summaryrefslogtreecommitdiff
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig22
-rw-r--r--arch/arm64/Makefile6
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi83
-rw-r--r--arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts44
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi4
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts12
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts4
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi4
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxl.dtsi61
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts4
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxm.dtsi17
-rw-r--r--arch/arm64/boot/dts/arm/juno-motherboard.dtsi2
-rw-r--r--arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi80
-rw-r--r--arch/arm64/boot/dts/exynos/exynos5433.dtsi2
-rw-r--r--arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts1
-rw-r--r--arch/arm64/boot/dts/marvell/armada-cp110.dtsi7
-rw-r--r--arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi2
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi2
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts8
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi2
-rw-r--r--arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi2
-rw-r--r--arch/arm64/crypto/Kconfig6
-rw-r--r--arch/arm64/crypto/Makefile3
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-core.S150
-rw-r--r--arch/arm64/crypto/aes-ce.S15
-rw-r--r--arch/arm64/crypto/aes-modes.S331
-rw-r--r--arch/arm64/crypto/aes-neonbs-core.S305
-rw-r--r--arch/arm64/crypto/crc32-ce-core.S40
-rw-r--r--arch/arm64/crypto/crct10dif-ce-core.S32
-rw-r--r--arch/arm64/crypto/ghash-ce-core.S113
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c28
-rw-r--r--arch/arm64/crypto/sha1-ce-core.S42
-rw-r--r--arch/arm64/crypto/sha2-ce-core.S37
-rw-r--r--arch/arm64/crypto/sha256-core.S_shipped12
-rw-r--r--arch/arm64/crypto/sha3-ce-core.S77
-rw-r--r--arch/arm64/crypto/sha512-armv8.pl12
-rw-r--r--arch/arm64/crypto/sha512-ce-core.S27
-rw-r--r--arch/arm64/crypto/sha512-core.S_shipped12
-rw-r--r--arch/arm64/crypto/sm4-ce-core.S36
-rw-r--r--arch/arm64/crypto/sm4-ce-glue.c73
-rw-r--r--arch/arm64/include/asm/atomic_lse.h24
-rw-r--r--arch/arm64/include/asm/compat.h43
-rw-r--r--arch/arm64/include/asm/cputype.h6
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h2
-rw-r--r--arch/arm64/include/asm/kvm_host.h3
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h16
-rw-r--r--arch/arm64/include/asm/module.h2
-rw-r--r--arch/arm64/include/asm/pci.h5
-rw-r--r--arch/arm64/include/asm/pgtable.h4
-rw-r--r--arch/arm64/include/asm/spinlock.h5
-rw-r--r--arch/arm64/include/asm/stat.h1
-rw-r--r--arch/arm64/include/uapi/asm/kvm.h6
-rw-r--r--arch/arm64/kernel/arm64ksyms.c8
-rw-r--r--arch/arm64/kernel/cpu_errata.c1
-rw-r--r--arch/arm64/kernel/cpufeature.c1
-rw-r--r--arch/arm64/kernel/fpsimd.c2
-rw-r--r--arch/arm64/kernel/hw_breakpoint.c1
-rw-r--r--arch/arm64/kernel/module-plts.c2
-rw-r--r--arch/arm64/kernel/module.c2
-rw-r--r--arch/arm64/kernel/perf_regs.c2
-rw-r--r--arch/arm64/kernel/ptrace.c20
-rw-r--r--arch/arm64/kernel/sys_compat.c1
-rw-r--r--arch/arm64/kernel/traps.c6
-rw-r--r--arch/arm64/kvm/guest.c14
-rw-r--r--arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c24
-rw-r--r--arch/arm64/kvm/sys_regs.c6
-rw-r--r--arch/arm64/lib/Makefile4
-rw-r--r--arch/arm64/lib/tishift.S15
-rw-r--r--arch/arm64/mm/dma-mapping.c10
-rw-r--r--arch/arm64/mm/fault.c69
-rw-r--r--arch/arm64/mm/flush.c2
-rw-r--r--arch/arm64/mm/init.c4
-rw-r--r--arch/arm64/mm/kasan_init.c4
-rw-r--r--arch/arm64/mm/mmu.c16
74 files changed, 1418 insertions, 633 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index eb2cf4938f6d..b25ed7834f6c 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -105,7 +105,6 @@ config ARM64
select HAVE_CONTEXT_TRACKING
select HAVE_DEBUG_BUGVERBOSE
select HAVE_DEBUG_KMEMLEAK
- select HAVE_DMA_API_DEBUG
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -133,6 +132,8 @@ config ARM64
select IRQ_FORCED_THREADING
select MODULES_USE_ELF_RELA
select MULTI_IRQ_HANDLER
+ select NEED_DMA_MAP_STATE
+ select NEED_SG_DMA_LENGTH
select NO_BOOTMEM
select OF
select OF_EARLY_FLATTREE
@@ -142,6 +143,7 @@ config ARM64
select POWER_SUPPLY
select REFCOUNT_FULL
select SPARSE_IRQ
+ select SWIOTLB
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
help
@@ -150,9 +152,6 @@ config ARM64
config 64BIT
def_bool y
-config ARCH_PHYS_ADDR_T_64BIT
- def_bool y
-
config MMU
def_bool y
@@ -237,24 +236,9 @@ config ZONE_DMA32
config HAVE_GENERIC_GUP
def_bool y
-config ARCH_DMA_ADDR_T_64BIT
- def_bool y
-
-config NEED_DMA_MAP_STATE
- def_bool y
-
-config NEED_SG_DMA_LENGTH
- def_bool y
-
config SMP
def_bool y
-config SWIOTLB
- def_bool y
-
-config IOMMU_HELPER
- def_bool SWIOTLB
-
config KERNEL_MODE_NEON
def_bool y
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 15402861bb59..3c353b4715dc 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -56,7 +56,11 @@ KBUILD_AFLAGS += $(lseinstr) $(brokengasinst)
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)
+ifeq ($(cc-name),clang)
+KBUILD_CFLAGS += -DCONFIG_ARCH_SUPPORTS_INT128
+else
KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0500, -DCONFIG_ARCH_SUPPORTS_INT128)
+endif
ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
KBUILD_CPPFLAGS += -mbig-endian
@@ -74,7 +78,7 @@ LDFLAGS += -maarch64linux
UTS_MACHINE := aarch64
endif
-CHECKFLAGS += -D__aarch64__ -m64
+CHECKFLAGS += -D__aarch64__
ifeq ($(CONFIG_ARM64_MODULE_PLTS),y)
KBUILD_LDFLAGS_MODULE += -T $(srctree)/arch/arm64/kernel/module.lds
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index c89d0c307f8d..e6b059378dc0 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -17,6 +17,7 @@
/dts-v1/;
#include <dt-bindings/reset/altr,rst-mgr-s10.h>
#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/clock/stratix10-clock.h>
/ {
compatible = "altr,socfpga-stratix10";
@@ -92,9 +93,32 @@
interrupt-parent = <&intc>;
ranges = <0 0 0 0xffffffff>;
- clkmgr@ffd1000 {
- compatible = "altr,clk-mgr";
+ clkmgr: clock-controller@ffd10000 {
+ compatible = "intel,stratix10-clkmgr";
reg = <0xffd10000 0x1000>;
+ #clock-cells = <1>;
+ };
+
+ clocks {
+ cb_intosc_hs_div2_clk: cb-intosc-hs-div2-clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ };
+
+ cb_intosc_ls_clk: cb-intosc-ls-clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ };
+
+ f2s_free_clk: f2s-free-clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ };
+
+ osc1: osc1 {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+ };
};
gmac0: ethernet@ff800000 {
@@ -105,6 +129,8 @@
mac-address = [00 00 00 00 00 00];
resets = <&rst EMAC0_RESET>;
reset-names = "stmmaceth";
+ clocks = <&clkmgr STRATIX10_EMAC0_CLK>;
+ clock-names = "stmmaceth";
status = "disabled";
};
@@ -116,6 +142,8 @@
mac-address = [00 00 00 00 00 00];
resets = <&rst EMAC1_RESET>;
reset-names = "stmmaceth";
+ clocks = <&clkmgr STRATIX10_EMAC1_CLK>;
+ clock-names = "stmmaceth";
status = "disabled";
};
@@ -127,6 +155,8 @@
mac-address = [00 00 00 00 00 00];
resets = <&rst EMAC2_RESET>;
reset-names = "stmmaceth";
+ clocks = <&clkmgr STRATIX10_EMAC2_CLK>;
+ clock-names = "stmmaceth";
status = "disabled";
};
@@ -177,6 +207,7 @@
reg = <0xffc02800 0x100>;
interrupts = <0 103 4>;
resets = <&rst I2C0_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -187,6 +218,7 @@
reg = <0xffc02900 0x100>;
interrupts = <0 104 4>;
resets = <&rst I2C1_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -197,6 +229,7 @@
reg = <0xffc02a00 0x100>;
interrupts = <0 105 4>;
resets = <&rst I2C2_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -207,6 +240,7 @@
reg = <0xffc02b00 0x100>;
interrupts = <0 106 4>;
resets = <&rst I2C3_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -217,6 +251,7 @@
reg = <0xffc02c00 0x100>;
interrupts = <0 107 4>;
resets = <&rst I2C4_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -229,6 +264,9 @@
fifo-depth = <0x400>;
resets = <&rst SDMMC_RESET>;
reset-names = "reset";
+ clocks = <&clkmgr STRATIX10_L4_MP_CLK>,
+ <&clkmgr STRATIX10_SDMMC_CLK>;
+ clock-names = "biu", "ciu";
status = "disabled";
};
@@ -237,6 +275,25 @@
reg = <0xffe00000 0x100000>;
};
+ pdma: pdma@ffda0000 {
+ compatible = "arm,pl330", "arm,primecell";
+ reg = <0xffda0000 0x1000>;
+ interrupts = <0 81 4>,
+ <0 82 4>,
+ <0 83 4>,
+ <0 84 4>,
+ <0 85 4>,
+ <0 86 4>,
+ <0 87 4>,
+ <0 88 4>,
+ <0 89 4>;
+ #dma-cells = <1>;
+ #dma-channels = <8>;
+ #dma-requests = <32>;
+ clocks = <&clkmgr STRATIX10_L4_MAIN_CLK>;
+ clock-names = "apb_pclk";
+ };
+
rst: rstmgr@ffd11000 {
#reset-cells = <1>;
compatible = "altr,rst-mgr";
@@ -288,24 +345,32 @@
compatible = "snps,dw-apb-timer";
interrupts = <0 113 4>;
reg = <0xffc03000 0x100>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+ clock-names = "timer";
};
timer1: timer1@ffc03100 {
compatible = "snps,dw-apb-timer";
interrupts = <0 114 4>;
reg = <0xffc03100 0x100>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+ clock-names = "timer";
};
timer2: timer2@ffd00000 {
compatible = "snps,dw-apb-timer";
interrupts = <0 115 4>;
reg = <0xffd00000 0x100>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+ clock-names = "timer";
};
timer3: timer3@ffd00100 {
compatible = "snps,dw-apb-timer";
interrupts = <0 116 4>;
reg = <0xffd00100 0x100>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
+ clock-names = "timer";
};
uart0: serial0@ffc02000 {
@@ -315,6 +380,7 @@
reg-shift = <2>;
reg-io-width = <4>;
resets = <&rst UART0_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -325,6 +391,7 @@
reg-shift = <2>;
reg-io-width = <4>;
resets = <&rst UART1_RESET>;
+ clocks = <&clkmgr STRATIX10_L4_SP_CLK>;
status = "disabled";
};
@@ -387,5 +454,17 @@
resets = <&rst WATCHDOG3_RESET>;
status = "disabled";
};
+
+ eccmgr {
+ compatible = "altr,socfpga-s10-ecc-manager";
+ interrupts = <0 15 4>, <0 95 4>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+
+ sdramedac {
+ compatible = "altr,sdram-edac-s10";
+ interrupts = <16 4>, <48 4>;
+ };
+ };
};
};
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
index eaf13fe29287..f9b1ef12db48 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10_socdk.dts
@@ -50,6 +50,21 @@
/* We expect the bootloader to fill in the reg */
reg = <0 0 0 0>;
};
+
+ ref_033v: 033-v-ref {
+ compatible = "regulator-fixed";
+ regulator-name = "0.33V";
+ regulator-min-microvolt = <330000>;
+ regulator-max-microvolt = <330000>;
+ };
+
+ soc {
+ clocks {
+ osc1 {
+ clock-frequency = <25000000>;
+ };
+ };
+ };
};
&gpio1 {
@@ -79,7 +94,7 @@
rxd2-skew-ps = <420>; /* 0ps */
rxd3-skew-ps = <420>; /* 0ps */
txen-skew-ps = <0>; /* -420ps */
- txc-skew-ps = <1860>; /* 960ps */
+ txc-skew-ps = <900>; /* 0ps */
rxdv-skew-ps = <420>; /* 0ps */
rxc-skew-ps = <1680>; /* 780ps */
};
@@ -105,3 +120,30 @@
&watchdog0 {
status = "okay";
};
+
+&i2c1 {
+ status = "okay";
+ clock-frequency = <100000>;
+
+ adc@14 {
+ compatible = "lltc,ltc2497";
+ reg = <0x14>;
+ vref-supply = <&ref_033v>;
+ };
+
+ temp@4c {
+ compatible = "maxim,max1619";
+ reg = <0x4c>;
+ };
+
+ eeprom@51 {
+ compatible = "atmel,24c32";
+ reg = <0x51>;
+ pagesize = <32>;
+ };
+
+ rtc@68 {
+ compatible = "dallas,ds1339";
+ reg = <0x68>;
+ };
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
index 4eef36b22538..88e712ea757a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi
@@ -212,3 +212,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
index 22bf37404ff1..3e3eb31748a3 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts
@@ -271,3 +271,15 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
+
+&usb2_phy0 {
+ /*
+ * even though the schematics don't show it:
+ * HDMI_5V is also used as supply for the USB VBUS.
+ */
+ phy-supply = <&hdmi_5v>;
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
index 69c721a70e44..6739697be1de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts
@@ -215,3 +215,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
index 0a0953fbc7d4..0cfd701809de 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi
@@ -185,3 +185,7 @@
pinctrl-0 = <&uart_ao_a_pins>;
pinctrl-names = "default";
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
index e1a39cbed8c9..dba365ed4bd5 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
@@ -20,6 +20,67 @@
no-map;
};
};
+
+ soc {
+ usb0: usb@c9000000 {
+ status = "disabled";
+ compatible = "amlogic,meson-gxl-dwc3";
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "usb_general";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "usb_otg";
+
+ dwc3: dwc3@c9000000 {
+ compatible = "snps,dwc3";
+ reg = <0x0 0xc9000000 0x0 0x100000>;
+ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
+ dr_mode = "host";
+ maximum-speed = "high-speed";
+ snps,dis_u2_susphy_quirk;
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>;
+ };
+ };
+ };
+};
+
+&apb {
+ usb2_phy0: phy@78000 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78000 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb2_phy1: phy@78020 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78020 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+
+ usb3_phy: phy@78080 {
+ compatible = "amlogic,meson-gxl-usb3-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78080 0x0 0x20>;
+ interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&clkc CLKID_USB>, <&clkc_AO CLKID_AO_CEC_32K>;
+ clock-names = "phy", "peripheral";
+ resets = <&reset RESET_USB_OTG>, <&reset RESET_USB_OTG>;
+ reset-names = "phy", "peripheral";
+ status = "okay";
+ };
};
&ethmac {
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
index 4fd46c1546a7..0868da476e41 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts
@@ -406,3 +406,7 @@
status = "okay";
vref-supply = <&vddio_ao18>;
};
+
+&usb0 {
+ status = "okay";
+};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
index d076a7c425dd..247888d68a3a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxm.dtsi
@@ -80,6 +80,19 @@
};
};
+&apb {
+ usb2_phy2: phy@78040 {
+ compatible = "amlogic,meson-gxl-usb2-phy";
+ #phy-cells = <0>;
+ reg = <0x0 0x78040 0x0 0x20>;
+ clocks = <&clkc CLKID_USB>;
+ clock-names = "phy";
+ resets = <&reset RESET_USB_OTG>;
+ reset-names = "phy";
+ status = "okay";
+ };
+};
+
&clkc_AO {
compatible = "amlogic,meson-gxm-aoclkc", "amlogic,meson-gx-aoclkc";
};
@@ -100,3 +113,7 @@
&hdmi_tx {
compatible = "amlogic,meson-gxm-dw-hdmi", "amlogic,meson-gx-dw-hdmi";
};
+
+&dwc3 {
+ phys = <&usb3_phy>, <&usb2_phy0>, <&usb2_phy1>, <&usb2_phy2>;
+};
diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
index 2ac43221ddb6..69804c5f1197 100644
--- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi
@@ -56,8 +56,6 @@
gpio_keys {
compatible = "gpio-keys";
- #address-cells = <1>;
- #size-cells = <0>;
power-button {
debounce_interval = <50>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
index 4b5465da81d8..8c68e0c26f1b 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-sata.dtsi
@@ -36,11 +36,11 @@
#size-cells = <1>;
ranges = <0x0 0x0 0x67d00000 0x00800000>;
- sata0: ahci@210000 {
+ sata0: ahci@0 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00210000 0x1000>;
+ reg = <0x00000000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 339 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 321 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -52,9 +52,9 @@
};
};
- sata_phy0: sata_phy@212100 {
+ sata_phy0: sata_phy@2100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00212100 0x1000>;
+ reg = <0x00002100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -66,11 +66,11 @@
};
};
- sata1: ahci@310000 {
+ sata1: ahci@10000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00310000 0x1000>;
+ reg = <0x00010000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 347 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 323 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -82,9 +82,9 @@
};
};
- sata_phy1: sata_phy@312100 {
+ sata_phy1: sata_phy@12100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00312100 0x1000>;
+ reg = <0x00012100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -96,11 +96,11 @@
};
};
- sata2: ahci@120000 {
+ sata2: ahci@20000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00120000 0x1000>;
+ reg = <0x00020000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 325 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -112,9 +112,9 @@
};
};
- sata_phy2: sata_phy@122100 {
+ sata_phy2: sata_phy@22100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00122100 0x1000>;
+ reg = <0x00022100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -126,11 +126,11 @@
};
};
- sata3: ahci@130000 {
+ sata3: ahci@30000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00130000 0x1000>;
+ reg = <0x00030000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 327 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -142,9 +142,9 @@
};
};
- sata_phy3: sata_phy@132100 {
+ sata_phy3: sata_phy@32100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00132100 0x1000>;
+ reg = <0x00032100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -156,11 +156,11 @@
};
};
- sata4: ahci@330000 {
+ sata4: ahci@100000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00330000 0x1000>;
+ reg = <0x00100000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 351 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 329 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -172,9 +172,9 @@
};
};
- sata_phy4: sata_phy@332100 {
+ sata_phy4: sata_phy@102100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00332100 0x1000>;
+ reg = <0x00102100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -186,11 +186,11 @@
};
};
- sata5: ahci@400000 {
+ sata5: ahci@110000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00400000 0x1000>;
+ reg = <0x00110000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 353 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 331 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -202,9 +202,9 @@
};
};
- sata_phy5: sata_phy@402100 {
+ sata_phy5: sata_phy@112100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00402100 0x1000>;
+ reg = <0x00112100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -216,11 +216,11 @@
};
};
- sata6: ahci@410000 {
+ sata6: ahci@120000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00410000 0x1000>;
+ reg = <0x00120000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 355 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 333 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -232,9 +232,9 @@
};
};
- sata_phy6: sata_phy@412100 {
+ sata_phy6: sata_phy@122100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00412100 0x1000>;
+ reg = <0x00122100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
@@ -246,11 +246,11 @@
};
};
- sata7: ahci@420000 {
+ sata7: ahci@130000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
- reg = <0x00420000 0x1000>;
+ reg = <0x00130000 0x1000>;
reg-names = "ahci";
- interrupts = <GIC_SPI 357 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_SPI 335 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
#size-cells = <0>;
status = "disabled";
@@ -262,9 +262,9 @@
};
};
- sata_phy7: sata_phy@422100 {
+ sata_phy7: sata_phy@132100 {
compatible = "brcm,iproc-sr-sata-phy";
- reg = <0x00422100 0x1000>;
+ reg = <0x00132100 0x1000>;
reg-names = "phy";
#address-cells = <1>;
#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/exynos/exynos5433.dtsi b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
index c0231d077fa6..1ad8677f6a0a 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433.dtsi
@@ -1317,7 +1317,7 @@
reg = <0x14d60000 0x100>;
dmas = <&pdma0 31 &pdma0 30>;
dma-names = "tx", "rx";
- interrupts = <GIC_SPI 435 IRQ_TYPE_NONE>;
+ interrupts = <GIC_SPI 435 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_PCLK_I2S1>,
<&cmu_peric CLK_SCLK_I2S1>;
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index 724a0d3b7683..edb4ee0b8896 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -299,7 +299,6 @@
/* GPIO blocks 16 thru 19 do not appear to be routed to pins */
dwmmc_0: dwmmc0@f723d000 {
- max-frequency = <150000000>;
cap-mmc-highspeed;
mmc-hs200-1_8v;
non-removable;
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
index 48cad7919efa..ed2f1237ea1e 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
@@ -38,9 +38,10 @@
compatible = "marvell,armada-7k-pp22";
reg = <0x0 0x100000>, <0x129000 0xb000>;
clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
- <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
+ <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>,
+ <&CP110_LABEL(clk) 1 18>;
clock-names = "pp_clk", "gop_clk",
- "mg_clk", "axi_clk";
+ "mg_clk", "mg_core_clk", "axi_clk";
marvell,system-controller = <&CP110_LABEL(syscon0)>;
status = "disabled";
dma-coherent;
@@ -141,6 +142,8 @@
#size-cells = <0>;
compatible = "marvell,xmdio";
reg = <0x12a600 0x10>;
+ clocks = <&CP110_LABEL(clk) 1 5>,
+ <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
index a8baad7b80df..13f57fff1477 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi
@@ -46,7 +46,7 @@
compatible = "ethernet-phy-ieee802.3-c22";
reg = <0x0>;
interrupt-parent = <&gpio>;
- interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <TEGRA_MAIN_GPIO(M, 5) IRQ_TYPE_LEVEL_LOW>;
};
};
};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
index e62bda1cf2d9..c32dd3419c87 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld11.dtsi
@@ -414,7 +414,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
index 2c1a92fafbfb..440c2e6a638b 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20-ref.dts
@@ -67,3 +67,11 @@
reg = <0>;
};
};
+
+&pinctrl_ether_rgmii {
+ tx {
+ pins = "RGMII_TXCLK", "RGMII_TXD0", "RGMII_TXD1",
+ "RGMII_TXD2", "RGMII_TXD3", "RGMII_TXCTL";
+ drive-strength = <9>;
+ };
+};
diff --git a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
index 9efe20d07589..3a5ed789c056 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-ld20.dtsi
@@ -519,7 +519,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
index 7c8f710d9bfa..e85d6ddea3c2 100644
--- a/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
+++ b/arch/arm64/boot/dts/socionext/uniphier-pxs3.dtsi
@@ -334,7 +334,7 @@
mmc-ddr-1_8v;
mmc-hs200-1_8v;
mmc-pwrseq = <&emmc_pwrseq>;
- cdns,phy-input-delay-legacy = <4>;
+ cdns,phy-input-delay-legacy = <9>;
cdns,phy-input-delay-mmc-highspeed = <2>;
cdns,phy-input-delay-mmc-ddr = <3>;
cdns,phy-dll-delay-sdclk = <21>;
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index cb5a243110c4..e3fdb0fd6f70 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -47,6 +47,12 @@ config CRYPTO_SM3_ARM64_CE
select CRYPTO_HASH
select CRYPTO_SM3
+config CRYPTO_SM4_ARM64_CE
+ tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_ALGAPI
+ select CRYPTO_SM4
+
config CRYPTO_GHASH_ARM64_CE
tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
depends on KERNEL_MODE_NEON
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index f35ac684b1c0..bcafd016618e 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -23,6 +23,9 @@ sha3-ce-y := sha3-ce-glue.o sha3-ce-core.o
obj-$(CONFIG_CRYPTO_SM3_ARM64_CE) += sm3-ce.o
sm3-ce-y := sm3-ce-glue.o sm3-ce-core.o
+obj-$(CONFIG_CRYPTO_SM4_ARM64_CE) += sm4-ce.o
+sm4-ce-y := sm4-ce-glue.o sm4-ce-core.o
+
obj-$(CONFIG_CRYPTO_GHASH_ARM64_CE) += ghash-ce.o
ghash-ce-y := ghash-ce-glue.o ghash-ce-core.o
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index e3a375c4cb83..88f5aef7934c 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -19,24 +19,33 @@
* u32 *macp, u8 const rk[], u32 rounds);
*/
ENTRY(ce_aes_ccm_auth_data)
- ldr w8, [x3] /* leftover from prev round? */
+ frame_push 7
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
+
+ ldr w25, [x22] /* leftover from prev round? */
ld1 {v0.16b}, [x0] /* load mac */
- cbz w8, 1f
- sub w8, w8, #16
+ cbz w25, 1f
+ sub w25, w25, #16
eor v1.16b, v1.16b, v1.16b
-0: ldrb w7, [x1], #1 /* get 1 byte of input */
- subs w2, w2, #1
- add w8, w8, #1
+0: ldrb w7, [x20], #1 /* get 1 byte of input */
+ subs w21, w21, #1
+ add w25, w25, #1
ins v1.b[0], w7
ext v1.16b, v1.16b, v1.16b, #1 /* rotate in the input bytes */
beq 8f /* out of input? */
- cbnz w8, 0b
+ cbnz w25, 0b
eor v0.16b, v0.16b, v1.16b
-1: ld1 {v3.4s}, [x4] /* load first round key */
- prfm pldl1strm, [x1]
- cmp w5, #12 /* which key size? */
- add x6, x4, #16
- sub w7, w5, #2 /* modified # of rounds */
+1: ld1 {v3.4s}, [x23] /* load first round key */
+ prfm pldl1strm, [x20]
+ cmp w24, #12 /* which key size? */
+ add x6, x23, #16
+ sub w7, w24, #2 /* modified # of rounds */
bmi 2f
bne 5f
mov v5.16b, v3.16b
@@ -55,33 +64,43 @@ ENTRY(ce_aes_ccm_auth_data)
ld1 {v5.4s}, [x6], #16 /* load next round key */
bpl 3b
aese v0.16b, v4.16b
- subs w2, w2, #16 /* last data? */
+ subs w21, w21, #16 /* last data? */
eor v0.16b, v0.16b, v5.16b /* final round */
bmi 6f
- ld1 {v1.16b}, [x1], #16 /* load next input block */
+ ld1 {v1.16b}, [x20], #16 /* load next input block */
eor v0.16b, v0.16b, v1.16b /* xor with mac */
- bne 1b
-6: st1 {v0.16b}, [x0] /* store mac */
+ beq 6f
+
+ if_will_cond_yield_neon
+ st1 {v0.16b}, [x19] /* store mac */
+ do_cond_yield_neon
+ ld1 {v0.16b}, [x19] /* reload mac */
+ endif_yield_neon
+
+ b 1b
+6: st1 {v0.16b}, [x19] /* store mac */
beq 10f
- adds w2, w2, #16
+ adds w21, w21, #16
beq 10f
- mov w8, w2
-7: ldrb w7, [x1], #1
+ mov w25, w21
+7: ldrb w7, [x20], #1
umov w6, v0.b[0]
eor w6, w6, w7
- strb w6, [x0], #1
- subs w2, w2, #1
+ strb w6, [x19], #1
+ subs w21, w21, #1
beq 10f
ext v0.16b, v0.16b, v0.16b, #1 /* rotate out the mac bytes */
b 7b
-8: mov w7, w8
- add w8, w8, #16
+8: mov w7, w25
+ add w25, w25, #16
9: ext v1.16b, v1.16b, v1.16b, #1
adds w7, w7, #1
bne 9b
eor v0.16b, v0.16b, v1.16b
- st1 {v0.16b}, [x0]
-10: str w8, [x3]
+ st1 {v0.16b}, [x19]
+10: str w25, [x22]
+
+ frame_pop
ret
ENDPROC(ce_aes_ccm_auth_data)
@@ -126,19 +145,29 @@ ENTRY(ce_aes_ccm_final)
ENDPROC(ce_aes_ccm_final)
.macro aes_ccm_do_crypt,enc
- ldr x8, [x6, #8] /* load lower ctr */
- ld1 {v0.16b}, [x5] /* load mac */
-CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
+ frame_push 8
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
+ mov x25, x6
+
+ ldr x26, [x25, #8] /* load lower ctr */
+ ld1 {v0.16b}, [x24] /* load mac */
+CPU_LE( rev x26, x26 ) /* keep swabbed ctr in reg */
0: /* outer loop */
- ld1 {v1.8b}, [x6] /* load upper ctr */
- prfm pldl1strm, [x1]
- add x8, x8, #1
- rev x9, x8
- cmp w4, #12 /* which key size? */
- sub w7, w4, #2 /* get modified # of rounds */
+ ld1 {v1.8b}, [x25] /* load upper ctr */
+ prfm pldl1strm, [x20]
+ add x26, x26, #1
+ rev x9, x26
+ cmp w23, #12 /* which key size? */
+ sub w7, w23, #2 /* get modified # of rounds */
ins v1.d[1], x9 /* no carry in lower ctr */
- ld1 {v3.4s}, [x3] /* load first round key */
- add x10, x3, #16
+ ld1 {v3.4s}, [x22] /* load first round key */
+ add x10, x22, #16
bmi 1f
bne 4f
mov v5.16b, v3.16b
@@ -165,9 +194,9 @@ CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
bpl 2b
aese v0.16b, v4.16b
aese v1.16b, v4.16b
- subs w2, w2, #16
- bmi 6f /* partial block? */
- ld1 {v2.16b}, [x1], #16 /* load next input block */
+ subs w21, w21, #16
+ bmi 7f /* partial block? */
+ ld1 {v2.16b}, [x20], #16 /* load next input block */
.if \enc == 1
eor v2.16b, v2.16b, v5.16b /* final round enc+mac */
eor v1.16b, v1.16b, v2.16b /* xor with crypted ctr */
@@ -176,18 +205,29 @@ CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
eor v1.16b, v2.16b, v5.16b /* final round enc */
.endif
eor v0.16b, v0.16b, v2.16b /* xor mac with pt ^ rk[last] */
- st1 {v1.16b}, [x0], #16 /* write output block */
- bne 0b
-CPU_LE( rev x8, x8 )
- st1 {v0.16b}, [x5] /* store mac */
- str x8, [x6, #8] /* store lsb end of ctr (BE) */
-5: ret
-
-6: eor v0.16b, v0.16b, v5.16b /* final round mac */
+ st1 {v1.16b}, [x19], #16 /* write output block */
+ beq 5f
+
+ if_will_cond_yield_neon
+ st1 {v0.16b}, [x24] /* store mac */
+ do_cond_yield_neon
+ ld1 {v0.16b}, [x24] /* reload mac */
+ endif_yield_neon
+
+ b 0b
+5:
+CPU_LE( rev x26, x26 )
+ st1 {v0.16b}, [x24] /* store mac */
+ str x26, [x25, #8] /* store lsb end of ctr (BE) */
+
+6: frame_pop
+ ret
+
+7: eor v0.16b, v0.16b, v5.16b /* final round mac */
eor v1.16b, v1.16b, v5.16b /* final round enc */
- st1 {v0.16b}, [x5] /* store mac */
- add w2, w2, #16 /* process partial tail block */
-7: ldrb w9, [x1], #1 /* get 1 byte of input */
+ st1 {v0.16b}, [x24] /* store mac */
+ add w21, w21, #16 /* process partial tail block */
+8: ldrb w9, [x20], #1 /* get 1 byte of input */
umov w6, v1.b[0] /* get top crypted ctr byte */
umov w7, v0.b[0] /* get top mac byte */
.if \enc == 1
@@ -197,13 +237,13 @@ CPU_LE( rev x8, x8 )
eor w9, w9, w6
eor w7, w7, w9
.endif
- strb w9, [x0], #1 /* store out byte */
- strb w7, [x5], #1 /* store mac byte */
- subs w2, w2, #1
- beq 5b
+ strb w9, [x19], #1 /* store out byte */
+ strb w7, [x24], #1 /* store mac byte */
+ subs w21, w21, #1
+ beq 6b
ext v0.16b, v0.16b, v0.16b, #1 /* shift out mac byte */
ext v1.16b, v1.16b, v1.16b, #1 /* shift out ctr byte */
- b 7b
+ b 8b
.endm
/*
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index 50330f5c3adc..623e74ed1c67 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -30,18 +30,21 @@
.endm
/* prepare for encryption with key in rk[] */
- .macro enc_prepare, rounds, rk, ignore
- load_round_keys \rounds, \rk
+ .macro enc_prepare, rounds, rk, temp
+ mov \temp, \rk
+ load_round_keys \rounds, \temp
.endm
/* prepare for encryption (again) but with new key in rk[] */
- .macro enc_switch_key, rounds, rk, ignore
- load_round_keys \rounds, \rk
+ .macro enc_switch_key, rounds, rk, temp
+ mov \temp, \rk
+ load_round_keys \rounds, \temp
.endm
/* prepare for decryption with key in rk[] */
- .macro dec_prepare, rounds, rk, ignore
- load_round_keys \rounds, \rk
+ .macro dec_prepare, rounds, rk, temp
+ mov \temp, \rk
+ load_round_keys \rounds, \temp
.endm
.macro do_enc_Nx, de, mc, k, i0, i1, i2, i3
diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S
index a68412e1e3a4..483a7130cf0e 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, w3, x2, x8, w7
+ encrypt_block4x v0, v1, v2, v3, w22, x21, x8, w7
ret
ENDPROC(aes_encrypt_block4x)
aes_decrypt_block4x:
- decrypt_block4x v0, v1, v2, v3, w3, x2, x8, w7
+ decrypt_block4x v0, v1, v2, v3, w22, x21, x8, w7
ret
ENDPROC(aes_decrypt_block4x)
@@ -31,57 +31,71 @@ ENDPROC(aes_decrypt_block4x)
*/
AES_ENTRY(aes_ecb_encrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 5
- enc_prepare w3, x2, x5
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+
+.Lecbencrestart:
+ enc_prepare w22, x21, x5
.LecbencloopNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lecbenc1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
bl aes_encrypt_block4x
- st1 {v0.16b-v3.16b}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
+ cond_yield_neon .Lecbencrestart
b .LecbencloopNx
.Lecbenc1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lecbencout
.Lecbencloop:
- 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
+ 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
bne .Lecbencloop
.Lecbencout:
- ldp x29, x30, [sp], #16
+ frame_pop
ret
AES_ENDPROC(aes_ecb_encrypt)
AES_ENTRY(aes_ecb_decrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 5
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
- dec_prepare w3, x2, x5
+.Lecbdecrestart:
+ dec_prepare w22, x21, x5
.LecbdecloopNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lecbdec1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 ct blocks */
bl aes_decrypt_block4x
- st1 {v0.16b-v3.16b}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
+ cond_yield_neon .Lecbdecrestart
b .LecbdecloopNx
.Lecbdec1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lecbdecout
.Lecbdecloop:
- 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
+ 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
bne .Lecbdecloop
.Lecbdecout:
- ldp x29, x30, [sp], #16
+ frame_pop
ret
AES_ENDPROC(aes_ecb_decrypt)
@@ -94,78 +108,100 @@ AES_ENDPROC(aes_ecb_decrypt)
*/
AES_ENTRY(aes_cbc_encrypt)
- ld1 {v4.16b}, [x5] /* get iv */
- enc_prepare w3, x2, x6
+ 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
.Lcbcencloop4x:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lcbcenc1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
eor v0.16b, v0.16b, v4.16b /* ..and xor with iv */
- encrypt_block v0, w3, x2, x6, w7
+ encrypt_block v0, w22, x21, x6, w7
eor v1.16b, v1.16b, v0.16b
- encrypt_block v1, w3, x2, x6, w7
+ encrypt_block v1, w22, x21, x6, w7
eor v2.16b, v2.16b, v1.16b
- encrypt_block v2, w3, x2, x6, w7
+ encrypt_block v2, w22, x21, x6, w7
eor v3.16b, v3.16b, v2.16b
- encrypt_block v3, w3, x2, x6, w7
- st1 {v0.16b-v3.16b}, [x0], #64
+ encrypt_block v3, w22, x21, x6, w7
+ st1 {v0.16b-v3.16b}, [x19], #64
mov v4.16b, v3.16b
+ st1 {v4.16b}, [x24] /* return iv */
+ cond_yield_neon .Lcbcencrestart
b .Lcbcencloop4x
.Lcbcenc1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lcbcencout
.Lcbcencloop:
- ld1 {v0.16b}, [x1], #16 /* get next pt block */
+ ld1 {v0.16b}, [x20], #16 /* get next pt block */
eor v4.16b, v4.16b, v0.16b /* ..and xor with iv */
- encrypt_block v4, w3, x2, x6, w7
- st1 {v4.16b}, [x0], #16
- subs w4, w4, #1
+ encrypt_block v4, w22, x21, x6, w7
+ st1 {v4.16b}, [x19], #16
+ subs w23, w23, #1
bne .Lcbcencloop
.Lcbcencout:
- st1 {v4.16b}, [x5] /* return iv */
+ st1 {v4.16b}, [x24] /* return iv */
+ frame_pop
ret
AES_ENDPROC(aes_cbc_encrypt)
AES_ENTRY(aes_cbc_decrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 6
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
- ld1 {v7.16b}, [x5] /* get iv */
- dec_prepare w3, x2, x6
+.Lcbcdecrestart:
+ ld1 {v7.16b}, [x24] /* get iv */
+ dec_prepare w22, x21, x6
.LcbcdecloopNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lcbcdec1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #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 x1, x1, #16
+ sub x20, x20, #16
eor v0.16b, v0.16b, v7.16b
eor v1.16b, v1.16b, v4.16b
- ld1 {v7.16b}, [x1], #16 /* reload 1 ct block */
+ ld1 {v7.16b}, [x20], #16 /* reload 1 ct block */
eor v2.16b, v2.16b, v5.16b
eor v3.16b, v3.16b, v6.16b
- st1 {v0.16b-v3.16b}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
+ st1 {v7.16b}, [x24] /* return iv */
+ cond_yield_neon .Lcbcdecrestart
b .LcbcdecloopNx
.Lcbcdec1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lcbcdecout
.Lcbcdecloop:
- ld1 {v1.16b}, [x1], #16 /* get next ct block */
+ ld1 {v1.16b}, [x20], #16 /* get next ct block */
mov v0.16b, v1.16b /* ...and copy to v0 */
- decrypt_block v0, w3, x2, x6, w7
+ decrypt_block v0, w22, x21, 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}, [x0], #16
- subs w4, w4, #1
+ st1 {v0.16b}, [x19], #16
+ subs w23, w23, #1
bne .Lcbcdecloop
.Lcbcdecout:
- st1 {v7.16b}, [x5] /* return iv */
- ldp x29, x30, [sp], #16
+ st1 {v7.16b}, [x24] /* return iv */
+ frame_pop
ret
AES_ENDPROC(aes_cbc_decrypt)
@@ -176,19 +212,26 @@ AES_ENDPROC(aes_cbc_decrypt)
*/
AES_ENTRY(aes_ctr_encrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 6
- enc_prepare w3, x2, x6
- ld1 {v4.16b}, [x5]
+ 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]
umov x6, v4.d[1] /* keep swabbed ctr in reg */
rev x6, x6
- cmn w6, w4 /* 32 bit overflow? */
- bcs .Lctrloop
.LctrloopNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lctr1x
+ cmn w6, #4 /* 32 bit overflow? */
+ bcs .Lctr1x
ldr q8, =0x30000000200000001 /* addends 1,2,3[,0] */
dup v7.4s, w6
mov v0.16b, v4.16b
@@ -200,25 +243,27 @@ AES_ENTRY(aes_ctr_encrypt)
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}, [x1], #48 /* get 3 input blocks */
+ ld1 {v5.16b-v7.16b}, [x20], #48 /* get 3 input blocks */
bl aes_encrypt_block4x
eor v0.16b, v5.16b, v0.16b
- ld1 {v5.16b}, [x1], #16 /* get 1 input block */
+ ld1 {v5.16b}, [x20], #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}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
add x6, x6, #4
rev x7, x6
ins v4.d[1], x7
- cbz w4, .Lctrout
+ cbz w23, .Lctrout
+ st1 {v4.16b}, [x24] /* return next CTR value */
+ cond_yield_neon .Lctrrestart
b .LctrloopNx
.Lctr1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lctrout
.Lctrloop:
mov v0.16b, v4.16b
- encrypt_block v0, w3, x2, x8, w7
+ encrypt_block v0, w22, x21, x8, w7
adds x6, x6, #1 /* increment BE ctr */
rev x7, x6
@@ -226,22 +271,22 @@ AES_ENTRY(aes_ctr_encrypt)
bcs .Lctrcarry /* overflow? */
.Lctrcarrydone:
- subs w4, w4, #1
+ subs w23, w23, #1
bmi .Lctrtailblock /* blocks <0 means tail block */
- ld1 {v3.16b}, [x1], #16
+ ld1 {v3.16b}, [x20], #16
eor v3.16b, v0.16b, v3.16b
- st1 {v3.16b}, [x0], #16
+ st1 {v3.16b}, [x19], #16
bne .Lctrloop
.Lctrout:
- st1 {v4.16b}, [x5] /* return next CTR value */
- ldp x29, x30, [sp], #16
+ st1 {v4.16b}, [x24] /* return next CTR value */
+.Lctrret:
+ frame_pop
ret
.Lctrtailblock:
- st1 {v0.16b}, [x0]
- ldp x29, x30, [sp], #16
- ret
+ st1 {v0.16b}, [x19]
+ b .Lctrret
.Lctrcarry:
umov x7, v4.d[0] /* load upper word of ctr */
@@ -274,10 +319,16 @@ CPU_LE( .quad 1, 0x87 )
CPU_BE( .quad 0x87, 1 )
AES_ENTRY(aes_xts_encrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 6
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x6
- ld1 {v4.16b}, [x6]
+ ld1 {v4.16b}, [x24]
cbz w7, .Lxtsencnotfirst
enc_prepare w3, x5, x8
@@ -286,15 +337,17 @@ AES_ENTRY(aes_xts_encrypt)
ldr q7, .Lxts_mul_x
b .LxtsencNx
+.Lxtsencrestart:
+ ld1 {v4.16b}, [x24]
.Lxtsencnotfirst:
- enc_prepare w3, x2, x8
+ enc_prepare w22, x21, x8
.LxtsencloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsencNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lxtsenc1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 pt blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 pt blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
next_tweak v6, v5, v7, v8
@@ -307,35 +360,43 @@ AES_ENTRY(aes_xts_encrypt)
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}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
mov v4.16b, v7.16b
- cbz w4, .Lxtsencout
+ cbz w23, .Lxtsencout
+ st1 {v4.16b}, [x24]
+ cond_yield_neon .Lxtsencrestart
b .LxtsencloopNx
.Lxtsenc1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lxtsencout
.Lxtsencloop:
- ld1 {v1.16b}, [x1], #16
+ ld1 {v1.16b}, [x20], #16
eor v0.16b, v1.16b, v4.16b
- encrypt_block v0, w3, x2, x8, w7
+ encrypt_block v0, w22, x21, x8, w7
eor v0.16b, v0.16b, v4.16b
- st1 {v0.16b}, [x0], #16
- subs w4, w4, #1
+ st1 {v0.16b}, [x19], #16
+ subs w23, w23, #1
beq .Lxtsencout
next_tweak v4, v4, v7, v8
b .Lxtsencloop
.Lxtsencout:
- st1 {v4.16b}, [x6]
- ldp x29, x30, [sp], #16
+ st1 {v4.16b}, [x24]
+ frame_pop
ret
AES_ENDPROC(aes_xts_encrypt)
AES_ENTRY(aes_xts_decrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 6
- ld1 {v4.16b}, [x6]
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x6
+
+ ld1 {v4.16b}, [x24]
cbz w7, .Lxtsdecnotfirst
enc_prepare w3, x5, x8
@@ -344,15 +405,17 @@ AES_ENTRY(aes_xts_decrypt)
ldr q7, .Lxts_mul_x
b .LxtsdecNx
+.Lxtsdecrestart:
+ ld1 {v4.16b}, [x24]
.Lxtsdecnotfirst:
- dec_prepare w3, x2, x8
+ dec_prepare w22, x21, x8
.LxtsdecloopNx:
ldr q7, .Lxts_mul_x
next_tweak v4, v4, v7, v8
.LxtsdecNx:
- subs w4, w4, #4
+ subs w23, w23, #4
bmi .Lxtsdec1x
- ld1 {v0.16b-v3.16b}, [x1], #64 /* get 4 ct blocks */
+ ld1 {v0.16b-v3.16b}, [x20], #64 /* get 4 ct blocks */
next_tweak v5, v4, v7, v8
eor v0.16b, v0.16b, v4.16b
next_tweak v6, v5, v7, v8
@@ -365,26 +428,28 @@ AES_ENTRY(aes_xts_decrypt)
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}, [x0], #64
+ st1 {v0.16b-v3.16b}, [x19], #64
mov v4.16b, v7.16b
- cbz w4, .Lxtsdecout
+ cbz w23, .Lxtsdecout
+ st1 {v4.16b}, [x24]
+ cond_yield_neon .Lxtsdecrestart
b .LxtsdecloopNx
.Lxtsdec1x:
- adds w4, w4, #4
+ adds w23, w23, #4
beq .Lxtsdecout
.Lxtsdecloop:
- ld1 {v1.16b}, [x1], #16
+ ld1 {v1.16b}, [x20], #16
eor v0.16b, v1.16b, v4.16b
- decrypt_block v0, w3, x2, x8, w7
+ decrypt_block v0, w22, x21, x8, w7
eor v0.16b, v0.16b, v4.16b
- st1 {v0.16b}, [x0], #16
- subs w4, w4, #1
+ st1 {v0.16b}, [x19], #16
+ subs w23, w23, #1
beq .Lxtsdecout
next_tweak v4, v4, v7, v8
b .Lxtsdecloop
.Lxtsdecout:
- st1 {v4.16b}, [x6]
- ldp x29, x30, [sp], #16
+ st1 {v4.16b}, [x24]
+ frame_pop
ret
AES_ENDPROC(aes_xts_decrypt)
@@ -393,43 +458,61 @@ AES_ENDPROC(aes_xts_decrypt)
* int blocks, u8 dg[], int enc_before, int enc_after)
*/
AES_ENTRY(aes_mac_update)
- ld1 {v0.16b}, [x4] /* get dg */
+ frame_push 6
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x6
+
+ ld1 {v0.16b}, [x23] /* get dg */
enc_prepare w2, x1, x7
cbz w5, .Lmacloop4x
encrypt_block v0, w2, x1, x7, w8
.Lmacloop4x:
- subs w3, w3, #4
+ subs w22, w22, #4
bmi .Lmac1x
- ld1 {v1.16b-v4.16b}, [x0], #64 /* get next pt block */
+ ld1 {v1.16b-v4.16b}, [x19], #64 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */
- encrypt_block v0, w2, x1, x7, w8
+ encrypt_block v0, w21, x20, x7, w8
eor v0.16b, v0.16b, v2.16b
- encrypt_block v0, w2, x1, x7, w8
+ encrypt_block v0, w21, x20, x7, w8
eor v0.16b, v0.16b, v3.16b
- encrypt_block v0, w2, x1, x7, w8
+ encrypt_block v0, w21, x20, x7, w8
eor v0.16b, v0.16b, v4.16b
- cmp w3, wzr
- csinv x5, x6, xzr, eq
+ cmp w22, wzr
+ csinv x5, x24, xzr, eq
cbz w5, .Lmacout
- encrypt_block v0, w2, x1, x7, w8
+ encrypt_block v0, w21, x20, x7, w8
+ st1 {v0.16b}, [x23] /* return dg */
+ cond_yield_neon .Lmacrestart
b .Lmacloop4x
.Lmac1x:
- add w3, w3, #4
+ add w22, w22, #4
.Lmacloop:
- cbz w3, .Lmacout
- ld1 {v1.16b}, [x0], #16 /* get next pt block */
+ cbz w22, .Lmacout
+ ld1 {v1.16b}, [x19], #16 /* get next pt block */
eor v0.16b, v0.16b, v1.16b /* ..and xor with dg */
- subs w3, w3, #1
- csinv x5, x6, xzr, eq
+ subs w22, w22, #1
+ csinv x5, x24, xzr, eq
cbz w5, .Lmacout
- encrypt_block v0, w2, x1, x7, w8
+.Lmacenc:
+ encrypt_block v0, w21, x20, x7, w8
b .Lmacloop
.Lmacout:
- st1 {v0.16b}, [x4] /* return dg */
+ st1 {v0.16b}, [x23] /* return dg */
+ frame_pop
ret
+
+.Lmacrestart:
+ ld1 {v0.16b}, [x23] /* get dg */
+ enc_prepare w21, x20, x0
+ b .Lmacloop4x
AES_ENDPROC(aes_mac_update)
diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S
index ca0472500433..e613a87f8b53 100644
--- a/arch/arm64/crypto/aes-neonbs-core.S
+++ b/arch/arm64/crypto/aes-neonbs-core.S
@@ -565,54 +565,61 @@ ENDPROC(aesbs_decrypt8)
* int blocks)
*/
.macro __ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 5
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
99: mov x5, #1
- lsl x5, x5, x4
- subs w4, w4, #8
- csel x4, x4, xzr, pl
+ lsl x5, x5, x23
+ subs w23, w23, #8
+ csel x23, x23, xzr, pl
csel x5, x5, xzr, mi
- ld1 {v0.16b}, [x1], #16
+ ld1 {v0.16b}, [x20], #16
tbnz x5, #1, 0f
- ld1 {v1.16b}, [x1], #16
+ ld1 {v1.16b}, [x20], #16
tbnz x5, #2, 0f
- ld1 {v2.16b}, [x1], #16
+ ld1 {v2.16b}, [x20], #16
tbnz x5, #3, 0f
- ld1 {v3.16b}, [x1], #16
+ ld1 {v3.16b}, [x20], #16
tbnz x5, #4, 0f
- ld1 {v4.16b}, [x1], #16
+ ld1 {v4.16b}, [x20], #16
tbnz x5, #5, 0f
- ld1 {v5.16b}, [x1], #16
+ ld1 {v5.16b}, [x20], #16
tbnz x5, #6, 0f
- ld1 {v6.16b}, [x1], #16
+ ld1 {v6.16b}, [x20], #16
tbnz x5, #7, 0f
- ld1 {v7.16b}, [x1], #16
+ ld1 {v7.16b}, [x20], #16
-0: mov bskey, x2
- mov rounds, x3
+0: mov bskey, x21
+ mov rounds, x22
bl \do8
- st1 {\o0\().16b}, [x0], #16
+ st1 {\o0\().16b}, [x19], #16
tbnz x5, #1, 1f
- st1 {\o1\().16b}, [x0], #16
+ st1 {\o1\().16b}, [x19], #16
tbnz x5, #2, 1f
- st1 {\o2\().16b}, [x0], #16
+ st1 {\o2\().16b}, [x19], #16
tbnz x5, #3, 1f
- st1 {\o3\().16b}, [x0], #16
+ st1 {\o3\().16b}, [x19], #16
tbnz x5, #4, 1f
- st1 {\o4\().16b}, [x0], #16
+ st1 {\o4\().16b}, [x19], #16
tbnz x5, #5, 1f
- st1 {\o5\().16b}, [x0], #16
+ st1 {\o5\().16b}, [x19], #16
tbnz x5, #6, 1f
- st1 {\o6\().16b}, [x0], #16
+ st1 {\o6\().16b}, [x19], #16
tbnz x5, #7, 1f
- st1 {\o7\().16b}, [x0], #16
+ st1 {\o7\().16b}, [x19], #16
- cbnz x4, 99b
+ cbz x23, 1f
+ cond_yield_neon
+ b 99b
-1: ldp x29, x30, [sp], #16
+1: frame_pop
ret
.endm
@@ -632,43 +639,49 @@ ENDPROC(aesbs_ecb_decrypt)
*/
.align 4
ENTRY(aesbs_cbc_decrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
+ frame_push 6
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
99: mov x6, #1
- lsl x6, x6, x4
- subs w4, w4, #8
- csel x4, x4, xzr, pl
+ lsl x6, x6, x23
+ subs w23, w23, #8
+ csel x23, x23, xzr, pl
csel x6, x6, xzr, mi
- ld1 {v0.16b}, [x1], #16
+ ld1 {v0.16b}, [x20], #16
mov v25.16b, v0.16b
tbnz x6, #1, 0f
- ld1 {v1.16b}, [x1], #16
+ ld1 {v1.16b}, [x20], #16
mov v26.16b, v1.16b
tbnz x6, #2, 0f
- ld1 {v2.16b}, [x1], #16
+ ld1 {v2.16b}, [x20], #16
mov v27.16b, v2.16b
tbnz x6, #3, 0f
- ld1 {v3.16b}, [x1], #16
+ ld1 {v3.16b}, [x20], #16
mov v28.16b, v3.16b
tbnz x6, #4, 0f
- ld1 {v4.16b}, [x1], #16
+ ld1 {v4.16b}, [x20], #16
mov v29.16b, v4.16b
tbnz x6, #5, 0f
- ld1 {v5.16b}, [x1], #16
+ ld1 {v5.16b}, [x20], #16
mov v30.16b, v5.16b
tbnz x6, #6, 0f
- ld1 {v6.16b}, [x1], #16
+ ld1 {v6.16b}, [x20], #16
mov v31.16b, v6.16b
tbnz x6, #7, 0f
- ld1 {v7.16b}, [x1]
+ ld1 {v7.16b}, [x20]
-0: mov bskey, x2
- mov rounds, x3
+0: mov bskey, x21
+ mov rounds, x22
bl aesbs_decrypt8
- ld1 {v24.16b}, [x5] // load IV
+ ld1 {v24.16b}, [x24] // load IV
eor v1.16b, v1.16b, v25.16b
eor v6.16b, v6.16b, v26.16b
@@ -679,34 +692,36 @@ ENTRY(aesbs_cbc_decrypt)
eor v3.16b, v3.16b, v30.16b
eor v5.16b, v5.16b, v31.16b
- st1 {v0.16b}, [x0], #16
+ st1 {v0.16b}, [x19], #16
mov v24.16b, v25.16b
tbnz x6, #1, 1f
- st1 {v1.16b}, [x0], #16
+ st1 {v1.16b}, [x19], #16
mov v24.16b, v26.16b
tbnz x6, #2, 1f
- st1 {v6.16b}, [x0], #16
+ st1 {v6.16b}, [x19], #16
mov v24.16b, v27.16b
tbnz x6, #3, 1f
- st1 {v4.16b}, [x0], #16
+ st1 {v4.16b}, [x19], #16
mov v24.16b, v28.16b
tbnz x6, #4, 1f
- st1 {v2.16b}, [x0], #16
+ st1 {v2.16b}, [x19], #16
mov v24.16b, v29.16b
tbnz x6, #5, 1f
- st1 {v7.16b}, [x0], #16
+ st1 {v7.16b}, [x19], #16
mov v24.16b, v30.16b
tbnz x6, #6, 1f
- st1 {v3.16b}, [x0], #16
+ st1 {v3.16b}, [x19], #16
mov v24.16b, v31.16b
tbnz x6, #7, 1f
- ld1 {v24.16b}, [x1], #16
- st1 {v5.16b}, [x0], #16
-1: st1 {v24.16b}, [x5] // store IV
+ ld1 {v24.16b}, [x20], #16
+ st1 {v5.16b}, [x19], #16
+1: st1 {v24.16b}, [x24] // store IV
- cbnz x4, 99b
+ cbz x23, 2f
+ cond_yield_neon
+ b 99b
- ldp x29, x30, [sp], #16
+2: frame_pop
ret
ENDPROC(aesbs_cbc_decrypt)
@@ -731,87 +746,93 @@ CPU_BE( .quad 0x87, 1 )
*/
__xts_crypt8:
mov x6, #1
- lsl x6, x6, x4
- subs w4, w4, #8
- csel x4, x4, xzr, pl
+ lsl x6, x6, x23
+ subs w23, w23, #8
+ csel x23, x23, xzr, pl
csel x6, x6, xzr, mi
- ld1 {v0.16b}, [x1], #16
+ ld1 {v0.16b}, [x20], #16
next_tweak v26, v25, v30, v31
eor v0.16b, v0.16b, v25.16b
tbnz x6, #1, 0f
- ld1 {v1.16b}, [x1], #16
+ ld1 {v1.16b}, [x20], #16
next_tweak v27, v26, v30, v31
eor v1.16b, v1.16b, v26.16b
tbnz x6, #2, 0f
- ld1 {v2.16b}, [x1], #16
+ ld1 {v2.16b}, [x20], #16
next_tweak v28, v27, v30, v31
eor v2.16b, v2.16b, v27.16b
tbnz x6, #3, 0f
- ld1 {v3.16b}, [x1], #16
+ ld1 {v3.16b}, [x20], #16
next_tweak v29, v28, v30, v31
eor v3.16b, v3.16b, v28.16b
tbnz x6, #4, 0f
- ld1 {v4.16b}, [x1], #16
- str q29, [sp, #16]
+ ld1 {v4.16b}, [x20], #16
+ str q29, [sp, #.Lframe_local_offset]
eor v4.16b, v4.16b, v29.16b
next_tweak v29, v29, v30, v31
tbnz x6, #5, 0f
- ld1 {v5.16b}, [x1], #16
- str q29, [sp, #32]
+ ld1 {v5.16b}, [x20], #16
+ str q29, [sp, #.Lframe_local_offset + 16]
eor v5.16b, v5.16b, v29.16b
next_tweak v29, v29, v30, v31
tbnz x6, #6, 0f
- ld1 {v6.16b}, [x1], #16
- str q29, [sp, #48]
+ ld1 {v6.16b}, [x20], #16
+ str q29, [sp, #.Lframe_local_offset + 32]
eor v6.16b, v6.16b, v29.16b
next_tweak v29, v29, v30, v31
tbnz x6, #7, 0f
- ld1 {v7.16b}, [x1], #16
- str q29, [sp, #64]
+ ld1 {v7.16b}, [x20], #16
+ str q29, [sp, #.Lframe_local_offset + 48]
eor v7.16b, v7.16b, v29.16b
next_tweak v29, v29, v30, v31
-0: mov bskey, x2
- mov rounds, x3
+0: mov bskey, x21
+ mov rounds, x22
br x7
ENDPROC(__xts_crypt8)
.macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
- stp x29, x30, [sp, #-80]!
- mov x29, sp
+ frame_push 6, 64
- ldr q30, .Lxts_mul_x
- ld1 {v25.16b}, [x5]
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
+
+0: ldr q30, .Lxts_mul_x
+ ld1 {v25.16b}, [x24]
99: adr x7, \do8
bl __xts_crypt8
- ldp q16, q17, [sp, #16]
- ldp q18, q19, [sp, #48]
+ ldp q16, q17, [sp, #.Lframe_local_offset]
+ ldp q18, q19, [sp, #.Lframe_local_offset + 32]
eor \o0\().16b, \o0\().16b, v25.16b
eor \o1\().16b, \o1\().16b, v26.16b
eor \o2\().16b, \o2\().16b, v27.16b
eor \o3\().16b, \o3\().16b, v28.16b
- st1 {\o0\().16b}, [x0], #16
+ st1 {\o0\().16b}, [x19], #16
mov v25.16b, v26.16b
tbnz x6, #1, 1f
- st1 {\o1\().16b}, [x0], #16
+ st1 {\o1\().16b}, [x19], #16
mov v25.16b, v27.16b
tbnz x6, #2, 1f
- st1 {\o2\().16b}, [x0], #16
+ st1 {\o2\().16b}, [x19], #16
mov v25.16b, v28.16b
tbnz x6, #3, 1f
- st1 {\o3\().16b}, [x0], #16
+ st1 {\o3\().16b}, [x19], #16
mov v25.16b, v29.16b
tbnz x6, #4, 1f
@@ -820,18 +841,22 @@ ENDPROC(__xts_crypt8)
eor \o6\().16b, \o6\().16b, v18.16b
eor \o7\().16b, \o7\().16b, v19.16b
- st1 {\o4\().16b}, [x0], #16
+ st1 {\o4\().16b}, [x19], #16
tbnz x6, #5, 1f
- st1 {\o5\().16b}, [x0], #16
+ st1 {\o5\().16b}, [x19], #16
tbnz x6, #6, 1f
- st1 {\o6\().16b}, [x0], #16
+ st1 {\o6\().16b}, [x19], #16
tbnz x6, #7, 1f
- st1 {\o7\().16b}, [x0], #16
+ st1 {\o7\().16b}, [x19], #16
+
+ cbz x23, 1f
+ st1 {v25.16b}, [x24]
- cbnz x4, 99b
+ cond_yield_neon 0b
+ b 99b
-1: st1 {v25.16b}, [x5]
- ldp x29, x30, [sp], #80
+1: st1 {v25.16b}, [x24]
+ frame_pop
ret
.endm
@@ -856,24 +881,31 @@ ENDPROC(aesbs_xts_decrypt)
* int rounds, int blocks, u8 iv[], u8 final[])
*/
ENTRY(aesbs_ctr_encrypt)
- stp x29, x30, [sp, #-16]!
- mov x29, sp
-
- cmp x6, #0
- cset x10, ne
- add x4, x4, x10 // do one extra block if final
-
- ldp x7, x8, [x5]
- ld1 {v0.16b}, [x5]
+ frame_push 8
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
+ mov x25, x6
+
+ cmp x25, #0
+ cset x26, ne
+ add x23, x23, x26 // do one extra block if final
+
+98: ldp x7, x8, [x24]
+ ld1 {v0.16b}, [x24]
CPU_LE( rev x7, x7 )
CPU_LE( rev x8, x8 )
adds x8, x8, #1
adc x7, x7, xzr
99: mov x9, #1
- lsl x9, x9, x4
- subs w4, w4, #8
- csel x4, x4, xzr, pl
+ lsl x9, x9, x23
+ subs w23, w23, #8
+ csel x23, x23, xzr, pl
csel x9, x9, xzr, le
tbnz x9, #1, 0f
@@ -891,82 +923,85 @@ CPU_LE( rev x8, x8 )
tbnz x9, #7, 0f
next_ctr v7
-0: mov bskey, x2
- mov rounds, x3
+0: mov bskey, x21
+ mov rounds, x22
bl aesbs_encrypt8
- lsr x9, x9, x10 // disregard the extra block
+ lsr x9, x9, x26 // disregard the extra block
tbnz x9, #0, 0f
- ld1 {v8.16b}, [x1], #16
+ ld1 {v8.16b}, [x20], #16
eor v0.16b, v0.16b, v8.16b
- st1 {v0.16b}, [x0], #16
+ st1 {v0.16b}, [x19], #16
tbnz x9, #1, 1f
- ld1 {v9.16b}, [x1], #16
+ ld1 {v9.16b}, [x20], #16
eor v1.16b, v1.16b, v9.16b
- st1 {v1.16b}, [x0], #16
+ st1 {v1.16b}, [x19], #16
tbnz x9, #2, 2f
- ld1 {v10.16b}, [x1], #16
+ ld1 {v10.16b}, [x20], #16
eor v4.16b, v4.16b, v10.16b
- st1 {v4.16b}, [x0], #16
+ st1 {v4.16b}, [x19], #16
tbnz x9, #3, 3f
- ld1 {v11.16b}, [x1], #16
+ ld1 {v11.16b}, [x20], #16
eor v6.16b, v6.16b, v11.16b
- st1 {v6.16b}, [x0], #16
+ st1 {v6.16b}, [x19], #16
tbnz x9, #4, 4f
- ld1 {v12.16b}, [x1], #16
+ ld1 {v12.16b}, [x20], #16
eor v3.16b, v3.16b, v12.16b
- st1 {v3.16b}, [x0], #16
+ st1 {v3.16b}, [x19], #16
tbnz x9, #5, 5f
- ld1 {v13.16b}, [x1], #16
+ ld1 {v13.16b}, [x20], #16
eor v7.16b, v7.16b, v13.16b
- st1 {v7.16b}, [x0], #16
+ st1 {v7.16b}, [x19], #16
tbnz x9, #6, 6f
- ld1 {v14.16b}, [x1], #16
+ ld1 {v14.16b}, [x20], #16
eor v2.16b, v2.16b, v14.16b
- st1 {v2.16b}, [x0], #16
+ st1 {v2.16b}, [x19], #16
tbnz x9, #7, 7f
- ld1 {v15.16b}, [x1], #16
+ ld1 {v15.16b}, [x20], #16
eor v5.16b, v5.16b, v15.16b
- st1 {v5.16b}, [x0], #16
+ st1 {v5.16b}, [x19], #16
8: next_ctr v0
- cbnz x4, 99b
+ st1 {v0.16b}, [x24]
+ cbz x23, 0f
+
+ cond_yield_neon 98b
+ b 99b
-0: st1 {v0.16b}, [x5]
- ldp x29, x30, [sp], #16
+0: frame_pop
ret
/*
* If we are handling the tail of the input (x6 != NULL), return the
* final keystream block back to the caller.
*/
-1: cbz x6, 8b
- st1 {v1.16b}, [x6]
+1: cbz x25, 8b
+ st1 {v1.16b}, [x25]
b 8b
-2: cbz x6, 8b
- st1 {v4.16b}, [x6]
+2: cbz x25, 8b
+ st1 {v4.16b}, [x25]
b 8b
-3: cbz x6, 8b
- st1 {v6.16b}, [x6]
+3: cbz x25, 8b
+ st1 {v6.16b}, [x25]
b 8b
-4: cbz x6, 8b
- st1 {v3.16b}, [x6]
+4: cbz x25, 8b
+ st1 {v3.16b}, [x25]
b 8b
-5: cbz x6, 8b
- st1 {v7.16b}, [x6]
+5: cbz x25, 8b
+ st1 {v7.16b}, [x25]
b 8b
-6: cbz x6, 8b
- st1 {v2.16b}, [x6]
+6: cbz x25, 8b
+ st1 {v2.16b}, [x25]
b 8b
-7: cbz x6, 8b
- st1 {v5.16b}, [x6]
+7: cbz x25, 8b
+ st1 {v5.16b}, [x25]
b 8b
ENDPROC(aesbs_ctr_encrypt)
diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S
index 16ed3c7ebd37..8061bf0f9c66 100644
--- a/arch/arm64/crypto/crc32-ce-core.S
+++ b/arch/arm64/crypto/crc32-ce-core.S
@@ -100,9 +100,10 @@
dCONSTANT .req d0
qCONSTANT .req q0
- BUF .req x0
- LEN .req x1
- CRC .req x2
+ BUF .req x19
+ LEN .req x20
+ CRC .req x21
+ CONST .req x22
vzr .req v9
@@ -123,7 +124,14 @@ ENTRY(crc32_pmull_le)
ENTRY(crc32c_pmull_le)
adr_l x3, .Lcrc32c_constants
-0: bic LEN, LEN, #15
+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
@@ -132,7 +140,7 @@ ENTRY(crc32c_pmull_le)
cmp LEN, #0x40
b.lt less_64
- ldr qCONSTANT, [x3]
+ ldr qCONSTANT, [CONST]
loop_64: /* 64 bytes Full cache line folding */
sub LEN, LEN, #0x40
@@ -162,10 +170,21 @@ loop_64: /* 64 bytes Full cache line folding */
eor v4.16b, v4.16b, v8.16b
cmp LEN, #0x40
- b.ge loop_64
+ 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, [x3, #16]
+ ldr qCONSTANT, [CONST, #16]
pmull2 v5.1q, v1.2d, vCONSTANT.2d
pmull v1.1q, v1.1d, vCONSTANT.1d
@@ -204,8 +223,8 @@ fold_64:
eor v1.16b, v1.16b, v2.16b
/* final 32-bit fold */
- ldr dCONSTANT, [x3, #32]
- ldr d3, [x3, #40]
+ ldr dCONSTANT, [CONST, #32]
+ ldr d3, [CONST, #40]
ext v2.16b, v1.16b, vzr.16b, #4
and v1.16b, v1.16b, v3.16b
@@ -213,7 +232,7 @@ fold_64:
eor v1.16b, v1.16b, v2.16b
/* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */
- ldr qCONSTANT, [x3, #48]
+ ldr qCONSTANT, [CONST, #48]
and v2.16b, v1.16b, v3.16b
ext v2.16b, vzr.16b, v2.16b, #8
@@ -223,6 +242,7 @@ fold_64:
eor v1.16b, v1.16b, v2.16b
mov w0, v1.s[1]
+ frame_pop
ret
ENDPROC(crc32_pmull_le)
ENDPROC(crc32c_pmull_le)
diff --git a/arch/arm64/crypto/crct10dif-ce-core.S b/arch/arm64/crypto/crct10dif-ce-core.S
index f179c01bd55c..663ea71cdb38 100644
--- a/arch/arm64/crypto/crct10dif-ce-core.S
+++ b/arch/arm64/crypto/crct10dif-ce-core.S
@@ -74,13 +74,19 @@
.text
.cpu generic+crypto
- arg1_low32 .req w0
- arg2 .req x1
- arg3 .req x2
+ arg1_low32 .req w19
+ arg2 .req x20
+ arg3 .req x21
vzr .req v13
ENTRY(crc_t10dif_pmull)
+ frame_push 3, 128
+
+ mov arg1_low32, w0
+ mov arg2, x1
+ mov arg3, x2
+
movi vzr.16b, #0 // init zero register
// adjust the 16-bit initial_crc value, scale it to 32 bits
@@ -175,8 +181,25 @@ CPU_LE( ext v12.16b, v12.16b, v12.16b, #8 )
subs arg3, arg3, #128
// check if there is another 64B in the buffer to be able to fold
- b.ge _fold_64_B_loop
+ b.lt _fold_64_B_end
+
+ if_will_cond_yield_neon
+ stp q0, q1, [sp, #.Lframe_local_offset]
+ stp q2, q3, [sp, #.Lframe_local_offset + 32]
+ stp q4, q5, [sp, #.Lframe_local_offset + 64]
+ stp q6, q7, [sp, #.Lframe_local_offset + 96]
+ do_cond_yield_neon
+ ldp q0, q1, [sp, #.Lframe_local_offset]
+ ldp q2, q3, [sp, #.Lframe_local_offset + 32]
+ ldp q4, q5, [sp, #.Lframe_local_offset + 64]
+ ldp q6, q7, [sp, #.Lframe_local_offset + 96]
+ ldr_l q10, rk3, x8
+ movi vzr.16b, #0 // init zero register
+ endif_yield_neon
+
+ b _fold_64_B_loop
+_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
@@ -304,6 +327,7 @@ _barrett:
_cleanup:
// scale the result back to 16 bits
lsr x0, x0, #16
+ frame_pop
ret
_less_than_128:
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 11ebf1ae248a..dcffb9e77589 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -213,22 +213,31 @@
.endm
.macro __pmull_ghash, pn
- ld1 {SHASH.2d}, [x3]
- ld1 {XL.2d}, [x1]
+ frame_push 5
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+
+0: ld1 {SHASH.2d}, [x22]
+ ld1 {XL.2d}, [x20]
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
eor SHASH2.16b, SHASH2.16b, SHASH.16b
__pmull_pre_\pn
/* do the head block first, if supplied */
- cbz x4, 0f
- ld1 {T1.2d}, [x4]
- b 1f
+ cbz x23, 1f
+ ld1 {T1.2d}, [x23]
+ mov x23, xzr
+ b 2f
-0: ld1 {T1.2d}, [x2], #16
- sub w0, w0, #1
+1: ld1 {T1.2d}, [x21], #16
+ sub w19, w19, #1
-1: /* multiply XL by SHASH in GF(2^128) */
+2: /* multiply XL by SHASH in GF(2^128) */
CPU_LE( rev64 T1.16b, T1.16b )
ext T2.16b, XL.16b, XL.16b, #8
@@ -250,9 +259,18 @@ CPU_LE( rev64 T1.16b, T1.16b )
eor T2.16b, T2.16b, XH.16b
eor XL.16b, XL.16b, T2.16b
- cbnz w0, 0b
+ cbz w19, 3f
+
+ if_will_cond_yield_neon
+ st1 {XL.2d}, [x20]
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+
+ b 1b
- st1 {XL.2d}, [x1]
+3: st1 {XL.2d}, [x20]
+ frame_pop
ret
.endm
@@ -304,38 +322,55 @@ ENDPROC(pmull_ghash_update_p8)
.endm
.macro pmull_gcm_do_crypt, enc
- ld1 {SHASH.2d}, [x4]
- ld1 {XL.2d}, [x1]
- ldr x8, [x5, #8] // load lower counter
+ frame_push 10
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+ mov x23, x4
+ mov x24, x5
+ mov x25, x6
+ mov x26, x7
+ .if \enc == 1
+ ldr x27, [sp, #96] // first stacked arg
+ .endif
+
+ ldr x28, [x24, #8] // load lower counter
+CPU_LE( rev x28, x28 )
+
+0: mov x0, x25
+ load_round_keys w26, x0
+ ld1 {SHASH.2d}, [x23]
+ ld1 {XL.2d}, [x20]
movi MASK.16b, #0xe1
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
-CPU_LE( rev x8, x8 )
shl MASK.2d, MASK.2d, #57
eor SHASH2.16b, SHASH2.16b, SHASH.16b
.if \enc == 1
- ld1 {KS.16b}, [x7]
+ ld1 {KS.16b}, [x27]
.endif
-0: ld1 {CTR.8b}, [x5] // load upper counter
- ld1 {INP.16b}, [x3], #16
- rev x9, x8
- add x8, x8, #1
- sub w0, w0, #1
+1: ld1 {CTR.8b}, [x24] // load upper counter
+ ld1 {INP.16b}, [x22], #16
+ rev x9, x28
+ add x28, x28, #1
+ sub w19, w19, #1
ins CTR.d[1], x9 // set lower counter
.if \enc == 1
eor INP.16b, INP.16b, KS.16b // encrypt input
- st1 {INP.16b}, [x2], #16
+ st1 {INP.16b}, [x21], #16
.endif
rev64 T1.16b, INP.16b
- cmp w6, #12
- b.ge 2f // AES-192/256?
+ cmp w26, #12
+ b.ge 4f // AES-192/256?
-1: enc_round CTR, v21
+2: enc_round CTR, v21
ext T2.16b, XL.16b, XL.16b, #8
ext IN1.16b, T1.16b, T1.16b, #8
@@ -390,27 +425,39 @@ CPU_LE( rev x8, x8 )
.if \enc == 0
eor INP.16b, INP.16b, KS.16b
- st1 {INP.16b}, [x2], #16
+ st1 {INP.16b}, [x21], #16
.endif
- cbnz w0, 0b
+ cbz w19, 3f
-CPU_LE( rev x8, x8 )
- st1 {XL.2d}, [x1]
- str x8, [x5, #8] // store lower counter
+ if_will_cond_yield_neon
+ st1 {XL.2d}, [x20]
+ .if \enc == 1
+ st1 {KS.16b}, [x27]
+ .endif
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+ b 1b
+
+3: st1 {XL.2d}, [x20]
.if \enc == 1
- st1 {KS.16b}, [x7]
+ st1 {KS.16b}, [x27]
.endif
+CPU_LE( rev x28, x28 )
+ str x28, [x24, #8] // store lower counter
+
+ frame_pop
ret
-2: b.eq 3f // AES-192?
+4: b.eq 5f // AES-192?
enc_round CTR, v17
enc_round CTR, v18
-3: enc_round CTR, v19
+5: enc_round CTR, v19
enc_round CTR, v20
- b 1b
+ b 2b
.endm
/*
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index cfc9c92814fd..7cf0b1aa6ea8 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -63,11 +63,12 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
const u8 src[], struct ghash_key const *k,
- u8 ctr[], int rounds, u8 ks[]);
+ u8 ctr[], u32 const rk[], int rounds,
+ u8 ks[]);
asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
const u8 src[], struct ghash_key const *k,
- u8 ctr[], int rounds);
+ u8 ctr[], u32 const rk[], int rounds);
asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
u32 const rk[], int rounds);
@@ -368,26 +369,29 @@ static int gcm_encrypt(struct aead_request *req)
pmull_gcm_encrypt_block(ks, iv, NULL,
num_rounds(&ctx->aes_key));
put_unaligned_be32(3, iv + GCM_IV_SIZE);
+ kernel_neon_end();
- err = skcipher_walk_aead_encrypt(&walk, req, true);
+ err = skcipher_walk_aead_encrypt(&walk, req, false);
while (walk.nbytes >= AES_BLOCK_SIZE) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
+ kernel_neon_begin();
pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
walk.src.virt.addr, &ctx->ghash_key,
- iv, num_rounds(&ctx->aes_key), ks);
+ iv, ctx->aes_key.key_enc,
+ num_rounds(&ctx->aes_key), ks);
+ kernel_neon_end();
err = skcipher_walk_done(&walk,
walk.nbytes % AES_BLOCK_SIZE);
}
- kernel_neon_end();
} else {
__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
num_rounds(&ctx->aes_key));
put_unaligned_be32(2, iv + GCM_IV_SIZE);
- err = skcipher_walk_aead_encrypt(&walk, req, true);
+ err = skcipher_walk_aead_encrypt(&walk, req, false);
while (walk.nbytes >= AES_BLOCK_SIZE) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
@@ -467,15 +471,19 @@ static int gcm_decrypt(struct aead_request *req)
pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
num_rounds(&ctx->aes_key));
put_unaligned_be32(2, iv + GCM_IV_SIZE);
+ kernel_neon_end();
- err = skcipher_walk_aead_decrypt(&walk, req, true);
+ err = skcipher_walk_aead_decrypt(&walk, req, false);
while (walk.nbytes >= AES_BLOCK_SIZE) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
+ kernel_neon_begin();
pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
walk.src.virt.addr, &ctx->ghash_key,
- iv, num_rounds(&ctx->aes_key));
+ iv, ctx->aes_key.key_enc,
+ num_rounds(&ctx->aes_key));
+ kernel_neon_end();
err = skcipher_walk_done(&walk,
walk.nbytes % AES_BLOCK_SIZE);
@@ -483,14 +491,12 @@ static int gcm_decrypt(struct aead_request *req)
if (walk.nbytes)
pmull_gcm_encrypt_block(iv, iv, NULL,
num_rounds(&ctx->aes_key));
-
- kernel_neon_end();
} else {
__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
num_rounds(&ctx->aes_key));
put_unaligned_be32(2, iv + GCM_IV_SIZE);
- err = skcipher_walk_aead_decrypt(&walk, req, true);
+ err = skcipher_walk_aead_decrypt(&walk, req, false);
while (walk.nbytes >= AES_BLOCK_SIZE) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
diff --git a/arch/arm64/crypto/sha1-ce-core.S b/arch/arm64/crypto/sha1-ce-core.S
index 46049850727d..78eb35fb5056 100644
--- a/arch/arm64/crypto/sha1-ce-core.S
+++ b/arch/arm64/crypto/sha1-ce-core.S
@@ -69,30 +69,36 @@
* int blocks)
*/
ENTRY(sha1_ce_transform)
+ frame_push 3
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+
/* load round constants */
- loadrc k0.4s, 0x5a827999, w6
+0: loadrc k0.4s, 0x5a827999, w6
loadrc k1.4s, 0x6ed9eba1, w6
loadrc k2.4s, 0x8f1bbcdc, w6
loadrc k3.4s, 0xca62c1d6, w6
/* load state */
- ld1 {dgav.4s}, [x0]
- ldr dgb, [x0, #16]
+ ld1 {dgav.4s}, [x19]
+ ldr dgb, [x19, #16]
/* load sha1_ce_state::finalize */
ldr_l w4, sha1_ce_offsetof_finalize, x4
- ldr w4, [x0, x4]
+ ldr w4, [x19, x4]
/* load input */
-0: ld1 {v8.4s-v11.4s}, [x1], #64
- sub w2, w2, #1
+1: ld1 {v8.4s-v11.4s}, [x20], #64
+ sub w21, w21, #1
CPU_LE( rev32 v8.16b, v8.16b )
CPU_LE( rev32 v9.16b, v9.16b )
CPU_LE( rev32 v10.16b, v10.16b )
CPU_LE( rev32 v11.16b, v11.16b )
-1: add t0.4s, v8.4s, k0.4s
+2: add t0.4s, v8.4s, k0.4s
mov dg0v.16b, dgav.16b
add_update c, ev, k0, 8, 9, 10, 11, dgb
@@ -123,16 +129,25 @@ CPU_LE( rev32 v11.16b, v11.16b )
add dgbv.2s, dgbv.2s, dg1v.2s
add dgav.4s, dgav.4s, dg0v.4s
- cbnz w2, 0b
+ cbz w21, 3f
+
+ if_will_cond_yield_neon
+ st1 {dgav.4s}, [x19]
+ str dgb, [x19, #16]
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+
+ b 1b
/*
* Final block: add padding and total bit count.
* Skip if the input size was not a round multiple of the block size,
* the padding is handled by the C code in that case.
*/
- cbz x4, 3f
+3: cbz x4, 4f
ldr_l w4, sha1_ce_offsetof_count, x4
- ldr x4, [x0, x4]
+ ldr x4, [x19, x4]
movi v9.2d, #0
mov x8, #0x80000000
movi v10.2d, #0
@@ -141,10 +156,11 @@ CPU_LE( rev32 v11.16b, v11.16b )
mov x4, #0
mov v11.d[0], xzr
mov v11.d[1], x7
- b 1b
+ b 2b
/* store new state */
-3: st1 {dgav.4s}, [x0]
- str dgb, [x0, #16]
+4: st1 {dgav.4s}, [x19]
+ str dgb, [x19, #16]
+ frame_pop
ret
ENDPROC(sha1_ce_transform)
diff --git a/arch/arm64/crypto/sha2-ce-core.S b/arch/arm64/crypto/sha2-ce-core.S
index 4c3c89b812ce..cd8b36412469 100644
--- a/arch/arm64/crypto/sha2-ce-core.S
+++ b/arch/arm64/crypto/sha2-ce-core.S
@@ -79,30 +79,36 @@
*/
.text
ENTRY(sha2_ce_transform)
+ frame_push 3
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+
/* load round constants */
- adr_l x8, .Lsha2_rcon
+0: adr_l x8, .Lsha2_rcon
ld1 { v0.4s- v3.4s}, [x8], #64
ld1 { v4.4s- v7.4s}, [x8], #64
ld1 { v8.4s-v11.4s}, [x8], #64
ld1 {v12.4s-v15.4s}, [x8]
/* load state */
- ld1 {dgav.4s, dgbv.4s}, [x0]
+ ld1 {dgav.4s, dgbv.4s}, [x19]
/* load sha256_ce_state::finalize */
ldr_l w4, sha256_ce_offsetof_finalize, x4
- ldr w4, [x0, x4]
+ ldr w4, [x19, x4]
/* load input */
-0: ld1 {v16.4s-v19.4s}, [x1], #64
- sub w2, w2, #1
+1: ld1 {v16.4s-v19.4s}, [x20], #64
+ sub w21, w21, #1
CPU_LE( rev32 v16.16b, v16.16b )
CPU_LE( rev32 v17.16b, v17.16b )
CPU_LE( rev32 v18.16b, v18.16b )
CPU_LE( rev32 v19.16b, v19.16b )
-1: add t0.4s, v16.4s, v0.4s
+2: add t0.4s, v16.4s, v0.4s
mov dg0v.16b, dgav.16b
mov dg1v.16b, dgbv.16b
@@ -131,16 +137,24 @@ CPU_LE( rev32 v19.16b, v19.16b )
add dgbv.4s, dgbv.4s, dg1v.4s
/* handled all input blocks? */
- cbnz w2, 0b
+ cbz w21, 3f
+
+ if_will_cond_yield_neon
+ st1 {dgav.4s, dgbv.4s}, [x19]
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+
+ b 1b
/*
* Final block: add padding and total bit count.
* Skip if the input size was not a round multiple of the block size,
* the padding is handled by the C code in that case.
*/
- cbz x4, 3f
+3: cbz x4, 4f
ldr_l w4, sha256_ce_offsetof_count, x4
- ldr x4, [x0, x4]
+ ldr x4, [x19, x4]
movi v17.2d, #0
mov x8, #0x80000000
movi v18.2d, #0
@@ -149,9 +163,10 @@ CPU_LE( rev32 v19.16b, v19.16b )
mov x4, #0
mov v19.d[0], xzr
mov v19.d[1], x7
- b 1b
+ b 2b
/* store new state */
-3: st1 {dgav.4s, dgbv.4s}, [x0]
+4: st1 {dgav.4s, dgbv.4s}, [x19]
+ frame_pop
ret
ENDPROC(sha2_ce_transform)
diff --git a/arch/arm64/crypto/sha256-core.S_shipped b/arch/arm64/crypto/sha256-core.S_shipped
index 3ce82cc860bc..7c7ce2e3bad6 100644
--- a/arch/arm64/crypto/sha256-core.S_shipped
+++ b/arch/arm64/crypto/sha256-core.S_shipped
@@ -1,3 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore 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.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
// Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
//
// Licensed under the OpenSSL license (the "License"). You may not use
@@ -10,8 +20,6 @@
// project. The module is, however, dual licensed under OpenSSL and
// CRYPTOGAMS licenses depending on where you obtain it. For further
// details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
// ====================================================================
//
// SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha3-ce-core.S b/arch/arm64/crypto/sha3-ce-core.S
index 332ad7530690..a7d587fa54f6 100644
--- a/arch/arm64/crypto/sha3-ce-core.S
+++ b/arch/arm64/crypto/sha3-ce-core.S
@@ -41,9 +41,16 @@
*/
.text
ENTRY(sha3_ce_transform)
- /* load state */
- add x8, x0, #32
- ld1 { v0.1d- v3.1d}, [x0]
+ frame_push 4
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+ mov x22, x3
+
+0: /* load state */
+ add x8, x19, #32
+ ld1 { v0.1d- v3.1d}, [x19]
ld1 { v4.1d- v7.1d}, [x8], #32
ld1 { v8.1d-v11.1d}, [x8], #32
ld1 {v12.1d-v15.1d}, [x8], #32
@@ -51,13 +58,13 @@ ENTRY(sha3_ce_transform)
ld1 {v20.1d-v23.1d}, [x8], #32
ld1 {v24.1d}, [x8]
-0: sub w2, w2, #1
+1: sub w21, w21, #1
mov w8, #24
adr_l x9, .Lsha3_rcon
/* load input */
- ld1 {v25.8b-v28.8b}, [x1], #32
- ld1 {v29.8b-v31.8b}, [x1], #24
+ ld1 {v25.8b-v28.8b}, [x20], #32
+ ld1 {v29.8b-v31.8b}, [x20], #24
eor v0.8b, v0.8b, v25.8b
eor v1.8b, v1.8b, v26.8b
eor v2.8b, v2.8b, v27.8b
@@ -66,10 +73,10 @@ ENTRY(sha3_ce_transform)
eor v5.8b, v5.8b, v30.8b
eor v6.8b, v6.8b, v31.8b
- tbnz x3, #6, 2f // SHA3-512
+ tbnz x22, #6, 3f // SHA3-512
- ld1 {v25.8b-v28.8b}, [x1], #32
- ld1 {v29.8b-v30.8b}, [x1], #16
+ ld1 {v25.8b-v28.8b}, [x20], #32
+ ld1 {v29.8b-v30.8b}, [x20], #16
eor v7.8b, v7.8b, v25.8b
eor v8.8b, v8.8b, v26.8b
eor v9.8b, v9.8b, v27.8b
@@ -77,34 +84,34 @@ ENTRY(sha3_ce_transform)
eor v11.8b, v11.8b, v29.8b
eor v12.8b, v12.8b, v30.8b
- tbnz x3, #4, 1f // SHA3-384 or SHA3-224
+ tbnz x22, #4, 2f // SHA3-384 or SHA3-224
// SHA3-256
- ld1 {v25.8b-v28.8b}, [x1], #32
+ ld1 {v25.8b-v28.8b}, [x20], #32
eor v13.8b, v13.8b, v25.8b
eor v14.8b, v14.8b, v26.8b
eor v15.8b, v15.8b, v27.8b
eor v16.8b, v16.8b, v28.8b
- b 3f
+ b 4f
-1: tbz x3, #2, 3f // bit 2 cleared? SHA-384
+2: tbz x22, #2, 4f // bit 2 cleared? SHA-384
// SHA3-224
- ld1 {v25.8b-v28.8b}, [x1], #32
- ld1 {v29.8b}, [x1], #8
+ ld1 {v25.8b-v28.8b}, [x20], #32
+ ld1 {v29.8b}, [x20], #8
eor v13.8b, v13.8b, v25.8b
eor v14.8b, v14.8b, v26.8b
eor v15.8b, v15.8b, v27.8b
eor v16.8b, v16.8b, v28.8b
eor v17.8b, v17.8b, v29.8b
- b 3f
+ b 4f
// SHA3-512
-2: ld1 {v25.8b-v26.8b}, [x1], #16
+3: ld1 {v25.8b-v26.8b}, [x20], #16
eor v7.8b, v7.8b, v25.8b
eor v8.8b, v8.8b, v26.8b
-3: sub w8, w8, #1
+4: sub w8, w8, #1
eor3 v29.16b, v4.16b, v9.16b, v14.16b
eor3 v26.16b, v1.16b, v6.16b, v11.16b
@@ -183,17 +190,33 @@ ENTRY(sha3_ce_transform)
eor v0.16b, v0.16b, v31.16b
- cbnz w8, 3b
- cbnz w2, 0b
+ cbnz w8, 4b
+ cbz w21, 5f
+
+ if_will_cond_yield_neon
+ add x8, x19, #32
+ st1 { v0.1d- v3.1d}, [x19]
+ st1 { v4.1d- v7.1d}, [x8], #32
+ st1 { v8.1d-v11.1d}, [x8], #32
+ st1 {v12.1d-v15.1d}, [x8], #32
+ st1 {v16.1d-v19.1d}, [x8], #32
+ st1 {v20.1d-v23.1d}, [x8], #32
+ st1 {v24.1d}, [x8]
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+
+ b 1b
/* save state */
- st1 { v0.1d- v3.1d}, [x0], #32
- st1 { v4.1d- v7.1d}, [x0], #32
- st1 { v8.1d-v11.1d}, [x0], #32
- st1 {v12.1d-v15.1d}, [x0], #32
- st1 {v16.1d-v19.1d}, [x0], #32
- st1 {v20.1d-v23.1d}, [x0], #32
- st1 {v24.1d}, [x0]
+5: st1 { v0.1d- v3.1d}, [x19], #32
+ st1 { v4.1d- v7.1d}, [x19], #32
+ st1 { v8.1d-v11.1d}, [x19], #32
+ st1 {v12.1d-v15.1d}, [x19], #32
+ st1 {v16.1d-v19.1d}, [x19], #32
+ st1 {v20.1d-v23.1d}, [x19], #32
+ st1 {v24.1d}, [x19]
+ frame_pop
ret
ENDPROC(sha3_ce_transform)
diff --git a/arch/arm64/crypto/sha512-armv8.pl b/arch/arm64/crypto/sha512-armv8.pl
index c55efb308544..2d8655d5b1af 100644
--- a/arch/arm64/crypto/sha512-armv8.pl
+++ b/arch/arm64/crypto/sha512-armv8.pl
@@ -1,4 +1,14 @@
#! /usr/bin/env perl
+# SPDX-License-Identifier: GPL-2.0
+
+# This code is taken from the OpenSSL project but the author (Andy Polyakov)
+# has relicensed it under the GPLv2. Therefore 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.
+#
+# The original headers, including the original license headers, are
+# included below for completeness.
+
# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
#
# Licensed under the OpenSSL license (the "License"). You may not use
@@ -11,8 +21,6 @@
# project. The module is, however, dual licensed under OpenSSL and
# CRYPTOGAMS licenses depending on where you obtain it. For further
# details see http://www.openssl.org/~appro/cryptogams/.
-#
-# Permission to use under GPLv2 terms is granted.
# ====================================================================
#
# SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sha512-ce-core.S b/arch/arm64/crypto/sha512-ce-core.S
index 7f3bca5c59a2..ce65e3abe4f2 100644
--- a/arch/arm64/crypto/sha512-ce-core.S
+++ b/arch/arm64/crypto/sha512-ce-core.S
@@ -107,17 +107,23 @@
*/
.text
ENTRY(sha512_ce_transform)
+ frame_push 3
+
+ mov x19, x0
+ mov x20, x1
+ mov x21, x2
+
/* load state */
- ld1 {v8.2d-v11.2d}, [x0]
+0: ld1 {v8.2d-v11.2d}, [x19]
/* load first 4 round constants */
adr_l x3, .Lsha512_rcon
ld1 {v20.2d-v23.2d}, [x3], #64
/* load input */
-0: ld1 {v12.2d-v15.2d}, [x1], #64
- ld1 {v16.2d-v19.2d}, [x1], #64
- sub w2, w2, #1
+1: ld1 {v12.2d-v15.2d}, [x20], #64
+ ld1 {v16.2d-v19.2d}, [x20], #64
+ sub w21, w21, #1
CPU_LE( rev64 v12.16b, v12.16b )
CPU_LE( rev64 v13.16b, v13.16b )
@@ -196,9 +202,18 @@ CPU_LE( rev64 v19.16b, v19.16b )
add v11.2d, v11.2d, v3.2d
/* handled all input blocks? */
- cbnz w2, 0b
+ cbz w21, 3f
+
+ if_will_cond_yield_neon
+ st1 {v8.2d-v11.2d}, [x19]
+ do_cond_yield_neon
+ b 0b
+ endif_yield_neon
+
+ b 1b
/* store new state */
-3: st1 {v8.2d-v11.2d}, [x0]
+3: st1 {v8.2d-v11.2d}, [x19]
+ frame_pop
ret
ENDPROC(sha512_ce_transform)
diff --git a/arch/arm64/crypto/sha512-core.S_shipped b/arch/arm64/crypto/sha512-core.S_shipped
index bd0f59f06c9d..e063a6106720 100644
--- a/arch/arm64/crypto/sha512-core.S_shipped
+++ b/arch/arm64/crypto/sha512-core.S_shipped
@@ -1,3 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// This code is taken from the OpenSSL project but the author (Andy Polyakov)
+// has relicensed it under the GPLv2. Therefore 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.
+//
+// The original headers, including the original license headers, are
+// included below for completeness.
+
// Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
//
// Licensed under the OpenSSL license (the "License"). You may not use
@@ -10,8 +20,6 @@
// project. The module is, however, dual licensed under OpenSSL and
// CRYPTOGAMS licenses depending on where you obtain it. For further
// details see http://www.openssl.org/~appro/cryptogams/.
-//
-// Permission to use under GPLv2 terms is granted.
// ====================================================================
//
// SHA256/512 for ARMv8.
diff --git a/arch/arm64/crypto/sm4-ce-core.S b/arch/arm64/crypto/sm4-ce-core.S
new file mode 100644
index 000000000000..af3bfbc3f4d4
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-core.S
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8
+ .set .Lv\b\().4s, \b
+ .endr
+
+ .macro sm4e, rd, rn
+ .inst 0xcec08400 | .L\rd | (.L\rn << 5)
+ .endm
+
+ /*
+ * void sm4_ce_do_crypt(const u32 *rk, u32 *out, const u32 *in);
+ */
+ .text
+ENTRY(sm4_ce_do_crypt)
+ ld1 {v8.4s}, [x2]
+ ld1 {v0.4s-v3.4s}, [x0], #64
+CPU_LE( rev32 v8.16b, v8.16b )
+ ld1 {v4.4s-v7.4s}, [x0]
+ sm4e v8.4s, v0.4s
+ sm4e v8.4s, v1.4s
+ sm4e v8.4s, v2.4s
+ sm4e v8.4s, v3.4s
+ sm4e v8.4s, v4.4s
+ sm4e v8.4s, v5.4s
+ sm4e v8.4s, v6.4s
+ sm4e v8.4s, v7.4s
+ rev64 v8.4s, v8.4s
+ ext v8.16b, v8.16b, v8.16b, #8
+CPU_LE( rev32 v8.16b, v8.16b )
+ st1 {v8.4s}, [x1]
+ ret
+ENDPROC(sm4_ce_do_crypt)
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
new file mode 100644
index 000000000000..b7fb5274b250
--- /dev/null
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/sm4.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/crypto.h>
+#include <linux/types.h>
+
+MODULE_ALIAS_CRYPTO("sm4");
+MODULE_ALIAS_CRYPTO("sm4-ce");
+MODULE_DESCRIPTION("SM4 symmetric cipher using ARMv8 Crypto Extensions");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+asmlinkage void sm4_ce_do_crypt(const u32 *rk, void *out, const void *in);
+
+static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ if (!may_use_simd()) {
+ crypto_sm4_encrypt(tfm, out, in);
+ } else {
+ kernel_neon_begin();
+ sm4_ce_do_crypt(ctx->rkey_enc, out, in);
+ kernel_neon_end();
+ }
+}
+
+static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
+{
+ const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ if (!may_use_simd()) {
+ crypto_sm4_decrypt(tfm, out, in);
+ } else {
+ kernel_neon_begin();
+ sm4_ce_do_crypt(ctx->rkey_dec, out, in);
+ kernel_neon_end();
+ }
+}
+
+static struct crypto_alg sm4_ce_alg = {
+ .cra_name = "sm4",
+ .cra_driver_name = "sm4-ce",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_CIPHER,
+ .cra_blocksize = SM4_BLOCK_SIZE,
+ .cra_ctxsize = sizeof(struct crypto_sm4_ctx),
+ .cra_module = THIS_MODULE,
+ .cra_u.cipher = {
+ .cia_min_keysize = SM4_KEY_SIZE,
+ .cia_max_keysize = SM4_KEY_SIZE,
+ .cia_setkey = crypto_sm4_set_key,
+ .cia_encrypt = sm4_ce_encrypt,
+ .cia_decrypt = sm4_ce_decrypt
+ }
+};
+
+static int __init sm4_ce_mod_init(void)
+{
+ return crypto_register_alg(&sm4_ce_alg);
+}
+
+static void __exit sm4_ce_mod_fini(void)
+{
+ crypto_unregister_alg(&sm4_ce_alg);
+}
+
+module_cpu_feature_match(SM3, sm4_ce_mod_init);
+module_exit(sm4_ce_mod_fini);
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 9ef0797380cb..f9b0b09153e0 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -117,7 +117,7 @@ static inline void atomic_and(int i, atomic_t *v)
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
+ : [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -135,7 +135,7 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v) \
/* LSE atomics */ \
" mvn %w[i], %w[i]\n" \
" ldclr" #mb " %w[i], %w[i], %[v]") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -161,7 +161,7 @@ static inline void atomic_sub(int i, atomic_t *v)
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
+ : [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -180,7 +180,7 @@ static inline int atomic_sub_return##name(int i, atomic_t *v) \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS , ##cl); \
\
@@ -207,7 +207,7 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v) \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], %w[i], %[v]") \
- : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -314,7 +314,7 @@ static inline void atomic64_and(long i, atomic64_t *v)
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
+ : [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -332,7 +332,7 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \
/* LSE atomics */ \
" mvn %[i], %[i]\n" \
" ldclr" #mb " %[i], %[i], %[v]") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -358,7 +358,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
+ : [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
@@ -377,7 +377,7 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v) \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -404,7 +404,7 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], %[i], %[v]") \
- : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
@@ -435,7 +435,7 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
" sub x30, x30, %[ret]\n"
" cbnz x30, 1b\n"
"2:")
- : [ret] "+r" (x0), [v] "+Q" (v->counter)
+ : [ret] "+&r" (x0), [v] "+Q" (v->counter)
:
: __LL_SC_CLOBBERS, "cc", "memory");
@@ -516,7 +516,7 @@ static inline long __cmpxchg_double##name(unsigned long old1, \
" eor %[old1], %[old1], %[oldval1]\n" \
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]") \
- : [old1] "+r" (x0), [old2] "+r" (x1), \
+ : [old1] "+&r" (x0), [old2] "+&r" (x1), \
[v] "+Q" (*(unsigned long *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index c00c62e1a4a3..1a037b94eba1 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -34,7 +34,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -66,16 +65,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
#ifdef __AARCH64EB__
short st_dev;
@@ -192,10 +181,10 @@ struct compat_ipc64_perm {
struct compat_semid64_ds {
struct compat_ipc64_perm sem_perm;
- compat_time_t sem_otime;
- compat_ulong_t __unused1;
- compat_time_t sem_ctime;
- compat_ulong_t __unused2;
+ compat_ulong_t sem_otime;
+ compat_ulong_t sem_otime_high;
+ compat_ulong_t sem_ctime;
+ compat_ulong_t sem_ctime_high;
compat_ulong_t sem_nsems;
compat_ulong_t __unused3;
compat_ulong_t __unused4;
@@ -203,12 +192,12 @@ struct compat_semid64_ds {
struct compat_msqid64_ds {
struct compat_ipc64_perm msg_perm;
- compat_time_t msg_stime;
- compat_ulong_t __unused1;
- compat_time_t msg_rtime;
- compat_ulong_t __unused2;
- compat_time_t msg_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t msg_stime;
+ compat_ulong_t msg_stime_high;
+ compat_ulong_t msg_rtime;
+ compat_ulong_t msg_rtime_high;
+ compat_ulong_t msg_ctime;
+ compat_ulong_t msg_ctime_high;
compat_ulong_t msg_cbytes;
compat_ulong_t msg_qnum;
compat_ulong_t msg_qbytes;
@@ -221,12 +210,12 @@ struct compat_msqid64_ds {
struct compat_shmid64_ds {
struct compat_ipc64_perm shm_perm;
compat_size_t shm_segsz;
- compat_time_t shm_atime;
- compat_ulong_t __unused1;
- compat_time_t shm_dtime;
- compat_ulong_t __unused2;
- compat_time_t shm_ctime;
- compat_ulong_t __unused3;
+ compat_ulong_t shm_atime;
+ compat_ulong_t shm_atime_high;
+ compat_ulong_t shm_dtime;
+ compat_ulong_t shm_dtime_high;
+ compat_ulong_t shm_ctime;
+ compat_ulong_t shm_ctime_high;
compat_pid_t shm_cpid;
compat_pid_t shm_lpid;
compat_ulong_t shm_nattch;
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 30014a9f8f2b..ea690b3562af 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
#define ARM_CPU_IMP_CAVIUM 0x43
#define ARM_CPU_IMP_BRCM 0x42
#define ARM_CPU_IMP_QCOM 0x51
+#define ARM_CPU_IMP_NVIDIA 0x4E
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -99,6 +100,9 @@
#define QCOM_CPU_PART_FALKOR 0xC00
#define QCOM_CPU_PART_KRYO 0x200
+#define NVIDIA_CPU_PART_DENVER 0x003
+#define NVIDIA_CPU_PART_CARMEL 0x004
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -114,6 +118,8 @@
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
#define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
#define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO)
+#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER)
+#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 23b33e8ea03a..1dab3a984608 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -333,7 +333,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
} else {
u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
sctlr |= (1 << 25);
- vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr);
+ vcpu_write_sys_reg(vcpu, sctlr, SCTLR_EL1);
}
}
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ab46bc70add6..469de8acd06f 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -75,6 +75,9 @@ struct kvm_arch {
/* Interrupt controller */
struct vgic_dist vgic;
+
+ /* Mandated version of PSCI */
+ u32 psci_version;
};
#define KVM_NR_MEM_OBJS 40
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 082110993647..6128992c2ded 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void)
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}
+/*
+ * We are not in the kvm->srcu critical section most of the time, so we take
+ * the SRCU read lock here. Since we copy the data from the user page, we
+ * can immediately drop the lock again.
+ */
+static inline int kvm_read_guest_lock(struct kvm *kvm,
+ gpa_t gpa, void *data, unsigned long len)
+{
+ int srcu_idx = srcu_read_lock(&kvm->srcu);
+ int ret = kvm_read_guest(kvm, gpa, data, len);
+
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ return ret;
+}
+
#ifdef CONFIG_KVM_INDIRECT_VECTORS
/*
* EL2 vectors can be mapped and rerouted in a number of ways,
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index b6dbbe3123a9..97d0ef12e2ff 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -39,7 +39,7 @@ struct mod_arch_specific {
u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
Elf64_Sym *sym);
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val);
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val);
#ifdef CONFIG_RANDOMIZE_BASE
extern u64 module_alloc_base;
diff --git a/arch/arm64/include/asm/pci.h b/arch/arm64/include/asm/pci.h
index 8747f7c5e0e7..9e690686e8aa 100644
--- a/arch/arm64/include/asm/pci.h
+++ b/arch/arm64/include/asm/pci.h
@@ -18,11 +18,6 @@
#define pcibios_assign_all_busses() \
(pci_has_flag(PCI_REASSIGN_ALL_BUS))
-/*
- * PCI address space differs from physical memory address space
- */
-#define PCI_DMA_BUS_IS_PHYS (0)
-
#define ARCH_GENERIC_PCI_MMAP_RESOURCE 1
extern int isa_dma_bridge_buggy;
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 7e2c27e63cd8..7c4c8f318ba9 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -230,7 +230,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
}
}
-extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
+extern void __sync_icache_dcache(pte_t pteval);
/*
* PTE bits configuration in the presence of hardware Dirty Bit Management
@@ -253,7 +253,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t old_pte;
if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
- __sync_icache_dcache(pte, addr);
+ __sync_icache_dcache(pte);
/*
* If the existing pte is valid, check for potential race with
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index ebdae15d665d..26c5bd7d88d8 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -122,11 +122,6 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
- /*
- * Ensure prior spin_lock operations to other locks have completed
- * on this CPU before we test whether "lock" is locked.
- */
- smp_mb(); /* ^^^ */
return !arch_spin_value_unlocked(READ_ONCE(*lock));
}
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
index 15e35598ac40..eab738019707 100644
--- a/arch/arm64/include/asm/stat.h
+++ b/arch/arm64/include/asm/stat.h
@@ -20,6 +20,7 @@
#ifdef CONFIG_COMPAT
+#include <linux/compat_time.h>
#include <asm/compat.h>
/*
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 9abbf3044654..04b3256f8e6d 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -206,6 +206,12 @@ struct kvm_arch_memory_slot {
#define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2)
#define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2)
+/* KVM-as-firmware specific pseudo-registers */
+#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT)
+#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
+ KVM_REG_ARM_FW | ((r) & 0xffff))
+#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0)
+
/* Device Control API: ARM VGIC */
#define KVM_DEV_ARM_VGIC_GRP_ADDR 0
#define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index 66be504edb6c..d894a20b70b2 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -75,3 +75,11 @@ NOKPROBE_SYMBOL(_mcount);
/* arm-smccc */
EXPORT_SYMBOL(__arm_smccc_smc);
EXPORT_SYMBOL(__arm_smccc_hvc);
+
+ /* tishift.S */
+extern long long __ashlti3(long long a, int b);
+EXPORT_SYMBOL(__ashlti3);
+extern long long __ashrti3(long long a, int b);
+EXPORT_SYMBOL(__ashrti3);
+extern long long __lshrti3(long long a, int b);
+EXPORT_SYMBOL(__lshrti3);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index a900befadfe8..e4a1182deff7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -316,6 +316,7 @@ static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
+ MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
{},
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 536d572e5596..9d1b06d67c53 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -868,6 +868,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
static const struct midr_range kpti_safe_list[] = {
MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
+ { /* sentinel */ }
};
char const *str = "command line option";
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 87a35364e750..4bcdd0318729 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -882,7 +882,7 @@ asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
si_code = FPE_FLTRES;
}
- memset(&info, 0, sizeof(info));
+ clear_siginfo(&info);
info.si_signo = SIGFPE;
info.si_code = si_code;
info.si_addr = (void __user *)instruction_pointer(regs);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 74bb56f656ef..413dbe530da8 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -30,7 +30,6 @@
#include <linux/smp.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index fa3637284a3d..f0690c2ca3e0 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -43,7 +43,7 @@ u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
}
#ifdef CONFIG_ARM64_ERRATUM_843419
-u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val)
+u64 module_emit_veneer_for_adrp(struct module *mod, void *loc, u64 val)
{
struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
&mod->arch.init;
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 719fde8dcc19..155fd91e78f4 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -215,7 +215,7 @@ static int reloc_insn_adrp(struct module *mod, __le32 *place, u64 val)
insn &= ~BIT(31);
} else {
/* out of range for ADR -> emit a veneer */
- val = module_emit_adrp_veneer(mod, place, val & ~0xfff);
+ val = module_emit_veneer_for_adrp(mod, place, val & ~0xfff);
if (!val)
return -ENOEXEC;
insn = aarch64_insn_gen_branch_imm((u64)place, val,
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 1d091d048d04..0bbac612146e 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/bug.h>
#include <linux/sched/task_stack.h>
-#include <asm/compat.h>
#include <asm/perf_regs.h>
#include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 71d99af24ef2..7ff81fed46e1 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -25,6 +25,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/mm.h>
+#include <linux/nospec.h>
#include <linux/smp.h>
#include <linux/ptrace.h>
#include <linux/user.h>
@@ -249,15 +250,20 @@ static struct perf_event *ptrace_hbp_get_event(unsigned int note_type,
switch (note_type) {
case NT_ARM_HW_BREAK:
- if (idx < ARM_MAX_BRP)
- bp = tsk->thread.debug.hbp_break[idx];
+ if (idx >= ARM_MAX_BRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_BRP);
+ bp = tsk->thread.debug.hbp_break[idx];
break;
case NT_ARM_HW_WATCH:
- if (idx < ARM_MAX_WRP)
- bp = tsk->thread.debug.hbp_watch[idx];
+ if (idx >= ARM_MAX_WRP)
+ goto out;
+ idx = array_index_nospec(idx, ARM_MAX_WRP);
+ bp = tsk->thread.debug.hbp_watch[idx];
break;
}
+out:
return bp;
}
@@ -1458,9 +1464,7 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
{
int ret;
u32 kdata;
- mm_segment_t old_fs = get_fs();
- set_fs(KERNEL_DS);
/* Watchpoint */
if (num < 0) {
ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata);
@@ -1471,7 +1475,6 @@ static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num,
} else {
ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata);
}
- set_fs(old_fs);
if (!ret)
ret = put_user(kdata, data);
@@ -1484,7 +1487,6 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
{
int ret;
u32 kdata = 0;
- mm_segment_t old_fs = get_fs();
if (num == 0)
return 0;
@@ -1493,12 +1495,10 @@ static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num,
if (ret)
return ret;
- set_fs(KERNEL_DS);
if (num < 0)
ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata);
else
ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata);
- set_fs(old_fs);
return ret;
}
diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c
index 93ab57dcfc14..a6109825eeb9 100644
--- a/arch/arm64/kernel/sys_compat.c
+++ b/arch/arm64/kernel/sys_compat.c
@@ -112,6 +112,7 @@ 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;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index ba964da31a25..d399d459397b 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -277,7 +277,8 @@ void arm64_skip_faulting_instruction(struct pt_regs *regs, unsigned long size)
* If we were single stepping, we want to get the step exception after
* we return from the trap.
*/
- user_fastforward_single_step(current);
+ if (user_mode(regs))
+ user_fastforward_single_step(current);
}
static LIST_HEAD(undef_hook);
@@ -366,7 +367,7 @@ void force_signal_inject(int signal, int code, unsigned long address)
}
/* Force signals we don't understand to SIGKILL */
- if (WARN_ON(signal != SIGKILL ||
+ if (WARN_ON(signal != SIGKILL &&
siginfo_layout(signal, code) != SIL_FAULT)) {
signal = SIGKILL;
}
@@ -634,6 +635,7 @@ 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;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 959e50d2588c..56a0260ceb11 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -25,6 +25,7 @@
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
+#include <kvm/arm_psci.h>
#include <asm/cputype.h>
#include <linux/uaccess.h>
#include <asm/kvm.h>
@@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
{
return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu)
- + NUM_TIMER_REGS;
+ + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS;
}
/**
@@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
uindices++;
}
+ ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices);
+ if (ret)
+ return ret;
+ uindices += kvm_arm_get_fw_num_regs(vcpu);
+
ret = copy_timer_indices(vcpu, uindices);
if (ret)
return ret;
@@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return get_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_get_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return get_timer_reg(vcpu, reg);
@@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE)
return set_core_reg(vcpu, reg);
+ if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW)
+ return kvm_arm_set_fw_reg(vcpu, reg);
+
if (is_timer_reg(reg->id))
return set_timer_reg(vcpu, reg);
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 86801b6055d6..39be799d0417 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -18,11 +18,20 @@
#include <linux/compiler.h>
#include <linux/irqchip/arm-gic.h>
#include <linux/kvm_host.h>
+#include <linux/swab.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
+static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
+{
+ if (vcpu_mode_is_32bit(vcpu))
+ return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+
+ return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
+}
+
/*
* __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the
* guest.
@@ -64,14 +73,19 @@ int __hyp_text __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu)
addr += fault_ipa - vgic->vgic_cpu_base;
if (kvm_vcpu_dabt_iswrite(vcpu)) {
- u32 data = vcpu_data_guest_to_host(vcpu,
- vcpu_get_reg(vcpu, rd),
- sizeof(u32));
+ u32 data = vcpu_get_reg(vcpu, rd);
+ if (__is_be(vcpu)) {
+ /* guest pre-swabbed data, undo this for writel() */
+ data = swab32(data);
+ }
writel_relaxed(data, addr);
} else {
u32 data = readl_relaxed(addr);
- vcpu_set_reg(vcpu, rd, vcpu_data_host_to_guest(vcpu, data,
- sizeof(u32)));
+ if (__is_be(vcpu)) {
+ /* guest expects swabbed data */
+ data = swab32(data);
+ }
+ vcpu_set_reg(vcpu, rd, data);
}
return 1;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 806b0b126a64..6e3b969391fd 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -996,14 +996,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz)
if (id == SYS_ID_AA64PFR0_EL1) {
if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT))
- pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("SVE unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT);
} else if (id == SYS_ID_AA64MMFR1_EL1) {
if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))
- pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n",
- task_pid_nr(current));
+ kvm_debug("LORegions unsupported for guests, suppressing\n");
val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT);
}
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 0ead8a1d1679..137710f4dac3 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -19,5 +19,9 @@ CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
-fcall-saved-x18 -fomit-frame-pointer
CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+GCOV_PROFILE_atomic_ll_sc.o := n
+KASAN_SANITIZE_atomic_ll_sc.o := n
+KCOV_INSTRUMENT_atomic_ll_sc.o := n
+UBSAN_SANITIZE_atomic_ll_sc.o := n
lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
diff --git a/arch/arm64/lib/tishift.S b/arch/arm64/lib/tishift.S
index d3db9b2cd479..0fdff97794de 100644
--- a/arch/arm64/lib/tishift.S
+++ b/arch/arm64/lib/tishift.S
@@ -1,17 +1,6 @@
-/*
- * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
*
- * 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/>.
+ * Copyright (C) 2017-2018 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*/
#include <linux/linkage.h>
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index a96ec0181818..db01f2709842 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -508,16 +508,6 @@ static int __init arm64_dma_init(void)
}
arch_initcall(arm64_dma_init);
-#define PREALLOC_DMA_DEBUG_ENTRIES 4096
-
-static int __init dma_debug_do_init(void)
-{
- dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
- return 0;
-}
-fs_initcall(dma_debug_do_init);
-
-
#ifdef CONFIG_IOMMU_DMA
#include <linux/dma-iommu.h>
#include <linux/platform_device.h>
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4165485e8b6e..576f15153080 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -293,6 +293,57 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
static void __do_user_fault(struct siginfo *info, unsigned int esr)
{
current->thread.fault_address = (unsigned long)info->si_addr;
+
+ /*
+ * If the faulting address is in the kernel, we must sanitize the ESR.
+ * From userspace's point of view, kernel-only mappings don't exist
+ * at all, so we report them as level 0 translation faults.
+ * (This is not quite the way that "no mapping there at all" behaves:
+ * an alignment fault not caused by the memory type would take
+ * precedence over translation fault for a real access to empty
+ * space. Unfortunately we can't easily distinguish "alignment fault
+ * not caused by memory type" from "alignment fault caused by memory
+ * type", so we ignore this wrinkle and just return the translation
+ * fault.)
+ */
+ if (current->thread.fault_address >= TASK_SIZE) {
+ switch (ESR_ELx_EC(esr)) {
+ case ESR_ELx_EC_DABT_LOW:
+ /*
+ * These bits provide only information about the
+ * faulting instruction, which userspace knows already.
+ * We explicitly clear bits which are architecturally
+ * RES0 in case they are given meanings in future.
+ * We always report the ESR as if the fault was taken
+ * to EL1 and so ISV and the bits in ISS[23:14] are
+ * clear. (In fact it always will be a fault to EL1.)
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL |
+ ESR_ELx_CM | ESR_ELx_WNR;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ case ESR_ELx_EC_IABT_LOW:
+ /*
+ * Claim a level 0 translation fault.
+ * All other bits are architecturally RES0 for faults
+ * reported with that DFSC value, so we clear them.
+ */
+ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL;
+ esr |= ESR_ELx_FSC_FAULT;
+ break;
+ default:
+ /*
+ * This should never happen (entry.S only brings us
+ * into this code for insn and data aborts from a lower
+ * exception level). Fail safe by not providing an ESR
+ * context record at all.
+ */
+ WARN(1, "ESR 0x%x is not DABT or IABT from EL0\n", esr);
+ esr = 0;
+ break;
+ }
+ }
+
current->thread.fault_code = esr;
arm64_force_sig_info(info, esr_to_fault_info(esr)->name, current);
}
@@ -305,11 +356,12 @@ 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 = {
- .si_signo = inf->sig,
- .si_code = inf->code,
- .si_addr = (void __user *)addr,
- };
+ 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);
} else {
@@ -583,6 +635,7 @@ 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;
@@ -687,6 +740,7 @@ 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;
@@ -729,6 +783,7 @@ asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
local_irq_enable();
}
+ clear_siginfo(&info);
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRALN;
@@ -772,7 +827,6 @@ asmlinkage int __exception do_debug_exception(unsigned long addr,
struct pt_regs *regs)
{
const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
- struct siginfo info;
int rv;
/*
@@ -788,6 +842,9 @@ 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;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index e36ed5087b5c..1059884f9a6f 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -58,7 +58,7 @@ void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
flush_ptrace_access(vma, page, uaddr, dst, len);
}
-void __sync_icache_dcache(pte_t pte, unsigned long addr)
+void __sync_icache_dcache(pte_t pte)
{
struct page *page = pte_page(pte);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9f3c47acf8ff..1b18b4722420 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -646,8 +646,10 @@ static int keep_initrd __initdata;
void __init free_initrd_mem(unsigned long start, unsigned long end)
{
- if (!keep_initrd)
+ if (!keep_initrd) {
free_reserved_area((void *)start, (void *)end, 0, "initrd");
+ memblock_free(__virt_to_phys(start), end - start);
+ }
}
static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index dabfc1ecda3d..12145874c02b 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -204,7 +204,7 @@ void __init kasan_init(void)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+ early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
kasan_populate_zero_shadow((void *)KASAN_SHADOW_START,
(void *)mod_shadow_start);
@@ -224,7 +224,7 @@ void __init kasan_init(void)
kasan_map_populate((unsigned long)kasan_mem_to_shadow(start),
(unsigned long)kasan_mem_to_shadow(end),
- pfn_to_nid(virt_to_pfn(start)));
+ early_pfn_to_nid(virt_to_pfn(start)));
}
/*
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 2dbb2c9f1ec1..493ff75670ff 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -933,13 +933,15 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pgprot_t sect_prot = __pgprot(PUD_TYPE_SECT |
pgprot_val(mk_sect_prot(prot)));
+ pud_t new_pud = pfn_pud(__phys_to_pfn(phys), sect_prot);
- /* ioremap_page_range doesn't honour BBM */
- if (pud_present(READ_ONCE(*pudp)))
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pud_val(*pudp)),
+ pud_val(new_pud)))
return 0;
BUG_ON(phys & ~PUD_MASK);
- set_pud(pudp, pfn_pud(__phys_to_pfn(phys), sect_prot));
+ set_pud(pudp, new_pud);
return 1;
}
@@ -947,13 +949,15 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
pgprot_t sect_prot = __pgprot(PMD_TYPE_SECT |
pgprot_val(mk_sect_prot(prot)));
+ pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), sect_prot);
- /* ioremap_page_range doesn't honour BBM */
- if (pmd_present(READ_ONCE(*pmdp)))
+ /* Only allow permission changes for now */
+ if (!pgattr_change_is_safe(READ_ONCE(pmd_val(*pmdp)),
+ pmd_val(new_pmd)))
return 0;
BUG_ON(phys & ~PMD_MASK);
- set_pmd(pmdp, pfn_pmd(__phys_to_pfn(phys), sect_prot));
+ set_pmd(pmdp, new_pmd);
return 1;
}