
~BIT(ARMV8_PMU_CYCLE_IDX);
+ if (!vcpu_is_el2(vcpu))
+ mask &= ~kvm_pmu_hyp_counter_mask(vcpu);
+
for_each_set_bit(i, &mask, 32)
kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true);
}
@@ -1027,12 +1025,30 @@ u8 kvm_arm_pmu_get_max_counters(struct kvm *kvm)
return bitmap_weight(arm_pmu->cntr_mask, ARMV8_PMU_MAX_GENERAL_COUNTERS);
}
+static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr)
+{
+ kvm->arch.nr_pmu_counters = nr;
+
+ /* Reset MDCR_EL2.HPMN behind the vcpus' back... */
+ if (test_bit(KVM_ARM_VCPU_HAS_EL2, kvm->arch.vcpu_features)) {
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
+ val &= ~MDCR_EL2_HPMN;
+ val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
+ __vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+ }
+ }
+}
+
static void kvm_arm_set_pmu(struct kvm *kvm, struct arm_pmu *arm_pmu)
{
lockdep_assert_held(&kvm->arch.config_lock);
kvm->arch.arm_pmu = arm_pmu;
- kvm->arch.pmcr_n = kvm_arm_pmu_get_max_counters(kvm);
+ kvm_arm_set_nr_counters(kvm, kvm_arm_pmu_get_max_counters(kvm));
}
/**
@@ -1088,6 +1104,20 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id)
return ret;
}
+static int kvm_arm_pmu_v3_set_nr_counters(struct kvm_vcpu *vcpu, unsigned int n)
+{
+ struct kvm *kvm = vcpu->kvm;
+
+ if (!kvm->arch.arm_pmu)
+ return -EINVAL;
+
+ if (n > kvm_arm_pmu_get_max_counters(kvm))
+ return -EINVAL;
+
+ kvm_arm_set_nr_counters(kvm, n);
+ return 0;
+}
+
int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
struct kvm *kvm = vcpu->kvm;
@@ -1184,6 +1214,15 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
return kvm_arm_pmu_v3_set_pmu(vcpu, pmu_id);
}
+ case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS: {
+ unsigned int __user *uaddr = (unsigned int __user *)(long)attr->addr;
+ unsigned int n;
+
+ if (get_user(n, uaddr))
+ return -EFAULT;
+
+ return kvm_arm_pmu_v3_set_nr_counters(vcpu, n);
+ }
case KVM_ARM_VCPU_PMU_V3_INIT:
return kvm_arm_pmu_v3_init(vcpu);
}
@@ -1222,6 +1261,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
case KVM_ARM_VCPU_PMU_V3_INIT:
case KVM_ARM_VCPU_PMU_V3_FILTER:
case KVM_ARM_VCPU_PMU_V3_SET_PMU:
+ case KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS:
if (kvm_vcpu_has_pmu(vcpu))
return 0;
}
@@ -1260,8 +1300,12 @@ u8 kvm_arm_pmu_get_pmuver_limit(void)
u64 kvm_vcpu_read_pmcr(struct kvm_vcpu *vcpu)
{
u64 pmcr = __vcpu_sys_reg(vcpu, PMCR_EL0);
+ u64 n = vcpu->kvm->arch.nr_pmu_counters;
+
+ if (vcpu_has_nv(vcpu) && !vcpu_is_el2(vcpu))
+ n = FIELD_GET(MDCR_EL2_HPMN, __vcpu_sys_reg(vcpu, MDCR_EL2));
- return u64_replace_bits(pmcr, vcpu->kvm->arch.pmcr_n, ARMV8_PMU_PMCR_N);
+ return u64_replace_bits(pmcr, n, ARMV8_PMU_PMCR_N);
}
void kvm_pmu_nested_transition(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f82fcc614e13..959532422d3a 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -158,6 +158,8 @@ void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu)
if (sve_state)
kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu));
kfree(sve_state);
+ free_page((unsigned long)vcpu->arch.ctxt.vncr_array);
+ kfree(vcpu->arch.vncr_tlb);
kfree(vcpu->arch.ccsidr);
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 5dde9285afc8..a6cf2888d150 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -785,7 +785,7 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 mask = BIT(ARMV8_PMU_CYCLE_IDX);
- u8 n = vcpu->kvm->arch.pmcr_n;
+ u8 n = vcpu->kvm->arch.nr_pmu_counters;
if (n)
mask |= GENMASK(n - 1, 0);
@@ -1216,8 +1216,9 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
* with the existing KVM behavior.
*/
if (!kvm_vm_has_ran_once(kvm) &&
+ !vcpu_has_nv(vcpu) &&
new_n <= kvm_arm_pmu_get_max_counters(kvm))
- kvm->arch.pmcr_n = new_n;
+ kvm->arch.nr_pmu_counters = new_n;
mutex_unlock(&kvm->arch.config_lock);
@@ -1600,13 +1601,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
val = sanitise_id_aa64pfr0_el1(vcpu, val);
break;
case SYS_ID_AA64PFR1_EL1:
- if (!kvm_has_mte(vcpu->kvm))
+ if (!kvm_has_mte(vcpu->kvm)) {
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
+ }
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);
@@ -1959,11 +1961,34 @@ static int set_id_aa64pfr1_el1(struct kvm_vcpu *vcpu,
{
u64 hw_val = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
u64 mpam_mask = ID_AA64PFR1_EL1_MPAM_frac_MASK;
+ u8 mte = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE, hw_val);
+ u8 user_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, user_val);
+ u8 hw_mte_frac = SYS_FIELD_GET(ID_AA64PFR1_EL1, MTE_frac, hw_val);
/* See set_id_aa64pfr0_el1 for comment about MPAM */
if ((hw_val & mpam_mask) == (user_val & mpam_mask))
user_val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK;
+ /*
+ * Previously MTE_frac was hidden from guest. However, if the
+ * hardware supports MTE2 but not MTE_ASYM_FAULT then a value
+ * of 0 for this field indicates that the hardware supports
+ * MTE_ASYNC. Whereas, 0xf indicates MTE_ASYNC is not supported.
+ *
+ * As KVM must accept values from KVM provided by user-space,
+ * when ID_AA64PFR1_EL1.MTE is 2 allow user-space to set
+ * ID_AA64PFR1_EL1.MTE_frac to 0. However, ignore it to avoid
+ * incorrectly claiming hardware support for MTE_ASYNC in the
+ * guest.
+ */
+
+ if (mte == ID_AA64PFR1_EL1_MTE_MTE2 &&
+ hw_mte_frac == ID_AA64PFR1_EL1_MTE_frac_NI &&
+ user_mte_frac == ID_AA64PFR1_EL1_MTE_frac_ASYNC) {
+ user_val &= ~ID_AA64PFR1_EL1_MTE_frac_MASK;
+ user_val |= hw_val & ID_AA64PFR1_EL1_MTE_frac_MASK;
+ }
+
return set_id_reg(vcpu, rd, user_val);
}
@@ -2287,15 +2312,6 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
"trap of EL2 register redirected to EL1");
}
-#define EL2_REG(name, acc, rst, v) { \
- SYS_DESC(SYS_##name), \
- .access = acc, \
- .reset = rst, \
- .reg = name, \
- .visibility = el2_visibility, \
- .val = v, \
-}
-
#define EL2_REG_FILTERED(name, acc, rst, v, filter) { \
SYS_DESC(SYS_##name), \
.access = acc, \
@@ -2305,6 +2321,9 @@ static bool bad_redir_trap(struct kvm_vcpu *vcpu,
.val = v, \
}
+#define EL2_REG(name, acc, rst, v) \
+ EL2_REG_FILTERED(name, acc, rst, v, el2_visibility)
+
#define EL2_REG_VNCR(name, rst, v) EL2_REG(name, bad_vncr_trap, rst, v)
#define EL2_REG_REDIR(name, rst, v) EL2_REG(name, bad_redir_trap, rst, v)
@@ -2452,6 +2471,16 @@ static unsigned int sve_el2_visibility(const struct kvm_vcpu *vcpu,
return __el2_visibility(vcpu, rd, sve_visibility);
}
+static unsigned int vncr_el2_visibility(const struct kvm_vcpu *vcpu,
+ const struct sys_reg_desc *rd)
+{
+ if (el2_visibility(vcpu, rd) == 0 &&
+ kvm_has_feat(vcpu->kvm, ID_AA64MMFR4_EL1, NV_frac, NV2_ONLY))
+ return 0;
+
+ return REG_HIDDEN;
+}
+
static bool access_zcr_el2(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
@@ -2576,16 +2605,33 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
- u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2);
+ u64 hpmn, val, old = __vcpu_sys_reg(vcpu, MDCR_EL2);
- if (!access_rw(vcpu, p, r))
- return false;
+ if (!p->is_write) {
+ p->regval = old;
+ return true;
+ }
+
+ val = p->regval;
+ hpmn = FIELD_GET(MDCR_EL2_HPMN, val);
+
+ /*
+ * If HPMN is out of bounds, limit it to what we actually
+ * support. This matches the UNKNOWN definition of the field
+ * in that case, and keeps the emulation simple. Sort of.
+ */
+ if (hpmn > vcpu->kvm->arch.nr_pmu_counters) {
+ hpmn = vcpu->kvm->arch.nr_pmu_counters;
+ u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
+ }
+
+ __vcpu_sys_reg(vcpu, MDCR_EL2) = val;
/*
- * Request a reload of the PMU to enable/disable the counters affected
- * by HPME.
+ * Request a reload of the PMU to enable/disable the counters
+ * affected by HPME.
*/
- if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME)
+ if ((old ^ val) & MDCR_EL2_HPME)
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
return true;
@@ -2704,6 +2750,12 @@ static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
.set_user = set_imp_id_reg, \
.reset = reset_imp_id_reg, \
.val = mask, \
+ }
+
+static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ __vcpu_sys_reg(vcpu, r->reg) = vcpu->kvm->arch.nr_pmu_counters;
+ return vcpu->kvm->arch.nr_pmu_counters;
}
/*
@@ -3249,7 +3301,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1),
EL2_REG(ACTLR_EL2, access_rw, reset_val, 0),
EL2_REG_VNCR(HCR_EL2, reset_hcr, 0),
- EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0),
+ EL2_REG(MDCR_EL2, access_mdcr, reset_mdcr, 0),
EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1),
EL2_REG_VNCR(HSTR_EL2, reset_val, 0),
EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0),
@@ -3269,6 +3321,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
tcr2_el2_visibility),
EL2_REG_VNCR(VTTBR_EL2, reset_val, 0),
EL2_REG_VNCR(VTCR_EL2, reset_val, 0),
+ EL2_REG_FILTERED(VNCR_EL2, bad_vncr_trap, reset_val, 0,
+ vncr_el2_visibility),
{ SYS_DESC(SYS_DACR32_EL2), undef_access, reset_unknown, DACR32_EL2 },
EL2_REG_VNCR(HDFGRTR_EL2, reset_val, 0),
@@ -3552,8 +3606,7 @@ static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
{
u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
- u64 base, range, tg, num, scale;
- int shift;
+ u64 base, range;
if (!kvm_supported_tlbi_ipas2_op(vcpu, sys_encoding))
return undef_access(vcpu, p, r);
@@ -3563,26 +3616,7 @@ static bool handle_ripas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
* of the guest's S2 (different base granule size, for example), we
* decide to ignore TTL and only use the described range.
*/
- tg = FIELD_GET(GENMASK(47, 46), p->regval);
- scale = FIELD_GET(GENMASK(45, 44), p->regval);
- num = FIELD_GET(GENMASK(43, 39), p->regval);
- base = p->regval & GENMASK(36, 0);
-
- switch(tg) {
- case 1:
- shift = 12;
- break;
- case 2:
- shift = 14;
- break;
- case 3:
- default: /* IMPDEF: handle tg==0 as 64k */
- shift = 16;
- break;
- }
-
- base <<= shift;
- range = __TLBI_RANGE_PAGES(num, scale) << shift;
+ base = decode_range_tlbi(p->regval, &range, NULL);
kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
&(union tlbi_info) {
@@ -3648,11 +3682,22 @@ static void s2_mmu_tlbi_s1e1(struct kvm_s2_mmu *mmu,
WARN_ON(__kvm_tlbi_s1e2(mmu, info->va.addr, info->va.encoding));
}
+static bool handle_tlbi_el2(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
+
+ if (!kvm_supported_tlbi_s1e2_op(vcpu, sys_encoding))
+ return undef_access(vcpu, p, r);
+
+ kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval);
+ return true;
+}
+
static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
u32 sys_encoding = sys_insn(p->Op0, p->Op1, p->CRn, p->CRm, p->Op2);
- u64 vttbr = vcpu_read_sys_reg(vcpu, VTTBR_EL2);
/*
* If we're here, this is because we've trapped on a EL1 TLBI
@@ -3663,6 +3708,13 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
* - HCR_EL2.E2H == 0 : a non-VHE guest
* - HCR_EL2.{E2H,TGE} == { 1, 0 } : a VHE guest in guest mode
*
+ * Another possibility is that we are invalidating the EL2 context
+ * using EL1 instructions, but that we landed here because we need
+ * additional invalidation for structures that are not held in the
+ * CPU TLBs (such as the VNCR pseudo-TLB and its EL2 mapping). In
+ * that case, we are guaranteed that HCR_EL2.{E2H,TGE} == { 1, 1 }
+ * as we don't allow an NV-capable L1 in a nVHE configuration.
+ *
* We don't expect these helpers to ever be called when running
* in a vEL1 context.
*/
@@ -3672,7 +3724,13 @@ static bool handle_tlbi_el1(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (!kvm_supported_tlbi_s1e1_op(vcpu, sys_encoding))
return undef_access(vcpu, p, r);
- kvm_s2_mmu_iterate_by_vmid(vcpu->kvm, get_vmid(vttbr),
+ if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) {
+ kvm_handle_s1e2_tlbi(vcpu, sys_encoding, p->regval);
+ return true;
+ }
+
+ kvm_s2_mmu_iterate_by_vmid(vcpu->kvm,
+ get_vmid(__vcpu_sys_reg(vcpu, VTTBR_EL2)),
&(union tlbi_info) {
.va = {
.addr = p->regval,
@@ -3794,16 +3852,21 @@ static struct sys_reg_desc sys_insn_descs[] = {
SYS_INSN(TLBI_IPAS2LE1IS, handle_ipas2e1is),
SYS_INSN(TLBI_RIPAS2LE1IS, handle_ripas2e1is),
- SYS_INSN(TLBI_ALLE2OS, undef_access),
- SYS_INSN(TLBI_VAE2OS, undef_access),
+ SYS_INSN(TLBI_ALLE2OS, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2OS, handle_tlbi_el2),
SYS_INSN(TLBI_ALLE1OS, handle_alle1is),
- SYS_INSN(TLBI_VALE2OS, undef_access),
+ SYS_INSN(TLBI_VALE2OS, handle_tlbi_el2),
SYS_INSN(TLBI_VMALLS12E1OS, handle_vmalls12e1is),
- SYS_INSN(TLBI_RVAE2IS, undef_access),
- SYS_INSN(TLBI_RVALE2IS, undef_access),
+ SYS_INSN(TLBI_RVAE2IS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2IS, handle_tlbi_el2),
+ SYS_INSN(TLBI_ALLE2IS, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2IS, handle_tlbi_el2),
SYS_INSN(TLBI_ALLE1IS, handle_alle1is),
+
+ SYS_INSN(TLBI_VALE2IS, handle_tlbi_el2),
+
SYS_INSN(TLBI_VMALLS12E1IS, handle_vmalls12e1is),
SYS_INSN(TLBI_IPAS2E1OS, handle_ipas2e1is),
SYS_INSN(TLBI_IPAS2E1, handle_ipas2e1is),
@@ -3813,11 +3876,17 @@ static struct sys_reg_desc sys_insn_descs[] = {
SYS_INSN(TLBI_IPAS2LE1, handle_ipas2e1is),
SYS_INSN(TLBI_RIPAS2LE1, handle_ripas2e1is),
SYS_INSN(TLBI_RIPAS2LE1OS, handle_ripas2e1is),
- SYS_INSN(TLBI_RVAE2OS, undef_access),
- SYS_INSN(TLBI_RVALE2OS, undef_access),
- SYS_INSN(TLBI_RVAE2, undef_access),
- SYS_INSN(TLBI_RVALE2, undef_access),
+ SYS_INSN(TLBI_RVAE2OS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2OS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVAE2, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2, handle_tlbi_el2),
+ SYS_INSN(TLBI_ALLE2, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2, handle_tlbi_el2),
+
SYS_INSN(TLBI_ALLE1, handle_alle1is),
+
+ SYS_INSN(TLBI_VALE2, handle_tlbi_el2),
+
SYS_INSN(TLBI_VMALLS12E1, handle_vmalls12e1is),
SYS_INSN(TLBI_IPAS2E1ISNXS, handle_ipas2e1is),
@@ -3825,19 +3894,19 @@ static struct sys_reg_desc sys_insn_descs[] = {
SYS_INSN(TLBI_IPAS2LE1ISNXS, handle_ipas2e1is),
SYS_INSN(TLBI_RIPAS2LE1ISNXS, handle_ripas2e1is),
- SYS_INSN(TLBI_ALLE2OSNXS, undef_access),
- SYS_INSN(TLBI_VAE2OSNXS, undef_access),
+ SYS_INSN(TLBI_ALLE2OSNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2OSNXS, handle_tlbi_el2),
SYS_INSN(TLBI_ALLE1OSNXS, handle_alle1is),
- SYS_INSN(TLBI_VALE2OSNXS, undef_access),
+ SYS_INSN(TLBI_VALE2OSNXS, handle_tlbi_el2),
SYS_INSN(TLBI_VMALLS12E1OSNXS, handle_vmalls12e1is),
- SYS_INSN(TLBI_RVAE2ISNXS, undef_access),
- SYS_INSN(TLBI_RVALE2ISNXS, undef_access),
- SYS_INSN(TLBI_ALLE2ISNXS, undef_access),
- SYS_INSN(TLBI_VAE2ISNXS, undef_access),
+ SYS_INSN(TLBI_RVAE2ISNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2ISNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_ALLE2ISNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2ISNXS, handle_tlbi_el2),
SYS_INSN(TLBI_ALLE1ISNXS, handle_alle1is),
- SYS_INSN(TLBI_VALE2ISNXS, undef_access),
+ SYS_INSN(TLBI_VALE2ISNXS, handle_tlbi_el2),
SYS_INSN(TLBI_VMALLS12E1ISNXS, handle_vmalls12e1is),
SYS_INSN(TLBI_IPAS2E1OSNXS, handle_ipas2e1is),
SYS_INSN(TLBI_IPAS2E1NXS, handle_ipas2e1is),
@@ -3847,14 +3916,14 @@ static struct sys_reg_desc sys_insn_descs[] = {
SYS_INSN(TLBI_IPAS2LE1NXS, handle_ipas2e1is),
SYS_INSN(TLBI_RIPAS2LE1NXS, handle_ripas2e1is),
SYS_INSN(TLBI_RIPAS2LE1OSNXS, handle_ripas2e1is),
- SYS_INSN(TLBI_RVAE2OSNXS, undef_access),
- SYS_INSN(TLBI_RVALE2OSNXS, undef_access),
- SYS_INSN(TLBI_RVAE2NXS, undef_access),
- SYS_INSN(TLBI_RVALE2NXS, undef_access),
- SYS_INSN(TLBI_ALLE2NXS, undef_access),
- SYS_INSN(TLBI_VAE2NXS, undef_access),
+ SYS_INSN(TLBI_RVAE2OSNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2OSNXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVAE2NXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_RVALE2NXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_ALLE2NXS, handle_tlbi_el2),
+ SYS_INSN(TLBI_VAE2NXS, handle_tlbi_el2),
SYS_INSN(TLBI_ALLE1NXS, handle_alle1is),
- SYS_INSN(TLBI_VALE2NXS, undef_access),
+ SYS_INSN(TLBI_VALE2NXS, handle_tlbi_el2),
SYS_INSN(TLBI_VMALLS12E1NXS, handle_vmalls12e1is),
};
@@ -5153,65 +5222,13 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu)
if (test_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags))
goto out;
- kvm->arch.fgu[HFGxTR_GROUP] = (HFGxTR_EL2_nAMAIR2_EL1 |
- HFGxTR_EL2_nMAIR2_EL1 |
- HFGxTR_EL2_nS2POR_EL1 |
- HFGxTR_EL2_nACCDATA_EL1 |
- HFGxTR_EL2_nSMPRI_EL1_MASK |
- HFGxTR_EL2_nTPIDR2_EL0_MASK);
-
- if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, OS))
- kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1OS|
- HFGITR_EL2_TLBIRVALE1OS |
- HFGITR_EL2_TLBIRVAAE1OS |
- HFGITR_EL2_TLBIRVAE1OS |
- HFGITR_EL2_TLBIVAALE1OS |
- HFGITR_EL2_TLBIVALE1OS |
- HFGITR_EL2_TLBIVAAE1OS |
- HFGITR_EL2_TLBIASIDE1OS |
- HFGITR_EL2_TLBIVAE1OS |
- HFGITR_EL2_TLBIVMALLE1OS);
-
- if (!kvm_has_feat(kvm, ID_AA64ISAR0_EL1, TLB, RANGE))
- kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_TLBIRVAALE1 |
- HFGITR_EL2_TLBIRVALE1 |
- HFGITR_EL2_TLBIRVAAE1 |
- HFGITR_EL2_TLBIRVAE1 |
- HFGITR_EL2_TLBIRVAALE1IS|
- HFGITR_EL2_TLBIRVALE1IS |
- HFGITR_EL2_TLBIRVAAE1IS |
- HFGITR_EL2_TLBIRVAE1IS |
- HFGITR_EL2_TLBIRVAALE1OS|
- HFGITR_EL2_TLBIRVALE1OS |
- HFGITR_EL2_TLBIRVAAE1OS |
- HFGITR_EL2_TLBIRVAE1OS);
-
- if (!kvm_has_feat(kvm, ID_AA64ISAR2_EL1, ATS1A, IMP))
- kvm->arch.fgu[HFGITR_GROUP] |= HFGITR_EL2_ATS1E1A;
-
- if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, PAN, PAN2))
- kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_ATS1E1RP |
- HFGITR_EL2_ATS1E1WP);
-
- if (!kvm_has_s1pie(kvm))
- kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPIRE0_EL1 |
- HFGxTR_EL2_nPIR_EL1);
-
- if (!kvm_has_s1poe(kvm))
- kvm->arch.fgu[HFGxTR_GROUP] |= (HFGxTR_EL2_nPOR_EL1 |
- HFGxTR_EL2_nPOR_EL0);
-
- if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP))
- kvm->arch.fgu[HAFGRTR_GROUP] |= ~(HAFGRTR_EL2_RES0 |
- HAFGRTR_EL2_RES1);
-
- if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, BRBE, IMP)) {
- kvm->arch.fgu[HDFGRTR_GROUP] |= (HDFGRTR_EL2_nBRBDATA |
- HDFGRTR_EL2_nBRBCTL |
- HDFGRTR_EL2_nBRBIDR);
- kvm->arch.fgu[HFGITR_GROUP] |= (HFGITR_EL2_nBRBINJ |
- HFGITR_EL2_nBRBIALL);
- }
+ compute_fgu(kvm, HFGRTR_GROUP);
+ compute_fgu(kvm, HFGITR_GROUP);
+ compute_fgu(kvm, HDFGRTR_GROUP);
+ compute_fgu(kvm, HAFGRTR_GROUP);
+ compute_fgu(kvm, HFGRTR2_GROUP);
+ compute_fgu(kvm, HFGITR2_GROUP);
+ compute_fgu(kvm, HDFGRTR2_GROUP);
set_bit(KVM_ARCH_FLAG_FGU_INITIALIZED, &kvm->arch.flags);
out:
@@ -5269,6 +5286,8 @@ int __init kvm_sys_reg_table_init(void)
ret = populate_nv_trap_config();
+ check_feature_map();
+
for (i = 0; !ret && i < ARRAY_SIZE(sys_reg_descs); i++)
ret = populate_sysreg_config(sys_reg_descs + i, i);
diff --git a/arch/arm64/kvm/trace_arm.h b/arch/arm64/kvm/trace_arm.h
index c18c1a95831e..9c60f6465c78 100644
--- a/arch/arm64/kvm/trace_arm.h
+++ b/arch/arm64/kvm/trace_arm.h
@@ -176,7 +176,7 @@ TRACE_EVENT(kvm_set_way_flush,
),
TP_printk("S/W flush at 0x%016lx (cache %s)",
- __entry->vcpu_pc, __entry->cache ? "on" : "off")
+ __entry->vcpu_pc, str_on_off(__entry->cache))
);
TRACE_EVENT(kvm_toggle_cache,
@@ -196,8 +196,8 @@ TRACE_EVENT(kvm_toggle_cache,
),
TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
- __entry->vcpu_pc, __entry->was ? "on" : "off",
- __entry->now ? "on" : "off")
+ __entry->vcpu_pc, str_on_off(__entry->was),
+ str_on_off(__entry->now))
);
/*
diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
index afb018528bc3..f8425f381de9 100644
--- a/arch/arm64/kvm/vgic/vgic-debug.c
+++ b/arch/arm64/kvm/vgic/vgic-debug.c
@@ -320,3 +320,227 @@ void vgic_debug_init(struct kvm *kvm)
void vgic_debug_destroy(struct kvm *kvm)
{
}
+
+/**
+ * struct vgic_its_iter - Iterator for traversing VGIC ITS device tables.
+ * @dev: Pointer to the current its_device being processed.
+ * @ite: Pointer to the current its_ite within the device being processed.
+ *
+ * This structure is used to maintain the current position during iteration
+ * over the ITS device tables. It holds pointers to both the current device
+ * and the current ITE within that device.
+ */
+struct vgic_its_iter {
+ struct its_device *dev;
+ struct its_ite *ite;
+};
+
+/**
+ * end_of_iter - Checks if the iterator has reached the end.
+ * @iter: The iterator to check.
+ *
+ * When the iterator completed processing the final ITE in the last device
+ * table, it was marked to indicate the end of iteration by setting its
+ * device and ITE pointers to NULL.
+ * This function checks whether the iterator was marked as end.
+ *
+ * Return: True if the iterator is marked as end, false otherwise.
+ */
+static inline bool end_of_iter(struct vgic_its_iter *iter)
+{
+ return !iter->dev && !iter->ite;
+}
+
+/**
+ * vgic_its_iter_next - Advances the iterator to the next entry in the ITS tables.
+ * @its: The VGIC ITS structure.
+ * @iter: The iterator to advance.
+ *
+ * This function moves the iterator to the next ITE within the current device,
+ * or to the first ITE of the next device if the current ITE is the last in
+ * the device. If the current device is the last device, the iterator is set
+ * to indicate the end of iteration.
+ */
+static void vgic_its_iter_next(struct vgic_its *its, struct vgic_its_iter *iter)
+{
+ struct its_device *dev = iter->dev;
+ struct its_ite *ite = iter->ite;
+
+ if (!ite || list_is_last(&ite->ite_list, &dev->itt_head)) {
+ if (list_is_last(&dev->dev_list, &its->device_list)) {
+ dev = NULL;
+ ite = NULL;
+ } else {
+ dev = list_next_entry(dev, dev_list);
+ ite = list_first_entry_or_null(&dev->itt_head,
+ struct its_ite,
+ ite_list);
+ }
+ } else {
+ ite = list_next_entry(ite, ite_list);
+ }
+
+ iter->dev = dev;
+ iter->ite = ite;
+}
+
+/**
+ * vgic_its_debug_start - Start function for the seq_file interface.
+ * @s: The seq_file structure.
+ * @pos: The starting position (offset).
+ *
+ * This function initializes the iterator to the beginning of the ITS tables
+ * and advances it to the specified position. It acquires the its_lock mutex
+ * to protect shared data.
+ *
+ * Return: An iterator pointer on success, NULL if no devices are found or
+ * the end of the list is reached, or ERR_PTR(-ENOMEM) on memory
+ * allocation failure.
+ */
+static void *vgic_its_debug_start(struct seq_file *s, loff_t *pos)
+{
+ struct vgic_its *its = s->private;
+ struct vgic_its_iter *iter;
+ struct its_device *dev;
+ loff_t offset = *pos;
+
+ mutex_lock(&its->its_lock);
+
+ dev = list_first_entry_or_null(&its->device_list,
+ struct its_device, dev_list);
+ if (!dev)
+ return NULL;
+
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+ if (!iter)
+ return ERR_PTR(-ENOMEM);
+
+ iter->dev = dev;
+ iter->ite = list_first_entry_or_null(&dev->itt_head,
+ struct its_ite, ite_list);
+
+ while (!end_of_iter(iter) && offset--)
+ vgic_its_iter_next(its, iter);
+
+ if (end_of_iter(iter)) {
+ kfree(iter);
+ return NULL;
+ }
+
+ return iter;
+}
+
+/**
+ * vgic_its_debug_next - Next function for the seq_file interface.
+ * @s: The seq_file structure.
+ * @v: The current iterator.
+ * @pos: The current position (offset).
+ *
+ * This function advances the iterator to the next entry and increments the
+ * position.
+ *
+ * Return: An iterator pointer on success, or NULL if the end of the list is
+ * reached.
+ */
+static void *vgic_its_debug_next(struct seq_file *s, void *v, loff_t *pos)
+{
+ struct vgic_its *its = s->private;
+ struct vgic_its_iter *iter = v;
+
+ ++*pos;
+ vgic_its_iter_next(its, iter);
+
+ if (end_of_iter(iter)) {
+ kfree(iter);
+ return NULL;
+ }
+ return iter;
+}
+
+/**
+ * vgic_its_debug_stop - Stop function for the seq_file interface.
+ * @s: The seq_file structure.
+ * @v: The current iterator.
+ *
+ * This function frees the iterator and releases the its_lock mutex.
+ */
+static void vgic_its_debug_stop(struct seq_file *s, void *v)
+{
+ struct vgic_its *its = s->private;
+ struct vgic_its_iter *iter = v;
+
+ if (!IS_ERR_OR_NULL(iter))
+ kfree(iter);
+ mutex_unlock(&its->its_lock);
+}
+
+/**
+ * vgic_its_debug_show - Show function for the seq_file interface.
+ * @s: The seq_file structure.
+ * @v: The current iterator.
+ *
+ * This function formats and prints the ITS table entry information to the
+ * seq_file output.
+ *
+ * Return: 0 on success.
+ */
+static int vgic_its_debug_show(struct seq_file *s, void *v)
+{
+ struct vgic_its_iter *iter = v;
+ struct its_device *dev = iter->dev;
+ struct its_ite *ite = iter->ite;
+
+ if (list_is_first(&ite->ite_list, &dev->itt_head)) {
+ seq_printf(s, "\n");
+ seq_printf(s, "Device ID: 0x%x, Event ID Range: [0 - %llu]\n",
+ dev->device_id, BIT_ULL(dev->num_eventid_bits) - 1);
+ seq_printf(s, "EVENT_ID INTID HWINTID TARGET COL_ID HW\n");
+ seq_printf(s, "-----------------------------------------------\n");
+ }
+
+ if (ite && ite->irq && ite->collection) {
+ seq_printf(s, "%8u %8u %8u %8u %8u %2d\n",
+ ite->event_id, ite->irq->intid, ite->irq->hwintid,
+ ite->collection->target_addr,
+ ite->collection->collection_id, ite->irq->hw);
+ }
+
+ return 0;
+}
+
+static const struct seq_operations vgic_its_debug_sops = {
+ .start = vgic_its_debug_start,
+ .next = vgic_its_debug_next,
+ .stop = vgic_its_debug_stop,
+ .show = vgic_its_debug_show
+};
+
+DEFINE_SEQ_ATTRIBUTE(vgic_its_debug);
+
+/**
+ * vgic_its_debug_init - Initializes the debugfs interface for VGIC ITS.
+ * @dev: The KVM device structure.
+ *
+ * This function creates a debugfs file named "vgic-its-state@%its_base"
+ * to expose the ITS table information.
+ *
+ * Return: 0 on success.
+ */
+int vgic_its_debug_init(struct kvm_device *dev)
+{
+ struct vgic_its *its = dev->private;
+ char *name;
+
+ name = kasprintf(GFP_KERNEL, "vgic-its-state@%llx", (u64)its->vgic_its_base);
+ if (!name)
+ return -ENOMEM;
+
+ debugfs_create_file(name, 0444, dev->kvm->debugfs_dentry, its, &vgic_its_debug_fops);
+
+ kfree(name);
+ return 0;
+}
+
+void vgic_its_debug_destroy(struct kvm_device *dev)
+{
+}
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index fb96802799c6..569f9da9049f 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -154,36 +154,6 @@ out_unlock:
return irq;
}
-struct its_device {
- struct list_head dev_list;
-
- /* the head for the list of ITTEs */
- struct list_head itt_head;
- u32 num_eventid_bits;
- gpa_t itt_addr;
- u32 device_id;
-};
-
-#define COLLECTION_NOT_MAPPED ((u32)~0)
-
-struct its_collection {
- struct list_head coll_list;
-
- u32 collection_id;
- u32 target_addr;
-};
-
-#define its_is_collection_mapped(coll) ((coll) && \
- ((coll)->target_addr != COLLECTION_NOT_MAPPED))
-
-struct its_ite {
- struct list_head ite_list;
-
- struct vgic_irq *irq;
- struct its_collection *collection;
- u32 event_id;
-};
-
/**
* struct vgic_its_abi - ITS abi ops and settings
* @cte_esz: collection table entry size
@@ -1938,6 +1908,8 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
mutex_lock(&its->its_lock);
+ vgic_its_debug_destroy(kvm_dev);
+
vgic_its_free_device_list(kvm, its);
vgic_its_free_collection_list(kvm, its);
vgic_its_invalidate_cache(its);
@@ -2771,7 +2743,12 @@ static int vgic_its_set_attr(struct kvm_device *dev,
if (ret)
return ret;
- return vgic_register_its_iodev(dev->kvm, its, addr);
+ ret = vgic_register_its_iodev(dev->kvm, its, addr);
+ if (ret)
+ return ret;
+
+ return vgic_its_debug_init(dev);
+
}
case KVM_DEV_ARM_VGIC_GRP_CTRL:
return vgic_its_ctrl(dev->kvm, its, attr->attr);
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index bfa5bde1f106..4f6954c30674 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -240,9 +240,6 @@ static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
goto next;
}
- /* It is illegal to have the EOI bit set with HW */
- lr &= ~ICH_LR_EOI;
-
/* Translate the virtual mapping to the real one */
lr &= ~ICH_LR_PHYS_ID_MASK;
lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 0c5a63712702..4349084cb9a6 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -172,6 +172,36 @@ struct vgic_reg_attr {
gpa_t addr;
};
+struct its_device {
+ struct list_head dev_list;
+
+ /* the head for the list of ITTEs */
+ struct list_head itt_head;
+ u32 num_eventid_bits;
+ gpa_t itt_addr;
+ u32 device_id;
+};
+
+#define COLLECTION_NOT_MAPPED ((u32)~0)
+
+struct its_collection {
+ struct list_head coll_list;
+
+ u32 collection_id;
+ u32 target_addr;
+};
+
+#define its_is_collection_mapped(coll) ((coll) && \
+ ((coll)->target_addr != COLLECTION_NOT_MAPPED))
+
+struct its_ite {
+ struct list_head ite_list;
+
+ struct vgic_irq *irq;
+ struct its_collection *collection;
+ u32 event_id;
+};
+
int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
struct vgic_reg_attr *reg_attr);
int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr,
@@ -359,4 +389,7 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu);
void vgic_v3_handle_nested_maint_irq(struct kvm_vcpu *vcpu);
void vgic_v3_nested_update_mi(struct kvm_vcpu *vcpu);
+int vgic_its_debug_init(struct kvm_device *dev);
+void vgic_its_debug_destroy(struct kvm_device *dev);
+
#endif
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 4d49dff721a8..027bfa9689c6 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,4 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
+
+obj-y += crypto/
+
lib-y := clear_user.o delay.o copy_from_user.o \
copy_to_user.o copy_page.o \
clear_page.o csum.o insn.o memchr.o memcpy.o \
@@ -14,10 +17,10 @@ endif
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
obj-$(CONFIG_CRC32_ARCH) += crc32-arm64.o
-crc32-arm64-y := crc32.o crc32-glue.o
+crc32-arm64-y := crc32.o crc32-core.o
obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-arm64.o
-crc-t10dif-arm64-y := crc-t10dif-glue.o crc-t10dif-core.o
+crc-t10dif-arm64-y := crc-t10dif.o crc-t10dif-core.o
obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
diff --git a/arch/arm64/lib/crc-t10dif-glue.c b/arch/arm64/lib/crc-t10dif.c
index bacd18f23168..c2ffe4fdb59d 100644
--- a/arch/arm64/lib/crc-t10dif-glue.c
+++ b/arch/arm64/lib/crc-t10dif.c
@@ -17,8 +17,8 @@
#include <asm/neon.h>
#include <asm/simd.h>
-static DEFINE_STATIC_KEY_FALSE(have_asimd);
-static DEFINE_STATIC_KEY_FALSE(have_pmull);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_asimd);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_pmull);
#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
@@ -61,7 +61,7 @@ static int __init crc_t10dif_arm64_init(void)
}
return 0;
}
-arch_initcall(crc_t10dif_arm64_init);
+subsys_initcall(crc_t10dif_arm64_init);
static void __exit crc_t10dif_arm64_exit(void)
{
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32-core.S
index 68825317460f..68825317460f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32-core.S
diff --git a/arch/arm64/lib/crc32-glue.c b/arch/arm64/lib/crc32.c
index ed3acd71178f..ed3acd71178f 100644
--- a/arch/arm64/lib/crc32-glue.c
+++ b/arch/arm64/lib/crc32.c
diff --git a/arch/arm64/lib/crypto/.gitignore b/arch/arm64/lib/crypto/.gitignore
new file mode 100644
index 000000000000..12d74d8b03d0
--- /dev/null
+++ b/arch/arm64/lib/crypto/.gitignore
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+poly1305-core.S
+sha256-core.S
diff --git a/arch/arm64/lib/crypto/Kconfig b/arch/arm64/lib/crypto/Kconfig
new file mode 100644
index 000000000000..129a7685cb4c
--- /dev/null
+++ b/arch/arm64/lib/crypto/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config CRYPTO_CHACHA20_NEON
+ tristate
+ depends on KERNEL_MODE_NEON
+ default CRYPTO_LIB_CHACHA
+ select CRYPTO_LIB_CHACHA_GENERIC
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
+
+config CRYPTO_POLY1305_NEON
+ tristate
+ depends on KERNEL_MODE_NEON
+ default CRYPTO_LIB_POLY1305
+ select CRYPTO_ARCH_HAVE_LIB_POLY1305
+
+config CRYPTO_SHA256_ARM64
+ tristate
+ default CRYPTO_LIB_SHA256
+ select CRYPTO_ARCH_HAVE_LIB_SHA256
+ select CRYPTO_ARCH_HAVE_LIB_SHA256_SIMD
diff --git a/arch/arm64/lib/crypto/Makefile b/arch/arm64/lib/crypto/Makefile
new file mode 100644
index 000000000000..946c09903711
--- /dev/null
+++ b/arch/arm64/lib/crypto/Makefile
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha-neon.o
+chacha-neon-y := chacha-neon-core.o chacha-neon-glue.o
+
+obj-$(CONFIG_CRYPTO_POLY1305_NEON) += poly1305-neon.o
+poly1305-neon-y := poly1305-core.o poly1305-glue.o
+AFLAGS_poly1305-core.o += -Dpoly1305_init=poly1305_block_init_arch
+AFLAGS_poly1305-core.o += -Dpoly1305_emit=poly1305_emit_arch
+
+obj-$(CONFIG_CRYPTO_SHA256_ARM64) += sha256-arm64.o
+sha256-arm64-y := sha256.o sha256-core.o
+sha256-arm64-$(CONFIG_KERNEL_MODE_NEON) += sha256-ce.o
+
+quiet_cmd_perlasm = PERLASM $@
+ cmd_perlasm = $(PERL) $(<) void $(@)
+
+$(obj)/%-core.S: $(src)/%-armv8.pl
+ $(call cmd,perlasm)
+
+$(obj)/sha256-core.S: $(src)/sha2-armv8.pl
+ $(call cmd,perlasm)
+
+clean-files += poly1305-core.S sha256-core.S
diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/lib/crypto/chacha-neon-core.S
index b70ac76f2610..80079586ecc7 100644
--- a/arch/arm64/crypto/chacha-neon-core.S
+++ b/arch/arm64/lib/crypto/chacha-neon-core.S
@@ -1,5 +1,5 @@
/*
- * ChaCha/XChaCha NEON helper functions
+ * ChaCha/HChaCha NEON helper functions
*
* Copyright (C) 2016-2018 Linaro, Ltd. <ard.biesheuvel@linaro.org>
*
diff --git a/arch/arm64/lib/crypto/chacha-neon-glue.c b/arch/arm64/lib/crypto/chacha-neon-glue.c
new file mode 100644
index 000000000000..d0188f974ca5
--- /dev/null
+++ b/arch/arm64/lib/crypto/chacha-neon-glue.c
@@ -0,0 +1,119 @@
+/*
+ * ChaCha and HChaCha functions (ARM64 optimized)
+ *
+ * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Based on:
+ * ChaCha20 256-bit cipher algorithm, RFC7539, SIMD glue code
+ *
+ * Copyright (C) 2015 Martin Willi
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+
+asmlinkage void chacha_block_xor_neon(const struct chacha_state *state,
+ u8 *dst, const u8 *src, int nrounds);
+asmlinkage void chacha_4block_xor_neon(const struct chacha_state *state,
+ u8 *dst, const u8 *src,
+ int nrounds, int bytes);
+asmlinkage void hchacha_block_neon(const struct chacha_state *state,
+ u32 out[HCHACHA_OUT_WORDS], int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+static void chacha_doneon(struct chacha_state *state, u8 *dst, const u8 *src,
+ int bytes, int nrounds)
+{
+ while (bytes > 0) {
+ int l = min(bytes, CHACHA_BLOCK_SIZE * 5);
+
+ if (l <= CHACHA_BLOCK_SIZE) {
+ u8 buf[CHACHA_BLOCK_SIZE];
+
+ memcpy(buf, src, l);
+ chacha_block_xor_neon(state, buf, buf, nrounds);
+ memcpy(dst, buf, l);
+ state->x[12] += 1;
+ break;
+ }
+ chacha_4block_xor_neon(state, dst, src, nrounds, l);
+ bytes -= l;
+ src += l;
+ dst += l;
+ state->x[12] += DIV_ROUND_UP(l, CHACHA_BLOCK_SIZE);
+ }
+}
+
+void hchacha_block_arch(const struct chacha_state *state,
+ u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+ if (!static_branch_likely(&have_neon) || !crypto_simd_usable()) {
+ hchacha_block_generic(state, out, nrounds);
+ } else {
+ kernel_neon_begin();
+ hchacha_block_neon(state, out, nrounds);
+ kernel_neon_end();
+ }
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_crypt_arch(struct chacha_state *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds)
+{
+ if (!static_branch_likely(&have_neon) || bytes <= CHACHA_BLOCK_SIZE ||
+ !crypto_simd_usable())
+ return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+ do {
+ unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+ kernel_neon_begin();
+ chacha_doneon(state, dst, src, todo, nrounds);
+ kernel_neon_end();
+
+ bytes -= todo;
+ src += todo;
+ dst += todo;
+ } while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+bool chacha_is_arch_optimized(void)
+{
+ return static_key_enabled(&have_neon);
+}
+EXPORT_SYMBOL(chacha_is_arch_optimized);
+
+static int __init chacha_simd_mod_init(void)
+{
+ if (cpu_have_named_feature(ASIMD))
+ static_branch_enable(&have_neon);
+ return 0;
+}
+subsys_initcall(chacha_simd_mod_init);
+
+static void __exit chacha_simd_mod_exit(void)
+{
+}
+module_exit(chacha_simd_mod_exit);
+
+MODULE_DESCRIPTION("ChaCha and HChaCha functions (ARM64 optimized)");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/crypto/poly1305-armv8.pl b/arch/arm64/lib/crypto/poly1305-armv8.pl
index 22c9069c0650..22c9069c0650 100644
--- a/arch/arm64/crypto/poly1305-armv8.pl
+++ b/arch/arm64/lib/crypto/poly1305-armv8.pl
diff --git a/arch/arm64/lib/crypto/poly1305-glue.c b/arch/arm64/lib/crypto/poly1305-glue.c
new file mode 100644
index 000000000000..6a661cf04821
--- /dev/null
+++ b/arch/arm64/lib/crypto/poly1305-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * OpenSSL/Cryptogams accelerated Poly1305 transform for arm64
+ *
+ * Copyright (C) 2019 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <crypto/internal/poly1305.h>
+#include <linux/cpufeature.h>
+#include <linux/jump_label.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/unaligned.h>
+
+asmlinkage void poly1305_block_init_arch(
+ struct poly1305_block_state *state,
+ const u8 raw_key[POLY1305_BLOCK_SIZE]);
+EXPORT_SYMBOL_GPL(poly1305_block_init_arch);
+asmlinkage void poly1305_blocks(struct poly1305_block_state *state,
+ const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_blocks_neon(struct poly1305_block_state *state,
+ const u8 *src, u32 len, u32 hibit);
+asmlinkage void poly1305_emit_arch(const struct poly1305_state *state,
+ u8 digest[POLY1305_DIGEST_SIZE],
+ const u32 nonce[4]);
+EXPORT_SYMBOL_GPL(poly1305_emit_arch);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+
+void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
+ unsigned int len, u32 padbit)
+{
+ len = round_down(len, POLY1305_BLOCK_SIZE);
+ if (static_branch_likely(&have_neon)) {
+ do {
+ unsigned int todo = min_t(unsigned int, len, SZ_4K);
+
+ kernel_neon_begin();
+ poly1305_blocks_neon(state, src, todo, 1);
+ kernel_neon_end();
+
+ len -= todo;
+ src += todo;
+ } while (len);
+ } else
+ poly1305_blocks(state, src, len, 1);
+}
+EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
+
+bool poly1305_is_arch_optimized(void)
+{
+ /* We always can use at least the ARM64 scalar implementation. */
+ return true;
+}
+EXPORT_SYMBOL(poly1305_is_arch_optimized);
+
+static int __init neon_poly1305_mod_init(void)
+{
+ if (cpu_have_named_feature(ASIMD))
+ static_branch_enable(&have_neon);
+ return 0;
+}
+subsys_initcall(neon_poly1305_mod_init);
+
+static void __exit neon_poly1305_mod_exit(void)
+{
+}
+module_exit(neon_poly1305_mod_exit);
+
+MODULE_DESCRIPTION("Poly1305 authenticator (ARM64 optimized)");
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/lib/crypto/sha2-armv8.pl
index 35ec9ae99fe1..4aebd20c498b 100644
--- a/arch/arm64/crypto/sha512-armv8.pl
+++ b/arch/arm64/lib/crypto/sha2-armv8.pl
@@ -95,7 +95,7 @@ if ($output =~ /512/) {
$reg_t="w";
}
-$func="sha${BITS}_block_data_order";
+$func="sha${BITS}_blocks_arch";
($ctx,$inp,$num,$Ktbl)=map("x$_",(0..2,30));
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/lib/crypto/sha256-ce.S
index fce84d88ddb2..f3e21c6d87d2 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/lib/crypto/sha256-ce.S
@@ -71,8 +71,8 @@
.word 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
/*
- * int __sha256_ce_transform(struct sha256_ce_state *sst, u8 const *src,
- * int blocks)
+ * size_t __sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+ * const u8 *data, size_t nblocks);
*/
.text
SYM_FUNC_START(__sha256_ce_transform)
@@ -86,20 +86,16 @@ SYM_FUNC_START(__sha256_ce_transform)
/* load state */
ld1 {dgav.4s, dgbv.4s}, [x0]
- /* load sha256_ce_state::finalize */
- ldr_l w4, sha256_ce_offsetof_finalize, x4
- ldr w4, [x0, x4]
-
/* load input */
0: ld1 {v16.4s-v19.4s}, [x1], #64
- sub w2, w2, #1
+ sub x2, x2, #1
CPU_LE( rev32 v16.16b, v16.16b )
CPU_LE( rev32 v17.16b, v17.16b )
CPU_LE( rev32 v18.16b, v18.16b )
CPU_LE( rev32 v19.16b, v19.16b )
-1: add t0.4s, v16.4s, v0.4s
+ add t0.4s, v16.4s, v0.4s
mov dg0v.16b, dgav.16b
mov dg1v.16b, dgbv.16b
@@ -127,31 +123,14 @@ CPU_LE( rev32 v19.16b, v19.16b )
add dgav.4s, dgav.4s, dg0v.4s
add dgbv.4s, dgbv.4s, dg1v.4s
- /* handled all input blocks? */
- cbz w2, 2f
- cond_yield 3f, x5, x6
- b 0b
+ /* return early if voluntary preemption is needed */
+ cond_yield 1f, x5, x6
- /*
- * Final block: add padding and total bit count.
- * Skip if the input size was not a round multiple of the block size,
- * the padding is handled by the C code in that case.
- */
-2: cbz x4, 3f
- ldr_l w4, sha256_ce_offsetof_count, x4
- ldr x4, [x0, x4]
- movi v17.2d, #0
- mov x8, #0x80000000
- movi v18.2d, #0
- ror x7, x4, #29 // ror(lsl(x4, 3), 32)
- fmov d16, x8
- mov x4, #0
- mov v19.d[0], xzr
- mov v19.d[1], x7
- b 1b
+ /* handled all input blocks? */
+ cbnz x2, 0b
/* store new state */
-3: st1 {dgav.4s, dgbv.4s}, [x0]
- mov w0, w2
+1: st1 {dgav.4s, dgbv.4s}, [x0]
+ mov x0, x2
ret
SYM_FUNC_END(__sha256_ce_transform)
diff --git a/arch/arm64/lib/crypto/sha256.c b/arch/arm64/lib/crypto/sha256.c
new file mode 100644
index 000000000000..bcf7a3adc0c4
--- /dev/null
+++ b/arch/arm64/lib/crypto/sha256.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * SHA-256 optimized for ARM64
+ *
+ * Copyright 2025 Google LLC
+ */
+#include <asm/neon.h>
+#include <crypto/internal/sha2.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+asmlinkage void sha256_blocks_arch(u32 state[SHA256_STATE_WORDS],
+ const u8 *data, size_t nblocks);
+EXPORT_SYMBOL_GPL(sha256_blocks_arch);
+asmlinkage void sha256_block_neon(u32 state[SHA256_STATE_WORDS],
+ const u8 *data, size_t nblocks);
+asmlinkage size_t __sha256_ce_transform(u32 state[SHA256_STATE_WORDS],
+ const u8 *data, size_t nblocks);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_ce);
+
+void sha256_blocks_simd(u32 state[SHA256_STATE_WORDS],
+ const u8 *data, size_t nblocks)
+{
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ static_branch_likely(&have_neon)) {
+ if (static_branch_likely(&have_ce)) {
+ do {
+ size_t rem;
+
+ kernel_neon_begin();
+ rem = __sha256_ce_transform(state,
+ data, nblocks);
+ kernel_neon_end();
+ data += (nblocks - rem) * SHA256_BLOCK_SIZE;
+ nblocks = rem;
+ } while (nblocks);
+ } else {
+ kernel_neon_begin();
+ sha256_block_neon(state, data, nblocks);
+ kernel_neon_end();
+ }
+ } else {
+ sha256_blocks_arch(state, data, nblocks);
+ }
+}
+EXPORT_SYMBOL_GPL(sha256_blocks_simd);
+
+bool sha256_is_arch_optimized(void)
+{
+ /* We always can use at least the ARM64 scalar implementation. */
+ return true;
+}
+EXPORT_SYMBOL_GPL(sha256_is_arch_optimized);
+
+static int __init sha256_arm64_mod_init(void)
+{
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ cpu_have_named_feature(ASIMD)) {
+ static_branch_enable(&have_neon);
+ if (cpu_have_named_feature(SHA2))
+ static_branch_enable(&have_ce);
+ }
+ return 0;
+}
+subsys_initcall(sha256_arm64_mod_init);
+
+static void __exit sha256_arm64_mod_exit(void)
+{
+}
+module_exit(sha256_arm64_mod_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA-256 optimized for ARM64");
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index cfe8cb8ba1cc..0c8737f4f2ce 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -129,7 +129,7 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
if (!pte_present(orig_pte) || !pte_cont(orig_pte))
return orig_pte;
- ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize);
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
for (i = 0; i < ncontig; i++, ptep++) {
pte_t pte = __ptep_get(ptep);
@@ -159,12 +159,11 @@ static pte_t get_clear_contig(struct mm_struct *mm,
pte_t pte, tmp_pte;
bool present;
- pte = __ptep_get_and_clear(mm, addr, ptep);
+ pte = __ptep_get_and_clear_anysz(mm, ptep, pgsize);
present = pte_present(pte);
while (--ncontig) {
ptep++;
- addr += pgsize;
- tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+ tmp_pte = __ptep_get_and_clear_anysz(mm, ptep, pgsize);
if (present) {
if (pte_dirty(tmp_pte))
pte = pte_mkdirty(pte);
@@ -183,8 +182,9 @@ static pte_t get_clear_contig_flush(struct mm_struct *mm,
{
pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig);
struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+ unsigned long end = addr + (pgsize * ncontig);
- flush_tlb_range(&vma, addr, addr + (pgsize * ncontig));
+ __flush_hugetlb_tlb_range(&vma, addr, end, pgsize, true);
return orig_pte;
}
@@ -207,9 +207,12 @@ static void clear_flush(struct mm_struct *mm,
unsigned long i, saddr = addr;
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
- __ptep_get_and_clear(mm, addr, ptep);
+ __ptep_get_and_clear_anysz(mm, ptep, pgsize);
- flush_tlb_range(&vma, saddr, addr);
+ if (mm == &init_mm)
+ flush_tlb_kernel_range(saddr, addr);
+ else
+ __flush_hugetlb_tlb_range(&vma, saddr, addr, pgsize, true);
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -218,30 +221,20 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
size_t pgsize;
int i;
int ncontig;
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
ncontig = num_contig_ptes(sz, &pgsize);
if (!pte_present(pte)) {
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
- __set_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- if (!pte_cont(pte)) {
- __set_ptes(mm, addr, ptep, pte, 1);
+ __set_ptes_anysz(mm, ptep, pte, 1, pgsize);
return;
}
- pfn = pte_pfn(pte);
- dpfn = pgsize >> PAGE_SHIFT;
- hugeprot = pte_pgprot(pte);
-
- clear_flush(mm, addr, ptep, pgsize, ncontig);
+ /* Only need to "break" if transitioning valid -> valid. */
+ if (pte_cont(pte) && pte_valid(__ptep_get(ptep)))
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+ __set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
}
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -431,23 +424,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- int ncontig, i;
+ int ncontig;
size_t pgsize = 0;
- unsigned long pfn = pte_pfn(pte), dpfn;
struct mm_struct *mm = vma->vm_mm;
- pgprot_t hugeprot;
pte_t orig_pte;
+ VM_WARN_ON(!pte_present(pte));
+
if (!pte_cont(pte))
return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- dpfn = pgsize >> PAGE_SHIFT;
+ ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
if (!__cont_access_flags_changed(ptep, pte, ncontig))
return 0;
orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
+ VM_WARN_ON(!pte_present(orig_pte));
/* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
@@ -456,38 +449,31 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
if (pte_young(orig_pte))
pte = pte_mkyoung(pte);
- hugeprot = pte_pgprot(pte);
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
-
+ __set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
- int ncontig, i;
+ int ncontig;
size_t pgsize;
pte_t pte;
- if (!pte_cont(__ptep_get(ptep))) {
+ pte = __ptep_get(ptep);
+ VM_WARN_ON(!pte_present(pte));
+
+ if (!pte_cont(pte)) {
__ptep_set_wrprotect(mm, addr, ptep);
return;
}
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- dpfn = pgsize >> PAGE_SHIFT;
pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
pte = pte_wrprotect(pte);
- hugeprot = pte_pgprot(pte);
- pfn = pte_pfn(pte);
-
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+ __set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
}
pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -497,10 +483,7 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
size_t pgsize;
int ncontig;
- if (!pte_cont(__ptep_get(ptep)))
- return ptep_clear_flush(vma, addr, ptep);
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index b99bf3980fc6..0c8c35dd645e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -275,26 +275,6 @@ void __init arm64_memblock_init(void)
}
}
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
- extern u16 memstart_offset_seed;
- u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
- int parange = cpuid_feature_extract_unsigned_field(
- mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
- s64 range = linear_region_size -
- BIT(id_aa64mmfr0_parange_to_phys_shift(parange));
-
- /*
- * If the size of the linear region exceeds, by a sufficient
- * margin, the size of the region that the physical memory can
- * span, randomize the linear region as well.
- */
- if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) {
- range /= ARM64_MEMSTART_ALIGN;
- memstart_addr -= ARM64_MEMSTART_ALIGN *
- ((range * memstart_offset_seed) >> 16);
- }
- }
-
/*
* Register the kernel text, kernel data, initrd, and initial
* pagetables with memblock.
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 39fd1f7ff02a..04d4a8f676db 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -96,8 +96,8 @@ static int change_memory_common(unsigned long addr, int numpages,
* we are operating on does not result in such splitting.
*
* Let's restrict ourselves to mappings created by vmalloc (or vmap).
- * Those are guaranteed to consist entirely of page mappings, and
- * splitting is never needed.
+ * Disallow VM_ALLOW_HUGE_VMAP mappings to guarantee that only page
+ * mappings are updated and splitting is never needed.
*
* So check whether the [addr, addr + size) interval is entirely
* covered by precisely one VM area that has the VM_ALLOC flag set.
@@ -105,7 +105,7 @@ static int change_memory_common(unsigned long addr, int numpages,
area = find_vm_area((void *)addr);
if (!area ||
end > (unsigned long)kasan_reset_tag(area->addr) + area->size ||
- !(area->flags & VM_ALLOC))
+ ((area->flags & (VM_ALLOC | VM_ALLOW_HUGE_VMAP)) != VM_ALLOC))
return -EINVAL;
if (!numpages)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index fb30c8804f87..80d470aa469d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -512,26 +512,11 @@ alternative_else_nop_endif
ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4
cbz x1, .Lskip_indirection
- /*
- * The PROT_* macros describing the various memory types may resolve to
- * C expressions if they include the PTE_MAYBE_* macros, and so they
- * can only be used from C code. The PIE_E* constants below are also
- * defined in terms of those macros, but will mask out those
- * PTE_MAYBE_* constants, whether they are set or not. So #define them
- * as 0x0 here so we can evaluate the PIE_E* constants in asm context.
- */
-
-#define PTE_MAYBE_NG 0
-#define PTE_MAYBE_SHARED 0
-
- mov_q x0, PIE_E0
+ mov_q x0, PIE_E0_ASM
msr REG_PIRE0_EL1, x0
- mov_q x0, PIE_E1
+ mov_q x0, PIE_E1_ASM
msr REG_PIR_EL1, x0
-#undef PTE_MAYBE_NG
-#undef PTE_MAYBE_SHARED
-
orr tcr2, tcr2, TCR2_EL1_PIE
msr REG_TCR2_EL1, x0
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 634d78422adb..da8b89dd2910 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2113,7 +2113,7 @@ bool bpf_jit_supports_subprog_tailcalls(void)
}
static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
- int args_off, int retval_off, int run_ctx_off,
+ int bargs_off, int retval_off, int run_ctx_off,
bool save_ret)
{
__le32 *branch;
@@ -2155,7 +2155,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
branch = ctx->image + ctx->idx;
emit(A64_NOP, ctx);
- emit(A64_ADD_I(1, A64_R(0), A64_SP, args_off), ctx);
+ emit(A64_ADD_I(1, A64_R(0), A64_SP, bargs_off), ctx);
if (!p->jited)
emit_addr_mov_i64(A64_R(1), (const u64)p->insnsi, ctx);
@@ -2180,7 +2180,7 @@ static void invoke_bpf_prog(struct jit_ctx *ctx, struct bpf_tramp_link *l,
}
static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
- int args_off, int retval_off, int run_ctx_off,
+ int bargs_off, int retval_off, int run_ctx_off,
__le32 **branches)
{
int i;
@@ -2190,7 +2190,7 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
*/
emit(A64_STR64I(A64_ZR, A64_SP, retval_off), ctx);
for (i = 0; i < tl->nr_links; i++) {
- invoke_bpf_prog(ctx, tl->links[i], args_off, retval_off,
+ invoke_bpf_prog(ctx, tl->links[i], bargs_off, retval_off,
run_ctx_off, true);
/* if (*(u64 *)(sp + retval_off) != 0)
* goto do_fexit;
@@ -2204,23 +2204,125 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
}
}
-static void save_args(struct jit_ctx *ctx, int args_off, int nregs)
+struct arg_aux {
+ /* how many args are passed through registers, the rest of the args are
+ * passed through stack
+ */
+ int args_in_regs;
+ /* how many registers are used to pass arguments */
+ int regs_for_args;
+ /* how much stack is used for additional args passed to bpf program
+ * that did not fit in original function registers
+ */
+ int bstack_for_args;
+ /* home much stack is used for additional args passed to the
+ * original function when called from trampoline (this one needs
+ * arguments to be properly aligned)
+ */
+ int ostack_for_args;
+};
+
+static int calc_arg_aux(const struct btf_func_model *m,
+ struct arg_aux *a)
{
- int i;
+ int stack_slots, nregs, slots, i;
+
+ /* verifier ensures m->nr_args <= MAX_BPF_FUNC_ARGS */
+ for (i = 0, nregs = 0; i < m->nr_args; i++) {
+ slots = (m->arg_size[i] + 7) / 8;
+ if (nregs + slots <= 8) /* passed through register ? */
+ nregs += slots;
+ else
+ break;
+ }
+
+ a->args_in_regs = i;
+ a->regs_for_args = nregs;
+ a->ostack_for_args = 0;
+ a->bstack_for_args = 0;
+
+ /* the rest arguments are passed through stack */
+ for (; i < m->nr_args; i++) {
+ /* We can not know for sure about exact alignment needs for
+ * struct passed on stack, so deny those
+ */
+ if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
+ return -ENOTSUPP;
+ stack_slots = (m->arg_size[i] + 7) / 8;
+ a->bstack_for_args += stack_slots * 8;
+ a->ostack_for_args = a->ostack_for_args + stack_slots * 8;
+ }
+
+ return 0;
+}
- for (i = 0; i < nregs; i++) {
- emit(A64_STR64I(i, A64_SP, args_off), ctx);
- args_off += 8;
+static void clear_garbage(struct jit_ctx *ctx, int reg, int effective_bytes)
+{
+ if (effective_bytes) {
+ int garbage_bits = 64 - 8 * effective_bytes;
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ /* garbage bits are at the right end */
+ emit(A64_LSR(1, reg, reg, garbage_bits), ctx);
+ emit(A64_LSL(1, reg, reg, garbage_bits), ctx);
+#else
+ /* garbage bits are at the left end */
+ emit(A64_LSL(1, reg, reg, garbage_bits), ctx);
+ emit(A64_LSR(1, reg, reg, garbage_bits), ctx);
+#endif
}
}
-static void restore_args(struct jit_ctx *ctx, int args_off, int nregs)
+static void save_args(struct jit_ctx *ctx, int bargs_off, int oargs_off,
+ const struct btf_func_model *m,
+ const struct arg_aux *a,
+ bool for_call_origin)
{
int i;
+ int reg;
+ int doff;
+ int soff;
+ int slots;
+ u8 tmp = bpf2a64[TMP_REG_1];
+
+ /* store arguments to the stack for the bpf program, or restore
+ * arguments from stack for the original function
+ */
+ for (reg = 0; reg < a->regs_for_args; reg++) {
+ emit(for_call_origin ?
+ A64_LDR64I(reg, A64_SP, bargs_off) :
+ A64_STR64I(reg, A64_SP, bargs_off),
+ ctx);
+ bargs_off += 8;
+ }
+
+ soff = 32; /* on stack arguments start from FP + 32 */
+ doff = (for_call_origin ? oargs_off : bargs_off);
+
+ /* save on stack arguments */
+ for (i = a->args_in_regs; i < m->nr_args; i++) {
+ slots = (m->arg_size[i] + 7) / 8;
+ /* verifier ensures arg_size <= 16, so slots equals 1 or 2 */
+ while (slots-- > 0) {
+ emit(A64_LDR64I(tmp, A64_FP, soff), ctx);
+ /* if there is unused space in the last slot, clear
+ * the garbage contained in the space.
+ */
+ if (slots == 0 && !for_call_origin)
+ clear_garbage(ctx, tmp, m->arg_size[i] % 8);
+ emit(A64_STR64I(tmp, A64_SP, doff), ctx);
+ soff += 8;
+ doff += 8;
+ }
+ }
+}
- for (i = 0; i < nregs; i++) {
- emit(A64_LDR64I(i, A64_SP, args_off), ctx);
- args_off += 8;
+static void restore_args(struct jit_ctx *ctx, int bargs_off, int nregs)
+{
+ int reg;
+
+ for (reg = 0; reg < nregs; reg++) {
+ emit(A64_LDR64I(reg, A64_SP, bargs_off), ctx);
+ bargs_off += 8;
}
}
@@ -2243,17 +2345,21 @@ static bool is_struct_ops_tramp(const struct bpf_tramp_links *fentry_links)
*/
static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
struct bpf_tramp_links *tlinks, void *func_addr,
- int nregs, u32 flags)
+ const struct btf_func_model *m,
+ const struct arg_aux *a,
+ u32 flags)
{
int i;
int stack_size;
int retaddr_off;
int regs_off;
int retval_off;
- int args_off;
- int nregs_off;
+ int bargs_off;
+ int nfuncargs_off;
int ip_off;
int run_ctx_off;
+ int oargs_off;
+ int nfuncargs;
struct bpf_tramp_links *fentry = &tlinks[BPF_TRAMP_FENTRY];
struct bpf_tramp_links *fexit = &tlinks[BPF_TRAMP_FEXIT];
struct bpf_tramp_links *fmod_ret = &tlinks[BPF_TRAMP_MODIFY_RETURN];
@@ -2262,31 +2368,38 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
bool is_struct_ops = is_struct_ops_tramp(fentry);
/* trampoline stack layout:
- * [ parent ip ]
- * [ FP ]
- * SP + retaddr_off [ self ip ]
- * [ FP ]
+ * [ parent ip ]
+ * [ FP ]
+ * SP + retaddr_off [ self ip ]
+ * [ FP ]
*
- * [ padding ] align SP to multiples of 16
+ * [ padding ] align SP to multiples of 16
*
- * [ x20 ] callee saved reg x20
- * SP + regs_off [ x19 ] callee saved reg x19
+ * [ x20 ] callee saved reg x20
+ * SP + regs_off [ x19 ] callee saved reg x19
*
- * SP + retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or
- * BPF_TRAMP_F_RET_FENTRY_RET
+ * SP + retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or
+ * BPF_TRAMP_F_RET_FENTRY_RET
+ * [ arg reg N ]
+ * [ ... ]
+ * SP + bargs_off [ arg reg 1 ] for bpf
*
- * [ arg reg N ]
- * [ ... ]
- * SP + args_off [ arg reg 1 ]
+ * SP + nfuncargs_off [ arg regs count ]
*
- * SP + nregs_off [ arg regs count ]
+ * SP + ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag
*
- * SP + ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag
+ * SP + run_ctx_off [ bpf_tramp_run_ctx ]
*
- * SP + run_ctx_off [ bpf_tramp_run_ctx ]
+ * [ stack arg N ]
+ * [ ... ]
+ * SP + oargs_off [ stack arg 1 ] for original func
*/
stack_size = 0;
+ oargs_off = stack_size;
+ if (flags & BPF_TRAMP_F_CALL_ORIG)
+ stack_size += a->ostack_for_args;
+
run_ctx_off = stack_size;
/* room for bpf_tramp_run_ctx */
stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8);
@@ -2296,13 +2409,14 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
if (flags & BPF_TRAMP_F_IP_ARG)
stack_size += 8;
- nregs_off = stack_size;
+ nfuncargs_off = stack_size;
/* room for args count */
stack_size += 8;
- args_off = stack_size;
+ bargs_off = stack_size;
/* room for args */
- stack_size += nregs * 8;
+ nfuncargs = a->regs_for_args + a->bstack_for_args / 8;
+ stack_size += 8 * nfuncargs;
/* room for return value */
retval_off = stack_size;
@@ -2349,11 +2463,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
/* save arg regs count*/
- emit(A64_MOVZ(1, A64_R(10), nregs, 0), ctx);
- emit(A64_STR64I(A64_R(10), A64_SP, nregs_off), ctx);
+ emit(A64_MOVZ(1, A64_R(10), nfuncargs, 0), ctx);
+ emit(A64_STR64I(A64_R(10), A64_SP, nfuncargs_off), ctx);
- /* save arg regs */
- save_args(ctx, args_off, nregs);
+ /* save args for bpf */
+ save_args(ctx, bargs_off, oargs_off, m, a, false);
/* save callee saved registers */
emit(A64_STR64I(A64_R(19), A64_SP, regs_off), ctx);
@@ -2369,7 +2483,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
for (i = 0; i < fentry->nr_links; i++)
- invoke_bpf_prog(ctx, fentry->links[i], args_off,
+ invoke_bpf_prog(ctx, fentry->links[i], bargs_off,
retval_off, run_ctx_off,
flags & BPF_TRAMP_F_RET_FENTRY_RET);
@@ -2379,12 +2493,13 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
if (!branches)
return -ENOMEM;
- invoke_bpf_mod_ret(ctx, fmod_ret, args_off, retval_off,
+ invoke_bpf_mod_ret(ctx, fmod_ret, bargs_off, retval_off,
run_ctx_off, branches);
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- restore_args(ctx, args_off, nregs);
+ /* save args for original func */
+ save_args(ctx, bargs_off, oargs_off, m, a, true);
/* call original func */
emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx);
emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx);
@@ -2403,7 +2518,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
for (i = 0; i < fexit->nr_links; i++)
- invoke_bpf_prog(ctx, fexit->links[i], args_off, retval_off,
+ invoke_bpf_prog(ctx, fexit->links[i], bargs_off, retval_off,
run_ctx_off, false);
if (flags & BPF_TRAMP_F_CALL_ORIG) {
@@ -2417,7 +2532,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
}
if (flags & BPF_TRAMP_F_RESTORE_REGS)
- restore_args(ctx, args_off, nregs);
+ restore_args(ctx, bargs_off, a->regs_for_args);
/* restore callee saved register x19 and x20 */
emit(A64_LDR64I(A64_R(19), A64_SP, regs_off), ctx);
@@ -2454,21 +2569,6 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
return ctx->idx;
}
-static int btf_func_model_nregs(const struct btf_func_model *m)
-{
- int nregs = m->nr_args;
- int i;
-
- /* extra registers needed for struct argument */
- for (i = 0; i < MAX_BPF_FUNC_ARGS; i++) {
- /* The arg_size is at most 16 bytes, enforced by the verifier. */
- if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG)
- nregs += (m->arg_size[i] + 7) / 8 - 1;
- }
-
- return nregs;
-}
-
int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
struct bpf_tramp_links *tlinks, void *func_addr)
{
@@ -2477,14 +2577,14 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
.idx = 0,
};
struct bpf_tramp_image im;
- int nregs, ret;
+ struct arg_aux aaux;
+ int ret;
- nregs = btf_func_model_nregs(m);
- /* the first 8 registers are used for arguments */
- if (nregs > 8)
- return -ENOTSUPP;
+ ret = calc_arg_aux(m, &aaux);
+ if (ret < 0)
+ return ret;
- ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, nregs, flags);
+ ret = prepare_trampoline(&ctx, &im, tlinks, func_addr, m, &aaux, flags);
if (ret < 0)
return ret;
@@ -2511,9 +2611,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
u32 flags, struct bpf_tramp_links *tlinks,
void *func_addr)
{
- int ret, nregs;
- void *image, *tmp;
u32 size = ro_image_end - ro_image;
+ struct arg_aux aaux;
+ void *image, *tmp;
+ int ret;
/* image doesn't need to be in module memory range, so we can
* use kvmalloc.
@@ -2529,13 +2630,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image,
.write = true,
};
- nregs = btf_func_model_nregs(m);
- /* the first 8 registers are used for arguments */
- if (nregs > 8)
- return -ENOTSUPP;
jit_fill_hole(image, (unsigned int)(ro_image_end - ro_image));
- ret = prepare_trampoline(&ctx, im, tlinks, func_addr, nregs, flags);
+ ret = calc_arg_aux(m, &aaux);
+ if (ret)
+ goto out;
+ ret = prepare_trampoline(&ctx, im, tlinks, func_addr, m, &aaux, flags);
if (ret > 0 && validate_code(&ctx) < 0) {
ret = -EINVAL;
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 772c1b008e43..10effd4cff6b 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -28,6 +28,7 @@ HAS_EPAN
HAS_EVT
HAS_FPMR
HAS_FGT
+HAS_FGT2
HAS_FPSIMD
HAS_GCS
HAS_GENERIC_AUTH
@@ -94,6 +95,7 @@ WORKAROUND_2457168
WORKAROUND_2645198
WORKAROUND_2658417
WORKAROUND_AMPERE_AC03_CPU_38
+WORKAROUND_AMPERE_AC04_CPU_23
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
WORKAROUND_TRBE_WRITE_OUT_OF_RANGE
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index bdf044c5d11b..8a8cf6874298 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -101,6 +101,17 @@ Res0 63:32
Field 31:0 DTRTX
EndSysreg
+Sysreg MDSELR_EL1 2 0 0 4 2
+Res0 63:6
+Field 5:4 BANK
+Res0 3:0
+EndSysreg
+
+Sysreg MDSTEPOP_EL1 2 0 0 5 2
+Res0 63:32
+Field 31:0 OPCODE
+EndSysreg
+
Sysreg OSECCR_EL1 2 0 0 6 2
Res0 63:32
Field 31:0 EDECCR
@@ -111,6 +122,285 @@ Res0 63:1
Field 0 OSLK
EndSysreg
+Sysreg SPMACCESSR_EL1 2 0 9 13 3
+UnsignedEnum 63:62 P31
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 61:60 P30
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 59:58 P29
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 57:56 P28
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 55:54 P27
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 53:52 P26
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 51:50 P25
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 49:48 P24
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 47:46 P23
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 45:44 P22
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 43:42 P21
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 41:40 P20
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 39:38 P19
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 37:36 P18
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 35:34 P17
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 33:32 P16
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 31:30 P15
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 29:28 P14
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 27:26 P13
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 25:24 P12
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 23:22 P11
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 21:20 P10
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 19:18 P9
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 17:16 P8
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 15:14 P7
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 13:12 P6
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 11:10 P5
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 9:8 P4
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 7:6 P3
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 5:4 P2
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 3:2 P1
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+UnsignedEnum 1:0 P0
+ 0b00 TRAP_RW
+ 0b01 TRAP_W
+ 0b11 NOTRAP
+EndEnum
+EndSysreg
+
+Sysreg SPMACCESSR_EL12 2 5 9 13 3
+Mapping SPMACCESSR_EL1
+EndSysreg
+
+Sysreg SPMIIDR_EL1 2 0 9 13 4
+Res0 63:32
+Field 31:20 ProductID
+Field 19:16 Variant
+Field 15:12 Revision
+Field 11:0 Implementer
+EndSysreg
+
+Sysreg SPMDEVARCH_EL1 2 0 9 13 5
+Res0 63:32
+Field 31:21 ARCHITECT
+Field 20 PRESENT
+Field 19:16 REVISION
+Field 15:12 ARCHVER
+Field 11:0 ARCHPART
+EndSysreg
+
+Sysreg SPMDEVAFF_EL1 2 0 9 13 6
+Res0 63:40
+Field 39:32 Aff3
+Field 31 F0V
+Field 30 U
+Res0 29:25
+Field 24 MT
+Field 23:16 Aff2
+Field 15:8 Aff1
+Field 7:0 Aff0
+EndSysreg
+
+Sysreg SPMCFGR_EL1 2 0 9 13 7
+Res0 63:32
+Field 31:28 NCG
+Res0 27:25
+Field 24 HDBG
+Field 23 TRO
+Field 22 SS
+Field 21 FZO
+Field 20 MSI
+Field 19 RAO
+Res0 18
+Field 17 NA
+Field 16 EX
+Field 15:14 RAZ
+Field 13:8 SIZE
+Field 7:0 N
+EndSysreg
+
+Sysreg SPMINTENSET_EL1 2 0 9 14 1
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMINTENCLR_EL1 2 0 9 14 2
+Field 63:0 P
+EndSysreg
+
+Sysreg PMCCNTSVR_EL1 2 0 14 11 7
+Field 63:0 CCNT
+EndSysreg
+
+Sysreg PMICNTSVR_EL1 2 0 14 12 0
+Field 63:0 ICNT
+EndSysreg
+
+Sysreg SPMCR_EL0 2 3 9 12 0
+Res0 63:12
+Field 11 TRO
+Field 10 HDBG
+Field 9 FZO
+Field 8 NA
+Res0 7:5
+Field 4 EX
+Res0 3:2
+Field 1 P
+Field 0 E
+EndSysreg
+
+Sysreg SPMCNTENSET_EL0 2 3 9 12 1
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMCNTENCLR_EL0 2 3 9 12 2
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMOVSCLR_EL0 2 3 9 12 3
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMZR_EL0 2 3 9 12 4
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMSELR_EL0 2 3 9 12 5
+Res0 63:10
+Field 9:4 SYSPMUSEL
+Res0 3:2
+Field 1:0 BANK
+EndSysreg
+
+Sysreg SPMOVSSET_EL0 2 3 9 14 3
+Field 63:0 P
+EndSysreg
+
+Sysreg SPMSCR_EL1 2 7 9 14 7
+Field 63:32 IMPDEF
+Field 31 RAO
+Res0 30:5
+Field 4 NAO
+Res0 3:1
+Field 0 SO
+EndSysreg
+
Sysreg ID_PFR0_EL1 3 0 0 1 0
Res0 63:32
UnsignedEnum 31:28 RAS
@@ -907,6 +1197,7 @@ UnsignedEnum 31:28 RAS
0b0000 NI
0b0001 IMP
0b0010 V1P1
+ 0b0011 V2
EndEnum
UnsignedEnum 27:24 GIC
0b0000 NI
@@ -1466,6 +1757,7 @@ UnsignedEnum 63:60 LS64
0b0001 LS64
0b0010 LS64_V
0b0011 LS64_ACCDATA
+ 0b0100 LS64WB
EndEnum
UnsignedEnum 59:56 XS
0b0000 NI
@@ -1945,12 +2237,21 @@ EndEnum
EndSysreg
Sysreg ID_AA64MMFR4_EL1 3 0 0 7 4
-Res0 63:40
+Res0 63:48
+UnsignedEnum 47:44 SRMASK
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
+Res0 43:40
UnsignedEnum 39:36 E3DSE
0b0000 NI
0b0001 IMP
EndEnum
-Res0 35:28
+Res0 35:32
+UnsignedEnum 31:28 RMEGDI
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
SignedEnum 27:24 E2H0
0b0000 IMP
0b1110 NI_NV1
@@ -1959,6 +2260,7 @@ EndEnum
UnsignedEnum 23:20 NV_frac
0b0000 NV_NV2
0b0001 NV2_ONLY
+ 0b0010 NV2P1
EndEnum
UnsignedEnum 19:16 FGWTE3
0b0000 NI
@@ -1978,7 +2280,10 @@ SignedEnum 7:4 EIESB
0b0010 ToELx
0b1111 ANY
EndEnum
-Res0 3:0
+UnsignedEnum 3:0 PoPS
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
EndSysreg
Sysreg SCTLR_EL1 3 0 1 0 0
@@ -2053,8 +2358,30 @@ Field 1 A
Field 0 M
EndSysreg
+Sysreg SCTLR_EL12 3 5 1 0 0
+Mapping SCTLR_EL1
+EndSysreg
+
+Sysreg SCTLRALIAS_EL1 3 0 1 4 6
+Mapping SCTLR_EL1
+EndSysreg
+
+Sysreg ACTLR_EL1 3 0 1 0 1
+Field 63:0 IMPDEF
+EndSysreg
+
+Sysreg ACTLR_EL12 3 5 1 0 1
+Mapping ACTLR_EL1
+EndSysreg
+
+Sysreg ACTLRALIAS_EL1 3 0 1 4 5
+Mapping ACTLR_EL1
+EndSysreg
+
Sysreg CPACR_EL1 3 0 1 0 2
-Res0 63:30
+Res0 63:32
+Field 31 TCPAC
+Field 30 TAM
Field 29 E0POE
Field 28 TTA
Res0 27:26
@@ -2066,6 +2393,323 @@ Field 17:16 ZEN
Res0 15:0
EndSysreg
+Sysreg CPACR_EL12 3 5 1 0 2
+Mapping CPACR_EL1
+EndSysreg
+
+Sysreg CPACRALIAS_EL1 3 0 1 4 4
+Mapping CPACR_EL1
+EndSysreg
+
+Sysreg ACTLRMASK_EL1 3 0 1 4 1
+Field 63:0 IMPDEF
+EndSysreg
+
+Sysreg ACTLRMASK_EL12 3 5 1 4 1
+Mapping ACTLRMASK_EL1
+EndSysreg
+
+Sysreg CPACRMASK_EL1 3 0 1 4 2
+Res0 63:32
+Field 31 TCPAC
+Field 30 TAM
+Field 29 E0POE
+Field 28 TTA
+Res0 27:25
+Field 24 SMEN
+Res0 23:21
+Field 20 FPEN
+Res0 19:17
+Field 16 ZEN
+Res0 15:0
+EndSysreg
+
+Sysreg CPACRMASK_EL12 3 5 1 4 2
+Mapping CPACRMASK_EL1
+EndSysreg
+
+Sysreg PFAR_EL1 3 0 6 0 5
+Field 63 NS
+Field 62 NSE
+Res0 61:56
+Field 55:52 PA_55_52
+Field 51:48 PA_51_48
+Field 47:0 PA
+EndSysreg
+
+Sysreg PFAR_EL12 3 5 6 0 5
+Mapping PFAR_EL1
+EndSysreg
+
+Sysreg RCWSMASK_EL1 3 0 13 0 3
+Field 63:0 RCWSMASK
+EndSysreg
+
+Sysreg SCTLR2_EL1 3 0 1 0 3
+Res0 63:13
+Field 12 CPTM0
+Field 11 CPTM
+Field 10 CPTA0
+Field 9 CPTA
+Field 8 EnPACM0
+Field 7 EnPACM
+Field 6 EnIDCP128
+Field 5 EASE
+Field 4 EnANERR
+Field 3 EnADERR
+Field 2 NMEA
+Res0 1:0
+EndSysreg
+
+Sysreg SCTLR2_EL12 3 5 1 0 3
+Mapping SCTLR2_EL1
+EndSysreg
+
+Sysreg SCTLR2ALIAS_EL1 3 0 1 4 7
+Mapping SCTLR2_EL1
+EndSysreg
+
+Sysreg SCTLR2MASK_EL1 3 0 1 4 3
+Res0 63:13
+Field 12 CPTM0
+Field 11 CPTM
+Field 10 CPTA0
+Field 9 CPTA
+Field 8 EnPACM0
+Field 7 EnPACM
+Field 6 EnIDCP128
+Field 5 EASE
+Field 4 EnANERR
+Field 3 EnADERR
+Field 2 NMEA
+Res0 1:0
+EndSysreg
+
+Sysreg SCTLR2MASK_EL12 3 5 1 4 3
+Mapping SCTLR2MASK_EL1
+EndSysreg
+
+Sysreg SCTLRMASK_EL1 3 0 1 4 0
+Field 63 TIDCP
+Field 62 SPINTMASK
+Field 61 NMI
+Field 60 EnTP2
+Field 59 TCSO
+Field 58 TCSO0
+Field 57 EPAN
+Field 56 EnALS
+Field 55 EnAS0
+Field 54 EnASR
+Field 53 TME
+Field 52 TME0
+Field 51 TMT
+Field 50 TMT0
+Res0 49:47
+Field 46 TWEDEL
+Field 45 TWEDEn
+Field 44 DSSBS
+Field 43 ATA
+Field 42 ATA0
+Res0 41
+Field 40 TCF
+Res0 39
+Field 38 TCF0
+Field 37 ITFSB
+Field 36 BT1
+Field 35 BT0
+Field 34 EnFPM
+Field 33 MSCEn
+Field 32 CMOW
+Field 31 EnIA
+Field 30 EnIB
+Field 29 LSMAOE
+Field 28 nTLSMD
+Field 27 EnDA
+Field 26 UCI
+Field 25 EE
+Field 24 E0E
+Field 23 SPAN
+Field 22 EIS
+Field 21 IESB
+Field 20 TSCXT
+Field 19 WXN
+Field 18 nTWE
+Res0 17
+Field 16 nTWI
+Field 15 UCT
+Field 14 DZE
+Field 13 EnDB
+Field 12 I
+Field 11 EOS
+Field 10 EnRCTX
+Field 9 UMA
+Field 8 SED
+Field 7 ITD
+Field 6 nAA
+Field 5 CP15BEN
+Field 4 SA0
+Field 3 SA
+Field 2 C
+Field 1 A
+Field 0 M
+EndSysreg
+
+Sysreg SCTLRMASK_EL12 3 5 1 4 0
+Mapping SCTLRMASK_EL1
+EndSysreg
+
+Sysreg TCR2MASK_EL1 3 0 2 7 3
+Res0 63:22
+Field 21 FNGNA1
+Field 20 FNGNA0
+Res0 19
+Field 18 FNG1
+Field 17 FNG0
+Field 16 A2
+Field 15 DisCH1
+Field 14 DisCH0
+Res0 13:12
+Field 11 HAFT
+Field 10 PTTWI
+Res0 9:6
+Field 5 D128
+Field 4 AIE
+Field 3 POE
+Field 2 E0POE
+Field 1 PIE
+Field 0 PnCH
+EndSysreg
+
+Sysreg TCR2MASK_EL12 3 5 2 7 3
+Mapping TCR2MASK_EL1
+EndSysreg
+
+Sysreg TCRMASK_EL1 3 0 2 7 2
+Res0 63:62
+Field 61 MTX1
+Field 60 MTX0
+Field 59 DS
+Field 58 TCMA1
+Field 57 TCMA0
+Field 56 E0PD1
+Field 55 E0PD0
+Field 54 NFD1
+Field 53 NFD0
+Field 52 TBID1
+Field 51 TBID0
+Field 50 HWU162
+Field 49 HWU161
+Field 48 HWU160
+Field 47 HWU159
+Field 46 HWU062
+Field 45 HWU061
+Field 44 HWU060
+Field 43 HWU059
+Field 42 HPD1
+Field 41 HPD0
+Field 40 HD
+Field 39 HA
+Field 38 TBI1
+Field 37 TBI0
+Field 36 AS
+Res0 35:33
+Field 32 IPS
+Res0 31
+Field 30 TG1
+Res0 29
+Field 28 SH1
+Res0 27
+Field 26 ORGN1
+Res0 25
+Field 24 IRGN1
+Field 23 EPD1
+Field 22 A1
+Res0 21:17
+Field 16 T1SZ
+Res0 15
+Field 14 TG0
+Res0 13
+Field 12 SH0
+Res0 11
+Field 10 ORGN0
+Res0 9
+Field 8 IRGN0
+Field 7 EPD0
+Res0 6:1
+Field 0 T0SZ
+EndSysreg
+
+Sysreg TCRMASK_EL12 3 5 2 7 2
+Mapping TCRMASK_EL1
+EndSysreg
+
+Sysreg ERXGSR_EL1 3 0 5 3 2
+Field 63 S63
+Field 62 S62
+Field 61 S61
+Field 60 S60
+Field 59 S59
+Field 58 S58
+Field 57 S57
+Field 56 S56
+Field 55 S55
+Field 54 S54
+Field 53 S53
+Field 52 S52
+Field 51 S51
+Field 50 S50
+Field 49 S49
+Field 48 S48
+Field 47 S47
+Field 46 S46
+Field 45 S45
+Field 44 S44
+Field 43 S43
+Field 42 S42
+Field 41 S41
+Field 40 S40
+Field 39 S39
+Field 38 S38
+Field 37 S37
+Field 36 S36
+Field 35 S35
+Field 34 S34
+Field 33 S33
+Field 32 S32
+Field 31 S31
+Field 30 S30
+Field 29 S29
+Field 28 S28
+Field 27 S27
+Field 26 S26
+Field 25 S25
+Field 24 S24
+Field 23 S23
+Field 22 S22
+Field 21 S21
+Field 20 S20
+Field 19 S19
+Field 18 S18
+Field 17 S17
+Field 16 S16
+Field 15 S15
+Field 14 S14
+Field 13 S13
+Field 12 S12
+Field 11 S11
+Field 10 S10
+Field 9 S9
+Field 8 S8
+Field 7 S7
+Field 6 S6
+Field 5 S5
+Field 4 S4
+Field 3 S3
+Field 2 S2
+Field 1 S1
+Field 0 S0
+EndSysreg
+
Sysreg TRFCR_EL1 3 0 1 2 1
Res0 63:7
UnsignedEnum 6:5 TS
@@ -2078,6 +2722,16 @@ Field 1 ExTRE
Field 0 E0TRE
EndSysreg
+Sysreg TRCITECR_EL1 3 0 1 2 3
+Res0 63:2
+Field 1 E1E
+Field 0 E0E
+EndSysreg
+
+Sysreg TRCITECR_EL12 3 5 1 2 3
+Mapping TRCITECR_EL1
+EndSysreg
+
Sysreg SMPRI_EL1 3 0 1 2 4
Res0 63:4
Field 3:0 PRIORITY
@@ -2226,7 +2880,28 @@ Field 15:0 MINLAT
EndSysreg
Sysreg PMSIDR_EL1 3 0 9 9 7
-Res0 63:25
+Res0 63:33
+UnsignedEnum 32 SME
+ 0b0 NI
+ 0b1 IMP
+EndEnum
+UnsignedEnum 31:28 ALTCLK
+ 0b0000 NI
+ 0b0001 IMP
+ 0b1111 IMPDEF
+EndEnum
+UnsignedEnum 27 FPF
+ 0b0 NI
+ 0b1 IMP
+EndEnum
+UnsignedEnum 26 EFT
+ 0b0 NI
+ 0b1 IMP
+EndEnum
+UnsignedEnum 25 CRR
+ 0b0 NI
+ 0b1 IMP
+EndEnum
Field 24 PBT
Field 23:20 FORMAT
Enum 19:16 COUNTSIZE
@@ -2244,7 +2919,10 @@ Enum 11:8 INTERVAL
0b0111 3072
0b1000 4096
EndEnum
-Res0 7
+UnsignedEnum 7 FDS
+ 0b0 NI
+ 0b1 IMP
+EndEnum
Field 6 FnE
Field 5 ERND
Field 4 LDS
@@ -2287,6 +2965,16 @@ Field 16 COLL
Field 15:0 MSS
EndSysreg
+Sysreg PMSDSFR_EL1 3 0 9 10 4
+Field 63:0 S
+EndSysreg
+
+Sysreg PMBMAR_EL1 3 0 9 10 5
+Res0 63:10
+Field 9:8 SH
+Field 7:0 Attr
+EndSysreg
+
Sysreg PMBIDR_EL1 3 0 9 10 7
Res0 63:12
Enum 11:8 EA
@@ -2300,6 +2988,21 @@ Field 4 P
Field 3:0 ALIGN
EndSysreg
+Sysreg TRBMPAM_EL1 3 0 9 11 5
+Res0 63:27
+Field 26 EN
+Field 25:24 MPAM_SP
+Field 23:16 PMG
+Field 15:0 PARTID
+EndSysreg
+
+Sysreg PMSSCR_EL1 3 0 9 13 3
+Res0 63:33
+Field 32 NC
+Res0 31:1
+Field 0 SS
+EndSysreg
+
Sysreg PMUACR_EL1 3 0 9 14 4
Res0 63:33
Field 32 F0
@@ -2307,11 +3010,29 @@ Field 31 C
Field 30:0 P
EndSysreg
+Sysreg PMECR_EL1 3 0 9 14 5
+Res0 63:5
+Field 4:3 SSE
+Field 2 KPME
+Field 1:0 PMEE
+EndSysreg
+
+Sysreg PMIAR_EL1 3 0 9 14 7
+Field 63:0 ADDRESS
+EndSysreg
+
Sysreg PMSELR_EL0 3 3 9 12 5
Res0 63:5
Field 4:0 SEL
EndSysreg
+Sysreg PMZR_EL0 3 3 9 13 4
+Res0 63:33
+Field 32 F0
+Field 31 C
+Field 30:0 P
+EndSysreg
+
SysregFields CONTEXTIDR_ELx
Res0 63:32
Field 31:0 PROCID
@@ -2450,7 +3171,110 @@ UnsignedEnum 2:0 F8S1
EndEnum
EndSysreg
-SysregFields HFGxTR_EL2
+Sysreg HCR_EL2 3 4 1 1 0
+Field 63:60 TWEDEL
+Field 59 TWEDEn
+Field 58 TID5
+Field 57 DCT
+Field 56 ATA
+Field 55 TTLBOS
+Field 54 TTLBIS
+Field 53 EnSCXT
+Field 52 TOCU
+Field 51 AMVOFFEN
+Field 50 TICAB
+Field 49 TID4
+Field 48 GPF
+Field 47 FIEN
+Field 46 FWB
+Field 45 NV2
+Field 44 AT
+Field 43 NV1
+Field 42 NV
+Field 41 API
+Field 40 APK
+Field 39 TME
+Field 38 MIOCNCE
+Field 37 TEA
+Field 36 TERR
+Field 35 TLOR
+Field 34 E2H
+Field 33 ID
+Field 32 CD
+Field 31 RW
+Field 30 TRVM
+Field 29 HCD
+Field 28 TDZ
+Field 27 TGE
+Field 26 TVM
+Field 25 TTLB
+Field 24 TPU
+Field 23 TPCP
+Field 22 TSW
+Field 21 TACR
+Field 20 TIDCP
+Field 19 TSC
+Field 18 TID3
+Field 17 TID2
+Field 16 TID1
+Field 15 TID0
+Field 14 TWE
+Field 13 TWI
+Field 12 DC
+UnsignedEnum 11:10 BSU
+ 0b00 NONE
+ 0b01 IS
+ 0b10 OS
+ 0b11 FS
+EndEnum
+Field 9 FB
+Field 8 VSE
+Field 7 VI
+Field 6 VF
+Field 5 AMO
+Field 4 IMO
+Field 3 FMO
+Field 2 PTW
+Field 1 SWIO
+Field 0 VM
+EndSysreg
+
+Sysreg MDCR_EL2 3 4 1 1 1
+Res0 63:51
+Field 50 EnSTEPOP
+Res0 49:44
+Field 43 EBWE
+Res0 42
+Field 41:40 PMEE
+Res0 39:37
+Field 36 HPMFZS
+Res0 35:32
+Field 31:30 PMSSE
+Field 29 HPMFZO
+Field 28 MTPME
+Field 27 TDCC
+Field 26 HLP
+Field 25:24 E2TB
+Field 23 HCCD
+Res0 22:20
+Field 19 TTRF
+Res0 18
+Field 17 HPMD
+Res0 16
+Field 15 EnSPM
+Field 14 TPMS
+Field 13:12 E2PB
+Field 11 TDRA
+Field 10 TDOSA
+Field 9 TDA
+Field 8 TDE
+Field 7 HPME
+Field 6 TPM
+Field 5 TPMCR
+Field 4:0 HPMN
+EndSysreg
+
+Sysreg HFGRTR_EL2 3 4 1 1 4
Field 63 nAMAIR2_EL1
Field 62 nMAIR2_EL1
Field 61 nS2POR_EL1
@@ -2515,53 +3339,74 @@ Field 3 AMAIR_EL1
Field 2 AIDR_EL1
Field 1 AFSR1_EL1
Field 0 AFSR0_EL1
-EndSysregFields
-
-Sysreg MDCR_EL2 3 4 1 1 1
-Res0 63:51
-Field 50 EnSTEPOP
-Res0 49:44
-Field 43 EBWE
-Res0 42
-Field 41:40 PMEE
-Res0 39:37
-Field 36 HPMFZS
-Res0 35:32
-Field 31:30 PMSSE
-Field 29 HPMFZO
-Field 28 MTPME
-Field 27 TDCC
-Field 26 HLP
-Field 25:24 E2TB
-Field 23 HCCD
-Res0 22:20
-Field 19 TTRF
-Res0 18
-Field 17 HPMD
-Res0 16
-Field 15 EnSPM
-Field 14 TPMS
-Field 13:12 E2PB
-Field 11 TDRA
-Field 10 TDOSA
-Field 9 TDA
-Field 8 TDE
-Field 7 HPME
-Field 6 TPM
-Field 5 TPMCR
-Field 4:0 HPMN
-EndSysreg
-
-Sysreg HFGRTR_EL2 3 4 1 1 4
-Fields HFGxTR_EL2
EndSysreg
Sysreg HFGWTR_EL2 3 4 1 1 5
-Fields HFGxTR_EL2
+Field 63 nAMAIR2_EL1
+Field 62 nMAIR2_EL1
+Field 61 nS2POR_EL1
+Field 60 nPOR_EL1
+Field 59 nPOR_EL0
+Field 58 nPIR_EL1
+Field 57 nPIRE0_EL1
+Field 56 nRCWMASK_EL1
+Field 55 nTPIDR2_EL0
+Field 54 nSMPRI_EL1
+Field 53 nGCS_EL1
+Field 52 nGCS_EL0
+Res0 51
+Field 50 nACCDATA_EL1
+Field 49 ERXADDR_EL1
+Field 48 ERXPFGCDN_EL1
+Field 47 ERXPFGCTL_EL1
+Res0 46
+Field 45 ERXMISCn_EL1
+Field 44 ERXSTATUS_EL1
+Field 43 ERXCTLR_EL1
+Res0 42
+Field 41 ERRSELR_EL1
+Res0 40
+Field 39 ICC_IGRPENn_EL1
+Field 38 VBAR_EL1
+Field 37 TTBR1_EL1
+Field 36 TTBR0_EL1
+Field 35 TPIDR_EL0
+Field 34 TPIDRRO_EL0
+Field 33 TPIDR_EL1
+Field 32 TCR_EL1
+Field 31 SCXTNUM_EL0
+Field 30 SCXTNUM_EL1
+Field 29 SCTLR_EL1
+Res0 28
+Field 27 PAR_EL1
+Res0 26:25
+Field 24 MAIR_EL1
+Field 23 LORSA_EL1
+Field 22 LORN_EL1
+Res0 21
+Field 20 LOREA_EL1
+Field 19 LORC_EL1
+Res0 18
+Field 17 FAR_EL1
+Field 16 ESR_EL1
+Res0 15:14
+Field 13 CSSELR_EL1
+Field 12 CPACR_EL1
+Field 11 CONTEXTIDR_EL1
+Res0 10:9
+Field 8 APIBKey
+Field 7 APIAKey
+Field 6 APGAKey
+Field 5 APDBKey
+Field 4 APDAKey
+Field 3 AMAIR_EL1
+Res0 2
+Field 1 AFSR1_EL1
+Field 0 AFSR0_EL1
EndSysreg
Sysreg HFGITR_EL2 3 4 1 1 6
-Res0 63
+Field 63 PSBCSYNC
Field 62 ATS1E1A
Res0 61
Field 60 COSPRCTX
@@ -2971,6 +3816,12 @@ Sysreg SMCR_EL2 3 4 1 2 6
Fields SMCR_ELx
EndSysreg
+Sysreg VNCR_EL2 3 4 2 2 0
+Field 63:57 RESS
+Field 56:12 BADDR
+Res0 11:0
+EndSysreg
+
Sysreg GCSCR_EL2 3 4 2 5 0
Fields GCSCR_ELx
EndSysreg
@@ -3244,6 +4095,60 @@ Sysreg TTBR1_EL1 3 0 2 0 1
Fields TTBRx_EL1
EndSysreg
+Sysreg TCR_EL1 3 0 2 0 2
+Res0 63:62
+Field 61 MTX1
+Field 60 MTX0
+Field 59 DS
+Field 58 TCMA1
+Field 57 TCMA0
+Field 56 E0PD1
+Field 55 E0PD0
+Field 54 NFD1
+Field 53 NFD0
+Field 52 TBID1
+Field 51 TBID0
+Field 50 HWU162
+Field 49 HWU161
+Field 48 HWU160
+Field 47 HWU159
+Field 46 HWU062
+Field 45 HWU061
+Field 44 HWU060
+Field 43 HWU059
+Field 42 HPD1
+Field 41 HPD0
+Field 40 HD
+Field 39 HA
+Field 38 TBI1
+Field 37 TBI0
+Field 36 AS
+Res0 35
+Field 34:32 IPS
+Field 31:30 TG1
+Field 29:28 SH1
+Field 27:26 ORGN1
+Field 25:24 IRGN1
+Field 23 EPD1
+Field 22 A1
+Field 21:16 T1SZ
+Field 15:14 TG0
+Field 13:12 SH0
+Field 11:10 ORGN0
+Field 9:8 IRGN0
+Field 7 EPD0
+Res0 6
+Field 5:0 T0SZ
+EndSysreg
+
+Sysreg TCR_EL12 3 5 2 0 2
+Mapping TCR_EL1
+EndSysreg
+
+Sysreg TCRALIAS_EL1 3 0 2 7 6
+Mapping TCR_EL1
+EndSysreg
+
Sysreg TCR2_EL1 3 0 2 0 3
Res0 63:16
Field 15 DisCH1
@@ -3264,6 +4169,10 @@ Sysreg TCR2_EL12 3 5 2 0 3
Mapping TCR2_EL1
EndSysreg
+Sysreg TCR2ALIAS_EL1 3 0 2 7 7
+Mapping TCR2_EL1
+EndSysreg
+
Sysreg TCR2_EL2 3 4 2 0 3
Res0 63:16
Field 15 DisCH1
@@ -3525,7 +4434,12 @@ Field 31:0 TRG
EndSysreg
Sysreg TRBIDR_EL1 3 0 9 11 7
-Res0 63:12
+Res0 63:16
+UnsignedEnum 15:12 MPAM
+ 0b0000 NI
+ 0b0001 DEFAULT
+ 0b0010 IMP
+EndEnum
Enum 11:8 EA
0b0000 NON_DESC
0b0001 IGNORE
diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S
index 9d01361696a1..ae551b857137 100644
--- a/arch/arm64/xen/hypercall.S
+++ b/arch/arm64/xen/hypercall.S
@@ -83,7 +83,26 @@ HYPERCALL3(vcpu_op);
HYPERCALL1(platform_op_raw);
HYPERCALL2(multicall);
HYPERCALL2(vm_assist);
-HYPERCALL3(dm_op);
+
+SYM_FUNC_START(HYPERVISOR_dm_op)
+ mov x16, #__HYPERVISOR_dm_op; \
+ /*
+ * dm_op hypercalls are issued by the userspace. The kernel needs to
+ * enable access to TTBR0_EL1 as the hypervisor would issue stage 1
+ * translations to user memory via AT instructions. Since AT
+ * instructions are not affected by the PAN bit (ARMv8.1), we only
+ * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
+ * is enabled (it implies that hardware UAO and PAN disabled).
+ */
+ uaccess_ttbr0_enable x6, x7, x8
+ hvc XEN_IMM
+
+ /*
+ * Disable userspace access from kernel once the hyp call completed.
+ */
+ uaccess_ttbr0_disable x6, x7
+ ret
+SYM_FUNC_END(HYPERVISOR_dm_op);
SYM_FUNC_START(privcmd_call)
mov x16, x0