summaryrefslogtreecommitdiffstats
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig39
-rw-r--r--arch/arm64/Kconfig.platforms1
-rw-r--r--arch/arm64/Makefile17
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts2
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi43
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts2
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi7
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/crypto/Kconfig11
-rw-r--r--arch/arm64/crypto/Makefile6
-rw-r--r--arch/arm64/crypto/aes-ce.S5
-rw-r--r--arch/arm64/crypto/aes-glue.c217
-rw-r--r--arch/arm64/crypto/aes-modes.S416
-rw-r--r--arch/arm64/crypto/aes-neon.S6
-rw-r--r--arch/arm64/crypto/crc32-ce-core.S287
-rw-r--r--arch/arm64/crypto/crc32-ce-glue.c244
-rw-r--r--arch/arm64/crypto/crct10dif-ce-core.S314
-rw-r--r--arch/arm64/crypto/crct10dif-ce-glue.c14
-rw-r--r--arch/arm64/crypto/speck-neon-core.S352
-rw-r--r--arch/arm64/crypto/speck-neon-glue.c282
-rw-r--r--arch/arm64/include/asm/assembler.h7
-rw-r--r--arch/arm64/include/asm/cache.h40
-rw-r--r--arch/arm64/include/asm/compat.h27
-rw-r--r--arch/arm64/include/asm/compiler.h30
-rw-r--r--arch/arm64/include/asm/cpucaps.h7
-rw-r--r--arch/arm64/include/asm/cpufeature.h30
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/daifflags.h15
-rw-r--r--arch/arm64/include/asm/device.h1
-rw-r--r--arch/arm64/include/asm/dma-mapping.h7
-rw-r--r--arch/arm64/include/asm/esr.h77
-rw-r--r--arch/arm64/include/asm/hugetlb.h39
-rw-r--r--arch/arm64/include/asm/io.h9
-rw-r--r--arch/arm64/include/asm/jump_label.h38
-rw-r--r--arch/arm64/include/asm/kernel-pgtable.h2
-rw-r--r--arch/arm64/include/asm/kvm_arm.h156
-rw-r--r--arch/arm64/include/asm/kvm_asm.h3
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h2
-rw-r--r--arch/arm64/include/asm/kvm_host.h31
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h10
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h47
-rw-r--r--arch/arm64/include/asm/mmu.h3
-rw-r--r--arch/arm64/include/asm/mmu_context.h17
-rw-r--r--arch/arm64/include/asm/page.h2
-rw-r--r--arch/arm64/include/asm/paravirt.h9
-rw-r--r--arch/arm64/include/asm/pgtable-hwdef.h2
-rw-r--r--arch/arm64/include/asm/pgtable.h48
-rw-r--r--arch/arm64/include/asm/processor.h11
-rw-r--r--arch/arm64/include/asm/ptrace.h4
-rw-r--r--arch/arm64/include/asm/stage2_pgtable-nopmd.h42
-rw-r--r--arch/arm64/include/asm/stage2_pgtable-nopud.h39
-rw-r--r--arch/arm64/include/asm/stage2_pgtable.h236
-rw-r--r--arch/arm64/include/asm/stat.h2
-rw-r--r--arch/arm64/include/asm/string.h14
-rw-r--r--arch/arm64/include/asm/sysreg.h44
-rw-r--r--arch/arm64/include/asm/system_misc.h3
-rw-r--r--arch/arm64/include/asm/tlb.h34
-rw-r--r--arch/arm64/include/asm/tlbflush.h112
-rw-r--r--arch/arm64/include/asm/topology.h3
-rw-r--r--arch/arm64/include/asm/traps.h5
-rw-r--r--arch/arm64/include/asm/uaccess.h1
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/xen/events.h2
-rw-r--r--arch/arm64/include/uapi/asm/Kbuild1
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h1
-rw-r--r--arch/arm64/include/uapi/asm/ptrace.h1
-rw-r--r--arch/arm64/include/uapi/asm/siginfo.h24
-rw-r--r--arch/arm64/include/uapi/asm/unistd.h1
-rw-r--r--arch/arm64/kernel/Makefile1
-rw-r--r--arch/arm64/kernel/arm64ksyms.c7
-rw-r--r--arch/arm64/kernel/cpu_errata.c96
-rw-r--r--arch/arm64/kernel/cpufeature.c195
-rw-r--r--arch/arm64/kernel/cpuinfo.c11
-rw-r--r--arch/arm64/kernel/crash_core.c19
-rw-r--r--arch/arm64/kernel/debug-monitors.c11
-rw-r--r--arch/arm64/kernel/entry.S18
-rw-r--r--arch/arm64/kernel/fpsimd.c10
-rw-r--r--arch/arm64/kernel/head.S40
-rw-r--r--arch/arm64/kernel/jump_label.c6
-rw-r--r--arch/arm64/kernel/machine_kexec.c11
-rw-r--r--arch/arm64/kernel/paravirt.c4
-rw-r--r--arch/arm64/kernel/pci.c5
-rw-r--r--arch/arm64/kernel/perf_event.c7
-rw-r--r--arch/arm64/kernel/probes/kprobes.c2
-rw-r--r--arch/arm64/kernel/process.c4
-rw-r--r--arch/arm64/kernel/psci.c1
-rw-r--r--arch/arm64/kernel/ptrace.c16
-rw-r--r--arch/arm64/kernel/setup.c60
-rw-r--r--arch/arm64/kernel/sleep.S1
-rw-r--r--arch/arm64/kernel/smp.c2
-rw-r--r--arch/arm64/kernel/ssbd.c24
-rw-r--r--arch/arm64/kernel/suspend.c4
-rw-r--r--arch/arm64/kernel/sys_compat.c13
-rw-r--r--arch/arm64/kernel/traps.c276
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S36
-rw-r--r--arch/arm64/kvm/guest.c61
-rw-r--r--arch/arm64/kvm/handle_exit.c7
-rw-r--r--arch/arm64/kvm/hyp-init.S3
-rw-r--r--arch/arm64/kvm/hyp/Makefile1
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S16
-rw-r--r--arch/arm64/kvm/hyp/s2-setup.c90
-rw-r--r--arch/arm64/kvm/hyp/switch.c13
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c30
-rw-r--r--arch/arm64/kvm/hyp/tlb.c4
-rw-r--r--arch/arm64/kvm/reset.c108
-rw-r--r--arch/arm64/lib/Makefile4
-rw-r--r--arch/arm64/lib/crc32.S60
-rw-r--r--arch/arm64/lib/memchr.S2
-rw-r--r--arch/arm64/lib/memcmp.S2
-rw-r--r--arch/arm64/lib/strchr.S2
-rw-r--r--arch/arm64/lib/strcmp.S2
-rw-r--r--arch/arm64/lib/strlen.S2
-rw-r--r--arch/arm64/lib/strncmp.S2
-rw-r--r--arch/arm64/lib/strnlen.S2
-rw-r--r--arch/arm64/lib/strrchr.S2
-rw-r--r--arch/arm64/mm/context.c11
-rw-r--r--arch/arm64/mm/dma-mapping.c267
-rw-r--r--arch/arm64/mm/dump.c6
-rw-r--r--arch/arm64/mm/fault.c132
-rw-r--r--arch/arm64/mm/hugetlbpage.c50
-rw-r--r--arch/arm64/mm/init.c2
-rw-r--r--arch/arm64/mm/kasan_init.c2
-rw-r--r--arch/arm64/mm/mmu.c56
-rw-r--r--arch/arm64/mm/numa.c13
-rw-r--r--arch/arm64/mm/proc.S11
125 files changed, 2704 insertions, 2649 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1b1a0e95c751..964f682a2b7b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -11,6 +11,8 @@ config ARM64
select ARCH_CLOCKSOURCE_DATA
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_DMA_COHERENT_TO_PFN
+ select ARCH_HAS_DMA_MMAP_PGPROT
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FAST_MULTIPLIER
@@ -24,6 +26,8 @@ config ARM64
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_HAS_STRICT_MODULE_RWX
+ select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYSCALL_WRAPPER
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
select ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -75,6 +79,7 @@ config ARM64
select CLONE_BACKWARDS
select COMMON_CLK
select CPU_PM if (SUSPEND || CPU_IDLE)
+ select CRC32
select DCACHE_WORD_ACCESS
select DMA_DIRECT_OPS
select EDAC_SUPPORT
@@ -104,6 +109,7 @@ config ARM64
select HAVE_ARCH_BITREVERSE
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
+ select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS
@@ -142,6 +148,7 @@ config ARM64
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RCU_TABLE_FREE
+ select HAVE_RCU_TABLE_INVALIDATE
select HAVE_RSEQ
select HAVE_STACKPROTECTOR
select HAVE_SYSCALL_TRACEPOINTS
@@ -479,6 +486,19 @@ config ARM64_ERRATUM_1024718
If unsure, say Y.
+config ARM64_ERRATUM_1188873
+ bool "Cortex-A76: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
+ default y
+ select ARM_ARCH_TIMER_OOL_WORKAROUND
+ help
+ This option adds work arounds for ARM Cortex-A76 erratum 1188873
+
+ Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could cause
+ register corruption when accessing the timer registers from
+ AArch32 userspace.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
@@ -769,9 +789,6 @@ source kernel/Kconfig.hz
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
-config ARCH_HAS_HOLES_MEMORYMODEL
- def_bool y if SPARSEMEM
-
config ARCH_SPARSEMEM_ENABLE
def_bool y
select SPARSEMEM_VMEMMAP_ENABLE
@@ -786,7 +803,7 @@ config ARCH_FLATMEM_ENABLE
def_bool !NUMA
config HAVE_ARCH_PFN_VALID
- def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
+ def_bool y
config HW_PERF_EVENTS
def_bool y
@@ -1132,6 +1149,20 @@ config ARM64_RAS_EXTN
and access the new registers if the system supports the extension.
Platform RAS features may additionally depend on firmware support.
+config ARM64_CNP
+ bool "Enable support for Common Not Private (CNP) translations"
+ default y
+ depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN
+ help
+ Common Not Private (CNP) allows translation table entries to
+ be shared between different PEs in the same inner shareable
+ domain, so the hardware can use this fact to optimise the
+ caching of such entries in the TLB.
+
+ Selecting this option allows the CNP feature to be detected
+ at runtime, and does not affect PEs that do not implement
+ this feature.
+
endmenu
config ARM64_SVE
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 393d2b524284..5a89a957641b 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -128,6 +128,7 @@ config ARCH_MVEBU
select MVEBU_ICU
select MVEBU_ODMI
select MVEBU_PIC
+ select MVEBU_SEI
select OF_GPIO
select PINCTRL
select PINCTRL_ARMADA_37XX
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 106039d25e2f..b4e994cd3a42 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -113,9 +113,8 @@ core-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
# Default target when executing plain make
boot := arch/arm64/boot
KBUILD_IMAGE := $(boot)/Image.gz
-KBUILD_DTBS := dtbs
-all: Image.gz $(KBUILD_DTBS)
+all: Image.gz
Image: vmlinux
@@ -127,17 +126,6 @@ Image.%: Image
zinstall install:
$(Q)$(MAKE) $(build)=$(boot) $@
-%.dtb: scripts
- $(Q)$(MAKE) $(build)=$(boot)/dts $(boot)/dts/$@
-
-PHONY += dtbs dtbs_install
-
-dtbs: prepare scripts
- $(Q)$(MAKE) $(build)=$(boot)/dts
-
-dtbs_install:
- $(Q)$(MAKE) $(dtbinst)=$(boot)/dts
-
PHONY += vdso_install
vdso_install:
$(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@
@@ -145,7 +133,6 @@ vdso_install:
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
$(Q)$(MAKE) $(clean)=$(boot)
- $(Q)$(MAKE) $(clean)=$(boot)/dts
# We need to generate vdso-offsets.h before compiling certain files in kernel/.
# In order to do that, we should use the archprepare target, but we can't since
@@ -160,8 +147,6 @@ vdso_prepare: prepare0
define archhelp
echo '* Image.gz - Compressed kernel image (arch/$(ARCH)/boot/Image.gz)'
echo ' Image - Uncompressed kernel image (arch/$(ARCH)/boot/Image)'
- echo '* dtbs - Build device tree blobs for enabled boards'
- echo ' dtbs_install - Install dtbs to $(INSTALL_DTBS_PATH)'
echo ' install - Install uncompressed kernel'
echo ' zinstall - Install compressed kernel'
echo ' Install using (your) ~/bin/installkernel or'
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
index ceffc40810ee..48daec7f78ba 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts
@@ -46,6 +46,7 @@
pinctrl-0 = <&mmc0_pins>;
vmmc-supply = <&reg_cldo1>;
cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>;
+ bus-width = <4>;
status = "okay";
};
@@ -56,6 +57,7 @@
vqmmc-supply = <&reg_bldo2>;
non-removable;
cap-mmc-hw-reset;
+ bus-width = <8>;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index bc6c141d7372..8253a1a9e985 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -137,6 +137,8 @@
reset-names = "stmmaceth", "stmmaceth-ocp";
clocks = <&clkmgr STRATIX10_EMAC0_CLK>;
clock-names = "stmmaceth";
+ tx-fifo-depth = <16384>;
+ rx-fifo-depth = <16384>;
status = "disabled";
};
@@ -150,6 +152,8 @@
reset-names = "stmmaceth", "stmmaceth-ocp";
clocks = <&clkmgr STRATIX10_EMAC1_CLK>;
clock-names = "stmmaceth";
+ tx-fifo-depth = <16384>;
+ rx-fifo-depth = <16384>;
status = "disabled";
};
@@ -163,6 +167,8 @@
reset-names = "stmmaceth", "stmmaceth-ocp";
clocks = <&clkmgr STRATIX10_EMAC2_CLK>;
clock-names = "stmmaceth";
+ tx-fifo-depth = <16384>;
+ rx-fifo-depth = <16384>;
status = "disabled";
};
@@ -467,16 +473,51 @@
status = "disabled";
};
+ sdr: sdr@f8011100 {
+ compatible = "altr,sdr-ctl", "syscon";
+ reg = <0xf8011100 0xc0>;
+ };
+
eccmgr {
- compatible = "altr,socfpga-s10-ecc-manager";
+ compatible = "altr,socfpga-a10-ecc-manager";
+ altr,sysmgr-syscon = <&sysmgr>;
+ #address-cells = <1>;
+ #size-cells = <1>;
interrupts = <0 15 4>, <0 95 4>;
interrupt-controller;
#interrupt-cells = <2>;
+ ranges;
sdramedac {
compatible = "altr,sdram-edac-s10";
+ altr,sdr-syscon = <&sdr>;
interrupts = <16 4>, <48 4>;
};
+
+ usb0-ecc@ff8c4000 {
+ compatible = "altr,socfpga-usb-ecc";
+ reg = <0xff8c4000 0x100>;
+ altr,ecc-parent = <&usb0>;
+ interrupts = <2 4>,
+ <34 4>;
+ };
+
+ emac0-rx-ecc@ff8c0000 {
+ compatible = "altr,socfpga-eth-mac-ecc";
+ reg = <0xff8c0000 0x100>;
+ altr,ecc-parent = <&gmac0>;
+ interrupts = <4 4>,
+ <36 4>;
+ };
+
+ emac0-tx-ecc@ff8c0400 {
+ compatible = "altr,socfpga-eth-mac-ecc";
+ reg = <0xff8c0400 0x100>;
+ altr,ecc-parent = <&gmac0>;
+ interrupts = <5 4>,
+ <37 4>;
+ };
+
};
qspi: spi@ff8d2000 {
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index 3d0db3024f6b..2e3863ee12b3 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -79,7 +79,7 @@
phy-mode = "rgmii";
phy-handle = <&phy0>;
- max-frame-size = <3800>;
+ max-frame-size = <9000>;
mdio0 {
#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index e45607419692..d188774a36e8 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -150,6 +150,7 @@
#address-cells = <2>;
#size-cells = <2>;
ranges;
+ dma-ranges = <0x0 0x0 0x0 0x0 0x10000 0x00000000>;
clockgen: clocking@1300000 {
compatible = "fsl,ls2080a-clockgen";
@@ -337,6 +338,8 @@
reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */
<0x00000000 0x08340000 0 0x40000>; /* MC control reg */
msi-parent = <&its>;
+ iommu-map = <0 &smmu 0 0>; /* This is fixed-up by u-boot */
+ dma-coherent;
#address-cells = <3>;
#size-cells = <1>;
@@ -440,6 +443,9 @@
compatible = "arm,mmu-500";
reg = <0 0x5000000 0 0x800000>;
#global-interrupts = <12>;
+ #iommu-cells = <1>;
+ stream-match-mask = <0x7C00>;
+ dma-coherent;
interrupts = <0 13 4>, /* global secure fault */
<0 14 4>, /* combined secure interrupt */
<0 15 4>, /* global non-secure fault */
@@ -482,7 +488,6 @@
<0 204 4>, <0 205 4>,
<0 206 4>, <0 207 4>,
<0 208 4>, <0 209 4>;
- mmu-masters = <&fsl_mc 0x300 0>;
};
dspi: spi@2100000 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index db8d364f8476..3d165b4cdd2a 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -698,6 +698,7 @@ CONFIG_MEMTEST=y
CONFIG_SECURITY=y
CONFIG_CRYPTO_ECHAINIV=y
CONFIG_CRYPTO_ANSI_CPRNG=y
+CONFIG_CRYPTO_DEV_FSL_DPAA2_CAAM=y
CONFIG_ARM64_CRYPTO=y
CONFIG_CRYPTO_SHA1_ARM64_CE=y
CONFIG_CRYPTO_SHA2_ARM64_CE=y
@@ -706,7 +707,6 @@ CONFIG_CRYPTO_SHA3_ARM64=m
CONFIG_CRYPTO_SM3_ARM64_CE=m
CONFIG_CRYPTO_GHASH_ARM64_CE=y
CONFIG_CRYPTO_CRCT10DIF_ARM64_CE=m
-CONFIG_CRYPTO_CRC32_ARM64_CE=m
CONFIG_CRYPTO_AES_ARM64_CE_CCM=y
CONFIG_CRYPTO_AES_ARM64_CE_BLK=y
CONFIG_CRYPTO_CHACHA20_NEON=m
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index e3fdb0fd6f70..a5606823ed4d 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -66,11 +66,6 @@ config CRYPTO_CRCT10DIF_ARM64_CE
depends on KERNEL_MODE_NEON && CRC_T10DIF
select CRYPTO_HASH
-config CRYPTO_CRC32_ARM64_CE
- tristate "CRC32 and CRC32C digest algorithms using ARMv8 extensions"
- depends on CRC32
- select CRYPTO_HASH
-
config CRYPTO_AES_ARM64
tristate "AES core cipher using scalar instructions"
select CRYPTO_AES
@@ -119,10 +114,4 @@ config CRYPTO_AES_ARM64_BS
select CRYPTO_AES_ARM64
select CRYPTO_SIMD
-config CRYPTO_SPECK_NEON
- tristate "NEON accelerated Speck cipher algorithms"
- depends on KERNEL_MODE_NEON
- select CRYPTO_BLKCIPHER
- select CRYPTO_SPECK
-
endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index bcafd016618e..f476fede09ba 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -32,9 +32,6 @@ ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
obj-$(CONFIG_CRYPTO_CRCT10DIF_ARM64_CE) += crct10dif-ce.o
crct10dif-ce-y := crct10dif-ce-core.o crct10dif-ce-glue.o
-obj-$(CONFIG_CRYPTO_CRC32_ARM64_CE) += crc32-ce.o
-crc32-ce-y:= crc32-ce-core.o crc32-ce-glue.o
-
obj-$(CONFIG_CRYPTO_AES_ARM64_CE) += aes-ce-cipher.o
aes-ce-cipher-y := aes-ce-core.o aes-ce-glue.o
@@ -56,9 +53,6 @@ sha512-arm64-y := sha512-glue.o sha512-core.o
obj-$(CONFIG_CRYPTO_CHACHA20_NEON) += chacha20-neon.o
chacha20-neon-y := chacha20-neon-core.o chacha20-neon-glue.o
-obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
-speck-neon-y := speck-neon-core.o speck-neon-glue.o
-
obj-$(CONFIG_CRYPTO_AES_ARM64) += aes-arm64.o
aes-arm64-y := aes-cipher-core.o aes-cipher-glue.o
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 623e74ed1c67..143070510809 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -17,6 +17,11 @@
.arch armv8-a+crypto
+ xtsmask .req v16
+
+ .macro xts_reload_mask, tmp
+ .endm
+
/* preload all round keys */
.macro load_round_keys, rounds, rk
cmp \rounds, #12
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index adcb83eb683c..1e676625ef33 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -15,6 +15,7 @@
#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/xts.h>
@@ -31,6 +32,8 @@
#define aes_ecb_decrypt ce_aes_ecb_decrypt
#define aes_cbc_encrypt ce_aes_cbc_encrypt
#define aes_cbc_decrypt ce_aes_cbc_decrypt
+#define aes_cbc_cts_encrypt ce_aes_cbc_cts_encrypt
+#define aes_cbc_cts_decrypt ce_aes_cbc_cts_decrypt
#define aes_ctr_encrypt ce_aes_ctr_encrypt
#define aes_xts_encrypt ce_aes_xts_encrypt
#define aes_xts_decrypt ce_aes_xts_decrypt
@@ -45,6 +48,8 @@ MODULE_DESCRIPTION("AES-ECB/CBC/CTR/XTS using ARMv8 Crypto Extensions");
#define aes_ecb_decrypt neon_aes_ecb_decrypt
#define aes_cbc_encrypt neon_aes_cbc_encrypt
#define aes_cbc_decrypt neon_aes_cbc_decrypt
+#define aes_cbc_cts_encrypt neon_aes_cbc_cts_encrypt
+#define aes_cbc_cts_decrypt neon_aes_cbc_cts_decrypt
#define aes_ctr_encrypt neon_aes_ctr_encrypt
#define aes_xts_encrypt neon_aes_xts_encrypt
#define aes_xts_decrypt neon_aes_xts_decrypt
@@ -63,30 +68,41 @@ MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
/* defined in aes-modes.S */
-asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void aes_ecb_encrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks);
-asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void aes_ecb_decrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks);
-asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void aes_cbc_encrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks, u8 iv[]);
-asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void aes_cbc_decrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks, u8 iv[]);
-asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+asmlinkage void aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int bytes, u8 const iv[]);
+asmlinkage void aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ int rounds, int bytes, u8 const iv[]);
+
+asmlinkage void aes_ctr_encrypt(u8 out[], u8 const in[], u32 const rk[],
int rounds, int blocks, u8 ctr[]);
-asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u8 const rk1[],
- int rounds, int blocks, u8 const rk2[], u8 iv[],
+asmlinkage void aes_xts_encrypt(u8 out[], u8 const in[], u32 const rk1[],
+ int rounds, int blocks, u32 const rk2[], u8 iv[],
int first);
-asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u8 const rk1[],
- int rounds, int blocks, u8 const rk2[], u8 iv[],
+asmlinkage void aes_xts_decrypt(u8 out[], u8 const in[], u32 const rk1[],
+ int rounds, int blocks, u32 const rk2[], u8 iv[],
int first);
asmlinkage void aes_mac_update(u8 const in[], u32 const rk[], int rounds,
int blocks, u8 dg[], int enc_before,
int enc_after);
+struct cts_cbc_req_ctx {
+ struct scatterlist sg_src[2];
+ struct scatterlist sg_dst[2];
+ struct skcipher_request subreq;
+};
+
struct crypto_aes_xts_ctx {
struct crypto_aes_ctx key1;
struct crypto_aes_ctx __aligned(8) key2;
@@ -142,7 +158,7 @@ static int ecb_encrypt(struct skcipher_request *req)
while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
kernel_neon_begin();
aes_ecb_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key_enc, rounds, blocks);
+ ctx->key_enc, rounds, blocks);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -162,7 +178,7 @@ static int ecb_decrypt(struct skcipher_request *req)
while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
kernel_neon_begin();
aes_ecb_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key_dec, rounds, blocks);
+ ctx->key_dec, rounds, blocks);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -182,7 +198,7 @@ static int cbc_encrypt(struct skcipher_request *req)
while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
kernel_neon_begin();
aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key_enc, rounds, blocks, walk.iv);
+ ctx->key_enc, rounds, blocks, walk.iv);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -202,13 +218,149 @@ static int cbc_decrypt(struct skcipher_request *req)
while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
kernel_neon_begin();
aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key_dec, rounds, blocks, walk.iv);
+ ctx->key_dec, rounds, blocks, walk.iv);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
return err;
}
+static int cts_cbc_init_tfm(struct crypto_skcipher *tfm)
+{
+ crypto_skcipher_set_reqsize(tfm, sizeof(struct cts_cbc_req_ctx));
+ return 0;
+}
+
+static int cts_cbc_encrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct cts_cbc_req_ctx *rctx = skcipher_request_ctx(req);
+ int err, rounds = 6 + ctx->key_length / 4;
+ int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+ struct scatterlist *src = req->src, *dst = req->dst;
+ struct skcipher_walk walk;
+
+ skcipher_request_set_tfm(&rctx->subreq, tfm);
+
+ if (req->cryptlen <= AES_BLOCK_SIZE) {
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+ cbc_blocks = 1;
+ }
+
+ if (cbc_blocks > 0) {
+ unsigned int blocks;
+
+ skcipher_request_set_crypt(&rctx->subreq, req->src, req->dst,
+ cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &rctx->subreq, false);
+
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ aes_cbc_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_enc, rounds, blocks, walk.iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (err)
+ return err;
+
+ if (req->cryptlen == AES_BLOCK_SIZE)
+ return 0;
+
+ dst = src = scatterwalk_ffwd(rctx->sg_src, req->src,
+ rctx->subreq.cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(rctx->sg_dst, req->dst,
+ rctx->subreq.cryptlen);
+ }
+
+ /* handle ciphertext stealing */
+ skcipher_request_set_crypt(&rctx->subreq, src, dst,
+ req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &rctx->subreq, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ aes_cbc_cts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_enc, rounds, walk.nbytes, walk.iv);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
+static int cts_cbc_decrypt(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct cts_cbc_req_ctx *rctx = skcipher_request_ctx(req);
+ int err, rounds = 6 + ctx->key_length / 4;
+ int cbc_blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2;
+ struct scatterlist *src = req->src, *dst = req->dst;
+ struct skcipher_walk walk;
+
+ skcipher_request_set_tfm(&rctx->subreq, tfm);
+
+ if (req->cryptlen <= AES_BLOCK_SIZE) {
+ if (req->cryptlen < AES_BLOCK_SIZE)
+ return -EINVAL;
+ cbc_blocks = 1;
+ }
+
+ if (cbc_blocks > 0) {
+ unsigned int blocks;
+
+ skcipher_request_set_crypt(&rctx->subreq, req->src, req->dst,
+ cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &rctx->subreq, false);
+
+ while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
+ kernel_neon_begin();
+ aes_cbc_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_dec, rounds, blocks, walk.iv);
+ kernel_neon_end();
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (err)
+ return err;
+
+ if (req->cryptlen == AES_BLOCK_SIZE)
+ return 0;
+
+ dst = src = scatterwalk_ffwd(rctx->sg_src, req->src,
+ rctx->subreq.cryptlen);
+ if (req->dst != req->src)
+ dst = scatterwalk_ffwd(rctx->sg_dst, req->dst,
+ rctx->subreq.cryptlen);
+ }
+
+ /* handle ciphertext stealing */
+ skcipher_request_set_crypt(&rctx->subreq, src, dst,
+ req->cryptlen - cbc_blocks * AES_BLOCK_SIZE,
+ req->iv);
+
+ err = skcipher_walk_virt(&walk, &rctx->subreq, false);
+ if (err)
+ return err;
+
+ kernel_neon_begin();
+ aes_cbc_cts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
+ ctx->key_dec, rounds, walk.nbytes, walk.iv);
+ kernel_neon_end();
+
+ return skcipher_walk_done(&walk, 0);
+}
+
static int ctr_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -222,7 +374,7 @@ static int ctr_encrypt(struct skcipher_request *req)
while ((blocks = (walk.nbytes / AES_BLOCK_SIZE))) {
kernel_neon_begin();
aes_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key_enc, rounds, blocks, walk.iv);
+ ctx->key_enc, rounds, blocks, walk.iv);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -238,7 +390,7 @@ static int ctr_encrypt(struct skcipher_request *req)
blocks = -1;
kernel_neon_begin();
- aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
+ aes_ctr_encrypt(tail, NULL, ctx->key_enc, rounds,
blocks, walk.iv);
kernel_neon_end();
crypto_xor_cpy(tdst, tsrc, tail, nbytes);
@@ -272,8 +424,8 @@ static int xts_encrypt(struct skcipher_request *req)
for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
kernel_neon_begin();
aes_xts_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key1.key_enc, rounds, blocks,
- (u8 *)ctx->key2.key_enc, walk.iv, first);
+ ctx->key1.key_enc, rounds, blocks,
+ ctx->key2.key_enc, walk.iv, first);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -294,8 +446,8 @@ static int xts_decrypt(struct skcipher_request *req)
for (first = 1; (blocks = (walk.nbytes / AES_BLOCK_SIZE)); first = 0) {
kernel_neon_begin();
aes_xts_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
- (u8 *)ctx->key1.key_dec, rounds, blocks,
- (u8 *)ctx->key2.key_enc, walk.iv, first);
+ ctx->key1.key_dec, rounds, blocks,
+ ctx->key2.key_enc, walk.iv, first);
kernel_neon_end();
err = skcipher_walk_done(&walk, walk.nbytes % AES_BLOCK_SIZE);
}
@@ -336,6 +488,24 @@ static struct skcipher_alg aes_algs[] = { {
.decrypt = cbc_decrypt,
}, {
.base = {
+ .cra_name = "__cts(cbc(aes))",
+ .cra_driver_name = "__cts-cbc-aes-" MODE,
+ .cra_priority = PRIO,
+ .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_blocksize = AES_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_aes_ctx),
+ .cra_module = THIS_MODULE,
+ },
+ .min_keysize = AES_MIN_KEY_SIZE,
+ .max_keysize = AES_MAX_KEY_SIZE,
+ .ivsize = AES_BLOCK_SIZE,
+ .walksize = 2 * AES_BLOCK_SIZE,
+ .setkey = skcipher_aes_setkey,
+ .encrypt = cts_cbc_encrypt,
+ .decrypt = cts_cbc_decrypt,
+ .init = cts_cbc_init_tfm,
+}, {
+ .base = {
.cra_name = "__ctr(aes)",
.cra_driver_name = "__ctr-aes-" MODE,
.cra_priority = PRIO,
@@ -412,7 +582,6 @@ static int cmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
{
struct mac_tfm_ctx *ctx = crypto_shash_ctx(tfm);
be128 *consts = (be128 *)ctx->consts;
- u8 *rk = (u8 *)ctx->key.key_enc;
int rounds = 6 + key_len / 4;
int err;
@@ -422,7 +591,8 @@ static int cmac_setkey(struct crypto_shash *tfm, const u8 *in_key,
/* encrypt the zero vector */
kernel_neon_begin();
- aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, rk, rounds, 1);
+ aes_ecb_encrypt(ctx->consts, (u8[AES_BLOCK_SIZE]){}, ctx->key.key_enc,
+ rounds, 1);
kernel_neon_end();
cmac_gf128_mul_by_x(consts, consts);
@@ -441,7 +611,6 @@ static int xcbc_setkey(struct crypto_shash *tfm, const u8 *in_key,
};
struct mac_tfm_ctx *ctx = crypto_shash_ctx(tfm);
- u8 *rk = (u8 *)ctx->key.key_enc;
int rounds = 6 + key_len / 4;
u8 key[AES_BLOCK_SIZE];
int err;
@@ -451,8 +620,8 @@ static int xcbc_setkey(struct crypto_shash *tfm, const u8 *in_key,
return err;
kernel_neon_begin();
- aes_ecb_encrypt(key, ks[0], rk, rounds, 1);
- aes_ecb_encrypt(ctx->consts, ks[1], rk, rounds, 2);
+ aes_ecb_encrypt(key, ks[0], ctx->key.key_enc, rounds, 1);
+ aes_ecb_encrypt(ctx->consts, ks[1], ctx->key.key_enc, rounds, 2);
kernel_neon_end();
return cbcmac_setkey(tfm, key, sizeof(key));
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index 483a7130cf0e..67700045a0e0 100644
--- a/arch/arm64/crypto/aes-modes.S
+++ b/arch/arm64/crypto/aes-modes.S
@@ -14,12 +14,12 @@
.align 4
aes_encrypt_block4x:
- encrypt_block4x v0, v1, v2, v3, w22, x21, x8, w7
+ encrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7
ret
ENDPROC(aes_encrypt_block4x)
aes_decrypt_block4x:
- decrypt_block4x v0, v1, v2, v3, w22, x21, x8, w7
+ decrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7
ret
ENDPROC(aes_decrypt_block4x)
@@ -31,71 +31,57 @@ ENDPROC(aes_decrypt_block4x)
*/
AES_ENTRY(aes_ecb_encrypt)
- frame_push 5
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
-
-.Lecbencrestart:
- enc_prepare w22, x21, x5
+ enc_prepare w3, x2, x5
.LecbencloopNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lecbenc1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
bl aes_encrypt_block4x
- st1 {v0.16b-v3.16b}, [x19], #64
- cond_yield_neon .Lecbencrestart
+ st1 {v0.16b-v3.16b}, [x0], #64
b .LecbencloopNx
.Lecbenc1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lecbencout
.Lecbencloop:
- ld1 {v0.16b}, [x20], #16 /* get next pt block */
- encrypt_block v0, w22, x21, x5, w6
- st1 {v0.16b}, [x19], #16
- subs w23, w23, #1
+ ld1 {v0.16b}, [x1], #16 /* get next pt block */
+ encrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
bne .Lecbencloop
.Lecbencout:
- frame_pop
+ ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_ecb_encrypt)
AES_ENTRY(aes_ecb_decrypt)
- frame_push 5
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
-
-.Lecbdecrestart:
- dec_prepare w22, x21, x5
+ dec_prepare w3, x2, x5
.LecbdecloopNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lecbdec1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 ct blocks */
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
bl aes_decrypt_block4x
- st1 {v0.16b-v3.16b}, [x19], #64
- cond_yield_neon .Lecbdecrestart
+ st1 {v0.16b-v3.16b}, [x0], #64
b .LecbdecloopNx
.Lecbdec1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lecbdecout
.Lecbdecloop:
- ld1 {v0.16b}, [x20], #16 /* get next ct block */
- decrypt_block v0, w22, x21, x5, w6
- st1 {v0.16b}, [x19], #16
- subs w23, w23, #1
+ ld1 {v0.16b}, [x1], #16 /* get next ct block */
+ decrypt_block v0, w3, x2, x5, w6
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
bne .Lecbdecloop
.Lecbdecout:
- frame_pop
+ ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_ecb_decrypt)
@@ -108,162 +94,211 @@ AES_ENDPROC(aes_ecb_decrypt)
*/
AES_ENTRY(aes_cbc_encrypt)
- frame_push 6
-
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
-
-.Lcbcencrestart:
- ld1 {v4.16b}, [x24] /* get iv */
- enc_prepare w22, x21, x6
+ ld1 {v4.16b}, [x5] /* get iv */
+ enc_prepare w3, x2, x6
.Lcbcencloop4x:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lcbcenc1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
eor v0.16b, v0.16b, v4.16b /* ..and xor with iv */
- encrypt_block v0, w22, x21, x6, w7
+ encrypt_block v0, w3, x2, x6, w7
eor v1.16b, v1.16b, v0.16b
- encrypt_block v1, w22, x21, x6, w7
+ encrypt_block v1, w3, x2, x6, w7
eor v2.16b, v2.16b, v1.16b
- encrypt_block v2, w22, x21, x6, w7
+ encrypt_block v2, w3, x2, x6, w7
eor v3.16b, v3.16b, v2.16b
- encrypt_block v3, w22, x21, x6, w7
- st1 {v0.16b-v3.16b}, [x19], #64
+ encrypt_block v3, w3, x2, x6, w7
+ st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v3.16b
- st1 {v4.16b}, [x24] /* return iv */
- cond_yield_neon .Lcbcencrestart
b .Lcbcencloop4x
.Lcbcenc1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lcbcencout
.Lcbcencloop:
- ld1 {v0.16b}, [x20], #16 /* get next pt block */
+ ld1 {v0.16b}, [x1], #16 /* get next pt block */
eor v4.16b, v4.16b, v0.16b /* ..and xor with iv */
- encrypt_block v4, w22, x21, x6, w7
- st1 {v4.16b}, [x19], #16
- subs w23, w23, #1
+ encrypt_block v4, w3, x2, x6, w7
+ st1 {v4.16b}, [x0], #16
+ subs w4, w4, #1
bne .Lcbcencloop
.Lcbcencout:
- st1 {v4.16b}, [x24] /* return iv */
- frame_pop
+ st1 {v4.16b}, [x5] /* return iv */
ret
AES_ENDPROC(aes_cbc_encrypt)
AES_ENTRY(aes_cbc_decrypt)
- frame_push 6
-
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
-.Lcbcdecrestart:
- ld1 {v7.16b}, [x24] /* get iv */
- dec_prepare w22, x21, x6
+ ld1 {v7.16b}, [x5] /* get iv */
+ dec_prepare w3, x2, x6
.LcbcdecloopNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lcbcdec1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 ct blocks */
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
mov v4.16b, v0.16b
mov v5.16b, v1.16b
mov v6.16b, v2.16b
bl aes_decrypt_block4x
- sub x20, x20, #16
+ sub x1, x1, #16
eor v0.16b, v0.16b, v7.16b
eor v1.16b, v1.16b, v4.16b
- ld1 {v7.16b}, [x20], #16 /* reload 1 ct block */
+ ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */
eor v2.16b, v2.16b, v5.16b
eor v3.16b, v3.16b, v6.16b
- st1 {v0.16b-v3.16b}, [x19], #64
- st1 {v7.16b}, [x24] /* return iv */
- cond_yield_neon .Lcbcdecrestart
+ st1 {v0.16b-v3.16b}, [x0], #64
b .LcbcdecloopNx
.Lcbcdec1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lcbcdecout
.Lcbcdecloop:
- ld1 {v1.16b}, [x20], #16 /* get next ct block */
+ ld1 {v1.16b}, [x1], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
- decrypt_block v0, w22, x21, x6, w7
+ decrypt_block v0, w3, x2, x6, w7
eor v0.16b, v0.16b, v7.16b /* xor with iv => pt */
mov v7.16b, v1.16b /* ct is next iv */
- st1 {v0.16b}, [x19], #16
- subs w23, w23, #1
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
bne .Lcbcdecloop
.Lcbcdecout:
- st1 {v7.16b}, [x24] /* return iv */
- frame_pop
+ st1 {v7.16b}, [x5] /* return iv */
+ ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_cbc_decrypt)
/*
+ * aes_cbc_cts_encrypt(u8 out[], u8 const in[], u32 const rk[],
+ * int rounds, int bytes, u8 const iv[])
+ * aes_cbc_cts_decrypt(u8 out[], u8 const in[], u32 const rk[],
+ * int rounds, int bytes, u8 const iv[])
+ */
+
+AES_ENTRY(aes_cbc_cts_encrypt)
+ adr_l x8, .Lcts_permute_table
+ sub x4, x4, #16
+ add x9, x8, #32
+ add x8, x8, x4
+ sub x9, x9, x4
+ ld1 {v3.16b}, [x8]
+ ld1 {v4.16b}, [x9]
+
+ ld1 {v0.16b}, [x1], x4 /* overlapping loads */
+ ld1 {v1.16b}, [x1]
+
+ ld1 {v5.16b}, [x5] /* get iv */
+ enc_prepare w3, x2, x6
+
+ eor v0.16b, v0.16b, v5.16b /* xor with iv */
+ tbl v1.16b, {v1.16b}, v4.16b
+ encrypt_block v0, w3, x2, x6, w7
+
+ eor v1.16b, v1.16b, v0.16b
+ tbl v0.16b, {v0.16b}, v3.16b
+ encrypt_block v1, w3, x2, x6, w7
+
+ add x4, x0, x4
+ st1 {v0.16b}, [x4] /* overlapping stores */
+ st1 {v1.16b}, [x0]
+ ret
+AES_ENDPROC(aes_cbc_cts_encrypt)
+
+AES_ENTRY(aes_cbc_cts_decrypt)
+ adr_l x8, .Lcts_permute_table
+ sub x4, x4, #16
+ add x9, x8, #32
+ add x8, x8, x4
+ sub x9, x9, x4
+ ld1 {v3.16b}, [x8]
+ ld1 {v4.16b}, [x9]
+
+ ld1 {v0.16b}, [x1], x4 /* overlapping loads */
+ ld1 {v1.16b}, [x1]
+
+ ld1 {v5.16b}, [x5] /* get iv */
+ dec_prepare w3, x2, x6
+
+ tbl v2.16b, {v1.16b}, v4.16b
+ decrypt_block v0, w3, x2, x6, w7
+ eor v2.16b, v2.16b, v0.16b
+
+ tbx v0.16b, {v1.16b}, v4.16b
+ tbl v2.16b, {v2.16b}, v3.16b
+ decrypt_block v0, w3, x2, x6, w7
+ eor v0.16b, v0.16b, v5.16b /* xor with iv */
+
+ add x4, x0, x4
+ st1 {v2.16b}, [x4] /* overlapping stores */
+ st1 {v0.16b}, [x0]
+ ret
+AES_ENDPROC(aes_cbc_cts_decrypt)
+
+ .section ".rodata", "a"
+ .align 6
+.Lcts_permute_table:
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7
+ .byte 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .byte 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+ .previous
+
+
+ /*
* aes_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
* int blocks, u8 ctr[])
*/
AES_ENTRY(aes_ctr_encrypt)
- frame_push 6
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x5
-
-.Lctrrestart:
- enc_prepare w22, x21, x6
- ld1 {v4.16b}, [x24]
+ enc_prepare w3, x2, x6
+ ld1 {v4.16b}, [x5]
umov x6, v4.d[1] /* keep swabbed ctr in reg */
rev x6, x6
+ cmn w6, w4 /* 32 bit overflow? */
+ bcs .Lctrloop
.LctrloopNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lctr1x
- cmn w6, #4 /* 32 bit overflow? */
- bcs .Lctr1x
- ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
- dup v7.4s, w6
+ add w7, w6, #1
mov v0.16b, v4.16b
- add v7.4s, v7.4s, v8.4s
+ add w8, w6, #2
mov v1.16b, v4.16b
- rev32 v8.16b, v7.16b
+ add w9, w6, #3
mov v2.16b, v4.16b
+ rev w7, w7
mov v3.16b, v4.16b
- mov v1.s[3], v8.s[0]
- mov v2.s[3], v8.s[1]
- mov v3.s[3], v8.s[2]
- ld1 {v5.16b-v7.16b}, [x20], #48 /* get 3 input blocks */
+ rev w8, w8
+ mov v1.s[3], w7
+ rev w9, w9
+ mov v2.s[3], w8
+ mov v3.s[3], w9
+ ld1 {v5.16b-v7.16b}, [x1], #48 /* get 3 input blocks */
bl aes_encrypt_block4x
eor v0.16b, v5.16b, v0.16b
- ld1 {v5.16b}, [x20], #16 /* get 1 input block */
+ ld1 {v5.16b}, [x1], #16 /* get 1 input block */
eor v1.16b, v6.16b, v1.16b
eor v2.16b, v7.16b, v2.16b
eor v3.16b, v5.16b, v3.16b
- st1 {v0.16b-v3.16b}, [x19], #64
+ st1 {v0.16b-v3.16b}, [x0], #64
add x6, x6, #4
rev x7, x6
ins v4.d[1], x7
- cbz w23, .Lctrout
- st1 {v4.16b}, [x24] /* return next CTR value */
- cond_yield_neon .Lctrrestart
+ cbz w4, .Lctrout
b .LctrloopNx
.Lctr1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lctrout
.Lctrloop:
mov v0.16b, v4.16b
- encrypt_block v0, w22, x21, x8, w7
+ encrypt_block v0, w3, x2, x8, w7
adds x6, x6, #1 /* increment BE ctr */
rev x7, x6
@@ -271,22 +306,22 @@ AES_ENTRY(aes_ctr_encrypt)
bcs .Lctrcarry /* overflow? */
.Lctrcarrydone:
- subs w23, w23, #1
+ subs w4, w4, #1
bmi .Lctrtailblock /* blocks <0 means tail block */
- ld1 {v3.16b}, [x20], #16
+ ld1 {v3.16b}, [x1], #16
eor v3.16b, v0.16b, v3.16b
- st1 {v3.16b}, [x19], #16
+ st1 {v3.16b}, [x0], #16
bne .Lctrloop
.Lctrout:
- st1 {v4.16b}, [x24] /* return next CTR value */
-.Lctrret:
- frame_pop
+ st1 {v4.16b}, [x5] /* return next CTR value */
+ ldp x29, x30, [sp], #16
ret
.Lctrtailblock:
- st1 {v0.16b}, [x19]
- b .Lctrret
+ st1 {v0.16b}, [x0]
+ ldp x29, x30, [sp], #16
+ ret
.Lctrcarry:
umov x7, v4.d[0] /* load upper word of ctr */
@@ -296,7 +331,6 @@ AES_ENTRY(aes_ctr_encrypt)
ins v4.d[0], x7
b .Lctrcarrydone
AES_ENDPROC(aes_ctr_encrypt)
- .ltorg
/*
@@ -306,150 +340,132 @@ AES_ENDPROC(aes_ctr_encrypt)
* int blocks, u8 const rk2[], u8 iv[], int first)
*/
- .macro next_tweak, out, in, const, tmp
+ .macro next_tweak, out, in, tmp
sshr \tmp\().2d, \in\().2d, #63
- and \tmp\().16b, \tmp\().16b, \const\().16b
+ and \tmp\().16b, \tmp\().16b, xtsmask.16b
add \out\().2d, \in\().2d, \in\().2d
ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
eor \out\().16b, \out\().16b, \tmp\().16b
.endm
-.Lxts_mul_x:
-CPU_LE( .quad 1, 0x87 )
-CPU_BE( .quad 0x87, 1 )
+ .macro xts_load_mask, tmp
+ movi xtsmask.2s, #0x1
+ movi \tmp\().2s, #0x87
+ uzp1 xtsmask.4s, xtsmask.4s, \tmp\().4s
+ .endm
AES_ENTRY(aes_xts_encrypt)
- frame_push 6
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x6
-
- ld1 {v4.16b}, [x24]
+ ld1 {v4.16b}, [x6]
+ xts_load_mask v8
cbz w7, .Lxtsencnotfirst
enc_prepare w3, x5, x8
encrypt_block v4, w3, x5, x8, w7 /* first tweak */
enc_switch_key w3, x2, x8
- ldr q7, .Lxts_mul_x
b .LxtsencNx
-.Lxtsencrestart:
- ld1 {v4.16b}, [x24]
.Lxtsencnotfirst:
- enc_prepare w22, x21, x8
+ enc_prepare w3, x2, x8
.LxtsencloopNx:
- ldr q7, .Lxts_mul_x
- next_tweak v4, v4, v7, v8
+ next_tweak v4, v4, v8
.LxtsencNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lxtsenc1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
- next_tweak v5, v4, v7, v8
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ next_tweak v5, v4, v8
eor v0.16b, v0.16b, v4.16b
- next_tweak v6, v5, v7, v8
+ next_tweak v6, v5, v8
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
- next_tweak v7, v6, v7, v8
+ next_tweak v7, v6, v8
eor v3.16b, v3.16b, v7.16b
bl aes_encrypt_block4x
eor v3.16b, v3.16b, v7.16b
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
- st1 {v0.16b-v3.16b}, [x19], #64
+ st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v7.16b
- cbz w23, .Lxtsencout
- st1 {v4.16b}, [x24]
- cond_yield_neon .Lxtsencrestart
+ cbz w4, .Lxtsencout
+ xts_reload_mask v8
b .LxtsencloopNx
.Lxtsenc1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lxtsencout
.Lxtsencloop:
- ld1 {v1.16b}, [x20], #16
+ ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
- encrypt_block v0, w22, x21, x8, w7
+ encrypt_block v0, w3, x2, x8, w7
eor v0.16b, v0.16b, v4.16b
- st1 {v0.16b}, [x19], #16
- subs w23, w23, #1
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
beq .Lxtsencout
- next_tweak v4, v4, v7, v8
+ next_tweak v4, v4, v8
b .Lxtsencloop
.Lxtsencout:
- st1 {v4.16b}, [x24]
- frame_pop
+ st1 {v4.16b}, [x6]
+ ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_xts_encrypt)
AES_ENTRY(aes_xts_decrypt)
- frame_push 6
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
- mov x19, x0
- mov x20, x1
- mov x21, x2
- mov x22, x3
- mov x23, x4
- mov x24, x6
-
- ld1 {v4.16b}, [x24]
+ ld1 {v4.16b}, [x6]
+ xts_load_mask v8
cbz w7, .Lxtsdecnotfirst
enc_prepare w3, x5, x8
encrypt_block v4, w3, x5, x8, w7 /* first tweak */
dec_prepare w3, x2, x8
- ldr q7, .Lxts_mul_x
b .LxtsdecNx
-.Lxtsdecrestart:
- ld1 {v4.16b}, [x24]
.Lxtsdecnotfirst:
- dec_prepare w22, x21, x8
+ dec_prepare w3, x2, x8
.LxtsdecloopNx:
- ldr q7, .Lxts_mul_x
- next_tweak v4, v4, v7, v8
+ next_tweak v4, v4, v8
.LxtsdecNx:
- subs w23, w23, #4
+ subs w4, w4, #4
bmi .Lxtsdec1x
- ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 ct blocks */
- next_tweak v5, v4, v7, v8
+ ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ next_tweak v5, v4, v8
eor v0.16b, v0.16b, v4.16b
- next_tweak v6, v5, v7, v8
+ next_tweak v6, v5, v8
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
- next_tweak v7, v6, v7, v8
+ next_tweak v7, v6, v8
eor v3.16b, v3.16b, v7.16b
bl aes_decrypt_block4x
eor v3.16b, v3.16b, v7.16b
eor v0.16b, v0.16b, v4.16b
eor v1.16b, v1.16b, v5.16b
eor v2.16b, v2.16b, v6.16b
- st1 {v0.16b-v3.16b}, [x19], #64
+ st1 {v0.16b-v3.16b}, [x0], #64
mov v4.16b, v7.16b
- cbz w23, .Lxtsdecout
- st1 {v4.16b}, [x24]
- cond_yield_neon .Lxtsdecrestart
+ cbz w4, .Lxtsdecout
+ xts_reload_mask v8
b .LxtsdecloopNx
.Lxtsdec1x:
- adds w23, w23, #4
+ adds w4, w4, #4
beq .Lxtsdecout
.Lxtsdecloop:
- ld1 {v1.16b}, [x20], #16
+ ld1 {v1.16b}, [x1], #16
eor v0.16b, v1.16b, v4.16b
- decrypt_block v0, w22, x21, x8, w7
+ decrypt_block v0, w3, x2, x8, w7
eor v0.16b, v0.16b, v4.16b
- st1 {v0.16b}, [x19], #16
- subs w23, w23, #1
+ st1 {v0.16b}, [x0], #16
+ subs w4, w4, #1
beq .Lxtsdecout
- next_tweak v4, v4, v7, v8
+ next_tweak v4, v4, v8
b .Lxtsdecloop
.Lxtsdecout:
- st1 {v4.16b}, [x24]
- frame_pop
+ st1 {v4.16b}, [x6]
+ ldp x29, x30, [sp], #16
ret
AES_ENDPROC(aes_xts_decrypt)
diff --git a/arch/arm64/crypto/aes-neon.S b/arch/arm64/crypto/aes-neon.S
index 1c7b45b7268e..29100f692e8a 100644
--- a/arch/arm64/crypto/aes-neon.S
+++ b/arch/arm64/crypto/aes-neon.S
@@ -14,6 +14,12 @@
#define AES_ENTRY(func) ENTRY(neon_ ## func)
#define AES_ENDPROC(func) ENDPROC(neon_ ## func)
+ xtsmask .req v7
+
+ .macro xts_reload_mask, tmp
+ xts_load_mask \tmp
+ .endm
+
/* multiply by polynomial 'x' in GF(2^8) */
.macro mul_by_x, out, in, temp, const
sshr \temp, \in, #7
diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S
deleted file mode 100644
index 8061bf0f9c66..000000000000
--- a/arch/arm64/crypto/crc32-ce-core.S
+++ /dev/null
@@ -1,287 +0,0 @@
-/*
- * Accelerated CRC32(C) using arm64 CRC, NEON and Crypto Extensions instructions
- *
- * Copyright (C) 2016 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.
- */
-
-/* GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see http://www.gnu.org/licenses
- *
- * Please visit http://www.xyratex.com/contact if you need additional
- * information or have any questions.
- *
- * GPL HEADER END
- */
-
-/*
- * Copyright 2012 Xyratex Technology Limited
- *
- * Using hardware provided PCLMULQDQ instruction to accelerate the CRC32
- * calculation.
- * CRC32 polynomial:0x04c11db7(BE)/0xEDB88320(LE)
- * PCLMULQDQ is a new instruction in Intel SSE4.2, the reference can be found
- * at:
- * http://www.intel.com/products/processor/manuals/
- * Intel(R) 64 and IA-32 Architectures Software Developer's Manual
- * Volume 2B: Instruction Set Reference, N-Z
- *
- * Authors: Gregory Prestas <Gregory_Prestas@us.xyratex.com>
- * Alexander Boyko <Alexander_Boyko@xyratex.com>
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-
- .section ".rodata", "a"
- .align 6
- .cpu generic+crypto+crc
-
-.Lcrc32_constants:
- /*
- * [x4*128+32 mod P(x) << 32)]' << 1 = 0x154442bd4
- * #define CONSTANT_R1 0x154442bd4LL
- *
- * [(x4*128-32 mod P(x) << 32)]' << 1 = 0x1c6e41596
- * #define CONSTANT_R2 0x1c6e41596LL
- */
- .octa 0x00000001c6e415960000000154442bd4
-
- /*
- * [(x128+32 mod P(x) << 32)]' << 1 = 0x1751997d0
- * #define CONSTANT_R3 0x1751997d0LL
- *
- * [(x128-32 mod P(x) << 32)]' << 1 = 0x0ccaa009e
- * #define CONSTANT_R4 0x0ccaa009eLL
- */
- .octa 0x00000000ccaa009e00000001751997d0
-
- /*
- * [(x64 mod P(x) << 32)]' << 1 = 0x163cd6124
- * #define CONSTANT_R5 0x163cd6124LL
- */
- .quad 0x0000000163cd6124
- .quad 0x00000000FFFFFFFF
-
- /*
- * #define CRCPOLY_TRUE_LE_FULL 0x1DB710641LL
- *
- * Barrett Reduction constant (u64`) = u` = (x**64 / P(x))`
- * = 0x1F7011641LL
- * #define CONSTANT_RU 0x1F7011641LL
- */
- .octa 0x00000001F701164100000001DB710641
-
-.Lcrc32c_constants:
- .octa 0x000000009e4addf800000000740eef02
- .octa 0x000000014cd00bd600000000f20c0dfe
- .quad 0x00000000dd45aab8
- .quad 0x00000000FFFFFFFF
- .octa 0x00000000dea713f10000000105ec76f0
-
- vCONSTANT .req v0
- dCONSTANT .req d0
- qCONSTANT .req q0
-
- BUF .req x19
- LEN .req x20
- CRC .req x21
- CONST .req x22
-
- vzr .req v9
-
- /**
- * Calculate crc32
- * BUF - buffer
- * LEN - sizeof buffer (multiple of 16 bytes), LEN should be > 63
- * CRC - initial crc32
- * return %eax crc32
- * uint crc32_pmull_le(unsigned char const *buffer,
- * size_t len, uint crc32)
- */
- .text
-ENTRY(crc32_pmull_le)
- adr_l x3, .Lcrc32_constants
- b 0f
-
-ENTRY(crc32c_pmull_le)
- adr_l x3, .Lcrc32c_constants
-
-0: frame_push 4, 64
-
- mov BUF, x0
- mov LEN, x1
- mov CRC, x2
- mov CONST, x3
-
- bic LEN, LEN, #15
- ld1 {v1.16b-v4.16b}, [BUF], #0x40
- movi vzr.16b, #0
- fmov dCONSTANT, CRC
- eor v1.16b, v1.16b, vCONSTANT.16b
- sub LEN, LEN, #0x40
- cmp LEN, #0x40
- b.lt less_64
-
- ldr qCONSTANT, [CONST]
-
-loop_64: /* 64 bytes Full cache line folding */
- sub LEN, LEN, #0x40
-
- pmull2 v5.1q, v1.2d, vCONSTANT.2d
- pmull2 v6.1q, v2.2d, vCONSTANT.2d
- pmull2 v7.1q, v3.2d, vCONSTANT.2d
- pmull2 v8.1q, v4.2d, vCONSTANT.2d
-
- pmull v1.1q, v1.1d, vCONSTANT.1d
- pmull v2.1q, v2.1d, vCONSTANT.1d
- pmull v3.1q, v3.1d, vCONSTANT.1d
- pmull v4.1q, v4.1d, vCONSTANT.1d
-
- eor v1.16b, v1.16b, v5.16b
- ld1 {v5.16b}, [BUF], #0x10
- eor v2.16b, v2.16b, v6.16b
- ld1 {v6.16b}, [BUF], #0x10
- eor v3.16b, v3.16b, v7.16b
- ld1 {v7.16b}, [BUF], #0x10
- eor v4.16b, v4.16b, v8.16b
- ld1 {v8.16b}, [BUF], #0x10
-
- eor v1.16b, v1.16b, v5.16b
- eor v2.16b, v2.16b, v6.16b
- eor v3.16b, v3.16b, v7.16b
- eor v4.16b, v4.16b, v8.16b
-
- cmp LEN, #0x40
- b.lt less_64
-
- if_will_cond_yield_neon
- stp q1, q2, [sp, #.Lframe_local_offset]
- stp q3, q4, [sp, #.Lframe_local_offset + 32]
- do_cond_yield_neon
- ldp q1, q2, [sp, #.Lframe_local_offset]
- ldp q3, q4, [sp, #.Lframe_local_offset + 32]
- ldr qCONSTANT, [CONST]
- movi vzr.16b, #0
- endif_yield_neon
- b loop_64
-
-less_64: /* Folding cache line into 128bit */
- ldr qCONSTANT, [CONST, #16]
-
- pmull2 v5.1q, v1.2d, vCONSTANT.2d
- pmull v1.1q, v1.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v5.16b
- eor v1.16b, v1.16b, v2.16b
-
- pmull2 v5.1q, v1.2d, vCONSTANT.2d
- pmull v1.1q, v1.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v5.16b
- eor v1.16b, v1.16b, v3.16b
-
- pmull2 v5.1q, v1.2d, vCONSTANT.2d
- pmull v1.1q, v1.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v5.16b
- eor v1.16b, v1.16b, v4.16b
-
- cbz LEN, fold_64
-
-loop_16: /* Folding rest buffer into 128bit */
- subs LEN, LEN, #0x10
-
- ld1 {v2.16b}, [BUF], #0x10
- pmull2 v5.1q, v1.2d, vCONSTANT.2d
- pmull v1.1q, v1.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v5.16b
- eor v1.16b, v1.16b, v2.16b
-
- b.ne loop_16
-
-fold_64:
- /* perform the last 64 bit fold, also adds 32 zeroes
- * to the input stream */
- ext v2.16b, v1.16b, v1.16b, #8
- pmull2 v2.1q, v2.2d, vCONSTANT.2d
- ext v1.16b, v1.16b, vzr.16b, #8
- eor v1.16b, v1.16b, v2.16b
-
- /* final 32-bit fold */
- ldr dCONSTANT, [CONST, #32]
- ldr d3, [CONST, #40]
-
- ext v2.16b, v1.16b, vzr.16b, #4
- and v1.16b, v1.16b, v3.16b
- pmull v1.1q, v1.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v2.16b
-
- /* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
- ldr qCONSTANT, [CONST, #48]
-
- and v2.16b, v1.16b, v3.16b
- ext v2.16b, vzr.16b, v2.16b, #8
- pmull2 v2.1q, v2.2d, vCONSTANT.2d
- and v2.16b, v2.16b, v3.16b
- pmull v2.1q, v2.1d, vCONSTANT.1d
- eor v1.16b, v1.16b, v2.16b
- mov w0, v1.s[1]
-
- frame_pop
- ret
-ENDPROC(crc32_pmull_le)
-ENDPROC(crc32c_pmull_le)
-
- .macro __crc32, c
-0: subs x2, x2, #16
- b.mi 8f
- ldp x3, x4, [x1], #16
-CPU_BE( rev x3, x3 )
-CPU_BE( rev x4, x4 )
- crc32\c\()x w0, w0, x3
- crc32\c\()x w0, w0, x4
- b.ne 0b
- ret
-
-8: tbz x2, #3, 4f
- ldr x3, [x1], #8
-CPU_BE( rev x3, x3 )
- crc32\c\()x w0, w0, x3
-4: tbz x2, #2, 2f
- ldr w3, [x1], #4
-CPU_BE( rev w3, w3 )
- crc32\c\()w w0, w0, w3
-2: tbz x2, #1, 1f
- ldrh w3, [x1], #2
-CPU_BE( rev16 w3, w3 )
- crc32\c\()h w0, w0, w3
-1: tbz x2, #0, 0f
- ldrb w3, [x1]
- crc32\c\()b w0, w0, w3
-0: ret
- .endm
-
- .align 5
-ENTRY(crc32_armv8_le)
- __crc32
-ENDPROC(crc32_armv8_le)
-
- .align 5
-ENTRY(crc32c_armv8_le)
- __crc32 c
-ENDPROC(crc32c_armv8_le)
diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
deleted file mode 100644
index 34b4e3d46aab..000000000000
--- a/arch/arm64/crypto/crc32-ce-glue.c
+++ /dev/null
@@ -1,244 +0,0 @@
-/*
- * Accelerated CRC32(C) using arm64 NEON and Crypto Extensions instructions
- *
- * 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.
- */
-
-#include <linux/cpufeature.h>
-#include <linux/crc32.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/string.h>
-
-#include <crypto/internal/hash.h>
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <asm/unaligned.h>
-
-#define PMULL_MIN_LEN 64L /* minimum size of buffer
- * for crc32_pmull_le_16 */
-#define SCALE_F 16L /* size of NEON register */
-
-asmlinkage u32 crc32_pmull_le(const u8 buf[], u64 len, u32 init_crc);
-asmlinkage u32 crc32_armv8_le(u32 init_crc, const u8 buf[], size_t len);
-
-asmlinkage u32 crc32c_pmull_le(const u8 buf[], u64 len, u32 init_crc);
-asmlinkage u32 crc32c_armv8_le(u32 init_crc, const u8 buf[], size_t len);
-
-static u32 (*fallback_crc32)(u32 init_crc, const u8 buf[], size_t len);
-static u32 (*fallback_crc32c)(u32 init_crc, const u8 buf[], size_t len);
-
-static int crc32_pmull_cra_init(struct crypto_tfm *tfm)
-{
- u32 *key = crypto_tfm_ctx(tfm);
-
- *key = 0;
- return 0;
-}
-
-static int crc32c_pmull_cra_init(struct crypto_tfm *tfm)
-{
- u32 *key = crypto_tfm_ctx(tfm);
-
- *key = ~0;
- return 0;
-}
-
-static int crc32_pmull_setkey(struct crypto_shash *hash, const u8 *key,
- unsigned int keylen)
-{
- u32 *mctx = crypto_shash_ctx(hash);
-
- if (keylen != sizeof(u32)) {
- crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN);
- return -EINVAL;
- }
- *mctx = le32_to_cpup((__le32 *)key);
- return 0;
-}
-
-static int crc32_pmull_init(struct shash_desc *desc)
-{
- u32 *mctx = crypto_shash_ctx(desc->tfm);
- u32 *crc = shash_desc_ctx(desc);
-
- *crc = *mctx;
- return 0;
-}
-
-static int crc32_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- u32 *crc = shash_desc_ctx(desc);
-
- *crc = crc32_armv8_le(*crc, data, length);
- return 0;
-}
-
-static int crc32c_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- u32 *crc = shash_desc_ctx(desc);
-
- *crc = crc32c_armv8_le(*crc, data, length);
- return 0;
-}
-
-static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- u32 *crc = shash_desc_ctx(desc);
- unsigned int l;
-
- if ((u64)data % SCALE_F) {
- l = min_t(u32, length, SCALE_F - ((u64)data % SCALE_F));
-
- *crc = fallback_crc32(*crc, data, l);
-
- data += l;
- length -= l;
- }
-
- if (length >= PMULL_MIN_LEN && may_use_simd()) {
- l = round_down(length, SCALE_F);
-
- kernel_neon_begin();
- *crc = crc32_pmull_le(data, l, *crc);
- kernel_neon_end();
-
- data += l;
- length -= l;
- }
-
- if (length > 0)
- *crc = fallback_crc32(*crc, data, length);
-
- return 0;
-}
-
-static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
- unsigned int length)
-{
- u32 *crc = shash_desc_ctx(desc);
- unsigned int l;
-
- if ((u64)data % SCALE_F) {
- l = min_t(u32, length, SCALE_F - ((u64)data % SCALE_F));
-
- *crc = fallback_crc32c(*crc, data, l);
-
- data += l;
- length -= l;
- }
-
- if (length >= PMULL_MIN_LEN && may_use_simd()) {
- l = round_down(length, SCALE_F);
-
- kernel_neon_begin();
- *crc = crc32c_pmull_le(data, l, *crc);
- kernel_neon_end();
-
- data += l;
- length -= l;
- }
-
- if (length > 0) {
- *crc = fallback_crc32c(*crc, data, length);
- }
-
- return 0;
-}
-
-static int crc32_pmull_final(struct shash_desc *desc, u8 *out)
-{
- u32 *crc = shash_desc_ctx(desc);
-
- put_unaligned_le32(*crc, out);
- return 0;
-}
-
-static int crc32c_pmull_final(struct shash_desc *desc, u8 *out)
-{
- u32 *crc = shash_desc_ctx(desc);
-
- put_unaligned_le32(~*crc, out);
- return 0;
-}
-
-static struct shash_alg crc32_pmull_algs[] = { {
- .setkey = crc32_pmull_setkey,
- .init = crc32_pmull_init,
- .update = crc32_update,
- .final = crc32_pmull_final,
- .descsize = sizeof(u32),
- .digestsize = sizeof(u32),
-
- .base.cra_ctxsize = sizeof(u32),
- .base.cra_init = crc32_pmull_cra_init,
- .base.cra_name = "crc32",
- .base.cra_driver_name = "crc32-arm64-ce",
- .base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY,
- .base.cra_blocksize = 1,
- .base.cra_module = THIS_MODULE,
-}, {
- .setkey = crc32_pmull_setkey,
- .init = crc32_pmull_init,
- .update = crc32c_update,
- .final = crc32c_pmull_final,
- .descsize = sizeof(u32),
- .digestsize = sizeof(u32),
-
- .base.cra_ctxsize = sizeof(u32),
- .base.cra_init = crc32c_pmull_cra_init,
- .base.cra_name = "crc32c",
- .base.cra_driver_name = "crc32c-arm64-ce",
- .base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_OPTIONAL_KEY,
- .base.cra_blocksize = 1,
- .base.cra_module = THIS_MODULE,
-} };
-
-static int __init crc32_pmull_mod_init(void)
-{
- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) {
- crc32_pmull_algs[0].update = crc32_pmull_update;
- crc32_pmull_algs[1].update = crc32c_pmull_update;
-
- if (elf_hwcap & HWCAP_CRC32) {
- fallback_crc32 = crc32_armv8_le;
- fallback_crc32c = crc32c_armv8_le;
- } else {
- fallback_crc32 = crc32_le;
- fallback_crc32c = __crc32c_le;
- }
- } else if (!(elf_hwcap & HWCAP_CRC32)) {
- return -ENODEV;
- }
- return crypto_register_shashes(crc32_pmull_algs,
- ARRAY_SIZE(crc32_pmull_algs));
-}
-
-static void __exit crc32_pmull_mod_exit(void)
-{
- crypto_unregister_shashes(crc32_pmull_algs,
- ARRAY_SIZE(crc32_pmull_algs));
-}
-
-static const struct cpu_feature crc32_cpu_feature[] = {
- { cpu_feature(CRC32) }, { cpu_feature(PMULL) }, { }
-};
-MODULE_DEVICE_TABLE(cpu, crc32_cpu_feature);
-
-module_init(crc32_pmull_mod_init);
-module_exit(crc32_pmull_mod_exit);
-
-MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
-MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index 663ea71cdb38..9e82e8e8ed05 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -80,7 +80,186 @@
vzr .req v13
-ENTRY(crc_t10dif_pmull)
+ ad .req v14
+ bd .req v10
+
+ k00_16 .req v15
+ k32_48 .req v16
+
+ t3 .req v17
+ t4 .req v18
+ t5 .req v19
+ t6 .req v20
+ t7 .req v21
+ t8 .req v22
+ t9 .req v23
+
+ perm1 .req v24
+ perm2 .req v25
+ perm3 .req v26
+ perm4 .req v27
+
+ bd1 .req v28
+ bd2 .req v29
+ bd3 .req v30
+ bd4 .req v31
+
+ .macro __pmull_init_p64
+ .endm
+
+ .macro __pmull_pre_p64, bd
+ .endm
+
+ .macro __pmull_init_p8
+ // k00_16 := 0x0000000000000000_000000000000ffff
+ // k32_48 := 0x00000000ffffffff_0000ffffffffffff
+ movi k32_48.2d, #0xffffffff
+ mov k32_48.h[2], k32_48.h[0]
+ ushr k00_16.2d, k32_48.2d, #32
+
+ // prepare the permutation vectors
+ mov_q x5, 0x080f0e0d0c0b0a09
+ movi perm4.8b, #8
+ dup perm1.2d, x5
+ eor perm1.16b, perm1.16b, perm4.16b
+ ushr perm2.2d, perm1.2d, #8
+ ushr perm3.2d, perm1.2d, #16
+ ushr perm4.2d, perm1.2d, #24
+ sli perm2.2d, perm1.2d, #56
+ sli perm3.2d, perm1.2d, #48
+ sli perm4.2d, perm1.2d, #40
+ .endm
+
+ .macro __pmull_pre_p8, bd
+ tbl bd1.16b, {\bd\().16b}, perm1.16b
+ tbl bd2.16b, {\bd\().16b}, perm2.16b
+ tbl bd3.16b, {\bd\().16b}, perm3.16b
+ tbl bd4.16b, {\bd\().16b}, perm4.16b
+ .endm
+
+__pmull_p8_core:
+.L__pmull_p8_core:
+ ext t4.8b, ad.8b, ad.8b, #1 // A1
+ ext t5.8b, ad.8b, ad.8b, #2 // A2
+ ext t6.8b, ad.8b, ad.8b, #3 // A3
+
+ pmull t4.8h, t4.8b, bd.8b // F = A1*B
+ pmull t8.8h, ad.8b, bd1.8b // E = A*B1
+ pmull t5.8h, t5.8b, bd.8b // H = A2*B
+ pmull t7.8h, ad.8b, bd2.8b // G = A*B2
+ pmull t6.8h, t6.8b, bd.8b // J = A3*B
+ pmull t9.8h, ad.8b, bd3.8b // I = A*B3
+ pmull t3.8h, ad.8b, bd4.8b // K = A*B4
+ b 0f
+
+.L__pmull_p8_core2:
+ tbl t4.16b, {ad.16b}, perm1.16b // A1
+ tbl t5.16b, {ad.16b}, perm2.16b // A2
+ tbl t6.16b, {ad.16b}, perm3.16b // A3
+
+ pmull2 t4.8h, t4.16b, bd.16b // F = A1*B
+ pmull2 t8.8h, ad.16b, bd1.16b // E = A*B1
+ pmull2 t5.8h, t5.16b, bd.16b // H = A2*B
+ pmull2 t7.8h, ad.16b, bd2.16b // G = A*B2
+ pmull2 t6.8h, t6.16b, bd.16b // J = A3*B
+ pmull2 t9.8h, ad.16b, bd3.16b // I = A*B3
+ pmull2 t3.8h, ad.16b, bd4.16b // K = A*B4
+
+0: eor t4.16b, t4.16b, t8.16b // L = E + F
+ eor t5.16b, t5.16b, t7.16b // M = G + H
+ eor t6.16b, t6.16b, t9.16b // N = I + J
+
+ uzp1 t8.2d, t4.2d, t5.2d
+ uzp2 t4.2d, t4.2d, t5.2d
+ uzp1 t7.2d, t6.2d, t3.2d
+ uzp2 t6.2d, t6.2d, t3.2d
+
+ // t4 = (L) (P0 + P1) << 8
+ // t5 = (M) (P2 + P3) << 16
+ eor t8.16b, t8.16b, t4.16b
+ and t4.16b, t4.16b, k32_48.16b
+
+ // t6 = (N) (P4 + P5) << 24
+ // t7 = (K) (P6 + P7) << 32
+ eor t7.16b, t7.16b, t6.16b
+ and t6.16b, t6.16b, k00_16.16b
+
+ eor t8.16b, t8.16b, t4.16b
+ eor t7.16b, t7.16b, t6.16b
+
+ zip2 t5.2d, t8.2d, t4.2d
+ zip1 t4.2d, t8.2d, t4.2d
+ zip2 t3.2d, t7.2d, t6.2d
+ zip1 t6.2d, t7.2d, t6.2d
+
+ ext t4.16b, t4.16b, t4.16b, #15
+ ext t5.16b, t5.16b, t5.16b, #14
+ ext t6.16b, t6.16b, t6.16b, #13
+ ext t3.16b, t3.16b, t3.16b, #12
+
+ eor t4.16b, t4.16b, t5.16b
+ eor t6.16b, t6.16b, t3.16b
+ ret
+ENDPROC(__pmull_p8_core)
+
+ .macro __pmull_p8, rq, ad, bd, i
+ .ifnc \bd, v10
+ .err
+ .endif
+ mov ad.16b, \ad\().16b
+ .ifb \i
+ pmull \rq\().8h, \ad\().8b, bd.8b // D = A*B
+ .else
+ pmull2 \rq\().8h, \ad\().16b, bd.16b // D = A*B
+ .endif
+
+ bl .L__pmull_p8_core\i
+
+ eor \rq\().16b, \rq\().16b, t4.16b
+ eor \rq\().16b, \rq\().16b, t6.16b
+ .endm
+
+ .macro fold64, p, reg1, reg2
+ ldp q11, q12, [arg2], #0x20
+
+ __pmull_\p v8, \reg1, v10, 2
+ __pmull_\p \reg1, \reg1, v10
+
+CPU_LE( rev64 v11.16b, v11.16b )
+CPU_LE( rev64 v12.16b, v12.16b )
+
+ __pmull_\p v9, \reg2, v10, 2
+ __pmull_\p \reg2, \reg2, v10
+
+CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
+CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
+
+ eor \reg1\().16b, \reg1\().16b, v8.16b
+ eor \reg2\().16b, \reg2\().16b, v9.16b
+ eor \reg1\().16b, \reg1\().16b, v11.16b
+ eor \reg2\().16b, \reg2\().16b, v12.16b
+ .endm
+
+ .macro fold16, p, reg, rk
+ __pmull_\p v8, \reg, v10
+ __pmull_\p \reg, \reg, v10, 2
+ .ifnb \rk
+ ldr_l q10, \rk, x8
+ __pmull_pre_\p v10
+ .endif
+ eor v7.16b, v7.16b, v8.16b
+ eor v7.16b, v7.16b, \reg\().16b
+ .endm
+
+ .macro __pmull_p64, rd, rn, rm, n
+ .ifb \n
+ pmull \rd\().1q, \rn\().1d, \rm\().1d
+ .else
+ pmull2 \rd\().1q, \rn\().2d, \rm\().2d
+ .endif
+ .endm
+
+ .macro crc_t10dif_pmull, p
frame_push 3, 128
mov arg1_low32, w0
@@ -89,6 +268,8 @@ ENTRY(crc_t10dif_pmull)
movi vzr.16b, #0 // init zero register
+ __pmull_init_\p
+
// adjust the 16-bit initial_crc value, scale it to 32 bits
lsl arg1_low32, arg1_low32, #16
@@ -96,7 +277,7 @@ ENTRY(crc_t10dif_pmull)
cmp arg3, #256
// for sizes less than 128, we can't fold 64B at a time...
- b.lt _less_than_128
+ b.lt .L_less_than_128_\@
// load the initial crc value
// crc value does not need to be byte-reflected, but it needs
@@ -137,6 +318,7 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
ldr_l q10, rk3, x8 // xmm10 has rk3 and rk4
// type of pmull instruction
// will determine which constant to use
+ __pmull_pre_\p v10
//
// we subtract 256 instead of 128 to save one instruction from the loop
@@ -147,41 +329,19 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
// buffer. The _fold_64_B_loop will fold 64B at a time
// until we have 64+y Bytes of buffer
-
// fold 64B at a time. This section of the code folds 4 vector
// registers in parallel
-_fold_64_B_loop:
+.L_fold_64_B_loop_\@:
- .macro fold64, reg1, reg2
- ldp q11, q12, [arg2], #0x20
-
- pmull2 v8.1q, \reg1\().2d, v10.2d
- pmull \reg1\().1q, \reg1\().1d, v10.1d
-
-CPU_LE( rev64 v11.16b, v11.16b )
-CPU_LE( rev64 v12.16b, v12.16b )
-
- pmull2 v9.1q, \reg2\().2d, v10.2d
- pmull \reg2\().1q, \reg2\().1d, v10.1d
-
-CPU_LE( ext v11.16b, v11.16b, v11.16b, #8 )
-CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
-
- eor \reg1\().16b, \reg1\().16b, v8.16b
- eor \reg2\().16b, \reg2\().16b, v9.16b
- eor \reg1\().16b, \reg1\().16b, v11.16b
- eor \reg2\().16b, \reg2\().16b, v12.16b
- .endm
-
- fold64 v0, v1
- fold64 v2, v3
- fold64 v4, v5
- fold64 v6, v7
+ fold64 \p, v0, v1
+ fold64 \p, v2, v3
+ fold64 \p, v4, v5
+ fold64 \p, v6, v7
subs arg3, arg3, #128
// check if there is another 64B in the buffer to be able to fold
- b.lt _fold_64_B_end
+ b.lt .L_fold_64_B_end_\@
if_will_cond_yield_neon
stp q0, q1, [sp, #.Lframe_local_offset]
@@ -195,11 +355,13 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
ldp q6, q7, [sp, #.Lframe_local_offset + 96]
ldr_l q10, rk3, x8
movi vzr.16b, #0 // init zero register
+ __pmull_init_\p
+ __pmull_pre_\p v10
endif_yield_neon
- b _fold_64_B_loop
+ b .L_fold_64_B_loop_\@
-_fold_64_B_end:
+.L_fold_64_B_end_\@:
// at this point, the buffer pointer is pointing at the last y Bytes
// of the buffer the 64B of folded data is in 4 of the vector
// registers: v0, v1, v2, v3
@@ -208,38 +370,29 @@ _fold_64_B_end:
// constants
ldr_l q10, rk9, x8
+ __pmull_pre_\p v10
- .macro fold16, reg, rk
- pmull v8.1q, \reg\().1d, v10.1d
- pmull2 \reg\().1q, \reg\().2d, v10.2d
- .ifnb \rk
- ldr_l q10, \rk, x8
- .endif
- eor v7.16b, v7.16b, v8.16b
- eor v7.16b, v7.16b, \reg\().16b
- .endm
-
- fold16 v0, rk11
- fold16 v1, rk13
- fold16 v2, rk15
- fold16 v3, rk17
- fold16 v4, rk19
- fold16 v5, rk1
- fold16 v6
+ fold16 \p, v0, rk11
+ fold16 \p, v1, rk13
+ fold16 \p, v2, rk15
+ fold16 \p, v3, rk17
+ fold16 \p, v4, rk19
+ fold16 \p, v5, rk1
+ fold16 \p, v6
// instead of 64, we add 48 to the loop counter to save 1 instruction
// from the loop instead of a cmp instruction, we use the negative
// flag with the jl instruction
adds arg3, arg3, #(128-16)
- b.lt _final_reduction_for_128
+ b.lt .L_final_reduction_for_128_\@
// now we have 16+y bytes left to reduce. 16 Bytes is in register v7
// and the rest is in memory. We can fold 16 bytes at a time if y>=16
// continue folding 16B at a time
-_16B_reduction_loop:
- pmull v8.1q, v7.1d, v10.1d
- pmull2 v7.1q, v7.2d, v10.2d
+.L_16B_reduction_loop_\@:
+ __pmull_\p v8, v7, v10
+ __pmull_\p v7, v7, v10, 2
eor v7.16b, v7.16b, v8.16b
ldr q0, [arg2], #16
@@ -251,22 +404,22 @@ CPU_LE( ext v0.16b, v0.16b, v0.16b, #8 )
// instead of a cmp instruction, we utilize the flags with the
// jge instruction equivalent of: cmp arg3, 16-16
// check if there is any more 16B in the buffer to be able to fold
- b.ge _16B_reduction_loop
+ b.ge .L_16B_reduction_loop_\@
// now we have 16+z bytes left to reduce, where 0<= z < 16.
// first, we reduce the data in the xmm7 register
-_final_reduction_for_128:
+.L_final_reduction_for_128_\@:
// check if any more data to fold. If not, compute the CRC of
// the final 128 bits
adds arg3, arg3, #16
- b.eq _128_done
+ b.eq .L_128_done_\@
// here we are getting data that is less than 16 bytes.
// since we know that there was data before the pointer, we can
// offset the input pointer before the actual point, to receive
// exactly 16 bytes. after that the registers need to be adjusted.
-_get_last_two_regs:
+.L_get_last_two_regs_\@:
add arg2, arg2, arg3
ldr q1, [arg2, #-16]
CPU_LE( rev64 v1.16b, v1.16b )
@@ -291,47 +444,48 @@ CPU_LE( ext v1.16b, v1.16b, v1.16b, #8 )
bsl v0.16b, v2.16b, v1.16b
// fold 16 Bytes
- pmull v8.1q, v7.1d, v10.1d
- pmull2 v7.1q, v7.2d, v10.2d
+ __pmull_\p v8, v7, v10
+ __pmull_\p v7, v7, v10, 2
eor v7.16b, v7.16b, v8.16b
eor v7.16b, v7.16b, v0.16b
-_128_done:
+.L_128_done_\@:
// compute crc of a 128-bit value
ldr_l q10, rk5, x8 // rk5 and rk6 in xmm10
+ __pmull_pre_\p v10
// 64b fold
ext v0.16b, vzr.16b, v7.16b, #8
mov v7.d[0], v7.d[1]
- pmull v7.1q, v7.1d, v10.1d
+ __pmull_\p v7, v7, v10
eor v7.16b, v7.16b, v0.16b
// 32b fold
ext v0.16b, v7.16b, vzr.16b, #4
mov v7.s[3], vzr.s[0]
- pmull2 v0.1q, v0.2d, v10.2d
+ __pmull_\p v0, v0, v10, 2
eor v7.16b, v7.16b, v0.16b
// barrett reduction
-_barrett:
ldr_l q10, rk7, x8
+ __pmull_pre_\p v10
mov v0.d[0], v7.d[1]
- pmull v0.1q, v0.1d, v10.1d
+ __pmull_\p v0, v0, v10
ext v0.16b, vzr.16b, v0.16b, #12
- pmull2 v0.1q, v0.2d, v10.2d
+ __pmull_\p v0, v0, v10, 2
ext v0.16b, vzr.16b, v0.16b, #12
eor v7.16b, v7.16b, v0.16b
mov w0, v7.s[1]
-_cleanup:
+.L_cleanup_\@:
// scale the result back to 16 bits
lsr x0, x0, #16
frame_pop
ret
-_less_than_128:
- cbz arg3, _cleanup
+.L_less_than_128_\@:
+ cbz arg3, .L_cleanup_\@
movi v0.16b, #0
mov v0.s[3], arg1_low32 // get the initial crc value
@@ -342,20 +496,21 @@ CPU_LE( ext v7.16b, v7.16b, v7.16b, #8 )
eor v7.16b, v7.16b, v0.16b // xor the initial crc value
cmp arg3, #16
- b.eq _128_done // exactly 16 left
- b.lt _less_than_16_left
+ b.eq .L_128_done_\@ // exactly 16 left
+ b.lt .L_less_than_16_left_\@
ldr_l q10, rk1, x8 // rk1 and rk2 in xmm10
+ __pmull_pre_\p v10
// update the counter. subtract 32 instead of 16 to save one
// instruction from the loop
subs arg3, arg3, #32
- b.ge _16B_reduction_loop
+ b.ge .L_16B_reduction_loop_\@
add arg3, arg3, #16
- b _get_last_two_regs
+ b .L_get_last_two_regs_\@
-_less_than_16_left:
+.L_less_than_16_left_\@:
// shl r9, 4
adr_l x0, tbl_shf_table + 16
sub x0, x0, arg3
@@ -363,8 +518,17 @@ _less_than_16_left:
movi v9.16b, #0x80
eor v0.16b, v0.16b, v9.16b
tbl v7.16b, {v7.16b}, v0.16b
- b _128_done
-ENDPROC(crc_t10dif_pmull)
+ b .L_128_done_\@
+ .endm
+
+ENTRY(crc_t10dif_pmull_p8)
+ crc_t10dif_pmull p8
+ENDPROC(crc_t10dif_pmull_p8)
+
+ .align 5
+ENTRY(crc_t10dif_pmull_p64)
+ crc_t10dif_pmull p64
+ENDPROC(crc_t10dif_pmull_p64)
// precomputed constants
// these constants are precomputed from the poly:
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index 96f0cae4a022..b461d62023f2 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -22,7 +22,10 @@
#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
-asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 buf[], u64 len);
+asmlinkage u16 crc_t10dif_pmull_p64(u16 init_crc, const u8 buf[], u64 len);
+asmlinkage u16 crc_t10dif_pmull_p8(u16 init_crc, const u8 buf[], u64 len);
+
+static u16 (*crc_t10dif_pmull)(u16 init_crc, const u8 buf[], u64 len);
static int crct10dif_init(struct shash_desc *desc)
{
@@ -85,6 +88,11 @@ static struct shash_alg crc_t10dif_alg = {
static int __init crc_t10dif_mod_init(void)
{
+ if (elf_hwcap & HWCAP_PMULL)
+ crc_t10dif_pmull = crc_t10dif_pmull_p64;
+ else
+ crc_t10dif_pmull = crc_t10dif_pmull_p8;
+
return crypto_register_shash(&crc_t10dif_alg);
}
@@ -93,8 +101,10 @@ static void __exit crc_t10dif_mod_exit(void)
crypto_unregister_shash(&crc_t10dif_alg);
}
-module_cpu_feature_match(PMULL, crc_t10dif_mod_init);
+module_cpu_feature_match(ASIMD, crc_t10dif_mod_init);
module_exit(crc_t10dif_mod_exit);
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-arm64-ce");
diff --git a/arch/arm64/crypto/speck-neon-core.S b/arch/arm64/crypto/speck-neon-core.S
deleted file mode 100644
index b14463438b09..000000000000
--- a/arch/arm64/crypto/speck-neon-core.S
+++ /dev/null
@@ -1,352 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * ARM64 NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- *
- * Copyright (c) 2018 Google, Inc
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-
-#include <linux/linkage.h>
-
- .text
-
- // arguments
- ROUND_KEYS .req x0 // const {u64,u32} *round_keys
- NROUNDS .req w1 // int nrounds
- NROUNDS_X .req x1
- DST .req x2 // void *dst
- SRC .req x3 // const void *src
- NBYTES .req w4 // unsigned int nbytes
- TWEAK .req x5 // void *tweak
-
- // registers which hold the data being encrypted/decrypted
- // (underscores avoid a naming collision with ARM64 registers x0-x3)
- X_0 .req v0
- Y_0 .req v1
- X_1 .req v2
- Y_1 .req v3
- X_2 .req v4
- Y_2 .req v5
- X_3 .req v6
- Y_3 .req v7
-
- // the round key, duplicated in all lanes
- ROUND_KEY .req v8
-
- // index vector for tbl-based 8-bit rotates
- ROTATE_TABLE .req v9
- ROTATE_TABLE_Q .req q9
-
- // temporary registers
- TMP0 .req v10
- TMP1 .req v11
- TMP2 .req v12
- TMP3 .req v13
-
- // multiplication table for updating XTS tweaks
- GFMUL_TABLE .req v14
- GFMUL_TABLE_Q .req q14
-
- // next XTS tweak value(s)
- TWEAKV_NEXT .req v15
-
- // XTS tweaks for the blocks currently being encrypted/decrypted
- TWEAKV0 .req v16
- TWEAKV1 .req v17
- TWEAKV2 .req v18
- TWEAKV3 .req v19
- TWEAKV4 .req v20
- TWEAKV5 .req v21
- TWEAKV6 .req v22
- TWEAKV7 .req v23
-
- .align 4
-.Lror64_8_table:
- .octa 0x080f0e0d0c0b0a090007060504030201
-.Lror32_8_table:
- .octa 0x0c0f0e0d080b0a090407060500030201
-.Lrol64_8_table:
- .octa 0x0e0d0c0b0a09080f0605040302010007
-.Lrol32_8_table:
- .octa 0x0e0d0c0f0a09080b0605040702010003
-.Lgf128mul_table:
- .octa 0x00000000000000870000000000000001
-.Lgf64mul_table:
- .octa 0x0000000000000000000000002d361b00
-
-/*
- * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
- *
- * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
- * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
- * of ROUND_KEY. 'n' is the lane size: 64 for Speck128, or 32 for Speck64.
- * 'lanes' is the lane specifier: "2d" for Speck128 or "4s" for Speck64.
- */
-.macro _speck_round_128bytes n, lanes
-
- // x = ror(x, 8)
- tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
- tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
- tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
- tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
-
- // x += y
- add X_0.\lanes, X_0.\lanes, Y_0.\lanes
- add X_1.\lanes, X_1.\lanes, Y_1.\lanes
- add X_2.\lanes, X_2.\lanes, Y_2.\lanes
- add X_3.\lanes, X_3.\lanes, Y_3.\lanes
-
- // x ^= k
- eor X_0.16b, X_0.16b, ROUND_KEY.16b
- eor X_1.16b, X_1.16b, ROUND_KEY.16b
- eor X_2.16b, X_2.16b, ROUND_KEY.16b
- eor X_3.16b, X_3.16b, ROUND_KEY.16b
-
- // y = rol(y, 3)
- shl TMP0.\lanes, Y_0.\lanes, #3
- shl TMP1.\lanes, Y_1.\lanes, #3
- shl TMP2.\lanes, Y_2.\lanes, #3
- shl TMP3.\lanes, Y_3.\lanes, #3
- sri TMP0.\lanes, Y_0.\lanes, #(\n - 3)
- sri TMP1.\lanes, Y_1.\lanes, #(\n - 3)
- sri TMP2.\lanes, Y_2.\lanes, #(\n - 3)
- sri TMP3.\lanes, Y_3.\lanes, #(\n - 3)
-
- // y ^= x
- eor Y_0.16b, TMP0.16b, X_0.16b
- eor Y_1.16b, TMP1.16b, X_1.16b
- eor Y_2.16b, TMP2.16b, X_2.16b
- eor Y_3.16b, TMP3.16b, X_3.16b
-.endm
-
-/*
- * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
- *
- * This is the inverse of _speck_round_128bytes().
- */
-.macro _speck_unround_128bytes n, lanes
-
- // y ^= x
- eor TMP0.16b, Y_0.16b, X_0.16b
- eor TMP1.16b, Y_1.16b, X_1.16b
- eor TMP2.16b, Y_2.16b, X_2.16b
- eor TMP3.16b, Y_3.16b, X_3.16b
-
- // y = ror(y, 3)
- ushr Y_0.\lanes, TMP0.\lanes, #3
- ushr Y_1.\lanes, TMP1.\lanes, #3
- ushr Y_2.\lanes, TMP2.\lanes, #3
- ushr Y_3.\lanes, TMP3.\lanes, #3
- sli Y_0.\lanes, TMP0.\lanes, #(\n - 3)
- sli Y_1.\lanes, TMP1.\lanes, #(\n - 3)
- sli Y_2.\lanes, TMP2.\lanes, #(\n - 3)
- sli Y_3.\lanes, TMP3.\lanes, #(\n - 3)
-
- // x ^= k
- eor X_0.16b, X_0.16b, ROUND_KEY.16b
- eor X_1.16b, X_1.16b, ROUND_KEY.16b
- eor X_2.16b, X_2.16b, ROUND_KEY.16b
- eor X_3.16b, X_3.16b, ROUND_KEY.16b
-
- // x -= y
- sub X_0.\lanes, X_0.\lanes, Y_0.\lanes
- sub X_1.\lanes, X_1.\lanes, Y_1.\lanes
- sub X_2.\lanes, X_2.\lanes, Y_2.\lanes
- sub X_3.\lanes, X_3.\lanes, Y_3.\lanes
-
- // x = rol(x, 8)
- tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
- tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
- tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
- tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
-.endm
-
-.macro _next_xts_tweak next, cur, tmp, n
-.if \n == 64
- /*
- * Calculate the next tweak by multiplying the current one by x,
- * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
- */
- sshr \tmp\().2d, \cur\().2d, #63
- and \tmp\().16b, \tmp\().16b, GFMUL_TABLE.16b
- shl \next\().2d, \cur\().2d, #1
- ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
- eor \next\().16b, \next\().16b, \tmp\().16b
-.else
- /*
- * Calculate the next two tweaks by multiplying the current ones by x^2,
- * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
- */
- ushr \tmp\().2d, \cur\().2d, #62
- shl \next\().2d, \cur\().2d, #2
- tbl \tmp\().16b, {GFMUL_TABLE.16b}, \tmp\().16b
- eor \next\().16b, \next\().16b, \tmp\().16b
-.endif
-.endm
-
-/*
- * _speck_xts_crypt() - Speck-XTS encryption/decryption
- *
- * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
- * using Speck-XTS, specifically the variant with a block size of '2n' and round
- * count given by NROUNDS. The expanded round keys are given in ROUND_KEYS, and
- * the current XTS tweak value is given in TWEAK. It's assumed that NBYTES is a
- * nonzero multiple of 128.
- */
-.macro _speck_xts_crypt n, lanes, decrypting
-
- /*
- * If decrypting, modify the ROUND_KEYS parameter to point to the last
- * round key rather than the first, since for decryption the round keys
- * are used in reverse order.
- */
-.if \decrypting
- mov NROUNDS, NROUNDS /* zero the high 32 bits */
-.if \n == 64
- add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #3
- sub ROUND_KEYS, ROUND_KEYS, #8
-.else
- add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #2
- sub ROUND_KEYS, ROUND_KEYS, #4
-.endif
-.endif
-
- // Load the index vector for tbl-based 8-bit rotates
-.if \decrypting
- ldr ROTATE_TABLE_Q, .Lrol\n\()_8_table
-.else
- ldr ROTATE_TABLE_Q, .Lror\n\()_8_table
-.endif
-
- // One-time XTS preparation
-.if \n == 64
- // Load first tweak
- ld1 {TWEAKV0.16b}, [TWEAK]
-
- // Load GF(2^128) multiplication table
- ldr GFMUL_TABLE_Q, .Lgf128mul_table
-.else
- // Load first tweak
- ld1 {TWEAKV0.8b}, [TWEAK]
-
- // Load GF(2^64) multiplication table
- ldr GFMUL_TABLE_Q, .Lgf64mul_table
-
- // Calculate second tweak, packing it together with the first
- ushr TMP0.2d, TWEAKV0.2d, #63
- shl TMP1.2d, TWEAKV0.2d, #1
- tbl TMP0.8b, {GFMUL_TABLE.16b}, TMP0.8b
- eor TMP0.8b, TMP0.8b, TMP1.8b
- mov TWEAKV0.d[1], TMP0.d[0]
-.endif
-
-.Lnext_128bytes_\@:
-
- // Calculate XTS tweaks for next 128 bytes
- _next_xts_tweak TWEAKV1, TWEAKV0, TMP0, \n
- _next_xts_tweak TWEAKV2, TWEAKV1, TMP0, \n
- _next_xts_tweak TWEAKV3, TWEAKV2, TMP0, \n
- _next_xts_tweak TWEAKV4, TWEAKV3, TMP0, \n
- _next_xts_tweak TWEAKV5, TWEAKV4, TMP0, \n
- _next_xts_tweak TWEAKV6, TWEAKV5, TMP0, \n
- _next_xts_tweak TWEAKV7, TWEAKV6, TMP0, \n
- _next_xts_tweak TWEAKV_NEXT, TWEAKV7, TMP0, \n
-
- // Load the next source blocks into {X,Y}[0-3]
- ld1 {X_0.16b-Y_1.16b}, [SRC], #64
- ld1 {X_2.16b-Y_3.16b}, [SRC], #64
-
- // XOR the source blocks with their XTS tweaks
- eor TMP0.16b, X_0.16b, TWEAKV0.16b
- eor Y_0.16b, Y_0.16b, TWEAKV1.16b
- eor TMP1.16b, X_1.16b, TWEAKV2.16b
- eor Y_1.16b, Y_1.16b, TWEAKV3.16b
- eor TMP2.16b, X_2.16b, TWEAKV4.16b
- eor Y_2.16b, Y_2.16b, TWEAKV5.16b
- eor TMP3.16b, X_3.16b, TWEAKV6.16b
- eor Y_3.16b, Y_3.16b, TWEAKV7.16b
-
- /*
- * De-interleave the 'x' and 'y' elements of each block, i.e. make it so
- * that the X[0-3] registers contain only the second halves of blocks,
- * and the Y[0-3] registers contain only the first halves of blocks.
- * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
- */
- uzp2 X_0.\lanes, TMP0.\lanes, Y_0.\lanes
- uzp1 Y_0.\lanes, TMP0.\lanes, Y_0.\lanes
- uzp2 X_1.\lanes, TMP1.\lanes, Y_1.\lanes
- uzp1 Y_1.\lanes, TMP1.\lanes, Y_1.\lanes
- uzp2 X_2.\lanes, TMP2.\lanes, Y_2.\lanes
- uzp1 Y_2.\lanes, TMP2.\lanes, Y_2.\lanes
- uzp2 X_3.\lanes, TMP3.\lanes, Y_3.\lanes
- uzp1 Y_3.\lanes, TMP3.\lanes, Y_3.\lanes
-
- // Do the cipher rounds
- mov x6, ROUND_KEYS
- mov w7, NROUNDS
-.Lnext_round_\@:
-.if \decrypting
- ld1r {ROUND_KEY.\lanes}, [x6]
- sub x6, x6, #( \n / 8 )
- _speck_unround_128bytes \n, \lanes
-.else
- ld1r {ROUND_KEY.\lanes}, [x6], #( \n / 8 )
- _speck_round_128bytes \n, \lanes
-.endif
- subs w7, w7, #1
- bne .Lnext_round_\@
-
- // Re-interleave the 'x' and 'y' elements of each block
- zip1 TMP0.\lanes, Y_0.\lanes, X_0.\lanes
- zip2 Y_0.\lanes, Y_0.\lanes, X_0.\lanes
- zip1 TMP1.\lanes, Y_1.\lanes, X_1.\lanes
- zip2 Y_1.\lanes, Y_1.\lanes, X_1.\lanes
- zip1 TMP2.\lanes, Y_2.\lanes, X_2.\lanes
- zip2 Y_2.\lanes, Y_2.\lanes, X_2.\lanes
- zip1 TMP3.\lanes, Y_3.\lanes, X_3.\lanes
- zip2 Y_3.\lanes, Y_3.\lanes, X_3.\lanes
-
- // XOR the encrypted/decrypted blocks with the tweaks calculated earlier
- eor X_0.16b, TMP0.16b, TWEAKV0.16b
- eor Y_0.16b, Y_0.16b, TWEAKV1.16b
- eor X_1.16b, TMP1.16b, TWEAKV2.16b
- eor Y_1.16b, Y_1.16b, TWEAKV3.16b
- eor X_2.16b, TMP2.16b, TWEAKV4.16b
- eor Y_2.16b, Y_2.16b, TWEAKV5.16b
- eor X_3.16b, TMP3.16b, TWEAKV6.16b
- eor Y_3.16b, Y_3.16b, TWEAKV7.16b
- mov TWEAKV0.16b, TWEAKV_NEXT.16b
-
- // Store the ciphertext in the destination buffer
- st1 {X_0.16b-Y_1.16b}, [DST], #64
- st1 {X_2.16b-Y_3.16b}, [DST], #64
-
- // Continue if there are more 128-byte chunks remaining
- subs NBYTES, NBYTES, #128
- bne .Lnext_128bytes_\@
-
- // Store the next tweak and return
-.if \n == 64
- st1 {TWEAKV_NEXT.16b}, [TWEAK]
-.else
- st1 {TWEAKV_NEXT.8b}, [TWEAK]
-.endif
- ret
-.endm
-
-ENTRY(speck128_xts_encrypt_neon)
- _speck_xts_crypt n=64, lanes=2d, decrypting=0
-ENDPROC(speck128_xts_encrypt_neon)
-
-ENTRY(speck128_xts_decrypt_neon)
- _speck_xts_crypt n=64, lanes=2d, decrypting=1
-ENDPROC(speck128_xts_decrypt_neon)
-
-ENTRY(speck64_xts_encrypt_neon)
- _speck_xts_crypt n=32, lanes=4s, decrypting=0
-ENDPROC(speck64_xts_encrypt_neon)
-
-ENTRY(speck64_xts_decrypt_neon)
- _speck_xts_crypt n=32, lanes=4s, decrypting=1
-ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm64/crypto/speck-neon-glue.c b/arch/arm64/crypto/speck-neon-glue.c
deleted file mode 100644
index 6e233aeb4ff4..000000000000
--- a/arch/arm64/crypto/speck-neon-glue.c
+++ /dev/null
@@ -1,282 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- * (64-bit version; based on the 32-bit version)
- *
- * Copyright (c) 2018 Google, Inc
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/algapi.h>
-#include <crypto/gf128mul.h>
-#include <crypto/internal/skcipher.h>
-#include <crypto/speck.h>
-#include <crypto/xts.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-/* The assembly functions only handle multiples of 128 bytes */
-#define SPECK_NEON_CHUNK_SIZE 128
-
-/* Speck128 */
-
-struct speck128_xts_tfm_ctx {
- struct speck128_tfm_ctx main_key;
- struct speck128_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
- void *dst, const void *src,
- unsigned int nbytes, void *tweak);
-
-asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
- void *dst, const void *src,
- unsigned int nbytes, void *tweak);
-
-typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
- u8 *, const u8 *);
-typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
- const void *, unsigned int, void *);
-
-static __always_inline int
-__speck128_xts_crypt(struct skcipher_request *req,
- speck128_crypt_one_t crypt_one,
- speck128_xts_crypt_many_t crypt_many)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- const struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct skcipher_walk walk;
- le128 tweak;
- int err;
-
- err = skcipher_walk_virt(&walk, req, true);
-
- crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
- while (walk.nbytes > 0) {
- unsigned int nbytes = walk.nbytes;
- u8 *dst = walk.dst.virt.addr;
- const u8 *src = walk.src.virt.addr;
-
- if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
- unsigned int count;
-
- count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
- kernel_neon_begin();
- (*crypt_many)(ctx->main_key.round_keys,
- ctx->main_key.nrounds,
- dst, src, count, &tweak);
- kernel_neon_end();
- dst += count;
- src += count;
- nbytes -= count;
- }
-
- /* Handle any remainder with generic code */
- while (nbytes >= sizeof(tweak)) {
- le128_xor((le128 *)dst, (const le128 *)src, &tweak);
- (*crypt_one)(&ctx->main_key, dst, dst);
- le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
- gf128mul_x_ble(&tweak, &tweak);
-
- dst += sizeof(tweak);
- src += sizeof(tweak);
- nbytes -= sizeof(tweak);
- }
- err = skcipher_walk_done(&walk, nbytes);
- }
-
- return err;
-}
-
-static int speck128_xts_encrypt(struct skcipher_request *req)
-{
- return __speck128_xts_crypt(req, crypto_speck128_encrypt,
- speck128_xts_encrypt_neon);
-}
-
-static int speck128_xts_decrypt(struct skcipher_request *req)
-{
- return __speck128_xts_crypt(req, crypto_speck128_decrypt,
- speck128_xts_decrypt_neon);
-}
-
-static int speck128_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
- unsigned int keylen)
-{
- struct speck128_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
- int err;
-
- err = xts_verify_key(tfm, key, keylen);
- if (err)
- return err;
-
- keylen /= 2;
-
- err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
- if (err)
- return err;
-
- return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-/* Speck64 */
-
-struct speck64_xts_tfm_ctx {
- struct speck64_tfm_ctx main_key;
- struct speck64_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
- void *dst, const void *src,
- unsigned int nbytes, void *tweak);
-
-asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
- void *dst, const void *src,
- unsigned int nbytes, void *tweak);
-
-typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
- u8 *, const u8 *);
-typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
- const void *, unsigned int, void *);
-
-static __always_inline int
-__speck64_xts_crypt(struct skcipher_request *req, speck64_crypt_one_t crypt_one,
- speck64_xts_crypt_many_t crypt_many)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- const struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
- struct skcipher_walk walk;
- __le64 tweak;
- int err;
-
- err = skcipher_walk_virt(&walk, req, true);
-
- crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
- while (walk.nbytes > 0) {
- unsigned int nbytes = walk.nbytes;
- u8 *dst = walk.dst.virt.addr;
- const u8 *src = walk.src.virt.addr;
-
- if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
- unsigned int count;
-
- count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
- kernel_neon_begin();
- (*crypt_many)(ctx->main_key.round_keys,
- ctx->main_key.nrounds,
- dst, src, count, &tweak);
- kernel_neon_end();
- dst += count;
- src += count;
- nbytes -= count;
- }
-
- /* Handle any remainder with generic code */
- while (nbytes >= sizeof(tweak)) {
- *(__le64 *)dst = *(__le64 *)src ^ tweak;
- (*crypt_one)(&ctx->main_key, dst, dst);
- *(__le64 *)dst ^= tweak;
- tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
- ((tweak & cpu_to_le64(1ULL << 63)) ?
- 0x1B : 0));
- dst += sizeof(tweak);
- src += sizeof(tweak);
- nbytes -= sizeof(tweak);
- }
- err = skcipher_walk_done(&walk, nbytes);
- }
-
- return err;
-}
-
-static int speck64_xts_encrypt(struct skcipher_request *req)
-{
- return __speck64_xts_crypt(req, crypto_speck64_encrypt,
- speck64_xts_encrypt_neon);
-}
-
-static int speck64_xts_decrypt(struct skcipher_request *req)
-{
- return __speck64_xts_crypt(req, crypto_speck64_decrypt,
- speck64_xts_decrypt_neon);
-}
-
-static int speck64_xts_setkey(struct crypto_skcipher *tfm, const u8 *key,
- unsigned int keylen)
-{
- struct speck64_xts_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
- int err;
-
- err = xts_verify_key(tfm, key, keylen);
- if (err)
- return err;
-
- keylen /= 2;
-
- err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
- if (err)
- return err;
-
- return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-static struct skcipher_alg speck_algs[] = {
- {
- .base.cra_name = "xts(speck128)",
- .base.cra_driver_name = "xts-speck128-neon",
- .base.cra_priority = 300,
- .base.cra_blocksize = SPECK128_BLOCK_SIZE,
- .base.cra_ctxsize = sizeof(struct speck128_xts_tfm_ctx),
- .base.cra_alignmask = 7,
- .base.cra_module = THIS_MODULE,
- .min_keysize = 2 * SPECK128_128_KEY_SIZE,
- .max_keysize = 2 * SPECK128_256_KEY_SIZE,
- .ivsize = SPECK128_BLOCK_SIZE,
- .walksize = SPECK_NEON_CHUNK_SIZE,
- .setkey = speck128_xts_setkey,
- .encrypt = speck128_xts_encrypt,
- .decrypt = speck128_xts_decrypt,
- }, {
- .base.cra_name = "xts(speck64)",
- .base.cra_driver_name = "xts-speck64-neon",
- .base.cra_priority = 300,
- .base.cra_blocksize = SPECK64_BLOCK_SIZE,
- .base.cra_ctxsize = sizeof(struct speck64_xts_tfm_ctx),
- .base.cra_alignmask = 7,
- .base.cra_module = THIS_MODULE,
- .min_keysize = 2 * SPECK64_96_KEY_SIZE,
- .max_keysize = 2 * SPECK64_128_KEY_SIZE,
- .ivsize = SPECK64_BLOCK_SIZE,
- .walksize = SPECK_NEON_CHUNK_SIZE,
- .setkey = speck64_xts_setkey,
- .encrypt = speck64_xts_encrypt,
- .decrypt = speck64_xts_decrypt,
- }
-};
-
-static int __init speck_neon_module_init(void)
-{
- if (!(elf_hwcap & HWCAP_ASIMD))
- return -ENODEV;
- return crypto_register_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-static void __exit speck_neon_module_exit(void)
-{
- crypto_unregister_skciphers(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-module_init(speck_neon_module_init);
-module_exit(speck_neon_module_exit);
-
-MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("xts(speck128)");
-MODULE_ALIAS_CRYPTO("xts-speck128-neon");
-MODULE_ALIAS_CRYPTO("xts(speck64)");
-MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 0bcc98dbba56..6142402c2eb4 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -286,12 +286,11 @@ alternative_endif
ldr \rd, [\rn, #MM_CONTEXT_ID]
.endm
/*
- * read_ctr - read CTR_EL0. If the system has mismatched
- * cache line sizes, provide the system wide safe value
- * from arm64_ftr_reg_ctrel0.sys_val
+ * read_ctr - read CTR_EL0. If the system has mismatched register fields,
+ * provide the system wide safe value from arm64_ftr_reg_ctrel0.sys_val
*/
.macro read_ctr, reg
-alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+alternative_if_not ARM64_MISMATCHED_CACHE_TYPE
mrs \reg, ctr_el0 // read CTR
nop
alternative_else
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 5ee5bca8c24b..13dd42c3ad4e 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -40,6 +40,15 @@
#define L1_CACHE_SHIFT (6)
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
+
+#define CLIDR_LOUU_SHIFT 27
+#define CLIDR_LOC_SHIFT 24
+#define CLIDR_LOUIS_SHIFT 21
+
+#define CLIDR_LOUU(clidr) (((clidr) >> CLIDR_LOUU_SHIFT) & 0x7)
+#define CLIDR_LOC(clidr) (((clidr) >> CLIDR_LOC_SHIFT) & 0x7)
+#define CLIDR_LOUIS(clidr) (((clidr) >> CLIDR_LOUIS_SHIFT) & 0x7)
+
/*
* Memory returned by kmalloc() may be used for DMA, so we must make
* sure that all such allocations are cache aligned. Otherwise,
@@ -84,6 +93,37 @@ static inline int cache_line_size(void)
return cwg ? 4 << cwg : ARCH_DMA_MINALIGN;
}
+/*
+ * Read the effective value of CTR_EL0.
+ *
+ * According to ARM ARM for ARMv8-A (ARM DDI 0487C.a),
+ * section D10.2.33 "CTR_EL0, Cache Type Register" :
+ *
+ * CTR_EL0.IDC reports the data cache clean requirements for
+ * instruction to data coherence.
+ *
+ * 0 - dcache clean to PoU is required unless :
+ * (CLIDR_EL1.LoC == 0) || (CLIDR_EL1.LoUIS == 0 && CLIDR_EL1.LoUU == 0)
+ * 1 - dcache clean to PoU is not required for i-to-d coherence.
+ *
+ * This routine provides the CTR_EL0 with the IDC field updated to the
+ * effective state.
+ */
+static inline u32 __attribute_const__ read_cpuid_effective_cachetype(void)
+{
+ u32 ctr = read_cpuid_cachetype();
+
+ if (!(ctr & BIT(CTR_IDC_SHIFT))) {
+ u64 clidr = read_sysreg(clidr_el1);
+
+ if (CLIDR_LOC(clidr) == 0 ||
+ (CLIDR_LOUIS(clidr) == 0 && CLIDR_LOUU(clidr) == 0))
+ ctr |= BIT(CTR_IDC_SHIFT);
+ }
+
+ return ctr;
+}
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 1a037b94eba1..93ce86d5dae1 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -25,6 +25,8 @@
#include <linux/sched.h>
#include <linux/sched/task_stack.h>
+#include <asm-generic/compat.h>
+
#define COMPAT_USER_HZ 100
#ifdef __AARCH64EB__
#define COMPAT_UTS_MACHINE "armv8b\0\0"
@@ -32,10 +34,6 @@
#define COMPAT_UTS_MACHINE "armv8l\0\0"
#endif
-typedef u32 compat_size_t;
-typedef s32 compat_ssize_t;
-typedef s32 compat_clock_t;
-typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
typedef u16 __compat_gid_t;
typedef u16 __compat_uid16_t;
@@ -43,27 +41,13 @@ typedef u16 __compat_gid16_t;
typedef u32 __compat_uid32_t;
typedef u32 __compat_gid32_t;
typedef u16 compat_mode_t;
-typedef u32 compat_ino_t;
typedef u32 compat_dev_t;
-typedef s32 compat_off_t;
-typedef s64 compat_loff_t;
typedef s32 compat_nlink_t;
typedef u16 compat_ipc_pid_t;
-typedef s32 compat_daddr_t;
typedef u32 compat_caddr_t;
typedef __kernel_fsid_t compat_fsid_t;
-typedef s32 compat_key_t;
-typedef s32 compat_timer_t;
-
-typedef s16 compat_short_t;
-typedef s32 compat_int_t;
-typedef s32 compat_long_t;
typedef s64 compat_s64;
-typedef u16 compat_ushort_t;
-typedef u32 compat_uint_t;
-typedef u32 compat_ulong_t;
typedef u64 compat_u64;
-typedef u32 compat_uptr_t;
struct compat_stat {
#ifdef __AARCH64EB__
@@ -86,11 +70,11 @@ struct compat_stat {
compat_off_t st_size;
compat_off_t st_blksize;
compat_off_t st_blocks;
- compat_time_t st_atime;
+ old_time32_t st_atime;
compat_ulong_t st_atime_nsec;
- compat_time_t st_mtime;
+ old_time32_t st_mtime;
compat_ulong_t st_mtime_nsec;
- compat_time_t st_ctime;
+ old_time32_t st_ctime;
compat_ulong_t st_ctime_nsec;
compat_ulong_t __unused4[2];
};
@@ -159,6 +143,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
}
#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
+#define COMPAT_MINSIGSTKSZ 2048
static inline void __user *arch_compat_alloc_user_space(long len)
{
diff --git a/arch/arm64/include/asm/compiler.h b/arch/arm64/include/asm/compiler.h
deleted file mode 100644
index ee35fd0f2236..000000000000
--- a/arch/arm64/include/asm/compiler.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Based on arch/arm/include/asm/compiler.h
- *
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_COMPILER_H
-#define __ASM_COMPILER_H
-
-/*
- * This is used to ensure the compiler did actually allocate the register we
- * asked it for some inline assembly sequences. Apparently we can't trust the
- * compiler from one version to another so a bit of paranoia won't hurt. This
- * string is meant to be concatenated with the inline asm string and will
- * cause compilation to stop on mismatch. (for details, see gcc PR 15089)
- */
-#define __asmeq(x, y) ".ifnc " x "," y " ; .err ; .endif\n\t"
-
-#endif /* __ASM_COMPILER_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index ae1f70450fb2..6e2d254c09eb 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -33,7 +33,7 @@
#define ARM64_WORKAROUND_CAVIUM_27456 12
#define ARM64_HAS_32BIT_EL0 13
#define ARM64_HARDEN_EL2_VECTORS 14
-#define ARM64_MISMATCHED_CACHE_LINE_SIZE 15
+#define ARM64_HAS_CNP 15
#define ARM64_HAS_NO_FPSIMD 16
#define ARM64_WORKAROUND_REPEAT_TLBI 17
#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18
@@ -51,7 +51,10 @@
#define ARM64_SSBD 30
#define ARM64_MISMATCHED_CACHE_TYPE 31
#define ARM64_HAS_STAGE2_FWB 32
+#define ARM64_HAS_CRC32 33
+#define ARM64_SSBS 34
+#define ARM64_WORKAROUND_1188873 35
-#define ARM64_NCAPS 33
+#define ARM64_NCAPS 36
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 1717ba1db35d..7e2ec64aa414 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -262,7 +262,7 @@ extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
/*
* CPU feature detected at boot time based on system-wide value of a
* feature. It is safe for a late CPU to have this feature even though
- * the system hasn't enabled it, although the featuer will not be used
+ * the system hasn't enabled it, although the feature will not be used
* by Linux in this case. If the system has enabled this feature already,
* then every late CPU must have it.
*/
@@ -508,6 +508,12 @@ static inline bool system_supports_sve(void)
cpus_have_const_cap(ARM64_SVE);
}
+static inline bool system_supports_cnp(void)
+{
+ return IS_ENABLED(CONFIG_ARM64_CNP) &&
+ cpus_have_const_cap(ARM64_HAS_CNP);
+}
+
#define ARM64_SSBD_UNKNOWN -1
#define ARM64_SSBD_FORCE_DISABLE 0
#define ARM64_SSBD_KERNEL 1
@@ -530,6 +536,28 @@ void arm64_set_ssbd_mitigation(bool state);
static inline void arm64_set_ssbd_mitigation(bool state) {}
#endif
+extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
+
+static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
+{
+ switch (parange) {
+ case 0: return 32;
+ case 1: return 36;
+ case 2: return 40;
+ case 3: return 42;
+ case 4: return 44;
+ case 5: return 48;
+ case 6: return 52;
+ /*
+ * A future PE could use a value unknown to the kernel.
+ * However, by the "D10.1.4 Principles of the ID scheme
+ * for fields in ID registers", ARM DDI 0487C.a, any new
+ * value is guaranteed to be higher than what we know already.
+ * As a safe limit, we return the limit supported by the kernel.
+ */
+ default: return CONFIG_ARM64_PA_BITS;
+ }
+}
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index ea690b3562af..12f93e4d2452 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -86,6 +86,7 @@
#define ARM_CPU_PART_CORTEX_A75 0xD0A
#define ARM_CPU_PART_CORTEX_A35 0xD04
#define ARM_CPU_PART_CORTEX_A55 0xD05
+#define ARM_CPU_PART_CORTEX_A76 0xD0B
#define APM_CPU_PART_POTENZA 0x000
@@ -110,6 +111,7 @@
#define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75)
#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
+#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h
index 22e4c83de5a5..8d91f2233135 100644
--- a/arch/arm64/include/asm/daifflags.h
+++ b/arch/arm64/include/asm/daifflags.h
@@ -36,11 +36,8 @@ static inline unsigned long local_daif_save(void)
{
unsigned long flags;
- asm volatile(
- "mrs %0, daif // local_daif_save\n"
- : "=r" (flags)
- :
- : "memory");
+ flags = arch_local_save_flags();
+
local_daif_mask();
return flags;
@@ -60,11 +57,9 @@ static inline void local_daif_restore(unsigned long flags)
{
if (!arch_irqs_disabled_flags(flags))
trace_hardirqs_on();
- asm volatile(
- "msr daif, %0 // local_daif_restore"
- :
- : "r" (flags)
- : "memory");
+
+ arch_local_irq_restore(flags);
+
if (arch_irqs_disabled_flags(flags))
trace_hardirqs_off();
}
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 5a5fa47a6b18..3dd3d664c5c5 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -23,7 +23,6 @@ struct dev_archdata {
#ifdef CONFIG_XEN
const struct dma_map_ops *dev_dma_ops;
#endif
- bool dma_coherent;
};
struct pdev_archdata {
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index b7847eb8a7bb..c41f3fb1446c 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -44,10 +44,13 @@ void arch_teardown_dma_ops(struct device *dev);
#define arch_teardown_dma_ops arch_teardown_dma_ops
#endif
-/* do not use this function in a driver */
+/*
+ * Do not use this function in a driver, it is only provided for
+ * arch/arm/mm/xen.c, which is used by arm64 as well.
+ */
static inline bool is_device_dma_coherent(struct device *dev)
{
- return dev->archdata.dma_coherent;
+ return dev->dma_coherent;
}
#endif /* __KERNEL__ */
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index ce70c3ffb993..676de2ec1762 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -137,6 +137,8 @@
#define ESR_ELx_CV (UL(1) << 24)
#define ESR_ELx_COND_SHIFT (20)
#define ESR_ELx_COND_MASK (UL(0xF) << ESR_ELx_COND_SHIFT)
+#define ESR_ELx_WFx_ISS_TI (UL(1) << 0)
+#define ESR_ELx_WFx_ISS_WFI (UL(0) << 0)
#define ESR_ELx_WFx_ISS_WFE (UL(1) << 0)
#define ESR_ELx_xVC_IMM_MASK ((1UL << 16) - 1)
@@ -148,6 +150,9 @@
#define DISR_EL1_ESR_MASK (ESR_ELx_AET | ESR_ELx_EA | ESR_ELx_FSC)
/* ESR value templates for specific events */
+#define ESR_ELx_WFx_MASK (ESR_ELx_EC_MASK | ESR_ELx_WFx_ISS_TI)
+#define ESR_ELx_WFx_WFI_VAL ((ESR_ELx_EC_WFx << ESR_ELx_EC_SHIFT) | \
+ ESR_ELx_WFx_ISS_WFI)
/* BRK instruction trap from AArch64 state */
#define ESR_ELx_VAL_BRK64(imm) \
@@ -187,6 +192,8 @@
#define ESR_ELx_SYS64_ISS_SYS_OP_MASK (ESR_ELx_SYS64_ISS_SYS_MASK | \
ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_RT(esr) \
+ (((esr) & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT)
/*
* User space cache operations have the following sysreg encoding
* in System instructions.
@@ -206,6 +213,18 @@
#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
(ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
ESR_ELx_SYS64_ISS_DIR_WRITE)
+/*
+ * User space MRS operations which are supported for emulation
+ * have the following sysreg encoding in System instructions.
+ * op0 = 3, op1= 0, crn = 0, {crm = 0, 4-7}, READ (L = 1)
+ */
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK (ESR_ELx_SYS64_ISS_OP0_MASK | \
+ ESR_ELx_SYS64_ISS_OP1_MASK | \
+ ESR_ELx_SYS64_ISS_CRN_MASK | \
+ ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL \
+ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 0, 0, 0, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
#define ESR_ELx_SYS64_ISS_SYS_CTR ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
@@ -249,6 +268,64 @@
#define ESR_ELx_FP_EXC_TFV (UL(1) << 23)
+/*
+ * ISS field definitions for CP15 accesses
+ */
+#define ESR_ELx_CP15_32_ISS_DIR_MASK 0x1
+#define ESR_ELx_CP15_32_ISS_DIR_READ 0x1
+#define ESR_ELx_CP15_32_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_CP15_32_ISS_RT_SHIFT 5
+#define ESR_ELx_CP15_32_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_32_ISS_RT_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRM_SHIFT 1
+#define ESR_ELx_CP15_32_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRM_SHIFT)
+#define ESR_ELx_CP15_32_ISS_CRN_SHIFT 10
+#define ESR_ELx_CP15_32_ISS_CRN_MASK (UL(0xf) << ESR_ELx_CP15_32_ISS_CRN_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP1_SHIFT 14
+#define ESR_ELx_CP15_32_ISS_OP1_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_32_ISS_OP2_SHIFT 17
+#define ESR_ELx_CP15_32_ISS_OP2_MASK (UL(0x7) << ESR_ELx_CP15_32_ISS_OP2_SHIFT)
+
+#define ESR_ELx_CP15_32_ISS_SYS_MASK (ESR_ELx_CP15_32_ISS_OP1_MASK | \
+ ESR_ELx_CP15_32_ISS_OP2_MASK | \
+ ESR_ELx_CP15_32_ISS_CRN_MASK | \
+ ESR_ELx_CP15_32_ISS_CRM_MASK | \
+ ESR_ELx_CP15_32_ISS_DIR_MASK)
+#define ESR_ELx_CP15_32_ISS_SYS_VAL(op1, op2, crn, crm) \
+ (((op1) << ESR_ELx_CP15_32_ISS_OP1_SHIFT) | \
+ ((op2) << ESR_ELx_CP15_32_ISS_OP2_SHIFT) | \
+ ((crn) << ESR_ELx_CP15_32_ISS_CRN_SHIFT) | \
+ ((crm) << ESR_ELx_CP15_32_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_DIR_MASK 0x1
+#define ESR_ELx_CP15_64_ISS_DIR_READ 0x1
+#define ESR_ELx_CP15_64_ISS_DIR_WRITE 0x0
+
+#define ESR_ELx_CP15_64_ISS_RT_SHIFT 5
+#define ESR_ELx_CP15_64_ISS_RT_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_RT2_SHIFT 10
+#define ESR_ELx_CP15_64_ISS_RT2_MASK (UL(0x1f) << ESR_ELx_CP15_64_ISS_RT2_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_OP1_SHIFT 16
+#define ESR_ELx_CP15_64_ISS_OP1_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_OP1_SHIFT)
+#define ESR_ELx_CP15_64_ISS_CRM_SHIFT 1
+#define ESR_ELx_CP15_64_ISS_CRM_MASK (UL(0xf) << ESR_ELx_CP15_64_ISS_CRM_SHIFT)
+
+#define ESR_ELx_CP15_64_ISS_SYS_VAL(op1, crm) \
+ (((op1) << ESR_ELx_CP15_64_ISS_OP1_SHIFT) | \
+ ((crm) << ESR_ELx_CP15_64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_CP15_64_ISS_SYS_MASK (ESR_ELx_CP15_64_ISS_OP1_MASK | \
+ ESR_ELx_CP15_64_ISS_CRM_MASK | \
+ ESR_ELx_CP15_64_ISS_DIR_MASK)
+
+#define ESR_ELx_CP15_64_ISS_SYS_CNTVCT (ESR_ELx_CP15_64_ISS_SYS_VAL(1, 14) | \
+ ESR_ELx_CP15_64_ISS_DIR_READ)
+
+#define ESR_ELx_CP15_32_ISS_SYS_CNTFRQ (ESR_ELx_CP15_32_ISS_SYS_VAL(0, 0, 14, 0) |\
+ ESR_ELx_CP15_32_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index e73f68569624..fb6609875455 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -20,48 +20,18 @@
#include <asm/page.h>
+#define __HAVE_ARCH_HUGE_PTEP_GET
static inline pte_t huge_ptep_get(pte_t *ptep)
{
return READ_ONCE(*ptep);
}
-
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end,
- unsigned long floor,
- unsigned long ceiling)
-{
- free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr, unsigned long len)
{
return 0;
}
-static inline int prepare_hugepage_range(struct file *file,
- unsigned long addr, unsigned long len)
-{
- struct hstate *h = hstate_file(file);
- if (len & ~huge_page_mask(h))
- return -EINVAL;
- if (addr & ~huge_page_mask(h))
- return -EINVAL;
- return 0;
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
- return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
- return pte_wrprotect(pte);
-}
-
static inline void arch_clear_hugepage_flags(struct page *page)
{
clear_bit(PG_dcache_clean, &page->flags);
@@ -70,20 +40,25 @@ static inline void arch_clear_hugepage_flags(struct page *page)
extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
struct page *page, int writable);
#define arch_make_huge_pte arch_make_huge_pte
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz);
-#define huge_pte_clear huge_pte_clear
extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte, unsigned long sz);
#define set_huge_swap_pte_at set_huge_swap_pte_at
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 35b2e50f17fb..9f8b915af3a7 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -31,8 +31,6 @@
#include <asm/alternative.h>
#include <asm/cpufeature.h>
-#include <xen/xen.h>
-
/*
* Generic IO read/write. These perform native-endian accesses.
*/
@@ -205,12 +203,5 @@ extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
extern int devmem_is_allowed(unsigned long pfn);
-struct bio_vec;
-extern bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
- const struct bio_vec *vec2);
-#define BIOVEC_PHYS_MERGEABLE(vec1, vec2) \
- (__BIOVEC_PHYS_MERGEABLE(vec1, vec2) && \
- (!xen_domain() || xen_biovec_phys_mergeable(vec1, vec2)))
-
#endif /* __KERNEL__ */
#endif /* __ASM_IO_H */
diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
index 1b5e0e843c3a..472023498d71 100644
--- a/arch/arm64/include/asm/jump_label.h
+++ b/arch/arm64/include/asm/jump_label.h
@@ -26,13 +26,16 @@
#define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key *key,
+ bool branch)
{
- asm goto("1: nop\n\t"
- ".pushsection __jump_table, \"aw\"\n\t"
- ".align 3\n\t"
- ".quad 1b, %l[l_yes], %c0\n\t"
- ".popsection\n\t"
+ asm_volatile_goto(
+ "1: nop \n\t"
+ " .pushsection __jump_table, \"aw\" \n\t"
+ " .align 3 \n\t"
+ " .long 1b - ., %l[l_yes] - . \n\t"
+ " .quad %c0 - . \n\t"
+ " .popsection \n\t"
: : "i"(&((char *)key)[branch]) : : l_yes);
return false;
@@ -40,13 +43,16 @@ l_yes:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key *key,
+ bool branch)
{
- asm goto("1: b %l[l_yes]\n\t"
- ".pushsection __jump_table, \"aw\"\n\t"
- ".align 3\n\t"
- ".quad 1b, %l[l_yes], %c0\n\t"
- ".popsection\n\t"
+ asm_volatile_goto(
+ "1: b %l[l_yes] \n\t"
+ " .pushsection __jump_table, \"aw\" \n\t"
+ " .align 3 \n\t"
+ " .long 1b - ., %l[l_yes] - . \n\t"
+ " .quad %c0 - . \n\t"
+ " .popsection \n\t"
: : "i"(&((char *)key)[branch]) : : l_yes);
return false;
@@ -54,13 +60,5 @@ l_yes:
return true;
}
-typedef u64 jump_label_t;
-
-struct jump_entry {
- jump_label_t code;
- jump_label_t target;
- jump_label_t key;
-};
-
#endif /* __ASSEMBLY__ */
#endif /* __ASM_JUMP_LABEL_H */
diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h
index a780f6714b44..850e2122d53f 100644
--- a/arch/arm64/include/asm/kernel-pgtable.h
+++ b/arch/arm64/include/asm/kernel-pgtable.h
@@ -97,7 +97,7 @@
+ EARLY_PGDS((vstart), (vend)) /* each PGDIR needs a next level page table */ \
+ EARLY_PUDS((vstart), (vend)) /* each PUD needs a next level page table */ \
+ EARLY_PMDS((vstart), (vend))) /* each PMD needs a next level page table */
-#define SWAPPER_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
+#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR + TEXT_OFFSET, _end))
#define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index aa45df752a16..6f602af5263c 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -107,6 +107,7 @@
#define VTCR_EL2_RES1 (1 << 31)
#define VTCR_EL2_HD (1 << 22)
#define VTCR_EL2_HA (1 << 21)
+#define VTCR_EL2_PS_SHIFT TCR_EL2_PS_SHIFT
#define VTCR_EL2_PS_MASK TCR_EL2_PS_MASK
#define VTCR_EL2_TG0_MASK TCR_TG0_MASK
#define VTCR_EL2_TG0_4K TCR_TG0_4K
@@ -120,62 +121,150 @@
#define VTCR_EL2_IRGN0_WBWA TCR_IRGN0_WBWA
#define VTCR_EL2_SL0_SHIFT 6
#define VTCR_EL2_SL0_MASK (3 << VTCR_EL2_SL0_SHIFT)
-#define VTCR_EL2_SL0_LVL1 (1 << VTCR_EL2_SL0_SHIFT)
#define VTCR_EL2_T0SZ_MASK 0x3f
-#define VTCR_EL2_T0SZ_40B 24
#define VTCR_EL2_VS_SHIFT 19
#define VTCR_EL2_VS_8BIT (0 << VTCR_EL2_VS_SHIFT)
#define VTCR_EL2_VS_16BIT (1 << VTCR_EL2_VS_SHIFT)
+#define VTCR_EL2_T0SZ(x) TCR_T0SZ(x)
+
/*
* We configure the Stage-2 page tables to always restrict the IPA space to be
* 40 bits wide (T0SZ = 24). Systems with a PARange smaller than 40 bits are
* not known to exist and will break with this configuration.
*
- * VTCR_EL2.PS is extracted from ID_AA64MMFR0_EL1.PARange at boot time
- * (see hyp-init.S).
+ * The VTCR_EL2 is configured per VM and is initialised in kvm_arm_setup_stage2().
*
* Note that when using 4K pages, we concatenate two first level page tables
* together. With 16K pages, we concatenate 16 first level page tables.
*
- * The magic numbers used for VTTBR_X in this patch can be found in Tables
- * D4-23 and D4-25 in ARM DDI 0487A.b.
*/
-#define VTCR_EL2_T0SZ_IPA VTCR_EL2_T0SZ_40B
#define VTCR_EL2_COMMON_BITS (VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
VTCR_EL2_IRGN0_WBWA | VTCR_EL2_RES1)
-#ifdef CONFIG_ARM64_64K_PAGES
/*
- * Stage2 translation configuration:
- * 64kB pages (TG0 = 1)
- * 2 level page tables (SL = 1)
+ * VTCR_EL2:SL0 indicates the entry level for Stage2 translation.
+ * Interestingly, it depends on the page size.
+ * See D.10.2.121, VTCR_EL2, in ARM DDI 0487C.a
+ *
+ * -----------------------------------------
+ * | Entry level | 4K | 16K/64K |
+ * ------------------------------------------
+ * | Level: 0 | 2 | - |
+ * ------------------------------------------
+ * | Level: 1 | 1 | 2 |
+ * ------------------------------------------
+ * | Level: 2 | 0 | 1 |
+ * ------------------------------------------
+ * | Level: 3 | - | 0 |
+ * ------------------------------------------
+ *
+ * The table roughly translates to :
+ *
+ * SL0(PAGE_SIZE, Entry_level) = TGRAN_SL0_BASE - Entry_Level
+ *
+ * Where TGRAN_SL0_BASE is a magic number depending on the page size:
+ * TGRAN_SL0_BASE(4K) = 2
+ * TGRAN_SL0_BASE(16K) = 3
+ * TGRAN_SL0_BASE(64K) = 3
+ * provided we take care of ruling out the unsupported cases and
+ * Entry_Level = 4 - Number_of_levels.
+ *
*/
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_64K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 38
+#ifdef CONFIG_ARM64_64K_PAGES
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_64K
+#define VTCR_EL2_TGRAN_SL0_BASE 3UL
+
#elif defined(CONFIG_ARM64_16K_PAGES)
-/*
- * Stage2 translation configuration:
- * 16kB pages (TG0 = 2)
- * 2 level page tables (SL = 1)
- */
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_16K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 42
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_16K
+#define VTCR_EL2_TGRAN_SL0_BASE 3UL
+
#else /* 4K */
-/*
- * Stage2 translation configuration:
- * 4kB pages (TG0 = 0)
- * 3 level page tables (SL = 1)
- */
-#define VTCR_EL2_TGRAN_FLAGS (VTCR_EL2_TG0_4K | VTCR_EL2_SL0_LVL1)
-#define VTTBR_X_TGRAN_MAGIC 37
+
+#define VTCR_EL2_TGRAN VTCR_EL2_TG0_4K
+#define VTCR_EL2_TGRAN_SL0_BASE 2UL
+
#endif
-#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
-#define VTTBR_X (VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
+#define VTCR_EL2_LVLS_TO_SL0(levels) \
+ ((VTCR_EL2_TGRAN_SL0_BASE - (4 - (levels))) << VTCR_EL2_SL0_SHIFT)
+#define VTCR_EL2_SL0_TO_LVLS(sl0) \
+ ((sl0) + 4 - VTCR_EL2_TGRAN_SL0_BASE)
+#define VTCR_EL2_LVLS(vtcr) \
+ VTCR_EL2_SL0_TO_LVLS(((vtcr) & VTCR_EL2_SL0_MASK) >> VTCR_EL2_SL0_SHIFT)
-#define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
+#define VTCR_EL2_FLAGS (VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN)
+#define VTCR_EL2_IPA(vtcr) (64 - ((vtcr) & VTCR_EL2_T0SZ_MASK))
+
+/*
+ * ARM VMSAv8-64 defines an algorithm for finding the translation table
+ * descriptors in section D4.2.8 in ARM DDI 0487C.a.
+ *
+ * The algorithm defines the expectations on the translation table
+ * addresses for each level, based on PAGE_SIZE, entry level
+ * and the translation table size (T0SZ). The variable "x" in the
+ * algorithm determines the alignment of a table base address at a given
+ * level and thus determines the alignment of VTTBR:BADDR for stage2
+ * page table entry level.
+ * Since the number of bits resolved at the entry level could vary
+ * depending on the T0SZ, the value of "x" is defined based on a
+ * Magic constant for a given PAGE_SIZE and Entry Level. The
+ * intermediate levels must be always aligned to the PAGE_SIZE (i.e,
+ * x = PAGE_SHIFT).
+ *
+ * The value of "x" for entry level is calculated as :
+ * x = Magic_N - T0SZ
+ *
+ * where Magic_N is an integer depending on the page size and the entry
+ * level of the page table as below:
+ *
+ * --------------------------------------------
+ * | Entry level | 4K 16K 64K |
+ * --------------------------------------------
+ * | Level: 0 (4 levels) | 28 | - | - |
+ * --------------------------------------------
+ * | Level: 1 (3 levels) | 37 | 31 | 25 |
+ * --------------------------------------------
+ * | Level: 2 (2 levels) | 46 | 42 | 38 |
+ * --------------------------------------------
+ * | Level: 3 (1 level) | - | 53 | 51 |
+ * --------------------------------------------
+ *
+ * We have a magic formula for the Magic_N below:
+ *
+ * Magic_N(PAGE_SIZE, Level) = 64 - ((PAGE_SHIFT - 3) * Number_of_levels)
+ *
+ * where Number_of_levels = (4 - Level). We are only interested in the
+ * value for Entry_Level for the stage2 page table.
+ *
+ * So, given that T0SZ = (64 - IPA_SHIFT), we can compute 'x' as follows:
+ *
+ * x = (64 - ((PAGE_SHIFT - 3) * Number_of_levels)) - (64 - IPA_SHIFT)
+ * = IPA_SHIFT - ((PAGE_SHIFT - 3) * Number of levels)
+ *
+ * Here is one way to explain the Magic Formula:
+ *
+ * x = log2(Size_of_Entry_Level_Table)
+ *
+ * Since, we can resolve (PAGE_SHIFT - 3) bits at each level, and another
+ * PAGE_SHIFT bits in the PTE, we have :
+ *
+ * Bits_Entry_level = IPA_SHIFT - ((PAGE_SHIFT - 3) * (n - 1) + PAGE_SHIFT)
+ * = IPA_SHIFT - (PAGE_SHIFT - 3) * n - 3
+ * where n = number of levels, and since each pointer is 8bytes, we have:
+ *
+ * x = Bits_Entry_Level + 3
+ * = IPA_SHIFT - (PAGE_SHIFT - 3) * n
+ *
+ * The only constraint here is that, we have to find the number of page table
+ * levels for a given IPA size (which we do, see stage2_pt_levels())
+ */
+#define ARM64_VTTBR_X(ipa, levels) ((ipa) - ((levels) * (PAGE_SHIFT - 3)))
+
+#define VTTBR_CNP_BIT (UL(1))
#define VTTBR_VMID_SHIFT (UL(48))
#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
@@ -223,6 +312,13 @@
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
+/*
+ * We have
+ * PAR [PA_Shift - 1 : 12] = PA [PA_Shift - 1 : 12]
+ * HPFAR [PA_Shift - 9 : 4] = FIPA [PA_Shift - 1 : 12]
+ */
+#define PAR_TO_HPFAR(par) \
+ (((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
#define kvm_arm_exception_type \
{0, "IRQ" }, \
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 102b5a5c47b6..aea01a09eb94 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -30,6 +30,7 @@
#define ARM_EXCEPTION_IRQ 0
#define ARM_EXCEPTION_EL1_SERROR 1
#define ARM_EXCEPTION_TRAP 2
+#define ARM_EXCEPTION_IL 3
/* The hyp-stub will return this for any kvm_call_hyp() call */
#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR
@@ -72,8 +73,6 @@ extern void __vgic_v3_init_lrs(void);
extern u32 __kvm_get_mdcr_el2(void);
-extern u32 __init_stage2_translation(void);
-
/* Home-grown __this_cpu_{ptr,read} variants that always work at HYP */
#define __hyp_this_cpu_ptr(sym) \
({ \
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 6106a85ae0be..21247870def7 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -335,7 +335,7 @@ static inline bool kvm_vcpu_dabt_isextabt(const struct kvm_vcpu *vcpu)
static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
{
u32 esr = kvm_vcpu_get_hsr(vcpu);
- return (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ return ESR_ELx_SYS64_ISS_RT(esr);
}
static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f26055f2306e..52fbc823ff8c 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -53,7 +53,7 @@ DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
-int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext);
+int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
struct kvm_arch {
@@ -61,12 +61,13 @@ struct kvm_arch {
u64 vmid_gen;
u32 vmid;
- /* 1-level 2nd stage table and lock */
- spinlock_t pgd_lock;
+ /* stage2 entry level table */
pgd_t *pgd;
/* VTTBR value associated with above pgd and vmid */
u64 vttbr;
+ /* VTCR_EL2 value for this VM */
+ u64 vtcr;
/* The last vcpu id that ran on each physical CPU */
int __percpu *last_vcpu_ran;
@@ -357,7 +358,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events);
#define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm,
unsigned long start, unsigned long end);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
@@ -389,6 +389,8 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);
DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state);
+void __kvm_enable_ssbs(void);
+
static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
unsigned long hyp_stack_ptr,
unsigned long vector_ptr)
@@ -409,6 +411,15 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
*/
BUG_ON(!static_branch_likely(&arm64_const_caps_ready));
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr, tpidr_el2);
+
+ /*
+ * Disabling SSBD on a non-VHE system requires us to enable SSBS
+ * at EL2.
+ */
+ if (!has_vhe() && this_cpu_has_cap(ARM64_SSBS) &&
+ arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+ kvm_call_hyp(__kvm_enable_ssbs);
+ }
}
static inline bool kvm_arch_check_sve_has_vhe(void)
@@ -442,13 +453,7 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
-static inline void __cpu_init_stage2(void)
-{
- u32 parange = kvm_call_hyp(__init_stage2_translation);
-
- WARN_ONCE(parange < 40,
- "PARange is %d bits, unsupported configuration!", parange);
-}
+static inline void __cpu_init_stage2(void) {}
/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
@@ -511,8 +516,12 @@ static inline int kvm_arm_have_ssbd(void)
void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu);
void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu);
+void kvm_set_ipa_limit(void);
+
#define __KVM_HAVE_ARCH_VM_ALLOC
struct kvm *kvm_arch_alloc_vm(void);
void kvm_arch_free_vm(struct kvm *kvm);
+int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
+
#endif /* __ARM64_KVM_HOST_H__ */
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 384c34397619..23aca66767f9 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -155,5 +155,15 @@ void deactivate_traps_vhe_put(void);
u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt);
void __noreturn __hyp_do_panic(unsigned long, ...);
+/*
+ * Must be called from hyp code running at EL2 with an updated VTTBR
+ * and interrupts disabled.
+ */
+static __always_inline void __hyp_text __load_guest_stage2(struct kvm *kvm)
+{
+ write_sysreg(kvm->arch.vtcr, vtcr_el2);
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+}
+
#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index d6fff7de5539..658657367f2f 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -141,8 +141,16 @@ static inline unsigned long __kern_hyp_va(unsigned long v)
* We currently only support a 40bit IPA.
*/
#define KVM_PHYS_SHIFT (40)
-#define KVM_PHYS_SIZE (1UL << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1UL)
+
+#define kvm_phys_shift(kvm) VTCR_EL2_IPA(kvm->arch.vtcr)
+#define kvm_phys_size(kvm) (_AC(1, ULL) << kvm_phys_shift(kvm))
+#define kvm_phys_mask(kvm) (kvm_phys_size(kvm) - _AC(1, ULL))
+
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
#include <asm/stage2_pgtable.h>
@@ -238,12 +246,6 @@ static inline bool kvm_s2pmd_exec(pmd_t *pmdp)
return !(READ_ONCE(pmd_val(*pmdp)) & PMD_S2_XN);
}
-static inline bool kvm_page_empty(void *ptr)
-{
- struct page *ptr_page = virt_to_page(ptr);
- return page_count(ptr_page) == 1;
-}
-
#define hyp_pte_table_empty(ptep) kvm_page_empty(ptep)
#ifdef __PAGETABLE_PMD_FOLDED
@@ -517,5 +519,34 @@ static inline int hyp_map_aux_data(void)
#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
+/*
+ * Get the magic number 'x' for VTTBR:BADDR of this KVM instance.
+ * With v8.2 LVA extensions, 'x' should be a minimum of 6 with
+ * 52bit IPS.
+ */
+static inline int arm64_vttbr_x(u32 ipa_shift, u32 levels)
+{
+ int x = ARM64_VTTBR_X(ipa_shift, levels);
+
+ return (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && x < 6) ? 6 : x;
+}
+
+static inline u64 vttbr_baddr_mask(u32 ipa_shift, u32 levels)
+{
+ unsigned int x = arm64_vttbr_x(ipa_shift, levels);
+
+ return GENMASK_ULL(PHYS_MASK_SHIFT - 1, x);
+}
+
+static inline u64 kvm_vttbr_baddr_mask(struct kvm *kvm)
+{
+ return vttbr_baddr_mask(kvm_phys_shift(kvm), kvm_stage2_levels(kvm));
+}
+
+static inline bool kvm_cpu_has_cnp(void)
+{
+ return system_supports_cnp();
+}
+
#endif /* __ASSEMBLY__ */
#endif /* __ARM64_KVM_MMU_H__ */
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index dd320df0d026..7689c7aa1d77 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -95,5 +95,8 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
extern void mark_linear_text_alias_ro(void);
+#define INIT_MM_CONTEXT(name) \
+ .pgd = init_pg_dir,
+
#endif /* !__ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index 39ec0b8a689e..1e58bf58c22b 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -147,12 +147,25 @@ static inline void cpu_replace_ttbr1(pgd_t *pgdp)
extern ttbr_replace_func idmap_cpu_replace_ttbr1;
ttbr_replace_func *replace_phys;
- phys_addr_t pgd_phys = virt_to_phys(pgdp);
+ /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */
+ phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp));
+
+ if (system_supports_cnp() && !WARN_ON(pgdp != lm_alias(swapper_pg_dir))) {
+ /*
+ * cpu_replace_ttbr1() is used when there's a boot CPU
+ * up (i.e. cpufeature framework is not up yet) and
+ * latter only when we enable CNP via cpufeature's
+ * enable() callback.
+ * Also we rely on the cpu_hwcap bit being set before
+ * calling the enable() function.
+ */
+ ttbr1 |= TTBR_CNP_BIT;
+ }
replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1);
cpu_install_idmap();
- replace_phys(pgd_phys);
+ replace_phys(ttbr1);
cpu_uninstall_idmap();
}
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 60d02c81a3a2..c88a3cb117a1 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -37,9 +37,7 @@ extern void clear_page(void *to);
typedef struct page *pgtable_t;
-#ifdef CONFIG_HAVE_ARCH_PFN_VALID
extern int pfn_valid(unsigned long);
-#endif
#include <asm/memory.h>
diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h
index bb5dcea42003..799d9dd6f7cc 100644
--- a/arch/arm64/include/asm/paravirt.h
+++ b/arch/arm64/include/asm/paravirt.h
@@ -10,11 +10,16 @@ extern struct static_key paravirt_steal_rq_enabled;
struct pv_time_ops {
unsigned long long (*steal_clock)(int cpu);
};
-extern struct pv_time_ops pv_time_ops;
+
+struct paravirt_patch_template {
+ struct pv_time_ops time;
+};
+
+extern struct paravirt_patch_template pv_ops;
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_time_ops.steal_clock(cpu);
+ return pv_ops.time.steal_clock(cpu);
}
#endif
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index fd208eac9f2a..1d7d8da2ef9b 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -211,6 +211,8 @@
#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS)
#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1)
+#define TTBR_CNP_BIT (UL(1) << 0)
+
/*
* TCR flags.
*/
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 1bdeca8918a6..50b1ef8584c0 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -360,6 +360,7 @@ static inline int pmd_protnone(pmd_t pmd)
#define pmd_present(pmd) pte_present(pmd_pte(pmd))
#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
#define pmd_young(pmd) pte_young(pmd_pte(pmd))
+#define pmd_valid(pmd) pte_valid(pmd_pte(pmd))
#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
@@ -428,10 +429,33 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
PUD_TYPE_TABLE)
#endif
+extern pgd_t init_pg_dir[PTRS_PER_PGD];
+extern pgd_t init_pg_end[];
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
+extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
+
+extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd);
+
+static inline bool in_swapper_pgdir(void *addr)
+{
+ return ((unsigned long)addr & PAGE_MASK) ==
+ ((unsigned long)swapper_pg_dir & PAGE_MASK);
+}
+
static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
{
+#ifdef __PAGETABLE_PMD_FOLDED
+ if (in_swapper_pgdir(pmdp)) {
+ set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd)));
+ return;
+ }
+#endif /* __PAGETABLE_PMD_FOLDED */
+
WRITE_ONCE(*pmdp, pmd);
- dsb(ishst);
+
+ if (pmd_valid(pmd))
+ dsb(ishst);
}
static inline void pmd_clear(pmd_t *pmdp)
@@ -477,11 +501,21 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
#define pud_none(pud) (!pud_val(pud))
#define pud_bad(pud) (!(pud_val(pud) & PUD_TABLE_BIT))
#define pud_present(pud) pte_present(pud_pte(pud))
+#define pud_valid(pud) pte_valid(pud_pte(pud))
static inline void set_pud(pud_t *pudp, pud_t pud)
{
+#ifdef __PAGETABLE_PUD_FOLDED
+ if (in_swapper_pgdir(pudp)) {
+ set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud)));
+ return;
+ }
+#endif /* __PAGETABLE_PUD_FOLDED */
+
WRITE_ONCE(*pudp, pud);
- dsb(ishst);
+
+ if (pud_valid(pud))
+ dsb(ishst);
}
static inline void pud_clear(pud_t *pudp)
@@ -532,6 +566,11 @@ static inline phys_addr_t pud_page_paddr(pud_t pud)
static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+ if (in_swapper_pgdir(pgdp)) {
+ set_swapper_pgd(pgdp, pgd);
+ return;
+ }
+
WRITE_ONCE(*pgdp, pgd);
dsb(ishst);
}
@@ -712,11 +751,6 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
}
#endif
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-extern pgd_t swapper_pg_end[];
-extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
-extern pgd_t tramp_pg_dir[PTRS_PER_PGD];
-
/*
* Encode and decode a swap entry:
* bits 0-1: present (must be zero)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 79657ad91397..2bf6691371c2 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -174,6 +174,10 @@ static inline void start_thread(struct pt_regs *regs, unsigned long pc,
{
start_thread_common(regs, pc);
regs->pstate = PSR_MODE_EL0t;
+
+ if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+ regs->pstate |= PSR_SSBS_BIT;
+
regs->sp = sp;
}
@@ -190,6 +194,9 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
regs->pstate |= PSR_AA32_E_BIT;
#endif
+ if (arm64_get_ssbd_state() != ARM64_SSBD_FORCE_ENABLE)
+ regs->pstate |= PSR_AA32_SSBS_BIT;
+
regs->compat_sp = sp;
}
#endif
@@ -244,10 +251,6 @@ static inline void spin_lock_prefetch(const void *ptr)
#endif
-void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused);
-void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused);
-void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused);
-
extern unsigned long __ro_after_init signal_minsigstksz; /* sigframe size */
extern void __init minsigstksz_setup(void);
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 177b851ca6d9..fce22c4b2f73 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -25,6 +25,9 @@
#define CurrentEL_EL1 (1 << 2)
#define CurrentEL_EL2 (2 << 2)
+/* Additional SPSR bits not exposed in the UABI */
+#define PSR_IL_BIT (1 << 20)
+
/* AArch32-specific ptrace requests */
#define COMPAT_PTRACE_GETREGS 12
#define COMPAT_PTRACE_SETREGS 13
@@ -50,6 +53,7 @@
#define PSR_AA32_I_BIT 0x00000080
#define PSR_AA32_A_BIT 0x00000100
#define PSR_AA32_E_BIT 0x00000200
+#define PSR_AA32_SSBS_BIT 0x00800000
#define PSR_AA32_DIT_BIT 0x01000000
#define PSR_AA32_Q_BIT 0x08000000
#define PSR_AA32_V_BIT 0x10000000
diff --git a/arch/arm64/include/asm/stage2_pgtable-nopmd.h b/arch/arm64/include/asm/stage2_pgtable-nopmd.h
deleted file mode 100644
index 2656a0fd05a6..000000000000
--- a/arch/arm64/include/asm/stage2_pgtable-nopmd.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_S2_PGTABLE_NOPMD_H_
-#define __ARM64_S2_PGTABLE_NOPMD_H_
-
-#include <asm/stage2_pgtable-nopud.h>
-
-#define __S2_PGTABLE_PMD_FOLDED
-
-#define S2_PMD_SHIFT S2_PUD_SHIFT
-#define S2_PTRS_PER_PMD 1
-#define S2_PMD_SIZE (1UL << S2_PMD_SHIFT)
-#define S2_PMD_MASK (~(S2_PMD_SIZE-1))
-
-#define stage2_pud_none(pud) (0)
-#define stage2_pud_present(pud) (1)
-#define stage2_pud_clear(pud) do { } while (0)
-#define stage2_pud_populate(pud, pmd) do { } while (0)
-#define stage2_pmd_offset(pud, address) ((pmd_t *)(pud))
-
-#define stage2_pmd_free(pmd) do { } while (0)
-
-#define stage2_pmd_addr_end(addr, end) (end)
-
-#define stage2_pud_huge(pud) (0)
-#define stage2_pmd_table_empty(pmdp) (0)
-
-#endif
diff --git a/arch/arm64/include/asm/stage2_pgtable-nopud.h b/arch/arm64/include/asm/stage2_pgtable-nopud.h
deleted file mode 100644
index 5ee87b54ebf3..000000000000
--- a/arch/arm64/include/asm/stage2_pgtable-nopud.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef __ARM64_S2_PGTABLE_NOPUD_H_
-#define __ARM64_S2_PGTABLE_NOPUD_H_
-
-#define __S2_PGTABLE_PUD_FOLDED
-
-#define S2_PUD_SHIFT S2_PGDIR_SHIFT
-#define S2_PTRS_PER_PUD 1
-#define S2_PUD_SIZE (_AC(1, UL) << S2_PUD_SHIFT)
-#define S2_PUD_MASK (~(S2_PUD_SIZE-1))
-
-#define stage2_pgd_none(pgd) (0)
-#define stage2_pgd_present(pgd) (1)
-#define stage2_pgd_clear(pgd) do { } while (0)
-#define stage2_pgd_populate(pgd, pud) do { } while (0)
-
-#define stage2_pud_offset(pgd, address) ((pud_t *)(pgd))
-
-#define stage2_pud_free(x) do { } while (0)
-
-#define stage2_pud_addr_end(addr, end) (end)
-#define stage2_pud_table_empty(pmdp) (0)
-
-#endif
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 8b68099348e5..d352f6df8d2c 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -19,9 +19,17 @@
#ifndef __ARM64_S2_PGTABLE_H_
#define __ARM64_S2_PGTABLE_H_
+#include <linux/hugetlb.h>
#include <asm/pgtable.h>
/*
+ * PGDIR_SHIFT determines the size a top-level page table entry can map
+ * and depends on the number of levels in the page table. Compute the
+ * PGDIR_SHIFT for a given number of levels.
+ */
+#define pt_levels_pgdir_shift(lvls) ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - (lvls))
+
+/*
* The hardware supports concatenation of up to 16 tables at stage2 entry level
* and we use the feature whenever possible.
*
@@ -29,112 +37,208 @@
* On arm64, the smallest PAGE_SIZE supported is 4k, which means
* (PAGE_SHIFT - 3) > 4 holds for all page sizes.
* This implies, the total number of page table levels at stage2 expected
- * by the hardware is actually the number of levels required for (KVM_PHYS_SHIFT - 4)
+ * by the hardware is actually the number of levels required for (IPA_SHIFT - 4)
* in normal translations(e.g, stage1), since we cannot have another level in
- * the range (KVM_PHYS_SHIFT, KVM_PHYS_SHIFT - 4).
+ * the range (IPA_SHIFT, IPA_SHIFT - 4).
*/
-#define STAGE2_PGTABLE_LEVELS ARM64_HW_PGTABLE_LEVELS(KVM_PHYS_SHIFT - 4)
+#define stage2_pgtable_levels(ipa) ARM64_HW_PGTABLE_LEVELS((ipa) - 4)
+#define kvm_stage2_levels(kvm) VTCR_EL2_LVLS(kvm->arch.vtcr)
-/*
- * With all the supported VA_BITs and 40bit guest IPA, the following condition
- * is always true:
- *
- * STAGE2_PGTABLE_LEVELS <= CONFIG_PGTABLE_LEVELS
- *
- * We base our stage-2 page table walker helpers on this assumption and
- * fall back to using the host version of the helper wherever possible.
- * i.e, if a particular level is not folded (e.g, PUD) at stage2, we fall back
- * to using the host version, since it is guaranteed it is not folded at host.
- *
- * If the condition breaks in the future, we can rearrange the host level
- * definitions and reuse them for stage2. Till then...
- */
-#if STAGE2_PGTABLE_LEVELS > CONFIG_PGTABLE_LEVELS
-#error "Unsupported combination of guest IPA and host VA_BITS."
-#endif
-
-/* S2_PGDIR_SHIFT is the size mapped by top-level stage2 entry */
-#define S2_PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - STAGE2_PGTABLE_LEVELS)
-#define S2_PGDIR_SIZE (_AC(1, UL) << S2_PGDIR_SHIFT)
-#define S2_PGDIR_MASK (~(S2_PGDIR_SIZE - 1))
+/* stage2_pgdir_shift() is the size mapped by top-level stage2 entry for the VM */
+#define stage2_pgdir_shift(kvm) pt_levels_pgdir_shift(kvm_stage2_levels(kvm))
+#define stage2_pgdir_size(kvm) (1ULL << stage2_pgdir_shift(kvm))
+#define stage2_pgdir_mask(kvm) ~(stage2_pgdir_size(kvm) - 1)
/*
* The number of PTRS across all concatenated stage2 tables given by the
* number of bits resolved at the initial level.
+ * If we force more levels than necessary, we may have (stage2_pgdir_shift > IPA),
+ * in which case, stage2_pgd_ptrs will have one entry.
*/
-#define PTRS_PER_S2_PGD (1 << (KVM_PHYS_SHIFT - S2_PGDIR_SHIFT))
+#define pgd_ptrs_shift(ipa, pgdir_shift) \
+ ((ipa) > (pgdir_shift) ? ((ipa) - (pgdir_shift)) : 0)
+#define __s2_pgd_ptrs(ipa, lvls) \
+ (1 << (pgd_ptrs_shift((ipa), pt_levels_pgdir_shift(lvls))))
+#define __s2_pgd_size(ipa, lvls) (__s2_pgd_ptrs((ipa), (lvls)) * sizeof(pgd_t))
+
+#define stage2_pgd_ptrs(kvm) __s2_pgd_ptrs(kvm_phys_shift(kvm), kvm_stage2_levels(kvm))
+#define stage2_pgd_size(kvm) __s2_pgd_size(kvm_phys_shift(kvm), kvm_stage2_levels(kvm))
/*
- * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
- * levels in addition to the PGD.
+ * kvm_mmmu_cache_min_pages() is the number of pages required to install
+ * a stage-2 translation. We pre-allocate the entry level page table at
+ * the VM creation.
*/
-#define KVM_MMU_CACHE_MIN_PAGES (STAGE2_PGTABLE_LEVELS - 1)
+#define kvm_mmu_cache_min_pages(kvm) (kvm_stage2_levels(kvm) - 1)
-
-#if STAGE2_PGTABLE_LEVELS > 3
+/* Stage2 PUD definitions when the level is present */
+static inline bool kvm_stage2_has_pud(struct kvm *kvm)
+{
+ return (CONFIG_PGTABLE_LEVELS > 3) && (kvm_stage2_levels(kvm) > 3);
+}
#define S2_PUD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
-#define S2_PUD_SIZE (_AC(1, UL) << S2_PUD_SHIFT)
+#define S2_PUD_SIZE (1UL << S2_PUD_SHIFT)
#define S2_PUD_MASK (~(S2_PUD_SIZE - 1))
-#define stage2_pgd_none(pgd) pgd_none(pgd)
-#define stage2_pgd_clear(pgd) pgd_clear(pgd)
-#define stage2_pgd_present(pgd) pgd_present(pgd)
-#define stage2_pgd_populate(pgd, pud) pgd_populate(NULL, pgd, pud)
-#define stage2_pud_offset(pgd, address) pud_offset(pgd, address)
-#define stage2_pud_free(pud) pud_free(NULL, pud)
+static inline bool stage2_pgd_none(struct kvm *kvm, pgd_t pgd)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return pgd_none(pgd);
+ else
+ return 0;
+}
-#define stage2_pud_table_empty(pudp) kvm_page_empty(pudp)
+static inline void stage2_pgd_clear(struct kvm *kvm, pgd_t *pgdp)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pgd_clear(pgdp);
+}
-static inline phys_addr_t stage2_pud_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline bool stage2_pgd_present(struct kvm *kvm, pgd_t pgd)
{
- phys_addr_t boundary = (addr + S2_PUD_SIZE) & S2_PUD_MASK;
+ if (kvm_stage2_has_pud(kvm))
+ return pgd_present(pgd);
+ else
+ return 1;
+}
- return (boundary - 1 < end - 1) ? boundary : end;
+static inline void stage2_pgd_populate(struct kvm *kvm, pgd_t *pgd, pud_t *pud)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pgd_populate(NULL, pgd, pud);
+}
+
+static inline pud_t *stage2_pud_offset(struct kvm *kvm,
+ pgd_t *pgd, unsigned long address)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return pud_offset(pgd, address);
+ else
+ return (pud_t *)pgd;
}
-#endif /* STAGE2_PGTABLE_LEVELS > 3 */
+static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
+{
+ if (kvm_stage2_has_pud(kvm))
+ pud_free(NULL, pud);
+}
+static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
+{
+ if (kvm_stage2_has_pud(kvm))
+ return kvm_page_empty(pudp);
+ else
+ return false;
+}
-#if STAGE2_PGTABLE_LEVELS > 2
+static inline phys_addr_t
+stage2_pud_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+ if (kvm_stage2_has_pud(kvm)) {
+ phys_addr_t boundary = (addr + S2_PUD_SIZE) & S2_PUD_MASK;
+
+ return (boundary - 1 < end - 1) ? boundary : end;
+ } else {
+ return end;
+ }
+}
+
+/* Stage2 PMD definitions when the level is present */
+static inline bool kvm_stage2_has_pmd(struct kvm *kvm)
+{
+ return (CONFIG_PGTABLE_LEVELS > 2) && (kvm_stage2_levels(kvm) > 2);
+}
#define S2_PMD_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
-#define S2_PMD_SIZE (_AC(1, UL) << S2_PMD_SHIFT)
+#define S2_PMD_SIZE (1UL << S2_PMD_SHIFT)
#define S2_PMD_MASK (~(S2_PMD_SIZE - 1))
-#define stage2_pud_none(pud) pud_none(pud)
-#define stage2_pud_clear(pud) pud_clear(pud)
-#define stage2_pud_present(pud) pud_present(pud)
-#define stage2_pud_populate(pud, pmd) pud_populate(NULL, pud, pmd)
-#define stage2_pmd_offset(pud, address) pmd_offset(pud, address)
-#define stage2_pmd_free(pmd) pmd_free(NULL, pmd)
+static inline bool stage2_pud_none(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_none(pud);
+ else
+ return 0;
+}
+
+static inline void stage2_pud_clear(struct kvm *kvm, pud_t *pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ pud_clear(pud);
+}
-#define stage2_pud_huge(pud) pud_huge(pud)
-#define stage2_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+static inline bool stage2_pud_present(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_present(pud);
+ else
+ return 1;
+}
-static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline void stage2_pud_populate(struct kvm *kvm, pud_t *pud, pmd_t *pmd)
{
- phys_addr_t boundary = (addr + S2_PMD_SIZE) & S2_PMD_MASK;
+ if (kvm_stage2_has_pmd(kvm))
+ pud_populate(NULL, pud, pmd);
+}
- return (boundary - 1 < end - 1) ? boundary : end;
+static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
+ pud_t *pud, unsigned long address)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pmd_offset(pud, address);
+ else
+ return (pmd_t *)pud;
}
-#endif /* STAGE2_PGTABLE_LEVELS > 2 */
+static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ pmd_free(NULL, pmd);
+}
+
+static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return pud_huge(pud);
+ else
+ return 0;
+}
+
+static inline bool stage2_pmd_table_empty(struct kvm *kvm, pmd_t *pmdp)
+{
+ if (kvm_stage2_has_pmd(kvm))
+ return kvm_page_empty(pmdp);
+ else
+ return 0;
+}
-#define stage2_pte_table_empty(ptep) kvm_page_empty(ptep)
+static inline phys_addr_t
+stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
+{
+ if (kvm_stage2_has_pmd(kvm)) {
+ phys_addr_t boundary = (addr + S2_PMD_SIZE) & S2_PMD_MASK;
-#if STAGE2_PGTABLE_LEVELS == 2
-#include <asm/stage2_pgtable-nopmd.h>
-#elif STAGE2_PGTABLE_LEVELS == 3
-#include <asm/stage2_pgtable-nopud.h>
-#endif
+ return (boundary - 1 < end - 1) ? boundary : end;
+ } else {
+ return end;
+ }
+}
+static inline bool stage2_pte_table_empty(struct kvm *kvm, pte_t *ptep)
+{
+ return kvm_page_empty(ptep);
+}
-#define stage2_pgd_index(addr) (((addr) >> S2_PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+static inline unsigned long stage2_pgd_index(struct kvm *kvm, phys_addr_t addr)
+{
+ return (((addr) >> stage2_pgdir_shift(kvm)) & (stage2_pgd_ptrs(kvm) - 1));
+}
-static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
{
- phys_addr_t boundary = (addr + S2_PGDIR_SIZE) & S2_PGDIR_MASK;
+ phys_addr_t boundary = (addr + stage2_pgdir_size(kvm)) & stage2_pgdir_mask(kvm);
return (boundary - 1 < end - 1) ? boundary : end;
}
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
index eab738019707..397c6ccd04e7 100644
--- a/arch/arm64/include/asm/stat.h
+++ b/arch/arm64/include/asm/stat.h
@@ -20,7 +20,7 @@
#ifdef CONFIG_COMPAT
-#include <linux/compat_time.h>
+#include <linux/time.h>
#include <asm/compat.h>
/*
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index dd95d33a5bd5..03a6c256b7ec 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -16,6 +16,7 @@
#ifndef __ASM_STRING_H
#define __ASM_STRING_H
+#ifndef CONFIG_KASAN
#define __HAVE_ARCH_STRRCHR
extern char *strrchr(const char *, int c);
@@ -34,6 +35,13 @@ extern __kernel_size_t strlen(const char *);
#define __HAVE_ARCH_STRNLEN
extern __kernel_size_t strnlen(const char *, __kernel_size_t);
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, size_t);
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void *, int, __kernel_size_t);
+#endif
+
#define __HAVE_ARCH_MEMCPY
extern void *memcpy(void *, const void *, __kernel_size_t);
extern void *__memcpy(void *, const void *, __kernel_size_t);
@@ -42,16 +50,10 @@ extern void *__memcpy(void *, const void *, __kernel_size_t);
extern void *memmove(void *, const void *, __kernel_size_t);
extern void *__memmove(void *, const void *, __kernel_size_t);
-#define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void *, int, __kernel_size_t);
-
#define __HAVE_ARCH_MEMSET
extern void *memset(void *, int, __kernel_size_t);
extern void *__memset(void *, int, __kernel_size_t);
-#define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *, const void *, size_t);
-
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
#define __HAVE_ARCH_MEMCPY_FLUSHCACHE
void memcpy_flushcache(void *dst, const void *src, size_t cnt);
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index c1470931b897..0c909c4a932f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -20,7 +20,6 @@
#ifndef __ASM_SYSREG_H
#define __ASM_SYSREG_H
-#include <asm/compiler.h>
#include <linux/stringify.h>
/*
@@ -84,13 +83,26 @@
#endif /* CONFIG_BROKEN_GAS_INST */
-#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
-#define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3)
+/*
+ * Instructions for modifying PSTATE fields.
+ * As per Arm ARM for v8-A, Section "C.5.1.3 op0 == 0b00, architectural hints,
+ * barriers and CLREX, and PSTATE access", ARM DDI 0487 C.a, system instructions
+ * for accessing PSTATE fields have the following encoding:
+ * Op0 = 0, CRn = 4
+ * Op1, Op2 encodes the PSTATE field modified and defines the constraints.
+ * CRm = Imm4 for the instruction.
+ * Rt = 0x1f
+ */
+#define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift)
+#define PSTATE_Imm_shift CRm_shift
+
+#define PSTATE_PAN pstate_field(0, 4)
+#define PSTATE_UAO pstate_field(0, 3)
+#define PSTATE_SSBS pstate_field(3, 1)
-#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM | \
- (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM | \
- (!!x)<<8 | 0x1f)
+#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2)
#define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2)
@@ -419,6 +431,7 @@
#define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7)
/* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_DSSBS (1UL << 44)
#define SCTLR_ELx_EE (1 << 25)
#define SCTLR_ELx_IESB (1 << 21)
#define SCTLR_ELx_WXN (1 << 19)
@@ -439,7 +452,7 @@
(1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
(1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
(1 << 27) | (1 << 30) | (1 << 31) | \
- (0xffffffffUL << 32))
+ (0xffffefffUL << 32))
#ifdef CONFIG_CPU_BIG_ENDIAN
#define ENDIAN_SET_EL2 SCTLR_ELx_EE
@@ -453,7 +466,7 @@
#define SCTLR_EL2_SET (SCTLR_ELx_IESB | ENDIAN_SET_EL2 | SCTLR_EL2_RES1)
#define SCTLR_EL2_CLEAR (SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
SCTLR_ELx_SA | SCTLR_ELx_I | SCTLR_ELx_WXN | \
- ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
+ SCTLR_ELx_DSSBS | ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff
#error "Inconsistent SCTLR_EL2 set/clear bits"
@@ -477,7 +490,7 @@
(1 << 29))
#define SCTLR_EL1_RES0 ((1 << 6) | (1 << 10) | (1 << 13) | (1 << 17) | \
(1 << 27) | (1 << 30) | (1 << 31) | \
- (0xffffffffUL << 32))
+ (0xffffefffUL << 32))
#ifdef CONFIG_CPU_BIG_ENDIAN
#define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE)
@@ -489,12 +502,12 @@
#define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\
SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I |\
- SCTLR_EL1_DZE | SCTLR_EL1_UCT | SCTLR_EL1_NTWI |\
+ SCTLR_EL1_DZE | SCTLR_EL1_UCT |\
SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\
ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1)
#define SCTLR_EL1_CLEAR (SCTLR_ELx_A | SCTLR_EL1_CP15BEN | SCTLR_EL1_ITD |\
SCTLR_EL1_UMA | SCTLR_ELx_WXN | ENDIAN_CLEAR_EL1 |\
- SCTLR_EL1_RES0)
+ SCTLR_ELx_DSSBS | SCTLR_EL1_NTWI | SCTLR_EL1_RES0)
#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff
#error "Inconsistent SCTLR_EL1 set/clear bits"
@@ -544,6 +557,13 @@
#define ID_AA64PFR0_EL0_64BIT_ONLY 0x1
#define ID_AA64PFR0_EL0_32BIT_64BIT 0x2
+/* id_aa64pfr1 */
+#define ID_AA64PFR1_SSBS_SHIFT 4
+
+#define ID_AA64PFR1_SSBS_PSTATE_NI 0
+#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1
+#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2
+
/* id_aa64mmfr0 */
#define ID_AA64MMFR0_TGRAN4_SHIFT 28
#define ID_AA64MMFR0_TGRAN64_SHIFT 24
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 28893a0b141d..0e2a0ecaf484 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -33,7 +33,8 @@ void die(const char *msg, struct pt_regs *regs, int err);
struct siginfo;
void arm64_notify_die(const char *str, struct pt_regs *regs,
- struct siginfo *info, int err);
+ int signo, int sicode, void __user *addr,
+ int err);
void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
struct pt_regs *),
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index a3233167be60..106fdc951b6e 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -22,16 +22,10 @@
#include <linux/pagemap.h>
#include <linux/swap.h>
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-
-#define tlb_remove_entry(tlb, entry) tlb_remove_table(tlb, entry)
static inline void __tlb_remove_table(void *_table)
{
free_page_and_swap_cache((struct page *)_table);
}
-#else
-#define tlb_remove_entry(tlb, entry) tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
static void tlb_flush(struct mmu_gather *tlb);
@@ -40,36 +34,35 @@ static void tlb_flush(struct mmu_gather *tlb);
static inline void tlb_flush(struct mmu_gather *tlb)
{
struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
+ bool last_level = !tlb->freed_tables;
+ unsigned long stride = tlb_get_unmap_size(tlb);
/*
- * The ASID allocator will either invalidate the ASID or mark
- * it as used.
+ * If we're tearing down the address space then we only care about
+ * invalidating the walk-cache, since the ASID allocator won't
+ * reallocate our ASID without invalidating the entire TLB.
*/
- if (tlb->fullmm)
+ if (tlb->fullmm) {
+ if (!last_level)
+ flush_tlb_mm(tlb->mm);
return;
+ }
- /*
- * The intermediate page table levels are already handled by
- * the __(pte|pmd|pud)_free_tlb() functions, so last level
- * TLBI is sufficient here.
- */
- __flush_tlb_range(&vma, tlb->start, tlb->end, true);
+ __flush_tlb_range(&vma, tlb->start, tlb->end, stride, last_level);
}
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
pgtable_page_dtor(pte);
- tlb_remove_entry(tlb, pte);
+ tlb_remove_table(tlb, pte);
}
#if CONFIG_PGTABLE_LEVELS > 2
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
- tlb_remove_entry(tlb, virt_to_page(pmdp));
+ tlb_remove_table(tlb, virt_to_page(pmdp));
}
#endif
@@ -77,8 +70,7 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp,
unsigned long addr)
{
- __flush_tlb_pgtable(tlb->mm, addr);
- tlb_remove_entry(tlb, virt_to_page(pudp));
+ tlb_remove_table(tlb, virt_to_page(pudp));
}
#endif
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index a4a1901140ee..c3c0387aee18 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -70,43 +70,73 @@
})
/*
- * TLB Management
- * ==============
+ * TLB Invalidation
+ * ================
*
- * The TLB specific code is expected to perform whatever tests it needs
- * to determine if it should invalidate the TLB for each call. Start
- * addresses are inclusive and end addresses are exclusive; it is safe to
- * round these addresses down.
+ * This header file implements the low-level TLB invalidation routines
+ * (sometimes referred to as "flushing" in the kernel) for arm64.
*
- * flush_tlb_all()
+ * Every invalidation operation uses the following template:
+ *
+ * DSB ISHST // Ensure prior page-table updates have completed
+ * TLBI ... // Invalidate the TLB
+ * DSB ISH // Ensure the TLB invalidation has completed
+ * if (invalidated kernel mappings)
+ * ISB // Discard any instructions fetched from the old mapping
+ *
+ *
+ * The following functions form part of the "core" TLB invalidation API,
+ * as documented in Documentation/core-api/cachetlb.rst:
*
- * Invalidate the entire TLB.
+ * flush_tlb_all()
+ * Invalidate the entire TLB (kernel + user) on all CPUs
*
* flush_tlb_mm(mm)
+ * Invalidate an entire user address space on all CPUs.
+ * The 'mm' argument identifies the ASID to invalidate.
+ *
+ * flush_tlb_range(vma, start, end)
+ * Invalidate the virtual-address range '[start, end)' on all
+ * CPUs for the user address space corresponding to 'vma->mm'.
+ * Note that this operation also invalidates any walk-cache
+ * entries associated with translations for the specified address
+ * range.
+ *
+ * flush_tlb_kernel_range(start, end)
+ * Same as flush_tlb_range(..., start, end), but applies to
+ * kernel mappings rather than a particular user address space.
+ * Whilst not explicitly documented, this function is used when
+ * unmapping pages from vmalloc/io space.
+ *
+ * flush_tlb_page(vma, addr)
+ * Invalidate a single user mapping for address 'addr' in the
+ * address space corresponding to 'vma->mm'. Note that this
+ * operation only invalidates a single, last-level page-table
+ * entry and therefore does not affect any walk-caches.
*
- * Invalidate all TLB entries in a particular address space.
- * - mm - mm_struct describing address space
*
- * flush_tlb_range(mm,start,end)
+ * Next, we have some undocumented invalidation routines that you probably
+ * don't want to call unless you know what you're doing:
*
- * Invalidate a range of TLB entries in the specified address
- * space.
- * - mm - mm_struct describing address space
- * - start - start address (may not be aligned)
- * - end - end address (exclusive, may not be aligned)
+ * local_flush_tlb_all()
+ * Same as flush_tlb_all(), but only applies to the calling CPU.
*
- * flush_tlb_page(vaddr,vma)
+ * __flush_tlb_kernel_pgtable(addr)
+ * Invalidate a single kernel mapping for address 'addr' on all
+ * CPUs, ensuring that any walk-cache entries associated with the
+ * translation are also invalidated.
*
- * Invalidate the specified page in the specified address range.
- * - vaddr - virtual address (may not be aligned)
- * - vma - vma_struct describing address range
+ * __flush_tlb_range(vma, start, end, stride, last_level)
+ * Invalidate the virtual-address range '[start, end)' on all
+ * CPUs for the user address space corresponding to 'vma->mm'.
+ * The invalidation operations are issued at a granularity
+ * determined by 'stride' and only affect any walk-cache entries
+ * if 'last_level' is equal to false.
*
- * flush_kern_tlb_page(kaddr)
*
- * Invalidate the TLB entry for the specified page. The address
- * will be in the kernels virtual memory space. Current uses
- * only require the D-TLB to be invalidated.
- * - kaddr - Kernel virtual memory address
+ * Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
+ * on top of these routines, since that is our interface to the mmu_gather
+ * API as used by munmap() and friends.
*/
static inline void local_flush_tlb_all(void)
{
@@ -149,25 +179,28 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
* This is meant to avoid soft lock-ups on large TLB flushing ranges and not
* necessarily a performance improvement.
*/
-#define MAX_TLB_RANGE (1024UL << PAGE_SHIFT)
+#define MAX_TLBI_OPS 1024UL
static inline void __flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end,
- bool last_level)
+ unsigned long stride, bool last_level)
{
unsigned long asid = ASID(vma->vm_mm);
unsigned long addr;
- if ((end - start) > MAX_TLB_RANGE) {
+ if ((end - start) > (MAX_TLBI_OPS * stride)) {
flush_tlb_mm(vma->vm_mm);
return;
}
+ /* Convert the stride into units of 4k */
+ stride >>= 12;
+
start = __TLBI_VADDR(start, asid);
end = __TLBI_VADDR(end, asid);
dsb(ishst);
- for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
+ for (addr = start; addr < end; addr += stride) {
if (last_level) {
__tlbi(vale1is, addr);
__tlbi_user(vale1is, addr);
@@ -182,14 +215,18 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
- __flush_tlb_range(vma, start, end, false);
+ /*
+ * We cannot use leaf-only invalidation here, since we may be invalidating
+ * table entries as part of collapsing hugepages or moving page tables.
+ */
+ __flush_tlb_range(vma, start, end, PAGE_SIZE, false);
}
static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
unsigned long addr;
- if ((end - start) > MAX_TLB_RANGE) {
+ if ((end - start) > (MAX_TLBI_OPS * PAGE_SIZE)) {
flush_tlb_all();
return;
}
@@ -199,7 +236,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
dsb(ishst);
for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
- __tlbi(vaae1is, addr);
+ __tlbi(vaale1is, addr);
dsb(ish);
isb();
}
@@ -208,20 +245,11 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
* Used to invalidate the TLB (walk caches) corresponding to intermediate page
* table levels (pgd/pud/pmd).
*/
-static inline void __flush_tlb_pgtable(struct mm_struct *mm,
- unsigned long uaddr)
-{
- unsigned long addr = __TLBI_VADDR(uaddr, ASID(mm));
-
- __tlbi(vae1is, addr);
- __tlbi_user(vae1is, addr);
- dsb(ish);
-}
-
static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
{
unsigned long addr = __TLBI_VADDR(kaddr, 0);
+ dsb(ishst);
__tlbi(vaae1is, addr);
dsb(ish);
}
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 49a0fee4f89b..0524f2438649 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -45,6 +45,9 @@ int pcibus_to_node(struct pci_bus *bus);
/* Replace task scheduler's default cpu-invariant accounting */
#define arch_scale_cpu_capacity topology_get_cpu_scale
+/* Enable topology flag updates */
+#define arch_update_cpu_topology topology_update_cpu_topology
+
#include <asm-generic/topology.h>
#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index c320f3bf6c57..f9c1aa6167d2 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -37,8 +37,9 @@ void register_undef_hook(struct undef_hook *hook);
void unregister_undef_hook(struct undef_hook *hook);
void force_signal_inject(int signal, int code, unsigned long address);
void arm64_notify_segfault(unsigned long addr);
-void arm64_force_sig_info(struct siginfo *info, const char *str,
- struct task_struct *tsk);
+void arm64_force_sig_fault(int signo, int code, void __user *addr, const char *str);
+void arm64_force_sig_mceerr(int code, void __user *addr, short lsb, const char *str);
+void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr, const char *str);
/*
* Move regs->pc to next instruction and do necessary setup before it
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index e66b0fca99c2..07c34087bd5e 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -32,7 +32,6 @@
#include <asm/cpufeature.h>
#include <asm/ptrace.h>
#include <asm/memory.h>
-#include <asm/compiler.h>
#include <asm/extable.h>
#define get_ds() (KERNEL_DS)
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e0d0f5b856e7..b13ca091f833 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -18,11 +18,11 @@
#define __ARCH_WANT_SYS_GETHOSTNAME
#define __ARCH_WANT_SYS_PAUSE
#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
#define __ARCH_WANT_SYS_NICE
#define __ARCH_WANT_SYS_SIGPENDING
#define __ARCH_WANT_SYS_SIGPROCMASK
#define __ARCH_WANT_COMPAT_SYS_SENDFILE
+#define __ARCH_WANT_SYS_UTIME32
#define __ARCH_WANT_SYS_FORK
#define __ARCH_WANT_SYS_VFORK
diff --git a/arch/arm64/include/asm/xen/events.h b/arch/arm64/include/asm/xen/events.h
index 4e22b7a8c038..2788e95d0ff0 100644
--- a/arch/arm64/include/asm/xen/events.h
+++ b/arch/arm64/include/asm/xen/events.h
@@ -14,7 +14,7 @@ enum ipi_vector {
static inline int xen_irqs_disabled(struct pt_regs *regs)
{
- return raw_irqs_disabled_flags((unsigned long) regs->pstate);
+ return !interrupts_enabled(regs);
}
#define xchg_xen_ulong(ptr, val) xchg((ptr), (val))
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index 198afbf0688f..6c5adf458690 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -19,3 +19,4 @@ generic-y += swab.h
generic-y += termbits.h
generic-y += termios.h
generic-y += types.h
+generic-y += siginfo.h
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 17c65c8f33cb..2bcd6e4f3474 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -48,5 +48,6 @@
#define HWCAP_USCAT (1 << 25)
#define HWCAP_ILRCPC (1 << 26)
#define HWCAP_FLAGM (1 << 27)
+#define HWCAP_SSBS (1 << 28)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h
index 98c4ce55d9c3..a36227fdb084 100644
--- a/arch/arm64/include/uapi/asm/ptrace.h
+++ b/arch/arm64/include/uapi/asm/ptrace.h
@@ -46,6 +46,7 @@
#define PSR_I_BIT 0x00000080
#define PSR_A_BIT 0x00000100
#define PSR_D_BIT 0x00000200
+#define PSR_SSBS_BIT 0x00001000
#define PSR_PAN_BIT 0x00400000
#define PSR_UAO_BIT 0x00800000
#define PSR_V_BIT 0x10000000
diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h
deleted file mode 100644
index 574d12f86039..000000000000
--- a/arch/arm64/include/uapi/asm/siginfo.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_SIGINFO_H
-#define __ASM_SIGINFO_H
-
-#define __ARCH_SI_PREAMBLE_SIZE (4 * sizeof(int))
-
-#include <asm-generic/siginfo.h>
-
-#endif
diff --git a/arch/arm64/include/uapi/asm/unistd.h b/arch/arm64/include/uapi/asm/unistd.h
index 5072cbd15c82..dae1584cf017 100644
--- a/arch/arm64/include/uapi/asm/unistd.h
+++ b/arch/arm64/include/uapi/asm/unistd.h
@@ -16,5 +16,6 @@
*/
#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_NEW_STAT
#include <asm-generic/unistd.h>
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 95ac7374d723..4c8b13bede80 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \
arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
+arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o
arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o
arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index d894a20b70b2..72f63a59b008 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -44,20 +44,23 @@ EXPORT_SYMBOL(__arch_copy_in_user);
EXPORT_SYMBOL(memstart_addr);
/* string / mem functions */
+#ifndef CONFIG_KASAN
EXPORT_SYMBOL(strchr);
EXPORT_SYMBOL(strrchr);
EXPORT_SYMBOL(strcmp);
EXPORT_SYMBOL(strncmp);
EXPORT_SYMBOL(strlen);
EXPORT_SYMBOL(strnlen);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(memchr);
+#endif
+
EXPORT_SYMBOL(memset);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(__memset);
EXPORT_SYMBOL(__memcpy);
EXPORT_SYMBOL(__memmove);
-EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(memcmp);
/* atomic bitops */
EXPORT_SYMBOL(set_bit);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index dec10898d688..a509e35132d2 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -68,21 +68,43 @@ static bool
has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
int scope)
{
- u64 mask = CTR_CACHE_MINLINE_MASK;
-
- /* Skip matching the min line sizes for cache type check */
- if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE)
- mask ^= arm64_ftr_reg_ctrel0.strict_mask;
+ u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+ u64 sys = arm64_ftr_reg_ctrel0.sys_val & mask;
+ u64 ctr_raw, ctr_real;
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
- return (read_cpuid_cachetype() & mask) !=
- (arm64_ftr_reg_ctrel0.sys_val & mask);
+
+ /*
+ * We want to make sure that all the CPUs in the system expose
+ * a consistent CTR_EL0 to make sure that applications behaves
+ * correctly with migration.
+ *
+ * If a CPU has CTR_EL0.IDC but does not advertise it via CTR_EL0 :
+ *
+ * 1) It is safe if the system doesn't support IDC, as CPU anyway
+ * reports IDC = 0, consistent with the rest.
+ *
+ * 2) If the system has IDC, it is still safe as we trap CTR_EL0
+ * access on this CPU via the ARM64_HAS_CACHE_IDC capability.
+ *
+ * So, we need to make sure either the raw CTR_EL0 or the effective
+ * CTR_EL0 matches the system's copy to allow a secondary CPU to boot.
+ */
+ ctr_raw = read_cpuid_cachetype() & mask;
+ ctr_real = read_cpuid_effective_cachetype() & mask;
+
+ return (ctr_real != sys) && (ctr_raw != sys);
}
static void
cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
{
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
+ u64 mask = arm64_ftr_reg_ctrel0.strict_mask;
+
+ /* Trap CTR_EL0 access on this CPU, only if it has a mismatch */
+ if ((read_cpuid_cachetype() & mask) !=
+ (arm64_ftr_reg_ctrel0.sys_val & mask))
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
}
atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
@@ -116,6 +138,15 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
static DEFINE_SPINLOCK(bp_lock);
int cpu, slot = -1;
+ /*
+ * enable_smccc_arch_workaround_1() passes NULL for the hyp_vecs
+ * start/end if we're a guest. Skip the hyp-vectors work.
+ */
+ if (!hyp_vecs_start) {
+ __this_cpu_write(bp_hardening_data.fn, fn);
+ return;
+ }
+
spin_lock(&bp_lock);
for_each_possible_cpu(cpu) {
if (per_cpu(bp_hardening_data.fn, cpu) == fn) {
@@ -312,6 +343,14 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
void arm64_set_ssbd_mitigation(bool state)
{
+ if (this_cpu_has_cap(ARM64_SSBS)) {
+ if (state)
+ asm volatile(SET_PSTATE_SSBS(0));
+ else
+ asm volatile(SET_PSTATE_SSBS(1));
+ return;
+ }
+
switch (psci_ops.conduit) {
case PSCI_CONDUIT_HVC:
arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_2, state, NULL);
@@ -336,6 +375,11 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+ if (this_cpu_has_cap(ARM64_SSBS)) {
+ required = false;
+ goto out_printmsg;
+ }
+
if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
ssbd_state = ARM64_SSBD_UNKNOWN;
return false;
@@ -384,7 +428,6 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
switch (ssbd_state) {
case ARM64_SSBD_FORCE_DISABLE:
- pr_info_once("%s disabled from command-line\n", entry->desc);
arm64_set_ssbd_mitigation(false);
required = false;
break;
@@ -397,7 +440,6 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
break;
case ARM64_SSBD_FORCE_ENABLE:
- pr_info_once("%s forced from command-line\n", entry->desc);
arm64_set_ssbd_mitigation(true);
required = true;
break;
@@ -407,10 +449,27 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
break;
}
+out_printmsg:
+ switch (ssbd_state) {
+ case ARM64_SSBD_FORCE_DISABLE:
+ pr_info_once("%s disabled from command-line\n", entry->desc);
+ break;
+
+ case ARM64_SSBD_FORCE_ENABLE:
+ pr_info_once("%s forced from command-line\n", entry->desc);
+ break;
+ }
+
return required;
}
#endif /* CONFIG_ARM64_SSBD */
+static void __maybe_unused
+cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
+{
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
+}
+
#define CAP_MIDR_RANGE(model, v_min, r_min, v_max, r_max) \
.matches = is_affected_midr_range, \
.midr_range = MIDR_RANGE(model, v_min, r_min, v_max, r_max)
@@ -616,14 +675,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
},
#endif
{
- .desc = "Mismatched cache line size",
- .capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
- .matches = has_mismatched_cache_type,
- .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
- .cpu_enable = cpu_enable_trap_ctr_access,
- },
- {
- .desc = "Mismatched cache type",
+ .desc = "Mismatched cache type (CTR_EL0)",
.capability = ARM64_MISMATCHED_CACHE_TYPE,
.matches = has_mismatched_cache_type,
.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
@@ -680,6 +732,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
.matches = has_ssbd_mitigation,
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+ {
+ /* Cortex-A76 r0p0 to r2p0 */
+ .desc = "ARM erratum 1188873",
+ .capability = ARM64_WORKAROUND_1188873,
+ ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+ },
+#endif
{
}
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index e238b7932096..af50064dea51 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -20,6 +20,7 @@
#include <linux/bsearch.h>
#include <linux/cpumask.h>
+#include <linux/crash_dump.h>
#include <linux/sort.h>
#include <linux/stop_machine.h>
#include <linux/types.h>
@@ -117,6 +118,7 @@ EXPORT_SYMBOL(cpu_hwcap_keys);
static bool __maybe_unused
cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
+static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap);
/*
* NOTE: Any changes to the visibility of features should be kept in
@@ -164,6 +166,11 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_END,
};
+static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR1_SSBS_SHIFT, 4, ID_AA64PFR1_SSBS_PSTATE_NI),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -371,7 +378,7 @@ static const struct __ftr_reg_entry {
/* Op1 = 0, CRn = 0, CRm = 4 */
ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
- ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_raz),
+ ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
/* Op1 = 0, CRn = 0, CRm = 5 */
@@ -657,7 +664,6 @@ void update_cpu_features(int cpu,
/*
* EL3 is not our concern.
- * ID_AA64PFR1 is currently RES0.
*/
taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu,
info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0);
@@ -848,15 +854,55 @@ static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unus
}
static bool has_cache_idc(const struct arm64_cpu_capabilities *entry,
- int __unused)
+ int scope)
{
- return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_IDC_SHIFT);
+ u64 ctr;
+
+ if (scope == SCOPE_SYSTEM)
+ ctr = arm64_ftr_reg_ctrel0.sys_val;
+ else
+ ctr = read_cpuid_effective_cachetype();
+
+ return ctr & BIT(CTR_IDC_SHIFT);
+}
+
+static void cpu_emulate_effective_ctr(const struct arm64_cpu_capabilities *__unused)
+{
+ /*
+ * If the CPU exposes raw CTR_EL0.IDC = 0, while effectively
+ * CTR_EL0.IDC = 1 (from CLIDR values), we need to trap accesses
+ * to the CTR_EL0 on this CPU and emulate it with the real/safe
+ * value.
+ */
+ if (!(read_cpuid_cachetype() & BIT(CTR_IDC_SHIFT)))
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
}
static bool has_cache_dic(const struct arm64_cpu_capabilities *entry,
- int __unused)
+ int scope)
{
- return read_sanitised_ftr_reg(SYS_CTR_EL0) & BIT(CTR_DIC_SHIFT);
+ u64 ctr;
+
+ if (scope == SCOPE_SYSTEM)
+ ctr = arm64_ftr_reg_ctrel0.sys_val;
+ else
+ ctr = read_cpuid_cachetype();
+
+ return ctr & BIT(CTR_DIC_SHIFT);
+}
+
+static bool __maybe_unused
+has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
+{
+ /*
+ * Kdump isn't guaranteed to power-off all secondary CPUs, CNP
+ * may share TLB entries with a CPU stuck in the crashed
+ * kernel.
+ */
+ if (is_kdump_kernel())
+ return false;
+
+ return has_cpuid_feature(entry, scope);
}
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
@@ -1035,6 +1081,70 @@ static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
WARN_ON(val & (7 << 27 | 7 << 21));
}
+#ifdef CONFIG_ARM64_SSBD
+static int ssbs_emulation_handler(struct pt_regs *regs, u32 instr)
+{
+ if (user_mode(regs))
+ return 1;
+
+ if (instr & BIT(PSTATE_Imm_shift))
+ regs->pstate |= PSR_SSBS_BIT;
+ else
+ regs->pstate &= ~PSR_SSBS_BIT;
+
+ arm64_skip_faulting_instruction(regs, 4);
+ return 0;
+}
+
+static struct undef_hook ssbs_emulation_hook = {
+ .instr_mask = ~(1U << PSTATE_Imm_shift),
+ .instr_val = 0xd500401f | PSTATE_SSBS,
+ .fn = ssbs_emulation_handler,
+};
+
+static void cpu_enable_ssbs(const struct arm64_cpu_capabilities *__unused)
+{
+ static bool undef_hook_registered = false;
+ static DEFINE_SPINLOCK(hook_lock);
+
+ spin_lock(&hook_lock);
+ if (!undef_hook_registered) {
+ register_undef_hook(&ssbs_emulation_hook);
+ undef_hook_registered = true;
+ }
+ spin_unlock(&hook_lock);
+
+ if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE) {
+ sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS);
+ arm64_set_ssbd_mitigation(false);
+ } else {
+ arm64_set_ssbd_mitigation(true);
+ }
+}
+#endif /* CONFIG_ARM64_SSBD */
+
+#ifdef CONFIG_ARM64_PAN
+static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
+{
+ /*
+ * We modify PSTATE. This won't work from irq context as the PSTATE
+ * is discarded once we return from the exception.
+ */
+ WARN_ON_ONCE(in_interrupt());
+
+ sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
+ asm(SET_PSTATE_PAN(1));
+}
+#endif /* CONFIG_ARM64_PAN */
+
+#ifdef CONFIG_ARM64_RAS_EXTN
+static void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
+{
+ /* Firmware may have left a deferred SError in this register. */
+ write_sysreg_s(0, SYS_DISR_EL1);
+}
+#endif /* CONFIG_ARM64_RAS_EXTN */
+
static const struct arm64_cpu_capabilities arm64_features[] = {
{
.desc = "GIC system register CPU interface",
@@ -1184,6 +1294,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.capability = ARM64_HAS_CACHE_IDC,
.type = ARM64_CPUCAP_SYSTEM_FEATURE,
.matches = has_cache_idc,
+ .cpu_enable = cpu_emulate_effective_ctr,
},
{
.desc = "Instruction cache invalidation not required for I/D coherence",
@@ -1222,6 +1333,41 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.cpu_enable = cpu_enable_hw_dbm,
},
#endif
+#ifdef CONFIG_ARM64_SSBD
+ {
+ .desc = "CRC32 instructions",
+ .capability = ARM64_HAS_CRC32,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64ISAR0_EL1,
+ .field_pos = ID_AA64ISAR0_CRC32_SHIFT,
+ .min_field_value = 1,
+ },
+ {
+ .desc = "Speculative Store Bypassing Safe (SSBS)",
+ .capability = ARM64_SSBS,
+ .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64PFR1_EL1,
+ .field_pos = ID_AA64PFR1_SSBS_SHIFT,
+ .sign = FTR_UNSIGNED,
+ .min_field_value = ID_AA64PFR1_SSBS_PSTATE_ONLY,
+ .cpu_enable = cpu_enable_ssbs,
+ },
+#endif
+#ifdef CONFIG_ARM64_CNP
+ {
+ .desc = "Common not Private translations",
+ .capability = ARM64_HAS_CNP,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_useable_cnp,
+ .sys_reg = SYS_ID_AA64MMFR2_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64MMFR2_CNP_SHIFT,
+ .min_field_value = 1,
+ .cpu_enable = cpu_enable_cnp,
+ },
+#endif
{},
};
@@ -1267,6 +1413,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
#ifdef CONFIG_ARM64_SVE
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
#endif
+ HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
{},
};
@@ -1658,6 +1805,11 @@ cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
}
+static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap)
+{
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+}
+
/*
* We emulate only the following system register space.
* Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7]
@@ -1719,27 +1871,32 @@ static int emulate_sys_reg(u32 id, u64 *valp)
return 0;
}
-static int emulate_mrs(struct pt_regs *regs, u32 insn)
+int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt)
{
int rc;
- u32 sys_reg, dst;
u64 val;
- /*
- * sys_reg values are defined as used in mrs/msr instruction.
- * shift the imm value to get the encoding.
- */
- sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
rc = emulate_sys_reg(sys_reg, &val);
if (!rc) {
- dst = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
- pt_regs_write_reg(regs, dst, val);
+ pt_regs_write_reg(regs, rt, val);
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
-
return rc;
}
+static int emulate_mrs(struct pt_regs *regs, u32 insn)
+{
+ u32 sys_reg, rt;
+
+ /*
+ * sys_reg values are defined as used in mrs/msr instruction.
+ * shift the imm value to get the encoding.
+ */
+ sys_reg = (u32)aarch64_insn_decode_immediate(AARCH64_INSN_IMM_16, insn) << 5;
+ rt = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RT, insn);
+ return do_emulate_mrs(regs, sys_reg, rt);
+}
+
static struct undef_hook mrs_hook = {
.instr_mask = 0xfff00000,
.instr_val = 0xd5300000,
@@ -1755,9 +1912,3 @@ static int __init enable_mrs_emulation(void)
}
core_initcall(enable_mrs_emulation);
-
-void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused)
-{
- /* Firmware may have left a deferred SError in this register. */
- write_sysreg_s(0, SYS_DISR_EL1);
-}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index e9ab7b3ed317..bcc2831399cb 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -81,6 +81,7 @@ static const char *const hwcap_str[] = {
"uscat",
"ilrcpc",
"flagm",
+ "ssbs",
NULL
};
@@ -324,7 +325,15 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
{
info->reg_cntfrq = arch_timer_get_cntfrq();
- info->reg_ctr = read_cpuid_cachetype();
+ /*
+ * Use the effective value of the CTR_EL0 than the raw value
+ * exposed by the CPU. CTR_E0.IDC field value must be interpreted
+ * with the CLIDR_EL1 fields to avoid triggering false warnings
+ * when there is a mismatch across the CPUs. Keep track of the
+ * effective value of the CTR_EL0 in our internal records for
+ * acurate sanity check and feature enablement.
+ */
+ info->reg_ctr = read_cpuid_effective_cachetype();
info->reg_dczid = read_cpuid(DCZID_EL0);
info->reg_midr = read_cpuid_id();
info->reg_revidr = read_cpuid(REVIDR_EL1);
diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c
new file mode 100644
index 000000000000..ca4c3e12d8c5
--- /dev/null
+++ b/arch/arm64/kernel/crash_core.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) Linaro.
+ * Copyright (C) Huawei Futurewei Technologies.
+ */
+
+#include <linux/crash_core.h>
+#include <asm/memory.h>
+
+void arch_crash_save_vmcoreinfo(void)
+{
+ VMCOREINFO_NUMBER(VA_BITS);
+ /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+ vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+ kimage_voffset);
+ vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+ PHYS_OFFSET);
+ vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
+}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 06ca574495af..d7bb6aefae0a 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -210,13 +210,6 @@ NOKPROBE_SYMBOL(call_step_hook);
static void send_user_sigtrap(int si_code)
{
struct pt_regs *regs = current_pt_regs();
- siginfo_t info;
-
- clear_siginfo(&info);
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)instruction_pointer(regs);
if (WARN_ON(!user_mode(regs)))
return;
@@ -224,7 +217,9 @@ static void send_user_sigtrap(int si_code)
if (interrupts_enabled(regs))
local_irq_enable();
- arm64_force_sig_info(&info, "User debug trap", current);
+ arm64_force_sig_fault(SIGTRAP, si_code,
+ (void __user *)instruction_pointer(regs),
+ "User debug trap");
}
static int single_step_handler(unsigned long addr, unsigned int esr,
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 09dbea221a27..039144ecbcb2 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -589,7 +589,7 @@ el1_undef:
inherit_daif pstate=x23, tmp=x2
mov x0, sp
bl do_undefinstr
- ASM_BUG()
+ kernel_exit 1
el1_dbg:
/*
* Debug exception handling
@@ -665,6 +665,7 @@ el0_sync:
cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception
b.eq el0_fpsimd_exc
cmp x24, #ESR_ELx_EC_SYS64 // configurable trap
+ ccmp x24, #ESR_ELx_EC_WFx, #4, ne
b.eq el0_sys
cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception
b.eq el0_sp_pc
@@ -697,9 +698,9 @@ el0_sync_compat:
cmp x24, #ESR_ELx_EC_UNKNOWN // unknown exception in EL0
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP15_32 // CP15 MRC/MCR trap
- b.eq el0_undef
+ b.eq el0_cp15
cmp x24, #ESR_ELx_EC_CP15_64 // CP15 MRRC/MCRR trap
- b.eq el0_undef
+ b.eq el0_cp15
cmp x24, #ESR_ELx_EC_CP14_MR // CP14 MRC/MCR trap
b.eq el0_undef
cmp x24, #ESR_ELx_EC_CP14_LS // CP14 LDC/STC trap
@@ -722,6 +723,17 @@ el0_irq_compat:
el0_error_compat:
kernel_entry 0, 32
b el0_error_naked
+
+el0_cp15:
+ /*
+ * Trapped CP15 (MRC, MCR, MRRC, MCRR) instructions
+ */
+ enable_daif
+ ct_user_exit
+ mov x0, x25
+ mov x1, sp
+ bl do_cp15instr
+ b ret_to_user
#endif
el0_da:
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 58c53bc96928..5ebe73b69961 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -842,7 +842,6 @@ asmlinkage void do_fpsimd_acc(unsigned int esr, struct pt_regs *regs)
*/
asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
{
- siginfo_t info;
unsigned int si_code = FPE_FLTUNK;
if (esr & ESR_ELx_FP_EXC_TFV) {
@@ -858,12 +857,9 @@ asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
si_code = FPE_FLTRES;
}
- clear_siginfo(&info);
- info.si_signo = SIGFPE;
- info.si_code = si_code;
- info.si_addr = (void __user *)instruction_pointer(regs);
-
- send_sig_info(SIGFPE, &info, current);
+ send_sig_fault(SIGFPE, si_code,
+ (void __user *)instruction_pointer(regs),
+ current);
}
void fpsimd_thread_switch(struct task_struct *next)
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index b0853069702f..4471f570a295 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -287,19 +287,21 @@ __create_page_tables:
mov x28, lr
/*
- * Invalidate the idmap and swapper page tables to avoid potential
- * dirty cache lines being evicted.
+ * Invalidate the init page tables to avoid potential dirty cache lines
+ * being evicted. Other page tables are allocated in rodata as part of
+ * the kernel image, and thus are clean to the PoC per the boot
+ * protocol.
*/
- adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x0, init_pg_dir
+ adrp x1, init_pg_end
sub x1, x1, x0
bl __inval_dcache_area
/*
- * Clear the idmap and swapper page tables.
+ * Clear the init page tables.
*/
- adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x0, init_pg_dir
+ adrp x1, init_pg_end
sub x1, x1, x0
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
@@ -373,7 +375,7 @@ __create_page_tables:
/*
* Map the kernel image (starting with PHYS_OFFSET).
*/
- adrp x0, swapper_pg_dir
+ adrp x0, init_pg_dir
mov_q x5, KIMAGE_VADDR + TEXT_OFFSET // compile time __va(_text)
add x5, x5, x23 // add KASLR displacement
mov x4, PTRS_PER_PGD
@@ -390,7 +392,7 @@ __create_page_tables:
* tables again to remove any speculatively loaded cache lines.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_end
+ adrp x1, init_pg_end
sub x1, x1, x0
dmb sy
bl __inval_dcache_area
@@ -706,6 +708,7 @@ secondary_startup:
* Common entry point for secondary CPUs.
*/
bl __cpu_setup // initialise processor
+ adrp x1, swapper_pg_dir
bl __enable_mmu
ldr x8, =__secondary_switched
br x8
@@ -748,6 +751,7 @@ ENDPROC(__secondary_switched)
* Enable the MMU.
*
* x0 = SCTLR_EL1 value for turning on the MMU.
+ * x1 = TTBR1_EL1 value
*
* Returns to the caller via x30/lr. This requires the caller to be covered
* by the .idmap.text section.
@@ -756,17 +760,16 @@ ENDPROC(__secondary_switched)
* If it isn't, park the CPU
*/
ENTRY(__enable_mmu)
- mrs x1, ID_AA64MMFR0_EL1
- ubfx x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
+ mrs x2, ID_AA64MMFR0_EL1
+ ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
b.ne __no_granule_support
- update_early_cpu_boot_status 0, x1, x2
- adrp x1, idmap_pg_dir
- adrp x2, swapper_pg_dir
- phys_to_ttbr x3, x1
- phys_to_ttbr x4, x2
- msr ttbr0_el1, x3 // load TTBR0
- msr ttbr1_el1, x4 // load TTBR1
+ update_early_cpu_boot_status 0, x2, x3
+ adrp x2, idmap_pg_dir
+ phys_to_ttbr x1, x1
+ phys_to_ttbr x2, x2
+ msr ttbr0_el1, x2 // load TTBR0
+ msr ttbr1_el1, x1 // load TTBR1
isb
msr sctlr_el1, x0
isb
@@ -823,6 +826,7 @@ __primary_switch:
mrs x20, sctlr_el1 // preserve old SCTLR_EL1 value
#endif
+ adrp x1, init_pg_dir
bl __enable_mmu
#ifdef CONFIG_RELOCATABLE
bl __relocate_kernel
diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
index e0756416e567..646b9562ee64 100644
--- a/arch/arm64/kernel/jump_label.c
+++ b/arch/arm64/kernel/jump_label.c
@@ -25,12 +25,12 @@
void arch_jump_label_transform(struct jump_entry *entry,
enum jump_label_type type)
{
- void *addr = (void *)entry->code;
+ void *addr = (void *)jump_entry_code(entry);
u32 insn;
if (type == JUMP_LABEL_JMP) {
- insn = aarch64_insn_gen_branch_imm(entry->code,
- entry->target,
+ insn = aarch64_insn_gen_branch_imm(jump_entry_code(entry),
+ jump_entry_target(entry),
AARCH64_INSN_BRANCH_NOLINK);
} else {
insn = aarch64_insn_gen_nop();
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index f6a5c6bc1434..922add8adb74 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
}
}
#endif /* CONFIG_HIBERNATION */
-
-void arch_crash_save_vmcoreinfo(void)
-{
- VMCOREINFO_NUMBER(VA_BITS);
- /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
- vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
- kimage_voffset);
- vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
- PHYS_OFFSET);
- vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
-}
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c
index 53f371ed4568..75c158b0353f 100644
--- a/arch/arm64/kernel/paravirt.c
+++ b/arch/arm64/kernel/paravirt.c
@@ -21,5 +21,5 @@
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops pv_time_ops;
-EXPORT_SYMBOL_GPL(pv_time_ops);
+struct paravirt_patch_template pv_ops;
+EXPORT_SYMBOL_GPL(pv_ops);
diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c
index 0e2ea1c78542..bb85e2f4603f 100644
--- a/arch/arm64/kernel/pci.c
+++ b/arch/arm64/kernel/pci.c
@@ -165,16 +165,15 @@ static void pci_acpi_generic_release_info(struct acpi_pci_root_info *ci)
/* Interface called from ACPI code to setup PCI host controller */
struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
{
- int node = acpi_get_node(root->device->handle);
struct acpi_pci_generic_root_info *ri;
struct pci_bus *bus, *child;
struct acpi_pci_root_ops *root_ops;
- ri = kzalloc_node(sizeof(*ri), GFP_KERNEL, node);
+ ri = kzalloc(sizeof(*ri), GFP_KERNEL);
if (!ri)
return NULL;
- root_ops = kzalloc_node(sizeof(*root_ops), GFP_KERNEL, node);
+ root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL);
if (!root_ops) {
kfree(ri);
return NULL;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8e38d5267f22..e213f8e867f6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
return 0;
}
+static int armv8pmu_filter_match(struct perf_event *event)
+{
+ unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
+ return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
static void armv8pmu_reset(void *info)
{
struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1114,6 +1120,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->stop = armv8pmu_stop,
cpu_pmu->reset = armv8pmu_reset,
cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
+ cpu_pmu->filter_match = armv8pmu_filter_match;
return 0;
}
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index e78c3ef04d95..9b65132e789a 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -107,7 +107,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
if (!p->ainsn.api.insn)
return -ENOMEM;
break;
- };
+ }
/* prepare the instruction */
if (p->ainsn.api.insn)
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 7f1628effe6d..ce99c58cd1f1 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -358,6 +358,10 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
if (IS_ENABLED(CONFIG_ARM64_UAO) &&
cpus_have_const_cap(ARM64_HAS_UAO))
childregs->pstate |= PSR_UAO_BIT;
+
+ if (arm64_get_ssbd_state() == ARM64_SSBD_FORCE_DISABLE)
+ childregs->pstate |= PSR_SSBS_BIT;
+
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index e8edbf13302a..8cdaf25e99cd 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -24,7 +24,6 @@
#include <uapi/linux/psci.h>
-#include <asm/compiler.h>
#include <asm/cpu_ops.h>
#include <asm/errno.h>
#include <asm/smp_plat.h>
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 6219486fa25f..1710a2d01669 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -182,13 +182,7 @@ static void ptrace_hbptriggered(struct perf_event *bp,
struct pt_regs *regs)
{
struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp);
- siginfo_t info;
-
- clear_siginfo(&info);
- info.si_signo = SIGTRAP;
- info.si_errno = 0;
- info.si_code = TRAP_HWBKPT;
- info.si_addr = (void __user *)(bkpt->trigger);
+ const char *desc = "Hardware breakpoint trap (ptrace)";
#ifdef CONFIG_COMPAT
if (is_compat_task()) {
@@ -208,10 +202,14 @@ static void ptrace_hbptriggered(struct perf_event *bp,
break;
}
}
- force_sig_ptrace_errno_trap(si_errno, (void __user *)bkpt->trigger);
+ arm64_force_sig_ptrace_errno_trap(si_errno,
+ (void __user *)bkpt->trigger,
+ desc);
}
#endif
- arm64_force_sig_info(&info, "Hardware breakpoint trap (ptrace)", current);
+ arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT,
+ (void __user *)(bkpt->trigger),
+ desc);
}
/*
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 5b4fac434c84..d0f62dd24c90 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -64,6 +64,9 @@
#include <asm/xen/hypervisor.h>
#include <asm/mmu_context.h>
+static int num_standard_resources;
+static struct resource *standard_resources;
+
phys_addr_t __fdt_pointer __initdata;
/*
@@ -206,14 +209,19 @@ static void __init request_standard_resources(void)
{
struct memblock_region *region;
struct resource *res;
+ unsigned long i = 0;
kernel_code.start = __pa_symbol(_text);
kernel_code.end = __pa_symbol(__init_begin - 1);
kernel_data.start = __pa_symbol(_sdata);
kernel_data.end = __pa_symbol(_end - 1);
+ num_standard_resources = memblock.memory.cnt;
+ standard_resources = alloc_bootmem_low(num_standard_resources *
+ sizeof(*standard_resources));
+
for_each_memblock(memory, region) {
- res = alloc_bootmem_low(sizeof(*res));
+ res = &standard_resources[i++];
if (memblock_is_nomap(region)) {
res->name = "reserved";
res->flags = IORESOURCE_MEM;
@@ -243,36 +251,26 @@ static void __init request_standard_resources(void)
static int __init reserve_memblock_reserved_regions(void)
{
- phys_addr_t start, end, roundup_end = 0;
- struct resource *mem, *res;
- u64 i;
-
- for_each_reserved_mem_region(i, &start, &end) {
- if (end <= roundup_end)
- continue; /* done already */
-
- start = __pfn_to_phys(PFN_DOWN(start));
- end = __pfn_to_phys(PFN_UP(end)) - 1;
- roundup_end = end;
-
- res = kzalloc(sizeof(*res), GFP_ATOMIC);
- if (WARN_ON(!res))
- return -ENOMEM;
- res->start = start;
- res->end = end;
- res->name = "reserved";
- res->flags = IORESOURCE_MEM;
-
- mem = request_resource_conflict(&iomem_resource, res);
- /*
- * We expected memblock_reserve() regions to conflict with
- * memory created by request_standard_resources().
- */
- if (WARN_ON_ONCE(!mem))
+ u64 i, j;
+
+ for (i = 0; i < num_standard_resources; ++i) {
+ struct resource *mem = &standard_resources[i];
+ phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+ if (!memblock_is_region_reserved(mem->start, mem_size))
continue;
- kfree(res);
- reserve_region_with_split(mem, start, end, "reserved");
+ for_each_reserved_mem_region(j, &r_start, &r_end) {
+ resource_size_t start, end;
+
+ start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+ end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+ if (start > mem->end || end < mem->start)
+ continue;
+
+ reserve_region_with_split(mem, start, end, "reserved");
+ }
}
return 0;
@@ -351,12 +349,8 @@ void __init setup_arch(char **cmdline_p)
#endif
#ifdef CONFIG_VT
-#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
-#elif defined(CONFIG_DUMMY_CONSOLE)
conswitchp = &dummy_con;
#endif
-#endif
if (boot_args[1] || boot_args[2] || boot_args[3]) {
pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n"
"\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n"
diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S
index bebec8ef9372..3e53ffa07994 100644
--- a/arch/arm64/kernel/sleep.S
+++ b/arch/arm64/kernel/sleep.S
@@ -101,6 +101,7 @@ ENTRY(cpu_resume)
bl el2_setup // if in EL2 drop to EL1 cleanly
bl __cpu_setup
/* enable the MMU early - so we can access sleep_save_stash by va */
+ adrp x1, swapper_pg_dir
bl __enable_mmu
ldr x8, =_cpu_resume
br x8
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 25fcd22a4bb2..96b8f2f51ab2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -602,7 +602,7 @@ static void __init of_parse_and_init_cpus(void)
{
struct device_node *dn;
- for_each_node_by_type(dn, "cpu") {
+ for_each_of_cpu_node(dn) {
u64 hwid = of_get_cpu_mpidr(dn);
if (hwid == INVALID_HWID)
diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c
index 3432e5ef9f41..885f13e58708 100644
--- a/arch/arm64/kernel/ssbd.c
+++ b/arch/arm64/kernel/ssbd.c
@@ -3,17 +3,33 @@
* Copyright (C) 2018 ARM Ltd, All Rights Reserved.
*/
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
#include <linux/thread_info.h>
#include <asm/cpufeature.h>
+static void ssbd_ssbs_enable(struct task_struct *task)
+{
+ u64 val = is_compat_thread(task_thread_info(task)) ?
+ PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+ task_pt_regs(task)->pstate |= val;
+}
+
+static void ssbd_ssbs_disable(struct task_struct *task)
+{
+ u64 val = is_compat_thread(task_thread_info(task)) ?
+ PSR_AA32_SSBS_BIT : PSR_SSBS_BIT;
+
+ task_pt_regs(task)->pstate &= ~val;
+}
+
/*
* prctl interface for SSBD
- * FIXME: Drop the below ifdefery once merged in 4.18.
*/
-#ifdef PR_SPEC_STORE_BYPASS
static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
{
int state = arm64_get_ssbd_state();
@@ -46,12 +62,14 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
return -EPERM;
task_clear_spec_ssb_disable(task);
clear_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_enable(task);
break;
case PR_SPEC_DISABLE:
if (state == ARM64_SSBD_FORCE_DISABLE)
return -EPERM;
task_set_spec_ssb_disable(task);
set_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_disable(task);
break;
case PR_SPEC_FORCE_DISABLE:
if (state == ARM64_SSBD_FORCE_DISABLE)
@@ -59,6 +77,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl)
task_set_spec_ssb_disable(task);
task_set_spec_ssb_force_disable(task);
set_tsk_thread_flag(task, TIF_SSBD);
+ ssbd_ssbs_disable(task);
break;
default:
return -ERANGE;
@@ -107,4 +126,3 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
return -ENODEV;
}
}
-#endif /* PR_SPEC_STORE_BYPASS */
diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c
index 70c283368b64..9405d1b7f4b0 100644
--- a/arch/arm64/kernel/suspend.c
+++ b/arch/arm64/kernel/suspend.c
@@ -48,6 +48,10 @@ void notrace __cpu_suspend_exit(void)
*/
cpu_uninstall_idmap();
+ /* Restore CnP bit in TTBR1_EL1 */
+ if (system_supports_cnp())
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+
/*
* PSTATE was not saved over suspend/resume, re-enable any detected
* features that might not have been set correctly.
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index a6109825eeb9..32653d156747 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -68,8 +68,8 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags)
*/
long compat_arm_syscall(struct pt_regs *regs)
{
- siginfo_t info;
unsigned int no = regs->regs[7];
+ void __user *addr;
switch (no) {
/*
@@ -112,13 +112,10 @@ long compat_arm_syscall(struct pt_regs *regs)
break;
}
- clear_siginfo(&info);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLTRP;
- info.si_addr = (void __user *)instruction_pointer(regs) -
- (compat_thumb_mode(regs) ? 2 : 4);
+ addr = (void __user *)instruction_pointer(regs) -
+ (compat_thumb_mode(regs) ? 2 : 4);
- arm64_notify_die("Oops - bad compat syscall(2)", regs, &info, no);
+ arm64_notify_die("Oops - bad compat syscall(2)", regs,
+ SIGILL, ILL_ILLTRP, addr, no);
return 0;
}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 039e9ff379cc..5f4d9acb32f5 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -224,24 +224,19 @@ void die(const char *str, struct pt_regs *regs, int err)
do_exit(SIGSEGV);
}
-static bool show_unhandled_signals_ratelimited(void)
+static void arm64_show_signal(int signo, const char *str)
{
static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
- return show_unhandled_signals && __ratelimit(&rs);
-}
-
-void arm64_force_sig_info(struct siginfo *info, const char *str,
- struct task_struct *tsk)
-{
+ struct task_struct *tsk = current;
unsigned int esr = tsk->thread.fault_code;
struct pt_regs *regs = task_pt_regs(tsk);
- if (!unhandled_signal(tsk, info->si_signo))
- goto send_sig;
-
- if (!show_unhandled_signals_ratelimited())
- goto send_sig;
+ /* Leave if the signal won't be shown */
+ if (!show_unhandled_signals ||
+ !unhandled_signal(tsk, signo) ||
+ !__ratelimit(&rs))
+ return;
pr_info("%s[%d]: unhandled exception: ", tsk->comm, task_pid_nr(tsk));
if (esr)
@@ -251,19 +246,39 @@ void arm64_force_sig_info(struct siginfo *info, const char *str,
print_vma_addr(KERN_CONT " in ", regs->pc);
pr_cont("\n");
__show_regs(regs);
+}
-send_sig:
- force_sig_info(info->si_signo, info, tsk);
+void arm64_force_sig_fault(int signo, int code, void __user *addr,
+ const char *str)
+{
+ arm64_show_signal(signo, str);
+ force_sig_fault(signo, code, addr, current);
+}
+
+void arm64_force_sig_mceerr(int code, void __user *addr, short lsb,
+ const char *str)
+{
+ arm64_show_signal(SIGBUS, str);
+ force_sig_mceerr(code, addr, lsb, current);
+}
+
+void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr,
+ const char *str)
+{
+ arm64_show_signal(SIGTRAP, str);
+ force_sig_ptrace_errno_trap(errno, addr);
}
void arm64_notify_die(const char *str, struct pt_regs *regs,
- struct siginfo *info, int err)
+ int signo, int sicode, void __user *addr,
+ int err)
{
if (user_mode(regs)) {
WARN_ON(regs != current_pt_regs());
current->thread.fault_address = 0;
current->thread.fault_code = err;
- arm64_force_sig_info(info, str, current);
+
+ arm64_force_sig_fault(signo, sicode, addr, str);
} else {
die(str, regs, err);
}
@@ -310,10 +325,12 @@ static int call_undef_hook(struct pt_regs *regs)
int (*fn)(struct pt_regs *regs, u32 instr) = NULL;
void __user *pc = (void __user *)instruction_pointer(regs);
- if (!user_mode(regs))
- return 1;
-
- if (compat_thumb_mode(regs)) {
+ if (!user_mode(regs)) {
+ __le32 instr_le;
+ if (probe_kernel_address((__force __le32 *)pc, instr_le))
+ goto exit;
+ instr = le32_to_cpu(instr_le);
+ } else if (compat_thumb_mode(regs)) {
/* 16-bit Thumb instruction */
__le16 instr_le;
if (get_user(instr_le, (__le16 __user *)pc))
@@ -348,11 +365,11 @@ exit:
void force_signal_inject(int signal, int code, unsigned long address)
{
- siginfo_t info;
const char *desc;
struct pt_regs *regs = current_pt_regs();
- clear_siginfo(&info);
+ if (WARN_ON(!user_mode(regs)))
+ return;
switch (signal) {
case SIGILL:
@@ -372,12 +389,7 @@ void force_signal_inject(int signal, int code, unsigned long address)
signal = SIGKILL;
}
- info.si_signo = signal;
- info.si_errno = 0;
- info.si_code = code;
- info.si_addr = (void __user *)address;
-
- arm64_notify_die(desc, regs, &info, 0);
+ arm64_notify_die(desc, regs, signal, code, (void __user *)address, 0);
}
/*
@@ -406,14 +418,10 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
if (call_undef_hook(regs) == 0)
return;
+ BUG_ON(!user_mode(regs));
force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
}
-void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
-{
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
-}
-
#define __user_cache_maint(insn, address, res) \
if (address >= user_addr_max()) { \
res = -EFAULT; \
@@ -437,7 +445,7 @@ void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
{
unsigned long address;
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
int ret = 0;
@@ -472,7 +480,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
unsigned long val = arm64_ftr_reg_user_value(&arm64_ftr_reg_ctrel0);
pt_regs_write_reg(regs, rt, val);
@@ -482,7 +490,7 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
@@ -490,12 +498,28 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
{
- int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+ int rt = ESR_ELx_SYS64_ISS_RT(esr);
pt_regs_write_reg(regs, rt, arch_timer_get_rate());
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
+static void mrs_handler(unsigned int esr, struct pt_regs *regs)
+{
+ u32 sysreg, rt;
+
+ rt = ESR_ELx_SYS64_ISS_RT(esr);
+ sysreg = esr_sys64_to_sysreg(esr);
+
+ if (do_emulate_mrs(regs, sysreg, rt) != 0)
+ force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc);
+}
+
+static void wfi_handler(unsigned int esr, struct pt_regs *regs)
+{
+ arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
+}
+
struct sys64_hook {
unsigned int esr_mask;
unsigned int esr_val;
@@ -526,9 +550,176 @@ static struct sys64_hook sys64_hooks[] = {
.esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ,
.handler = cntfrq_read_handler,
},
+ {
+ /* Trap read access to CPUID registers */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_MRS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_MRS_OP_VAL,
+ .handler = mrs_handler,
+ },
+ {
+ /* Trap WFI instructions executed in userspace */
+ .esr_mask = ESR_ELx_WFx_MASK,
+ .esr_val = ESR_ELx_WFx_WFI_VAL,
+ .handler = wfi_handler,
+ },
{},
};
+
+#ifdef CONFIG_COMPAT
+#define PSTATE_IT_1_0_SHIFT 25
+#define PSTATE_IT_1_0_MASK (0x3 << PSTATE_IT_1_0_SHIFT)
+#define PSTATE_IT_7_2_SHIFT 10
+#define PSTATE_IT_7_2_MASK (0x3f << PSTATE_IT_7_2_SHIFT)
+
+static u32 compat_get_it_state(struct pt_regs *regs)
+{
+ u32 it, pstate = regs->pstate;
+
+ it = (pstate & PSTATE_IT_1_0_MASK) >> PSTATE_IT_1_0_SHIFT;
+ it |= ((pstate & PSTATE_IT_7_2_MASK) >> PSTATE_IT_7_2_SHIFT) << 2;
+
+ return it;
+}
+
+static void compat_set_it_state(struct pt_regs *regs, u32 it)
+{
+ u32 pstate_it;
+
+ pstate_it = (it << PSTATE_IT_1_0_SHIFT) & PSTATE_IT_1_0_MASK;
+ pstate_it |= ((it >> 2) << PSTATE_IT_7_2_SHIFT) & PSTATE_IT_7_2_MASK;
+
+ regs->pstate &= ~PSR_AA32_IT_MASK;
+ regs->pstate |= pstate_it;
+}
+
+static bool cp15_cond_valid(unsigned int esr, struct pt_regs *regs)
+{
+ int cond;
+
+ /* Only a T32 instruction can trap without CV being set */
+ if (!(esr & ESR_ELx_CV)) {
+ u32 it;
+
+ it = compat_get_it_state(regs);
+ if (!it)
+ return true;
+
+ cond = it >> 4;
+ } else {
+ cond = (esr & ESR_ELx_COND_MASK) >> ESR_ELx_COND_SHIFT;
+ }
+
+ return aarch32_opcode_cond_checks[cond](regs->pstate);
+}
+
+static void advance_itstate(struct pt_regs *regs)
+{
+ u32 it;
+
+ /* ARM mode */
+ if (!(regs->pstate & PSR_AA32_T_BIT) ||
+ !(regs->pstate & PSR_AA32_IT_MASK))
+ return;
+
+ it = compat_get_it_state(regs);
+
+ /*
+ * If this is the last instruction of the block, wipe the IT
+ * state. Otherwise advance it.
+ */
+ if (!(it & 7))
+ it = 0;
+ else
+ it = (it & 0xe0) | ((it << 1) & 0x1f);
+
+ compat_set_it_state(regs, it);
+}
+
+static void arm64_compat_skip_faulting_instruction(struct pt_regs *regs,
+ unsigned int sz)
+{
+ advance_itstate(regs);
+ arm64_skip_faulting_instruction(regs, sz);
+}
+
+static void compat_cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int reg = (esr & ESR_ELx_CP15_32_ISS_RT_MASK) >> ESR_ELx_CP15_32_ISS_RT_SHIFT;
+
+ pt_regs_write_reg(regs, reg, arch_timer_get_rate());
+ arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static struct sys64_hook cp15_32_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_CP15_32_ISS_SYS_MASK,
+ .esr_val = ESR_ELx_CP15_32_ISS_SYS_CNTFRQ,
+ .handler = compat_cntfrq_read_handler,
+ },
+ {},
+};
+
+static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
+ int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
+ u64 val = arch_counter_get_cntvct();
+
+ pt_regs_write_reg(regs, rt, lower_32_bits(val));
+ pt_regs_write_reg(regs, rt2, upper_32_bits(val));
+ arm64_compat_skip_faulting_instruction(regs, 4);
+}
+
+static struct sys64_hook cp15_64_hooks[] = {
+ {
+ .esr_mask = ESR_ELx_CP15_64_ISS_SYS_MASK,
+ .esr_val = ESR_ELx_CP15_64_ISS_SYS_CNTVCT,
+ .handler = compat_cntvct_read_handler,
+ },
+ {},
+};
+
+asmlinkage void __exception do_cp15instr(unsigned int esr, struct pt_regs *regs)
+{
+ struct sys64_hook *hook, *hook_base;
+
+ if (!cp15_cond_valid(esr, regs)) {
+ /*
+ * There is no T16 variant of a CP access, so we
+ * always advance PC by 4 bytes.
+ */
+ arm64_compat_skip_faulting_instruction(regs, 4);
+ return;
+ }
+
+ switch (ESR_ELx_EC(esr)) {
+ case ESR_ELx_EC_CP15_32:
+ hook_base = cp15_32_hooks;
+ break;
+ case ESR_ELx_EC_CP15_64:
+ hook_base = cp15_64_hooks;
+ break;
+ default:
+ do_undefinstr(regs);
+ return;
+ }
+
+ for (hook = hook_base; hook->handler; hook++)
+ if ((hook->esr_mask & esr) == hook->esr_val) {
+ hook->handler(esr, regs);
+ return;
+ }
+
+ /*
+ * New cp15 instructions may previously have been undefined at
+ * EL0. Fall back to our usual undefined instruction handler
+ * so that we handle these consistently.
+ */
+ do_undefinstr(regs);
+}
+#endif
+
asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
{
struct sys64_hook *hook;
@@ -605,7 +796,6 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
handler[reason], smp_processor_id(), esr,
esr_get_class_string(esr));
- die("Oops - bad mode", regs, 0);
local_daif_mask();
panic("bad mode");
}
@@ -616,19 +806,13 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr)
*/
asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
{
- siginfo_t info;
void __user *pc = (void __user *)instruction_pointer(regs);
- clear_siginfo(&info);
- info.si_signo = SIGILL;
- info.si_errno = 0;
- info.si_code = ILL_ILLOPC;
- info.si_addr = pc;
-
current->thread.fault_address = 0;
current->thread.fault_code = esr;
- arm64_force_sig_info(&info, "Bad EL0 synchronous exception", current);
+ arm64_force_sig_fault(SIGILL, ILL_ILLOPC, pc,
+ "Bad EL0 synchronous exception");
}
#ifdef CONFIG_VMAP_STACK
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 605d1b60469c..03b00007553d 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -138,6 +138,23 @@ SECTIONS
EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */
NOTES
+ . = ALIGN(PAGE_SIZE);
+ idmap_pg_dir = .;
+ . += IDMAP_DIR_SIZE;
+
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+ tramp_pg_dir = .;
+ . += PAGE_SIZE;
+#endif
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ reserved_ttbr0 = .;
+ . += RESERVED_TTBR0_SIZE;
+#endif
+ swapper_pg_dir = .;
+ . += PAGE_SIZE;
+ swapper_pg_end = .;
+
. = ALIGN(SEGMENT_ALIGN);
__init_begin = .;
__inittext_begin = .;
@@ -166,7 +183,6 @@ SECTIONS
INIT_SETUP(16)
INIT_CALLS
CON_INITCALL
- SECURITY_INITCALL
INIT_RAM_FS
*(.init.rodata.* .init.bss) /* from the EFI stub */
}
@@ -216,21 +232,9 @@ SECTIONS
BSS_SECTION(0, 0, 0)
. = ALIGN(PAGE_SIZE);
- idmap_pg_dir = .;
- . += IDMAP_DIR_SIZE;
-
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
- tramp_pg_dir = .;
- . += PAGE_SIZE;
-#endif
-
-#ifdef CONFIG_ARM64_SW_TTBR0_PAN
- reserved_ttbr0 = .;
- . += RESERVED_TTBR0_SIZE;
-#endif
- swapper_pg_dir = .;
- . += SWAPPER_DIR_SIZE;
- swapper_pg_end = .;
+ init_pg_dir = .;
+ . += INIT_DIR_SIZE;
+ init_pg_end = .;
__pecoff_data_size = ABSOLUTE(. - __initdata_begin);
_end = .;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 07256b08226c..dd436a50fce7 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
}
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+ u64 off = core_reg_offset_from_id(reg->id);
+ int size;
+
+ switch (off) {
+ case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+ KVM_REG_ARM_CORE_REG(regs.regs[30]):
+ case KVM_REG_ARM_CORE_REG(regs.sp):
+ case KVM_REG_ARM_CORE_REG(regs.pc):
+ case KVM_REG_ARM_CORE_REG(regs.pstate):
+ case KVM_REG_ARM_CORE_REG(sp_el1):
+ case KVM_REG_ARM_CORE_REG(elr_el1):
+ case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+ KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+ size = sizeof(__u64);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ size = sizeof(__uint128_t);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ size = sizeof(__u32);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (KVM_REG_SIZE(reg->id) == size &&
+ IS_ALIGNED(off, size / sizeof(__u32)))
+ return 0;
+
+ return -EINVAL;
+}
+
static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
return -EFAULT;
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
return -EINVAL;
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
}
if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
- u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
+ u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
switch (mode) {
case PSR_AA32_MODE_USR:
+ if (!system_supports_32bit_el0())
+ return -EINVAL;
+ break;
case PSR_AA32_MODE_FIQ:
case PSR_AA32_MODE_IRQ:
case PSR_AA32_MODE_SVC:
case PSR_AA32_MODE_ABT:
case PSR_AA32_MODE_UND:
+ if (!vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
+ break;
case PSR_MODE_EL0t:
case PSR_MODE_EL1t:
case PSR_MODE_EL1h:
+ if (vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
break;
default:
err = -EINVAL;
@@ -338,15 +391,15 @@ int __attribute_const__ kvm_target_cpu(void)
return KVM_ARM_TARGET_CORTEX_A53;
case ARM_CPU_PART_CORTEX_A57:
return KVM_ARM_TARGET_CORTEX_A57;
- };
+ }
break;
case ARM_CPU_IMP_APM:
switch (part_number) {
case APM_CPU_PART_POTENZA:
return KVM_ARM_TARGET_XGENE_POTENZA;
- };
+ }
break;
- };
+ }
/* Return a default generic target */
return KVM_ARM_TARGET_GENERIC_V8;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index e5e741bfffe1..35a81bebd02b 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -284,6 +284,13 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
*/
run->exit_reason = KVM_EXIT_FAIL_ENTRY;
return 0;
+ case ARM_EXCEPTION_IL:
+ /*
+ * We attempted an illegal exception return. Guest state must
+ * have been corrupted somehow. Give up.
+ */
+ run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ return -EINVAL;
default:
kvm_pr_unimpl("Unsupported exception type: %d",
exception_index);
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index ea9225160786..4576b86a5579 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -65,6 +65,9 @@ __do_hyp_init:
b.lo __kvm_handle_stub_hvc
phys_to_ttbr x4, x0
+alternative_if ARM64_HAS_CNP
+ orr x4, x4, #TTBR_CNP_BIT
+alternative_else_nop_endif
msr ttbr0_el2, x4
mrs x4, tcr_el1
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 2fabc2dc1966..82d1904328ad 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_KVM_ARM_HOST) += switch.o
obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o
obj-$(CONFIG_KVM_ARM_HOST) += tlb.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o
-obj-$(CONFIG_KVM_ARM_HOST) += s2-setup.o
# KVM code is run at a different exception code with a different map, so
# compiler instrumentation that inserts callbacks or checks into the code may
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 24b4fbafe3e4..b1f14f736962 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -162,6 +162,20 @@ el1_error:
mov x0, #ARM_EXCEPTION_EL1_SERROR
b __guest_exit
+el2_sync:
+ /* Check for illegal exception return, otherwise panic */
+ mrs x0, spsr_el2
+
+ /* if this was something else, then panic! */
+ tst x0, #PSR_IL_BIT
+ b.eq __hyp_panic
+
+ /* Let's attempt a recovery from the illegal exception return */
+ get_vcpu_ptr x1, x0
+ mov x0, #ARM_EXCEPTION_IL
+ b __guest_exit
+
+
el2_error:
ldp x0, x1, [sp], #16
@@ -240,7 +254,7 @@ ENTRY(__kvm_hyp_vector)
invalid_vect el2t_fiq_invalid // FIQ EL2t
invalid_vect el2t_error_invalid // Error EL2t
- invalid_vect el2h_sync_invalid // Synchronous EL2h
+ valid_vect el2_sync // Synchronous EL2h
invalid_vect el2h_irq_invalid // IRQ EL2h
invalid_vect el2h_fiq_invalid // FIQ EL2h
valid_vect el2_error // Error EL2h
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
deleted file mode 100644
index 603e1ee83e89..000000000000
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Copyright (C) 2016 - ARM Ltd
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/types.h>
-#include <asm/kvm_arm.h>
-#include <asm/kvm_asm.h>
-#include <asm/kvm_hyp.h>
-
-u32 __hyp_text __init_stage2_translation(void)
-{
- u64 val = VTCR_EL2_FLAGS;
- u64 parange;
- u64 tmp;
-
- /*
- * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS
- * bits in VTCR_EL2. Amusingly, the PARange is 4 bits, while
- * PS is only 3. Fortunately, bit 19 is RES0 in VTCR_EL2...
- */
- parange = read_sysreg(id_aa64mmfr0_el1) & 7;
- if (parange > ID_AA64MMFR0_PARANGE_MAX)
- parange = ID_AA64MMFR0_PARANGE_MAX;
- val |= parange << 16;
-
- /* Compute the actual PARange... */
- switch (parange) {
- case 0:
- parange = 32;
- break;
- case 1:
- parange = 36;
- break;
- case 2:
- parange = 40;
- break;
- case 3:
- parange = 42;
- break;
- case 4:
- parange = 44;
- break;
- case 5:
- default:
- parange = 48;
- break;
- }
-
- /*
- * ... and clamp it to 40 bits, unless we have some braindead
- * HW that implements less than that. In all cases, we'll
- * return that value for the rest of the kernel to decide what
- * to do.
- */
- val |= 64 - (parange > 40 ? 40 : parange);
-
- /*
- * Check the availability of Hardware Access Flag / Dirty Bit
- * Management in ID_AA64MMFR1_EL1 and enable the feature in VTCR_EL2.
- */
- tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_HADBS_SHIFT) & 0xf;
- if (tmp)
- val |= VTCR_EL2_HA;
-
- /*
- * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS
- * bit in VTCR_EL2.
- */
- tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_VMIDBITS_SHIFT) & 0xf;
- val |= (tmp == ID_AA64MMFR1_VMIDBITS_16) ?
- VTCR_EL2_VS_16BIT :
- VTCR_EL2_VS_8BIT;
-
- write_sysreg(val, vtcr_el2);
-
- return parange;
-}
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index d496ef579859..7cc175c88a37 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu)
val = read_sysreg(cpacr_el1);
val |= CPACR_EL1_TTA;
val &= ~CPACR_EL1_ZEN;
- if (!update_fp_enabled(vcpu))
+ if (!update_fp_enabled(vcpu)) {
val &= ~CPACR_EL1_FPEN;
+ __activate_traps_fpsimd32(vcpu);
+ }
write_sysreg(val, cpacr_el1);
@@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu)
val = CPTR_EL2_DEFAULT;
val |= CPTR_EL2_TTA | CPTR_EL2_TZ;
- if (!update_fp_enabled(vcpu))
+ if (!update_fp_enabled(vcpu)) {
val |= CPTR_EL2_TFP;
+ __activate_traps_fpsimd32(vcpu);
+ }
write_sysreg(val, cptr_el2);
}
@@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE))
write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2);
- __activate_traps_fpsimd32(vcpu);
if (has_vhe())
activate_traps_vhe(vcpu);
else
@@ -195,7 +198,7 @@ void deactivate_traps_vhe_put(void)
static void __hyp_text __activate_vm(struct kvm *kvm)
{
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
}
static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu)
@@ -260,7 +263,7 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
return false; /* Translation failed, back to guest */
/* Convert PAR to HPFAR format */
- *hpfar = ((tmp >> 12) & ((1UL << 36) - 1)) << 4;
+ *hpfar = PAR_TO_HPFAR(tmp);
return true;
}
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 9ce223944983..68d6f7c3b237 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -152,8 +152,25 @@ static void __hyp_text __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
static void __hyp_text
__sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt)
{
+ u64 pstate = ctxt->gp_regs.regs.pstate;
+ u64 mode = pstate & PSR_AA32_MODE_MASK;
+
+ /*
+ * Safety check to ensure we're setting the CPU up to enter the guest
+ * in a less privileged mode.
+ *
+ * If we are attempting a return to EL2 or higher in AArch64 state,
+ * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that
+ * we'll take an illegal exception state exception immediately after
+ * the ERET to the guest. Attempts to return to AArch32 Hyp will
+ * result in an illegal exception return because EL2's execution state
+ * is determined by SCR_EL3.RW.
+ */
+ if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t)
+ pstate = PSR_MODE_EL2h | PSR_IL_BIT;
+
write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
- write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
+ write_sysreg_el2(pstate, spsr);
if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN))
write_sysreg_s(ctxt->sys_regs[DISR_EL1], SYS_VDISR_EL2);
@@ -288,3 +305,14 @@ void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu)
vcpu->arch.sysregs_loaded_on_cpu = false;
}
+
+void __hyp_text __kvm_enable_ssbs(void)
+{
+ u64 tmp;
+
+ asm volatile(
+ "mrs %0, sctlr_el2\n"
+ "orr %0, %0, %1\n"
+ "msr sctlr_el2, %0"
+ : "=&r" (tmp) : "L" (SCTLR_ELx_DSSBS));
+}
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index 131c7772703c..4dbd9c69a96d 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -30,7 +30,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
* bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
* let's flip TGE before executing the TLB operation.
*/
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
val = read_sysreg(hcr_el2);
val &= ~HCR_TGE;
write_sysreg(val, hcr_el2);
@@ -39,7 +39,7 @@ static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
{
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ __load_guest_stage2(kvm);
isb();
}
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index e37c78bbe1ca..b72a3dd56204 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -26,6 +26,7 @@
#include <kvm/arm_arch_timer.h>
+#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/ptrace.h>
#include <asm/kvm_arm.h>
@@ -33,6 +34,9 @@
#include <asm/kvm_coproc.h>
#include <asm/kvm_mmu.h>
+/* Maximum phys_shift supported for any VM on this host */
+static u32 kvm_ipa_limit;
+
/*
* ARMv8 Reset Values
*/
@@ -55,12 +59,12 @@ static bool cpu_has_32bit_el1(void)
}
/**
- * kvm_arch_dev_ioctl_check_extension
+ * kvm_arch_vm_ioctl_check_extension
*
* We currently assume that the number of HW registers is uniform
* across all CPUs (see cpuinfo_sanity_check).
*/
-int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
+int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
@@ -82,9 +86,11 @@ int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_SET_GUEST_DEBUG:
case KVM_CAP_VCPU_ATTRIBUTES:
- case KVM_CAP_VCPU_EVENTS:
r = 1;
break;
+ case KVM_CAP_ARM_VM_IPA_SIZE:
+ r = kvm_ipa_limit;
+ break;
default:
r = 0;
}
@@ -133,3 +139,99 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
/* Reset timer */
return kvm_timer_vcpu_reset(vcpu);
}
+
+void kvm_set_ipa_limit(void)
+{
+ unsigned int ipa_max, pa_max, va_max, parange;
+
+ parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 0x7;
+ pa_max = id_aa64mmfr0_parange_to_phys_shift(parange);
+
+ /* Clamp the IPA limit to the PA size supported by the kernel */
+ ipa_max = (pa_max > PHYS_MASK_SHIFT) ? PHYS_MASK_SHIFT : pa_max;
+ /*
+ * Since our stage2 table is dependent on the stage1 page table code,
+ * we must always honor the following condition:
+ *
+ * Number of levels in Stage1 >= Number of levels in Stage2.
+ *
+ * So clamp the ipa limit further down to limit the number of levels.
+ * Since we can concatenate upto 16 tables at entry level, we could
+ * go upto 4bits above the maximum VA addressible with the current
+ * number of levels.
+ */
+ va_max = PGDIR_SHIFT + PAGE_SHIFT - 3;
+ va_max += 4;
+
+ if (va_max < ipa_max)
+ ipa_max = va_max;
+
+ /*
+ * If the final limit is lower than the real physical address
+ * limit of the CPUs, report the reason.
+ */
+ if (ipa_max < pa_max)
+ pr_info("kvm: Limiting the IPA size due to kernel %s Address limit\n",
+ (va_max < pa_max) ? "Virtual" : "Physical");
+
+ WARN(ipa_max < KVM_PHYS_SHIFT,
+ "KVM IPA limit (%d bit) is smaller than default size\n", ipa_max);
+ kvm_ipa_limit = ipa_max;
+ kvm_info("IPA Size Limit: %dbits\n", kvm_ipa_limit);
+}
+
+/*
+ * Configure the VTCR_EL2 for this VM. The VTCR value is common
+ * across all the physical CPUs on the system. We use system wide
+ * sanitised values to fill in different fields, except for Hardware
+ * Management of Access Flags. HA Flag is set unconditionally on
+ * all CPUs, as it is safe to run with or without the feature and
+ * the bit is RES0 on CPUs that don't support it.
+ */
+int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
+{
+ u64 vtcr = VTCR_EL2_FLAGS;
+ u32 parange, phys_shift;
+ u8 lvls;
+
+ if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+ return -EINVAL;
+
+ phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
+ if (phys_shift) {
+ if (phys_shift > kvm_ipa_limit ||
+ phys_shift < 32)
+ return -EINVAL;
+ } else {
+ phys_shift = KVM_PHYS_SHIFT;
+ }
+
+ parange = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1) & 7;
+ if (parange > ID_AA64MMFR0_PARANGE_MAX)
+ parange = ID_AA64MMFR0_PARANGE_MAX;
+ vtcr |= parange << VTCR_EL2_PS_SHIFT;
+
+ vtcr |= VTCR_EL2_T0SZ(phys_shift);
+ /*
+ * Use a minimum 2 level page table to prevent splitting
+ * host PMD huge pages at stage2.
+ */
+ lvls = stage2_pgtable_levels(phys_shift);
+ if (lvls < 2)
+ lvls = 2;
+ vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls);
+
+ /*
+ * Enable the Hardware Access Flag management, unconditionally
+ * on all CPUs. The features is RES0 on CPUs without the support
+ * and must be ignored by the CPUs.
+ */
+ vtcr |= VTCR_EL2_HA;
+
+ /* Set the vmid bits */
+ vtcr |= (kvm_get_vmid_bits() == 16) ?
+ VTCR_EL2_VS_16BIT :
+ VTCR_EL2_VS_8BIT;
+ kvm->arch.vtcr = vtcr;
+ return 0;
+}
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 68755fd70dcf..69ff9887f724 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -12,7 +12,7 @@ lib-y := clear_user.o delay.o copy_from_user.o \
# when supported by the CPU. Result and argument registers are handled
# correctly, based on the function prototype.
lib-$(CONFIG_ARM64_LSE_ATOMICS) += atomic_ll_sc.o
-CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \
+CFLAGS_atomic_ll_sc.o := -ffixed-x1 -ffixed-x2 \
-ffixed-x3 -ffixed-x4 -ffixed-x5 -ffixed-x6 \
-ffixed-x7 -fcall-saved-x8 -fcall-saved-x9 \
-fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \
@@ -25,3 +25,5 @@ KCOV_INSTRUMENT_atomic_ll_sc.o := n
UBSAN_SANITIZE_atomic_ll_sc.o := n
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
+
+obj-$(CONFIG_CRC32) += crc32.o
diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
new file mode 100644
index 000000000000..5bc1e85b4e1c
--- /dev/null
+++ b/arch/arm64/lib/crc32.S
@@ -0,0 +1,60 @@
+/*
+ * Accelerated CRC32(C) using AArch64 CRC instructions
+ *
+ * Copyright (C) 2016 - 2018 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative.h>
+#include <asm/assembler.h>
+
+ .cpu generic+crc
+
+ .macro __crc32, c
+0: subs x2, x2, #16
+ b.mi 8f
+ ldp x3, x4, [x1], #16
+CPU_BE( rev x3, x3 )
+CPU_BE( rev x4, x4 )
+ crc32\c\()x w0, w0, x3
+ crc32\c\()x w0, w0, x4
+ b.ne 0b
+ ret
+
+8: tbz x2, #3, 4f
+ ldr x3, [x1], #8
+CPU_BE( rev x3, x3 )
+ crc32\c\()x w0, w0, x3
+4: tbz x2, #2, 2f
+ ldr w3, [x1], #4
+CPU_BE( rev w3, w3 )
+ crc32\c\()w w0, w0, w3
+2: tbz x2, #1, 1f
+ ldrh w3, [x1], #2
+CPU_BE( rev16 w3, w3 )
+ crc32\c\()h w0, w0, w3
+1: tbz x2, #0, 0f
+ ldrb w3, [x1]
+ crc32\c\()b w0, w0, w3
+0: ret
+ .endm
+
+ .align 5
+ENTRY(crc32_le)
+alternative_if_not ARM64_HAS_CRC32
+ b crc32_le_base
+alternative_else_nop_endif
+ __crc32
+ENDPROC(crc32_le)
+
+ .align 5
+ENTRY(__crc32c_le)
+alternative_if_not ARM64_HAS_CRC32
+ b __crc32c_le_base
+alternative_else_nop_endif
+ __crc32 c
+ENDPROC(__crc32c_le)
diff --git a/arch/arm64/lib/memchr.S b/arch/arm64/lib/memchr.S
index 4444c1d25f4b..0f164a4baf52 100644
--- a/arch/arm64/lib/memchr.S
+++ b/arch/arm64/lib/memchr.S
@@ -30,7 +30,7 @@
* Returns:
* x0 - address of first occurrence of 'c' or 0
*/
-ENTRY(memchr)
+WEAK(memchr)
and w1, w1, #0xff
1: subs x2, x2, #1
b.mi 2f
diff --git a/arch/arm64/lib/memcmp.S b/arch/arm64/lib/memcmp.S
index 2a4e239bd17a..fb295f52e9f8 100644
--- a/arch/arm64/lib/memcmp.S
+++ b/arch/arm64/lib/memcmp.S
@@ -58,7 +58,7 @@ pos .req x11
limit_wd .req x12
mask .req x13
-ENTRY(memcmp)
+WEAK(memcmp)
cbz limit, .Lret0
eor tmp1, src1, src2
tst tmp1, #7
diff --git a/arch/arm64/lib/strchr.S b/arch/arm64/lib/strchr.S
index dae0cf5591f9..7c83091d1bcd 100644
--- a/arch/arm64/lib/strchr.S
+++ b/arch/arm64/lib/strchr.S
@@ -29,7 +29,7 @@
* Returns:
* x0 - address of first occurrence of 'c' or 0
*/
-ENTRY(strchr)
+WEAK(strchr)
and w1, w1, #0xff
1: ldrb w2, [x0], #1
cmp w2, w1
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 471fe61760ef..7d5d15398bfb 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -60,7 +60,7 @@ tmp3 .req x9
zeroones .req x10
pos .req x11
-ENTRY(strcmp)
+WEAK(strcmp)
eor tmp1, src1, src2
mov zeroones, #REP8_01
tst tmp1, #7
diff --git a/arch/arm64/lib/strlen.S b/arch/arm64/lib/strlen.S
index 55ccc8e24c08..8e0b14205dcb 100644
--- a/arch/arm64/lib/strlen.S
+++ b/arch/arm64/lib/strlen.S
@@ -56,7 +56,7 @@ pos .req x12
#define REP8_7f 0x7f7f7f7f7f7f7f7f
#define REP8_80 0x8080808080808080
-ENTRY(strlen)
+WEAK(strlen)
mov zeroones, #REP8_01
bic src, srcin, #15
ands tmp1, srcin, #15
diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S
index e267044761c6..66bd145935d9 100644
--- a/arch/arm64/lib/strncmp.S
+++ b/arch/arm64/lib/strncmp.S
@@ -64,7 +64,7 @@ limit_wd .req x13
mask .req x14
endloop .req x15
-ENTRY(strncmp)
+WEAK(strncmp)
cbz limit, .Lret0
eor tmp1, src1, src2
mov zeroones, #REP8_01
diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S
index eae38da6e0bb..355be04441fe 100644
--- a/arch/arm64/lib/strnlen.S
+++ b/arch/arm64/lib/strnlen.S
@@ -59,7 +59,7 @@ limit_wd .req x14
#define REP8_7f 0x7f7f7f7f7f7f7f7f
#define REP8_80 0x8080808080808080
-ENTRY(strnlen)
+WEAK(strnlen)
cbz limit, .Lhit_limit
mov zeroones, #REP8_01
bic src, srcin, #15
diff --git a/arch/arm64/lib/strrchr.S b/arch/arm64/lib/strrchr.S
index f8e2784d5752..ea84924d5990 100644
--- a/arch/arm64/lib/strrchr.S
+++ b/arch/arm64/lib/strrchr.S
@@ -29,7 +29,7 @@
* Returns:
* x0 - address of last occurrence of 'c' or 0
*/
-ENTRY(strrchr)
+WEAK(strrchr)
mov x3, #0
and w1, w1, #0xff
1: ldrb w2, [x0], #1
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index c127f94da8e2..1f0ea2facf24 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -88,7 +88,7 @@ void verify_cpu_asid_bits(void)
}
}
-static void flush_context(unsigned int cpu)
+static void flush_context(void)
{
int i;
u64 asid;
@@ -142,7 +142,7 @@ static bool check_update_reserved_asid(u64 asid, u64 newasid)
return hit;
}
-static u64 new_context(struct mm_struct *mm, unsigned int cpu)
+static u64 new_context(struct mm_struct *mm)
{
static u32 cur_idx = 1;
u64 asid = atomic64_read(&mm->context.id);
@@ -180,7 +180,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
/* We're out of ASIDs, so increment the global generation count */
generation = atomic64_add_return_relaxed(ASID_FIRST_VERSION,
&asid_generation);
- flush_context(cpu);
+ flush_context();
/* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
@@ -196,6 +196,9 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
unsigned long flags;
u64 asid, old_active_asid;
+ if (system_supports_cnp())
+ cpu_set_reserved_ttbr0();
+
asid = atomic64_read(&mm->context.id);
/*
@@ -223,7 +226,7 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
/* Check that our ASID belongs to the current generation. */
asid = atomic64_read(&mm->context.id);
if ((asid ^ atomic64_read(&asid_generation)) >> asid_bits) {
- asid = new_context(mm, cpu);
+ asid = new_context(mm);
atomic64_set(&mm->context.id, asid);
}
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 072c51fb07d7..d190612b8f33 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -25,6 +25,7 @@
#include <linux/slab.h>
#include <linux/genalloc.h>
#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
#include <linux/dma-contiguous.h>
#include <linux/vmalloc.h>
#include <linux/swiotlb.h>
@@ -32,16 +33,6 @@
#include <asm/cacheflush.h>
-static int swiotlb __ro_after_init;
-
-static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
- bool coherent)
-{
- if (!coherent || (attrs & DMA_ATTR_WRITE_COMBINE))
- return pgprot_writecombine(prot);
- return prot;
-}
-
static struct gen_pool *atomic_pool __ro_after_init;
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
@@ -91,18 +82,16 @@ static int __free_from_pool(void *start, size_t size)
return 1;
}
-static void *__dma_alloc(struct device *dev, size_t size,
- dma_addr_t *dma_handle, gfp_t flags,
- unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t flags, unsigned long attrs)
{
struct page *page;
void *ptr, *coherent_ptr;
- bool coherent = is_device_dma_coherent(dev);
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false);
+ pgprot_t prot = pgprot_writecombine(PAGE_KERNEL);
size = PAGE_ALIGN(size);
- if (!coherent && !gfpflags_allow_blocking(flags)) {
+ if (!gfpflags_allow_blocking(flags)) {
struct page *page = NULL;
void *addr = __alloc_from_pool(size, &page, flags);
@@ -112,14 +101,10 @@ static void *__dma_alloc(struct device *dev, size_t size,
return addr;
}
- ptr = swiotlb_alloc(dev, size, dma_handle, flags, attrs);
+ ptr = dma_direct_alloc_pages(dev, size, dma_handle, flags, attrs);
if (!ptr)
goto no_mem;
- /* no need for non-cacheable mapping if coherent */
- if (coherent)
- return ptr;
-
/* remove any dirty cache lines on the kernel alias */
__dma_flush_area(ptr, size);
@@ -133,130 +118,57 @@ static void *__dma_alloc(struct device *dev, size_t size,
return coherent_ptr;
no_map:
- swiotlb_free(dev, size, ptr, *dma_handle, attrs);
+ dma_direct_free_pages(dev, size, ptr, *dma_handle, attrs);
no_mem:
return NULL;
}
-static void __dma_free(struct device *dev, size_t size,
- void *vaddr, dma_addr_t dma_handle,
- unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle, unsigned long attrs)
{
- void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+ if (!__free_from_pool(vaddr, PAGE_ALIGN(size))) {
+ void *kaddr = phys_to_virt(dma_to_phys(dev, dma_handle));
- size = PAGE_ALIGN(size);
-
- if (!is_device_dma_coherent(dev)) {
- if (__free_from_pool(vaddr, size))
- return;
vunmap(vaddr);
+ dma_direct_free_pages(dev, size, kaddr, dma_handle, attrs);
}
- swiotlb_free(dev, size, swiotlb_addr, dma_handle, attrs);
}
-static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
- unsigned long offset, size_t size,
- enum dma_data_direction dir,
- unsigned long attrs)
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+ dma_addr_t dma_addr)
{
- dma_addr_t dev_addr;
-
- dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
- if (!is_device_dma_coherent(dev) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
- __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
-
- return dev_addr;
-}
-
-
-static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
- size_t size, enum dma_data_direction dir,
- unsigned long attrs)
-{
- if (!is_device_dma_coherent(dev) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
- __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
- swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+ return __phys_to_pfn(dma_to_phys(dev, dma_addr));
}
-static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
- int nelems, enum dma_data_direction dir,
- unsigned long attrs)
+pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
+ unsigned long attrs)
{
- struct scatterlist *sg;
- int i, ret;
-
- ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
- if (!is_device_dma_coherent(dev) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
- for_each_sg(sgl, sg, ret, i)
- __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
- sg->length, dir);
-
- return ret;
-}
-
-static void __swiotlb_unmap_sg_attrs(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir,
- unsigned long attrs)
-{
- struct scatterlist *sg;
- int i;
-
- if (!is_device_dma_coherent(dev) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
- for_each_sg(sgl, sg, nelems, i)
- __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
- sg->length, dir);
- swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+ if (!dev_is_dma_coherent(dev) || (attrs & DMA_ATTR_WRITE_COMBINE))
+ return pgprot_writecombine(prot);
+ return prot;
}
-static void __swiotlb_sync_single_for_cpu(struct device *dev,
- dma_addr_t dev_addr, size_t size,
- enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- if (!is_device_dma_coherent(dev))
- __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
- swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+ __dma_map_area(phys_to_virt(paddr), size, dir);
}
-static void __swiotlb_sync_single_for_device(struct device *dev,
- dma_addr_t dev_addr, size_t size,
- enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+ size_t size, enum dma_data_direction dir)
{
- swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
- if (!is_device_dma_coherent(dev))
- __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+ __dma_unmap_area(phys_to_virt(paddr), size, dir);
}
-static void __swiotlb_sync_sg_for_cpu(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
+static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
+ struct page *page, size_t size)
{
- struct scatterlist *sg;
- int i;
-
- if (!is_device_dma_coherent(dev))
- for_each_sg(sgl, sg, nelems, i)
- __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
- sg->length, dir);
- swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
-}
+ int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-static void __swiotlb_sync_sg_for_device(struct device *dev,
- struct scatterlist *sgl, int nelems,
- enum dma_data_direction dir)
-{
- struct scatterlist *sg;
- int i;
+ if (!ret)
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
- swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
- if (!is_device_dma_coherent(dev))
- for_each_sg(sgl, sg, nelems, i)
- __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
- sg->length, dir);
+ return ret;
}
static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
@@ -277,74 +189,6 @@ static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
return ret;
}
-static int __swiotlb_mmap(struct device *dev,
- struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs)
-{
- int ret;
- unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
-
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
- is_device_dma_coherent(dev));
-
- if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
- return ret;
-
- return __swiotlb_mmap_pfn(vma, pfn, size);
-}
-
-static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
- struct page *page, size_t size)
-{
- int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
-
- if (!ret)
- sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
-
- return ret;
-}
-
-static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t handle, size_t size,
- unsigned long attrs)
-{
- struct page *page = phys_to_page(dma_to_phys(dev, handle));
-
- return __swiotlb_get_sgtable_page(sgt, page, size);
-}
-
-static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
-{
- if (swiotlb)
- return swiotlb_dma_supported(hwdev, mask);
- return 1;
-}
-
-static int __swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t addr)
-{
- if (swiotlb)
- return swiotlb_dma_mapping_error(hwdev, addr);
- return 0;
-}
-
-static const struct dma_map_ops arm64_swiotlb_dma_ops = {
- .alloc = __dma_alloc,
- .free = __dma_free,
- .mmap = __swiotlb_mmap,
- .get_sgtable = __swiotlb_get_sgtable,
- .map_page = __swiotlb_map_page,
- .unmap_page = __swiotlb_unmap_page,
- .map_sg = __swiotlb_map_sg_attrs,
- .unmap_sg = __swiotlb_unmap_sg_attrs,
- .sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
- .sync_single_for_device = __swiotlb_sync_single_for_device,
- .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
- .sync_sg_for_device = __swiotlb_sync_sg_for_device,
- .dma_supported = __swiotlb_dma_supported,
- .mapping_error = __swiotlb_dma_mapping_error,
-};
-
static int __init atomic_pool_init(void)
{
pgprot_t prot = __pgprot(PROT_NORMAL_NC);
@@ -500,10 +344,6 @@ EXPORT_SYMBOL(dummy_dma_ops);
static int __init arm64_dma_init(void)
{
- if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
- swiotlb = 1;
-
WARN_TAINT(ARCH_DMA_MINALIGN < cache_line_size(),
TAINT_CPU_OUT_OF_SPEC,
"ARCH_DMA_MINALIGN smaller than CTR_EL0.CWG (%d < %d)",
@@ -528,7 +368,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
dma_addr_t *handle, gfp_t gfp,
unsigned long attrs)
{
- bool coherent = is_device_dma_coherent(dev);
+ bool coherent = dev_is_dma_coherent(dev);
int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
size_t iosize = size;
void *addr;
@@ -569,7 +409,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
addr = NULL;
}
} else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
struct page *page;
page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
@@ -596,7 +436,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
size >> PAGE_SHIFT);
}
} else {
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ pgprot_t prot = arch_dma_mmap_pgprot(dev, PAGE_KERNEL, attrs);
struct page **pages;
pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
@@ -658,8 +498,7 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
struct vm_struct *area;
int ret;
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
- is_device_dma_coherent(dev));
+ vma->vm_page_prot = arch_dma_mmap_pgprot(dev, vma->vm_page_prot, attrs);
if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
@@ -709,11 +548,11 @@ static void __iommu_sync_single_for_cpu(struct device *dev,
{
phys_addr_t phys;
- if (is_device_dma_coherent(dev))
+ if (dev_is_dma_coherent(dev))
return;
- phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
- __dma_unmap_area(phys_to_virt(phys), size, dir);
+ phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
+ arch_sync_dma_for_cpu(dev, phys, size, dir);
}
static void __iommu_sync_single_for_device(struct device *dev,
@@ -722,11 +561,11 @@ static void __iommu_sync_single_for_device(struct device *dev,
{
phys_addr_t phys;
- if (is_device_dma_coherent(dev))
+ if (dev_is_dma_coherent(dev))
return;
- phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr);
- __dma_map_area(phys_to_virt(phys), size, dir);
+ phys = iommu_iova_to_phys(iommu_get_dma_domain(dev), dev_addr);
+ arch_sync_dma_for_device(dev, phys, size, dir);
}
static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
@@ -734,13 +573,13 @@ static dma_addr_t __iommu_map_page(struct device *dev, struct page *page,
enum dma_data_direction dir,
unsigned long attrs)
{
- bool coherent = is_device_dma_coherent(dev);
+ bool coherent = dev_is_dma_coherent(dev);
int prot = dma_info_to_prot(dir, coherent, attrs);
dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot);
- if (!iommu_dma_mapping_error(dev, dev_addr) &&
- (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
- __iommu_sync_single_for_device(dev, dev_addr, size, dir);
+ if (!coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ !iommu_dma_mapping_error(dev, dev_addr))
+ __dma_map_area(page_address(page) + offset, size, dir);
return dev_addr;
}
@@ -762,11 +601,11 @@ static void __iommu_sync_sg_for_cpu(struct device *dev,
struct scatterlist *sg;
int i;
- if (is_device_dma_coherent(dev))
+ if (dev_is_dma_coherent(dev))
return;
for_each_sg(sgl, sg, nelems, i)
- __dma_unmap_area(sg_virt(sg), sg->length, dir);
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
}
static void __iommu_sync_sg_for_device(struct device *dev,
@@ -776,18 +615,18 @@ static void __iommu_sync_sg_for_device(struct device *dev,
struct scatterlist *sg;
int i;
- if (is_device_dma_coherent(dev))
+ if (dev_is_dma_coherent(dev))
return;
for_each_sg(sgl, sg, nelems, i)
- __dma_map_area(sg_virt(sg), sg->length, dir);
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
}
static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
int nelems, enum dma_data_direction dir,
unsigned long attrs)
{
- bool coherent = is_device_dma_coherent(dev);
+ bool coherent = dev_is_dma_coherent(dev);
if ((attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0)
__iommu_sync_sg_for_device(dev, sgl, nelems, dir);
@@ -879,9 +718,9 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
const struct iommu_ops *iommu, bool coherent)
{
if (!dev->dma_ops)
- dev->dma_ops = &arm64_swiotlb_dma_ops;
+ dev->dma_ops = &swiotlb_dma_ops;
- dev->archdata.dma_coherent = coherent;
+ dev->dma_coherent = coherent;
__iommu_setup_dma_ops(dev, dma_base, size, iommu);
#ifdef CONFIG_XEN
diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c
index 65dfc8571bf8..fcb1f2a6d7c6 100644
--- a/arch/arm64/mm/dump.c
+++ b/arch/arm64/mm/dump.c
@@ -36,8 +36,8 @@ static const struct addr_marker address_markers[] = {
#endif
{ MODULES_VADDR, "Modules start" },
{ MODULES_END, "Modules end" },
- { VMALLOC_START, "vmalloc() Area" },
- { VMALLOC_END, "vmalloc() End" },
+ { VMALLOC_START, "vmalloc() area" },
+ { VMALLOC_END, "vmalloc() end" },
{ FIXADDR_START, "Fixmap start" },
{ FIXADDR_TOP, "Fixmap end" },
{ PCI_IO_START, "PCI I/O start" },
@@ -46,7 +46,7 @@ static const struct addr_marker address_markers[] = {
{ VMEMMAP_START, "vmemmap start" },
{ VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" },
#endif
- { PAGE_OFFSET, "Linear Mapping" },
+ { PAGE_OFFSET, "Linear mapping" },
{ -1, NULL },
};
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 50b30ff30de4..7d9571f4ae3d 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -37,6 +37,7 @@
#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
+#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/sysreg.h>
@@ -56,10 +57,16 @@ struct fault_info {
};
static const struct fault_info fault_info[];
+static struct fault_info debug_fault_info[];
static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
{
- return fault_info + (esr & 63);
+ return fault_info + (esr & ESR_ELx_FSC);
+}
+
+static inline const struct fault_info *esr_to_debug_fault_info(unsigned int esr)
+{
+ return debug_fault_info + DBG_ESR_EVT(esr);
}
#ifdef CONFIG_KPROBES
@@ -235,9 +242,8 @@ static bool is_el1_instruction_abort(unsigned int esr)
return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
}
-static inline bool is_el1_permission_fault(unsigned int esr,
- struct pt_regs *regs,
- unsigned long addr)
+static inline bool is_el1_permission_fault(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs)
{
unsigned int ec = ESR_ELx_EC(esr);
unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
@@ -283,7 +289,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
if (!is_el1_instruction_abort(esr) && fixup_exception(regs))
return;
- if (is_el1_permission_fault(esr, regs, addr)) {
+ if (is_el1_permission_fault(addr, esr, regs)) {
if (esr & ESR_ELx_WNR)
msg = "write to read-only memory";
else
@@ -297,9 +303,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
die_kernel_fault(msg, addr, esr, regs);
}
-static void __do_user_fault(struct siginfo *info, unsigned int esr)
+static void set_thread_esr(unsigned long address, unsigned int esr)
{
- current->thread.fault_address = (unsigned long)info->si_addr;
+ current->thread.fault_address = address;
/*
* If the faulting address is in the kernel, we must sanitize the ESR.
@@ -352,7 +358,6 @@ static void __do_user_fault(struct siginfo *info, unsigned int esr)
}
current->thread.fault_code = esr;
- arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
}
static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
@@ -363,14 +368,10 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
*/
if (user_mode(regs)) {
const struct fault_info *inf = esr_to_fault_info(esr);
- struct siginfo si;
-
- clear_siginfo(&si);
- si.si_signo = inf->sig;
- si.si_code = inf->code;
- si.si_addr = (void __user *)addr;
- __do_user_fault(&si, esr);
+ set_thread_esr(addr, esr);
+ arm64_force_sig_fault(inf->sig, inf->code, (void __user *)addr,
+ inf->name);
} else {
__do_kernel_fault(addr, esr, regs);
}
@@ -424,9 +425,9 @@ static bool is_el0_instruction_abort(unsigned int esr)
static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
+ const struct fault_info *inf;
struct task_struct *tsk;
struct mm_struct *mm;
- struct siginfo si;
vm_fault_t fault, major = 0;
unsigned long vm_flags = VM_READ | VM_WRITE;
unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -454,7 +455,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
mm_flags |= FAULT_FLAG_WRITE;
}
- if (addr < TASK_SIZE && is_el1_permission_fault(esr, regs, addr)) {
+ if (addr < TASK_SIZE && is_el1_permission_fault(addr, esr, regs)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die_kernel_fault("access to user memory with fs=KERNEL_DS",
@@ -562,37 +563,35 @@ retry:
return 0;
}
- clear_siginfo(&si);
- si.si_addr = (void __user *)addr;
-
+ inf = esr_to_fault_info(esr);
+ set_thread_esr(addr, esr);
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to successfully fix up
* this page fault.
*/
- si.si_signo = SIGBUS;
- si.si_code = BUS_ADRERR;
- } else if (fault & VM_FAULT_HWPOISON_LARGE) {
- unsigned int hindex = VM_FAULT_GET_HINDEX(fault);
-
- si.si_signo = SIGBUS;
- si.si_code = BUS_MCEERR_AR;
- si.si_addr_lsb = hstate_index_to_shift(hindex);
- } else if (fault & VM_FAULT_HWPOISON) {
- si.si_signo = SIGBUS;
- si.si_code = BUS_MCEERR_AR;
- si.si_addr_lsb = PAGE_SHIFT;
+ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)addr,
+ inf->name);
+ } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) {
+ unsigned int lsb;
+
+ lsb = PAGE_SHIFT;
+ if (fault & VM_FAULT_HWPOISON_LARGE)
+ lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault));
+
+ arm64_force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr, lsb,
+ inf->name);
} else {
/*
* Something tried to access memory that isn't in our memory
* map.
*/
- si.si_signo = SIGSEGV;
- si.si_code = fault == VM_FAULT_BADACCESS ?
- SEGV_ACCERR : SEGV_MAPERR;
+ arm64_force_sig_fault(SIGSEGV,
+ fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR,
+ (void __user *)addr,
+ inf->name);
}
- __do_user_fault(&si, esr);
return 0;
no_context:
@@ -625,8 +624,8 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
- struct siginfo info;
const struct fault_info *inf;
+ void __user *siaddr;
inf = esr_to_fault_info(esr);
@@ -645,15 +644,11 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs)
nmi_exit();
}
- clear_siginfo(&info);
- info.si_signo = inf->sig;
- info.si_errno = 0;
- info.si_code = inf->code;
if (esr & ESR_ELx_FnV)
- info.si_addr = NULL;
+ siaddr = NULL;
else
- info.si_addr = (void __user *)addr;
- arm64_notify_die(inf->name, regs, &info, esr);
+ siaddr = (void __user *)addr;
+ arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr);
return 0;
}
@@ -734,7 +729,6 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
const struct fault_info *inf = esr_to_fault_info(esr);
- struct siginfo info;
if (!inf->fn(addr, esr, regs))
return;
@@ -745,12 +739,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
show_pte(addr);
}
- clear_siginfo(&info);
- info.si_signo = inf->sig;
- info.si_errno = 0;
- info.si_code = inf->code;
- info.si_addr = (void __user *)addr;
- arm64_notify_die(inf->name, regs, &info, esr);
+ arm64_notify_die(inf->name, regs,
+ inf->sig, inf->code, (void __user *)addr, esr);
}
asmlinkage void __exception do_el0_irq_bp_hardening(void)
@@ -771,7 +761,7 @@ asmlinkage void __exception do_el0_ia_bp_hardening(unsigned long addr,
if (addr > TASK_SIZE)
arm64_apply_bp_hardening();
- local_irq_enable();
+ local_daif_restore(DAIF_PROCCTX);
do_mem_abort(addr, esr, regs);
}
@@ -780,20 +770,14 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
unsigned int esr,
struct pt_regs *regs)
{
- struct siginfo info;
-
if (user_mode(regs)) {
if (instruction_pointer(regs) > TASK_SIZE)
arm64_apply_bp_hardening();
- local_irq_enable();
+ local_daif_restore(DAIF_PROCCTX);
}
- clear_siginfo(&info);
- info.si_signo = SIGBUS;
- info.si_errno = 0;
- info.si_code = BUS_ADRALN;
- info.si_addr = (void __user *)addr;
- arm64_notify_die("SP/PC alignment exception", regs, &info, esr);
+ arm64_notify_die("SP/PC alignment exception", regs,
+ SIGBUS, BUS_ADRALN, (void __user *)addr, esr);
}
int __init early_brk64(unsigned long addr, unsigned int esr,
@@ -831,7 +815,7 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
+ const struct fault_info *inf = esr_to_debug_fault_info(esr);
int rv;
/*
@@ -847,14 +831,8 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
if (!inf->fn(addr, esr, regs)) {
rv = 1;
} else {
- struct siginfo info;
-
- clear_siginfo(&info);
- info.si_signo = inf->sig;
- info.si_errno = 0;
- info.si_code = inf->code;
- info.si_addr = (void __user *)addr;
- arm64_notify_die(inf->name, regs, &info, esr);
+ arm64_notify_die(inf->name, regs,
+ inf->sig, inf->code, (void __user *)addr, esr);
rv = 0;
}
@@ -864,17 +842,3 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
return rv;
}
NOKPROBE_SYMBOL(do_debug_exception);
-
-#ifdef CONFIG_ARM64_PAN
-void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
-{
- /*
- * We modify PSTATE. This won't work from irq context as the PSTATE
- * is discarded once we return from the exception.
- */
- WARN_ON_ONCE(in_interrupt());
-
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
- asm(SET_PSTATE_PAN(1));
-}
-#endif /* CONFIG_ARM64_PAN */
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 192b3ba07075..f58ea503ad01 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
/*
* If HW_AFDBM is enabled, then the HW could turn on
- * the dirty bit for any page in the set, so check
- * them all. All hugetlb entries are already young.
+ * the dirty or accessed bit for any page in the set,
+ * so check them all.
*/
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
}
if (valid) {
@@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+ int i;
+
+ if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+ return 1;
+
+ for (i = 0; i < ncontig; i++) {
+ pte_t orig_pte = huge_ptep_get(ptep + i);
+
+ if (pte_dirty(pte) != pte_dirty(orig_pte))
+ return 1;
+
+ if (pte_young(pte) != pte_young(orig_pte))
+ return 1;
+ }
+
+ return 0;
+}
+
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, changed = 0;
+ int ncontig, i;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
@@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
+ if (!__cont_access_flags_changed(ptep, pte, ncontig))
+ return 0;
+
orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
- if (!pte_same(orig_pte, pte))
- changed = 1;
- /* Make sure we don't lose the dirty state */
+ /* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
+ 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_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
- return changed;
+ return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 787e27964ab9..3cf87341859f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -284,7 +284,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
#endif /* CONFIG_NUMA */
-#ifdef CONFIG_HAVE_ARCH_PFN_VALID
int pfn_valid(unsigned long pfn)
{
phys_addr_t addr = pfn << PAGE_SHIFT;
@@ -294,7 +293,6 @@ int pfn_valid(unsigned long pfn)
return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_valid);
-#endif
#ifndef CONFIG_SPARSEMEM
static void __init arm64_memory_present(void)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 12145874c02b..fccb1a6f8c6f 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -192,7 +192,7 @@ void __init kasan_init(void)
/*
* We are going to perform proper setup of shadow memory.
- * At first we should unmap early shadow (clear_pgds() call bellow).
+ * At first we should unmap early shadow (clear_pgds() call below).
* However, instrumented code couldn't execute without shadow memory.
* tmp_pg_dir used to keep early shadow mapped until full shadow
* setup will be finished.
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 65f86271f02b..9498c15b847b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -67,6 +67,24 @@ static pte_t bm_pte[PTRS_PER_PTE] __page_aligned_bss;
static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
+static DEFINE_SPINLOCK(swapper_pgdir_lock);
+
+void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ pgd_t *fixmap_pgdp;
+
+ spin_lock(&swapper_pgdir_lock);
+ fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp));
+ WRITE_ONCE(*fixmap_pgdp, pgd);
+ /*
+ * We need dsb(ishst) here to ensure the page-table-walker sees
+ * our new entry before set_p?d() returns. The fixmap's
+ * flush_tlb_kernel_range() via clear_fixmap() does this for us.
+ */
+ pgd_clear_fixmap();
+ spin_unlock(&swapper_pgdir_lock);
+}
+
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
{
@@ -629,34 +647,18 @@ static void __init map_kernel(pgd_t *pgdp)
*/
void __init paging_init(void)
{
- phys_addr_t pgd_phys = early_pgtable_alloc();
- pgd_t *pgdp = pgd_set_fixmap(pgd_phys);
+ pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir));
map_kernel(pgdp);
map_mem(pgdp);
- /*
- * We want to reuse the original swapper_pg_dir so we don't have to
- * communicate the new address to non-coherent secondaries in
- * secondary_entry, and so cpu_switch_mm can generate the address with
- * adrp+add rather than a load from some global variable.
- *
- * To do this we need to go via a temporary pgd.
- */
- cpu_replace_ttbr1(__va(pgd_phys));
- memcpy(swapper_pg_dir, pgdp, PGD_SIZE);
- cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
-
pgd_clear_fixmap();
- memblock_free(pgd_phys, PAGE_SIZE);
- /*
- * We only reuse the PGD from the swapper_pg_dir, not the pud + pmd
- * allocated with it.
- */
- memblock_free(__pa_symbol(swapper_pg_dir) + PAGE_SIZE,
- __pa_symbol(swapper_pg_end) - __pa_symbol(swapper_pg_dir)
- - PAGE_SIZE);
+ cpu_replace_ttbr1(lm_alias(swapper_pg_dir));
+ init_mm.pgd = swapper_pg_dir;
+
+ memblock_free(__pa_symbol(init_pg_dir),
+ __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir));
}
/*
@@ -985,8 +987,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
pmd = READ_ONCE(*pmdp);
- /* No-op for empty entry and WARN_ON for valid entry */
- if (!pmd_present(pmd) || !pmd_table(pmd)) {
+ if (!pmd_present(pmd))
+ return 1;
+ if (!pmd_table(pmd)) {
VM_WARN_ON(!pmd_table(pmd));
return 1;
}
@@ -1007,8 +1010,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
pud = READ_ONCE(*pudp);
- /* No-op for empty entry and WARN_ON for valid entry */
- if (!pud_present(pud) || !pud_table(pud)) {
+ if (!pud_present(pud))
+ return 1;
+ if (!pud_table(pud)) {
VM_WARN_ON(!pud_table(pud));
return 1;
}
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 146c04ceaa51..d7b66fc5e1c5 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -391,7 +391,6 @@ static int __init numa_init(int (*init_func)(void))
nodes_clear(numa_nodes_parsed);
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
- numa_free_distance();
ret = numa_alloc_distance();
if (ret < 0)
@@ -399,20 +398,24 @@ static int __init numa_init(int (*init_func)(void))
ret = init_func();
if (ret < 0)
- return ret;
+ goto out_free_distance;
if (nodes_empty(numa_nodes_parsed)) {
pr_info("No NUMA configuration found\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_free_distance;
}
ret = numa_register_nodes();
if (ret < 0)
- return ret;
+ goto out_free_distance;
setup_node_to_cpumask_map();
return 0;
+out_free_distance:
+ numa_free_distance();
+ return ret;
}
/**
@@ -432,7 +435,7 @@ static int __init dummy_numa_init(void)
if (numa_off)
pr_info("NUMA disabled\n"); /* Forced off on command line. */
pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
- 0LLU, PFN_PHYS(max_pfn) - 1);
+ memblock_start_of_DRAM(), memblock_end_of_DRAM() - 1);
for_each_memblock(memory, mblk) {
ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 03646e6a2ef4..2c75b0b903ae 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -160,6 +160,12 @@ ENTRY(cpu_do_switch_mm)
mrs x2, ttbr1_el1
mmid x1, x1 // get mm->context.id
phys_to_ttbr x3, x0
+
+alternative_if ARM64_HAS_CNP
+ cbz x1, 1f // skip CNP for reserved ASID
+ orr x3, x3, #TTBR_CNP_BIT
+1:
+alternative_else_nop_endif
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
bfi x3, x1, #48, #16 // set the ASID field in TTBR0
#endif
@@ -184,7 +190,7 @@ ENDPROC(cpu_do_switch_mm)
.endm
/*
- * void idmap_cpu_replace_ttbr1(phys_addr_t new_pgd)
+ * void idmap_cpu_replace_ttbr1(phys_addr_t ttbr1)
*
* This is the low-level counterpart to cpu_replace_ttbr1, and should not be
* called by anything else. It can only be executed from a TTBR0 mapping.
@@ -194,8 +200,7 @@ ENTRY(idmap_cpu_replace_ttbr1)
__idmap_cpu_set_reserved_ttbr1 x1, x3
- phys_to_ttbr x3, x0
- msr ttbr1_el1, x3
+ msr ttbr1_el1, x0
isb
restore_daif x2