summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/kernel/console.c1
-rw-r--r--arch/arm/boot/dts/am57xx-beagle-x15.dts1
-rw-r--r--arch/arm/boot/dts/dra7-evm.dts2
-rw-r--r--arch/arm/boot/dts/exynos4412-trats2.dts2
-rw-r--r--arch/arm/boot/dts/logicpd-torpedo-som.dtsi8
-rw-r--r--arch/arm/boot/dts/moxart-uc7112lx.dts2
-rw-r--r--arch/arm/boot/dts/moxart.dtsi17
-rw-r--r--arch/arm/boot/dts/r8a7790.dtsi7
-rw-r--r--arch/arm/boot/dts/r8a7791-koelsch.dts2
-rw-r--r--arch/arm/boot/dts/r8a7791.dtsi7
-rw-r--r--arch/arm/configs/ranchu_defconfig1
-rw-r--r--arch/arm/kernel/ftrace.c11
-rw-r--r--arch/arm/mach-mvebu/Kconfig4
-rw-r--r--arch/arm/mach-omap2/clockdomains7xx_data.c2
-rw-r--r--arch/arm/mach-omap2/omap-secure.c2
-rw-r--r--arch/arm64/crypto/Kconfig7
-rw-r--r--arch/arm64/crypto/Makefile3
-rw-r--r--arch/arm64/crypto/speck-neon-core.S352
-rw-r--r--arch/arm64/crypto/speck-neon-glue.c308
-rw-r--r--arch/arm64/include/asm/memory.h6
-rw-r--r--arch/arm64/mm/mmu.c12
-rw-r--r--arch/frv/include/asm/timex.h6
-rw-r--r--arch/ia64/kernel/module.c4
-rw-r--r--arch/mips/ath25/board.c2
-rw-r--r--arch/mips/cavium-octeon/octeon-irq.c2
-rw-r--r--arch/mips/kernel/smp-bmips.c8
-rw-r--r--arch/mips/net/bpf_jit.c16
-rw-r--r--arch/mips/net/bpf_jit_asm.S23
-rw-r--r--arch/mips/ralink/reset.c7
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_host.c5
-rw-r--r--arch/powerpc/kvm/book3s_pr.c6
-rw-r--r--arch/powerpc/mm/fault.c2
-rw-r--r--arch/x86/Makefile9
-rw-r--r--arch/x86/boot/compressed/misc.c4
-rw-r--r--arch/x86/configs/i386_ranchu_defconfig1
-rw-r--r--arch/x86/configs/x86_64_ranchu_defconfig1
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c3
-rw-r--r--arch/x86/entry/entry_64.S18
-rw-r--r--arch/x86/include/asm/nospec-branch.h37
-rw-r--r--arch/x86/include/asm/vmx.h1
-rw-r--r--arch/x86/kernel/apic/vector.c14
-rw-r--r--arch/x86/kernel/cpu/bugs.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c22
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c2
-rw-r--r--arch/x86/kernel/i8259.c1
-rw-r--r--arch/x86/kernel/kprobes/core.c16
-rw-r--r--arch/x86/kernel/kprobes/opt.c3
-rw-r--r--arch/x86/kernel/machine_kexec_64.c1
-rw-r--r--arch/x86/kernel/module.c14
-rw-r--r--arch/x86/kernel/traps.c24
-rw-r--r--arch/x86/kernel/vm86_32.c3
-rw-r--r--arch/x86/kvm/vmx.c9
-rw-r--r--arch/x86/mm/fault.c6
-rw-r--r--arch/x86/mm/pgtable.c48
-rw-r--r--arch/x86/net/bpf_jit_comp.c12
-rw-r--r--arch/x86/tools/relocs.c3
56 files changed, 994 insertions, 99 deletions
diff --git a/arch/alpha/kernel/console.c b/arch/alpha/kernel/console.c
index 6a61deed4a85..ab228ed45945 100644
--- a/arch/alpha/kernel/console.c
+++ b/arch/alpha/kernel/console.c
@@ -20,6 +20,7 @@
struct pci_controller *pci_vga_hose;
static struct resource alpha_vga = {
.name = "alpha-vga+",
+ .flags = IORESOURCE_IO,
.start = 0x3C0,
.end = 0x3DF
};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 00352e761b8c..5c3bd34af9fd 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -411,6 +411,7 @@
interrupt-controller;
ti,system-power-controller;
+ ti,palmas-override-powerhold;
tps659038_pmic {
compatible = "ti,tps659038-pmic";
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index 864f60020124..0736d04f032e 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -410,6 +410,8 @@
tps659038: tps659038@58 {
compatible = "ti,tps659038";
reg = <0x58>;
+ ti,palmas-override-powerhold;
+ ti,system-power-controller;
tps659038_pmic {
compatible = "ti,tps659038-pmic";
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 40a474c4374b..4c52358734ef 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -359,7 +359,7 @@
reg = <0>;
vdd3-supply = <&lcd_vdd3_reg>;
vci-supply = <&ldo25_reg>;
- reset-gpios = <&gpy4 5 GPIO_ACTIVE_HIGH>;
+ reset-gpios = <&gpf2 1 GPIO_ACTIVE_HIGH>;
power-on-delay= <50>;
reset-delay = <100>;
init-delay = <100>;
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 80f6c786a37e..e05670423d8b 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -90,6 +90,8 @@
};
&i2c1 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&i2c1_pins>;
clock-frequency = <2600000>;
twl: twl@48 {
@@ -137,6 +139,12 @@
OMAP3_CORE1_IOPAD(0x218e, PIN_OUTPUT | MUX_MODE4) /* mcbsp1_fsr.gpio_157 */
>;
};
+ i2c1_pins: pinmux_i2c1_pins {
+ pinctrl-single,pins = <
+ OMAP3_CORE1_IOPAD(0x21ba, PIN_INPUT | MUX_MODE0) /* i2c1_scl.i2c1_scl */
+ OMAP3_CORE1_IOPAD(0x21bc, PIN_INPUT | MUX_MODE0) /* i2c1_sda.i2c1_sda */
+ >;
+ };
};
&omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/moxart-uc7112lx.dts b/arch/arm/boot/dts/moxart-uc7112lx.dts
index 10d088df0c35..4a962a26482d 100644
--- a/arch/arm/boot/dts/moxart-uc7112lx.dts
+++ b/arch/arm/boot/dts/moxart-uc7112lx.dts
@@ -6,7 +6,7 @@
*/
/dts-v1/;
-/include/ "moxart.dtsi"
+#include "moxart.dtsi"
/ {
model = "MOXA UC-7112-LX";
diff --git a/arch/arm/boot/dts/moxart.dtsi b/arch/arm/boot/dts/moxart.dtsi
index 1fd27ed65a01..64f2f44235d0 100644
--- a/arch/arm/boot/dts/moxart.dtsi
+++ b/arch/arm/boot/dts/moxart.dtsi
@@ -6,6 +6,7 @@
*/
/include/ "skeleton.dtsi"
+#include <dt-bindings/interrupt-controller/irq.h>
/ {
compatible = "moxa,moxart";
@@ -36,8 +37,8 @@
ranges;
intc: interrupt-controller@98800000 {
- compatible = "moxa,moxart-ic";
- reg = <0x98800000 0x38>;
+ compatible = "moxa,moxart-ic", "faraday,ftintc010";
+ reg = <0x98800000 0x100>;
interrupt-controller;
#interrupt-cells = <2>;
interrupt-mask = <0x00080000>;
@@ -59,7 +60,7 @@
timer: timer@98400000 {
compatible = "moxa,moxart-timer";
reg = <0x98400000 0x42>;
- interrupts = <19 1>;
+ interrupts = <19 IRQ_TYPE_EDGE_FALLING>;
clocks = <&clk_apb>;
};
@@ -80,7 +81,7 @@
dma: dma@90500000 {
compatible = "moxa,moxart-dma";
reg = <0x90500080 0x40>;
- interrupts = <24 0>;
+ interrupts = <24 IRQ_TYPE_LEVEL_HIGH>;
#dma-cells = <1>;
};
@@ -93,7 +94,7 @@
sdhci: sdhci@98e00000 {
compatible = "moxa,moxart-sdhci";
reg = <0x98e00000 0x5C>;
- interrupts = <5 0>;
+ interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk_apb>;
dmas = <&dma 5>,
<&dma 5>;
@@ -120,7 +121,7 @@
mac0: mac@90900000 {
compatible = "moxa,moxart-mac";
reg = <0x90900000 0x90>;
- interrupts = <25 0>;
+ interrupts = <25 IRQ_TYPE_LEVEL_HIGH>;
phy-handle = <&ethphy0>;
phy-mode = "mii";
status = "disabled";
@@ -129,7 +130,7 @@
mac1: mac@92000000 {
compatible = "moxa,moxart-mac";
reg = <0x92000000 0x90>;
- interrupts = <27 0>;
+ interrupts = <27 IRQ_TYPE_LEVEL_HIGH>;
phy-handle = <&ethphy1>;
phy-mode = "mii";
status = "disabled";
@@ -138,7 +139,7 @@
uart0: uart@98200000 {
compatible = "ns16550a";
reg = <0x98200000 0x20>;
- interrupts = <31 8>;
+ interrupts = <31 IRQ_TYPE_LEVEL_HIGH>;
reg-shift = <2>;
reg-io-width = <4>;
clock-frequency = <14745600>;
diff --git a/arch/arm/boot/dts/r8a7790.dtsi b/arch/arm/boot/dts/r8a7790.dtsi
index 7b39d8fae61e..bd83a61f724f 100644
--- a/arch/arm/boot/dts/r8a7790.dtsi
+++ b/arch/arm/boot/dts/r8a7790.dtsi
@@ -1360,8 +1360,11 @@
compatible = "renesas,r8a7790-mstp-clocks", "renesas,cpg-mstp-clocks";
reg = <0 0xe6150998 0 4>, <0 0xe61509a8 0 4>;
clocks = <&p_clk>,
- <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>,
- <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>,
+ <&mstp10_clks R8A7790_CLK_SSI_ALL>, <&mstp10_clks R8A7790_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7790_CLK_SSI_ALL>, <&mstp10_clks R8A7790_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7790_CLK_SSI_ALL>, <&mstp10_clks R8A7790_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7790_CLK_SSI_ALL>, <&mstp10_clks R8A7790_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7790_CLK_SSI_ALL>, <&mstp10_clks R8A7790_CLK_SSI_ALL>,
<&p_clk>,
<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
<&mstp10_clks R8A7790_CLK_SCU_ALL>, <&mstp10_clks R8A7790_CLK_SCU_ALL>,
diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts
index fc44ea361a4b..62eae315af1f 100644
--- a/arch/arm/boot/dts/r8a7791-koelsch.dts
+++ b/arch/arm/boot/dts/r8a7791-koelsch.dts
@@ -280,7 +280,7 @@
x2_clk: x2-clock {
compatible = "fixed-clock";
#clock-cells = <0>;
- clock-frequency = <148500000>;
+ clock-frequency = <74250000>;
};
x13_clk: x13-clock {
diff --git a/arch/arm/boot/dts/r8a7791.dtsi b/arch/arm/boot/dts/r8a7791.dtsi
index 328f48bd15e7..d2585a4c6098 100644
--- a/arch/arm/boot/dts/r8a7791.dtsi
+++ b/arch/arm/boot/dts/r8a7791.dtsi
@@ -1374,8 +1374,11 @@
compatible = "renesas,r8a7791-mstp-clocks", "renesas,cpg-mstp-clocks";
reg = <0 0xe6150998 0 4>, <0 0xe61509a8 0 4>;
clocks = <&p_clk>,
- <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>,
- <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>, <&p_clk>,
+ <&mstp10_clks R8A7791_CLK_SSI_ALL>, <&mstp10_clks R8A7791_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7791_CLK_SSI_ALL>, <&mstp10_clks R8A7791_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7791_CLK_SSI_ALL>, <&mstp10_clks R8A7791_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7791_CLK_SSI_ALL>, <&mstp10_clks R8A7791_CLK_SSI_ALL>,
+ <&mstp10_clks R8A7791_CLK_SSI_ALL>, <&mstp10_clks R8A7791_CLK_SSI_ALL>,
<&p_clk>,
<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
<&mstp10_clks R8A7791_CLK_SCU_ALL>, <&mstp10_clks R8A7791_CLK_SCU_ALL>,
diff --git a/arch/arm/configs/ranchu_defconfig b/arch/arm/configs/ranchu_defconfig
index 49e7bbd5825a..d5a16dfe678f 100644
--- a/arch/arm/configs/ranchu_defconfig
+++ b/arch/arm/configs/ranchu_defconfig
@@ -173,6 +173,7 @@ CONFIG_USB_USBNET=y
CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_KEYRESET=y
CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+CONFIG_KEYBOARD_GOLDFISH_ROTARY=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_JOYSTICK=y
CONFIG_JOYSTICK_XPAD=y
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index 709ee1d6d4df..faa9a905826e 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -29,11 +29,6 @@
#endif
#ifdef CONFIG_DYNAMIC_FTRACE
-#ifdef CONFIG_OLD_MCOUNT
-#define OLD_MCOUNT_ADDR ((unsigned long) mcount)
-#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
-
-#define OLD_NOP 0xe1a00000 /* mov r0, r0 */
static int __ftrace_modify_code(void *data)
{
@@ -51,6 +46,12 @@ void arch_ftrace_update_code(int command)
stop_machine(__ftrace_modify_code, &command, NULL);
}
+#ifdef CONFIG_OLD_MCOUNT
+#define OLD_MCOUNT_ADDR ((unsigned long) mcount)
+#define OLD_FTRACE_ADDR ((unsigned long) ftrace_caller_old)
+
+#define OLD_NOP 0xe1a00000 /* mov r0, r0 */
+
static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
{
return rec->arch.old_mcount ? OLD_NOP : NOP;
diff --git a/arch/arm/mach-mvebu/Kconfig b/arch/arm/mach-mvebu/Kconfig
index e20fc4178b15..1c8a6098a2ca 100644
--- a/arch/arm/mach-mvebu/Kconfig
+++ b/arch/arm/mach-mvebu/Kconfig
@@ -37,7 +37,7 @@ config MACH_ARMADA_370
config MACH_ARMADA_375
bool "Marvell Armada 375 boards" if ARCH_MULTI_V7
select ARM_ERRATA_720789
- select ARM_ERRATA_753970
+ select PL310_ERRATA_753970
select ARM_GIC
select ARMADA_375_CLK
select HAVE_ARM_SCU
@@ -52,7 +52,7 @@ config MACH_ARMADA_375
config MACH_ARMADA_38X
bool "Marvell Armada 380/385 boards" if ARCH_MULTI_V7
select ARM_ERRATA_720789
- select ARM_ERRATA_753970
+ select PL310_ERRATA_753970
select ARM_GIC
select ARMADA_38X_CLK
select HAVE_ARM_SCU
diff --git a/arch/arm/mach-omap2/clockdomains7xx_data.c b/arch/arm/mach-omap2/clockdomains7xx_data.c
index 7581e036bda6..70e3b711e79c 100644
--- a/arch/arm/mach-omap2/clockdomains7xx_data.c
+++ b/arch/arm/mach-omap2/clockdomains7xx_data.c
@@ -524,7 +524,7 @@ static struct clockdomain pcie_7xx_clkdm = {
.dep_bit = DRA7XX_PCIE_STATDEP_SHIFT,
.wkdep_srcs = pcie_wkup_sleep_deps,
.sleepdep_srcs = pcie_wkup_sleep_deps,
- .flags = CLKDM_CAN_HWSUP_SWSUP,
+ .flags = CLKDM_CAN_SWSUP,
};
static struct clockdomain atl_7xx_clkdm = {
diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c
index 9ff92050053c..fa7f308c9027 100644
--- a/arch/arm/mach-omap2/omap-secure.c
+++ b/arch/arm/mach-omap2/omap-secure.c
@@ -73,6 +73,7 @@ phys_addr_t omap_secure_ram_mempool_base(void)
return omap_secure_memblock_base;
}
+#if defined(CONFIG_ARCH_OMAP3) && defined(CONFIG_PM)
u32 omap3_save_secure_ram(void __iomem *addr, int size)
{
u32 ret;
@@ -91,6 +92,7 @@ u32 omap3_save_secure_ram(void __iomem *addr, int size)
return ret;
}
+#endif
/**
* rx51_secure_dispatcher: Routine to dispatch secure PPA API calls
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index de1aab4b5da8..487cd382d333 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -58,4 +58,11 @@ config CRYPTO_CRC32_ARM64
tristate "CRC32 and CRC32C using optional ARMv8 instructions"
depends on ARM64
select CRYPTO_HASH
+
+config CRYPTO_SPECK_NEON
+ tristate "NEON accelerated Speck cipher algorithms"
+ depends on KERNEL_MODE_NEON
+ select CRYPTO_BLKCIPHER
+ select CRYPTO_GF128MUL
+ select CRYPTO_SPECK
endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index f0a8f2475ea3..28a71246e0a3 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -32,6 +32,9 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
+obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
+speck-neon-y := speck-neon-core.o speck-neon-glue.o
+
AFLAGS_aes-ce.o := -DINTERLEAVE=4
AFLAGS_aes-neon.o := -DINTERLEAVE=4
diff --git a/arch/arm64/crypto/speck-neon-core.S b/arch/arm64/crypto/speck-neon-core.S
new file mode 100644
index 000000000000..b14463438b09
--- /dev/null
+++ b/arch/arm64/crypto/speck-neon-core.S
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ *
+ * Copyright (c) 2018 Google, Inc
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+
+#include <linux/linkage.h>
+
+ .text
+
+ // arguments
+ ROUND_KEYS .req x0 // const {u64,u32} *round_keys
+ NROUNDS .req w1 // int nrounds
+ NROUNDS_X .req x1
+ DST .req x2 // void *dst
+ SRC .req x3 // const void *src
+ NBYTES .req w4 // unsigned int nbytes
+ TWEAK .req x5 // void *tweak
+
+ // registers which hold the data being encrypted/decrypted
+ // (underscores avoid a naming collision with ARM64 registers x0-x3)
+ X_0 .req v0
+ Y_0 .req v1
+ X_1 .req v2
+ Y_1 .req v3
+ X_2 .req v4
+ Y_2 .req v5
+ X_3 .req v6
+ Y_3 .req v7
+
+ // the round key, duplicated in all lanes
+ ROUND_KEY .req v8
+
+ // index vector for tbl-based 8-bit rotates
+ ROTATE_TABLE .req v9
+ ROTATE_TABLE_Q .req q9
+
+ // temporary registers
+ TMP0 .req v10
+ TMP1 .req v11
+ TMP2 .req v12
+ TMP3 .req v13
+
+ // multiplication table for updating XTS tweaks
+ GFMUL_TABLE .req v14
+ GFMUL_TABLE_Q .req q14
+
+ // next XTS tweak value(s)
+ TWEAKV_NEXT .req v15
+
+ // XTS tweaks for the blocks currently being encrypted/decrypted
+ TWEAKV0 .req v16
+ TWEAKV1 .req v17
+ TWEAKV2 .req v18
+ TWEAKV3 .req v19
+ TWEAKV4 .req v20
+ TWEAKV5 .req v21
+ TWEAKV6 .req v22
+ TWEAKV7 .req v23
+
+ .align 4
+.Lror64_8_table:
+ .octa 0x080f0e0d0c0b0a090007060504030201
+.Lror32_8_table:
+ .octa 0x0c0f0e0d080b0a090407060500030201
+.Lrol64_8_table:
+ .octa 0x0e0d0c0b0a09080f0605040302010007
+.Lrol32_8_table:
+ .octa 0x0e0d0c0f0a09080b0605040702010003
+.Lgf128mul_table:
+ .octa 0x00000000000000870000000000000001
+.Lgf64mul_table:
+ .octa 0x0000000000000000000000002d361b00
+
+/*
+ * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
+ *
+ * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
+ * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
+ * of ROUND_KEY. 'n' is the lane size: 64 for Speck128, or 32 for Speck64.
+ * 'lanes' is the lane specifier: "2d" for Speck128 or "4s" for Speck64.
+ */
+.macro _speck_round_128bytes n, lanes
+
+ // x = ror(x, 8)
+ tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
+ tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
+ tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
+ tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
+
+ // x += y
+ add X_0.\lanes, X_0.\lanes, Y_0.\lanes
+ add X_1.\lanes, X_1.\lanes, Y_1.\lanes
+ add X_2.\lanes, X_2.\lanes, Y_2.\lanes
+ add X_3.\lanes, X_3.\lanes, Y_3.\lanes
+
+ // x ^= k
+ eor X_0.16b, X_0.16b, ROUND_KEY.16b
+ eor X_1.16b, X_1.16b, ROUND_KEY.16b
+ eor X_2.16b, X_2.16b, ROUND_KEY.16b
+ eor X_3.16b, X_3.16b, ROUND_KEY.16b
+
+ // y = rol(y, 3)
+ shl TMP0.\lanes, Y_0.\lanes, #3
+ shl TMP1.\lanes, Y_1.\lanes, #3
+ shl TMP2.\lanes, Y_2.\lanes, #3
+ shl TMP3.\lanes, Y_3.\lanes, #3
+ sri TMP0.\lanes, Y_0.\lanes, #(\n - 3)
+ sri TMP1.\lanes, Y_1.\lanes, #(\n - 3)
+ sri TMP2.\lanes, Y_2.\lanes, #(\n - 3)
+ sri TMP3.\lanes, Y_3.\lanes, #(\n - 3)
+
+ // y ^= x
+ eor Y_0.16b, TMP0.16b, X_0.16b
+ eor Y_1.16b, TMP1.16b, X_1.16b
+ eor Y_2.16b, TMP2.16b, X_2.16b
+ eor Y_3.16b, TMP3.16b, X_3.16b
+.endm
+
+/*
+ * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
+ *
+ * This is the inverse of _speck_round_128bytes().
+ */
+.macro _speck_unround_128bytes n, lanes
+
+ // y ^= x
+ eor TMP0.16b, Y_0.16b, X_0.16b
+ eor TMP1.16b, Y_1.16b, X_1.16b
+ eor TMP2.16b, Y_2.16b, X_2.16b
+ eor TMP3.16b, Y_3.16b, X_3.16b
+
+ // y = ror(y, 3)
+ ushr Y_0.\lanes, TMP0.\lanes, #3
+ ushr Y_1.\lanes, TMP1.\lanes, #3
+ ushr Y_2.\lanes, TMP2.\lanes, #3
+ ushr Y_3.\lanes, TMP3.\lanes, #3
+ sli Y_0.\lanes, TMP0.\lanes, #(\n - 3)
+ sli Y_1.\lanes, TMP1.\lanes, #(\n - 3)
+ sli Y_2.\lanes, TMP2.\lanes, #(\n - 3)
+ sli Y_3.\lanes, TMP3.\lanes, #(\n - 3)
+
+ // x ^= k
+ eor X_0.16b, X_0.16b, ROUND_KEY.16b
+ eor X_1.16b, X_1.16b, ROUND_KEY.16b
+ eor X_2.16b, X_2.16b, ROUND_KEY.16b
+ eor X_3.16b, X_3.16b, ROUND_KEY.16b
+
+ // x -= y
+ sub X_0.\lanes, X_0.\lanes, Y_0.\lanes
+ sub X_1.\lanes, X_1.\lanes, Y_1.\lanes
+ sub X_2.\lanes, X_2.\lanes, Y_2.\lanes
+ sub X_3.\lanes, X_3.\lanes, Y_3.\lanes
+
+ // x = rol(x, 8)
+ tbl X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
+ tbl X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
+ tbl X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
+ tbl X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
+.endm
+
+.macro _next_xts_tweak next, cur, tmp, n
+.if \n == 64
+ /*
+ * Calculate the next tweak by multiplying the current one by x,
+ * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
+ */
+ sshr \tmp\().2d, \cur\().2d, #63
+ and \tmp\().16b, \tmp\().16b, GFMUL_TABLE.16b
+ shl \next\().2d, \cur\().2d, #1
+ ext \tmp\().16b, \tmp\().16b, \tmp\().16b, #8
+ eor \next\().16b, \next\().16b, \tmp\().16b
+.else
+ /*
+ * Calculate the next two tweaks by multiplying the current ones by x^2,
+ * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
+ */
+ ushr \tmp\().2d, \cur\().2d, #62
+ shl \next\().2d, \cur\().2d, #2
+ tbl \tmp\().16b, {GFMUL_TABLE.16b}, \tmp\().16b
+ eor \next\().16b, \next\().16b, \tmp\().16b
+.endif
+.endm
+
+/*
+ * _speck_xts_crypt() - Speck-XTS encryption/decryption
+ *
+ * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
+ * using Speck-XTS, specifically the variant with a block size of '2n' and round
+ * count given by NROUNDS. The expanded round keys are given in ROUND_KEYS, and
+ * the current XTS tweak value is given in TWEAK. It's assumed that NBYTES is a
+ * nonzero multiple of 128.
+ */
+.macro _speck_xts_crypt n, lanes, decrypting
+
+ /*
+ * If decrypting, modify the ROUND_KEYS parameter to point to the last
+ * round key rather than the first, since for decryption the round keys
+ * are used in reverse order.
+ */
+.if \decrypting
+ mov NROUNDS, NROUNDS /* zero the high 32 bits */
+.if \n == 64
+ add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #3
+ sub ROUND_KEYS, ROUND_KEYS, #8
+.else
+ add ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #2
+ sub ROUND_KEYS, ROUND_KEYS, #4
+.endif
+.endif
+
+ // Load the index vector for tbl-based 8-bit rotates
+.if \decrypting
+ ldr ROTATE_TABLE_Q, .Lrol\n\()_8_table
+.else
+ ldr ROTATE_TABLE_Q, .Lror\n\()_8_table
+.endif
+
+ // One-time XTS preparation
+.if \n == 64
+ // Load first tweak
+ ld1 {TWEAKV0.16b}, [TWEAK]
+
+ // Load GF(2^128) multiplication table
+ ldr GFMUL_TABLE_Q, .Lgf128mul_table
+.else
+ // Load first tweak
+ ld1 {TWEAKV0.8b}, [TWEAK]
+
+ // Load GF(2^64) multiplication table
+ ldr GFMUL_TABLE_Q, .Lgf64mul_table
+
+ // Calculate second tweak, packing it together with the first
+ ushr TMP0.2d, TWEAKV0.2d, #63
+ shl TMP1.2d, TWEAKV0.2d, #1
+ tbl TMP0.8b, {GFMUL_TABLE.16b}, TMP0.8b
+ eor TMP0.8b, TMP0.8b, TMP1.8b
+ mov TWEAKV0.d[1], TMP0.d[0]
+.endif
+
+.Lnext_128bytes_\@:
+
+ // Calculate XTS tweaks for next 128 bytes
+ _next_xts_tweak TWEAKV1, TWEAKV0, TMP0, \n
+ _next_xts_tweak TWEAKV2, TWEAKV1, TMP0, \n
+ _next_xts_tweak TWEAKV3, TWEAKV2, TMP0, \n
+ _next_xts_tweak TWEAKV4, TWEAKV3, TMP0, \n
+ _next_xts_tweak TWEAKV5, TWEAKV4, TMP0, \n
+ _next_xts_tweak TWEAKV6, TWEAKV5, TMP0, \n
+ _next_xts_tweak TWEAKV7, TWEAKV6, TMP0, \n
+ _next_xts_tweak TWEAKV_NEXT, TWEAKV7, TMP0, \n
+
+ // Load the next source blocks into {X,Y}[0-3]
+ ld1 {X_0.16b-Y_1.16b}, [SRC], #64
+ ld1 {X_2.16b-Y_3.16b}, [SRC], #64
+
+ // XOR the source blocks with their XTS tweaks
+ eor TMP0.16b, X_0.16b, TWEAKV0.16b
+ eor Y_0.16b, Y_0.16b, TWEAKV1.16b
+ eor TMP1.16b, X_1.16b, TWEAKV2.16b
+ eor Y_1.16b, Y_1.16b, TWEAKV3.16b
+ eor TMP2.16b, X_2.16b, TWEAKV4.16b
+ eor Y_2.16b, Y_2.16b, TWEAKV5.16b
+ eor TMP3.16b, X_3.16b, TWEAKV6.16b
+ eor Y_3.16b, Y_3.16b, TWEAKV7.16b
+
+ /*
+ * De-interleave the 'x' and 'y' elements of each block, i.e. make it so
+ * that the X[0-3] registers contain only the second halves of blocks,
+ * and the Y[0-3] registers contain only the first halves of blocks.
+ * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
+ */
+ uzp2 X_0.\lanes, TMP0.\lanes, Y_0.\lanes
+ uzp1 Y_0.\lanes, TMP0.\lanes, Y_0.\lanes
+ uzp2 X_1.\lanes, TMP1.\lanes, Y_1.\lanes
+ uzp1 Y_1.\lanes, TMP1.\lanes, Y_1.\lanes
+ uzp2 X_2.\lanes, TMP2.\lanes, Y_2.\lanes
+ uzp1 Y_2.\lanes, TMP2.\lanes, Y_2.\lanes
+ uzp2 X_3.\lanes, TMP3.\lanes, Y_3.\lanes
+ uzp1 Y_3.\lanes, TMP3.\lanes, Y_3.\lanes
+
+ // Do the cipher rounds
+ mov x6, ROUND_KEYS
+ mov w7, NROUNDS
+.Lnext_round_\@:
+.if \decrypting
+ ld1r {ROUND_KEY.\lanes}, [x6]
+ sub x6, x6, #( \n / 8 )
+ _speck_unround_128bytes \n, \lanes
+.else
+ ld1r {ROUND_KEY.\lanes}, [x6], #( \n / 8 )
+ _speck_round_128bytes \n, \lanes
+.endif
+ subs w7, w7, #1
+ bne .Lnext_round_\@
+
+ // Re-interleave the 'x' and 'y' elements of each block
+ zip1 TMP0.\lanes, Y_0.\lanes, X_0.\lanes
+ zip2 Y_0.\lanes, Y_0.\lanes, X_0.\lanes
+ zip1 TMP1.\lanes, Y_1.\lanes, X_1.\lanes
+ zip2 Y_1.\lanes, Y_1.\lanes, X_1.\lanes
+ zip1 TMP2.\lanes, Y_2.\lanes, X_2.\lanes
+ zip2 Y_2.\lanes, Y_2.\lanes, X_2.\lanes
+ zip1 TMP3.\lanes, Y_3.\lanes, X_3.\lanes
+ zip2 Y_3.\lanes, Y_3.\lanes, X_3.\lanes
+
+ // XOR the encrypted/decrypted blocks with the tweaks calculated earlier
+ eor X_0.16b, TMP0.16b, TWEAKV0.16b
+ eor Y_0.16b, Y_0.16b, TWEAKV1.16b
+ eor X_1.16b, TMP1.16b, TWEAKV2.16b
+ eor Y_1.16b, Y_1.16b, TWEAKV3.16b
+ eor X_2.16b, TMP2.16b, TWEAKV4.16b
+ eor Y_2.16b, Y_2.16b, TWEAKV5.16b
+ eor X_3.16b, TMP3.16b, TWEAKV6.16b
+ eor Y_3.16b, Y_3.16b, TWEAKV7.16b
+ mov TWEAKV0.16b, TWEAKV_NEXT.16b
+
+ // Store the ciphertext in the destination buffer
+ st1 {X_0.16b-Y_1.16b}, [DST], #64
+ st1 {X_2.16b-Y_3.16b}, [DST], #64
+
+ // Continue if there are more 128-byte chunks remaining
+ subs NBYTES, NBYTES, #128
+ bne .Lnext_128bytes_\@
+
+ // Store the next tweak and return
+.if \n == 64
+ st1 {TWEAKV_NEXT.16b}, [TWEAK]
+.else
+ st1 {TWEAKV_NEXT.8b}, [TWEAK]
+.endif
+ ret
+.endm
+
+ENTRY(speck128_xts_encrypt_neon)
+ _speck_xts_crypt n=64, lanes=2d, decrypting=0
+ENDPROC(speck128_xts_encrypt_neon)
+
+ENTRY(speck128_xts_decrypt_neon)
+ _speck_xts_crypt n=64, lanes=2d, decrypting=1
+ENDPROC(speck128_xts_decrypt_neon)
+
+ENTRY(speck64_xts_encrypt_neon)
+ _speck_xts_crypt n=32, lanes=4s, decrypting=0
+ENDPROC(speck64_xts_encrypt_neon)
+
+ENTRY(speck64_xts_decrypt_neon)
+ _speck_xts_crypt n=32, lanes=4s, decrypting=1
+ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm64/crypto/speck-neon-glue.c b/arch/arm64/crypto/speck-neon-glue.c
new file mode 100644
index 000000000000..c7d18569d408
--- /dev/null
+++ b/arch/arm64/crypto/speck-neon-glue.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
+ * (64-bit version; based on the 32-bit version)
+ *
+ * Copyright (c) 2018 Google, Inc
+ */
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+#include <asm/simd.h>
+#include <crypto/algapi.h>
+#include <crypto/gf128mul.h>
+#include <crypto/speck.h>
+#include <crypto/xts.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/* The assembly functions only handle multiples of 128 bytes */
+#define SPECK_NEON_CHUNK_SIZE 128
+
+/* Speck128 */
+
+struct speck128_xts_tfm_ctx {
+ struct speck128_tfm_ctx main_key;
+ struct speck128_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
+ void *dst, const void *src,
+ unsigned int nbytes, void *tweak);
+
+asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
+ void *dst, const void *src,
+ unsigned int nbytes, void *tweak);
+
+typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
+ u8 *, const u8 *);
+typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
+ const void *, unsigned int, void *);
+
+static __always_inline int
+__speck128_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes,
+ speck128_crypt_one_t crypt_one,
+ speck128_xts_crypt_many_t crypt_many)
+{
+ struct crypto_blkcipher *tfm = desc->tfm;
+ const struct speck128_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
+ struct blkcipher_walk walk;
+ le128 tweak;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
+
+ crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+ while (walk.nbytes > 0) {
+ unsigned int nbytes = walk.nbytes;
+ u8 *dst = walk.dst.virt.addr;
+ const u8 *src = walk.src.virt.addr;
+
+ if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+ unsigned int count;
+
+ count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+ kernel_neon_begin();
+ (*crypt_many)(ctx->main_key.round_keys,
+ ctx->main_key.nrounds,
+ dst, src, count, &tweak);
+ kernel_neon_end();
+ dst += count;
+ src += count;
+ nbytes -= count;
+ }
+
+ /* Handle any remainder with generic code */
+ while (nbytes >= sizeof(tweak)) {
+ le128_xor((le128 *)dst, (const le128 *)src, &tweak);
+ (*crypt_one)(&ctx->main_key, dst, dst);
+ le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
+ gf128mul_x_ble((be128 *)&tweak, (const be128 *)&tweak);
+
+ dst += sizeof(tweak);
+ src += sizeof(tweak);
+ nbytes -= sizeof(tweak);
+ }
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+
+ return err;
+}
+
+static int speck128_xts_encrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src,
+ unsigned int nbytes)
+{
+ return __speck128_xts_crypt(desc, dst, src, nbytes,
+ crypto_speck128_encrypt,
+ speck128_xts_encrypt_neon);
+}
+
+static int speck128_xts_decrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst,
+ struct scatterlist *src,
+ unsigned int nbytes)
+{
+ return __speck128_xts_crypt(desc, dst, src, nbytes,
+ crypto_speck128_decrypt,
+ speck128_xts_decrypt_neon);
+}
+
+static int speck128_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct speck128_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
+
+ if (keylen % 2)
+ return -EINVAL;
+
+ keylen /= 2;
+
+ err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
+ if (err)
+ return err;
+
+ return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+/* Speck64 */
+
+struct speck64_xts_tfm_ctx {
+ struct speck64_tfm_ctx main_key;
+ struct speck64_tfm_ctx tweak_key;
+};
+
+asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
+ void *dst, const void *src,
+ unsigned int nbytes, void *tweak);
+
+asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
+ void *dst, const void *src,
+ unsigned int nbytes, void *tweak);
+
+typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
+ u8 *, const u8 *);
+typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
+ const void *, unsigned int, void *);
+
+static __always_inline int
+__speck64_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+ struct scatterlist *src, unsigned int nbytes,
+ speck64_crypt_one_t crypt_one,
+ speck64_xts_crypt_many_t crypt_many)
+{
+ struct crypto_blkcipher *tfm = desc->tfm;
+ const struct speck64_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
+ struct blkcipher_walk walk;
+ __le64 tweak;
+ int err;
+
+ blkcipher_walk_init(&walk, dst, src, nbytes);
+ err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
+
+ crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
+
+ while (walk.nbytes > 0) {
+ unsigned int nbytes = walk.nbytes;
+ u8 *dst = walk.dst.virt.addr;
+ const u8 *src = walk.src.virt.addr;
+
+ if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
+ unsigned int count;
+
+ count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
+ kernel_neon_begin();
+ (*crypt_many)(ctx->main_key.round_keys,
+ ctx->main_key.nrounds,
+ dst, src, count, &tweak);
+ kernel_neon_end();
+ dst += count;
+ src += count;
+ nbytes -= count;
+ }
+
+ /* Handle any remainder with generic code */
+ while (nbytes >= sizeof(tweak)) {
+ *(__le64 *)dst = *(__le64 *)src ^ tweak;
+ (*crypt_one)(&ctx->main_key, dst, dst);
+ *(__le64 *)dst ^= tweak;
+ tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
+ ((tweak & cpu_to_le64(1ULL << 63)) ?
+ 0x1B : 0));
+ dst += sizeof(tweak);
+ src += sizeof(tweak);
+ nbytes -= sizeof(tweak);
+ }
+ err = blkcipher_walk_done(desc, &walk, nbytes);
+ }
+
+ return err;
+}
+
+static int speck64_xts_encrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst, struct scatterlist *src,
+ unsigned int nbytes)
+{
+ return __speck64_xts_crypt(desc, dst, src, nbytes,
+ crypto_speck64_encrypt,
+ speck64_xts_encrypt_neon);
+}
+
+static int speck64_xts_decrypt(struct blkcipher_desc *desc,
+ struct scatterlist *dst, struct scatterlist *src,
+ unsigned int nbytes)
+{
+ return __speck64_xts_crypt(desc, dst, src, nbytes,
+ crypto_speck64_decrypt,
+ speck64_xts_decrypt_neon);
+}
+
+static int speck64_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
+ unsigned int keylen)
+{
+ struct speck64_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+ int err;
+
+ if (keylen % 2)
+ return -EINVAL;
+
+ keylen /= 2;
+
+ err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
+ if (err)
+ return err;
+
+ return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
+}
+
+static struct crypto_alg speck_algs[] = {
+ {
+ .cra_name = "xts(speck128)",
+ .cra_driver_name = "xts-speck128-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SPECK128_BLOCK_SIZE,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct speck128_xts_tfm_ctx),
+ .cra_alignmask = 7,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = 2 * SPECK128_128_KEY_SIZE,
+ .max_keysize = 2 * SPECK128_256_KEY_SIZE,
+ .ivsize = SPECK128_BLOCK_SIZE,
+ .setkey = speck128_xts_setkey,
+ .encrypt = speck128_xts_encrypt,
+ .decrypt = speck128_xts_decrypt,
+ }
+ }
+ }, {
+ .cra_name = "xts(speck64)",
+ .cra_driver_name = "xts-speck64-neon",
+ .cra_priority = 300,
+ .cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
+ .cra_blocksize = SPECK64_BLOCK_SIZE,
+ .cra_type = &crypto_blkcipher_type,
+ .cra_ctxsize = sizeof(struct speck64_xts_tfm_ctx),
+ .cra_alignmask = 7,
+ .cra_module = THIS_MODULE,
+ .cra_u = {
+ .blkcipher = {
+ .min_keysize = 2 * SPECK64_96_KEY_SIZE,
+ .max_keysize = 2 * SPECK64_128_KEY_SIZE,
+ .ivsize = SPECK64_BLOCK_SIZE,
+ .setkey = speck64_xts_setkey,
+ .encrypt = speck64_xts_encrypt,
+ .decrypt = speck64_xts_decrypt,
+ }
+ }
+ }
+};
+
+static int __init speck_neon_module_init(void)
+{
+ if (!(elf_hwcap & HWCAP_ASIMD))
+ return -ENODEV;
+ return crypto_register_algs(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+static void __exit speck_neon_module_exit(void)
+{
+ crypto_unregister_algs(speck_algs, ARRAY_SIZE(speck_algs));
+}
+
+module_init(speck_neon_module_init);
+module_exit(speck_neon_module_exit);
+
+MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
+MODULE_ALIAS_CRYPTO("xts(speck128)");
+MODULE_ALIAS_CRYPTO("xts-speck128-neon");
+MODULE_ALIAS_CRYPTO("xts(speck64)");
+MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 279978e1a070..1d870666b8d9 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -48,8 +48,10 @@
* TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
*/
#define VA_BITS (CONFIG_ARM64_VA_BITS)
-#define VA_START (UL(0xffffffffffffffff) << VA_BITS)
-#define PAGE_OFFSET (UL(0xffffffffffffffff) << (VA_BITS - 1))
+#define VA_START (UL(0xffffffffffffffff) - \
+ (UL(1) << VA_BITS) + 1)
+#define PAGE_OFFSET (UL(0xffffffffffffffff) - \
+ (UL(1) << (VA_BITS - 1)) + 1)
#define KIMAGE_VADDR (MODULES_END)
#define MODULES_END (MODULES_VADDR + MODULES_VSIZE)
#define MODULES_VADDR (VA_START + KASAN_SHADOW_SIZE)
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 23ee968646a9..b30bdffa3066 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1355,3 +1355,15 @@ int pmd_clear_huge(pmd_t *pmd)
pmd_clear(pmd);
return 1;
}
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+int pud_free_pmd_page(pud_t *pud)
+{
+ return pud_none(*pud);
+}
+
+int pmd_free_pte_page(pmd_t *pmd)
+{
+ return pmd_none(*pmd);
+}
+#endif
diff --git a/arch/frv/include/asm/timex.h b/arch/frv/include/asm/timex.h
index a89bddefdacf..139093fab326 100644
--- a/arch/frv/include/asm/timex.h
+++ b/arch/frv/include/asm/timex.h
@@ -16,5 +16,11 @@ static inline cycles_t get_cycles(void)
#define vxtime_lock() do {} while (0)
#define vxtime_unlock() do {} while (0)
+/* This attribute is used in include/linux/jiffies.h alongside with
+ * __cacheline_aligned_in_smp. It is assumed that __cacheline_aligned_in_smp
+ * for frv does not contain another section specification.
+ */
+#define __jiffy_arch_data __attribute__((__section__(".data")))
+
#endif
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index b15933c31b2f..36b2c94a8eb5 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -153,7 +153,7 @@ slot (const struct insn *insn)
static int
apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
{
- if (slot(insn) != 2) {
+ if (slot(insn) != 1 && slot(insn) != 2) {
printk(KERN_ERR "%s: invalid slot number %d for IMM64\n",
mod->name, slot(insn));
return 0;
@@ -165,7 +165,7 @@ apply_imm64 (struct module *mod, struct insn *insn, uint64_t val)
static int
apply_imm60 (struct module *mod, struct insn *insn, uint64_t val)
{
- if (slot(insn) != 2) {
+ if (slot(insn) != 1 && slot(insn) != 2) {
printk(KERN_ERR "%s: invalid slot number %d for IMM60\n",
mod->name, slot(insn));
return 0;
diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c
index 9ab48ff80c1c..6d11ae581ea7 100644
--- a/arch/mips/ath25/board.c
+++ b/arch/mips/ath25/board.c
@@ -135,6 +135,8 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
}
board_data = kzalloc(BOARD_CONFIG_BUFSZ, GFP_KERNEL);
+ if (!board_data)
+ goto error;
ath25_board.config = (struct ath25_boarddata *)board_data;
memcpy_fromio(board_data, bcfg, 0x100);
if (broken_boarddata) {
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 4f9eb0576884..10d0b2140375 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2246,6 +2246,8 @@ static int __init octeon_irq_init_cib(struct device_node *ciu_node,
}
host_data = kzalloc(sizeof(*host_data), GFP_KERNEL);
+ if (!host_data)
+ return -ENOMEM;
raw_spin_lock_init(&host_data->lock);
addr = of_get_address(ciu_node, 0, NULL, NULL);
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 78cf8c2f1de0..4874712b475e 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -166,11 +166,11 @@ static void bmips_prepare_cpus(unsigned int max_cpus)
return;
}
- if (request_irq(IPI0_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
- "smp_ipi0", NULL))
+ if (request_irq(IPI0_IRQ, bmips_ipi_interrupt,
+ IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi0", NULL))
panic("Can't request IPI0 interrupt");
- if (request_irq(IPI1_IRQ, bmips_ipi_interrupt, IRQF_PERCPU,
- "smp_ipi1", NULL))
+ if (request_irq(IPI1_IRQ, bmips_ipi_interrupt,
+ IRQF_PERCPU | IRQF_NO_SUSPEND, "smp_ipi1", NULL))
panic("Can't request IPI1 interrupt");
}
diff --git a/arch/mips/net/bpf_jit.c b/arch/mips/net/bpf_jit.c
index 1a8c96035716..c0c1e9529dbd 100644
--- a/arch/mips/net/bpf_jit.c
+++ b/arch/mips/net/bpf_jit.c
@@ -527,7 +527,8 @@ static void save_bpf_jit_regs(struct jit_ctx *ctx, unsigned offset)
u32 sflags, tmp_flags;
/* Adjust the stack pointer */
- emit_stack_offset(-align_sp(offset), ctx);
+ if (offset)
+ emit_stack_offset(-align_sp(offset), ctx);
tmp_flags = sflags = ctx->flags >> SEEN_SREG_SFT;
/* sflags is essentially a bitmap */
@@ -579,7 +580,8 @@ static void restore_bpf_jit_regs(struct jit_ctx *ctx,
emit_load_stack_reg(r_ra, r_sp, real_off, ctx);
/* Restore the sp and discard the scrach memory */
- emit_stack_offset(align_sp(offset), ctx);
+ if (offset)
+ emit_stack_offset(align_sp(offset), ctx);
}
static unsigned int get_stack_depth(struct jit_ctx *ctx)
@@ -626,8 +628,14 @@ static void build_prologue(struct jit_ctx *ctx)
if (ctx->flags & SEEN_X)
emit_jit_reg_move(r_X, r_zero, ctx);
- /* Do not leak kernel data to userspace */
- if (bpf_needs_clear_a(&ctx->skf->insns[0]))
+ /*
+ * Do not leak kernel data to userspace, we only need to clear
+ * r_A if it is ever used. In fact if it is never used, we
+ * will not save/restore it, so clearing it in this case would
+ * corrupt the state of the caller.
+ */
+ if (bpf_needs_clear_a(&ctx->skf->insns[0]) &&
+ (ctx->flags & SEEN_A))
emit_jit_reg_move(r_A, r_zero, ctx);
}
diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S
index 5d2e0c8d29c0..88a2075305d1 100644
--- a/arch/mips/net/bpf_jit_asm.S
+++ b/arch/mips/net/bpf_jit_asm.S
@@ -90,18 +90,14 @@ FEXPORT(sk_load_half_positive)
is_offset_in_header(2, half)
/* Offset within header boundaries */
PTR_ADDU t1, $r_skb_data, offset
- .set reorder
- lh $r_A, 0(t1)
- .set noreorder
+ lhu $r_A, 0(t1)
#ifdef CONFIG_CPU_LITTLE_ENDIAN
# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
- wsbh t0, $r_A
- seh $r_A, t0
+ wsbh $r_A, $r_A
# else
- sll t0, $r_A, 24
- andi t1, $r_A, 0xff00
- sra t0, t0, 16
- srl t1, t1, 8
+ sll t0, $r_A, 8
+ srl t1, $r_A, 8
+ andi t0, t0, 0xff00
or $r_A, t0, t1
# endif
#endif
@@ -115,7 +111,7 @@ FEXPORT(sk_load_byte_positive)
is_offset_in_header(1, byte)
/* Offset within header boundaries */
PTR_ADDU t1, $r_skb_data, offset
- lb $r_A, 0(t1)
+ lbu $r_A, 0(t1)
jr $r_ra
move $r_ret, zero
END(sk_load_byte)
@@ -139,6 +135,11 @@ FEXPORT(sk_load_byte_positive)
* (void *to) is returned in r_s0
*
*/
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define DS_OFFSET(SIZE) (4 * SZREG)
+#else
+#define DS_OFFSET(SIZE) ((4 * SZREG) + (4 - SIZE))
+#endif
#define bpf_slow_path_common(SIZE) \
/* Quick check. Are we within reasonable boundaries? */ \
LONG_ADDIU $r_s1, $r_skb_len, -SIZE; \
@@ -150,7 +151,7 @@ FEXPORT(sk_load_byte_positive)
PTR_LA t0, skb_copy_bits; \
PTR_S $r_ra, (5 * SZREG)($r_sp); \
/* Assign low slot to a2 */ \
- move a2, $r_sp; \
+ PTR_ADDIU a2, $r_sp, DS_OFFSET(SIZE); \
jalr t0; \
/* Reset our destination slot (DS but it's ok) */ \
INT_S zero, (4 * SZREG)($r_sp); \
diff --git a/arch/mips/ralink/reset.c b/arch/mips/ralink/reset.c
index ee117c4bc4a3..8037a4bd84fd 100644
--- a/arch/mips/ralink/reset.c
+++ b/arch/mips/ralink/reset.c
@@ -96,16 +96,9 @@ static void ralink_restart(char *command)
unreachable();
}
-static void ralink_halt(void)
-{
- local_irq_disable();
- unreachable();
-}
-
static int __init mips_reboot_setup(void)
{
_machine_restart = ralink_restart;
- _machine_halt = ralink_halt;
return 0;
}
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 79ad35abd196..ddec22828673 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -177,12 +177,15 @@ map_again:
ret = ppc_md.hpte_insert(hpteg, vpn, hpaddr, rflags, vflags,
hpsize, hpsize, MMU_SEGSIZE_256M);
- if (ret < 0) {
+ if (ret == -1) {
/* If we couldn't map a primary PTE, try a secondary */
hash = ~hash;
vflags ^= HPTE_V_SECONDARY;
attempt++;
goto map_again;
+ } else if (ret < 0) {
+ r = -EIO;
+ goto out_unlock;
} else {
trace_kvm_book3s_64_mmu_map(rflags, hpteg,
vpn, hpaddr, orig_pte);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 64891b081ad5..81313844d81c 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -625,7 +625,11 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
kvmppc_mmu_unmap_page(vcpu, &pte);
}
/* The guest's PTE is not mapped yet. Map on the host */
- kvmppc_mmu_map_page(vcpu, &pte, iswrite);
+ if (kvmppc_mmu_map_page(vcpu, &pte, iswrite) == -EIO) {
+ /* Exit KVM if mapping failed */
+ run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ return RESUME_HOST;
+ }
if (data)
vcpu->stat.sp_storage++;
else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index a67c6d781c52..d154e333f76b 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -294,7 +294,7 @@ int __kprobes do_page_fault(struct pt_regs *regs, unsigned long address,
* can result in fault, which will cause a deadlock when called with
* mmap_sem held
*/
- if (user_mode(regs))
+ if (!is_exec && user_mode(regs))
store_update_sp = store_updates_sp(regs);
if (user_mode(regs))
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 82fac1b62626..568930248ad0 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -200,6 +200,15 @@ KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr)
LDFLAGS := -m elf_$(UTS_MACHINE)
+#
+# The 64-bit kernel must be aligned to 2MB. Pass -z max-page-size=0x200000 to
+# the linker to force 2MB page size regardless of the default page size used
+# by the linker.
+#
+ifdef CONFIG_X86_64
+LDFLAGS += $(call ld-option, -z max-page-size=0x200000)
+endif
+
# Speed up the build
KBUILD_CFLAGS += -pipe
# Workaround for a gcc prelease that unfortunately was shipped in a suse release
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 79dac1758e7c..16df89c30c20 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -366,6 +366,10 @@ static void parse_elf(void *output)
switch (phdr->p_type) {
case PT_LOAD:
+#ifdef CONFIG_X86_64
+ if ((phdr->p_align % 0x200000) != 0)
+ error("Alignment of LOAD segment isn't multiple of 2MB");
+#endif
#ifdef CONFIG_RELOCATABLE
dest = output;
dest += (phdr->p_paddr - LOAD_PHYSICAL_ADDR);
diff --git a/arch/x86/configs/i386_ranchu_defconfig b/arch/x86/configs/i386_ranchu_defconfig
index 65ed8c8f8444..dde67eacd8e2 100644
--- a/arch/x86/configs/i386_ranchu_defconfig
+++ b/arch/x86/configs/i386_ranchu_defconfig
@@ -240,6 +240,7 @@ CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_KEYRESET=y
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+CONFIG_KEYBOARD_GOLDFISH_ROTARY=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_JOYSTICK=y
CONFIG_JOYSTICK_XPAD=y
diff --git a/arch/x86/configs/x86_64_ranchu_defconfig b/arch/x86/configs/x86_64_ranchu_defconfig
index d977bd91e390..e8ed8eef62ec 100644
--- a/arch/x86/configs/x86_64_ranchu_defconfig
+++ b/arch/x86/configs/x86_64_ranchu_defconfig
@@ -237,6 +237,7 @@ CONFIG_INPUT_EVDEV=y
CONFIG_INPUT_KEYRESET=y
# CONFIG_KEYBOARD_ATKBD is not set
CONFIG_KEYBOARD_GOLDFISH_EVENTS=y
+CONFIG_KEYBOARD_GOLDFISH_ROTARY=y
# CONFIG_INPUT_MOUSE is not set
CONFIG_INPUT_JOYSTICK=y
CONFIG_JOYSTICK_XPAD=y
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 8648158f3916..f8fe11d24cde 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -66,8 +66,6 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
void (*fn)(struct cast5_ctx *ctx, u8 *dst, const u8 *src);
int err;
- fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way;
-
err = blkcipher_walk_virt(desc, walk);
desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
@@ -79,6 +77,7 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
/* Process multi-block batch */
if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
+ fn = (enc) ? cast5_ecb_enc_16way : cast5_ecb_dec_16way;
do {
fn(ctx, wdst, wsrc);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 113de1592cc1..a619254275f2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -178,12 +178,14 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
jnz tracesys
entry_SYSCALL_64_fastpath:
#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max, %rax
+ cmpq $NR_syscalls, %rax
#else
andl $__SYSCALL_MASK, %eax
- cmpl $__NR_syscall_max, %eax
+ cmpl $NR_syscalls, %eax
#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ jae 1f /* return -ENOSYS (already in pt_regs->ax) */
+ sbb %rcx, %rcx /* array_index_mask_nospec() */
+ and %rcx, %rax
movq %r10, %rcx
#ifdef CONFIG_RETPOLINE
movq sys_call_table(, %rax, 8), %rax
@@ -276,12 +278,14 @@ tracesys_phase2:
RESTORE_C_REGS_EXCEPT_RAX
RESTORE_EXTRA_REGS
#if __SYSCALL_MASK == ~0
- cmpq $__NR_syscall_max, %rax
+ cmpq $NR_syscalls, %rax
#else
andl $__SYSCALL_MASK, %eax
- cmpl $__NR_syscall_max, %eax
+ cmpl $NR_syscalls, %eax
#endif
- ja 1f /* return -ENOSYS (already in pt_regs->ax) */
+ jae 1f /* return -ENOSYS (already in pt_regs->ax) */
+ sbb %rcx, %rcx /* array_index_mask_nospec() */
+ and %rcx, %rax
movq %r10, %rcx /* fixup for C */
#ifdef CONFIG_RETPOLINE
movq sys_call_table(, %rax, 8), %rax
@@ -1020,7 +1024,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
#endif /* CONFIG_HYPERV */
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0
idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 66094a0473a8..249f1c769f21 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -195,4 +195,41 @@ static inline void vmexit_fill_RSB(void)
}
#endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ * callq do_rop
+ * spec_trap:
+ * pause
+ * lfence
+ * jmp spec_trap
+ * do_rop:
+ * mov %rax,(%rsp)
+ * retq
+ *
+ * Without retpolines configured:
+ *
+ * jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE 17
+# define RETPOLINE_RAX_BPF_JIT() \
+ EMIT1_off32(0xE8, 7); /* callq do_rop */ \
+ /* spec_trap: */ \
+ EMIT2(0xF3, 0x90); /* pause */ \
+ EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \
+ EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
+ /* do_rop: */ \
+ EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \
+ EMIT1(0xC3); /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE 2
+# define RETPOLINE_RAX_BPF_JIT() \
+ EMIT2(0xFF, 0xE0); /* jmp *%rax */
+#endif
+
#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 6b6e16d813b9..dd11f5cb4149 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -310,6 +310,7 @@ enum vmcs_field {
#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */
#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */
#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */
+#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */
#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */
/* GUEST_INTERRUPTIBILITY_INFO flags. */
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index a41e523536a2..592e260ba05b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -91,8 +91,12 @@ out_data:
return NULL;
}
-static void free_apic_chip_data(struct apic_chip_data *data)
+static void free_apic_chip_data(unsigned int virq, struct apic_chip_data *data)
{
+#ifdef CONFIG_X86_IO_APIC
+ if (virq < nr_legacy_irqs())
+ legacy_irq_data[virq] = NULL;
+#endif
if (data) {
free_cpumask_var(data->domain);
free_cpumask_var(data->old_domain);
@@ -316,11 +320,7 @@ static void x86_vector_free_irqs(struct irq_domain *domain,
apic_data = irq_data->chip_data;
irq_domain_reset_irq_data(irq_data);
raw_spin_unlock_irqrestore(&vector_lock, flags);
- free_apic_chip_data(apic_data);
-#ifdef CONFIG_X86_IO_APIC
- if (virq + i < nr_legacy_irqs())
- legacy_irq_data[virq + i] = NULL;
-#endif
+ free_apic_chip_data(virq + i, apic_data);
}
}
}
@@ -361,7 +361,7 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
err = assign_irq_vector_policy(virq + i, node, data, info);
if (err) {
irq_data->chip_data = NULL;
- free_apic_chip_data(data);
+ free_apic_chip_data(virq + i, data);
goto error;
}
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ecaf7c9baf75..2bbc74f8a4a8 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -175,8 +175,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
}
if (i >= ARRAY_SIZE(mitigation_options)) {
- pr_err("unknown option (%s). Switching to AUTO select\n",
- mitigation_options[i].option);
+ pr_err("unknown option (%s). Switching to AUTO select\n", arg);
return SPECTRE_V2_CMD_AUTO;
}
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 364fbad72e60..6edb9530d7e9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -60,6 +60,9 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex);
smp_load_acquire(&(p)); \
})
+/* sysfs synchronization */
+static DEFINE_MUTEX(mce_sysfs_mutex);
+
#define CREATE_TRACE_POINTS
#include <trace/events/mce.h>
@@ -2220,6 +2223,7 @@ static ssize_t set_ignore_ce(struct device *s,
if (kstrtou64(buf, 0, &new) < 0)
return -EINVAL;
+ mutex_lock(&mce_sysfs_mutex);
if (mca_cfg.ignore_ce ^ !!new) {
if (new) {
/* disable ce features */
@@ -2232,6 +2236,8 @@ static ssize_t set_ignore_ce(struct device *s,
on_each_cpu(mce_enable_ce, (void *)1, 1);
}
}
+ mutex_unlock(&mce_sysfs_mutex);
+
return size;
}
@@ -2244,6 +2250,7 @@ static ssize_t set_cmci_disabled(struct device *s,
if (kstrtou64(buf, 0, &new) < 0)
return -EINVAL;
+ mutex_lock(&mce_sysfs_mutex);
if (mca_cfg.cmci_disabled ^ !!new) {
if (new) {
/* disable cmci */
@@ -2255,6 +2262,8 @@ static ssize_t set_cmci_disabled(struct device *s,
on_each_cpu(mce_enable_ce, NULL, 1);
}
}
+ mutex_unlock(&mce_sysfs_mutex);
+
return size;
}
@@ -2262,8 +2271,19 @@ static ssize_t store_int_with_restart(struct device *s,
struct device_attribute *attr,
const char *buf, size_t size)
{
- ssize_t ret = device_store_int(s, attr, buf, size);
+ unsigned long old_check_interval = check_interval;
+ ssize_t ret = device_store_ulong(s, attr, buf, size);
+
+ if (check_interval == old_check_interval)
+ return ret;
+
+ if (check_interval < 1)
+ check_interval = 1;
+
+ mutex_lock(&mce_sysfs_mutex);
mce_restart();
+ mutex_unlock(&mce_sysfs_mutex);
+
return ret;
}
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 5cc2242d77c6..7b79c80ce029 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2716,7 +2716,7 @@ static unsigned bdw_limit_period(struct perf_event *event, unsigned left)
X86_CONFIG(.event=0xc0, .umask=0x01)) {
if (left < 128)
left = 128;
- left &= ~0x3fu;
+ left &= ~0x3fULL;
}
return left;
}
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index be22f5a2192e..4e3b8a587c88 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -418,6 +418,7 @@ struct legacy_pic default_legacy_pic = {
};
struct legacy_pic *legacy_pic = &default_legacy_pic;
+EXPORT_SYMBOL(legacy_pic);
static int __init i8259A_init_ops(void)
{
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 3eb804335458..30bc63876035 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -50,6 +50,8 @@
#include <linux/kallsyms.h>
#include <linux/ftrace.h>
#include <linux/kasan.h>
+#include <linux/moduleloader.h>
+
#include <asm/cacheflush.h>
#include <asm/desc.h>
#include <asm/pgtable.h>
@@ -196,6 +198,8 @@ retry:
return (opcode != 0x62 && opcode != 0x67);
case 0x70:
return 0; /* can't boost conditional jump */
+ case 0x90:
+ return opcode != 0x9a; /* can't boost call far */
case 0xc0:
/* can't boost software-interruptions */
return (0xc1 < opcode && opcode < 0xcc) || opcode == 0xcf;
@@ -400,10 +404,20 @@ int __copy_instruction(u8 *dest, u8 *src)
return length;
}
+/* Recover page to RW mode before releasing it */
+void free_insn_page(void *page)
+{
+ set_memory_nx((unsigned long)page & PAGE_MASK, 1);
+ set_memory_rw((unsigned long)page & PAGE_MASK, 1);
+ module_memfree(page);
+}
+
static int arch_copy_kprobe(struct kprobe *p)
{
int ret;
+ set_memory_rw((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
+
/* Copy an instruction with recovering if other optprobe modifies it.*/
ret = __copy_instruction(p->ainsn.insn, p->addr);
if (!ret)
@@ -418,6 +432,8 @@ static int arch_copy_kprobe(struct kprobe *p)
else
p->ainsn.boostable = -1;
+ set_memory_ro((unsigned long)p->ainsn.insn & PAGE_MASK, 1);
+
/* Check whether the instruction modifies Interrupt Flag or not */
p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn);
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index ea8e2b846101..7aba9d6475a5 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -370,6 +370,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
}
buf = (u8 *)op->optinsn.insn;
+ set_memory_rw((unsigned long)buf & PAGE_MASK, 1);
/* Copy instructions into the out-of-line buffer */
ret = copy_optimized_instructions(buf + TMPL_END_IDX, op->kp.addr);
@@ -392,6 +393,8 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op,
synthesize_reljump(buf + TMPL_END_IDX + op->optinsn.size,
(u8 *)op->kp.addr + op->optinsn.size);
+ set_memory_ro((unsigned long)buf & PAGE_MASK, 1);
+
flush_icache_range((unsigned long) buf,
(unsigned long) buf + TMPL_END_IDX +
op->optinsn.size + RELATIVEJUMP_SIZE);
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 819ab3f9c9c7..ca6e65250b1a 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -519,6 +519,7 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
goto overflow;
break;
case R_X86_64_PC32:
+ case R_X86_64_PLT32:
value -= (u64)address;
*(u32 *)location = value;
break;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 005c03e93fc5..94779f66bf49 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -170,19 +170,28 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
case R_X86_64_NONE:
break;
case R_X86_64_64:
+ if (*(u64 *)loc != 0)
+ goto invalid_relocation;
*(u64 *)loc = val;
break;
case R_X86_64_32:
+ if (*(u32 *)loc != 0)
+ goto invalid_relocation;
*(u32 *)loc = val;
if (val != *(u32 *)loc)
goto overflow;
break;
case R_X86_64_32S:
+ if (*(s32 *)loc != 0)
+ goto invalid_relocation;
*(s32 *)loc = val;
if ((s64)val != *(s32 *)loc)
goto overflow;
break;
case R_X86_64_PC32:
+ case R_X86_64_PLT32:
+ if (*(u32 *)loc != 0)
+ goto invalid_relocation;
val -= (u64)loc;
*(u32 *)loc = val;
#if 0
@@ -198,6 +207,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
}
return 0;
+invalid_relocation:
+ pr_err("x86/modules: Skipping invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
+ (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
+ return -ENOEXEC;
+
overflow:
pr_err("overflow in relocation type %d val %Lx\n",
(int)ELF64_R_TYPE(rel[i].r_info), val);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 22b81f35c500..1fbd2631be60 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -480,7 +480,6 @@ do_general_protection(struct pt_regs *regs, long error_code)
}
NOKPROBE_SYMBOL(do_general_protection);
-/* May run on IST stack. */
dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
{
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -495,7 +494,15 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
if (poke_int3_handler(regs))
return;
+ /*
+ * Use ist_enter despite the fact that we don't use an IST stack.
+ * We can be called from a kprobe in non-CONTEXT_KERNEL kernel
+ * mode or even during context tracking state changes.
+ *
+ * This means that we can't schedule. That's okay.
+ */
ist_enter(regs);
+
RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
@@ -512,15 +519,9 @@ dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code)
SIGTRAP) == NOTIFY_STOP)
goto exit;
- /*
- * Let others (NMI) know that the debug stack is in use
- * as we may switch to the interrupt stack.
- */
- debug_stack_usage_inc();
preempt_conditional_sti(regs);
do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
preempt_conditional_cli(regs);
- debug_stack_usage_dec();
exit:
ist_exit(regs);
}
@@ -886,19 +887,16 @@ void __init trap_init(void)
cpu_init();
/*
- * X86_TRAP_DB and X86_TRAP_BP have been set
- * in early_trap_init(). However, ITS works only after
- * cpu_init() loads TSS. See comments in early_trap_init().
+ * X86_TRAP_DB was installed in early_trap_init(). However,
+ * IST works only after cpu_init() loads TSS. See comments
+ * in early_trap_init().
*/
set_intr_gate_ist(X86_TRAP_DB, &debug, DEBUG_STACK);
- /* int3 can be called from all */
- set_system_intr_gate_ist(X86_TRAP_BP, &int3, DEBUG_STACK);
x86_init.irqs.trap_init();
#ifdef CONFIG_X86_64
memcpy(&debug_idt_table, &idt_table, IDT_ENTRIES * 16);
set_nmi_gate(X86_TRAP_DB, &debug);
- set_nmi_gate(X86_TRAP_BP, &int3);
#endif
}
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 510e80da7de4..af57736a0309 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -715,7 +715,8 @@ void handle_vm86_fault(struct kernel_vm86_regs *regs, long error_code)
return;
check_vip:
- if (VEFLAGS & X86_EFLAGS_VIP) {
+ if ((VEFLAGS & (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) ==
+ (X86_EFLAGS_VIP | X86_EFLAGS_VIF)) {
save_v86_state(regs, VM86_STI);
return;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 849517805eef..46bbc69844bd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1011,6 +1011,13 @@ static inline bool is_machine_check(u32 intr_info)
(INTR_TYPE_HARD_EXCEPTION | MC_VECTOR | INTR_INFO_VALID_MASK);
}
+/* Undocumented: icebp/int1 */
+static inline bool is_icebp(u32 intr_info)
+{
+ return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
+ == (INTR_TYPE_PRIV_SW_EXCEPTION | INTR_INFO_VALID_MASK);
+}
+
static inline bool cpu_has_vmx_msr_bitmap(void)
{
return vmcs_config.cpu_based_exec_ctrl & CPU_BASED_USE_MSR_BITMAPS;
@@ -5333,7 +5340,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
vcpu->arch.dr6 &= ~15;
vcpu->arch.dr6 |= dr6 | DR6_RTM;
- if (!(dr6 & ~DR6_RESERVED)) /* icebp */
+ if (is_icebp(intr_info))
skip_emulated_instruction(vcpu);
kvm_queue_exception(vcpu, DB_VECTOR);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e830c71a1323..e0a34b0d381e 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -287,7 +287,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (!pmd_k)
return -1;
- if (pmd_huge(*pmd_k))
+ if (pmd_large(*pmd_k))
return 0;
pte_k = pte_offset_kernel(pmd_k, address);
@@ -407,7 +407,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref))
BUG();
- if (pud_huge(*pud))
+ if (pud_large(*pud))
return 0;
pmd = pmd_offset(pud, address);
@@ -418,7 +418,7 @@ static noinline int vmalloc_fault(unsigned long address)
if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref))
BUG();
- if (pmd_huge(*pmd))
+ if (pmd_large(*pmd))
return 0;
pte_ref = pte_offset_kernel(pmd_ref, address);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dbc27a2b4ad5..c013326a0d7a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -666,4 +666,52 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
+
+/**
+ * pud_free_pmd_page - Clear pud entry and free pmd page.
+ * @pud: Pointer to a PUD.
+ *
+ * Context: The pud range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pud_free_pmd_page(pud_t *pud)
+{
+ pmd_t *pmd;
+ int i;
+
+ if (pud_none(*pud))
+ return 1;
+
+ pmd = (pmd_t *)pud_page_vaddr(*pud);
+
+ for (i = 0; i < PTRS_PER_PMD; i++)
+ if (!pmd_free_pte_page(&pmd[i]))
+ return 0;
+
+ pud_clear(pud);
+ free_page((unsigned long)pmd);
+
+ return 1;
+}
+
+/**
+ * pmd_free_pte_page - Clear pmd entry and free pte page.
+ * @pmd: Pointer to a PMD.
+ *
+ * Context: The pmd range has been unmaped and TLB purged.
+ * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ */
+int pmd_free_pte_page(pmd_t *pmd)
+{
+ pte_t *pte;
+
+ if (pmd_none(*pmd))
+ return 1;
+
+ pte = (pte_t *)pmd_page_vaddr(*pmd);
+ pmd_clear(pmd);
+ free_page((unsigned long)pte);
+
+ return 1;
+}
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 33c42b826791..dd9a861fd526 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -12,6 +12,7 @@
#include <linux/filter.h>
#include <linux/if_vlan.h>
#include <asm/cacheflush.h>
+#include <asm/nospec-branch.h>
#include <linux/bpf.h>
int bpf_jit_enable __read_mostly;
@@ -269,7 +270,7 @@ static void emit_bpf_tail_call(u8 **pprog)
EMIT2(0x89, 0xD2); /* mov edx, edx */
EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */
offsetof(struct bpf_array, map.max_entries));
-#define OFFSET1 43 /* number of bytes to jump */
+#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */
EMIT2(X86_JBE, OFFSET1); /* jbe out */
label1 = cnt;
@@ -278,7 +279,7 @@ static void emit_bpf_tail_call(u8 **pprog)
*/
EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 32
+#define OFFSET2 (30 + RETPOLINE_RAX_BPF_JIT_SIZE)
EMIT2(X86_JA, OFFSET2); /* ja out */
label2 = cnt;
EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
@@ -292,7 +293,7 @@ static void emit_bpf_tail_call(u8 **pprog)
* goto out;
*/
EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */
-#define OFFSET3 10
+#define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE)
EMIT2(X86_JE, OFFSET3); /* je out */
label3 = cnt;
@@ -305,7 +306,7 @@ static void emit_bpf_tail_call(u8 **pprog)
* rdi == ctx (1st arg)
* rax == prog->bpf_func + prologue_size
*/
- EMIT2(0xFF, 0xE0); /* jmp rax */
+ RETPOLINE_RAX_BPF_JIT();
/* out: */
BUILD_BUG_ON(cnt - label1 != OFFSET1);
@@ -1076,7 +1077,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
* may converge on the last pass. In such case do one more
* pass to emit the final image
*/
- for (pass = 0; pass < 10 || image; pass++) {
+ for (pass = 0; pass < 20 || image; pass++) {
proglen = do_jit(prog, addrs, image, oldproglen, &ctx);
if (proglen <= 0) {
image = NULL;
@@ -1099,6 +1100,7 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
goto out;
}
oldproglen = proglen;
+ cond_resched();
}
if (bpf_jit_enable > 1)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 73eb7fd4aec4..5b6c8486a0be 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -769,9 +769,12 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
break;
case R_X86_64_PC32:
+ case R_X86_64_PLT32:
/*
* PC relative relocations don't need to be adjusted unless
* referencing a percpu symbol.
+ *
+ * NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
*/
if (is_percpu_sym(sym, symname))
add_reloc(&relocs32neg, offset);