summaryrefslogtreecommitdiff
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig13
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts15
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts15
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts16
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts15
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi20
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts17
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts17
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts17
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi3
-rw-r--r--arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi12
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi31
-rw-r--r--arch/arm64/boot/dts/marvell/armada-ap806.dtsi4
-rw-r--r--arch/arm64/boot/dts/renesas/salvator-common.dtsi2
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328-evb.dts17
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3328.dtsi39
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/crypto/Kconfig22
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-core.S30
-rw-r--r--arch/arm64/crypto/aes-ce-ccm-glue.c174
-rw-r--r--arch/arm64/crypto/aes-ce-cipher.c55
-rw-r--r--arch/arm64/crypto/aes-ce.S12
-rw-r--r--arch/arm64/crypto/aes-cipher-core.S152
-rw-r--r--arch/arm64/crypto/aes-ctr-fallback.h53
-rw-r--r--arch/arm64/crypto/aes-glue.c63
-rw-r--r--arch/arm64/crypto/aes-neonbs-glue.c53
-rw-r--r--arch/arm64/crypto/chacha20-neon-glue.c5
-rw-r--r--arch/arm64/crypto/crc32-ce-glue.c11
-rw-r--r--arch/arm64/crypto/crct10dif-ce-glue.c13
-rw-r--r--arch/arm64/crypto/ghash-ce-core.S401
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c517
-rw-r--r--arch/arm64/crypto/sha1-ce-glue.c18
-rw-r--r--arch/arm64/crypto/sha2-ce-glue.c30
-rw-r--r--arch/arm64/crypto/sha256-glue.c1
-rw-r--r--arch/arm64/include/asm/Kbuild1
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h7
-rw-r--r--arch/arm64/include/asm/arch_timer.h4
-rw-r--r--arch/arm64/include/asm/asm-bug.h54
-rw-r--r--arch/arm64/include/asm/assembler.h25
-rw-r--r--arch/arm64/include/asm/bug.h35
-rw-r--r--arch/arm64/include/asm/cacheflush.h4
-rw-r--r--arch/arm64/include/asm/cpucaps.h3
-rw-r--r--arch/arm64/include/asm/efi.h16
-rw-r--r--arch/arm64/include/asm/elf.h6
-rw-r--r--arch/arm64/include/asm/esr.h42
-rw-r--r--arch/arm64/include/asm/fpsimd.h16
-rw-r--r--arch/arm64/include/asm/fpsimdmacros.h56
-rw-r--r--arch/arm64/include/asm/futex.h26
-rw-r--r--arch/arm64/include/asm/hugetlb.h9
-rw-r--r--arch/arm64/include/asm/irq.h42
-rw-r--r--arch/arm64/include/asm/kvm_host.h6
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h21
-rw-r--r--arch/arm64/include/asm/memory.h53
-rw-r--r--arch/arm64/include/asm/mmu.h2
-rw-r--r--arch/arm64/include/asm/neon.h16
-rw-r--r--arch/arm64/include/asm/numa.h3
-rw-r--r--arch/arm64/include/asm/page-def.h34
-rw-r--r--arch/arm64/include/asm/page.h12
-rw-r--r--arch/arm64/include/asm/pgtable-prot.h18
-rw-r--r--arch/arm64/include/asm/pgtable.h103
-rw-r--r--arch/arm64/include/asm/processor.h4
-rw-r--r--arch/arm64/include/asm/ptrace.h31
-rw-r--r--arch/arm64/include/asm/signal32.h2
-rw-r--r--arch/arm64/include/asm/simd.h56
-rw-r--r--arch/arm64/include/asm/smp.h2
-rw-r--r--arch/arm64/include/asm/spinlock.h69
-rw-r--r--arch/arm64/include/asm/stacktrace.h61
-rw-r--r--arch/arm64/include/asm/string.h4
-rw-r--r--arch/arm64/include/asm/sysreg.h1
-rw-r--r--arch/arm64/include/asm/thread_info.h17
-rw-r--r--arch/arm64/include/asm/traps.h12
-rw-r--r--arch/arm64/include/asm/uaccess.h15
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h1
-rw-r--r--arch/arm64/kernel/acpi.c4
-rw-r--r--arch/arm64/kernel/asm-offsets.c1
-rw-r--r--arch/arm64/kernel/cpufeature.c13
-rw-r--r--arch/arm64/kernel/cpuinfo.c1
-rw-r--r--arch/arm64/kernel/entry-fpsimd.S24
-rw-r--r--arch/arm64/kernel/entry.S283
-rw-r--r--arch/arm64/kernel/fpsimd.c170
-rw-r--r--arch/arm64/kernel/head.S23
-rw-r--r--arch/arm64/kernel/hibernate.c4
-rw-r--r--arch/arm64/kernel/irq.c40
-rw-r--r--arch/arm64/kernel/kaslr.c20
-rw-r--r--arch/arm64/kernel/machine_kexec.c2
-rw-r--r--arch/arm64/kernel/perf_callchain.c1
-rw-r--r--arch/arm64/kernel/perf_event.c208
-rw-r--r--arch/arm64/kernel/probes/uprobes.c2
-rw-r--r--arch/arm64/kernel/process.c15
-rw-r--r--arch/arm64/kernel/ptrace.c5
-rw-r--r--arch/arm64/kernel/return_address.c1
-rw-r--r--arch/arm64/kernel/signal.c15
-rw-r--r--arch/arm64/kernel/signal32.c2
-rw-r--r--arch/arm64/kernel/smp.c14
-rw-r--r--arch/arm64/kernel/stacktrace.c60
-rw-r--r--arch/arm64/kernel/time.c1
-rw-r--r--arch/arm64/kernel/traps.c79
-rw-r--r--arch/arm64/kernel/vdso.c15
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S18
-rw-r--r--arch/arm64/kvm/hyp/s2-setup.c2
-rw-r--r--arch/arm64/lib/Makefile2
-rw-r--r--arch/arm64/lib/uaccess_flushcache.c47
-rw-r--r--arch/arm64/mm/cache.S37
-rw-r--r--arch/arm64/mm/dma-mapping.c4
-rw-r--r--arch/arm64/mm/fault.c82
-rw-r--r--arch/arm64/mm/flush.c16
-rw-r--r--arch/arm64/mm/hugetlbpage.c314
-rw-r--r--arch/arm64/net/bpf_jit.h4
-rw-r--r--arch/arm64/net/bpf_jit_comp.c20
110 files changed, 3009 insertions, 1299 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dfd908630631..0df64a6a56d4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -75,6 +75,7 @@ config ARM64
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
+ select HAVE_ARCH_VMAP_STACK
select HAVE_ARM_SMCCC
select HAVE_EBPF_JIT
select HAVE_C_RECORDMCOUNT
@@ -960,6 +961,18 @@ config ARM64_UAO
regular load/store instructions if the cpu does not implement the
feature.
+config ARM64_PMEM
+ bool "Enable support for persistent memory"
+ select ARCH_HAS_PMEM_API
+ select ARCH_HAS_UACCESS_FLUSHCACHE
+ help
+ Say Y to enable support for the persistent memory API based on the
+ ARMv8.2 DCPoP feature.
+
+ The feature is detected at runtime, and the kernel will use DC CVAC
+ operations if DC CVAP is not supported (following the behaviour of
+ DC CVAP itself if the system does not define a point of persistence).
+
endmenu
config ARM64_MODULE_CMODEL_LARGE
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
index 0d1f026d831a..6872135d7f84 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts
@@ -67,14 +67,6 @@
};
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
- phy-handle = <&ext_rgmii_phy>;
- status = "okay";
-};
-
&i2c1 {
pinctrl-names = "default";
pinctrl-0 = <&i2c1_pins>;
@@ -85,13 +77,6 @@
bias-pull-up;
};
-&mdio {
- ext_rgmii_phy: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
index 24f1aac366d6..f82ccf332c0f 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
@@ -48,18 +48,3 @@
/* TODO: Camera, touchscreen, etc. */
};
-
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
- phy-handle = <&ext_rgmii_phy>;
- status = "okay";
-};
-
-&mdio {
- ext_rgmii_phy: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
index 08cda24ea194..7c533b6d4ba9 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts
@@ -78,15 +78,6 @@
status = "okay";
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&rmii_pins>;
- phy-mode = "rmii";
- phy-handle = <&ext_rmii_phy1>;
- status = "okay";
-
-};
-
&i2c1 {
pinctrl-names = "default";
pinctrl-0 = <&i2c1_pins>;
@@ -97,13 +88,6 @@
bias-pull-up;
};
-&mdio {
- ext_rmii_phy1: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
index 17eb1cc5bf6b..d891a1a27f6c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
@@ -76,21 +76,6 @@
status = "okay";
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&rgmii_pins>;
- phy-mode = "rgmii";
- phy-handle = <&ext_rgmii_phy>;
- status = "okay";
-};
-
-&mdio {
- ext_rgmii_phy: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
-
&mmc2 {
pinctrl-names = "default";
pinctrl-0 = <&mmc2_pins>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index bd0f33b77f57..68aadc9b96dc 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -449,26 +449,6 @@
#size-cells = <0>;
};
- emac: ethernet@1c30000 {
- compatible = "allwinner,sun50i-a64-emac";
- syscon = <&syscon>;
- reg = <0x01c30000 0x10000>;
- interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "macirq";
- resets = <&ccu RST_BUS_EMAC>;
- reset-names = "stmmaceth";
- clocks = <&ccu CLK_BUS_EMAC>;
- clock-names = "stmmaceth";
- status = "disabled";
- #address-cells = <1>;
- #size-cells = <0>;
-
- mdio: mdio {
- #address-cells = <1>;
- #size-cells = <0>;
- };
- };
-
gic: interrupt-controller@1c81000 {
compatible = "arm,gic-400";
reg = <0x01c81000 0x1000>,
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
index 968908761194..1c2387bd5df6 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
@@ -50,7 +50,6 @@
compatible = "friendlyarm,nanopi-neo2", "allwinner,sun50i-h5";
aliases {
- ethernet0 = &emac;
serial0 = &uart0;
};
@@ -109,22 +108,6 @@
status = "okay";
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&emac_rgmii_pins>;
- phy-supply = <&reg_gmac_3v3>;
- phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
- status = "okay";
-};
-
-&mdio {
- ext_rgmii_phy: ethernet-phy@7 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <7>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
index a8296feee884..4f77c8470f6c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts
@@ -59,7 +59,6 @@
};
aliases {
- ethernet0 = &emac;
serial0 = &uart0;
};
@@ -137,28 +136,12 @@
status = "okay";
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&emac_rgmii_pins>;
- phy-supply = <&reg_gmac_3v3>;
- phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
- status = "okay";
-};
-
&ir {
pinctrl-names = "default";
pinctrl-0 = <&ir_pins_a>;
status = "okay";
};
-&mdio {
- ext_rgmii_phy: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
index d906b302cbcd..6be06873e5af 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts
@@ -54,7 +54,6 @@
compatible = "xunlong,orangepi-prime", "allwinner,sun50i-h5";
aliases {
- ethernet0 = &emac;
serial0 = &uart0;
};
@@ -144,28 +143,12 @@
status = "okay";
};
-&emac {
- pinctrl-names = "default";
- pinctrl-0 = <&emac_rgmii_pins>;
- phy-supply = <&reg_gmac_3v3>;
- phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
- status = "okay";
-};
-
&ir {
pinctrl-names = "default";
pinctrl-0 = <&ir_pins_a>;
status = "okay";
};
-&mdio {
- ext_rgmii_phy: ethernet-phy@1 {
- compatible = "ethernet-phy-ieee802.3-c22";
- reg = <1>;
- };
-};
-
&mmc0 {
pinctrl-names = "default";
pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>;
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
index 732e2e06f503..d9a720bff05d 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi
@@ -120,5 +120,8 @@
};
&pio {
+ interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
compatible = "allwinner,sun50i-h5-pinctrl";
};
diff --git a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
index e2b0da2c0bc7..105b2938082f 100644
--- a/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
+++ b/arch/arm64/boot/dts/exynos/exynos5433-tm2-common.dtsi
@@ -280,9 +280,6 @@
&decon {
status = "okay";
-
- i80-if-timings {
- };
};
&decon_tv {
@@ -1116,9 +1113,6 @@
&mic {
status = "okay";
-
- i80-if-timings {
- };
};
&pmu_system_controller {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index 31fd77f82ced..d16b9cc1e825 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -653,21 +653,21 @@
};
msi1: msi-controller1@1571000 {
- compatible = "fsl,1s1043a-msi";
+ compatible = "fsl,ls1043a-msi";
reg = <0x0 0x1571000 0x0 0x8>;
msi-controller;
interrupts = <0 116 0x4>;
};
msi2: msi-controller2@1572000 {
- compatible = "fsl,1s1043a-msi";
+ compatible = "fsl,ls1043a-msi";
reg = <0x0 0x1572000 0x0 0x8>;
msi-controller;
interrupts = <0 126 0x4>;
};
msi3: msi-controller3@1573000 {
- compatible = "fsl,1s1043a-msi";
+ compatible = "fsl,ls1043a-msi";
reg = <0x0 0x1573000 0x0 0x8>;
msi-controller;
interrupts = <0 160 0x4>;
@@ -689,7 +689,7 @@
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x00000000 0x40 0x00010000 0x0 0x00010000 /* downstream I/O */
0x82000000 0x0 0x40000000 0x40 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */
- msi-parent = <&msi1>;
+ msi-parent = <&msi1>, <&msi2>, <&msi3>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0000 0 0 1 &gic 0 110 0x4>,
@@ -714,7 +714,7 @@
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x00000000 0x48 0x00010000 0x0 0x00010000 /* downstream I/O */
0x82000000 0x0 0x40000000 0x48 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */
- msi-parent = <&msi2>;
+ msi-parent = <&msi1>, <&msi2>, <&msi3>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0000 0 0 1 &gic 0 120 0x4>,
@@ -739,7 +739,7 @@
bus-range = <0x0 0xff>;
ranges = <0x81000000 0x0 0x00000000 0x50 0x00010000 0x0 0x00010000 /* downstream I/O */
0x82000000 0x0 0x40000000 0x50 0x40000000 0x0 0x40000000>; /* non-prefetchable memory */
- msi-parent = <&msi3>;
+ msi-parent = <&msi1>, <&msi2>, <&msi3>;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 7>;
interrupt-map = <0000 0 0 1 &gic 0 154 0x4>,
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index dc1640be0345..c8ff0baddf1d 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -630,6 +630,37 @@
interrupts = <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clockgen 4 1>;
};
+
+ msi1: msi-controller@1580000 {
+ compatible = "fsl,ls1046a-msi";
+ msi-controller;
+ reg = <0x0 0x1580000 0x0 0x10000>;
+ interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 111 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 112 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ msi2: msi-controller@1590000 {
+ compatible = "fsl,ls1046a-msi";
+ msi-controller;
+ reg = <0x0 0x1590000 0x0 0x10000>;
+ interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ msi3: msi-controller@15a0000 {
+ compatible = "fsl,ls1046a-msi";
+ msi-controller;
+ reg = <0x0 0x15a0000 0x0 0x10000>;
+ interrupts = <GIC_SPI 160 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 156 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 157 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
};
reserved-memory {
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index 1eb1f1e9aac4..4d360713ed12 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -268,10 +268,10 @@
ap_gpio: gpio {
compatible = "marvell,armada-8k-gpio";
offset = <0x1040>;
- ngpios = <19>;
+ ngpios = <20>;
gpio-controller;
#gpio-cells = <2>;
- gpio-ranges = <&ap_pinctrl 0 0 19>;
+ gpio-ranges = <&ap_pinctrl 0 0 20>;
};
};
};
diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
index a451996f590a..f903957da504 100644
--- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi
+++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi
@@ -45,7 +45,7 @@
stdout-path = "serial0:115200n8";
};
- audio_clkout: audio_clkout {
+ audio_clkout: audio-clkout {
/*
* This is same as <&rcar_sound 0>
* but needed to avoid cs2000/rcar_sound probe dead-lock
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
index cf272392cebf..b9f36dad17e6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts
@@ -50,6 +50,23 @@
chosen {
stdout-path = "serial2:1500000n8";
};
+
+ vcc_phy: vcc-phy-regulator {
+ compatible = "regulator-fixed";
+ regulator-name = "vcc_phy";
+ regulator-always-on;
+ regulator-boot-on;
+ };
+};
+
+&gmac2phy {
+ phy-supply = <&vcc_phy>;
+ clock_in_out = "output";
+ assigned-clocks = <&cru SCLK_MAC2PHY_SRC>;
+ assigned-clock-rate = <50000000>;
+ assigned-clocks = <&cru SCLK_MAC2PHY>;
+ assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>;
+ status = "okay";
};
&uart2 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 0be96cee27bd..d48bf5d9f8bd 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -63,6 +63,8 @@
i2c1 = &i2c1;
i2c2 = &i2c2;
i2c3 = &i2c3;
+ ethernet0 = &gmac2io;
+ ethernet1 = &gmac2phy;
};
cpus {
@@ -424,6 +426,43 @@
status = "disabled";
};
+ gmac2phy: ethernet@ff550000 {
+ compatible = "rockchip,rk3328-gmac";
+ reg = <0x0 0xff550000 0x0 0x10000>;
+ rockchip,grf = <&grf>;
+ interrupts = <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq";
+ clocks = <&cru SCLK_MAC2PHY_SRC>, <&cru SCLK_MAC2PHY_RXTX>,
+ <&cru SCLK_MAC2PHY_RXTX>, <&cru SCLK_MAC2PHY_REF>,
+ <&cru ACLK_MAC2PHY>, <&cru PCLK_MAC2PHY>,
+ <&cru SCLK_MAC2PHY_OUT>;
+ clock-names = "stmmaceth", "mac_clk_rx",
+ "mac_clk_tx", "clk_mac_ref",
+ "aclk_mac", "pclk_mac",
+ "clk_macphy";
+ resets = <&cru SRST_GMAC2PHY_A>, <&cru SRST_MACPHY>;
+ reset-names = "stmmaceth", "mac-phy";
+ phy-mode = "rmii";
+ phy-handle = <&phy>;
+ status = "disabled";
+
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ phy: phy@0 {
+ compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22";
+ reg = <0>;
+ clocks = <&cru SCLK_MAC2PHY_OUT>;
+ resets = <&cru SRST_MACPHY>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&fephyled_rxm1 &fephyled_linkm1>;
+ phy-is-integrated;
+ };
+ };
+ };
+
gic: interrupt-controller@ff811000 {
compatible = "arm,gic-400";
#interrupt-cells = <3>;
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index b4ca115b3be1..cdde4f56a281 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -203,6 +203,7 @@ CONFIG_MARVELL_PHY=m
CONFIG_MESON_GXL_PHY=m
CONFIG_MICREL_PHY=y
CONFIG_REALTEK_PHY=m
+CONFIG_ROCKCHIP_PHY=y
CONFIG_USB_PEGASUS=m
CONFIG_USB_RTL8150=m
CONFIG_USB_RTL8152=m
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index d92293747d63..7ca54a76f6b9 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -18,18 +18,23 @@ config CRYPTO_SHA512_ARM64
config CRYPTO_SHA1_ARM64_CE
tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_HASH
+ select CRYPTO_SHA1
config CRYPTO_SHA2_ARM64_CE
tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_HASH
+ select CRYPTO_SHA256_ARM64
config CRYPTO_GHASH_ARM64_CE
- tristate "GHASH (for GCM chaining mode) using ARMv8 Crypto Extensions"
- depends on ARM64 && KERNEL_MODE_NEON
+ tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions"
+ depends on KERNEL_MODE_NEON
select CRYPTO_HASH
+ select CRYPTO_GF128MUL
+ select CRYPTO_AES
+ select CRYPTO_AES_ARM64
config CRYPTO_CRCT10DIF_ARM64_CE
tristate "CRCT10DIF digest algorithm using PMULL instructions"
@@ -49,25 +54,29 @@ config CRYPTO_AES_ARM64_CE
tristate "AES core cipher using ARMv8 Crypto Extensions"
depends on ARM64 && KERNEL_MODE_NEON
select CRYPTO_ALGAPI
+ select CRYPTO_AES_ARM64
config CRYPTO_AES_ARM64_CE_CCM
tristate "AES in CCM mode using ARMv8 Crypto Extensions"
depends on ARM64 && KERNEL_MODE_NEON
select CRYPTO_ALGAPI
select CRYPTO_AES_ARM64_CE
+ select CRYPTO_AES_ARM64
select CRYPTO_AEAD
config CRYPTO_AES_ARM64_CE_BLK
tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_BLKCIPHER
select CRYPTO_AES_ARM64_CE
+ select CRYPTO_AES_ARM64
select CRYPTO_SIMD
config CRYPTO_AES_ARM64_NEON_BLK
tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions"
- depends on ARM64 && KERNEL_MODE_NEON
+ depends on KERNEL_MODE_NEON
select CRYPTO_BLKCIPHER
+ select CRYPTO_AES_ARM64
select CRYPTO_AES
select CRYPTO_SIMD
@@ -82,6 +91,7 @@ config CRYPTO_AES_ARM64_BS
depends on KERNEL_MODE_NEON
select CRYPTO_BLKCIPHER
select CRYPTO_AES_ARM64_NEON_BLK
+ select CRYPTO_AES_ARM64
select CRYPTO_SIMD
endif
diff --git a/arch/arm64/crypto/aes-ce-ccm-core.S b/arch/arm64/crypto/aes-ce-ccm-core.S
index 3363560c79b7..e3a375c4cb83 100644
--- a/arch/arm64/crypto/aes-ce-ccm-core.S
+++ b/arch/arm64/crypto/aes-ce-ccm-core.S
@@ -1,7 +1,7 @@
/*
* aesce-ccm-core.S - AES-CCM transform for ARMv8 with Crypto Extensions
*
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -32,7 +32,7 @@ ENTRY(ce_aes_ccm_auth_data)
beq 8f /* out of input? */
cbnz w8, 0b
eor v0.16b, v0.16b, v1.16b
-1: ld1 {v3.16b}, [x4] /* load first round key */
+1: ld1 {v3.4s}, [x4] /* load first round key */
prfm pldl1strm, [x1]
cmp w5, #12 /* which key size? */
add x6, x4, #16
@@ -42,17 +42,17 @@ ENTRY(ce_aes_ccm_auth_data)
mov v5.16b, v3.16b
b 4f
2: mov v4.16b, v3.16b
- ld1 {v5.16b}, [x6], #16 /* load 2nd round key */
+ ld1 {v5.4s}, [x6], #16 /* load 2nd round key */
3: aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
-4: ld1 {v3.16b}, [x6], #16 /* load next round key */
+4: ld1 {v3.4s}, [x6], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
-5: ld1 {v4.16b}, [x6], #16 /* load next round key */
+5: ld1 {v4.4s}, [x6], #16 /* load next round key */
subs w7, w7, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
- ld1 {v5.16b}, [x6], #16 /* load next round key */
+ ld1 {v5.4s}, [x6], #16 /* load next round key */
bpl 3b
aese v0.16b, v4.16b
subs w2, w2, #16 /* last data? */
@@ -90,7 +90,7 @@ ENDPROC(ce_aes_ccm_auth_data)
* u32 rounds);
*/
ENTRY(ce_aes_ccm_final)
- ld1 {v3.16b}, [x2], #16 /* load first round key */
+ ld1 {v3.4s}, [x2], #16 /* load first round key */
ld1 {v0.16b}, [x0] /* load mac */
cmp w3, #12 /* which key size? */
sub w3, w3, #2 /* modified # of rounds */
@@ -100,17 +100,17 @@ ENTRY(ce_aes_ccm_final)
mov v5.16b, v3.16b
b 2f
0: mov v4.16b, v3.16b
-1: ld1 {v5.16b}, [x2], #16 /* load next round key */
+1: ld1 {v5.4s}, [x2], #16 /* load next round key */
aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
aese v1.16b, v4.16b
aesmc v1.16b, v1.16b
-2: ld1 {v3.16b}, [x2], #16 /* load next round key */
+2: ld1 {v3.4s}, [x2], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
aese v1.16b, v5.16b
aesmc v1.16b, v1.16b
-3: ld1 {v4.16b}, [x2], #16 /* load next round key */
+3: ld1 {v4.4s}, [x2], #16 /* load next round key */
subs w3, w3, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
@@ -137,31 +137,31 @@ CPU_LE( rev x8, x8 ) /* keep swabbed ctr in reg */
cmp w4, #12 /* which key size? */
sub w7, w4, #2 /* get modified # of rounds */
ins v1.d[1], x9 /* no carry in lower ctr */
- ld1 {v3.16b}, [x3] /* load first round key */
+ ld1 {v3.4s}, [x3] /* load first round key */
add x10, x3, #16
bmi 1f
bne 4f
mov v5.16b, v3.16b
b 3f
1: mov v4.16b, v3.16b
- ld1 {v5.16b}, [x10], #16 /* load 2nd round key */
+ ld1 {v5.4s}, [x10], #16 /* load 2nd round key */
2: /* inner loop: 3 rounds, 2x interleaved */
aese v0.16b, v4.16b
aesmc v0.16b, v0.16b
aese v1.16b, v4.16b
aesmc v1.16b, v1.16b
-3: ld1 {v3.16b}, [x10], #16 /* load next round key */
+3: ld1 {v3.4s}, [x10], #16 /* load next round key */
aese v0.16b, v5.16b
aesmc v0.16b, v0.16b
aese v1.16b, v5.16b
aesmc v1.16b, v1.16b
-4: ld1 {v4.16b}, [x10], #16 /* load next round key */
+4: ld1 {v4.4s}, [x10], #16 /* load next round key */
subs w7, w7, #3
aese v0.16b, v3.16b
aesmc v0.16b, v0.16b
aese v1.16b, v3.16b
aesmc v1.16b, v1.16b
- ld1 {v5.16b}, [x10], #16 /* load next round key */
+ ld1 {v5.4s}, [x10], #16 /* load next round key */
bpl 2b
aese v0.16b, v4.16b
aese v1.16b, v4.16b
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 6a7dbc7c83a6..a1254036f2b1 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -1,7 +1,7 @@
/*
* aes-ccm-glue.c - AES-CCM transform for ARMv8 with Crypto Extensions
*
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
#include <asm/unaligned.h>
#include <crypto/aes.h>
#include <crypto/scatterwalk.h>
@@ -44,6 +45,8 @@ asmlinkage void ce_aes_ccm_decrypt(u8 out[], u8 const in[], u32 cbytes,
asmlinkage void ce_aes_ccm_final(u8 mac[], u8 const ctr[], u32 const rk[],
u32 rounds);
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
static int ccm_setkey(struct crypto_aead *tfm, const u8 *in_key,
unsigned int key_len)
{
@@ -103,7 +106,45 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
return 0;
}
-static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
+static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
+ u32 abytes, u32 *macp, bool use_neon)
+{
+ if (likely(use_neon)) {
+ ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
+ num_rounds(key));
+ } else {
+ if (*macp > 0 && *macp < AES_BLOCK_SIZE) {
+ int added = min(abytes, AES_BLOCK_SIZE - *macp);
+
+ crypto_xor(&mac[*macp], in, added);
+
+ *macp += added;
+ in += added;
+ abytes -= added;
+ }
+
+ while (abytes > AES_BLOCK_SIZE) {
+ __aes_arm64_encrypt(key->key_enc, mac, mac,
+ num_rounds(key));
+ crypto_xor(mac, in, AES_BLOCK_SIZE);
+
+ in += AES_BLOCK_SIZE;
+ abytes -= AES_BLOCK_SIZE;
+ }
+
+ if (abytes > 0) {
+ __aes_arm64_encrypt(key->key_enc, mac, mac,
+ num_rounds(key));
+ crypto_xor(mac, in, abytes);
+ *macp = abytes;
+ } else {
+ *macp = 0;
+ }
+ }
+}
+
+static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[],
+ bool use_neon)
{
struct crypto_aead *aead = crypto_aead_reqtfm(req);
struct crypto_aes_ctx *ctx = crypto_aead_ctx(aead);
@@ -122,8 +163,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
ltag.len = 6;
}
- ce_aes_ccm_auth_data(mac, (u8 *)&ltag, ltag.len, &macp, ctx->key_enc,
- num_rounds(ctx));
+ ccm_update_mac(ctx, mac, (u8 *)&ltag, ltag.len, &macp, use_neon);
scatterwalk_start(&walk, req->src);
do {
@@ -135,8 +175,7 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
n = scatterwalk_clamp(&walk, len);
}
p = scatterwalk_map(&walk);
- ce_aes_ccm_auth_data(mac, p, n, &macp, ctx->key_enc,
- num_rounds(ctx));
+ ccm_update_mac(ctx, mac, p, n, &macp, use_neon);
len -= n;
scatterwalk_unmap(p);
@@ -145,6 +184,56 @@ static void ccm_calculate_auth_mac(struct aead_request *req, u8 mac[])
} while (len);
}
+static int ccm_crypt_fallback(struct skcipher_walk *walk, u8 mac[], u8 iv0[],
+ struct crypto_aes_ctx *ctx, bool enc)
+{
+ u8 buf[AES_BLOCK_SIZE];
+ int err = 0;
+
+ while (walk->nbytes) {
+ int blocks = walk->nbytes / AES_BLOCK_SIZE;
+ u32 tail = walk->nbytes % AES_BLOCK_SIZE;
+ u8 *dst = walk->dst.virt.addr;
+ u8 *src = walk->src.virt.addr;
+ u32 nbytes = walk->nbytes;
+
+ if (nbytes == walk->total && tail > 0) {
+ blocks++;
+ tail = 0;
+ }
+
+ do {
+ u32 bsize = AES_BLOCK_SIZE;
+
+ if (nbytes < AES_BLOCK_SIZE)
+ bsize = nbytes;
+
+ crypto_inc(walk->iv, AES_BLOCK_SIZE);
+ __aes_arm64_encrypt(ctx->key_enc, buf, walk->iv,
+ num_rounds(ctx));
+ __aes_arm64_encrypt(ctx->key_enc, mac, mac,
+ num_rounds(ctx));
+ if (enc)
+ crypto_xor(mac, src, bsize);
+ crypto_xor_cpy(dst, src, buf, bsize);
+ if (!enc)
+ crypto_xor(mac, dst, bsize);
+ dst += bsize;
+ src += bsize;
+ nbytes -= bsize;
+ } while (--blocks);
+
+ err = skcipher_walk_done(walk, tail);
+ }
+
+ if (!err) {
+ __aes_arm64_encrypt(ctx->key_enc, buf, iv0, num_rounds(ctx));
+ __aes_arm64_encrypt(ctx->key_enc, mac, mac, num_rounds(ctx));
+ crypto_xor(mac, buf, AES_BLOCK_SIZE);
+ }
+ return err;
+}
+
static int ccm_encrypt(struct aead_request *req)
{
struct crypto_aead *aead = crypto_aead_reqtfm(req);
@@ -153,39 +242,46 @@ static int ccm_encrypt(struct aead_request *req)
u8 __aligned(8) mac[AES_BLOCK_SIZE];
u8 buf[AES_BLOCK_SIZE];
u32 len = req->cryptlen;
+ bool use_neon = may_use_simd();
int err;
err = ccm_init_mac(req, mac, len);
if (err)
return err;
- kernel_neon_begin_partial(6);
+ if (likely(use_neon))
+ kernel_neon_begin();
if (req->assoclen)
- ccm_calculate_auth_mac(req, mac);
+ ccm_calculate_auth_mac(req, mac, use_neon);
/* preserve the original iv for the final round */
memcpy(buf, req->iv, AES_BLOCK_SIZE);
err = skcipher_walk_aead_encrypt(&walk, req, true);
- while (walk.nbytes) {
- u32 tail = walk.nbytes % AES_BLOCK_SIZE;
-
- if (walk.nbytes == walk.total)
- tail = 0;
+ if (likely(use_neon)) {
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
- ce_aes_ccm_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
- walk.nbytes - tail, ctx->key_enc,
- num_rounds(ctx), mac, walk.iv);
+ if (walk.nbytes == walk.total)
+ tail = 0;
- err = skcipher_walk_done(&walk, tail);
- }
- if (!err)
- ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+ ce_aes_ccm_encrypt(walk.dst.virt.addr,
+ walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
- kernel_neon_end();
+ err = skcipher_walk_done(&walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc,
+ num_rounds(ctx));
+ kernel_neon_end();
+ } else {
+ err = ccm_crypt_fallback(&walk, mac, buf, ctx, true);
+ }
if (err)
return err;
@@ -205,38 +301,46 @@ static int ccm_decrypt(struct aead_request *req)
u8 __aligned(8) mac[AES_BLOCK_SIZE];
u8 buf[AES_BLOCK_SIZE];
u32 len = req->cryptlen - authsize;
+ bool use_neon = may_use_simd();
int err;
err = ccm_init_mac(req, mac, len);
if (err)
return err;
- kernel_neon_begin_partial(6);
+ if (likely(use_neon))
+ kernel_neon_begin();
if (req->assoclen)
- ccm_calculate_auth_mac(req, mac);
+ ccm_calculate_auth_mac(req, mac, use_neon);
/* preserve the original iv for the final round */
memcpy(buf, req->iv, AES_BLOCK_SIZE);
err = skcipher_walk_aead_decrypt(&walk, req, true);
- while (walk.nbytes) {
- u32 tail = walk.nbytes % AES_BLOCK_SIZE;
+ if (likely(use_neon)) {
+ while (walk.nbytes) {
+ u32 tail = walk.nbytes % AES_BLOCK_SIZE;
- if (walk.nbytes == walk.total)
- tail = 0;
+ if (walk.nbytes == walk.total)
+ tail = 0;
- ce_aes_ccm_decrypt(walk.dst.virt.addr, walk.src.virt.addr,
- walk.nbytes - tail, ctx->key_enc,
- num_rounds(ctx), mac, walk.iv);
+ ce_aes_ccm_decrypt(walk.dst.virt.addr,
+ walk.src.virt.addr,
+ walk.nbytes - tail, ctx->key_enc,
+ num_rounds(ctx), mac, walk.iv);
- err = skcipher_walk_done(&walk, tail);
- }
- if (!err)
- ce_aes_ccm_final(mac, buf, ctx->key_enc, num_rounds(ctx));
+ err = skcipher_walk_done(&walk, tail);
+ }
+ if (!err)
+ ce_aes_ccm_final(mac, buf, ctx->key_enc,
+ num_rounds(ctx));
- kernel_neon_end();
+ kernel_neon_end();
+ } else {
+ err = ccm_crypt_fallback(&walk, mac, buf, ctx, false);
+ }
if (err)
return err;
diff --git a/arch/arm64/crypto/aes-ce-cipher.c b/arch/arm64/crypto/aes-ce-cipher.c
index 50d9fe11d0c8..6a75cd75ed11 100644
--- a/arch/arm64/crypto/aes-ce-cipher.c
+++ b/arch/arm64/crypto/aes-ce-cipher.c
@@ -1,7 +1,7 @@
/*
* aes-ce-cipher.c - core AES cipher using ARMv8 Crypto Extensions
*
- * Copyright (C) 2013 - 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,8 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
+#include <asm/unaligned.h>
#include <crypto/aes.h>
#include <linux/cpufeature.h>
#include <linux/crypto.h>
@@ -20,6 +22,9 @@ MODULE_DESCRIPTION("Synchronous AES cipher using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+asmlinkage void __aes_arm64_decrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
struct aes_block {
u8 b[AES_BLOCK_SIZE];
};
@@ -44,27 +49,32 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
void *dummy0;
int dummy1;
- kernel_neon_begin_partial(4);
+ if (!may_use_simd()) {
+ __aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
+ return;
+ }
+
+ kernel_neon_begin();
__asm__(" ld1 {v0.16b}, %[in] ;"
- " ld1 {v1.16b}, [%[key]], #16 ;"
+ " ld1 {v1.4s}, [%[key]], #16 ;"
" cmp %w[rounds], #10 ;"
" bmi 0f ;"
" bne 3f ;"
" mov v3.16b, v1.16b ;"
" b 2f ;"
"0: mov v2.16b, v1.16b ;"
- " ld1 {v3.16b}, [%[key]], #16 ;"
+ " ld1 {v3.4s}, [%[key]], #16 ;"
"1: aese v0.16b, v2.16b ;"
" aesmc v0.16b, v0.16b ;"
- "2: ld1 {v1.16b}, [%[key]], #16 ;"
+ "2: ld1 {v1.4s}, [%[key]], #16 ;"
" aese v0.16b, v3.16b ;"
" aesmc v0.16b, v0.16b ;"
- "3: ld1 {v2.16b}, [%[key]], #16 ;"
+ "3: ld1 {v2.4s}, [%[key]], #16 ;"
" subs %w[rounds], %w[rounds], #3 ;"
" aese v0.16b, v1.16b ;"
" aesmc v0.16b, v0.16b ;"
- " ld1 {v3.16b}, [%[key]], #16 ;"
+ " ld1 {v3.4s}, [%[key]], #16 ;"
" bpl 1b ;"
" aese v0.16b, v2.16b ;"
" eor v0.16b, v0.16b, v3.16b ;"
@@ -89,27 +99,32 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
void *dummy0;
int dummy1;
- kernel_neon_begin_partial(4);
+ if (!may_use_simd()) {
+ __aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
+ return;
+ }
+
+ kernel_neon_begin();
__asm__(" ld1 {v0.16b}, %[in] ;"
- " ld1 {v1.16b}, [%[key]], #16 ;"
+ " ld1 {v1.4s}, [%[key]], #16 ;"
" cmp %w[rounds], #10 ;"
" bmi 0f ;"
" bne 3f ;"
" mov v3.16b, v1.16b ;"
" b 2f ;"
"0: mov v2.16b, v1.16b ;"
- " ld1 {v3.16b}, [%[key]], #16 ;"
+ " ld1 {v3.4s}, [%[key]], #16 ;"
"1: aesd v0.16b, v2.16b ;"
" aesimc v0.16b, v0.16b ;"
- "2: ld1 {v1.16b}, [%[key]], #16 ;"
+ "2: ld1 {v1.4s}, [%[key]], #16 ;"
" aesd v0.16b, v3.16b ;"
" aesimc v0.16b, v0.16b ;"
- "3: ld1 {v2.16b}, [%[key]], #16 ;"
+ "3: ld1 {v2.4s}, [%[key]], #16 ;"
" subs %w[rounds], %w[rounds], #3 ;"
" aesd v0.16b, v1.16b ;"
" aesimc v0.16b, v0.16b ;"
- " ld1 {v3.16b}, [%[key]], #16 ;"
+ " ld1 {v3.4s}, [%[key]], #16 ;"
" bpl 1b ;"
" aesd v0.16b, v2.16b ;"
" eor v0.16b, v0.16b, v3.16b ;"
@@ -165,20 +180,16 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
key_len != AES_KEYSIZE_256)
return -EINVAL;
- memcpy(ctx->key_enc, in_key, key_len);
ctx->key_length = key_len;
+ for (i = 0; i < kwords; i++)
+ ctx->key_enc[i] = get_unaligned_le32(in_key + i * sizeof(u32));
- kernel_neon_begin_partial(2);
+ kernel_neon_begin();
for (i = 0; i < sizeof(rcon); i++) {
u32 *rki = ctx->key_enc + (i * kwords);
u32 *rko = rki + kwords;
-#ifndef CONFIG_CPU_BIG_ENDIAN
rko[0] = ror32(aes_sub(rki[kwords - 1]), 8) ^ rcon[i] ^ rki[0];
-#else
- rko[0] = rol32(aes_sub(rki[kwords - 1]), 8) ^ (rcon[i] << 24) ^
- rki[0];
-#endif
rko[1] = rko[0] ^ rki[1];
rko[2] = rko[1] ^ rki[2];
rko[3] = rko[2] ^ rki[3];
@@ -210,9 +221,9 @@ int ce_aes_expandkey(struct crypto_aes_ctx *ctx, const u8 *in_key,
key_dec[0] = key_enc[j];
for (i = 1, j--; j > 0; i++, j--)
- __asm__("ld1 {v0.16b}, %[in] ;"
+ __asm__("ld1 {v0.4s}, %[in] ;"
"aesimc v1.16b, v0.16b ;"
- "st1 {v1.16b}, %[out] ;"
+ "st1 {v1.4s}, %[out] ;"
: [out] "=Q"(key_dec[i])
: [in] "Q"(key_enc[j])
diff --git a/arch/arm64/crypto/aes-ce.S b/arch/arm64/crypto/aes-ce.S
index b46093d567e5..50330f5c3adc 100644
--- a/arch/arm64/crypto/aes-ce.S
+++ b/arch/arm64/crypto/aes-ce.S
@@ -2,7 +2,7 @@
* linux/arch/arm64/crypto/aes-ce.S - AES cipher for ARMv8 with
* Crypto Extensions
*
- * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2013 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -22,11 +22,11 @@
cmp \rounds, #12
blo 2222f /* 128 bits */
beq 1111f /* 192 bits */
- ld1 {v17.16b-v18.16b}, [\rk], #32
-1111: ld1 {v19.16b-v20.16b}, [\rk], #32
-2222: ld1 {v21.16b-v24.16b}, [\rk], #64
- ld1 {v25.16b-v28.16b}, [\rk], #64
- ld1 {v29.16b-v31.16b}, [\rk]
+ ld1 {v17.4s-v18.4s}, [\rk], #32
+1111: ld1 {v19.4s-v20.4s}, [\rk], #32
+2222: ld1 {v21.4s-v24.4s}, [\rk], #64
+ ld1 {v25.4s-v28.4s}, [\rk], #64
+ ld1 {v29.4s-v31.4s}, [\rk]
.endm
/* prepare for encryption with key in rk[] */
diff --git a/arch/arm64/crypto/aes-cipher-core.S b/arch/arm64/crypto/aes-cipher-core.S
index f2f9cc519309..6d2445d603cc 100644
--- a/arch/arm64/crypto/aes-cipher-core.S
+++ b/arch/arm64/crypto/aes-cipher-core.S
@@ -10,6 +10,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/cache.h>
.text
@@ -17,94 +18,155 @@
out .req x1
in .req x2
rounds .req x3
- tt .req x4
- lt .req x2
+ tt .req x2
- .macro __pair, enc, reg0, reg1, in0, in1e, in1d, shift
+ .macro __pair1, sz, op, reg0, reg1, in0, in1e, in1d, shift
+ .ifc \op\shift, b0
+ ubfiz \reg0, \in0, #2, #8
+ ubfiz \reg1, \in1e, #2, #8
+ .else
ubfx \reg0, \in0, #\shift, #8
- .if \enc
ubfx \reg1, \in1e, #\shift, #8
- .else
- ubfx \reg1, \in1d, #\shift, #8
.endif
+
+ /*
+ * AArch64 cannot do byte size indexed loads from a table containing
+ * 32-bit quantities, i.e., 'ldrb w12, [tt, w12, uxtw #2]' is not a
+ * valid instruction. So perform the shift explicitly first for the
+ * high bytes (the low byte is shifted implicitly by using ubfiz rather
+ * than ubfx above)
+ */
+ .ifnc \op, b
ldr \reg0, [tt, \reg0, uxtw #2]
ldr \reg1, [tt, \reg1, uxtw #2]
+ .else
+ .if \shift > 0
+ lsl \reg0, \reg0, #2
+ lsl \reg1, \reg1, #2
+ .endif
+ ldrb \reg0, [tt, \reg0, uxtw]
+ ldrb \reg1, [tt, \reg1, uxtw]
+ .endif
.endm
- .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc
+ .macro __pair0, sz, op, reg0, reg1, in0, in1e, in1d, shift
+ ubfx \reg0, \in0, #\shift, #8
+ ubfx \reg1, \in1d, #\shift, #8
+ ldr\op \reg0, [tt, \reg0, uxtw #\sz]
+ ldr\op \reg1, [tt, \reg1, uxtw #\sz]
+ .endm
+
+ .macro __hround, out0, out1, in0, in1, in2, in3, t0, t1, enc, sz, op
ldp \out0, \out1, [rk], #8
- __pair \enc, w13, w14, \in0, \in1, \in3, 0
- __pair \enc, w15, w16, \in1, \in2, \in0, 8
- __pair \enc, w17, w18, \in2, \in3, \in1, 16
- __pair \enc, \t0, \t1, \in3, \in0, \in2, 24
-
- eor \out0, \out0, w13
- eor \out1, \out1, w14
- eor \out0, \out0, w15, ror #24
- eor \out1, \out1, w16, ror #24
- eor \out0, \out0, w17, ror #16
- eor \out1, \out1, w18, ror #16
+ __pair\enc \sz, \op, w12, w13, \in0, \in1, \in3, 0
+ __pair\enc \sz, \op, w14, w15, \in1, \in2, \in0, 8
+ __pair\enc \sz, \op, w16, w17, \in2, \in3, \in1, 16
+ __pair\enc \sz, \op, \t0, \t1, \in3, \in0, \in2, 24
+
+ eor \out0, \out0, w12
+ eor \out1, \out1, w13
+ eor \out0, \out0, w14, ror #24
+ eor \out1, \out1, w15, ror #24
+ eor \out0, \out0, w16, ror #16
+ eor \out1, \out1, w17, ror #16
eor \out0, \out0, \t0, ror #8
eor \out1, \out1, \t1, ror #8
.endm
- .macro fround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1
- __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1
+ .macro fround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in1, \in2, \in3, \out2, \out3, 1, \sz, \op
+ __hround \out2, \out3, \in2, \in3, \in0, \in1, \in1, \in2, 1, \sz, \op
.endm
- .macro iround, out0, out1, out2, out3, in0, in1, in2, in3
- __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0
- __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0
+ .macro iround, out0, out1, out2, out3, in0, in1, in2, in3, sz=2, op
+ __hround \out0, \out1, \in0, \in3, \in2, \in1, \out2, \out3, 0, \sz, \op
+ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op
.endm
- .macro do_crypt, round, ttab, ltab
- ldp w5, w6, [in]
- ldp w7, w8, [in, #8]
- ldp w9, w10, [rk], #16
- ldp w11, w12, [rk, #-8]
+ .macro do_crypt, round, ttab, ltab, bsz
+ ldp w4, w5, [in]
+ ldp w6, w7, [in, #8]
+ ldp w8, w9, [rk], #16
+ ldp w10, w11, [rk, #-8]
+CPU_BE( rev w4, w4 )
CPU_BE( rev w5, w5 )
CPU_BE( rev w6, w6 )
CPU_BE( rev w7, w7 )
-CPU_BE( rev w8, w8 )
+ eor w4, w4, w8
eor w5, w5, w9
eor w6, w6, w10
eor w7, w7, w11
- eor w8, w8, w12
adr_l tt, \ttab
- adr_l lt, \ltab
tbnz rounds, #1, 1f
-0: \round w9, w10, w11, w12, w5, w6, w7, w8
- \round w5, w6, w7, w8, w9, w10, w11, w12
+0: \round w8, w9, w10, w11, w4, w5, w6, w7
+ \round w4, w5, w6, w7, w8, w9, w10, w11
1: subs rounds, rounds, #4
- \round w9, w10, w11, w12, w5, w6, w7, w8
- csel tt, tt, lt, hi
- \round w5, w6, w7, w8, w9, w10, w11, w12
- b.hi 0b
-
+ \round w8, w9, w10, w11, w4, w5, w6, w7
+ b.ls 3f
+2: \round w4, w5, w6, w7, w8, w9, w10, w11
+ b 0b
+3: adr_l tt, \ltab
+ \round w4, w5, w6, w7, w8, w9, w10, w11, \bsz, b
+
+CPU_BE( rev w4, w4 )
CPU_BE( rev w5, w5 )
CPU_BE( rev w6, w6 )
CPU_BE( rev w7, w7 )
-CPU_BE( rev w8, w8 )
- stp w5, w6, [out]
- stp w7, w8, [out, #8]
+ stp w4, w5, [out]
+ stp w6, w7, [out, #8]
ret
.endm
- .align 5
+ .align L1_CACHE_SHIFT
+ .type __aes_arm64_inverse_sbox, %object
+__aes_arm64_inverse_sbox:
+ .byte 0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
+ .byte 0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
+ .byte 0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
+ .byte 0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
+ .byte 0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
+ .byte 0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
+ .byte 0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
+ .byte 0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
+ .byte 0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
+ .byte 0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
+ .byte 0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
+ .byte 0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
+ .byte 0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
+ .byte 0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
+ .byte 0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
+ .byte 0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
+ .byte 0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
+ .byte 0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
+ .byte 0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
+ .byte 0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
+ .byte 0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
+ .byte 0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
+ .byte 0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
+ .byte 0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
+ .byte 0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
+ .byte 0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
+ .byte 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
+ .byte 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
+ .byte 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
+ .byte 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
+ .byte 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
+ .byte 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
+ .size __aes_arm64_inverse_sbox, . - __aes_arm64_inverse_sbox
+
ENTRY(__aes_arm64_encrypt)
- do_crypt fround, crypto_ft_tab, crypto_fl_tab
+ do_crypt fround, crypto_ft_tab, crypto_ft_tab + 1, 2
ENDPROC(__aes_arm64_encrypt)
.align 5
ENTRY(__aes_arm64_decrypt)
- do_crypt iround, crypto_it_tab, crypto_il_tab
+ do_crypt iround, crypto_it_tab, __aes_arm64_inverse_sbox, 0
ENDPROC(__aes_arm64_decrypt)
diff --git a/arch/arm64/crypto/aes-ctr-fallback.h b/arch/arm64/crypto/aes-ctr-fallback.h
new file mode 100644
index 000000000000..c9285717b6b5
--- /dev/null
+++ b/arch/arm64/crypto/aes-ctr-fallback.h
@@ -0,0 +1,53 @@
+/*
+ * Fallback for sync aes(ctr) in contexts where kernel mode NEON
+ * is not allowed
+ *
+ * Copyright (C) 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/aes.h>
+#include <crypto/internal/skcipher.h>
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
+
+static inline int aes_ctr_encrypt_fallback(struct crypto_aes_ctx *ctx,
+ struct skcipher_request *req)
+{
+ struct skcipher_walk walk;
+ u8 buf[AES_BLOCK_SIZE];
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, true);
+
+ while (walk.nbytes > 0) {
+ u8 *dst = walk.dst.virt.addr;
+ u8 *src = walk.src.virt.addr;
+ int nbytes = walk.nbytes;
+ int tail = 0;
+
+ if (nbytes < walk.total) {
+ nbytes = round_down(nbytes, AES_BLOCK_SIZE);
+ tail = walk.nbytes % AES_BLOCK_SIZE;
+ }
+
+ do {
+ int bsize = min(nbytes, AES_BLOCK_SIZE);
+
+ __aes_arm64_encrypt(ctx->key_enc, buf, walk.iv,
+ 6 + ctx->key_length / 4);
+ crypto_xor_cpy(dst, src, buf, bsize);
+ crypto_inc(walk.iv, AES_BLOCK_SIZE);
+
+ dst += AES_BLOCK_SIZE;
+ src += AES_BLOCK_SIZE;
+ nbytes -= AES_BLOCK_SIZE;
+ } while (nbytes > 0);
+
+ err = skcipher_walk_done(&walk, tail);
+ }
+ return err;
+}
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index bcf596b0197e..998ba519a026 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -10,6 +10,7 @@
#include <asm/neon.h>
#include <asm/hwcap.h>
+#include <asm/simd.h>
#include <crypto/aes.h>
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
@@ -19,6 +20,7 @@
#include <crypto/xts.h>
#include "aes-ce-setkey.h"
+#include "aes-ctr-fallback.h"
#ifdef USE_V8_CRYPTO_EXTENSIONS
#define MODE "ce"
@@ -241,9 +243,7 @@ static int ctr_encrypt(struct skcipher_request *req)
aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc, rounds,
blocks, walk.iv, first);
- if (tdst != tsrc)
- memcpy(tdst, tsrc, nbytes);
- crypto_xor(tdst, tail, nbytes);
+ crypto_xor_cpy(tdst, tsrc, tail, nbytes);
err = skcipher_walk_done(&walk, 0);
}
kernel_neon_end();
@@ -251,6 +251,17 @@ static int ctr_encrypt(struct skcipher_request *req)
return err;
}
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ if (!may_use_simd())
+ return aes_ctr_encrypt_fallback(ctx, req);
+
+ return ctr_encrypt(req);
+}
+
static int xts_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -357,8 +368,8 @@ static struct skcipher_alg aes_algs[] = { {
.ivsize = AES_BLOCK_SIZE,
.chunksize = AES_BLOCK_SIZE,
.setkey = skcipher_aes_setkey,
- .encrypt = ctr_encrypt,
- .decrypt = ctr_encrypt,
+ .encrypt = ctr_encrypt_sync,
+ .decrypt = ctr_encrypt_sync,
}, {
.base = {
.cra_name = "__xts(aes)",
@@ -460,11 +471,35 @@ static int mac_init(struct shash_desc *desc)
return 0;
}
+static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
+ u8 dg[], int enc_before, int enc_after)
+{
+ int rounds = 6 + ctx->key_length / 4;
+
+ if (may_use_simd()) {
+ kernel_neon_begin();
+ aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
+ enc_after);
+ kernel_neon_end();
+ } else {
+ if (enc_before)
+ __aes_arm64_encrypt(ctx->key_enc, dg, dg, rounds);
+
+ while (blocks--) {
+ crypto_xor(dg, in, AES_BLOCK_SIZE);
+ in += AES_BLOCK_SIZE;
+
+ if (blocks || enc_after)
+ __aes_arm64_encrypt(ctx->key_enc, dg, dg,
+ rounds);
+ }
+ }
+}
+
static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
- int rounds = 6 + tctx->key.key_length / 4;
while (len > 0) {
unsigned int l;
@@ -476,10 +511,8 @@ static int mac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
len %= AES_BLOCK_SIZE;
- kernel_neon_begin();
- aes_mac_update(p, tctx->key.key_enc, rounds, blocks,
- ctx->dg, (ctx->len != 0), (len != 0));
- kernel_neon_end();
+ mac_do_update(&tctx->key, p, blocks, ctx->dg,
+ (ctx->len != 0), (len != 0));
p += blocks * AES_BLOCK_SIZE;
@@ -507,11 +540,8 @@ static int cbcmac_final(struct shash_desc *desc, u8 *out)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
- int rounds = 6 + tctx->key.key_length / 4;
- kernel_neon_begin();
- aes_mac_update(NULL, tctx->key.key_enc, rounds, 0, ctx->dg, 1, 0);
- kernel_neon_end();
+ mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1, 0);
memcpy(out, ctx->dg, AES_BLOCK_SIZE);
@@ -522,7 +552,6 @@ static int cmac_final(struct shash_desc *desc, u8 *out)
{
struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
- int rounds = 6 + tctx->key.key_length / 4;
u8 *consts = tctx->consts;
if (ctx->len != AES_BLOCK_SIZE) {
@@ -530,9 +559,7 @@ static int cmac_final(struct shash_desc *desc, u8 *out)
consts += AES_BLOCK_SIZE;
}
- kernel_neon_begin();
- aes_mac_update(consts, tctx->key.key_enc, rounds, 1, ctx->dg, 0, 1);
- kernel_neon_end();
+ mac_do_update(&tctx->key, consts, 1, ctx->dg, 0, 1);
memcpy(out, ctx->dg, AES_BLOCK_SIZE);
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index db2501d93550..c55d68ccb89f 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -1,7 +1,7 @@
/*
* Bit sliced AES using NEON instructions
*
- * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -9,12 +9,15 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
#include <crypto/aes.h>
#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/xts.h>
#include <linux/module.h>
+#include "aes-ctr-fallback.h"
+
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
@@ -58,6 +61,11 @@ struct aesbs_cbc_ctx {
u32 enc[AES_MAX_KEYLENGTH_U32];
};
+struct aesbs_ctr_ctx {
+ struct aesbs_ctx key; /* must be first member */
+ struct crypto_aes_ctx fallback;
+};
+
struct aesbs_xts_ctx {
struct aesbs_ctx key;
u32 twkey[AES_MAX_KEYLENGTH_U32];
@@ -196,6 +204,25 @@ static int cbc_decrypt(struct skcipher_request *req)
return err;
}
+static int aesbs_ctr_setkey_sync(struct crypto_skcipher *tfm, const u8 *in_key,
+ unsigned int key_len)
+{
+ struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+ int err;
+
+ err = crypto_aes_expand_key(&ctx->fallback, in_key, key_len);
+ if (err)
+ return err;
+
+ ctx->key.rounds = 6 + key_len / 4;
+
+ kernel_neon_begin();
+ aesbs_convert_key(ctx->key.rk, ctx->fallback.key_enc, ctx->key.rounds);
+ kernel_neon_end();
+
+ return 0;
+}
+
static int ctr_encrypt(struct skcipher_request *req)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
@@ -224,9 +251,8 @@ static int ctr_encrypt(struct skcipher_request *req)
u8 *dst = walk.dst.virt.addr + blocks * AES_BLOCK_SIZE;
u8 *src = walk.src.virt.addr + blocks * AES_BLOCK_SIZE;
- if (dst != src)
- memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
- crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE);
+ crypto_xor_cpy(dst, src, final,
+ walk.total % AES_BLOCK_SIZE);
err = skcipher_walk_done(&walk, 0);
break;
@@ -260,6 +286,17 @@ static int aesbs_xts_setkey(struct crypto_skcipher *tfm, const u8 *in_key,
return aesbs_setkey(tfm, in_key, key_len);
}
+static int ctr_encrypt_sync(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ if (!may_use_simd())
+ return aes_ctr_encrypt_fallback(&ctx->fallback, req);
+
+ return ctr_encrypt(req);
+}
+
static int __xts_crypt(struct skcipher_request *req,
void (*fn)(u8 out[], u8 const in[], u8 const rk[],
int rounds, int blocks, u8 iv[]))
@@ -356,7 +393,7 @@ static struct skcipher_alg aes_algs[] = { {
.base.cra_driver_name = "ctr-aes-neonbs",
.base.cra_priority = 250 - 1,
.base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct aesbs_ctx),
+ .base.cra_ctxsize = sizeof(struct aesbs_ctr_ctx),
.base.cra_module = THIS_MODULE,
.min_keysize = AES_MIN_KEY_SIZE,
@@ -364,9 +401,9 @@ static struct skcipher_alg aes_algs[] = { {
.chunksize = AES_BLOCK_SIZE,
.walksize = 8 * AES_BLOCK_SIZE,
.ivsize = AES_BLOCK_SIZE,
- .setkey = aesbs_setkey,
- .encrypt = ctr_encrypt,
- .decrypt = ctr_encrypt,
+ .setkey = aesbs_ctr_setkey_sync,
+ .encrypt = ctr_encrypt_sync,
+ .decrypt = ctr_encrypt_sync,
}, {
.base.cra_name = "__xts(aes)",
.base.cra_driver_name = "__xts-aes-neonbs",
diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c
index a7cd575ea223..cbdb75d15cd0 100644
--- a/arch/arm64/crypto/chacha20-neon-glue.c
+++ b/arch/arm64/crypto/chacha20-neon-glue.c
@@ -1,7 +1,7 @@
/*
* ChaCha20 256-bit cipher algorithm, RFC7539, arm64 NEON functions
*
- * Copyright (C) 2016 Linaro, Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2016 - 2017 Linaro, Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -26,6 +26,7 @@
#include <asm/hwcap.h>
#include <asm/neon.h>
+#include <asm/simd.h>
asmlinkage void chacha20_block_xor_neon(u32 *state, u8 *dst, const u8 *src);
asmlinkage void chacha20_4block_xor_neon(u32 *state, u8 *dst, const u8 *src);
@@ -64,7 +65,7 @@ static int chacha20_neon(struct skcipher_request *req)
u32 state[16];
int err;
- if (req->cryptlen <= CHACHA20_BLOCK_SIZE)
+ if (!may_use_simd() || req->cryptlen <= CHACHA20_BLOCK_SIZE)
return crypto_chacha20_crypt(req);
err = skcipher_walk_virt(&walk, req, true);
diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
index eccb1ae90064..624f4137918c 100644
--- a/arch/arm64/crypto/crc32-ce-glue.c
+++ b/arch/arm64/crypto/crc32-ce-glue.c
@@ -1,7 +1,7 @@
/*
* Accelerated CRC32(C) using arm64 NEON and Crypto Extensions instructions
*
- * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -19,6 +19,7 @@
#include <asm/hwcap.h>
#include <asm/neon.h>
+#include <asm/simd.h>
#include <asm/unaligned.h>
#define PMULL_MIN_LEN 64L /* minimum size of buffer
@@ -105,10 +106,10 @@ static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
length -= l;
}
- if (length >= PMULL_MIN_LEN) {
+ if (length >= PMULL_MIN_LEN && may_use_simd()) {
l = round_down(length, SCALE_F);
- kernel_neon_begin_partial(10);
+ kernel_neon_begin();
*crc = crc32_pmull_le(data, l, *crc);
kernel_neon_end();
@@ -137,10 +138,10 @@ static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
length -= l;
}
- if (length >= PMULL_MIN_LEN) {
+ if (length >= PMULL_MIN_LEN && may_use_simd()) {
l = round_down(length, SCALE_F);
- kernel_neon_begin_partial(10);
+ kernel_neon_begin();
*crc = crc32c_pmull_le(data, l, *crc);
kernel_neon_end();
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index 60cb590c2590..96f0cae4a022 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -1,7 +1,7 @@
/*
* Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
*
- * Copyright (C) 2016 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2016 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -18,6 +18,7 @@
#include <crypto/internal/hash.h>
#include <asm/neon.h>
+#include <asm/simd.h>
#define CRC_T10DIF_PMULL_CHUNK_SIZE 16U
@@ -48,9 +49,13 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data,
}
if (length > 0) {
- kernel_neon_begin_partial(14);
- *crc = crc_t10dif_pmull(*crc, data, length);
- kernel_neon_end();
+ if (may_use_simd()) {
+ kernel_neon_begin();
+ *crc = crc_t10dif_pmull(*crc, data, length);
+ kernel_neon_end();
+ } else {
+ *crc = crc_t10dif_generic(*crc, data, length);
+ }
}
return 0;
diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index f0bb9f0b524f..11ebf1ae248a 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -1,7 +1,7 @@
/*
* Accelerated GHASH implementation with ARMv8 PMULL instructions.
*
- * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -11,31 +11,215 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
- SHASH .req v0
- SHASH2 .req v1
- T1 .req v2
- T2 .req v3
- MASK .req v4
- XL .req v5
- XM .req v6
- XH .req v7
- IN1 .req v7
+ SHASH .req v0
+ SHASH2 .req v1
+ T1 .req v2
+ T2 .req v3
+ MASK .req v4
+ XL .req v5
+ XM .req v6
+ XH .req v7
+ IN1 .req v7
+
+ k00_16 .req v8
+ k32_48 .req v9
+
+ t3 .req v10
+ t4 .req v11
+ t5 .req v12
+ t6 .req v13
+ t7 .req v14
+ t8 .req v15
+ t9 .req v16
+
+ perm1 .req v17
+ perm2 .req v18
+ perm3 .req v19
+
+ sh1 .req v20
+ sh2 .req v21
+ sh3 .req v22
+ sh4 .req v23
+
+ ss1 .req v24
+ ss2 .req v25
+ ss3 .req v26
+ ss4 .req v27
.text
.arch armv8-a+crypto
- /*
- * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
- * struct ghash_key const *k, const char *head)
- */
-ENTRY(pmull_ghash_update)
+ .macro __pmull_p64, rd, rn, rm
+ pmull \rd\().1q, \rn\().1d, \rm\().1d
+ .endm
+
+ .macro __pmull2_p64, rd, rn, rm
+ pmull2 \rd\().1q, \rn\().2d, \rm\().2d
+ .endm
+
+ .macro __pmull_p8, rq, ad, bd
+ ext t3.8b, \ad\().8b, \ad\().8b, #1 // A1
+ ext t5.8b, \ad\().8b, \ad\().8b, #2 // A2
+ ext t7.8b, \ad\().8b, \ad\().8b, #3 // A3
+
+ __pmull_p8_\bd \rq, \ad
+ .endm
+
+ .macro __pmull2_p8, rq, ad, bd
+ tbl t3.16b, {\ad\().16b}, perm1.16b // A1
+ tbl t5.16b, {\ad\().16b}, perm2.16b // A2
+ tbl t7.16b, {\ad\().16b}, perm3.16b // A3
+
+ __pmull2_p8_\bd \rq, \ad
+ .endm
+
+ .macro __pmull_p8_SHASH, rq, ad
+ __pmull_p8_tail \rq, \ad\().8b, SHASH.8b, 8b,, sh1, sh2, sh3, sh4
+ .endm
+
+ .macro __pmull_p8_SHASH2, rq, ad
+ __pmull_p8_tail \rq, \ad\().8b, SHASH2.8b, 8b,, ss1, ss2, ss3, ss4
+ .endm
+
+ .macro __pmull2_p8_SHASH, rq, ad
+ __pmull_p8_tail \rq, \ad\().16b, SHASH.16b, 16b, 2, sh1, sh2, sh3, sh4
+ .endm
+
+ .macro __pmull_p8_tail, rq, ad, bd, nb, t, b1, b2, b3, b4
+ pmull\t t3.8h, t3.\nb, \bd // F = A1*B
+ pmull\t t4.8h, \ad, \b1\().\nb // E = A*B1
+ pmull\t t5.8h, t5.\nb, \bd // H = A2*B
+ pmull\t t6.8h, \ad, \b2\().\nb // G = A*B2
+ pmull\t t7.8h, t7.\nb, \bd // J = A3*B
+ pmull\t t8.8h, \ad, \b3\().\nb // I = A*B3
+ pmull\t t9.8h, \ad, \b4\().\nb // K = A*B4
+ pmull\t \rq\().8h, \ad, \bd // D = A*B
+
+ eor t3.16b, t3.16b, t4.16b // L = E + F
+ eor t5.16b, t5.16b, t6.16b // M = G + H
+ eor t7.16b, t7.16b, t8.16b // N = I + J
+
+ uzp1 t4.2d, t3.2d, t5.2d
+ uzp2 t3.2d, t3.2d, t5.2d
+ uzp1 t6.2d, t7.2d, t9.2d
+ uzp2 t7.2d, t7.2d, t9.2d
+
+ // t3 = (L) (P0 + P1) << 8
+ // t5 = (M) (P2 + P3) << 16
+ eor t4.16b, t4.16b, t3.16b
+ and t3.16b, t3.16b, k32_48.16b
+
+ // t7 = (N) (P4 + P5) << 24
+ // t9 = (K) (P6 + P7) << 32
+ eor t6.16b, t6.16b, t7.16b
+ and t7.16b, t7.16b, k00_16.16b
+
+ eor t4.16b, t4.16b, t3.16b
+ eor t6.16b, t6.16b, t7.16b
+
+ zip2 t5.2d, t4.2d, t3.2d
+ zip1 t3.2d, t4.2d, t3.2d
+ zip2 t9.2d, t6.2d, t7.2d
+ zip1 t7.2d, t6.2d, t7.2d
+
+ ext t3.16b, t3.16b, t3.16b, #15
+ ext t5.16b, t5.16b, t5.16b, #14
+ ext t7.16b, t7.16b, t7.16b, #13
+ ext t9.16b, t9.16b, t9.16b, #12
+
+ eor t3.16b, t3.16b, t5.16b
+ eor t7.16b, t7.16b, t9.16b
+ eor \rq\().16b, \rq\().16b, t3.16b
+ eor \rq\().16b, \rq\().16b, t7.16b
+ .endm
+
+ .macro __pmull_pre_p64
+ movi MASK.16b, #0xe1
+ shl MASK.2d, MASK.2d, #57
+ .endm
+
+ .macro __pmull_pre_p8
+ // k00_16 := 0x0000000000000000_000000000000ffff
+ // k32_48 := 0x00000000ffffffff_0000ffffffffffff
+ movi k32_48.2d, #0xffffffff
+ mov k32_48.h[2], k32_48.h[0]
+ ushr k00_16.2d, k32_48.2d, #32
+
+ // prepare the permutation vectors
+ mov_q x5, 0x080f0e0d0c0b0a09
+ movi T1.8b, #8
+ dup perm1.2d, x5
+ eor perm1.16b, perm1.16b, T1.16b
+ ushr perm2.2d, perm1.2d, #8
+ ushr perm3.2d, perm1.2d, #16
+ ushr T1.2d, perm1.2d, #24
+ sli perm2.2d, perm1.2d, #56
+ sli perm3.2d, perm1.2d, #48
+ sli T1.2d, perm1.2d, #40
+
+ // precompute loop invariants
+ tbl sh1.16b, {SHASH.16b}, perm1.16b
+ tbl sh2.16b, {SHASH.16b}, perm2.16b
+ tbl sh3.16b, {SHASH.16b}, perm3.16b
+ tbl sh4.16b, {SHASH.16b}, T1.16b
+ ext ss1.8b, SHASH2.8b, SHASH2.8b, #1
+ ext ss2.8b, SHASH2.8b, SHASH2.8b, #2
+ ext ss3.8b, SHASH2.8b, SHASH2.8b, #3
+ ext ss4.8b, SHASH2.8b, SHASH2.8b, #4
+ .endm
+
+ //
+ // PMULL (64x64->128) based reduction for CPUs that can do
+ // it in a single instruction.
+ //
+ .macro __pmull_reduce_p64
+ pmull T2.1q, XL.1d, MASK.1d
+ eor XM.16b, XM.16b, T1.16b
+
+ mov XH.d[0], XM.d[1]
+ mov XM.d[1], XL.d[0]
+
+ eor XL.16b, XM.16b, T2.16b
+ ext T2.16b, XL.16b, XL.16b, #8
+ pmull XL.1q, XL.1d, MASK.1d
+ .endm
+
+ //
+ // Alternative reduction for CPUs that lack support for the
+ // 64x64->128 PMULL instruction
+ //
+ .macro __pmull_reduce_p8
+ eor XM.16b, XM.16b, T1.16b
+
+ mov XL.d[1], XM.d[0]
+ mov XH.d[0], XM.d[1]
+
+ shl T1.2d, XL.2d, #57
+ shl T2.2d, XL.2d, #62
+ eor T2.16b, T2.16b, T1.16b
+ shl T1.2d, XL.2d, #63
+ eor T2.16b, T2.16b, T1.16b
+ ext T1.16b, XL.16b, XH.16b, #8
+ eor T2.16b, T2.16b, T1.16b
+
+ mov XL.d[1], T2.d[0]
+ mov XH.d[0], T2.d[1]
+
+ ushr T2.2d, XL.2d, #1
+ eor XH.16b, XH.16b, XL.16b
+ eor XL.16b, XL.16b, T2.16b
+ ushr T2.2d, T2.2d, #6
+ ushr XL.2d, XL.2d, #1
+ .endm
+
+ .macro __pmull_ghash, pn
ld1 {SHASH.2d}, [x3]
ld1 {XL.2d}, [x1]
- movi MASK.16b, #0xe1
ext SHASH2.16b, SHASH.16b, SHASH.16b, #8
- shl MASK.2d, MASK.2d, #57
eor SHASH2.16b, SHASH2.16b, SHASH.16b
+ __pmull_pre_\pn
+
/* do the head block first, if supplied */
cbz x4, 0f
ld1 {T1.2d}, [x4]
@@ -52,28 +236,209 @@ CPU_LE( rev64 T1.16b, T1.16b )
eor T1.16b, T1.16b, T2.16b
eor XL.16b, XL.16b, IN1.16b
+ __pmull2_\pn XH, XL, SHASH // a1 * b1
+ eor T1.16b, T1.16b, XL.16b
+ __pmull_\pn XL, XL, SHASH // a0 * b0
+ __pmull_\pn XM, T1, SHASH2 // (a1 + a0)(b1 + b0)
+
+ eor T2.16b, XL.16b, XH.16b
+ ext T1.16b, XL.16b, XH.16b, #8
+ eor XM.16b, XM.16b, T2.16b
+
+ __pmull_reduce_\pn
+
+ eor T2.16b, T2.16b, XH.16b
+ eor XL.16b, XL.16b, T2.16b
+
+ cbnz w0, 0b
+
+ st1 {XL.2d}, [x1]
+ ret
+ .endm
+
+ /*
+ * void pmull_ghash_update(int blocks, u64 dg[], const char *src,
+ * struct ghash_key const *k, const char *head)
+ */
+ENTRY(pmull_ghash_update_p64)
+ __pmull_ghash p64
+ENDPROC(pmull_ghash_update_p64)
+
+ENTRY(pmull_ghash_update_p8)
+ __pmull_ghash p8
+ENDPROC(pmull_ghash_update_p8)
+
+ KS .req v8
+ CTR .req v9
+ INP .req v10
+
+ .macro load_round_keys, rounds, rk
+ cmp \rounds, #12
+ blo 2222f /* 128 bits */
+ beq 1111f /* 192 bits */
+ ld1 {v17.4s-v18.4s}, [\rk], #32
+1111: ld1 {v19.4s-v20.4s}, [\rk], #32
+2222: ld1 {v21.4s-v24.4s}, [\rk], #64
+ ld1 {v25.4s-v28.4s}, [\rk], #64
+ ld1 {v29.4s-v31.4s}, [\rk]
+ .endm
+
+ .macro enc_round, state, key
+ aese \state\().16b, \key\().16b
+ aesmc \state\().16b, \state\().16b
+ .endm
+
+ .macro enc_block, state, rounds
+ cmp \rounds, #12
+ b.lo 2222f /* 128 bits */
+ b.eq 1111f /* 192 bits */
+ enc_round \state, v17
+ enc_round \state, v18
+1111: enc_round \state, v19
+ enc_round \state, v20
+2222: .irp key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+ enc_round \state, \key
+ .endr
+ aese \state\().16b, v30.16b
+ eor \state\().16b, \state\().16b, v31.16b
+ .endm
+
+ .macro pmull_gcm_do_crypt, enc
+ ld1 {SHASH.2d}, [x4]
+ ld1 {XL.2d}, [x1]
+ ldr x8, [x5, #8] // load lower counter
+
+ 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]
+ .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
+ 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
+ .endif
+
+ rev64 T1.16b, INP.16b
+
+ cmp w6, #12
+ b.ge 2f // AES-192/256?
+
+1: enc_round CTR, v21
+
+ ext T2.16b, XL.16b, XL.16b, #8
+ ext IN1.16b, T1.16b, T1.16b, #8
+
+ enc_round CTR, v22
+
+ eor T1.16b, T1.16b, T2.16b
+ eor XL.16b, XL.16b, IN1.16b
+
+ enc_round CTR, v23
+
pmull2 XH.1q, SHASH.2d, XL.2d // a1 * b1
eor T1.16b, T1.16b, XL.16b
+
+ enc_round CTR, v24
+
pmull XL.1q, SHASH.1d, XL.1d // a0 * b0
pmull XM.1q, SHASH2.1d, T1.1d // (a1 + a0)(b1 + b0)
+ enc_round CTR, v25
+
ext T1.16b, XL.16b, XH.16b, #8
eor T2.16b, XL.16b, XH.16b
eor XM.16b, XM.16b, T1.16b
+
+ enc_round CTR, v26
+
eor XM.16b, XM.16b, T2.16b
pmull T2.1q, XL.1d, MASK.1d
+ enc_round CTR, v27
+
mov XH.d[0], XM.d[1]
mov XM.d[1], XL.d[0]
+ enc_round CTR, v28
+
eor XL.16b, XM.16b, T2.16b
+
+ enc_round CTR, v29
+
ext T2.16b, XL.16b, XL.16b, #8
+
+ aese CTR.16b, v30.16b
+
pmull XL.1q, XL.1d, MASK.1d
eor T2.16b, T2.16b, XH.16b
+
+ eor KS.16b, CTR.16b, v31.16b
+
eor XL.16b, XL.16b, T2.16b
+ .if \enc == 0
+ eor INP.16b, INP.16b, KS.16b
+ st1 {INP.16b}, [x2], #16
+ .endif
+
cbnz w0, 0b
+CPU_LE( rev x8, x8 )
st1 {XL.2d}, [x1]
+ str x8, [x5, #8] // store lower counter
+
+ .if \enc == 1
+ st1 {KS.16b}, [x7]
+ .endif
+
+ ret
+
+2: b.eq 3f // AES-192?
+ enc_round CTR, v17
+ enc_round CTR, v18
+3: enc_round CTR, v19
+ enc_round CTR, v20
+ b 1b
+ .endm
+
+ /*
+ * void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
+ * struct ghash_key const *k, u8 ctr[],
+ * int rounds, u8 ks[])
+ */
+ENTRY(pmull_gcm_encrypt)
+ pmull_gcm_do_crypt 1
+ENDPROC(pmull_gcm_encrypt)
+
+ /*
+ * void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[], const u8 src[],
+ * struct ghash_key const *k, u8 ctr[],
+ * int rounds)
+ */
+ENTRY(pmull_gcm_decrypt)
+ pmull_gcm_do_crypt 0
+ENDPROC(pmull_gcm_decrypt)
+
+ /*
+ * void pmull_gcm_encrypt_block(u8 dst[], u8 src[], u8 rk[], int rounds)
+ */
+ENTRY(pmull_gcm_encrypt_block)
+ cbz x2, 0f
+ load_round_keys w3, x2
+0: ld1 {v0.16b}, [x1]
+ enc_block v0, w3
+ st1 {v0.16b}, [x0]
ret
-ENDPROC(pmull_ghash_update)
+ENDPROC(pmull_gcm_encrypt_block)
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 833ec1e3f3e9..cfc9c92814fd 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -1,7 +1,7 @@
/*
* Accelerated GHASH implementation with ARMv8 PMULL instructions.
*
- * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -9,22 +9,33 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
#include <asm/unaligned.h>
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/b128ops.h>
+#include <crypto/gf128mul.h>
+#include <crypto/internal/aead.h>
#include <crypto/internal/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/scatterwalk.h>
#include <linux/cpufeature.h>
#include <linux/crypto.h>
#include <linux/module.h>
-MODULE_DESCRIPTION("GHASH secure hash using ARMv8 Crypto Extensions");
+MODULE_DESCRIPTION("GHASH and AES-GCM using ARMv8 Crypto Extensions");
MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("ghash");
#define GHASH_BLOCK_SIZE 16
#define GHASH_DIGEST_SIZE 16
+#define GCM_IV_SIZE 12
struct ghash_key {
u64 a;
u64 b;
+ be128 k;
};
struct ghash_desc_ctx {
@@ -33,8 +44,35 @@ struct ghash_desc_ctx {
u32 count;
};
-asmlinkage void pmull_ghash_update(int blocks, u64 dg[], const char *src,
- struct ghash_key const *k, const char *head);
+struct gcm_aes_ctx {
+ struct crypto_aes_ctx aes_key;
+ struct ghash_key ghash_key;
+};
+
+asmlinkage void pmull_ghash_update_p64(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
+
+asmlinkage void pmull_ghash_update_p8(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
+
+static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
+ struct ghash_key const *k,
+ const char *head);
+
+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[]);
+
+asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
+ const u8 src[], struct ghash_key const *k,
+ u8 ctr[], int rounds);
+
+asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
+ u32 const rk[], int rounds);
+
+asmlinkage void __aes_arm64_encrypt(u32 *rk, u8 *out, const u8 *in, int rounds);
static int ghash_init(struct shash_desc *desc)
{
@@ -44,6 +82,36 @@ static int ghash_init(struct shash_desc *desc)
return 0;
}
+static void ghash_do_update(int blocks, u64 dg[], const char *src,
+ struct ghash_key *key, const char *head)
+{
+ if (likely(may_use_simd())) {
+ kernel_neon_begin();
+ pmull_ghash_update(blocks, dg, src, key, head);
+ kernel_neon_end();
+ } else {
+ be128 dst = { cpu_to_be64(dg[1]), cpu_to_be64(dg[0]) };
+
+ do {
+ const u8 *in = src;
+
+ if (head) {
+ in = head;
+ blocks++;
+ head = NULL;
+ } else {
+ src += GHASH_BLOCK_SIZE;
+ }
+
+ crypto_xor((u8 *)&dst, in, GHASH_BLOCK_SIZE);
+ gf128mul_lle(&dst, &key->k);
+ } while (--blocks);
+
+ dg[0] = be64_to_cpu(dst.b);
+ dg[1] = be64_to_cpu(dst.a);
+ }
+}
+
static int ghash_update(struct shash_desc *desc, const u8 *src,
unsigned int len)
{
@@ -67,10 +135,9 @@ static int ghash_update(struct shash_desc *desc, const u8 *src,
blocks = len / GHASH_BLOCK_SIZE;
len %= GHASH_BLOCK_SIZE;
- kernel_neon_begin_partial(8);
- pmull_ghash_update(blocks, ctx->digest, src, key,
- partial ? ctx->buf : NULL);
- kernel_neon_end();
+ ghash_do_update(blocks, ctx->digest, src, key,
+ partial ? ctx->buf : NULL);
+
src += blocks * GHASH_BLOCK_SIZE;
partial = 0;
}
@@ -89,9 +156,7 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
memset(ctx->buf + partial, 0, GHASH_BLOCK_SIZE - partial);
- kernel_neon_begin_partial(8);
- pmull_ghash_update(1, ctx->digest, ctx->buf, key, NULL);
- kernel_neon_end();
+ ghash_do_update(1, ctx->digest, ctx->buf, key, NULL);
}
put_unaligned_be64(ctx->digest[1], dst);
put_unaligned_be64(ctx->digest[0], dst + 8);
@@ -100,16 +165,13 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
return 0;
}
-static int ghash_setkey(struct crypto_shash *tfm,
- const u8 *inkey, unsigned int keylen)
+static int __ghash_setkey(struct ghash_key *key,
+ const u8 *inkey, unsigned int keylen)
{
- struct ghash_key *key = crypto_shash_ctx(tfm);
u64 a, b;
- if (keylen != GHASH_BLOCK_SIZE) {
- crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
- return -EINVAL;
- }
+ /* needed for the fallback */
+ memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
/* perform multiplication by 'x' in GF(2^128) */
b = get_unaligned_be64(inkey);
@@ -124,33 +186,418 @@ static int ghash_setkey(struct crypto_shash *tfm,
return 0;
}
+static int ghash_setkey(struct crypto_shash *tfm,
+ const u8 *inkey, unsigned int keylen)
+{
+ struct ghash_key *key = crypto_shash_ctx(tfm);
+
+ if (keylen != GHASH_BLOCK_SIZE) {
+ crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+ return -EINVAL;
+ }
+
+ return __ghash_setkey(key, inkey, keylen);
+}
+
static struct shash_alg ghash_alg = {
- .digestsize = GHASH_DIGEST_SIZE,
- .init = ghash_init,
- .update = ghash_update,
- .final = ghash_final,
- .setkey = ghash_setkey,
- .descsize = sizeof(struct ghash_desc_ctx),
- .base = {
- .cra_name = "ghash",
- .cra_driver_name = "ghash-ce",
- .cra_priority = 200,
- .cra_flags = CRYPTO_ALG_TYPE_SHASH,
- .cra_blocksize = GHASH_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct ghash_key),
- .cra_module = THIS_MODULE,
- },
+ .base.cra_name = "ghash",
+ .base.cra_driver_name = "ghash-ce",
+ .base.cra_priority = 200,
+ .base.cra_flags = CRYPTO_ALG_TYPE_SHASH,
+ .base.cra_blocksize = GHASH_BLOCK_SIZE,
+ .base.cra_ctxsize = sizeof(struct ghash_key),
+ .base.cra_module = THIS_MODULE,
+
+ .digestsize = GHASH_DIGEST_SIZE,
+ .init = ghash_init,
+ .update = ghash_update,
+ .final = ghash_final,
+ .setkey = ghash_setkey,
+ .descsize = sizeof(struct ghash_desc_ctx),
+};
+
+static int num_rounds(struct crypto_aes_ctx *ctx)
+{
+ /*
+ * # of rounds specified by AES:
+ * 128 bit key 10 rounds
+ * 192 bit key 12 rounds
+ * 256 bit key 14 rounds
+ * => n byte key => 6 + (n/4) rounds
+ */
+ return 6 + ctx->key_length / 4;
+}
+
+static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
+ unsigned int keylen)
+{
+ struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
+ u8 key[GHASH_BLOCK_SIZE];
+ int ret;
+
+ ret = crypto_aes_expand_key(&ctx->aes_key, inkey, keylen);
+ if (ret) {
+ tfm->base.crt_flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+ return -EINVAL;
+ }
+
+ __aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){},
+ num_rounds(&ctx->aes_key));
+
+ return __ghash_setkey(&ctx->ghash_key, key, sizeof(key));
+}
+
+static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+ switch (authsize) {
+ case 4:
+ case 8:
+ case 12 ... 16:
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static void gcm_update_mac(u64 dg[], const u8 *src, int count, u8 buf[],
+ int *buf_count, struct gcm_aes_ctx *ctx)
+{
+ if (*buf_count > 0) {
+ int buf_added = min(count, GHASH_BLOCK_SIZE - *buf_count);
+
+ memcpy(&buf[*buf_count], src, buf_added);
+
+ *buf_count += buf_added;
+ src += buf_added;
+ count -= buf_added;
+ }
+
+ if (count >= GHASH_BLOCK_SIZE || *buf_count == GHASH_BLOCK_SIZE) {
+ int blocks = count / GHASH_BLOCK_SIZE;
+
+ ghash_do_update(blocks, dg, src, &ctx->ghash_key,
+ *buf_count ? buf : NULL);
+
+ src += blocks * GHASH_BLOCK_SIZE;
+ count %= GHASH_BLOCK_SIZE;
+ *buf_count = 0;
+ }
+
+ if (count > 0) {
+ memcpy(buf, src, count);
+ *buf_count = count;
+ }
+}
+
+static void gcm_calculate_auth_mac(struct aead_request *req, u64 dg[])
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+ u8 buf[GHASH_BLOCK_SIZE];
+ struct scatter_walk walk;
+ u32 len = req->assoclen;
+ int buf_count = 0;
+
+ scatterwalk_start(&walk, req->src);
+
+ do {
+ u32 n = scatterwalk_clamp(&walk, len);
+ u8 *p;
+
+ if (!n) {
+ scatterwalk_start(&walk, sg_next(walk.sg));
+ n = scatterwalk_clamp(&walk, len);
+ }
+ p = scatterwalk_map(&walk);
+
+ gcm_update_mac(dg, p, n, buf, &buf_count, ctx);
+ len -= n;
+
+ scatterwalk_unmap(p);
+ scatterwalk_advance(&walk, n);
+ scatterwalk_done(&walk, 0, len);
+ } while (len);
+
+ if (buf_count) {
+ memset(&buf[buf_count], 0, GHASH_BLOCK_SIZE - buf_count);
+ ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL);
+ }
+}
+
+static void gcm_final(struct aead_request *req, struct gcm_aes_ctx *ctx,
+ u64 dg[], u8 tag[], int cryptlen)
+{
+ u8 mac[AES_BLOCK_SIZE];
+ u128 lengths;
+
+ lengths.a = cpu_to_be64(req->assoclen * 8);
+ lengths.b = cpu_to_be64(cryptlen * 8);
+
+ ghash_do_update(1, dg, (void *)&lengths, &ctx->ghash_key, NULL);
+
+ put_unaligned_be64(dg[1], mac);
+ put_unaligned_be64(dg[0], mac + 8);
+
+ crypto_xor(tag, mac, AES_BLOCK_SIZE);
+}
+
+static int gcm_encrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+ struct skcipher_walk walk;
+ u8 iv[AES_BLOCK_SIZE];
+ u8 ks[AES_BLOCK_SIZE];
+ u8 tag[AES_BLOCK_SIZE];
+ u64 dg[2] = {};
+ int err;
+
+ if (req->assoclen)
+ gcm_calculate_auth_mac(req, dg);
+
+ memcpy(iv, req->iv, GCM_IV_SIZE);
+ put_unaligned_be32(1, iv + GCM_IV_SIZE);
+
+ if (likely(may_use_simd())) {
+ kernel_neon_begin();
+
+ pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
+ num_rounds(&ctx->aes_key));
+ put_unaligned_be32(2, iv + GCM_IV_SIZE);
+ pmull_gcm_encrypt_block(ks, iv, NULL,
+ num_rounds(&ctx->aes_key));
+ put_unaligned_be32(3, iv + GCM_IV_SIZE);
+
+ err = skcipher_walk_aead_encrypt(&walk, req, true);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
+ walk.src.virt.addr, &ctx->ghash_key,
+ iv, num_rounds(&ctx->aes_key), ks);
+
+ 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);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int blocks = walk.nbytes / AES_BLOCK_SIZE;
+ u8 *dst = walk.dst.virt.addr;
+ u8 *src = walk.src.virt.addr;
+
+ do {
+ __aes_arm64_encrypt(ctx->aes_key.key_enc,
+ ks, iv,
+ num_rounds(&ctx->aes_key));
+ crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE);
+ crypto_inc(iv, AES_BLOCK_SIZE);
+
+ dst += AES_BLOCK_SIZE;
+ src += AES_BLOCK_SIZE;
+ } while (--blocks > 0);
+
+ ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg,
+ walk.dst.virt.addr, &ctx->ghash_key,
+ NULL);
+
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (walk.nbytes)
+ __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv,
+ num_rounds(&ctx->aes_key));
+ }
+
+ /* handle the tail */
+ if (walk.nbytes) {
+ u8 buf[GHASH_BLOCK_SIZE];
+
+ crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks,
+ walk.nbytes);
+
+ memcpy(buf, walk.dst.virt.addr, walk.nbytes);
+ memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes);
+ ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL);
+
+ err = skcipher_walk_done(&walk, 0);
+ }
+
+ if (err)
+ return err;
+
+ gcm_final(req, ctx, dg, tag, req->cryptlen);
+
+ /* copy authtag to end of dst */
+ scatterwalk_map_and_copy(tag, req->dst, req->assoclen + req->cryptlen,
+ crypto_aead_authsize(aead), 1);
+
+ return 0;
+}
+
+static int gcm_decrypt(struct aead_request *req)
+{
+ struct crypto_aead *aead = crypto_aead_reqtfm(req);
+ struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
+ unsigned int authsize = crypto_aead_authsize(aead);
+ struct skcipher_walk walk;
+ u8 iv[AES_BLOCK_SIZE];
+ u8 tag[AES_BLOCK_SIZE];
+ u8 buf[GHASH_BLOCK_SIZE];
+ u64 dg[2] = {};
+ int err;
+
+ if (req->assoclen)
+ gcm_calculate_auth_mac(req, dg);
+
+ memcpy(iv, req->iv, GCM_IV_SIZE);
+ put_unaligned_be32(1, iv + GCM_IV_SIZE);
+
+ if (likely(may_use_simd())) {
+ kernel_neon_begin();
+
+ pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
+ num_rounds(&ctx->aes_key));
+ put_unaligned_be32(2, iv + GCM_IV_SIZE);
+
+ err = skcipher_walk_aead_decrypt(&walk, req, true);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int blocks = walk.nbytes / AES_BLOCK_SIZE;
+
+ pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
+ walk.src.virt.addr, &ctx->ghash_key,
+ iv, num_rounds(&ctx->aes_key));
+
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ 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);
+
+ while (walk.nbytes >= AES_BLOCK_SIZE) {
+ int blocks = walk.nbytes / AES_BLOCK_SIZE;
+ u8 *dst = walk.dst.virt.addr;
+ u8 *src = walk.src.virt.addr;
+
+ ghash_do_update(blocks, dg, walk.src.virt.addr,
+ &ctx->ghash_key, NULL);
+
+ do {
+ __aes_arm64_encrypt(ctx->aes_key.key_enc,
+ buf, iv,
+ num_rounds(&ctx->aes_key));
+ crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE);
+ crypto_inc(iv, AES_BLOCK_SIZE);
+
+ dst += AES_BLOCK_SIZE;
+ src += AES_BLOCK_SIZE;
+ } while (--blocks > 0);
+
+ err = skcipher_walk_done(&walk,
+ walk.nbytes % AES_BLOCK_SIZE);
+ }
+ if (walk.nbytes)
+ __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv,
+ num_rounds(&ctx->aes_key));
+ }
+
+ /* handle the tail */
+ if (walk.nbytes) {
+ memcpy(buf, walk.src.virt.addr, walk.nbytes);
+ memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes);
+ ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL);
+
+ crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv,
+ walk.nbytes);
+
+ err = skcipher_walk_done(&walk, 0);
+ }
+
+ if (err)
+ return err;
+
+ gcm_final(req, ctx, dg, tag, req->cryptlen - authsize);
+
+ /* compare calculated auth tag with the stored one */
+ scatterwalk_map_and_copy(buf, req->src,
+ req->assoclen + req->cryptlen - authsize,
+ authsize, 0);
+
+ if (crypto_memneq(tag, buf, authsize))
+ return -EBADMSG;
+ return 0;
+}
+
+static struct aead_alg gcm_aes_alg = {
+ .ivsize = GCM_IV_SIZE,
+ .chunksize = AES_BLOCK_SIZE,
+ .maxauthsize = AES_BLOCK_SIZE,
+ .setkey = gcm_setkey,
+ .setauthsize = gcm_setauthsize,
+ .encrypt = gcm_encrypt,
+ .decrypt = gcm_decrypt,
+
+ .base.cra_name = "gcm(aes)",
+ .base.cra_driver_name = "gcm-aes-ce",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct gcm_aes_ctx),
+ .base.cra_module = THIS_MODULE,
};
static int __init ghash_ce_mod_init(void)
{
- return crypto_register_shash(&ghash_alg);
+ int ret;
+
+ if (!(elf_hwcap & HWCAP_ASIMD))
+ return -ENODEV;
+
+ if (elf_hwcap & HWCAP_PMULL)
+ pmull_ghash_update = pmull_ghash_update_p64;
+
+ else
+ pmull_ghash_update = pmull_ghash_update_p8;
+
+ ret = crypto_register_shash(&ghash_alg);
+ if (ret)
+ return ret;
+
+ if (elf_hwcap & HWCAP_PMULL) {
+ ret = crypto_register_aead(&gcm_aes_alg);
+ if (ret)
+ crypto_unregister_shash(&ghash_alg);
+ }
+ return ret;
}
static void __exit ghash_ce_mod_exit(void)
{
crypto_unregister_shash(&ghash_alg);
+ crypto_unregister_aead(&gcm_aes_alg);
}
-module_cpu_feature_match(PMULL, ghash_ce_mod_init);
+static const struct cpu_feature ghash_cpu_feature[] = {
+ { cpu_feature(PMULL) }, { }
+};
+MODULE_DEVICE_TABLE(cpu, ghash_cpu_feature);
+
+module_init(ghash_ce_mod_init);
module_exit(ghash_ce_mod_exit);
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index ea319c055f5d..efbeb3e0dcfb 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -1,7 +1,7 @@
/*
* sha1-ce-glue.c - SHA-1 secure hash using ARMv8 Crypto Extensions
*
- * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
#include <asm/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
@@ -37,8 +38,11 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
{
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+ if (!may_use_simd())
+ return crypto_sha1_update(desc, data, len);
+
sctx->finalize = 0;
- kernel_neon_begin_partial(16);
+ kernel_neon_begin();
sha1_base_do_update(desc, data, len,
(sha1_block_fn *)sha1_ce_transform);
kernel_neon_end();
@@ -52,13 +56,16 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
+ if (!may_use_simd())
+ return crypto_sha1_finup(desc, data, len, out);
+
/*
* Allow the asm code to perform the finalization if there is no
* partial data and the input is a round multiple of the block size.
*/
sctx->finalize = finalize;
- kernel_neon_begin_partial(16);
+ kernel_neon_begin();
sha1_base_do_update(desc, data, len,
(sha1_block_fn *)sha1_ce_transform);
if (!finalize)
@@ -71,8 +78,11 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out)
{
struct sha1_ce_state *sctx = shash_desc_ctx(desc);
+ if (!may_use_simd())
+ return crypto_sha1_finup(desc, NULL, 0, out);
+
sctx->finalize = 0;
- kernel_neon_begin_partial(16);
+ kernel_neon_begin();
sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform);
kernel_neon_end();
return sha1_base_finish(desc, out);
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 0ed9486f75dd..fd1ff2b13dfa 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -1,7 +1,7 @@
/*
* sha2-ce-glue.c - SHA-224/SHA-256 using ARMv8 Crypto Extensions
*
- * Copyright (C) 2014 Linaro Ltd <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2017 Linaro Ltd <ard.biesheuvel@linaro.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
@@ -9,6 +9,7 @@
*/
#include <asm/neon.h>
+#include <asm/simd.h>
#include <asm/unaligned.h>
#include <crypto/internal/hash.h>
#include <crypto/sha.h>
@@ -34,13 +35,19 @@ const u32 sha256_ce_offsetof_count = offsetof(struct sha256_ce_state,
const u32 sha256_ce_offsetof_finalize = offsetof(struct sha256_ce_state,
finalize);
+asmlinkage void sha256_block_data_order(u32 *digest, u8 const *src, int blocks);
+
static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+ if (!may_use_simd())
+ return sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha256_block_data_order);
+
sctx->finalize = 0;
- kernel_neon_begin_partial(28);
+ kernel_neon_begin();
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
@@ -54,13 +61,22 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
struct sha256_ce_state *sctx = shash_desc_ctx(desc);
bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
+ if (!may_use_simd()) {
+ if (len)
+ sha256_base_do_update(desc, data, len,
+ (sha256_block_fn *)sha256_block_data_order);
+ sha256_base_do_finalize(desc,
+ (sha256_block_fn *)sha256_block_data_order);
+ return sha256_base_finish(desc, out);
+ }
+
/*
* Allow the asm code to perform the finalization if there is no
* partial data and the input is a round multiple of the block size.
*/
sctx->finalize = finalize;
- kernel_neon_begin_partial(28);
+ kernel_neon_begin();
sha256_base_do_update(desc, data, len,
(sha256_block_fn *)sha2_ce_transform);
if (!finalize)
@@ -74,8 +90,14 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out)
{
struct sha256_ce_state *sctx = shash_desc_ctx(desc);
+ if (!may_use_simd()) {
+ sha256_base_do_finalize(desc,
+ (sha256_block_fn *)sha256_block_data_order);
+ return sha256_base_finish(desc, out);
+ }
+
sctx->finalize = 0;
- kernel_neon_begin_partial(28);
+ kernel_neon_begin();
sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform);
kernel_neon_end();
return sha256_base_finish(desc, out);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index a2226f841960..b064d925fe2a 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -29,6 +29,7 @@ MODULE_ALIAS_CRYPTO("sha256");
asmlinkage void sha256_block_data_order(u32 *digest, const void *data,
unsigned int num_blks);
+EXPORT_SYMBOL(sha256_block_data_order);
asmlinkage void sha256_block_neon(u32 *digest, const void *data,
unsigned int num_blks);
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index f81c7b685fc6..2326e39d5892 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -20,7 +20,6 @@ generic-y += rwsem.h
generic-y += segment.h
generic-y += serial.h
generic-y += set_memory.h
-generic-y += simd.h
generic-y += sizes.h
generic-y += switch_to.h
generic-y += trace_clock.h
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index 8cef47fa2218..b7e3f74822da 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -116,6 +116,8 @@ static inline void gic_write_bpr1(u32 val)
#define gic_read_typer(c) readq_relaxed(c)
#define gic_write_irouter(v, c) writeq_relaxed(v, c)
+#define gic_read_lpir(c) readq_relaxed(c)
+#define gic_write_lpir(v, c) writeq_relaxed(v, c)
#define gic_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
@@ -133,5 +135,10 @@ static inline void gic_write_bpr1(u32 val)
#define gicr_write_pendbaser(v, c) writeq_relaxed(v, c)
#define gicr_read_pendbaser(c) readq_relaxed(c)
+#define gits_write_vpropbaser(v, c) writeq_relaxed(v, c)
+
+#define gits_write_vpendbaser(v, c) writeq_relaxed(v, c)
+#define gits_read_vpendbaser(c) readq_relaxed(c)
+
#endif /* __ASSEMBLY__ */
#endif /* __ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index 74d08e44a651..a652ce0a5cb2 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -65,13 +65,13 @@ DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
u64 _val; \
if (needs_unstable_timer_counter_workaround()) { \
const struct arch_timer_erratum_workaround *wa; \
- preempt_disable(); \
+ preempt_disable_notrace(); \
wa = __this_cpu_read(timer_unstable_counter_workaround); \
if (wa && wa->read_##reg) \
_val = wa->read_##reg(); \
else \
_val = read_sysreg(reg); \
- preempt_enable(); \
+ preempt_enable_notrace(); \
} else { \
_val = read_sysreg(reg); \
} \
diff --git a/arch/arm64/include/asm/asm-bug.h b/arch/arm64/include/asm/asm-bug.h
new file mode 100644
index 000000000000..636e755bcdca
--- /dev/null
+++ b/arch/arm64/include/asm/asm-bug.h
@@ -0,0 +1,54 @@
+#ifndef __ASM_ASM_BUG_H
+/*
+ * Copyright (C) 2017 ARM Limited
+ *
+ * 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/>.
+ */
+#define __ASM_ASM_BUG_H
+
+#include <asm/brk-imm.h>
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
+#define __BUGVERBOSE_LOCATION(file, line) \
+ .pushsection .rodata.str,"aMS",@progbits,1; \
+ 2: .string file; \
+ .popsection; \
+ \
+ .long 2b - 0b; \
+ .short line;
+#else
+#define _BUGVERBOSE_LOCATION(file, line)
+#endif
+
+#ifdef CONFIG_GENERIC_BUG
+
+#define __BUG_ENTRY(flags) \
+ .pushsection __bug_table,"aw"; \
+ .align 2; \
+ 0: .long 1f - 0b; \
+_BUGVERBOSE_LOCATION(__FILE__, __LINE__) \
+ .short flags; \
+ .popsection; \
+ 1:
+#else
+#define __BUG_ENTRY(flags)
+#endif
+
+#define ASM_BUG_FLAGS(flags) \
+ __BUG_ENTRY(flags) \
+ brk BUG_BRK_IMM
+
+#define ASM_BUG() ASM_BUG_FLAGS(0)
+
+#endif /* __ASM_ASM_BUG_H */
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 1b67c3782d00..d58a6253c6ab 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -230,12 +230,18 @@ lr .req x30 // link register
.endm
/*
- * @dst: Result of per_cpu(sym, smp_processor_id())
+ * @dst: Result of per_cpu(sym, smp_processor_id()), can be SP for
+ * non-module code
* @sym: The name of the per-cpu variable
* @tmp: scratch register
*/
.macro adr_this_cpu, dst, sym, tmp
+#ifndef MODULE
+ adrp \tmp, \sym
+ add \dst, \tmp, #:lo12:\sym
+#else
adr_l \dst, \sym
+#endif
mrs \tmp, tpidr_el1
add \dst, \dst, \tmp
.endm
@@ -353,6 +359,12 @@ alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
alternative_else
dc civac, \kaddr
alternative_endif
+ .elseif (\op == cvap)
+alternative_if ARM64_HAS_DCPOP
+ sys 3, c7, c12, 1, \kaddr // dc cvap
+alternative_else
+ dc cvac, \kaddr
+alternative_endif
.else
dc \op, \kaddr
.endif
@@ -403,6 +415,17 @@ alternative_endif
.size __pi_##x, . - x; \
ENDPROC(x)
+/*
+ * Annotate a function as being unsuitable for kprobes.
+ */
+#ifdef CONFIG_KPROBES
+#define NOKPROBE(x) \
+ .pushsection "_kprobe_blacklist", "aw"; \
+ .quad x; \
+ .popsection;
+#else
+#define NOKPROBE(x)
+#endif
/*
* Emit a 64-bit absolute little endian symbol reference in a way that
* ensures that it will be resolved at build time, even when building a
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
index a02a57186f56..d7dc43752705 100644
--- a/arch/arm64/include/asm/bug.h
+++ b/arch/arm64/include/asm/bug.h
@@ -18,41 +18,12 @@
#ifndef _ARCH_ARM64_ASM_BUG_H
#define _ARCH_ARM64_ASM_BUG_H
-#include <asm/brk-imm.h>
+#include <linux/stringify.h>
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
-#define __BUGVERBOSE_LOCATION(file, line) \
- ".pushsection .rodata.str,\"aMS\",@progbits,1\n" \
- "2: .string \"" file "\"\n\t" \
- ".popsection\n\t" \
- \
- ".long 2b - 0b\n\t" \
- ".short " #line "\n\t"
-#else
-#define _BUGVERBOSE_LOCATION(file, line)
-#endif
-
-#ifdef CONFIG_GENERIC_BUG
-
-#define __BUG_ENTRY(flags) \
- ".pushsection __bug_table,\"aw\"\n\t" \
- ".align 2\n\t" \
- "0: .long 1f - 0b\n\t" \
-_BUGVERBOSE_LOCATION(__FILE__, __LINE__) \
- ".short " #flags "\n\t" \
- ".popsection\n" \
- "1: "
-#else
-#define __BUG_ENTRY(flags) ""
-#endif
+#include <asm/asm-bug.h>
#define __BUG_FLAGS(flags) \
- asm volatile ( \
- __BUG_ENTRY(flags) \
- "brk %[imm]" :: [imm] "i" (BUG_BRK_IMM) \
- );
-
+ asm volatile (__stringify(ASM_BUG_FLAGS(flags)));
#define BUG() do { \
__BUG_FLAGS(0); \
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d74a284abdc2..76d1cc85d5b1 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -67,7 +67,9 @@
*/
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
+extern void __inval_dcache_area(void *addr, size_t len);
extern void __clean_dcache_area_poc(void *addr, size_t len);
+extern void __clean_dcache_area_pop(void *addr, size_t len);
extern void __clean_dcache_area_pou(void *addr, size_t len);
extern long __flush_cache_user_range(unsigned long start, unsigned long end);
extern void sync_icache_aliases(void *kaddr, unsigned long len);
@@ -150,6 +152,6 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
{
}
-int set_memory_valid(unsigned long addr, unsigned long size, int enable);
+int set_memory_valid(unsigned long addr, int numpages, int enable);
#endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8d2272c6822c..8da621627d7c 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -39,7 +39,8 @@
#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18
#define ARM64_WORKAROUND_858921 19
#define ARM64_WORKAROUND_CAVIUM_30115 20
+#define ARM64_HAS_DCPOP 21
-#define ARM64_NCAPS 21
+#define ARM64_NCAPS 22
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 8f3043aba873..b93904b16fc2 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -3,7 +3,9 @@
#include <asm/boot.h>
#include <asm/cpufeature.h>
+#include <asm/fpsimd.h>
#include <asm/io.h>
+#include <asm/memory.h>
#include <asm/mmu_context.h>
#include <asm/neon.h>
#include <asm/ptrace.h>
@@ -20,8 +22,8 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
#define arch_efi_call_virt_setup() \
({ \
- kernel_neon_begin(); \
efi_virtmap_load(); \
+ __efi_fpsimd_begin(); \
})
#define arch_efi_call_virt(p, f, args...) \
@@ -33,8 +35,8 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
#define arch_efi_call_virt_teardown() \
({ \
+ __efi_fpsimd_end(); \
efi_virtmap_unload(); \
- kernel_neon_end(); \
})
#define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
@@ -48,6 +50,13 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
*/
#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */
+/*
+ * In some configurations (e.g. VMAP_STACK && 64K pages), stacks built into the
+ * kernel need greater alignment than we require the segments to be padded to.
+ */
+#define EFI_KIMG_ALIGN \
+ (SEGMENT_ALIGN > THREAD_ALIGN ? SEGMENT_ALIGN : THREAD_ALIGN)
+
/* on arm64, the FDT may be located anywhere in system RAM */
static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
{
@@ -81,6 +90,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
#define alloc_screen_info(x...) &screen_info
#define free_screen_info(x...)
+/* redeclare as 'hidden' so the compiler will generate relative references */
+extern struct screen_info screen_info __attribute__((__visibility__("hidden")));
+
static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
{
}
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index acae781f7359..33be513ef24c 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -114,10 +114,10 @@
/*
* This is the base location for PIE (ET_DYN with INTERP) loads. On
- * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * 64-bit, this is above 4GB to leave the entire 32-bit address
* space open for things that want to use the area for 32-bit pointers.
*/
-#define ELF_ET_DYN_BASE 0x100000000UL
+#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3)
#ifndef __ASSEMBLY__
@@ -139,7 +139,6 @@ typedef struct user_fpsimd_state elf_fpregset_t;
#define SET_PERSONALITY(ex) \
({ \
- clear_bit(TIF_32BIT, &current->mm->context.flags); \
clear_thread_flag(TIF_32BIT); \
current->personality &= ~READ_IMPLIES_EXEC; \
})
@@ -195,7 +194,6 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
*/
#define COMPAT_SET_PERSONALITY(ex) \
({ \
- set_bit(TIF_32BIT, &current->mm->context.flags); \
set_thread_flag(TIF_32BIT); \
})
#define COMPAT_ARCH_DLINFO
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 8cabd57b6348..66ed8b6b9976 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -77,16 +77,23 @@
#define ESR_ELx_EC_MASK (UL(0x3F) << ESR_ELx_EC_SHIFT)
#define ESR_ELx_EC(esr) (((esr) & ESR_ELx_EC_MASK) >> ESR_ELx_EC_SHIFT)
-#define ESR_ELx_IL (UL(1) << 25)
+#define ESR_ELx_IL_SHIFT (25)
+#define ESR_ELx_IL (UL(1) << ESR_ELx_IL_SHIFT)
#define ESR_ELx_ISS_MASK (ESR_ELx_IL - 1)
/* ISS field definitions shared by different classes */
-#define ESR_ELx_WNR (UL(1) << 6)
+#define ESR_ELx_WNR_SHIFT (6)
+#define ESR_ELx_WNR (UL(1) << ESR_ELx_WNR_SHIFT)
/* Shared ISS field definitions for Data/Instruction aborts */
-#define ESR_ELx_FnV (UL(1) << 10)
-#define ESR_ELx_EA (UL(1) << 9)
-#define ESR_ELx_S1PTW (UL(1) << 7)
+#define ESR_ELx_SET_SHIFT (11)
+#define ESR_ELx_SET_MASK (UL(3) << ESR_ELx_SET_SHIFT)
+#define ESR_ELx_FnV_SHIFT (10)
+#define ESR_ELx_FnV (UL(1) << ESR_ELx_FnV_SHIFT)
+#define ESR_ELx_EA_SHIFT (9)
+#define ESR_ELx_EA (UL(1) << ESR_ELx_EA_SHIFT)
+#define ESR_ELx_S1PTW_SHIFT (7)
+#define ESR_ELx_S1PTW (UL(1) << ESR_ELx_S1PTW_SHIFT)
/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
#define ESR_ELx_FSC (0x3F)
@@ -97,15 +104,20 @@
#define ESR_ELx_FSC_PERM (0x0C)
/* ISS field definitions for Data Aborts */
-#define ESR_ELx_ISV (UL(1) << 24)
+#define ESR_ELx_ISV_SHIFT (24)
+#define ESR_ELx_ISV (UL(1) << ESR_ELx_ISV_SHIFT)
#define ESR_ELx_SAS_SHIFT (22)
#define ESR_ELx_SAS (UL(3) << ESR_ELx_SAS_SHIFT)
-#define ESR_ELx_SSE (UL(1) << 21)
+#define ESR_ELx_SSE_SHIFT (21)
+#define ESR_ELx_SSE (UL(1) << ESR_ELx_SSE_SHIFT)
#define ESR_ELx_SRT_SHIFT (16)
#define ESR_ELx_SRT_MASK (UL(0x1F) << ESR_ELx_SRT_SHIFT)
-#define ESR_ELx_SF (UL(1) << 15)
-#define ESR_ELx_AR (UL(1) << 14)
-#define ESR_ELx_CM (UL(1) << 8)
+#define ESR_ELx_SF_SHIFT (15)
+#define ESR_ELx_SF (UL(1) << ESR_ELx_SF_SHIFT)
+#define ESR_ELx_AR_SHIFT (14)
+#define ESR_ELx_AR (UL(1) << ESR_ELx_AR_SHIFT)
+#define ESR_ELx_CM_SHIFT (8)
+#define ESR_ELx_CM (UL(1) << ESR_ELx_CM_SHIFT)
/* ISS field definitions for exceptions taken in to Hyp */
#define ESR_ELx_CV (UL(1) << 24)
@@ -157,9 +169,10 @@
/*
* User space cache operations have the following sysreg encoding
* in System instructions.
- * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0)
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 14 }, WRITE (L=0)
*/
#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAP 12
#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11
#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10
#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU 5
@@ -209,6 +222,13 @@
#ifndef __ASSEMBLY__
#include <asm/types.h>
+static inline bool esr_is_data_abort(u32 esr)
+{
+ const u32 ec = ESR_ELx_EC(esr);
+
+ return ec == ESR_ELx_EC_DABT_LOW || ec == ESR_ELx_EC_DABT_CUR;
+}
+
const char *esr_get_class_string(u32 esr);
#endif /* __ASSEMBLY */
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index 50f559f574fe..410c48163c6a 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -41,16 +41,6 @@ struct fpsimd_state {
unsigned int cpu;
};
-/*
- * Struct for stacking the bottom 'n' FP/SIMD registers.
- */
-struct fpsimd_partial_state {
- u32 fpsr;
- u32 fpcr;
- u32 num_regs;
- __uint128_t vregs[32];
-};
-
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/* Masks for extracting the FPSR and FPCR from the FPSCR */
@@ -77,9 +67,9 @@ extern void fpsimd_update_current_state(struct fpsimd_state *state);
extern void fpsimd_flush_task_state(struct task_struct *target);
-extern void fpsimd_save_partial_state(struct fpsimd_partial_state *state,
- u32 num_regs);
-extern void fpsimd_load_partial_state(struct fpsimd_partial_state *state);
+/* For use by EFI runtime services calls only */
+extern void __efi_fpsimd_begin(void);
+extern void __efi_fpsimd_end(void);
#endif
diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h
index a2daf1293028..0f5fdd388b0d 100644
--- a/arch/arm64/include/asm/fpsimdmacros.h
+++ b/arch/arm64/include/asm/fpsimdmacros.h
@@ -75,59 +75,3 @@
ldr w\tmpnr, [\state, #16 * 2 + 4]
fpsimd_restore_fpcr x\tmpnr, \state
.endm
-
-.macro fpsimd_save_partial state, numnr, tmpnr1, tmpnr2
- mrs x\tmpnr1, fpsr
- str w\numnr, [\state, #8]
- mrs x\tmpnr2, fpcr
- stp w\tmpnr1, w\tmpnr2, [\state]
- adr x\tmpnr1, 0f
- add \state, \state, x\numnr, lsl #4
- sub x\tmpnr1, x\tmpnr1, x\numnr, lsl #1
- br x\tmpnr1
- stp q30, q31, [\state, #-16 * 30 - 16]
- stp q28, q29, [\state, #-16 * 28 - 16]
- stp q26, q27, [\state, #-16 * 26 - 16]
- stp q24, q25, [\state, #-16 * 24 - 16]
- stp q22, q23, [\state, #-16 * 22 - 16]
- stp q20, q21, [\state, #-16 * 20 - 16]
- stp q18, q19, [\state, #-16 * 18 - 16]
- stp q16, q17, [\state, #-16 * 16 - 16]
- stp q14, q15, [\state, #-16 * 14 - 16]
- stp q12, q13, [\state, #-16 * 12 - 16]
- stp q10, q11, [\state, #-16 * 10 - 16]
- stp q8, q9, [\state, #-16 * 8 - 16]
- stp q6, q7, [\state, #-16 * 6 - 16]
- stp q4, q5, [\state, #-16 * 4 - 16]
- stp q2, q3, [\state, #-16 * 2 - 16]
- stp q0, q1, [\state, #-16 * 0 - 16]
-0:
-.endm
-
-.macro fpsimd_restore_partial state, tmpnr1, tmpnr2
- ldp w\tmpnr1, w\tmpnr2, [\state]
- msr fpsr, x\tmpnr1
- fpsimd_restore_fpcr x\tmpnr2, x\tmpnr1
- adr x\tmpnr1, 0f
- ldr w\tmpnr2, [\state, #8]
- add \state, \state, x\tmpnr2, lsl #4
- sub x\tmpnr1, x\tmpnr1, x\tmpnr2, lsl #1
- br x\tmpnr1
- ldp q30, q31, [\state, #-16 * 30 - 16]
- ldp q28, q29, [\state, #-16 * 28 - 16]
- ldp q26, q27, [\state, #-16 * 26 - 16]
- ldp q24, q25, [\state, #-16 * 24 - 16]
- ldp q22, q23, [\state, #-16 * 22 - 16]
- ldp q20, q21, [\state, #-16 * 20 - 16]
- ldp q18, q19, [\state, #-16 * 18 - 16]
- ldp q16, q17, [\state, #-16 * 16 - 16]
- ldp q14, q15, [\state, #-16 * 14 - 16]
- ldp q12, q13, [\state, #-16 * 12 - 16]
- ldp q10, q11, [\state, #-16 * 10 - 16]
- ldp q8, q9, [\state, #-16 * 8 - 16]
- ldp q6, q7, [\state, #-16 * 6 - 16]
- ldp q4, q5, [\state, #-16 * 4 - 16]
- ldp q2, q3, [\state, #-16 * 2 - 16]
- ldp q0, q1, [\state, #-16 * 0 - 16]
-0:
-.endm
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index f32b42e8725d..5bb2fd4674e7 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -48,20 +48,10 @@ do { \
} while (0)
static inline int
-futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
{
- int op = (encoded_op >> 28) & 7;
- int cmp = (encoded_op >> 24) & 15;
- int oparg = (int)(encoded_op << 8) >> 20;
- int cmparg = (int)(encoded_op << 20) >> 20;
int oldval = 0, ret, tmp;
- if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
- oparg = 1U << (oparg & 0x1f);
-
- if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
- return -EFAULT;
-
pagefault_disable();
switch (op) {
@@ -91,17 +81,9 @@ futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
pagefault_enable();
- if (!ret) {
- switch (cmp) {
- case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
- case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
- case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
- case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
- case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
- case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
- default: ret = -ENOSYS;
- }
- }
+ if (!ret)
+ *oval = oldval;
+
return ret;
}
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 793bd73b0d07..1dca41bea16a 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -18,7 +18,6 @@
#ifndef __ASM_HUGETLB_H
#define __ASM_HUGETLB_H
-#include <asm-generic/hugetlb.h>
#include <asm/page.h>
static inline pte_t huge_ptep_get(pte_t *ptep)
@@ -82,6 +81,14 @@ extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
+extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz);
+#define huge_pte_clear huge_pte_clear
+extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz);
+#define set_huge_swap_pte_at set_huge_swap_pte_at
+
+#include <asm-generic/hugetlb.h>
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
static inline bool gigantic_page_supported(void) { return true; }
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index b77197d941fc..5e6f77239064 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -1,45 +1,12 @@
#ifndef __ASM_IRQ_H
#define __ASM_IRQ_H
-#define IRQ_STACK_SIZE THREAD_SIZE
-#define IRQ_STACK_START_SP THREAD_START_SP
-
#ifndef __ASSEMBLER__
-#include <linux/percpu.h>
-
#include <asm-generic/irq.h>
-#include <asm/thread_info.h>
struct pt_regs;
-DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
-
-/*
- * The highest address on the stack, and the first to be used. Used to
- * find the dummy-stack frame put down by el?_irq() in entry.S, which
- * is structured as follows:
- *
- * ------------
- * | | <- irq_stack_ptr
- * top ------------
- * | x19 | <- irq_stack_ptr - 0x08
- * ------------
- * | x29 | <- irq_stack_ptr - 0x10
- * ------------
- *
- * where x19 holds a copy of the task stack pointer where the struct pt_regs
- * from kernel_entry can be found.
- *
- */
-#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP)
-
-/*
- * The offset from irq_stack_ptr where entry.S will store the original
- * stack pointer. Used by unwind_frame() and dump_backtrace().
- */
-#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08)))
-
extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
static inline int nr_legacy_irqs(void)
@@ -47,14 +14,5 @@ static inline int nr_legacy_irqs(void)
return 0;
}
-static inline bool on_irq_stack(unsigned long sp, int cpu)
-{
- /* variable names the same as kernel/stacktrace.c */
- unsigned long low = (unsigned long)per_cpu(irq_stack, cpu);
- unsigned long high = low + IRQ_STACK_START_SP;
-
- return (low <= sp && sp <= high);
-}
-
#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index d68630007b14..e923b58606e2 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -326,12 +326,6 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
-/* We do not have shadow page tables, hence the empty hooks */
-static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
- unsigned long address)
-{
-}
-
struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
void kvm_arm_halt_guest(struct kvm *kvm);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index a89cc22abadc..672c8684d5c2 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -175,18 +175,15 @@ static inline pmd_t kvm_s2pmd_mkwrite(pmd_t pmd)
static inline void kvm_set_s2pte_readonly(pte_t *pte)
{
- pteval_t pteval;
- unsigned long tmp;
-
- asm volatile("// kvm_set_s2pte_readonly\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " and %0, %0, %3 // clear PTE_S2_RDWR\n"
- " orr %0, %0, %4 // set PTE_S2_RDONLY\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*pte))
- : "L" (~PTE_S2_RDWR), "L" (PTE_S2_RDONLY));
+ pteval_t old_pteval, pteval;
+
+ pteval = READ_ONCE(pte_val(*pte));
+ do {
+ old_pteval = pteval;
+ pteval &= ~PTE_S2_RDWR;
+ pteval |= PTE_S2_RDONLY;
+ pteval = cmpxchg_relaxed(&pte_val(*pte), old_pteval, pteval);
+ } while (pteval != old_pteval);
}
static inline bool kvm_s2pte_readonly(pte_t *pte)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index ef39dcb9ca6a..3585a5e26151 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -25,6 +25,7 @@
#include <linux/const.h>
#include <linux/types.h>
#include <asm/bug.h>
+#include <asm/page-def.h>
#include <asm/sizes.h>
/*
@@ -103,6 +104,58 @@
#define KASAN_SHADOW_SIZE (0)
#endif
+#define MIN_THREAD_SHIFT 14
+
+/*
+ * VMAP'd stacks are allocated at page granularity, so we must ensure that such
+ * stacks are a multiple of page size.
+ */
+#if defined(CONFIG_VMAP_STACK) && (MIN_THREAD_SHIFT < PAGE_SHIFT)
+#define THREAD_SHIFT PAGE_SHIFT
+#else
+#define THREAD_SHIFT MIN_THREAD_SHIFT
+#endif
+
+#if THREAD_SHIFT >= PAGE_SHIFT
+#define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT)
+#endif
+
+#define THREAD_SIZE (UL(1) << THREAD_SHIFT)
+
+/*
+ * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by
+ * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry
+ * assembly.
+ */
+#ifdef CONFIG_VMAP_STACK
+#define THREAD_ALIGN (2 * THREAD_SIZE)
+#else
+#define THREAD_ALIGN THREAD_SIZE
+#endif
+
+#define IRQ_STACK_SIZE THREAD_SIZE
+
+#define OVERFLOW_STACK_SIZE SZ_4K
+
+/*
+ * Alignment of kernel segments (e.g. .text, .data).
+ */
+#if defined(CONFIG_DEBUG_ALIGN_RODATA)
+/*
+ * 4 KB granule: 1 level 2 entry
+ * 16 KB granule: 128 level 3 entries, with contiguous bit
+ * 64 KB granule: 32 level 3 entries, with contiguous bit
+ */
+#define SEGMENT_ALIGN SZ_2M
+#else
+/*
+ * 4 KB granule: 16 level 3 entries, with contiguous bit
+ * 16 KB granule: 4 level 3 entries, without contiguous bit
+ * 64 KB granule: 1 level 3 entry
+ */
+#define SEGMENT_ALIGN SZ_64K
+#endif
+
/*
* Memory types available.
*/
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 5468c834b072..0d34bf0a89c7 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -16,6 +16,8 @@
#ifndef __ASM_MMU_H
#define __ASM_MMU_H
+#define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */
+
typedef struct {
atomic64_t id;
void *vdso;
diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index ad4cdc966c0f..f922eaf780f9 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -8,12 +8,22 @@
* published by the Free Software Foundation.
*/
+#ifndef __ASM_NEON_H
+#define __ASM_NEON_H
+
#include <linux/types.h>
#include <asm/fpsimd.h>
#define cpu_has_neon() system_supports_fpsimd()
-#define kernel_neon_begin() kernel_neon_begin_partial(32)
-
-void kernel_neon_begin_partial(u32 num_regs);
+void kernel_neon_begin(void);
void kernel_neon_end(void);
+
+/*
+ * Temporary macro to allow the crypto code to compile. Note that the
+ * semantics of kernel_neon_begin_partial() are now different from the
+ * original as it does not allow being called in an interrupt context.
+ */
+#define kernel_neon_begin_partial(num_regs) kernel_neon_begin()
+
+#endif /* ! __ASM_NEON_H */
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index bf466d1876e3..ef7b23863a7c 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -7,9 +7,6 @@
#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2)
-/* currently, arm64 implements flat NUMA topology */
-#define parent_node(node) (node)
-
int __node_distance(int from, int to);
#define node_distance(a, b) __node_distance(a, b)
diff --git a/arch/arm64/include/asm/page-def.h b/arch/arm64/include/asm/page-def.h
new file mode 100644
index 000000000000..01591a29dc2e
--- /dev/null
+++ b/arch/arm64/include/asm/page-def.h
@@ -0,0 +1,34 @@
+/*
+ * Based on arch/arm/include/asm/page.h
+ *
+ * Copyright (C) 1995-2003 Russell King
+ * Copyright (C) 2017 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_PAGE_DEF_H
+#define __ASM_PAGE_DEF_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+/* CONT_SHIFT determines the number of pages which can be tracked together */
+#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT
+#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT
+#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#define CONT_SIZE (_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT))
+#define CONT_MASK (~(CONT_SIZE-1))
+
+#endif /* __ASM_PAGE_DEF_H */
diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h
index 8472c6def5ef..60d02c81a3a2 100644
--- a/arch/arm64/include/asm/page.h
+++ b/arch/arm64/include/asm/page.h
@@ -19,17 +19,7 @@
#ifndef __ASM_PAGE_H
#define __ASM_PAGE_H
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-/* CONT_SHIFT determines the number of pages which can be tracked together */
-#define PAGE_SHIFT CONFIG_ARM64_PAGE_SHIFT
-#define CONT_SHIFT CONFIG_ARM64_CONT_SHIFT
-#define PAGE_SIZE (_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
-
-#define CONT_SIZE (_AC(1, UL) << (CONT_SHIFT + PAGE_SHIFT))
-#define CONT_MASK (~(CONT_SIZE-1))
+#include <asm/page-def.h>
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2142c7726e76..0a5635fb0ef9 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -63,23 +63,21 @@
#define PAGE_S2 __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_NORMAL) | PTE_S2_RDONLY)
#define PAGE_S2_DEVICE __pgprot(PROT_DEFAULT | PTE_S2_MEMATTR(MT_S2_DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_UXN)
-#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_PXN | PTE_UXN)
+#define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_PXN | PTE_UXN)
#define PAGE_SHARED __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
-#define PAGE_COPY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_COPY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
-#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
+#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
+#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
+#define __P010 PAGE_READONLY
+#define __P011 PAGE_READONLY
#define __P100 PAGE_EXECONLY
#define __P101 PAGE_READONLY_EXEC
-#define __P110 PAGE_COPY_EXEC
-#define __P111 PAGE_COPY_EXEC
+#define __P110 PAGE_READONLY_EXEC
+#define __P111 PAGE_READONLY_EXEC
#define __S000 PAGE_NONE
#define __S001 PAGE_READONLY
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6eae342ced6b..bc4e92337d16 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -39,6 +39,7 @@
#ifndef __ASSEMBLY__
+#include <asm/cmpxchg.h>
#include <asm/fixmap.h>
#include <linux/mmdebug.h>
@@ -84,11 +85,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
(__boundary - 1 < (end) - 1) ? __boundary : (end); \
})
-#ifdef CONFIG_ARM64_HW_AFDBM
#define pte_hw_dirty(pte) (pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
-#else
-#define pte_hw_dirty(pte) (0)
-#endif
#define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY))
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
@@ -124,12 +121,16 @@ static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot)
static inline pte_t pte_wrprotect(pte_t pte)
{
- return clear_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = clear_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = set_pte_bit(pte, __pgprot(PTE_RDONLY));
+ return pte;
}
static inline pte_t pte_mkwrite(pte_t pte)
{
- return set_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = set_pte_bit(pte, __pgprot(PTE_WRITE));
+ pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+ return pte;
}
static inline pte_t pte_mkclean(pte_t pte)
@@ -168,11 +169,6 @@ static inline pte_t pte_mknoncont(pte_t pte)
return clear_pte_bit(pte, __pgprot(PTE_CONT));
}
-static inline pte_t pte_clear_rdonly(pte_t pte)
-{
- return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
-}
-
static inline pte_t pte_mkpresent(pte_t pte)
{
return set_pte_bit(pte, __pgprot(PTE_VALID));
@@ -220,22 +216,15 @@ extern void __sync_icache_dcache(pte_t pteval, unsigned long addr);
static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
- if (pte_present(pte)) {
- if (pte_sw_dirty(pte) && pte_write(pte))
- pte_val(pte) &= ~PTE_RDONLY;
- else
- pte_val(pte) |= PTE_RDONLY;
- if (pte_user_exec(pte) && !pte_special(pte))
- __sync_icache_dcache(pte, addr);
- }
+ if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
+ __sync_icache_dcache(pte, addr);
/*
* If the existing pte is valid, check for potential race with
* hardware updates of the pte (ptep_set_access_flags safely changes
* valid ptes without going through an invalid entry).
*/
- if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
- pte_valid(*ptep) && pte_valid(pte)) {
+ if (pte_valid(*ptep) && pte_valid(pte)) {
VM_WARN_ONCE(!pte_young(pte),
"%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
__func__, pte_val(*ptep), pte_val(pte));
@@ -571,7 +560,6 @@ static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
}
-#ifdef CONFIG_ARM64_HW_AFDBM
#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
@@ -593,20 +581,17 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
static inline int __ptep_test_and_clear_young(pte_t *ptep)
{
- pteval_t pteval;
- unsigned int tmp, res;
+ pte_t old_pte, pte;
- asm volatile("// __ptep_test_and_clear_young\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " ubfx %w3, %w0, %5, #1 // extract PTE_AF (young)\n"
- " and %0, %0, %4 // clear PTE_AF\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)), "=&r" (res)
- : "L" (~PTE_AF), "I" (ilog2(PTE_AF)));
+ pte = READ_ONCE(*ptep);
+ do {
+ old_pte = pte;
+ pte = pte_mkold(pte);
+ pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+ pte_val(old_pte), pte_val(pte));
+ } while (pte_val(pte) != pte_val(old_pte));
- return res;
+ return pte_young(pte);
}
static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
@@ -630,17 +615,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long address, pte_t *ptep)
{
- pteval_t old_pteval;
- unsigned int tmp;
-
- asm volatile("// ptep_get_and_clear\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " stxr %w1, xzr, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep)));
-
- return __pte(old_pteval);
+ return __pte(xchg_relaxed(&pte_val(*ptep), 0));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -653,27 +628,32 @@ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * ptep_set_wrprotect - mark read-only while trasferring potential hardware
- * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit.
+ * ptep_set_wrprotect - mark read-only while preserving the hardware update of
+ * the Access Flag.
*/
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
{
- pteval_t pteval;
- unsigned long tmp;
+ pte_t old_pte, pte;
- asm volatile("// ptep_set_wrprotect\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " tst %0, %4 // check for hw dirty (!PTE_RDONLY)\n"
- " csel %1, %3, xzr, eq // set PTE_DIRTY|PTE_RDONLY if dirty\n"
- " orr %0, %0, %1 // if !dirty, PTE_RDONLY is already set\n"
- " and %0, %0, %5 // clear PTE_WRITE/PTE_DBM\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
- : "r" (PTE_DIRTY|PTE_RDONLY), "L" (PTE_RDONLY), "L" (~PTE_WRITE)
- : "cc");
+ /*
+ * ptep_set_wrprotect() is only called on CoW mappings which are
+ * private (!VM_SHARED) with the pte either read-only (!PTE_WRITE &&
+ * PTE_RDONLY) or writable and software-dirty (PTE_WRITE &&
+ * !PTE_RDONLY && PTE_DIRTY); see is_cow_mapping() and
+ * protection_map[]. There is no race with the hardware update of the
+ * dirty state: clearing of PTE_RDONLY when PTE_WRITE (a.k.a. PTE_DBM)
+ * is set.
+ */
+ VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(*ptep),
+ "%s: potential race with hardware DBM", __func__);
+ pte = READ_ONCE(*ptep);
+ do {
+ old_pte = pte;
+ pte = pte_wrprotect(pte);
+ pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep),
+ pte_val(old_pte), pte_val(pte));
+ } while (pte_val(pte) != pte_val(old_pte));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -684,7 +664,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
ptep_set_wrprotect(mm, address, (pte_t *)pmdp);
}
#endif
-#endif /* CONFIG_ARM64_HW_AFDBM */
extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 64c9e78f9882..29adab8138c3 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -112,7 +112,7 @@ void tls_preserve_current_state(void);
static inline void start_thread_common(struct pt_regs *regs, unsigned long pc)
{
memset(regs, 0, sizeof(*regs));
- regs->syscallno = ~0UL;
+ forget_syscall(regs);
regs->pc = pc;
}
@@ -159,7 +159,7 @@ extern struct task_struct *cpu_switch_to(struct task_struct *prev,
struct task_struct *next);
#define task_pt_regs(p) \
- ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
+ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
#define KSTK_EIP(tsk) ((unsigned long)task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) user_stack_pointer(task_pt_regs(tsk))
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 11403fdd0a50..6069d66e0bc2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -72,8 +72,19 @@
#define COMPAT_PT_TEXT_ADDR 0x10000
#define COMPAT_PT_DATA_ADDR 0x10004
#define COMPAT_PT_TEXT_END_ADDR 0x10008
+
+/*
+ * If pt_regs.syscallno == NO_SYSCALL, then the thread is not executing
+ * a syscall -- i.e., its most recent entry into the kernel from
+ * userspace was not via SVC, or otherwise a tracer cancelled the syscall.
+ *
+ * This must have the value -1, for ABI compatibility with ptrace etc.
+ */
+#define NO_SYSCALL (-1)
+
#ifndef __ASSEMBLY__
#include <linux/bug.h>
+#include <linux/types.h>
/* sizeof(struct user) for AArch32 */
#define COMPAT_USER_SZ 296
@@ -116,11 +127,29 @@ struct pt_regs {
};
};
u64 orig_x0;
- u64 syscallno;
+#ifdef __AARCH64EB__
+ u32 unused2;
+ s32 syscallno;
+#else
+ s32 syscallno;
+ u32 unused2;
+#endif
+
u64 orig_addr_limit;
u64 unused; // maintain 16 byte alignment
+ u64 stackframe[2];
};
+static inline bool in_syscall(struct pt_regs const *regs)
+{
+ return regs->syscallno != NO_SYSCALL;
+}
+
+static inline void forget_syscall(struct pt_regs *regs)
+{
+ regs->syscallno = NO_SYSCALL;
+}
+
#define MAX_REG_OFFSET offsetof(struct pt_regs, pstate)
#define arch_has_single_step() (1)
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index eeaa97559bab..81abea0b7650 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -22,8 +22,6 @@
#define AARCH32_KERN_SIGRET_CODE_OFFSET 0x500
-extern const compat_ulong_t aarch32_sigret_code[6];
-
int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs);
int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
new file mode 100644
index 000000000000..fa8b3fe932e6
--- /dev/null
+++ b/arch/arm64/include/asm/simd.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#ifndef __ASM_SIMD_H
+#define __ASM_SIMD_H
+
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+DECLARE_PER_CPU(bool, kernel_neon_busy);
+
+/*
+ * may_use_simd - whether it is allowable at this time to issue SIMD
+ * instructions or access the SIMD register file
+ *
+ * Callers must not assume that the result remains true beyond the next
+ * preempt_enable() or return from softirq context.
+ */
+static __must_check inline bool may_use_simd(void)
+{
+ /*
+ * The raw_cpu_read() is racy if called with preemption enabled.
+ * This is not a bug: kernel_neon_busy is only set when
+ * preemption is disabled, so we cannot migrate to another CPU
+ * while it is set, nor can we migrate to a CPU where it is set.
+ * So, if we find it clear on some CPU then we're guaranteed to
+ * find it clear on any CPU we could migrate to.
+ *
+ * If we are in between kernel_neon_begin()...kernel_neon_end(),
+ * the flag will be set, but preemption is also disabled, so we
+ * can't migrate to another CPU and spuriously see it become
+ * false.
+ */
+ return !in_irq() && !irqs_disabled() && !in_nmi() &&
+ !raw_cpu_read(kernel_neon_busy);
+}
+
+#else /* ! CONFIG_KERNEL_MODE_NEON */
+
+static __must_check inline bool may_use_simd(void) {
+ return false;
+}
+
+#endif /* ! CONFIG_KERNEL_MODE_NEON */
+
+#endif
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 55f08c5acfad..f82b447bd34f 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -148,7 +148,7 @@ static inline void cpu_panic_kernel(void)
*/
bool cpus_are_stuck_in_kernel(void);
-extern void smp_send_crash_stop(void);
+extern void crash_smp_send_stop(void);
extern bool smp_crash_stop_failed(void);
#endif /* ifndef __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index cae331d553f8..95ad7102b63c 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -26,58 +26,6 @@
* The memory barriers are implicit with the load-acquire and store-release
* instructions.
*/
-static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
-{
- unsigned int tmp;
- arch_spinlock_t lockval;
- u32 owner;
-
- /*
- * Ensure prior spin_lock operations to other locks have completed
- * on this CPU before we test whether "lock" is locked.
- */
- smp_mb();
- owner = READ_ONCE(lock->owner) << 16;
-
- asm volatile(
-" sevl\n"
-"1: wfe\n"
-"2: ldaxr %w0, %2\n"
- /* Is the lock free? */
-" eor %w1, %w0, %w0, ror #16\n"
-" cbz %w1, 3f\n"
- /* Lock taken -- has there been a subsequent unlock->lock transition? */
-" eor %w1, %w3, %w0, lsl #16\n"
-" cbz %w1, 1b\n"
- /*
- * The owner has been updated, so there was an unlock->lock
- * transition that we missed. That means we can rely on the
- * store-release of the unlock operation paired with the
- * load-acquire of the lock operation to publish any of our
- * previous stores to the new lock owner and therefore don't
- * need to bother with the writeback below.
- */
-" b 4f\n"
-"3:\n"
- /*
- * Serialise against any concurrent lockers by writing back the
- * unlocked lock value
- */
- ARM64_LSE_ATOMIC_INSN(
- /* LL/SC */
-" stxr %w1, %w0, %2\n"
- __nops(2),
- /* LSE atomics */
-" mov %w1, %w0\n"
-" cas %w0, %w0, %2\n"
-" eor %w1, %w1, %w0\n")
- /* Somebody else wrote to the lock, GOTO 10 and reload the value */
-" cbnz %w1, 2b\n"
-"4:"
- : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
- : "r" (owner)
- : "memory");
-}
#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
@@ -176,7 +124,11 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
- smp_mb(); /* See arch_spin_unlock_wait */
+ /*
+ * 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));
}
@@ -358,14 +310,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
-/*
- * Accesses appearing in program order before a spin_lock() operation
- * can be reordered with accesses inside the critical section, by virtue
- * of arch_spin_lock being constructed using acquire semantics.
- *
- * In cases where this is problematic (e.g. try_to_wake_up), an
- * smp_mb__before_spinlock() can restore the required ordering.
- */
-#define smp_mb__before_spinlock() smp_mb()
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock() smp_mb()
#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 5b6eafccc5d8..6ad30776e984 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -16,11 +16,15 @@
#ifndef __ASM_STACKTRACE_H
#define __ASM_STACKTRACE_H
-struct task_struct;
+#include <linux/percpu.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/memory.h>
+#include <asm/ptrace.h>
struct stackframe {
unsigned long fp;
- unsigned long sp;
unsigned long pc;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
unsigned int graph;
@@ -32,4 +36,57 @@ extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
int (*fn)(struct stackframe *, void *), void *data);
extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk);
+DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
+
+static inline bool on_irq_stack(unsigned long sp)
+{
+ unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
+ unsigned long high = low + IRQ_STACK_SIZE;
+
+ if (!low)
+ return false;
+
+ return (low <= sp && sp < high);
+}
+
+static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp)
+{
+ unsigned long low = (unsigned long)task_stack_page(tsk);
+ unsigned long high = low + THREAD_SIZE;
+
+ return (low <= sp && sp < high);
+}
+
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+
+static inline bool on_overflow_stack(unsigned long sp)
+{
+ unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
+ unsigned long high = low + OVERFLOW_STACK_SIZE;
+
+ return (low <= sp && sp < high);
+}
+#else
+static inline bool on_overflow_stack(unsigned long sp) { return false; }
+#endif
+
+/*
+ * We can only safely access per-cpu stacks from current in a non-preemptible
+ * context.
+ */
+static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp)
+{
+ if (on_task_stack(tsk, sp))
+ return true;
+ if (tsk != current || preemptible())
+ return false;
+ if (on_irq_stack(sp))
+ return true;
+ if (on_overflow_stack(sp))
+ return true;
+
+ return false;
+}
+
#endif /* __ASM_STACKTRACE_H */
diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
index d0aa42907569..dd95d33a5bd5 100644
--- a/arch/arm64/include/asm/string.h
+++ b/arch/arm64/include/asm/string.h
@@ -52,6 +52,10 @@ extern void *__memset(void *, int, __kernel_size_t);
#define __HAVE_ARCH_MEMCMP
extern int memcmp(const void *, const void *, size_t);
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+#define __HAVE_ARCH_MEMCPY_FLUSHCACHE
+void memcpy_flushcache(void *dst, const void *src, size_t cnt);
+#endif
#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 248339e4aaf5..f707fed5886f 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -329,6 +329,7 @@
#define ID_AA64ISAR1_LRCPC_SHIFT 20
#define ID_AA64ISAR1_FCMA_SHIFT 16
#define ID_AA64ISAR1_JSCVT_SHIFT 12
+#define ID_AA64ISAR1_DPB_SHIFT 0
/* id_aa64pfr0 */
#define ID_AA64PFR0_GIC_SHIFT 24
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 46c3b93cf865..ddded6497a8a 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -23,19 +23,11 @@
#include <linux/compiler.h>
-#ifdef CONFIG_ARM64_4K_PAGES
-#define THREAD_SIZE_ORDER 2
-#elif defined(CONFIG_ARM64_16K_PAGES)
-#define THREAD_SIZE_ORDER 0
-#endif
-
-#define THREAD_SIZE 16384
-#define THREAD_START_SP (THREAD_SIZE - 16)
-
#ifndef __ASSEMBLY__
struct task_struct;
+#include <asm/memory.h>
#include <asm/stack_pointer.h>
#include <asm/types.h>
@@ -68,6 +60,9 @@ struct thread_info {
#define thread_saved_fp(tsk) \
((unsigned long)(tsk->thread.cpu_context.fp))
+void arch_setup_new_exec(void);
+#define arch_setup_new_exec arch_setup_new_exec
+
#endif
/*
@@ -86,6 +81,7 @@ struct thread_info {
#define TIF_NOTIFY_RESUME 2 /* callback before returning to user */
#define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */
#define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */
+#define TIF_FSCHECK 5 /* Check FS is USER_DS on return */
#define TIF_NOHZ 7
#define TIF_SYSCALL_TRACE 8
#define TIF_SYSCALL_AUDIT 9
@@ -107,11 +103,12 @@ struct thread_info {
#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
#define _TIF_SECCOMP (1 << TIF_SECCOMP)
#define _TIF_UPROBE (1 << TIF_UPROBE)
+#define _TIF_FSCHECK (1 << TIF_FSCHECK)
#define _TIF_32BIT (1 << TIF_32BIT)
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
- _TIF_UPROBE)
+ _TIF_UPROBE | _TIF_FSCHECK)
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h
index 02e9035b0685..d131501c6222 100644
--- a/arch/arm64/include/asm/traps.h
+++ b/arch/arm64/include/asm/traps.h
@@ -37,18 +37,11 @@ void unregister_undef_hook(struct undef_hook *hook);
void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static inline int __in_irqentry_text(unsigned long ptr)
{
return ptr >= (unsigned long)&__irqentry_text_start &&
ptr < (unsigned long)&__irqentry_text_end;
}
-#else
-static inline int __in_irqentry_text(unsigned long ptr)
-{
- return 0;
-}
-#endif
static inline int in_exception_text(unsigned long ptr)
{
@@ -60,4 +53,9 @@ static inline int in_exception_text(unsigned long ptr)
return in ? : __in_irqentry_text(ptr);
}
+static inline int in_entry_text(unsigned long ptr)
+{
+ return ptr >= (unsigned long)&__entry_text_start &&
+ ptr < (unsigned long)&__entry_text_end;
+}
#endif
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index fab46a0ea223..fc0f9eb66039 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -45,6 +45,9 @@ static inline void set_fs(mm_segment_t fs)
{
current_thread_info()->addr_limit = fs;
+ /* On user-mode return, check fs is correct */
+ set_thread_flag(TIF_FSCHECK);
+
/*
* Enable/disable UAO so that copy_to_user() etc can access
* kernel memory with the unprivileged instructions.
@@ -347,4 +350,16 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
extern __must_check long strnlen_user(const char __user *str, long n);
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+struct page;
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset, size_t len);
+extern unsigned long __must_check __copy_user_flushcache(void *to, const void __user *from, unsigned long n);
+
+static inline int __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+ kasan_check_write(dst, size);
+ return __copy_user_flushcache(dst, src, size);
+}
+#endif
+
#endif /* __ASM_UACCESS_H */
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 4e187ce2a811..4b9344cba83a 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -35,5 +35,6 @@
#define HWCAP_JSCVT (1 << 13)
#define HWCAP_FCMA (1 << 14)
#define HWCAP_LRCPC (1 << 15)
+#define HWCAP_DCPOP (1 << 16)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index e25c11e727fe..b3162715ed78 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -95,7 +95,7 @@ static int __init dt_scan_depth1_nodes(unsigned long node,
* __acpi_map_table() will be called before page_init(), so early_ioremap()
* or early_memremap() should be called here to for ACPI table mapping.
*/
-char *__init __acpi_map_table(unsigned long phys, unsigned long size)
+void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
{
if (!size)
return NULL;
@@ -103,7 +103,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
return early_memremap(phys, size);
}
-void __init __acpi_unmap_table(char *map, unsigned long size)
+void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
{
if (!map || !size)
return;
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b3bb7ef97bc8..71bf088f1e4b 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -75,6 +75,7 @@ int main(void)
DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0));
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit));
+ DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 9f9e0064c8c1..cd52d365d1f0 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -120,6 +120,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_LRCPC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_FCMA_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_JSCVT_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64ISAR1_DPB_SHIFT, 4, 0),
ARM64_FTR_END,
};
@@ -888,6 +889,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.min_field_value = 0,
.matches = has_no_fpsimd,
},
+#ifdef CONFIG_ARM64_PMEM
+ {
+ .desc = "Data cache clean to Point of Persistence",
+ .capability = ARM64_HAS_DCPOP,
+ .def_scope = SCOPE_SYSTEM,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64ISAR1_EL1,
+ .field_pos = ID_AA64ISAR1_DPB_SHIFT,
+ .min_field_value = 1,
+ },
+#endif
{},
};
@@ -916,6 +928,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index f495ee5049fd..311885962830 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -68,6 +68,7 @@ static const char *const hwcap_str[] = {
"jscvt",
"fcma",
"lrcpc",
+ "dcpop",
NULL
};
diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S
index c44a82f146b1..6a27cd6dbfa6 100644
--- a/arch/arm64/kernel/entry-fpsimd.S
+++ b/arch/arm64/kernel/entry-fpsimd.S
@@ -41,27 +41,3 @@ ENTRY(fpsimd_load_state)
fpsimd_restore x0, 8
ret
ENDPROC(fpsimd_load_state)
-
-#ifdef CONFIG_KERNEL_MODE_NEON
-
-/*
- * Save the bottom n FP registers.
- *
- * x0 - pointer to struct fpsimd_partial_state
- */
-ENTRY(fpsimd_save_partial_state)
- fpsimd_save_partial x0, 1, 8, 9
- ret
-ENDPROC(fpsimd_save_partial_state)
-
-/*
- * Load the bottom n FP registers.
- *
- * x0 - pointer to struct fpsimd_partial_state
- */
-ENTRY(fpsimd_load_partial_state)
- fpsimd_restore_partial x0, 8, 9
- ret
-ENDPROC(fpsimd_load_partial_state)
-
-#endif
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index b738880350f9..e1c59d4008a8 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -69,8 +69,55 @@
#define BAD_FIQ 2
#define BAD_ERROR 3
- .macro kernel_entry, el, regsize = 64
+ .macro kernel_ventry label
+ .align 7
sub sp, sp, #S_FRAME_SIZE
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * Test whether the SP has overflowed, without corrupting a GPR.
+ * Task and IRQ stacks are aligned to (1 << THREAD_SHIFT).
+ */
+ add sp, sp, x0 // sp' = sp + x0
+ sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp
+ tbnz x0, #THREAD_SHIFT, 0f
+ sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0
+ sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp
+ b \label
+
+0:
+ /*
+ * Either we've just detected an overflow, or we've taken an exception
+ * while on the overflow stack. Either way, we won't return to
+ * userspace, and can clobber EL0 registers to free up GPRs.
+ */
+
+ /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+ msr tpidr_el0, x0
+
+ /* Recover the original x0 value and stash it in tpidrro_el0 */
+ sub x0, sp, x0
+ msr tpidrro_el0, x0
+
+ /* Switch to the overflow stack */
+ adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0
+
+ /*
+ * Check whether we were already on the overflow stack. This may happen
+ * after panic() re-enables interrupts.
+ */
+ mrs x0, tpidr_el0 // sp of interrupted context
+ sub x0, sp, x0 // delta with top of overflow stack
+ tst x0, #~(OVERFLOW_STACK_SIZE - 1) // within range?
+ b.ne __bad_stack // no? -> bad stack pointer
+
+ /* We were already on the overflow stack. Restore sp/x0 and carry on. */
+ sub sp, sp, x0
+ mrs x0, tpidrro_el0
+#endif
+ b \label
+ .endm
+
+ .macro kernel_entry, el, regsize = 64
.if \regsize == 32
mov w0, w0 // zero upper 32 bits of x0
.endif
@@ -111,6 +158,18 @@
mrs x23, spsr_el1
stp lr, x21, [sp, #S_LR]
+ /*
+ * In order to be able to dump the contents of struct pt_regs at the
+ * time the exception was taken (in case we attempt to walk the call
+ * stack later), chain it together with the stack frames.
+ */
+ .if \el == 0
+ stp xzr, xzr, [sp, #S_STACKFRAME]
+ .else
+ stp x29, x22, [sp, #S_STACKFRAME]
+ .endif
+ add x29, sp, #S_STACKFRAME
+
#ifdef CONFIG_ARM64_SW_TTBR0_PAN
/*
* Set the TTBR0 PAN bit in SPSR. When the exception is taken from
@@ -138,12 +197,10 @@ alternative_else_nop_endif
stp x22, x23, [sp, #S_PC]
- /*
- * Set syscallno to -1 by default (overridden later if real syscall).
- */
+ /* Not in a syscall by default (el0_svc overwrites for real syscall) */
.if \el == 0
- mvn x21, xzr
- str x21, [sp, #S_SYSCALLNO]
+ mov w21, #NO_SYSCALL
+ str w21, [sp, #S_SYSCALLNO]
.endif
/*
@@ -259,20 +316,12 @@ alternative_else_nop_endif
and x25, x25, #~(THREAD_SIZE - 1)
cbnz x25, 9998f
- adr_this_cpu x25, irq_stack, x26
- mov x26, #IRQ_STACK_START_SP
+ ldr_this_cpu x25, irq_stack_ptr, x26
+ mov x26, #IRQ_STACK_SIZE
add x26, x25, x26
/* switch to the irq stack */
mov sp, x26
-
- /*
- * Add a dummy stack frame, this non-standard format is fixed up
- * by unwind_frame()
- */
- stp x29, x19, [sp, #-16]!
- mov x29, sp
-
9998:
.endm
@@ -290,8 +339,9 @@ alternative_else_nop_endif
*
* x7 is reserved for the system call number in 32-bit mode.
*/
-sc_nr .req x25 // number of system calls
-scno .req x26 // syscall number
+wsc_nr .req w25 // number of system calls
+wscno .req w26 // syscall number
+xscno .req x26 // syscall number (zero-extended)
stbl .req x27 // syscall table pointer
tsk .req x28 // current thread_info
@@ -315,34 +365,62 @@ tsk .req x28 // current thread_info
.align 11
ENTRY(vectors)
- ventry el1_sync_invalid // Synchronous EL1t
- ventry el1_irq_invalid // IRQ EL1t
- ventry el1_fiq_invalid // FIQ EL1t
- ventry el1_error_invalid // Error EL1t
+ kernel_ventry el1_sync_invalid // Synchronous EL1t
+ kernel_ventry el1_irq_invalid // IRQ EL1t
+ kernel_ventry el1_fiq_invalid // FIQ EL1t
+ kernel_ventry el1_error_invalid // Error EL1t
- ventry el1_sync // Synchronous EL1h
- ventry el1_irq // IRQ EL1h
- ventry el1_fiq_invalid // FIQ EL1h
- ventry el1_error_invalid // Error EL1h
+ kernel_ventry el1_sync // Synchronous EL1h
+ kernel_ventry el1_irq // IRQ EL1h
+ kernel_ventry el1_fiq_invalid // FIQ EL1h
+ kernel_ventry el1_error_invalid // Error EL1h
- ventry el0_sync // Synchronous 64-bit EL0
- ventry el0_irq // IRQ 64-bit EL0
- ventry el0_fiq_invalid // FIQ 64-bit EL0
- ventry el0_error_invalid // Error 64-bit EL0
+ kernel_ventry el0_sync // Synchronous 64-bit EL0
+ kernel_ventry el0_irq // IRQ 64-bit EL0
+ kernel_ventry el0_fiq_invalid // FIQ 64-bit EL0
+ kernel_ventry el0_error_invalid // Error 64-bit EL0
#ifdef CONFIG_COMPAT
- ventry el0_sync_compat // Synchronous 32-bit EL0
- ventry el0_irq_compat // IRQ 32-bit EL0
- ventry el0_fiq_invalid_compat // FIQ 32-bit EL0
- ventry el0_error_invalid_compat // Error 32-bit EL0
+ kernel_ventry el0_sync_compat // Synchronous 32-bit EL0
+ kernel_ventry el0_irq_compat // IRQ 32-bit EL0
+ kernel_ventry el0_fiq_invalid_compat // FIQ 32-bit EL0
+ kernel_ventry el0_error_invalid_compat // Error 32-bit EL0
#else
- ventry el0_sync_invalid // Synchronous 32-bit EL0
- ventry el0_irq_invalid // IRQ 32-bit EL0
- ventry el0_fiq_invalid // FIQ 32-bit EL0
- ventry el0_error_invalid // Error 32-bit EL0
+ kernel_ventry el0_sync_invalid // Synchronous 32-bit EL0
+ kernel_ventry el0_irq_invalid // IRQ 32-bit EL0
+ kernel_ventry el0_fiq_invalid // FIQ 32-bit EL0
+ kernel_ventry el0_error_invalid // Error 32-bit EL0
#endif
END(vectors)
+#ifdef CONFIG_VMAP_STACK
+ /*
+ * We detected an overflow in kernel_ventry, which switched to the
+ * overflow stack. Stash the exception regs, and head to our overflow
+ * handler.
+ */
+__bad_stack:
+ /* Restore the original x0 value */
+ mrs x0, tpidrro_el0
+
+ /*
+ * Store the original GPRs to the new stack. The orginal SP (minus
+ * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+ */
+ sub sp, sp, #S_FRAME_SIZE
+ kernel_entry 1
+ mrs x0, tpidr_el0
+ add x0, x0, #S_FRAME_SIZE
+ str x0, [sp, #S_SP]
+
+ /* Stash the regs for handle_bad_stack */
+ mov x0, sp
+
+ /* Time to die */
+ bl handle_bad_stack
+ ASM_BUG()
+#endif /* CONFIG_VMAP_STACK */
+
/*
* Invalid mode handlers
*/
@@ -351,7 +429,8 @@ END(vectors)
mov x0, sp
mov x1, #\reason
mrs x2, esr_el1
- b bad_mode
+ bl bad_mode
+ ASM_BUG()
.endm
el0_sync_invalid:
@@ -448,14 +527,16 @@ el1_sp_pc:
mrs x0, far_el1
enable_dbg
mov x2, sp
- b do_sp_pc_abort
+ bl do_sp_pc_abort
+ ASM_BUG()
el1_undef:
/*
* Undefined instruction
*/
enable_dbg
mov x0, sp
- b do_undefinstr
+ bl do_undefinstr
+ ASM_BUG()
el1_dbg:
/*
* Debug exception handling
@@ -473,7 +554,8 @@ el1_inv:
mov x0, sp
mov x2, x1
mov x1, #BAD_SYNC
- b bad_mode
+ bl bad_mode
+ ASM_BUG()
ENDPROC(el1_sync)
.align 6
@@ -577,8 +659,8 @@ el0_svc_compat:
* AArch32 syscall handling
*/
adrp stbl, compat_sys_call_table // load compat syscall table pointer
- uxtw scno, w7 // syscall number in w7 (r7)
- mov sc_nr, #__NR_compat_syscalls
+ mov wscno, w7 // syscall number in w7 (r7)
+ mov wsc_nr, #__NR_compat_syscalls
b el0_svc_naked
.align 6
@@ -707,38 +789,6 @@ el0_irq_naked:
ENDPROC(el0_irq)
/*
- * Register switch for AArch64. The callee-saved registers need to be saved
- * and restored. On entry:
- * x0 = previous task_struct (must be preserved across the switch)
- * x1 = next task_struct
- * Previous and next are guaranteed not to be the same.
- *
- */
-ENTRY(cpu_switch_to)
- mov x10, #THREAD_CPU_CONTEXT
- add x8, x0, x10
- mov x9, sp
- stp x19, x20, [x8], #16 // store callee-saved registers
- stp x21, x22, [x8], #16
- stp x23, x24, [x8], #16
- stp x25, x26, [x8], #16
- stp x27, x28, [x8], #16
- stp x29, x9, [x8], #16
- str lr, [x8]
- add x8, x1, x10
- ldp x19, x20, [x8], #16 // restore callee-saved registers
- ldp x21, x22, [x8], #16
- ldp x23, x24, [x8], #16
- ldp x25, x26, [x8], #16
- ldp x27, x28, [x8], #16
- ldp x29, x9, [x8], #16
- ldr lr, [x8]
- mov sp, x9
- msr sp_el0, x1
- ret
-ENDPROC(cpu_switch_to)
-
-/*
* This is the fast syscall return path. We do as little as possible here,
* and this includes saving x0 back into the kernel stack.
*/
@@ -781,36 +831,24 @@ finish_ret_to_user:
ENDPROC(ret_to_user)
/*
- * This is how we return from a fork.
- */
-ENTRY(ret_from_fork)
- bl schedule_tail
- cbz x19, 1f // not a kernel thread
- mov x0, x20
- blr x19
-1: get_thread_info tsk
- b ret_to_user
-ENDPROC(ret_from_fork)
-
-/*
* SVC handler.
*/
.align 6
el0_svc:
adrp stbl, sys_call_table // load syscall table pointer
- uxtw scno, w8 // syscall number in w8
- mov sc_nr, #__NR_syscalls
+ mov wscno, w8 // syscall number in w8
+ mov wsc_nr, #__NR_syscalls
el0_svc_naked: // compat entry point
- stp x0, scno, [sp, #S_ORIG_X0] // save the original x0 and syscall number
+ stp x0, xscno, [sp, #S_ORIG_X0] // save the original x0 and syscall number
enable_dbg_and_irq
ct_user_exit 1
ldr x16, [tsk, #TSK_TI_FLAGS] // check for syscall hooks
tst x16, #_TIF_SYSCALL_WORK
b.ne __sys_trace
- cmp scno, sc_nr // check upper syscall limit
+ cmp wscno, wsc_nr // check upper syscall limit
b.hs ni_sys
- ldr x16, [stbl, scno, lsl #3] // address in the syscall table
+ ldr x16, [stbl, xscno, lsl #3] // address in the syscall table
blr x16 // call sys_* routine
b ret_fast_syscall
ni_sys:
@@ -824,24 +862,23 @@ ENDPROC(el0_svc)
* switches, and waiting for our parent to respond.
*/
__sys_trace:
- mov w0, #-1 // set default errno for
- cmp scno, x0 // user-issued syscall(-1)
+ cmp wscno, #NO_SYSCALL // user-issued syscall(-1)?
b.ne 1f
- mov x0, #-ENOSYS
+ mov x0, #-ENOSYS // set default errno if so
str x0, [sp, #S_X0]
1: mov x0, sp
bl syscall_trace_enter
- cmp w0, #-1 // skip the syscall?
+ cmp w0, #NO_SYSCALL // skip the syscall?
b.eq __sys_trace_return_skipped
- uxtw scno, w0 // syscall number (possibly new)
+ mov wscno, w0 // syscall number (possibly new)
mov x1, sp // pointer to regs
- cmp scno, sc_nr // check upper syscall limit
+ cmp wscno, wsc_nr // check upper syscall limit
b.hs __ni_sys_trace
ldp x0, x1, [sp] // restore the syscall args
ldp x2, x3, [sp, #S_X2]
ldp x4, x5, [sp, #S_X4]
ldp x6, x7, [sp, #S_X6]
- ldr x16, [stbl, scno, lsl #3] // address in the syscall table
+ ldr x16, [stbl, xscno, lsl #3] // address in the syscall table
blr x16 // call sys_* routine
__sys_trace_return:
@@ -865,3 +902,49 @@ ENTRY(sys_rt_sigreturn_wrapper)
mov x0, sp
b sys_rt_sigreturn
ENDPROC(sys_rt_sigreturn_wrapper)
+
+/*
+ * Register switch for AArch64. The callee-saved registers need to be saved
+ * and restored. On entry:
+ * x0 = previous task_struct (must be preserved across the switch)
+ * x1 = next task_struct
+ * Previous and next are guaranteed not to be the same.
+ *
+ */
+ENTRY(cpu_switch_to)
+ mov x10, #THREAD_CPU_CONTEXT
+ add x8, x0, x10
+ mov x9, sp
+ stp x19, x20, [x8], #16 // store callee-saved registers
+ stp x21, x22, [x8], #16
+ stp x23, x24, [x8], #16
+ stp x25, x26, [x8], #16
+ stp x27, x28, [x8], #16
+ stp x29, x9, [x8], #16
+ str lr, [x8]
+ add x8, x1, x10
+ ldp x19, x20, [x8], #16 // restore callee-saved registers
+ ldp x21, x22, [x8], #16
+ ldp x23, x24, [x8], #16
+ ldp x25, x26, [x8], #16
+ ldp x27, x28, [x8], #16
+ ldp x29, x9, [x8], #16
+ ldr lr, [x8]
+ mov sp, x9
+ msr sp_el0, x1
+ ret
+ENDPROC(cpu_switch_to)
+NOKPROBE(cpu_switch_to)
+
+/*
+ * This is how we return from a fork.
+ */
+ENTRY(ret_from_fork)
+ bl schedule_tail
+ cbz x19, 1f // not a kernel thread
+ mov x0, x20
+ blr x19
+1: get_thread_info tsk
+ b ret_to_user
+ENDPROC(ret_from_fork)
+NOKPROBE(ret_from_fork)
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 06da8ea16bbe..3a68cf38a6b3 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -17,16 +17,19 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/bottom_half.h>
#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
#include <linux/sched/signal.h>
#include <linux/signal.h>
-#include <linux/hardirq.h>
#include <asm/fpsimd.h>
#include <asm/cputype.h>
+#include <asm/simd.h>
#define FPEXC_IOF (1 << 0)
#define FPEXC_DZF (1 << 1)
@@ -62,6 +65,13 @@
* CPU currently contain the most recent userland FPSIMD state of the current
* task.
*
+ * In order to allow softirq handlers to use FPSIMD, kernel_neon_begin() may
+ * save the task's FPSIMD context back to task_struct from softirq context.
+ * To prevent this from racing with the manipulation of the task's FPSIMD state
+ * from task context and thereby corrupting the state, it is necessary to
+ * protect any manipulation of a task's fpsimd_state or TIF_FOREIGN_FPSTATE
+ * flag with local_bh_disable() unless softirqs are already masked.
+ *
* For a certain task, the sequence may look something like this:
* - the task gets scheduled in; if both the task's fpsimd_state.cpu field
* contains the id of the current CPU, and the CPU's fpsimd_last_state per-cpu
@@ -161,9 +171,14 @@ void fpsimd_flush_thread(void)
{
if (!system_supports_fpsimd())
return;
+
+ local_bh_disable();
+
memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
fpsimd_flush_task_state(current);
set_thread_flag(TIF_FOREIGN_FPSTATE);
+
+ local_bh_enable();
}
/*
@@ -174,10 +189,13 @@ void fpsimd_preserve_current_state(void)
{
if (!system_supports_fpsimd())
return;
- preempt_disable();
+
+ local_bh_disable();
+
if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
fpsimd_save_state(&current->thread.fpsimd_state);
- preempt_enable();
+
+ local_bh_enable();
}
/*
@@ -189,15 +207,18 @@ void fpsimd_restore_current_state(void)
{
if (!system_supports_fpsimd())
return;
- preempt_disable();
+
+ local_bh_disable();
+
if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
struct fpsimd_state *st = &current->thread.fpsimd_state;
fpsimd_load_state(st);
- this_cpu_write(fpsimd_last_state, st);
+ __this_cpu_write(fpsimd_last_state, st);
st->cpu = smp_processor_id();
}
- preempt_enable();
+
+ local_bh_enable();
}
/*
@@ -209,15 +230,18 @@ void fpsimd_update_current_state(struct fpsimd_state *state)
{
if (!system_supports_fpsimd())
return;
- preempt_disable();
+
+ local_bh_disable();
+
fpsimd_load_state(state);
if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
struct fpsimd_state *st = &current->thread.fpsimd_state;
- this_cpu_write(fpsimd_last_state, st);
+ __this_cpu_write(fpsimd_last_state, st);
st->cpu = smp_processor_id();
}
- preempt_enable();
+
+ local_bh_enable();
}
/*
@@ -230,52 +254,122 @@ void fpsimd_flush_task_state(struct task_struct *t)
#ifdef CONFIG_KERNEL_MODE_NEON
-static DEFINE_PER_CPU(struct fpsimd_partial_state, hardirq_fpsimdstate);
-static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
+DEFINE_PER_CPU(bool, kernel_neon_busy);
+EXPORT_PER_CPU_SYMBOL(kernel_neon_busy);
/*
* Kernel-side NEON support functions
*/
-void kernel_neon_begin_partial(u32 num_regs)
+
+/*
+ * kernel_neon_begin(): obtain the CPU FPSIMD registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the FPSIMD registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_neon_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the FPSIMD registers until kernel_neon_end() is
+ * called.
+ */
+void kernel_neon_begin(void)
{
if (WARN_ON(!system_supports_fpsimd()))
return;
- if (in_interrupt()) {
- struct fpsimd_partial_state *s = this_cpu_ptr(
- in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
- BUG_ON(num_regs > 32);
- fpsimd_save_partial_state(s, roundup(num_regs, 2));
- } else {
- /*
- * Save the userland FPSIMD state if we have one and if we
- * haven't done so already. Clear fpsimd_last_state to indicate
- * that there is no longer userland FPSIMD state in the
- * registers.
- */
- preempt_disable();
- if (current->mm &&
- !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
- fpsimd_save_state(&current->thread.fpsimd_state);
- this_cpu_write(fpsimd_last_state, NULL);
- }
+ BUG_ON(!may_use_simd());
+
+ local_bh_disable();
+
+ __this_cpu_write(kernel_neon_busy, true);
+
+ /* Save unsaved task fpsimd state, if any: */
+ if (current->mm && !test_and_set_thread_flag(TIF_FOREIGN_FPSTATE))
+ fpsimd_save_state(&current->thread.fpsimd_state);
+
+ /* Invalidate any task state remaining in the fpsimd regs: */
+ __this_cpu_write(fpsimd_last_state, NULL);
+
+ preempt_disable();
+
+ local_bh_enable();
}
-EXPORT_SYMBOL(kernel_neon_begin_partial);
+EXPORT_SYMBOL(kernel_neon_begin);
+/*
+ * kernel_neon_end(): give the CPU FPSIMD registers back to the current task
+ *
+ * Must be called from a context in which kernel_neon_begin() was previously
+ * called, with no call to kernel_neon_end() in the meantime.
+ *
+ * The caller must not use the FPSIMD registers after this function is called,
+ * unless kernel_neon_begin() is called again in the meantime.
+ */
void kernel_neon_end(void)
{
+ bool busy;
+
if (!system_supports_fpsimd())
return;
- if (in_interrupt()) {
- struct fpsimd_partial_state *s = this_cpu_ptr(
- in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
- fpsimd_load_partial_state(s);
- } else {
- preempt_enable();
- }
+
+ busy = __this_cpu_xchg(kernel_neon_busy, false);
+ WARN_ON(!busy); /* No matching kernel_neon_begin()? */
+
+ preempt_enable();
}
EXPORT_SYMBOL(kernel_neon_end);
+static DEFINE_PER_CPU(struct fpsimd_state, efi_fpsimd_state);
+static DEFINE_PER_CPU(bool, efi_fpsimd_state_used);
+
+/*
+ * EFI runtime services support functions
+ *
+ * The ABI for EFI runtime services allows EFI to use FPSIMD during the call.
+ * This means that for EFI (and only for EFI), we have to assume that FPSIMD
+ * is always used rather than being an optional accelerator.
+ *
+ * These functions provide the necessary support for ensuring FPSIMD
+ * save/restore in the contexts from which EFI is used.
+ *
+ * Do not use them for any other purpose -- if tempted to do so, you are
+ * either doing something wrong or you need to propose some refactoring.
+ */
+
+/*
+ * __efi_fpsimd_begin(): prepare FPSIMD for making an EFI runtime services call
+ */
+void __efi_fpsimd_begin(void)
+{
+ if (!system_supports_fpsimd())
+ return;
+
+ WARN_ON(preemptible());
+
+ if (may_use_simd())
+ kernel_neon_begin();
+ else {
+ fpsimd_save_state(this_cpu_ptr(&efi_fpsimd_state));
+ __this_cpu_write(efi_fpsimd_state_used, true);
+ }
+}
+
+/*
+ * __efi_fpsimd_end(): clean up FPSIMD after an EFI runtime services call
+ */
+void __efi_fpsimd_end(void)
+{
+ if (!system_supports_fpsimd())
+ return;
+
+ if (__this_cpu_xchg(efi_fpsimd_state_used, false))
+ fpsimd_load_state(this_cpu_ptr(&efi_fpsimd_state));
+ else
+ kernel_neon_end();
+}
+
#endif /* CONFIG_KERNEL_MODE_NEON */
#ifdef CONFIG_CPU_PM
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 973df7de7bf8..7434ec0c7a27 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -143,8 +143,8 @@ preserve_boot_args:
dmb sy // needed before dc ivac with
// MMU off
- add x1, x0, #0x20 // 4 x 8 bytes
- b __inval_cache_range // tail call
+ mov x1, #0x20 // 4 x 8 bytes
+ b __inval_dcache_area // tail call
ENDPROC(preserve_boot_args)
/*
@@ -221,20 +221,20 @@ __create_page_tables:
* dirty cache lines being evicted.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
- bl __inval_cache_range
+ ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
+ bl __inval_dcache_area
/*
* Clear the idmap and swapper page tables.
*/
adrp x0, idmap_pg_dir
- adrp x6, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
+ ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
1: stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
stp xzr, xzr, [x0], #16
- cmp x0, x6
- b.lo 1b
+ subs x1, x1, #64
+ b.ne 1b
mov x7, SWAPPER_MM_MMUFLAGS
@@ -307,9 +307,9 @@ __create_page_tables:
* tables again to remove any speculatively loaded cache lines.
*/
adrp x0, idmap_pg_dir
- adrp x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
+ ldr x1, =(IDMAP_DIR_SIZE + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE)
dmb sy
- bl __inval_cache_range
+ bl __inval_dcache_area
ret x28
ENDPROC(__create_page_tables)
@@ -354,7 +354,6 @@ __primary_switched:
tst x23, ~(MIN_KIMG_ALIGN - 1) // already running randomized?
b.ne 0f
mov x0, x21 // pass FDT address in x0
- mov x1, x23 // pass modulo offset in x1
bl kaslr_early_init // parse FDT for KASLR options
cbz x0, 0f // KASLR disabled? just proceed
orr x23, x23, x0 // record KASLR offset
@@ -362,6 +361,9 @@ __primary_switched:
ret // to __primary_switch()
0:
#endif
+ add sp, sp, #16
+ mov x29, #0
+ mov x30, #0
b start_kernel
ENDPROC(__primary_switched)
@@ -617,6 +619,7 @@ __secondary_switched:
ldr x2, [x0, #CPU_BOOT_TASK]
msr sp_el0, x2
mov x29, #0
+ mov x30, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index a44e13942d30..095d3c170f5d 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -330,7 +330,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
* read only (code, rodata). Clear the RDONLY bit from
* the temporary mappings we use during restore.
*/
- set_pte(dst_pte, pte_clear_rdonly(pte));
+ set_pte(dst_pte, pte_mkwrite(pte));
} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
/*
* debug_pagealloc will removed the PTE_VALID bit if
@@ -343,7 +343,7 @@ static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
*/
BUG_ON(!pfn_valid(pte_pfn(pte)));
- set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte)));
+ set_pte(dst_pte, pte_mkpresent(pte_mkwrite(pte)));
}
}
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 2386b26c0712..713561e5bcab 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -23,15 +23,16 @@
#include <linux/kernel_stat.h>
#include <linux/irq.h>
+#include <linux/memory.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/irqchip.h>
#include <linux/seq_file.h>
+#include <linux/vmalloc.h>
unsigned long irq_err_count;
-/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
-DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16);
+DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
int arch_show_interrupts(struct seq_file *p, int prec)
{
@@ -50,8 +51,43 @@ void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
handle_arch_irq = handle_irq;
}
+#ifdef CONFIG_VMAP_STACK
+static void init_irq_stacks(void)
+{
+ int cpu;
+ unsigned long *p;
+
+ for_each_possible_cpu(cpu) {
+ /*
+ * To ensure that VMAP'd stack overflow detection works
+ * correctly, the IRQ stacks need to have the same
+ * alignment as other stacks.
+ */
+ p = __vmalloc_node_range(IRQ_STACK_SIZE, THREAD_ALIGN,
+ VMALLOC_START, VMALLOC_END,
+ THREADINFO_GFP, PAGE_KERNEL,
+ 0, cpu_to_node(cpu),
+ __builtin_return_address(0));
+
+ per_cpu(irq_stack_ptr, cpu) = p;
+ }
+}
+#else
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
+
+static void init_irq_stacks(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu);
+}
+#endif
+
void __init init_IRQ(void)
{
+ init_irq_stacks();
irqchip_init();
if (!handle_arch_irq)
panic("No interrupt controller found.");
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index a9710efb8c01..47080c49cc7e 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -75,7 +75,7 @@ extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size,
* containing function pointers) to be reinitialized, and zero-initialized
* .bss variables will be reset to 0.
*/
-u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
+u64 __init kaslr_early_init(u64 dt_phys)
{
void *fdt;
u64 seed, offset, mask, module_range;
@@ -131,15 +131,17 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset)
/*
* The kernel Image should not extend across a 1GB/32MB/512MB alignment
* boundary (for 4KB/16KB/64KB granule kernels, respectively). If this
- * happens, increase the KASLR offset by the size of the kernel image
- * rounded up by SWAPPER_BLOCK_SIZE.
+ * happens, round down the KASLR offset by (1 << SWAPPER_TABLE_SHIFT).
+ *
+ * NOTE: The references to _text and _end below will already take the
+ * modulo offset (the physical displacement modulo 2 MB) into
+ * account, given that the physical placement is controlled by
+ * the loader, and will not change as a result of the virtual
+ * mapping we choose.
*/
- if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
- (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) {
- u64 kimg_sz = _end - _text;
- offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE))
- & mask;
- }
+ if ((((u64)_text + offset) >> SWAPPER_TABLE_SHIFT) !=
+ (((u64)_end + offset) >> SWAPPER_TABLE_SHIFT))
+ offset = round_down(offset, 1 << SWAPPER_TABLE_SHIFT);
if (IS_ENABLED(CONFIG_KASAN))
/*
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 481f54a866c5..11121f608eb5 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -252,7 +252,7 @@ void machine_crash_shutdown(struct pt_regs *regs)
local_irq_disable();
/* shutdown non-crashing cpus */
- smp_send_crash_stop();
+ crash_smp_send_stop();
/* for crashing cpu */
crash_save_cpu(regs, smp_processor_id());
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index 713ca824f266..bcafd7dcfe8b 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -162,7 +162,6 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
}
frame.fp = regs->regs[29];
- frame.sp = regs->sp;
frame.pc = regs->pc;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = current->curr_ret_stack;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index b5798ba21189..9eaef51f83ff 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -202,55 +202,6 @@ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
};
-/* ARM Cortex-A53 HW events mapping. */
-static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = {
- PERF_MAP_ALL_UNSUPPORTED,
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
- [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
-};
-
-/* ARM Cortex-A57 and Cortex-A72 events mapping. */
-static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = {
- PERF_MAP_ALL_UNSUPPORTED,
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
- [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
-};
-
-static const unsigned armv8_thunder_perf_map[PERF_COUNT_HW_MAX] = {
- PERF_MAP_ALL_UNSUPPORTED,
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
- [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
-};
-
-/* Broadcom Vulcan events mapping */
-static const unsigned armv8_vulcan_perf_map[PERF_COUNT_HW_MAX] = {
- PERF_MAP_ALL_UNSUPPORTED,
- [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
- [PERF_COUNT_HW_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_INST_RETIRED,
- [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [PERF_COUNT_HW_CACHE_MISSES] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
- [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV8_PMUV3_PERFCTR_BR_RETIRED,
- [PERF_COUNT_HW_BRANCH_MISSES] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
- [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
- [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
-};
-
static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
@@ -281,27 +232,10 @@ static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
PERF_CACHE_MAP_ALL_UNSUPPORTED,
- [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
- [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE,
- [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_A53_PERFCTR_PREF_LINEFILL,
- [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
- [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
-
- [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L2D_CACHE,
- [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL,
- [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L2D_CACHE,
- [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L2D_CACHE_REFILL,
-
- [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
- [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
-
- [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+ [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+ [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
};
static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -314,18 +248,26 @@ static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR,
- [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
- [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
-
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
- [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+ [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+ [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
+};
- [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+static const unsigned armv8_a73_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+ PERF_CACHE_MAP_ALL_UNSUPPORTED,
+
+ [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_RD,
+ [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
+
+ [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+ [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
+
+ [C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
+ [C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
};
static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -340,8 +282,6 @@ static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_ACCESS,
[C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1D_CACHE_PREF_MISS,
- [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
- [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
[C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_ACCESS,
[C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS,
@@ -349,13 +289,6 @@ static const unsigned armv8_thunder_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
-
- [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
-
- [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
};
static const unsigned armv8_vulcan_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
@@ -368,22 +301,11 @@ static const unsigned armv8_vulcan_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_WR,
[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_CACHE_REFILL_WR,
- [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE,
- [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
-
- [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
- [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_L1I_TLB,
-
[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_RD,
[C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_WR,
[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_RD,
[C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_IMPDEF_PERFCTR_L1D_TLB_REFILL_WR,
- [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_PMUV3_PERFCTR_BR_PRED,
- [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
-
[C(NODE)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_RD,
[C(NODE)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV8_IMPDEF_PERFCTR_BUS_ACCESS_WR,
};
@@ -846,17 +768,14 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
struct hw_perf_event *hwc = &event->hw;
unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
- /* Always place a cycle counter into the cycle counter. */
+ /* Always prefer to place a cycle counter into the cycle counter. */
if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
- if (test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
- return -EAGAIN;
-
- return ARMV8_IDX_CYCLE_COUNTER;
+ if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
+ return ARMV8_IDX_CYCLE_COUNTER;
}
/*
- * For anything other than a cycle counter, try and use
- * the events counters
+ * Otherwise use events counters
*/
for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
if (!test_and_set_bit(idx, cpuc->used_mask))
@@ -924,7 +843,13 @@ static void armv8pmu_reset(void *info)
ARMV8_PMU_PMCR_LC);
}
-static int armv8_pmuv3_map_event(struct perf_event *event)
+static int __armv8_pmuv3_map_event(struct perf_event *event,
+ const unsigned (*extra_event_map)
+ [PERF_COUNT_HW_MAX],
+ const unsigned (*extra_cache_map)
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX])
{
int hw_event_id;
struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
@@ -932,44 +857,47 @@ static int armv8_pmuv3_map_event(struct perf_event *event)
hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
&armv8_pmuv3_perf_cache_map,
ARMV8_PMU_EVTYPE_EVENT);
- if (hw_event_id < 0)
- return hw_event_id;
- /* disable micro/arch events not supported by this PMU */
- if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) &&
- !test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
- return -EOPNOTSUPP;
+ /* Onl expose micro/arch events supported by this PMU */
+ if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
+ && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+ return hw_event_id;
}
- return hw_event_id;
+ return armpmu_map_event(event, extra_event_map, extra_cache_map,
+ ARMV8_PMU_EVTYPE_EVENT);
+}
+
+static int armv8_pmuv3_map_event(struct perf_event *event)
+{
+ return __armv8_pmuv3_map_event(event, NULL, NULL);
}
static int armv8_a53_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_a53_perf_map,
- &armv8_a53_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ return __armv8_pmuv3_map_event(event, NULL, &armv8_a53_perf_cache_map);
}
static int armv8_a57_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_a57_perf_map,
- &armv8_a57_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ return __armv8_pmuv3_map_event(event, NULL, &armv8_a57_perf_cache_map);
+}
+
+static int armv8_a73_map_event(struct perf_event *event)
+{
+ return __armv8_pmuv3_map_event(event, NULL, &armv8_a73_perf_cache_map);
}
static int armv8_thunder_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_thunder_perf_map,
- &armv8_thunder_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ return __armv8_pmuv3_map_event(event, NULL,
+ &armv8_thunder_perf_cache_map);
}
static int armv8_vulcan_map_event(struct perf_event *event)
{
- return armpmu_map_event(event, &armv8_vulcan_perf_map,
- &armv8_vulcan_perf_cache_map,
- ARMV8_PMU_EVTYPE_EVENT);
+ return __armv8_pmuv3_map_event(event, NULL,
+ &armv8_vulcan_perf_cache_map);
}
struct armv8pmu_probe_info {
@@ -1062,6 +990,22 @@ static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
return 0;
}
+static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
+ cpu_pmu->name = "armv8_cortex_a35";
+ cpu_pmu->map_event = armv8_a53_map_event;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
+
+ return 0;
+}
+
static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
{
int ret = armv8_pmu_init(cpu_pmu);
@@ -1110,6 +1054,22 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
return 0;
}
+static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
+{
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
+ cpu_pmu->name = "armv8_cortex_a73";
+ cpu_pmu->map_event = armv8_a73_map_event;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+ &armv8_pmuv3_events_attr_group;
+ cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+ &armv8_pmuv3_format_attr_group;
+
+ return 0;
+}
+
static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
{
int ret = armv8_pmu_init(cpu_pmu);
@@ -1144,9 +1104,11 @@ static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
static const struct of_device_id armv8_pmu_of_device_ids[] = {
{.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init},
+ {.compatible = "arm,cortex-a35-pmu", .data = armv8_a35_pmu_init},
{.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init},
{.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init},
{.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init},
+ {.compatible = "arm,cortex-a73-pmu", .data = armv8_a73_pmu_init},
{.compatible = "cavium,thunder-pmu", .data = armv8_thunder_pmu_init},
{.compatible = "brcm,vulcan-pmu", .data = armv8_vulcan_pmu_init},
{},
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 26c998534dca..636ca0119c0e 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -40,7 +40,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
probe_opcode_t insn;
/* TODO: Currently we do not support AARCH32 instruction probing */
- if (test_bit(TIF_32BIT, &mm->context.flags))
+ if (mm->context.flags & MMCF_AARCH32)
return -ENOTSUPP;
else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE))
return -EINVAL;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 659ae8094ed5..2dc0f8482210 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -360,6 +360,8 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
/*
* Complete any pending TLB or cache maintenance on this CPU in case
* the thread migrates to a different CPU.
+ * This full barrier is also required by the membarrier system
+ * call.
*/
dsb(ish);
@@ -382,15 +384,12 @@ unsigned long get_wchan(struct task_struct *p)
return 0;
frame.fp = thread_saved_fp(p);
- frame.sp = thread_saved_sp(p);
frame.pc = thread_saved_pc(p);
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = p->curr_ret_stack;
#endif
do {
- if (frame.sp < stack_page ||
- frame.sp >= stack_page + THREAD_SIZE ||
- unwind_frame(p, &frame))
+ if (unwind_frame(p, &frame))
goto out;
if (!in_sched_functions(frame.pc)) {
ret = frame.pc;
@@ -417,3 +416,11 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
else
return randomize_page(mm->brk, SZ_1G);
}
+
+/*
+ * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
+ */
+void arch_setup_new_exec(void)
+{
+ current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
+}
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 1b38c0150aec..9cbb6123208f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -42,6 +42,7 @@
#include <asm/compat.h>
#include <asm/debug-monitors.h>
#include <asm/pgtable.h>
+#include <asm/stacktrace.h>
#include <asm/syscall.h>
#include <asm/traps.h>
#include <asm/system_misc.h>
@@ -127,7 +128,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
{
return ((addr & ~(THREAD_SIZE - 1)) ==
(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
- on_irq_stack(addr, raw_smp_processor_id());
+ on_irq_stack(addr);
}
/**
@@ -1363,7 +1364,7 @@ static void tracehook_report_syscall(struct pt_regs *regs,
if (dir == PTRACE_SYSCALL_EXIT)
tracehook_report_syscall_exit(regs, 0);
else if (tracehook_report_syscall_entry(regs))
- regs->syscallno = ~0UL;
+ forget_syscall(regs);
regs->regs[regno] = saved_reg;
}
diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c
index 12a87f2600f2..933adbc0f654 100644
--- a/arch/arm64/kernel/return_address.c
+++ b/arch/arm64/kernel/return_address.c
@@ -42,7 +42,6 @@ void *return_address(unsigned int level)
data.addr = NULL;
frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.sp = current_stack_pointer;
frame.pc = (unsigned long)return_address; /* dummy */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = current->curr_ret_stack;
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 089c3747995d..c45214f8fb54 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -29,6 +29,7 @@
#include <linux/string.h>
#include <linux/tracehook.h>
#include <linux/ratelimit.h>
+#include <linux/syscalls.h>
#include <asm/debug-monitors.h>
#include <asm/elf.h>
@@ -36,6 +37,7 @@
#include <asm/ucontext.h>
#include <asm/unistd.h>
#include <asm/fpsimd.h>
+#include <asm/ptrace.h>
#include <asm/signal32.h>
#include <asm/vdso.h>
@@ -387,7 +389,7 @@ static int restore_sigframe(struct pt_regs *regs,
/*
* Avoid sys_rt_sigreturn() restarting.
*/
- regs->syscallno = ~0UL;
+ forget_syscall(regs);
err |= !valid_user_regs(&regs->user_regs, current);
if (err == 0)
@@ -673,13 +675,12 @@ static void do_signal(struct pt_regs *regs)
{
unsigned long continue_addr = 0, restart_addr = 0;
int retval = 0;
- int syscall = (int)regs->syscallno;
struct ksignal ksig;
/*
* If we were from a system call, check for system call restarting...
*/
- if (syscall >= 0) {
+ if (in_syscall(regs)) {
continue_addr = regs->pc;
restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4);
retval = regs->regs[0];
@@ -687,7 +688,7 @@ static void do_signal(struct pt_regs *regs)
/*
* Avoid additional syscall restarting via ret_to_user.
*/
- regs->syscallno = ~0UL;
+ forget_syscall(regs);
/*
* Prepare for system call restart. We do this here so that a
@@ -731,7 +732,7 @@ static void do_signal(struct pt_regs *regs)
* Handle restarting a different system call. As above, if a debugger
* has chosen to restart at a different PC, ignore the restart.
*/
- if (syscall >= 0 && regs->pc == restart_addr) {
+ if (in_syscall(regs) && regs->pc == restart_addr) {
if (retval == -ERESTART_RESTARTBLOCK)
setup_restart_syscall(regs);
user_rewind_single_step(current);
@@ -749,6 +750,10 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
* Update the trace code with the current status.
*/
trace_hardirqs_off();
+
+ /* Check valid user FS if needed */
+ addr_limit_user_check();
+
do {
if (thread_flags & _TIF_NEED_RESCHED) {
schedule();
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index c747a0fc5d7d..4e5a664be04b 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -354,7 +354,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
/*
* Avoid compat_sys_sigreturn() restarting.
*/
- regs->syscallno = ~0UL;
+ forget_syscall(regs);
err |= !valid_user_regs(&regs->user_regs, current);
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dc66e6ec3a99..ffe089942ac4 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -154,7 +154,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
* page tables.
*/
secondary_data.task = idle;
- secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
+ secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
update_cpu_boot_status(CPU_MMU_OFF);
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
@@ -977,11 +977,21 @@ void smp_send_stop(void)
}
#ifdef CONFIG_KEXEC_CORE
-void smp_send_crash_stop(void)
+void crash_smp_send_stop(void)
{
+ static int cpus_stopped;
cpumask_t mask;
unsigned long timeout;
+ /*
+ * This function can be called twice in panic path, but obviously
+ * we execute this only once.
+ */
+ if (cpus_stopped)
+ return;
+
+ cpus_stopped = 1;
+
if (num_online_cpus() == 1)
return;
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 09d37d66b630..3144584617e7 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -42,33 +42,17 @@
*/
int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
{
- unsigned long high, low;
unsigned long fp = frame->fp;
- unsigned long irq_stack_ptr;
+
+ if (fp & 0xf)
+ return -EINVAL;
if (!tsk)
tsk = current;
- /*
- * Switching between stacks is valid when tracing current and in
- * non-preemptible context.
- */
- if (tsk == current && !preemptible())
- irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
- else
- irq_stack_ptr = 0;
-
- low = frame->sp;
- /* irq stacks are not THREAD_SIZE aligned */
- if (on_irq_stack(frame->sp, raw_smp_processor_id()))
- high = irq_stack_ptr;
- else
- high = ALIGN(low, THREAD_SIZE) - 0x20;
-
- if (fp < low || fp > high || fp & 0xf)
+ if (!on_accessible_stack(tsk, fp))
return -EINVAL;
- frame->sp = fp + 0x10;
frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
@@ -86,34 +70,13 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
/*
- * Check whether we are going to walk through from interrupt stack
- * to task stack.
- * If we reach the end of the stack - and its an interrupt stack,
- * unpack the dummy frame to find the original elr.
- *
- * Check the frame->fp we read from the bottom of the irq_stack,
- * and the original task stack pointer are both in current->stack.
+ * Frames created upon entry from EL0 have NULL FP and PC values, so
+ * don't bother reporting these. Frames created by __noreturn functions
+ * might have a valid FP even if PC is bogus, so only terminate where
+ * both are NULL.
*/
- if (frame->sp == irq_stack_ptr) {
- struct pt_regs *irq_args;
- unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
-
- if (object_is_on_stack((void *)orig_sp) &&
- object_is_on_stack((void *)frame->fp)) {
- frame->sp = orig_sp;
-
- /* orig_sp is the saved pt_regs, find the elr */
- irq_args = (struct pt_regs *)orig_sp;
- frame->pc = irq_args->pc;
- } else {
- /*
- * This frame has a non-standard format, and we
- * didn't fix it, because the data looked wrong.
- * Refuse to output this frame.
- */
- return -EINVAL;
- }
- }
+ if (!frame->fp && !frame->pc)
+ return -EINVAL;
return 0;
}
@@ -167,7 +130,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
data.no_sched_functions = 0;
frame.fp = regs->regs[29];
- frame.sp = regs->sp;
frame.pc = regs->pc;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = current->curr_ret_stack;
@@ -192,12 +154,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
if (tsk != current) {
data.no_sched_functions = 1;
frame.fp = thread_saved_fp(tsk);
- frame.sp = thread_saved_sp(tsk);
frame.pc = thread_saved_pc(tsk);
} else {
data.no_sched_functions = 0;
frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.sp = current_stack_pointer;
frame.pc = (unsigned long)save_stack_trace_tsk;
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c
index da33c90248e9..a4391280fba9 100644
--- a/arch/arm64/kernel/time.c
+++ b/arch/arm64/kernel/time.c
@@ -50,7 +50,6 @@ unsigned long profile_pc(struct pt_regs *regs)
return regs->pc;
frame.fp = regs->regs[29];
- frame.sp = regs->sp;
frame.pc = regs->pc;
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
frame.graph = -1; /* no task info */
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8a62648848e5..5ea4b85aee0e 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -32,6 +32,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
+#include <linux/sizes.h>
#include <linux/syscalls.h>
#include <linux/mm_types.h>
@@ -41,6 +42,7 @@
#include <asm/esr.h>
#include <asm/insn.h>
#include <asm/traps.h>
+#include <asm/smp.h>
#include <asm/stack_pointer.h>
#include <asm/stacktrace.h>
#include <asm/exception.h>
@@ -143,7 +145,6 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
{
struct stackframe frame;
- unsigned long irq_stack_ptr;
int skip;
pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
@@ -154,25 +155,14 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
if (!try_get_task_stack(tsk))
return;
- /*
- * Switching between stacks is valid when tracing current and in
- * non-preemptible context.
- */
- if (tsk == current && !preemptible())
- irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
- else
- irq_stack_ptr = 0;
-
if (tsk == current) {
frame.fp = (unsigned long)__builtin_frame_address(0);
- frame.sp = current_stack_pointer;
frame.pc = (unsigned long)dump_backtrace;
} else {
/*
* task blocked in __switch_to
*/
frame.fp = thread_saved_fp(tsk);
- frame.sp = thread_saved_sp(tsk);
frame.pc = thread_saved_pc(tsk);
}
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -182,13 +172,12 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
skip = !!regs;
printk("Call trace:\n");
while (1) {
- unsigned long where = frame.pc;
unsigned long stack;
int ret;
/* skip until specified stack frame */
if (!skip) {
- dump_backtrace_entry(where);
+ dump_backtrace_entry(frame.pc);
} else if (frame.fp == regs->regs[29]) {
skip = 0;
/*
@@ -203,20 +192,12 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
ret = unwind_frame(tsk, &frame);
if (ret < 0)
break;
- stack = frame.sp;
- if (in_exception_text(where)) {
- /*
- * If we switched to the irq_stack before calling this
- * exception handler, then the pt_regs will be on the
- * task stack. The easiest way to tell is if the large
- * pt_regs would overlap with the end of the irq_stack.
- */
- if (stack < irq_stack_ptr &&
- (stack + sizeof(struct pt_regs)) > irq_stack_ptr)
- stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
+ if (in_entry_text(frame.pc)) {
+ stack = frame.fp - offsetof(struct pt_regs, stackframe);
- dump_mem("", "Exception stack", stack,
- stack + sizeof(struct pt_regs));
+ if (on_accessible_stack(tsk, stack))
+ dump_mem("", "Exception stack", stack,
+ stack + sizeof(struct pt_regs));
}
}
@@ -257,8 +238,6 @@ static int __die(const char *str, int err, struct pt_regs *regs)
end_of_stack(tsk));
if (!user_mode(regs)) {
- dump_mem(KERN_EMERG, "Stack: ", regs->sp,
- THREAD_SIZE + (unsigned long)task_stack_page(tsk));
dump_backtrace(regs, tsk);
dump_instr(KERN_EMERG, regs);
}
@@ -484,6 +463,9 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */
__user_cache_maint("dc civac", address, ret);
break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVAP: /* DC CVAP */
+ __user_cache_maint("sys 3, c7, c12, 1", address, ret);
+ break;
case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC: /* DC CIVAC */
__user_cache_maint("dc civac", address, ret);
break;
@@ -593,7 +575,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
if (show_unhandled_signals_ratelimited()) {
pr_info("%s[%d]: syscall %d\n", current->comm,
- task_pid_nr(current), (int)regs->syscallno);
+ task_pid_nr(current), regs->syscallno);
dump_instr("", regs);
if (user_mode(regs))
__show_regs(regs);
@@ -689,6 +671,43 @@ asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
force_sig_info(info.si_signo, &info, current);
}
+#ifdef CONFIG_VMAP_STACK
+
+DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
+ __aligned(16);
+
+asmlinkage void handle_bad_stack(struct pt_regs *regs)
+{
+ unsigned long tsk_stk = (unsigned long)current->stack;
+ unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
+ unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
+ unsigned int esr = read_sysreg(esr_el1);
+ unsigned long far = read_sysreg(far_el1);
+
+ console_verbose();
+ pr_emerg("Insufficient stack space to handle exception!");
+
+ pr_emerg("ESR: 0x%08x -- %s\n", esr, esr_get_class_string(esr));
+ pr_emerg("FAR: 0x%016lx\n", far);
+
+ pr_emerg("Task stack: [0x%016lx..0x%016lx]\n",
+ tsk_stk, tsk_stk + THREAD_SIZE);
+ pr_emerg("IRQ stack: [0x%016lx..0x%016lx]\n",
+ irq_stk, irq_stk + THREAD_SIZE);
+ pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n",
+ ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE);
+
+ __show_regs(regs);
+
+ /*
+ * We use nmi_panic to limit the potential for recusive overflows, and
+ * to get a better stack trace.
+ */
+ nmi_panic(NULL, "kernel stack overflow");
+ cpu_park_loop();
+}
+#endif
+
void __pte_error(const char *file, int line, unsigned long val)
{
pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index e8f759f764f2..2d419006ad43 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -110,12 +110,27 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
}
#endif /* CONFIG_COMPAT */
+static int vdso_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+ unsigned long vdso_size = vdso_end - vdso_start;
+
+ if (vdso_size != new_size)
+ return -EINVAL;
+
+ current->mm->context.vdso = (void *)new_vma->vm_start;
+
+ return 0;
+}
+
static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
{
.name = "[vvar]",
},
{
.name = "[vdso]",
+ .mremap = vdso_mremap,
},
};
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 987a00ee446c..fe56c268a7d9 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -72,22 +72,6 @@ PECOFF_FILE_ALIGNMENT = 0x200;
#define PECOFF_EDATA_PADDING
#endif
-#if defined(CONFIG_DEBUG_ALIGN_RODATA)
-/*
- * 4 KB granule: 1 level 2 entry
- * 16 KB granule: 128 level 3 entries, with contiguous bit
- * 64 KB granule: 32 level 3 entries, with contiguous bit
- */
-#define SEGMENT_ALIGN SZ_2M
-#else
-/*
- * 4 KB granule: 16 level 3 entries, with contiguous bit
- * 16 KB granule: 4 level 3 entries, without contiguous bit
- * 64 KB granule: 1 level 3 entry
- */
-#define SEGMENT_ALIGN SZ_64K
-#endif
-
SECTIONS
{
/*
@@ -192,7 +176,7 @@ SECTIONS
_data = .;
_sdata = .;
- RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+ RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
/*
* Data written with the MMU off but read with the MMU on requires
diff --git a/arch/arm64/kvm/hyp/s2-setup.c b/arch/arm64/kvm/hyp/s2-setup.c
index b81f4091c909..a81f5e10fc8c 100644
--- a/arch/arm64/kvm/hyp/s2-setup.c
+++ b/arch/arm64/kvm/hyp/s2-setup.c
@@ -70,7 +70,7 @@ u32 __hyp_text __init_stage2_translation(void)
* Management in ID_AA64MMFR1_EL1 and enable the feature in VTCR_EL2.
*/
tmp = (read_sysreg(id_aa64mmfr1_el1) >> ID_AA64MMFR1_HADBS_SHIFT) & 0xf;
- if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) && tmp)
+ if (tmp)
val |= VTCR_EL2_HA;
/*
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index c86b7909ef31..a0abc142c92b 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -17,3 +17,5 @@ CFLAGS_atomic_ll_sc.o := -fcall-used-x0 -ffixed-x1 -ffixed-x2 \
-fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
-fcall-saved-x18
+
+lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c
new file mode 100644
index 000000000000..b6ceafdb8b72
--- /dev/null
+++ b/arch/arm64/lib/uaccess_flushcache.c
@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2017 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/uaccess.h>
+#include <asm/barrier.h>
+#include <asm/cacheflush.h>
+
+void memcpy_flushcache(void *dst, const void *src, size_t cnt)
+{
+ /*
+ * We assume this should not be called with @dst pointing to
+ * non-cacheable memory, such that we don't need an explicit
+ * barrier to order the cache maintenance against the memcpy.
+ */
+ memcpy(dst, src, cnt);
+ __clean_dcache_area_pop(dst, cnt);
+}
+EXPORT_SYMBOL_GPL(memcpy_flushcache);
+
+void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
+ size_t len)
+{
+ memcpy_flushcache(to, page_address(page) + offset, len);
+}
+
+unsigned long __copy_user_flushcache(void *to, const void __user *from,
+ unsigned long n)
+{
+ unsigned long rc = __arch_copy_from_user(to, from, n);
+
+ /* See above */
+ __clean_dcache_area_pop(to, n - rc);
+ return rc;
+}
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 83c27b6e6dca..7f1dbe962cf5 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -109,20 +109,25 @@ ENTRY(__clean_dcache_area_pou)
ENDPROC(__clean_dcache_area_pou)
/*
- * __dma_inv_area(start, size)
- * - start - virtual start address of region
+ * __inval_dcache_area(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are invalidated. Any partial lines at the ends of the interval are
+ * also cleaned to PoC to prevent data loss.
+ *
+ * - kaddr - kernel address
* - size - size in question
*/
-__dma_inv_area:
- add x1, x1, x0
+ENTRY(__inval_dcache_area)
/* FALLTHROUGH */
/*
- * __inval_cache_range(start, end)
- * - start - start address of region
- * - end - end address of region
+ * __dma_inv_area(start, size)
+ * - start - virtual start address of region
+ * - size - size in question
*/
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+ add x1, x1, x0
dcache_line_size x2, x3
sub x3, x2, #1
tst x1, x3 // end cache line aligned?
@@ -140,7 +145,7 @@ ENTRY(__inval_cache_range)
b.lo 2b
dsb sy
ret
-ENDPIPROC(__inval_cache_range)
+ENDPIPROC(__inval_dcache_area)
ENDPROC(__dma_inv_area)
/*
@@ -167,6 +172,20 @@ ENDPIPROC(__clean_dcache_area_poc)
ENDPROC(__dma_clean_area)
/*
+ * __clean_dcache_area_pop(kaddr, size)
+ *
+ * Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * are cleaned to the PoP.
+ *
+ * - kaddr - kernel address
+ * - size - size in question
+ */
+ENTRY(__clean_dcache_area_pop)
+ dcache_by_line_op cvap, sy, x0, x1, x2, x3
+ ret
+ENDPIPROC(__clean_dcache_area_pop)
+
+/*
* __dma_flush_area(start, size)
*
* clean & invalidate D / U line
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index f27d4dd04384..614af886b7ef 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -42,7 +42,7 @@ static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
return prot;
}
-static struct gen_pool *atomic_pool;
+static struct gen_pool *atomic_pool __ro_after_init;
#define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K
static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE;
@@ -425,7 +425,7 @@ static int __init atomic_pool_init(void)
gen_pool_set_algo(atomic_pool,
gen_pool_first_fit_order_align,
- (void *)PAGE_SHIFT);
+ NULL);
pr_info("DMA: preallocated %zu KiB pool for atomic allocations\n",
atomic_pool_size / 1024);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2509e4fe6992..89993c4be1be 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -34,6 +34,7 @@
#include <linux/hugetlb.h>
#include <asm/bug.h>
+#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
@@ -82,6 +83,49 @@ static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
}
#endif
+static void data_abort_decode(unsigned int esr)
+{
+ pr_alert("Data abort info:\n");
+
+ if (esr & ESR_ELx_ISV) {
+ pr_alert(" Access size = %u byte(s)\n",
+ 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT));
+ pr_alert(" SSE = %lu, SRT = %lu\n",
+ (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT,
+ (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT);
+ pr_alert(" SF = %lu, AR = %lu\n",
+ (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
+ (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
+ } else {
+ pr_alert(" ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+ }
+
+ pr_alert(" CM = %lu, WnR = %lu\n",
+ (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT,
+ (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT);
+}
+
+/*
+ * Decode mem abort information
+ */
+static void mem_abort_decode(unsigned int esr)
+{
+ pr_alert("Mem abort info:\n");
+
+ pr_alert(" Exception class = %s, IL = %u bits\n",
+ esr_get_class_string(esr),
+ (esr & ESR_ELx_IL) ? 32 : 16);
+ pr_alert(" SET = %lu, FnV = %lu\n",
+ (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT,
+ (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT);
+ pr_alert(" EA = %lu, S1PTW = %lu\n",
+ (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT,
+ (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT);
+
+ if (esr_is_data_abort(esr))
+ data_abort_decode(esr);
+}
+
/*
* Dump out the page tables associated with 'addr' in the currently active mm.
*/
@@ -139,7 +183,6 @@ void show_pte(unsigned long addr)
pr_cont("\n");
}
-#ifdef CONFIG_ARM64_HW_AFDBM
/*
* This function sets the access flags (dirty, accessed), as well as write
* permission, and only to a more permissive setting.
@@ -154,18 +197,13 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
- pteval_t old_pteval;
- unsigned int tmp;
+ pteval_t old_pteval, pteval;
if (pte_same(*ptep, entry))
return 0;
/* only preserve the access flags and write permission */
- pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
-
- /* set PTE_RDONLY if actual read-only or clean PTE */
- if (!pte_write(entry) || !pte_sw_dirty(entry))
- pte_val(entry) |= PTE_RDONLY;
+ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
/*
* Setting the flags must be done atomically to avoid racing with the
@@ -174,21 +212,18 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
* (calculated as: a & b == ~(~a | ~b)).
*/
pte_val(entry) ^= PTE_RDONLY;
- asm volatile("// ptep_set_access_flags\n"
- " prfm pstl1strm, %2\n"
- "1: ldxr %0, %2\n"
- " eor %0, %0, %3 // negate PTE_RDONLY in *ptep\n"
- " orr %0, %0, %4 // set flags\n"
- " eor %0, %0, %3 // negate final PTE_RDONLY\n"
- " stxr %w1, %0, %2\n"
- " cbnz %w1, 1b\n"
- : "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
- : "L" (PTE_RDONLY), "r" (pte_val(entry)));
+ pteval = READ_ONCE(pte_val(*ptep));
+ do {
+ old_pteval = pteval;
+ pteval ^= PTE_RDONLY;
+ pteval |= pte_val(entry);
+ pteval ^= PTE_RDONLY;
+ pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval);
+ } while (pteval != old_pteval);
flush_tlb_fix_spurious_fault(vma, address);
return 1;
}
-#endif
static bool is_el1_instruction_abort(unsigned int esr)
{
@@ -248,6 +283,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned int esr,
pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
addr);
+ mem_abort_decode(esr);
+
show_pte(addr);
die("Oops", regs, esr);
bust_spinlocks(0);
@@ -435,8 +472,11 @@ retry:
* the mmap_sem because it would already be released
* in __lock_page_or_retry in mm/filemap.c.
*/
- if (fatal_signal_pending(current))
+ if (fatal_signal_pending(current)) {
+ if (!user_mode(regs))
+ goto no_context;
return 0;
+ }
/*
* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
@@ -702,6 +742,8 @@ asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
inf->name, esr, addr);
+ mem_abort_decode(esr);
+
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 21a8d828cbf4..e36ed5087b5c 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -83,3 +83,19 @@ EXPORT_SYMBOL(flush_dcache_page);
* Additional functions defined in assembly.
*/
EXPORT_SYMBOL(flush_icache_range);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+ /* Ensure order against any prior non-cacheable writes */
+ dmb(osh);
+ __clean_dcache_area_pop(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+void arch_invalidate_pmem(void *addr, size_t size)
+{
+ __inval_dcache_area(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_invalidate_pmem);
+#endif
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 656e0ece2289..6cb0fa92a651 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,6 +41,16 @@ int pud_huge(pud_t pud)
#endif
}
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+ unsigned long pfn = pte_pfn(pte);
+
+ return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
static int find_num_contig(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, size_t *pgsize)
{
@@ -58,15 +68,107 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
return CONT_PTES;
}
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+ int contig_ptes = 0;
+
+ *pgsize = size;
+
+ switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE:
+ contig_ptes = 1;
+ break;
+ case CONT_PMD_SIZE:
+ *pgsize = PMD_SIZE;
+ contig_ptes = CONT_PMDS;
+ break;
+ case CONT_PTE_SIZE:
+ *pgsize = PAGE_SIZE;
+ contig_ptes = CONT_PTES;
+ break;
+ }
+
+ return contig_ptes;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = { .vm_mm = mm };
+ pte_t orig_pte = huge_ptep_get(ptep);
+ bool valid = pte_valid(orig_pte);
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+ pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+ /*
+ * If HW_AFDBM is enabled, then the HW could turn on
+ * the dirty bit for any page in the set, so check
+ * them all. All hugetlb entries are already young.
+ */
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+ }
+
+ if (valid)
+ flush_tlb_range(&vma, saddr, addr);
+ return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ struct vm_area_struct vma = { .vm_mm = mm };
+ unsigned long i, saddr = addr;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
size_t pgsize;
int i;
int ncontig;
- unsigned long pfn;
+ unsigned long pfn, dpfn;
pgprot_t hugeprot;
+ /*
+ * Code needs to be expanded to handle huge swap and migration
+ * entries. Needed for HUGETLB and MEMORY_FAILURE.
+ */
+ WARN_ON(!pte_present(pte));
+
if (!pte_cont(pte)) {
set_pte_at(mm, addr, ptep, pte);
return;
@@ -74,17 +176,30 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
pfn = pte_pfn(pte);
- hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
- for (i = 0; i < ncontig; i++) {
+ dpfn = pgsize >> PAGE_SHIFT;
+ hugeprot = pte_pgprot(pte);
+
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
pte_val(pfn_pte(pfn, hugeprot)));
set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
- ptep++;
- pfn += pgsize >> PAGE_SHIFT;
- addr += pgsize;
}
}
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, ptep++)
+ set_pte(ptep, pte);
+}
+
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz)
{
@@ -144,19 +259,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return NULL;
pud = pud_offset(pgd, addr);
- if (pud_none(*pud))
+ if (sz != PUD_SIZE && pud_none(*pud))
return NULL;
- /* swap or huge page */
- if (!pud_present(*pud) || pud_huge(*pud))
+ /* hugepage or swap? */
+ if (pud_huge(*pud) || !pud_present(*pud))
return (pte_t *)pud;
/* table; check the next level */
+ if (sz == CONT_PMD_SIZE)
+ addr &= CONT_PMD_MASK;
+
pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd))
+ if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+ pmd_none(*pmd))
return NULL;
- if (!pmd_present(*pmd) || pmd_huge(*pmd))
+ if (pmd_huge(*pmd) || !pmd_present(*pmd))
return (pte_t *)pmd;
+ if (sz == CONT_PTE_SIZE) {
+ pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
+ return pte;
+ }
+
return NULL;
}
@@ -176,111 +300,133 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
return entry;
}
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, unsigned long sz)
+{
+ int i, ncontig;
+ size_t pgsize;
+
+ ncontig = num_contig_ptes(sz, &pgsize);
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+ pte_clear(mm, addr, ptep);
+}
+
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- pte_t pte;
+ int ncontig;
+ size_t pgsize;
+ pte_t orig_pte = huge_ptep_get(ptep);
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize;
- bool is_dirty = false;
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- /* save the 1st pte to return */
- pte = ptep_get_and_clear(mm, addr, ptep);
- for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
- /*
- * If HW_AFDBM is enabled, then the HW could
- * turn on the dirty bit for any of the page
- * in the set, so check them all.
- */
- ++ptep;
- if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
- is_dirty = true;
- }
- if (is_dirty)
- return pte_mkdirty(pte);
- else
- return pte;
- } else {
+ if (!pte_cont(orig_pte))
return ptep_get_and_clear(mm, addr, ptep);
- }
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+
+ return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- if (pte_cont(pte)) {
- int ncontig, i, changed = 0;
- size_t pgsize = 0;
- unsigned long pfn = pte_pfn(pte);
- /* Select all bits except the pfn */
- pgprot_t hugeprot =
- __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
- pte_val(pte));
-
- pfn = pte_pfn(pte);
- ncontig = find_num_contig(vma->vm_mm, addr, ptep,
- &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize) {
- changed |= ptep_set_access_flags(vma, addr, ptep,
- pfn_pte(pfn,
- hugeprot),
- dirty);
- pfn += pgsize >> PAGE_SHIFT;
- }
- return changed;
- } else {
+ int ncontig, i, changed = 0;
+ size_t pgsize = 0;
+ unsigned long pfn = pte_pfn(pte), dpfn;
+ pgprot_t hugeprot;
+ pte_t orig_pte;
+
+ if (!pte_cont(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
- }
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+ if (!pte_same(orig_pte, pte))
+ changed = 1;
+
+ /* Make sure we don't lose the dirty state */
+ if (pte_dirty(orig_pte))
+ pte = pte_mkdirty(pte);
+
+ hugeprot = pte_pgprot(pte);
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+
+ return changed;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize = 0;
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
- ptep_set_wrprotect(mm, addr, ptep);
- } else {
+ unsigned long pfn, dpfn;
+ pgprot_t hugeprot;
+ int ncontig, i;
+ size_t pgsize;
+ pte_t pte;
+
+ if (!pte_cont(*ptep)) {
ptep_set_wrprotect(mm, addr, ptep);
+ return;
}
+
+ ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ dpfn = pgsize >> PAGE_SHIFT;
+
+ pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+ pte = pte_wrprotect(pte);
+
+ hugeprot = pte_pgprot(pte);
+ pfn = pte_pfn(pte);
+
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+ set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
}
void huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
- if (pte_cont(*ptep)) {
- int ncontig, i;
- size_t pgsize = 0;
-
- ncontig = find_num_contig(vma->vm_mm, addr, ptep,
- &pgsize);
- for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
- ptep_clear_flush(vma, addr, ptep);
- } else {
+ size_t pgsize;
+ int ncontig;
+
+ if (!pte_cont(*ptep)) {
ptep_clear_flush(vma, addr, ptep);
+ return;
}
+
+ ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+ clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
}
static __init int setup_hugepagesz(char *opt)
{
unsigned long ps = memparse(opt, &opt);
- if (ps == PMD_SIZE) {
- hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
- } else if (ps == PUD_SIZE) {
- hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else {
- hugetlb_bad_size();
- pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
- return 0;
+ switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+ case PUD_SIZE:
+#endif
+ case PMD_SIZE * CONT_PMDS:
+ case PMD_SIZE:
+ case PAGE_SIZE * CONT_PTES:
+ hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+ return 1;
}
- return 1;
+
+ hugetlb_bad_size();
+ pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+ return 0;
}
__setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+ if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+ hugetlb_add_hstate(CONT_PTE_SHIFT);
+ return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index b02a9268dfbf..783de51a6c4e 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -44,8 +44,12 @@
#define A64_COND_NE AARCH64_INSN_COND_NE /* != */
#define A64_COND_CS AARCH64_INSN_COND_CS /* unsigned >= */
#define A64_COND_HI AARCH64_INSN_COND_HI /* unsigned > */
+#define A64_COND_LS AARCH64_INSN_COND_LS /* unsigned <= */
+#define A64_COND_CC AARCH64_INSN_COND_CC /* unsigned < */
#define A64_COND_GE AARCH64_INSN_COND_GE /* signed >= */
#define A64_COND_GT AARCH64_INSN_COND_GT /* signed > */
+#define A64_COND_LE AARCH64_INSN_COND_LE /* signed <= */
+#define A64_COND_LT AARCH64_INSN_COND_LT /* signed < */
#define A64_B_(cond, imm19) A64_COND_BRANCH(cond, (imm19) << 2)
/* Unconditional branch (immediate) */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index f32144b2e07f..ba38d403abb2 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -527,10 +527,14 @@ emit_bswap_uxt:
/* IF (dst COND src) JUMP off */
case BPF_JMP | BPF_JEQ | BPF_X:
case BPF_JMP | BPF_JGT | BPF_X:
+ case BPF_JMP | BPF_JLT | BPF_X:
case BPF_JMP | BPF_JGE | BPF_X:
+ case BPF_JMP | BPF_JLE | BPF_X:
case BPF_JMP | BPF_JNE | BPF_X:
case BPF_JMP | BPF_JSGT | BPF_X:
+ case BPF_JMP | BPF_JSLT | BPF_X:
case BPF_JMP | BPF_JSGE | BPF_X:
+ case BPF_JMP | BPF_JSLE | BPF_X:
emit(A64_CMP(1, dst, src), ctx);
emit_cond_jmp:
jmp_offset = bpf2a64_offset(i + off, i, ctx);
@@ -542,9 +546,15 @@ emit_cond_jmp:
case BPF_JGT:
jmp_cond = A64_COND_HI;
break;
+ case BPF_JLT:
+ jmp_cond = A64_COND_CC;
+ break;
case BPF_JGE:
jmp_cond = A64_COND_CS;
break;
+ case BPF_JLE:
+ jmp_cond = A64_COND_LS;
+ break;
case BPF_JSET:
case BPF_JNE:
jmp_cond = A64_COND_NE;
@@ -552,9 +562,15 @@ emit_cond_jmp:
case BPF_JSGT:
jmp_cond = A64_COND_GT;
break;
+ case BPF_JSLT:
+ jmp_cond = A64_COND_LT;
+ break;
case BPF_JSGE:
jmp_cond = A64_COND_GE;
break;
+ case BPF_JSLE:
+ jmp_cond = A64_COND_LE;
+ break;
default:
return -EFAULT;
}
@@ -566,10 +582,14 @@ emit_cond_jmp:
/* IF (dst COND imm) JUMP off */
case BPF_JMP | BPF_JEQ | BPF_K:
case BPF_JMP | BPF_JGT | BPF_K:
+ case BPF_JMP | BPF_JLT | BPF_K:
case BPF_JMP | BPF_JGE | BPF_K:
+ case BPF_JMP | BPF_JLE | BPF_K:
case BPF_JMP | BPF_JNE | BPF_K:
case BPF_JMP | BPF_JSGT | BPF_K:
+ case BPF_JMP | BPF_JSLT | BPF_K:
case BPF_JMP | BPF_JSGE | BPF_K:
+ case BPF_JMP | BPF_JSLE | BPF_K:
emit_a64_mov_i(1, tmp, imm, ctx);
emit(A64_CMP(1, dst, tmp), ctx);
goto emit_cond_jmp;