summaryrefslogtreecommitdiffstats
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig27
-rw-r--r--arch/arm64/Kconfig.debug4
-rw-r--r--arch/arm64/Makefile4
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi2
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gx.dtsi2
-rw-r--r--arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi5
-rw-r--r--arch/arm64/boot/dts/broadcom/ns2.dtsi11
-rw-r--r--arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts5
-rw-r--r--arch/arm64/boot/dts/marvell/armada-3720-db.dts6
-rw-r--r--arch/arm64/boot/dts/marvell/armada-37xx.dtsi7
-rw-r--r--arch/arm64/boot/dts/marvell/armada-ap806.dtsi3
-rw-r--r--arch/arm64/configs/defconfig1
-rw-r--r--arch/arm64/include/asm/Kbuild1
-rw-r--r--arch/arm64/include/asm/acpi.h2
-rw-r--r--arch/arm64/include/asm/arch_gicv3.h81
-rw-r--r--arch/arm64/include/asm/arch_timer.h43
-rw-r--r--arch/arm64/include/asm/bug.h32
-rw-r--r--arch/arm64/include/asm/cache.h38
-rw-r--r--arch/arm64/include/asm/cacheflush.h5
-rw-r--r--arch/arm64/include/asm/cachetype.h100
-rw-r--r--arch/arm64/include/asm/cpucaps.h3
-rw-r--r--arch/arm64/include/asm/cpufeature.h6
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/current.h2
-rw-r--r--arch/arm64/include/asm/device.h3
-rw-r--r--arch/arm64/include/asm/dma-mapping.h13
-rw-r--r--arch/arm64/include/asm/efi.h24
-rw-r--r--arch/arm64/include/asm/esr.h6
-rw-r--r--arch/arm64/include/asm/extable.h25
-rw-r--r--arch/arm64/include/asm/hardirq.h2
-rw-r--r--arch/arm64/include/asm/hw_breakpoint.h4
-rw-r--r--arch/arm64/include/asm/insn.h30
-rw-r--r--arch/arm64/include/asm/kexec.h52
-rw-r--r--arch/arm64/include/asm/kvm_asm.h5
-rw-r--r--arch/arm64/include/asm/kvm_host.h13
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h14
-rw-r--r--arch/arm64/include/asm/mmu.h1
-rw-r--r--arch/arm64/include/asm/module.h14
-rw-r--r--arch/arm64/include/asm/pgtable-types.h4
-rw-r--r--arch/arm64/include/asm/pgtable.h10
-rw-r--r--arch/arm64/include/asm/processor.h2
-rw-r--r--arch/arm64/include/asm/sections.h2
-rw-r--r--arch/arm64/include/asm/smp.h3
-rw-r--r--arch/arm64/include/asm/sysreg.h167
-rw-r--r--arch/arm64/include/asm/uaccess.h83
-rw-r--r--arch/arm64/include/asm/unistd.h3
-rw-r--r--arch/arm64/include/asm/unistd32.h10
-rw-r--r--arch/arm64/include/asm/virt.h31
-rw-r--r--arch/arm64/include/uapi/asm/hwcap.h3
-rw-r--r--arch/arm64/include/uapi/asm/kvm.h4
-rw-r--r--arch/arm64/kernel/Makefile3
-rw-r--r--arch/arm64/kernel/acpi.c3
-rw-r--r--arch/arm64/kernel/alternative.c11
-rw-r--r--arch/arm64/kernel/arm64ksyms.c2
-rw-r--r--arch/arm64/kernel/cacheinfo.c38
-rw-r--r--arch/arm64/kernel/cpu_errata.c15
-rw-r--r--arch/arm64/kernel/cpufeature.c43
-rw-r--r--arch/arm64/kernel/cpuidle.c2
-rw-r--r--arch/arm64/kernel/cpuinfo.c37
-rw-r--r--arch/arm64/kernel/crash_dump.c71
-rw-r--r--arch/arm64/kernel/debug-monitors.c2
-rw-r--r--arch/arm64/kernel/efi-header.S155
-rw-r--r--arch/arm64/kernel/head.S222
-rw-r--r--arch/arm64/kernel/hibernate.c10
-rw-r--r--arch/arm64/kernel/hyp-stub.S38
-rw-r--r--arch/arm64/kernel/insn.c106
-rw-r--r--arch/arm64/kernel/kaslr.c10
-rw-r--r--arch/arm64/kernel/machine_kexec.c170
-rw-r--r--arch/arm64/kernel/module-plts.c108
-rw-r--r--arch/arm64/kernel/module.c2
-rw-r--r--arch/arm64/kernel/module.lds1
-rw-r--r--arch/arm64/kernel/perf_event.c120
-rw-r--r--arch/arm64/kernel/probes/kprobes.c6
-rw-r--r--arch/arm64/kernel/process.c2
-rw-r--r--arch/arm64/kernel/reloc_test_core.c81
-rw-r--r--arch/arm64/kernel/reloc_test_syms.S83
-rw-r--r--arch/arm64/kernel/setup.c12
-rw-r--r--arch/arm64/kernel/smp.c81
-rw-r--r--arch/arm64/kernel/traps.c28
-rw-r--r--arch/arm64/kernel/vdso/.gitignore1
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S27
-rw-r--r--arch/arm64/kvm/handle_exit.c19
-rw-r--r--arch/arm64/kvm/hyp-init.S46
-rw-r--r--arch/arm64/kvm/hyp.S5
-rw-r--r--arch/arm64/kvm/hyp/hyp-entry.S43
-rw-r--r--arch/arm64/kvm/hyp/tlb.c86
-rw-r--r--arch/arm64/kvm/reset.c2
-rw-r--r--arch/arm64/kvm/sys_regs.c500
-rw-r--r--arch/arm64/kvm/sys_regs.h23
-rw-r--r--arch/arm64/kvm/sys_regs_generic_v8.c4
-rw-r--r--arch/arm64/lib/copy_in_user.S4
-rw-r--r--arch/arm64/mm/context.c3
-rw-r--r--arch/arm64/mm/dma-mapping.c135
-rw-r--r--arch/arm64/mm/fault.c97
-rw-r--r--arch/arm64/mm/flush.c4
-rw-r--r--arch/arm64/mm/hugetlbpage.c14
-rw-r--r--arch/arm64/mm/init.c181
-rw-r--r--arch/arm64/mm/kasan_init.c2
-rw-r--r--arch/arm64/mm/mmu.c311
-rw-r--r--arch/arm64/mm/pageattr.c16
-rw-r--r--arch/arm64/net/bpf_jit.h19
-rw-r--r--arch/arm64/net/bpf_jit_comp.c34
102 files changed, 2595 insertions, 1363 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index a39029b5414e..3dcd7ec69bca 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,6 +2,7 @@ config ARM64
def_bool y
select ACPI_CCA_REQUIRED if ACPI
select ACPI_GENERIC_GSI if ACPI
+ select ACPI_GTDT if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ACPI_MCFG if ACPI
select ACPI_SPCR_TABLE if ACPI
@@ -60,7 +61,6 @@ config ARM64
select HAVE_ALIGNED_STRUCT_PAGE if SLUB
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_BITREVERSE
- select HAVE_ARCH_HARDENED_USERCOPY
select HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
@@ -508,6 +508,16 @@ config QCOM_FALKOR_ERRATUM_1009
If unsure, say Y.
+config QCOM_QDF2400_ERRATUM_0065
+ bool "QDF2400 E0065: Incorrect GITS_TYPER.ITT_Entry_size"
+ default y
+ help
+ On Qualcomm Datacenter Technologies QDF2400 SoC, ITS hardware reports
+ ITE size incorrectly. The GITS_TYPER.ITT_Entry_size field should have
+ been indicated as 16Bytes (0xf), not 8Bytes (0x7).
+
+ If unsure, say Y.
+
endmenu
@@ -726,6 +736,17 @@ config KEXEC
but it is independent of the system firmware. And like a reboot
you can start any kernel with it, not just Linux.
+config CRASH_DUMP
+ bool "Build kdump crash kernel"
+ help
+ Generate crash dump after being started by kexec. This should
+ be normally only set in special crash dump kernels which are
+ loaded in the main kernel with kexec-tools into a specially
+ reserved region and then later executed after a crash by
+ kdump/kexec.
+
+ For more details see Documentation/kdump/kdump.txt
+
config XEN_DOM0
def_bool y
depends on XEN
@@ -1063,6 +1084,10 @@ config SYSVIPC_COMPAT
def_bool y
depends on COMPAT && SYSVIPC
+config KEYS_COMPAT
+ def_bool y
+ depends on COMPAT && KEYS
+
endmenu
menu "Power management options"
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index fca2f02cde68..cc6bd559af85 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -92,6 +92,10 @@ config DEBUG_EFI
the kernel that are only useful when using a debug build of the
UEFI firmware
+config ARM64_RELOC_TEST
+ depends on m
+ tristate "Relocation testing module"
+
source "drivers/hwtracing/coresight/Kconfig"
endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index b9a4a934ca05..7dedf2d8494e 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -37,10 +37,12 @@ $(warning LSE atomics not supported by binutils)
endif
endif
+ifeq ($(CONFIG_ARM64), y)
brokengasinst := $(call as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n,,-DCONFIG_BROKEN_GAS_INST=1)
-ifneq ($(brokengasinst),)
+ ifneq ($(brokengasinst),)
$(warning Detected assembler with broken .inst; disassembly will be unreliable)
+ endif
endif
KBUILD_CFLAGS += -mgeneral-regs-only $(lseinstr) $(brokengasinst)
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 1c64ea2d23f9..0565779e66fa 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -179,8 +179,10 @@
usbphy: phy@01c19400 {
compatible = "allwinner,sun50i-a64-usb-phy";
reg = <0x01c19400 0x14>,
+ <0x01c1a800 0x4>,
<0x01c1b800 0x4>;
reg-names = "phy_ctrl",
+ "pmu0",
"pmu1";
clocks = <&ccu CLK_USB_PHY0>,
<&ccu CLK_USB_PHY1>;
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 5d995f7724af..620495a43363 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -380,7 +380,7 @@
#size-cells = <2>;
ranges = <0x0 0x0 0x0 0xc8834000 0x0 0x2000>;
- rng {
+ hwrng: rng {
compatible = "amlogic,meson-rng";
reg = <0x0 0x0 0x0 0x4>;
};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
index 04b3324bc132..a375cb21cc8b 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
@@ -524,3 +524,8 @@
&vpu {
compatible = "amlogic,meson-gxbb-vpu", "amlogic,meson-gx-vpu";
};
+
+&hwrng {
+ clocks = <&clkc CLKID_RNG0>;
+ clock-names = "core";
+};
diff --git a/arch/arm64/boot/dts/broadcom/ns2.dtsi b/arch/arm64/boot/dts/broadcom/ns2.dtsi
index 9f9e203c09c5..bcb03fc32665 100644
--- a/arch/arm64/boot/dts/broadcom/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/ns2.dtsi
@@ -114,6 +114,7 @@
pcie0: pcie@20020000 {
compatible = "brcm,iproc-pcie";
reg = <0 0x20020000 0 0x1000>;
+ dma-coherent;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
@@ -144,6 +145,7 @@
pcie4: pcie@50020000 {
compatible = "brcm,iproc-pcie";
reg = <0 0x50020000 0 0x1000>;
+ dma-coherent;
#interrupt-cells = <1>;
interrupt-map-mask = <0 0 0 0>;
@@ -174,6 +176,7 @@
pcie8: pcie@60c00000 {
compatible = "brcm,iproc-pcie-paxc";
reg = <0 0x60c00000 0 0x1000>;
+ dma-coherent;
linux,pci-domain = <8>;
bus-range = <0x0 0x1>;
@@ -203,6 +206,7 @@
<0x61030000 0x100>;
reg-names = "amac_base", "idm_base", "nicpm_base";
interrupts = <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
phy-handle = <&gphy0>;
phy-mode = "rgmii";
status = "disabled";
@@ -213,6 +217,7 @@
reg = <0x612c0000 0x445>; /* PDC FS0 regs */
interrupts = <GIC_SPI 187 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -222,6 +227,7 @@
reg = <0x612e0000 0x445>; /* PDC FS1 regs */
interrupts = <GIC_SPI 189 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -231,6 +237,7 @@
reg = <0x61300000 0x445>; /* PDC FS2 regs */
interrupts = <GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -240,6 +247,7 @@
reg = <0x61320000 0x445>; /* PDC FS3 regs */
interrupts = <GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>;
#mbox-cells = <1>;
+ dma-coherent;
brcm,rx-status-len = <32>;
brcm,use-bcm-hdr;
};
@@ -644,6 +652,7 @@
sata: ahci@663f2000 {
compatible = "brcm,iproc-ahci", "generic-ahci";
reg = <0x663f2000 0x1000>;
+ dma-coherent;
reg-names = "ahci";
interrupts = <GIC_SPI 438 IRQ_TYPE_LEVEL_HIGH>;
#address-cells = <1>;
@@ -667,6 +676,7 @@
compatible = "brcm,sdhci-iproc-cygnus";
reg = <0x66420000 0x100>;
interrupts = <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
bus-width = <8>;
clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
status = "disabled";
@@ -676,6 +686,7 @@
compatible = "brcm,sdhci-iproc-cygnus";
reg = <0x66430000 0x100>;
interrupts = <GIC_SPI 422 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
bus-width = <8>;
clocks = <&genpll_sw BCM_NS2_GENPLL_SW_SDIO_CLK>;
status = "disabled";
diff --git a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
index dba3c131c62c..9b4ba7169210 100644
--- a/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
+++ b/arch/arm64/boot/dts/hisilicon/hi6220-hikey.dts
@@ -98,6 +98,11 @@
assigned-clocks = <&sys_ctrl HI6220_UART1_SRC>;
assigned-clock-rates = <150000000>;
status = "ok";
+
+ bluetooth {
+ compatible = "ti,wl1835-st";
+ enable-gpios = <&gpio1 7 GPIO_ACTIVE_HIGH>;
+ };
};
uart2: uart@f7112000 {
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-db.dts b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
index 86602c907a61..a07a0c1cd4e6 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-db.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-db.dts
@@ -116,6 +116,12 @@
status = "okay";
};
+/* CON27 */
+&usb2 {
+ status = "okay";
+};
+
+
&mdio {
status = "okay";
phy0: ethernet-phy@0 {
diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
index b48d668a6ab6..42747b7db683 100644
--- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi
@@ -200,6 +200,13 @@
status = "disabled";
};
+ usb2: usb@5e000 {
+ compatible = "marvell,armada-3700-ehci";
+ reg = <0x5e000 0x2000>;
+ interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
+ status = "disabled";
+ };
+
xor@60900 {
compatible = "marvell,armada-3700-xor";
reg = <0x60900 0x100
diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
index a749ba2edec4..5019c8f4acd0 100644
--- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi
@@ -235,7 +235,8 @@
#clock-cells = <1>;
clock-output-names = "ap-cpu-cluster-0",
"ap-cpu-cluster-1",
- "ap-fixed", "ap-mss";
+ "ap-fixed", "ap-mss",
+ "ap-emmc";
reg = <0x6f4000 0x1000>;
};
};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 7c48028ec64a..927ee18bbdf2 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -82,6 +82,7 @@ CONFIG_CMA=y
CONFIG_SECCOMP=y
CONFIG_XEN=y
CONFIG_KEXEC=y
+CONFIG_CRASH_DUMP=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
CONFIG_COMPAT=y
CONFIG_CPU_IDLE=y
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index a12f1afc95a3..a7a97a608033 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -29,6 +29,7 @@ generic-y += rwsem.h
generic-y += segment.h
generic-y += sembuf.h
generic-y += serial.h
+generic-y += set_memory.h
generic-y += shmbuf.h
generic-y += simd.h
generic-y += sizes.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index c1976c0adca7..0e99978da3f0 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -85,6 +85,8 @@ static inline bool acpi_has_cpu_in_madt(void)
return true;
}
+struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu);
+
static inline void arch_fix_phys_package_id(int num, u32 slot) { }
void __init acpi_init_cpus(void);
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index f37e3a21f6e7..1a98bc8602a2 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -20,69 +20,14 @@
#include <asm/sysreg.h>
-#define ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
-#define ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
-#define ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
-#define ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5)
-#define ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
-#define ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
-#define ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
-#define ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
-#define ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3)
-
-#define ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
-
-/*
- * System register definitions
- */
-#define ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4)
-#define ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0)
-#define ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1)
-#define ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2)
-#define ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3)
-#define ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5)
-#define ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7)
-
-#define __LR0_EL2(x) sys_reg(3, 4, 12, 12, x)
-#define __LR8_EL2(x) sys_reg(3, 4, 12, 13, x)
-
-#define ICH_LR0_EL2 __LR0_EL2(0)
-#define ICH_LR1_EL2 __LR0_EL2(1)
-#define ICH_LR2_EL2 __LR0_EL2(2)
-#define ICH_LR3_EL2 __LR0_EL2(3)
-#define ICH_LR4_EL2 __LR0_EL2(4)
-#define ICH_LR5_EL2 __LR0_EL2(5)
-#define ICH_LR6_EL2 __LR0_EL2(6)
-#define ICH_LR7_EL2 __LR0_EL2(7)
-#define ICH_LR8_EL2 __LR8_EL2(0)
-#define ICH_LR9_EL2 __LR8_EL2(1)
-#define ICH_LR10_EL2 __LR8_EL2(2)
-#define ICH_LR11_EL2 __LR8_EL2(3)
-#define ICH_LR12_EL2 __LR8_EL2(4)
-#define ICH_LR13_EL2 __LR8_EL2(5)
-#define ICH_LR14_EL2 __LR8_EL2(6)
-#define ICH_LR15_EL2 __LR8_EL2(7)
-
-#define __AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
-#define ICH_AP0R0_EL2 __AP0Rx_EL2(0)
-#define ICH_AP0R1_EL2 __AP0Rx_EL2(1)
-#define ICH_AP0R2_EL2 __AP0Rx_EL2(2)
-#define ICH_AP0R3_EL2 __AP0Rx_EL2(3)
-
-#define __AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x)
-#define ICH_AP1R0_EL2 __AP1Rx_EL2(0)
-#define ICH_AP1R1_EL2 __AP1Rx_EL2(1)
-#define ICH_AP1R2_EL2 __AP1Rx_EL2(2)
-#define ICH_AP1R3_EL2 __AP1Rx_EL2(3)
-
#ifndef __ASSEMBLY__
#include <linux/stringify.h>
#include <asm/barrier.h>
#include <asm/cacheflush.h>
-#define read_gicreg read_sysreg_s
-#define write_gicreg write_sysreg_s
+#define read_gicreg(r) read_sysreg_s(SYS_ ## r)
+#define write_gicreg(v, r) write_sysreg_s(v, SYS_ ## r)
/*
* Low-level accessors
@@ -93,13 +38,13 @@
static inline void gic_write_eoir(u32 irq)
{
- write_sysreg_s(irq, ICC_EOIR1_EL1);
+ write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
isb();
}
static inline void gic_write_dir(u32 irq)
{
- write_sysreg_s(irq, ICC_DIR_EL1);
+ write_sysreg_s(irq, SYS_ICC_DIR_EL1);
isb();
}
@@ -107,7 +52,7 @@ static inline u64 gic_read_iar_common(void)
{
u64 irqstat;
- irqstat = read_sysreg_s(ICC_IAR1_EL1);
+ irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
dsb(sy);
return irqstat;
}
@@ -124,7 +69,7 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
u64 irqstat;
nops(8);
- irqstat = read_sysreg_s(ICC_IAR1_EL1);
+ irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
nops(4);
mb();
@@ -133,40 +78,40 @@ static inline u64 gic_read_iar_cavium_thunderx(void)
static inline void gic_write_pmr(u32 val)
{
- write_sysreg_s(val, ICC_PMR_EL1);
+ write_sysreg_s(val, SYS_ICC_PMR_EL1);
}
static inline void gic_write_ctlr(u32 val)
{
- write_sysreg_s(val, ICC_CTLR_EL1);
+ write_sysreg_s(val, SYS_ICC_CTLR_EL1);
isb();
}
static inline void gic_write_grpen1(u32 val)
{
- write_sysreg_s(val, ICC_GRPEN1_EL1);
+ write_sysreg_s(val, SYS_ICC_GRPEN1_EL1);
isb();
}
static inline void gic_write_sgi1r(u64 val)
{
- write_sysreg_s(val, ICC_SGI1R_EL1);
+ write_sysreg_s(val, SYS_ICC_SGI1R_EL1);
}
static inline u32 gic_read_sre(void)
{
- return read_sysreg_s(ICC_SRE_EL1);
+ return read_sysreg_s(SYS_ICC_SRE_EL1);
}
static inline void gic_write_sre(u32 val)
{
- write_sysreg_s(val, ICC_SRE_EL1);
+ write_sysreg_s(val, SYS_ICC_SRE_EL1);
isb();
}
static inline void gic_write_bpr1(u32 val)
{
- asm volatile("msr_s " __stringify(ICC_BPR1_EL1) ", %0" : : "r" (val));
+ write_sysreg_s(val, SYS_ICC_BPR1_EL1);
}
#define gic_read_typer(c) readq_relaxed(c)
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index b4b34004a21e..74d08e44a651 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -25,6 +25,7 @@
#include <linux/bug.h>
#include <linux/init.h>
#include <linux/jump_label.h>
+#include <linux/smp.h>
#include <linux/types.h>
#include <clocksource/arm_arch_timer.h>
@@ -37,24 +38,44 @@ extern struct static_key_false arch_timer_read_ool_enabled;
#define needs_unstable_timer_counter_workaround() false
#endif
+enum arch_timer_erratum_match_type {
+ ate_match_dt,
+ ate_match_local_cap_id,
+ ate_match_acpi_oem_info,
+};
+
+struct clock_event_device;
struct arch_timer_erratum_workaround {
- const char *id; /* Indicate the Erratum ID */
+ enum arch_timer_erratum_match_type match_type;
+ const void *id;
+ const char *desc;
u32 (*read_cntp_tval_el0)(void);
u32 (*read_cntv_tval_el0)(void);
u64 (*read_cntvct_el0)(void);
+ int (*set_next_event_phys)(unsigned long, struct clock_event_device *);
+ int (*set_next_event_virt)(unsigned long, struct clock_event_device *);
};
-extern const struct arch_timer_erratum_workaround *timer_unstable_counter_workaround;
-
-#define arch_timer_reg_read_stable(reg) \
-({ \
- u64 _val; \
- if (needs_unstable_timer_counter_workaround()) \
- _val = timer_unstable_counter_workaround->read_##reg();\
- else \
- _val = read_sysreg(reg); \
- _val; \
+DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
+ timer_unstable_counter_workaround);
+
+#define arch_timer_reg_read_stable(reg) \
+({ \
+ u64 _val; \
+ if (needs_unstable_timer_counter_workaround()) { \
+ const struct arch_timer_erratum_workaround *wa; \
+ preempt_disable(); \
+ wa = __this_cpu_read(timer_unstable_counter_workaround); \
+ if (wa && wa->read_##reg) \
+ _val = wa->read_##reg(); \
+ else \
+ _val = read_sysreg(reg); \
+ preempt_enable(); \
+ } else { \
+ _val = read_sysreg(reg); \
+ } \
+ _val; \
})
/*
diff --git a/arch/arm64/include/asm/bug.h b/arch/arm64/include/asm/bug.h
index 561190d15881..366448eb0fb7 100644
--- a/arch/arm64/include/asm/bug.h
+++ b/arch/arm64/include/asm/bug.h
@@ -20,9 +20,6 @@
#include <asm/brk-imm.h>
-#ifdef CONFIG_GENERIC_BUG
-#define HAVE_ARCH_BUG
-
#ifdef CONFIG_DEBUG_BUGVERBOSE
#define _BUGVERBOSE_LOCATION(file, line) __BUGVERBOSE_LOCATION(file, line)
#define __BUGVERBOSE_LOCATION(file, line) \
@@ -36,28 +33,35 @@
#define _BUGVERBOSE_LOCATION(file, line)
#endif
-#define _BUG_FLAGS(flags) __BUG_FLAGS(flags)
+#ifdef CONFIG_GENERIC_BUG
-#define __BUG_FLAGS(flags) asm volatile ( \
+#define __BUG_ENTRY(flags) \
".pushsection __bug_table,\"a\"\n\t" \
".align 2\n\t" \
"0: .long 1f - 0b\n\t" \
_BUGVERBOSE_LOCATION(__FILE__, __LINE__) \
".short " #flags "\n\t" \
".popsection\n" \
- \
- "1: brk %[imm]" \
- :: [imm] "i" (BUG_BRK_IMM) \
-)
+ "1: "
+#else
+#define __BUG_ENTRY(flags) ""
+#endif
+
+#define __BUG_FLAGS(flags) \
+ asm volatile ( \
+ __BUG_ENTRY(flags) \
+ "brk %[imm]" :: [imm] "i" (BUG_BRK_IMM) \
+ );
-#define BUG() do { \
- _BUG_FLAGS(0); \
- unreachable(); \
+
+#define BUG() do { \
+ __BUG_FLAGS(0); \
+ unreachable(); \
} while (0)
-#define __WARN_TAINT(taint) _BUG_FLAGS(BUGFLAG_TAINT(taint))
+#define __WARN_FLAGS(flags) __BUG_FLAGS(BUGFLAG_WARNING|(flags))
-#endif /* ! CONFIG_GENERIC_BUG */
+#define HAVE_ARCH_BUG
#include <asm-generic/bug.h>
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 5082b30bc2c0..ea9bb4e0e9bb 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -16,7 +16,18 @@
#ifndef __ASM_CACHE_H
#define __ASM_CACHE_H
-#include <asm/cachetype.h>
+#include <asm/cputype.h>
+
+#define CTR_L1IP_SHIFT 14
+#define CTR_L1IP_MASK 3
+#define CTR_CWG_SHIFT 24
+#define CTR_CWG_MASK 15
+
+#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
+
+#define ICACHE_POLICY_VPIPT 0
+#define ICACHE_POLICY_VIPT 2
+#define ICACHE_POLICY_PIPT 3
#define L1_CACHE_SHIFT 7
#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT)
@@ -32,6 +43,31 @@
#ifndef __ASSEMBLY__
+#include <linux/bitops.h>
+
+#define ICACHEF_ALIASING 0
+#define ICACHEF_VPIPT 1
+extern unsigned long __icache_flags;
+
+/*
+ * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
+ * permitted in the I-cache.
+ */
+static inline int icache_is_aliasing(void)
+{
+ return test_bit(ICACHEF_ALIASING, &__icache_flags);
+}
+
+static inline int icache_is_vpipt(void)
+{
+ return test_bit(ICACHEF_VPIPT, &__icache_flags);
+}
+
+static inline u32 cache_type_cwg(void)
+{
+ return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK;
+}
+
#define __read_mostly __attribute__((__section__(".data..read_mostly")))
static inline int cache_line_size(void)
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 5a2a6ee65f65..d74a284abdc2 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -150,9 +150,6 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
{
}
-int set_memory_ro(unsigned long addr, int numpages);
-int set_memory_rw(unsigned long addr, int numpages);
-int set_memory_x(unsigned long addr, int numpages);
-int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_valid(unsigned long addr, unsigned long size, int enable);
#endif
diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h
deleted file mode 100644
index f5588692f1d4..000000000000
--- a/arch/arm64/include/asm/cachetype.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef __ASM_CACHETYPE_H
-#define __ASM_CACHETYPE_H
-
-#include <asm/cputype.h>
-
-#define CTR_L1IP_SHIFT 14
-#define CTR_L1IP_MASK 3
-#define CTR_CWG_SHIFT 24
-#define CTR_CWG_MASK 15
-
-#define ICACHE_POLICY_RESERVED 0
-#define ICACHE_POLICY_AIVIVT 1
-#define ICACHE_POLICY_VIPT 2
-#define ICACHE_POLICY_PIPT 3
-
-#ifndef __ASSEMBLY__
-
-#include <linux/bitops.h>
-
-#define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
-
-#define ICACHEF_ALIASING 0
-#define ICACHEF_AIVIVT 1
-
-extern unsigned long __icache_flags;
-
-/*
- * NumSets, bits[27:13] - (Number of sets in cache) - 1
- * Associativity, bits[12:3] - (Associativity of cache) - 1
- * LineSize, bits[2:0] - (Log2(Number of words in cache line)) - 2
- */
-#define CCSIDR_EL1_WRITE_THROUGH BIT(31)
-#define CCSIDR_EL1_WRITE_BACK BIT(30)
-#define CCSIDR_EL1_READ_ALLOCATE BIT(29)
-#define CCSIDR_EL1_WRITE_ALLOCATE BIT(28)
-#define CCSIDR_EL1_LINESIZE_MASK 0x7
-#define CCSIDR_EL1_LINESIZE(x) ((x) & CCSIDR_EL1_LINESIZE_MASK)
-#define CCSIDR_EL1_ASSOCIATIVITY_SHIFT 3
-#define CCSIDR_EL1_ASSOCIATIVITY_MASK 0x3ff
-#define CCSIDR_EL1_ASSOCIATIVITY(x) \
- (((x) >> CCSIDR_EL1_ASSOCIATIVITY_SHIFT) & CCSIDR_EL1_ASSOCIATIVITY_MASK)
-#define CCSIDR_EL1_NUMSETS_SHIFT 13
-#define CCSIDR_EL1_NUMSETS_MASK 0x7fff
-#define CCSIDR_EL1_NUMSETS(x) \
- (((x) >> CCSIDR_EL1_NUMSETS_SHIFT) & CCSIDR_EL1_NUMSETS_MASK)
-
-#define CACHE_LINESIZE(x) (16 << CCSIDR_EL1_LINESIZE(x))
-#define CACHE_NUMSETS(x) (CCSIDR_EL1_NUMSETS(x) + 1)
-#define CACHE_ASSOCIATIVITY(x) (CCSIDR_EL1_ASSOCIATIVITY(x) + 1)
-
-extern u64 __attribute_const__ cache_get_ccsidr(u64 csselr);
-
-/* Helpers for Level 1 Instruction cache csselr = 1L */
-static inline int icache_get_linesize(void)
-{
- return CACHE_LINESIZE(cache_get_ccsidr(1L));
-}
-
-static inline int icache_get_numsets(void)
-{
- return CACHE_NUMSETS(cache_get_ccsidr(1L));
-}
-
-/*
- * Whilst the D-side always behaves as PIPT on AArch64, aliasing is
- * permitted in the I-cache.
- */
-static inline int icache_is_aliasing(void)
-{
- return test_bit(ICACHEF_ALIASING, &__icache_flags);
-}
-
-static inline int icache_is_aivivt(void)
-{
- return test_bit(ICACHEF_AIVIVT, &__icache_flags);
-}
-
-static inline u32 cache_type_cwg(void)
-{
- return (read_cpuid_cachetype() >> CTR_CWG_SHIFT) & CTR_CWG_MASK;
-}
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_CACHETYPE_H */
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index fb78a5d3b60b..b3aab8a17868 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -37,7 +37,8 @@
#define ARM64_HAS_NO_FPSIMD 16
#define ARM64_WORKAROUND_REPEAT_TLBI 17
#define ARM64_WORKAROUND_QCOM_FALKOR_E1003 18
+#define ARM64_WORKAROUND_858921 19
-#define ARM64_NCAPS 19
+#define ARM64_NCAPS 20
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 05310ad8c5ab..e7f84a7b4465 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -226,7 +226,7 @@ void update_cpu_errata_workarounds(void);
void __init enable_errata_workarounds(void);
void verify_local_cpu_errata_workarounds(void);
-u64 read_system_reg(u32 id);
+u64 read_sanitised_ftr_reg(u32 id);
static inline bool cpu_supports_mixed_endian_el0(void)
{
@@ -240,7 +240,7 @@ static inline bool system_supports_32bit_el0(void)
static inline bool system_supports_mixed_endian_el0(void)
{
- return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
+ return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1));
}
static inline bool system_supports_fpsimd(void)
@@ -251,7 +251,7 @@ static inline bool system_supports_fpsimd(void)
static inline bool system_uses_ttbr0_pan(void)
{
return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
- !cpus_have_cap(ARM64_HAS_PAN);
+ !cpus_have_const_cap(ARM64_HAS_PAN);
}
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index fc502713ab37..0984d1b3a8f2 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,6 +80,7 @@
#define ARM_CPU_PART_FOUNDATION 0xD00
#define ARM_CPU_PART_CORTEX_A57 0xD07
#define ARM_CPU_PART_CORTEX_A53 0xD03
+#define ARM_CPU_PART_CORTEX_A73 0xD09
#define APM_CPU_PART_POTENZA 0x000
@@ -92,6 +93,7 @@
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
+#define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
diff --git a/arch/arm64/include/asm/current.h b/arch/arm64/include/asm/current.h
index 86c404171305..f6580d4afb0e 100644
--- a/arch/arm64/include/asm/current.h
+++ b/arch/arm64/include/asm/current.h
@@ -3,8 +3,6 @@
#include <linux/compiler.h>
-#include <asm/sysreg.h>
-
#ifndef __ASSEMBLY__
struct task_struct;
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 73d5bab015eb..5a5fa47a6b18 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -20,6 +20,9 @@ struct dev_archdata {
#ifdef CONFIG_IOMMU_API
void *iommu; /* private IOMMU data */
#endif
+#ifdef CONFIG_XEN
+ const struct dma_map_ops *dev_dma_ops;
+#endif
bool dma_coherent;
};
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 505756cdc67a..5392dbeffa45 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -27,11 +27,8 @@
#define DMA_ERROR_CODE (~(dma_addr_t)0)
extern const struct dma_map_ops dummy_dma_ops;
-static inline const struct dma_map_ops *__generic_dma_ops(struct device *dev)
+static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
{
- if (dev && dev->dma_ops)
- return dev->dma_ops;
-
/*
* We expect no ISA devices, and all other DMA masters are expected to
* have someone call arch_setup_dma_ops at device creation time.
@@ -39,14 +36,6 @@ static inline const struct dma_map_ops *__generic_dma_ops(struct device *dev)
return &dummy_dma_ops;
}
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
- if (xen_initial_domain())
- return xen_dma_ops;
- else
- return __generic_dma_ops(NULL);
-}
-
void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
const struct iommu_ops *iommu, bool coherent);
#define arch_setup_dma_ops arch_setup_dma_ops
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index e7445281e534..8f3043aba873 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -1,6 +1,7 @@
#ifndef _ASM_EFI_H
#define _ASM_EFI_H
+#include <asm/boot.h>
#include <asm/cpufeature.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
@@ -46,7 +47,28 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
* 2MiB so we know it won't cross a 2MiB boundary.
*/
#define EFI_FDT_ALIGN SZ_2M /* used by allocate_new_fdt_and_exit_boot() */
-#define MAX_FDT_OFFSET SZ_512M
+
+/* on arm64, the FDT may be located anywhere in system RAM */
+static inline unsigned long efi_get_max_fdt_addr(unsigned long dram_base)
+{
+ return ULONG_MAX;
+}
+
+/*
+ * On arm64, we have to ensure that the initrd ends up in the linear region,
+ * which is a 1 GB aligned region of size '1UL << (VA_BITS - 1)' that is
+ * guaranteed to cover the kernel Image.
+ *
+ * Since the EFI stub is part of the kernel Image, we can relax the
+ * usual requirements in Documentation/arm64/booting.txt, which still
+ * apply to other bootloaders, and are required for some kernel
+ * configurations.
+ */
+static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
+ unsigned long image_addr)
+{
+ return (image_addr & ~(SZ_1G - 1UL)) + (1UL << (VA_BITS - 1));
+}
#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
#define __efi_call_early(f, ...) f(__VA_ARGS__)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index d14c478976d0..85997c0e5443 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -175,6 +175,12 @@
#define ESR_ELx_SYS64_ISS_SYS_CTR_READ (ESR_ELx_SYS64_ISS_SYS_CTR | \
ESR_ELx_SYS64_ISS_DIR_READ)
+#define ESR_ELx_SYS64_ISS_SYS_CNTVCT (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 2, 14, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
+#define ESR_ELx_SYS64_ISS_SYS_CNTFRQ (ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 0, 14, 0) | \
+ ESR_ELx_SYS64_ISS_DIR_READ)
+
#ifndef __ASSEMBLY__
#include <asm/types.h>
diff --git a/arch/arm64/include/asm/extable.h b/arch/arm64/include/asm/extable.h
new file mode 100644
index 000000000000..42f50f15a44c
--- /dev/null
+++ b/arch/arm64/include/asm/extable.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative offsets: the first
+ * is the relative offset to an instruction that is allowed to fault,
+ * and the second is the relative offset at which the program should
+ * continue. No registers are modified, so it is entirely up to the
+ * continuation code to figure out what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path. This means when everything is well,
+ * we don't even have to jump over them. Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry
+{
+ int insn, fixup;
+};
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+extern int fixup_exception(struct pt_regs *regs);
+#endif
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 8740297dac77..1473fc2f7ab7 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -20,7 +20,7 @@
#include <linux/threads.h>
#include <asm/irq.h>
-#define NR_IPI 6
+#define NR_IPI 7
typedef struct {
unsigned int __softirq_pending;
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index b6b167ac082b..41770766d964 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -149,7 +149,7 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task)
/* Determine number of BRP registers available. */
static inline int get_num_brps(void)
{
- u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
+ u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
return 1 +
cpuid_feature_extract_unsigned_field(dfr0,
ID_AA64DFR0_BRPS_SHIFT);
@@ -158,7 +158,7 @@ static inline int get_num_brps(void)
/* Determine number of WRP registers available. */
static inline int get_num_wrps(void)
{
- u64 dfr0 = read_system_reg(SYS_ID_AA64DFR0_EL1);
+ u64 dfr0 = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
return 1 +
cpuid_feature_extract_unsigned_field(dfr0,
ID_AA64DFR0_WRPS_SHIFT);
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index aecc07e09a18..29cb2ca756f6 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -80,6 +80,7 @@ enum aarch64_insn_register_type {
AARCH64_INSN_REGTYPE_RM,
AARCH64_INSN_REGTYPE_RD,
AARCH64_INSN_REGTYPE_RA,
+ AARCH64_INSN_REGTYPE_RS,
};
enum aarch64_insn_register {
@@ -188,6 +189,8 @@ enum aarch64_insn_ldst_type {
AARCH64_INSN_LDST_STORE_PAIR_PRE_INDEX,
AARCH64_INSN_LDST_LOAD_PAIR_POST_INDEX,
AARCH64_INSN_LDST_STORE_PAIR_POST_INDEX,
+ AARCH64_INSN_LDST_LOAD_EX,
+ AARCH64_INSN_LDST_STORE_EX,
};
enum aarch64_insn_adsb_type {
@@ -240,6 +243,23 @@ enum aarch64_insn_logic_type {
AARCH64_INSN_LOGIC_BIC_SETFLAGS
};
+enum aarch64_insn_prfm_type {
+ AARCH64_INSN_PRFM_TYPE_PLD,
+ AARCH64_INSN_PRFM_TYPE_PLI,
+ AARCH64_INSN_PRFM_TYPE_PST,
+};
+
+enum aarch64_insn_prfm_target {
+ AARCH64_INSN_PRFM_TARGET_L1,
+ AARCH64_INSN_PRFM_TARGET_L2,
+ AARCH64_INSN_PRFM_TARGET_L3,
+};
+
+enum aarch64_insn_prfm_policy {
+ AARCH64_INSN_PRFM_POLICY_KEEP,
+ AARCH64_INSN_PRFM_POLICY_STRM,
+};
+
#define __AARCH64_INSN_FUNCS(abbr, mask, val) \
static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
{ return (code & (mask)) == (val); } \
@@ -248,6 +268,7 @@ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
__AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000)
__AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000)
+__AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000)
__AARCH64_INSN_FUNCS(prfm_lit, 0xFF000000, 0xD8000000)
__AARCH64_INSN_FUNCS(str_reg, 0x3FE0EC00, 0x38206800)
__AARCH64_INSN_FUNCS(ldr_reg, 0x3FE0EC00, 0x38606800)
@@ -357,6 +378,11 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
int offset,
enum aarch64_insn_variant variant,
enum aarch64_insn_ldst_type type);
+u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
+ enum aarch64_insn_register base,
+ enum aarch64_insn_register state,
+ enum aarch64_insn_size_type size,
+ enum aarch64_insn_ldst_type type);
u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
enum aarch64_insn_register src,
int imm, enum aarch64_insn_variant variant,
@@ -397,6 +423,10 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst,
int shift,
enum aarch64_insn_variant variant,
enum aarch64_insn_logic_type type);
+u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
+ enum aarch64_insn_prfm_type type,
+ enum aarch64_insn_prfm_target target,
+ enum aarch64_insn_prfm_policy policy);
s32 aarch64_get_branch_offset(u32 insn);
u32 aarch64_set_branch_offset(u32 insn, s32 offset);
diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index 04744dc5fb61..e17f0529a882 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -40,9 +40,59 @@
static inline void crash_setup_regs(struct pt_regs *newregs,
struct pt_regs *oldregs)
{
- /* Empty routine needed to avoid build errors. */
+ if (oldregs) {
+ memcpy(newregs, oldregs, sizeof(*newregs));
+ } else {
+ u64 tmp1, tmp2;
+
+ __asm__ __volatile__ (
+ "stp x0, x1, [%2, #16 * 0]\n"
+ "stp x2, x3, [%2, #16 * 1]\n"
+ "stp x4, x5, [%2, #16 * 2]\n"
+ "stp x6, x7, [%2, #16 * 3]\n"
+ "stp x8, x9, [%2, #16 * 4]\n"
+ "stp x10, x11, [%2, #16 * 5]\n"
+ "stp x12, x13, [%2, #16 * 6]\n"
+ "stp x14, x15, [%2, #16 * 7]\n"
+ "stp x16, x17, [%2, #16 * 8]\n"
+ "stp x18, x19, [%2, #16 * 9]\n"
+ "stp x20, x21, [%2, #16 * 10]\n"
+ "stp x22, x23, [%2, #16 * 11]\n"
+ "stp x24, x25, [%2, #16 * 12]\n"
+ "stp x26, x27, [%2, #16 * 13]\n"
+ "stp x28, x29, [%2, #16 * 14]\n"
+ "mov %0, sp\n"
+ "stp x30, %0, [%2, #16 * 15]\n"
+
+ "/* faked current PSTATE */\n"
+ "mrs %0, CurrentEL\n"
+ "mrs %1, SPSEL\n"
+ "orr %0, %0, %1\n"
+ "mrs %1, DAIF\n"
+ "orr %0, %0, %1\n"
+ "mrs %1, NZCV\n"
+ "orr %0, %0, %1\n"
+ /* pc */
+ "adr %1, 1f\n"
+ "1:\n"
+ "stp %1, %0, [%2, #16 * 16]\n"
+ : "=&r" (tmp1), "=&r" (tmp2)
+ : "r" (newregs)
+ : "memory"
+ );
+ }
}
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_HIBERNATION)
+extern bool crash_is_nosave(unsigned long pfn);
+extern void crash_prepare_suspend(void);
+extern void crash_post_resume(void);
+#else
+static inline bool crash_is_nosave(unsigned long pfn) {return false; }
+static inline void crash_prepare_suspend(void) {}
+static inline void crash_post_resume(void) {}
+#endif
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index ec3553eb9349..26a64d0f9ab9 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -28,7 +28,7 @@
#define ARM_EXCEPTION_EL1_SERROR 1
#define ARM_EXCEPTION_TRAP 2
/* The hyp-stub will return this for any kvm_call_hyp() call */
-#define ARM_EXCEPTION_HYP_GONE 3
+#define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR
#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0
#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT)
@@ -47,7 +47,6 @@ struct kvm_vcpu;
extern char __kvm_hyp_init[];
extern char __kvm_hyp_init_end[];
-extern char __kvm_hyp_reset[];
extern char __kvm_hyp_vector[];
@@ -59,6 +58,8 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu);
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
extern void __vgic_v3_init_lrs(void);
extern u32 __kvm_get_mdcr_el2(void);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f21fd3894370..5e19165c5fa8 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,9 +30,7 @@
#define __KVM_HAVE_ARCH_INTC_INITIALIZED
-#define KVM_USER_MEM_SLOTS 32
-#define KVM_PRIVATE_MEM_SLOTS 4
-#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_USER_MEM_SLOTS 512
#define KVM_HALT_POLL_NS_DEFAULT 500000
#include <kvm/arm_vgic.h>
@@ -43,7 +41,7 @@
#define KVM_VCPU_MAX_FEATURES 4
-#define KVM_REQ_VCPU_EXIT 8
+#define KVM_REQ_VCPU_EXIT (8 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
int __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -363,13 +361,6 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
__kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr);
}
-void __kvm_hyp_teardown(void);
-static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
- phys_addr_t phys_idmap_start)
-{
- kvm_call_hyp(__kvm_hyp_teardown, phys_idmap_start);
-}
-
static inline void kvm_arch_hardware_unsetup(void) {}
static inline void kvm_arch_sync_events(struct kvm *kvm) {}
static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index ed1246014901..a89cc22abadc 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -108,7 +108,7 @@ alternative_else_nop_endif
#else
#include <asm/pgalloc.h>
-#include <asm/cachetype.h>
+#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
@@ -155,7 +155,6 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
phys_addr_t kvm_mmu_get_httbr(void);
phys_addr_t kvm_get_idmap_vector(void);
-phys_addr_t kvm_get_idmap_start(void);
int kvm_mmu_init(void);
void kvm_clear_hyp_idmap(void);
@@ -242,12 +241,13 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
kvm_flush_dcache_to_poc(va, size);
- if (!icache_is_aliasing()) { /* PIPT */
- flush_icache_range((unsigned long)va,
- (unsigned long)va + size);
- } else if (!icache_is_aivivt()) { /* non ASID-tagged VIVT */
+ if (icache_is_aliasing()) {
/* any kind of VIPT cache */
__flush_icache_all();
+ } else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
+ /* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
+ flush_icache_range((unsigned long)va,
+ (unsigned long)va + size);
}
}
@@ -307,7 +307,7 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd,
static inline unsigned int kvm_get_vmid_bits(void)
{
- int reg = read_system_reg(SYS_ID_AA64MMFR1_EL1);
+ int reg = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8;
}
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index 47619411f0ff..5468c834b072 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -37,5 +37,6 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot, bool page_mappings_only);
extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
+extern void mark_linear_text_alias_ro(void);
#endif
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 06ff7fd9e81f..d57693f5d4ec 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -17,26 +17,26 @@
#define __ASM_MODULE_H
#include <asm-generic/module.h>
-#include <asm/memory.h>
#define MODULE_ARCH_VERMAGIC "aarch64"
#ifdef CONFIG_ARM64_MODULE_PLTS
-struct mod_arch_specific {
+struct mod_plt_sec {
struct elf64_shdr *plt;
int plt_num_entries;
int plt_max_entries;
};
+
+struct mod_arch_specific {
+ struct mod_plt_sec core;
+ struct mod_plt_sec init;
+};
#endif
-u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
+u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
Elf64_Sym *sym);
#ifdef CONFIG_RANDOMIZE_BASE
-#ifdef CONFIG_MODVERSIONS
-#define ARCH_RELOCATES_KCRCTAB
-#define reloc_start (kimage_vaddr - KIMAGE_VADDR)
-#endif
extern u64 module_alloc_base;
#else
#define module_alloc_base ((u64)_etext - MODULES_VSIZE)
diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h
index 69b2fd41503c..345a072b5856 100644
--- a/arch/arm64/include/asm/pgtable-types.h
+++ b/arch/arm64/include/asm/pgtable-types.h
@@ -55,9 +55,13 @@ typedef struct { pteval_t pgprot; } pgprot_t;
#define __pgprot(x) ((pgprot_t) { (x) } )
#if CONFIG_PGTABLE_LEVELS == 2
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopmd.h>
#elif CONFIG_PGTABLE_LEVELS == 3
+#define __ARCH_USE_5LEVEL_HACK
#include <asm-generic/pgtable-nopud.h>
+#elif CONFIG_PGTABLE_LEVELS == 4
+#include <asm-generic/5level-fixup.h>
#endif
#endif /* __ASM_PGTABLE_TYPES_H */
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 0eef6064bf3b..c213fdbd056c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -74,6 +74,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN))
#define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT))
+#define pte_cont_addr_end(addr, end) \
+({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \
+ (__boundary - 1 < (end) - 1) ? __boundary : (end); \
+})
+
+#define pmd_cont_addr_end(addr, end) \
+({ unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK; \
+ (__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
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index c97b8bd2acba..9428b93fefb2 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -50,6 +50,7 @@ extern phys_addr_t arm64_dma_phys_limit;
#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
struct debug_info {
+#ifdef CONFIG_HAVE_HW_BREAKPOINT
/* Have we suspended stepping by a debugger? */
int suspended_step;
/* Allow breakpoints and watchpoints to be disabled for this thread. */
@@ -58,6 +59,7 @@ struct debug_info {
/* Hardware breakpoints pinned to this task. */
struct perf_event *hbp_break[ARM_MAX_BRP];
struct perf_event *hbp_watch[ARM_MAX_WRP];
+#endif
};
struct cpu_context {
diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h
index 4e7e7067afdb..941267caa39c 100644
--- a/arch/arm64/include/asm/sections.h
+++ b/arch/arm64/include/asm/sections.h
@@ -24,6 +24,8 @@ extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
extern char __hyp_text_start[], __hyp_text_end[];
extern char __idmap_text_start[], __idmap_text_end[];
+extern char __initdata_begin[], __initdata_end[];
+extern char __inittext_begin[], __inittext_end[];
extern char __irqentry_text_start[], __irqentry_text_end[];
extern char __mmuoff_data_start[], __mmuoff_data_end[];
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index d050d720a1b4..55f08c5acfad 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -148,6 +148,9 @@ static inline void cpu_panic_kernel(void)
*/
bool cpus_are_stuck_in_kernel(void);
+extern void smp_send_crash_stop(void);
+extern bool smp_crash_stop_failed(void);
+
#endif /* ifndef __ASSEMBLY__ */
#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index ac24b6e798b1..15c142ce991c 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -48,6 +48,8 @@
((crn) << CRn_shift) | ((crm) << CRm_shift) | \
((op2) << Op2_shift))
+#define sys_insn sys_reg
+
#define sys_reg_Op0(id) (((id) >> Op0_shift) & Op0_mask)
#define sys_reg_Op1(id) (((id) >> Op1_shift) & Op1_mask)
#define sys_reg_CRn(id) (((id) >> CRn_shift) & CRn_mask)
@@ -81,6 +83,41 @@
#endif /* CONFIG_BROKEN_GAS_INST */
+#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
+#define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3)
+
+#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM | \
+ (!!x)<<8 | 0x1f)
+#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM | \
+ (!!x)<<8 | 0x1f)
+
+#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2)
+#define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2)
+#define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2)
+
+#define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2)
+#define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0)
+#define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2)
+#define SYS_OSDTRTX_EL1 sys_reg(2, 0, 0, 3, 2)
+#define SYS_OSECCR_EL1 sys_reg(2, 0, 0, 6, 2)
+#define SYS_DBGBVRn_EL1(n) sys_reg(2, 0, 0, n, 4)
+#define SYS_DBGBCRn_EL1(n) sys_reg(2, 0, 0, n, 5)
+#define SYS_DBGWVRn_EL1(n) sys_reg(2, 0, 0, n, 6)
+#define SYS_DBGWCRn_EL1(n) sys_reg(2, 0, 0, n, 7)
+#define SYS_MDRAR_EL1 sys_reg(2, 0, 1, 0, 0)
+#define SYS_OSLAR_EL1 sys_reg(2, 0, 1, 0, 4)
+#define SYS_OSLSR_EL1 sys_reg(2, 0, 1, 1, 4)
+#define SYS_OSDLR_EL1 sys_reg(2, 0, 1, 3, 4)
+#define SYS_DBGPRCR_EL1 sys_reg(2, 0, 1, 4, 4)
+#define SYS_DBGCLAIMSET_EL1 sys_reg(2, 0, 7, 8, 6)
+#define SYS_DBGCLAIMCLR_EL1 sys_reg(2, 0, 7, 9, 6)
+#define SYS_DBGAUTHSTATUS_EL1 sys_reg(2, 0, 7, 14, 6)
+#define SYS_MDCCSR_EL0 sys_reg(2, 3, 0, 1, 0)
+#define SYS_DBGDTR_EL0 sys_reg(2, 3, 0, 4, 0)
+#define SYS_DBGDTRRX_EL0 sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGDTRTX_EL0 sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGVCR32_EL2 sys_reg(2, 4, 0, 7, 0)
+
#define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0)
#define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5)
#define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6)
@@ -88,6 +125,7 @@
#define SYS_ID_PFR0_EL1 sys_reg(3, 0, 0, 1, 0)
#define SYS_ID_PFR1_EL1 sys_reg(3, 0, 0, 1, 1)
#define SYS_ID_DFR0_EL1 sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_AFR0_EL1 sys_reg(3, 0, 0, 1, 3)
#define SYS_ID_MMFR0_EL1 sys_reg(3, 0, 0, 1, 4)
#define SYS_ID_MMFR1_EL1 sys_reg(3, 0, 0, 1, 5)
#define SYS_ID_MMFR2_EL1 sys_reg(3, 0, 0, 1, 6)
@@ -118,17 +156,127 @@
#define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1)
#define SYS_ID_AA64MMFR2_EL1 sys_reg(3, 0, 0, 7, 2)
-#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0)
+#define SYS_SCTLR_EL1 sys_reg(3, 0, 1, 0, 0)
+#define SYS_ACTLR_EL1 sys_reg(3, 0, 1, 0, 1)
+#define SYS_CPACR_EL1 sys_reg(3, 0, 1, 0, 2)
+
+#define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0)
+#define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1)
+#define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2)
+
+#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
+
+#define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0)
+#define SYS_AFSR1_EL1 sys_reg(3, 0, 5, 1, 1)
+#define SYS_ESR_EL1 sys_reg(3, 0, 5, 2, 0)
+#define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0)
+#define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0)
+
+#define SYS_PMINTENSET_EL1 sys_reg(3, 0, 9, 14, 1)
+#define SYS_PMINTENCLR_EL1 sys_reg(3, 0, 9, 14, 2)
+
+#define SYS_MAIR_EL1 sys_reg(3, 0, 10, 2, 0)
+#define SYS_AMAIR_EL1 sys_reg(3, 0, 10, 3, 0)
+
+#define SYS_VBAR_EL1 sys_reg(3, 0, 12, 0, 0)
+
+#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5)
+#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3)
+#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
+#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+
+#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1)
+#define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4)
+
+#define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)
+
+#define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1)
+#define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7)
+
+#define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0)
+
#define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1)
#define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7)
-#define REG_PSTATE_PAN_IMM sys_reg(0, 0, 4, 0, 4)
-#define REG_PSTATE_UAO_IMM sys_reg(0, 0, 4, 0, 3)
+#define SYS_PMCR_EL0 sys_reg(3, 3, 9, 12, 0)
+#define SYS_PMCNTENSET_EL0 sys_reg(3, 3, 9, 12, 1)
+#define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2)
+#define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3)
+#define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4)
+#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5)
+#define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6)
+#define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7)
+#define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0)
+#define SYS_PMXEVTYPER_EL0 sys_reg(3, 3, 9, 13, 1)
+#define SYS_PMXEVCNTR_EL0 sys_reg(3, 3, 9, 13, 2)
+#define SYS_PMUSERENR_EL0 sys_reg(3, 3, 9, 14, 0)
+#define SYS_PMOVSSET_EL0 sys_reg(3, 3, 9, 14, 3)
+
+#define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2)
+#define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3)
-#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM | \
- (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM | \
- (!!x)<<8 | 0x1f)
+#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0)
+
+#define SYS_CNTP_TVAL_EL0 sys_reg(3, 3, 14, 2, 0)
+#define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2)
+
+#define __PMEV_op2(n) ((n) & 0x7)
+#define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTRn_EL0(n) sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
+#define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3))
+#define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
+
+#define SYS_PMCCFILTR_EL0 sys_reg (3, 3, 14, 15, 7)
+
+#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0)
+#define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1)
+#define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0)
+
+#define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
+#define SYS_ICH_AP0R0_EL2 __SYS__AP0Rx_EL2(0)
+#define SYS_ICH_AP0R1_EL2 __SYS__AP0Rx_EL2(1)
+#define SYS_ICH_AP0R2_EL2 __SYS__AP0Rx_EL2(2)
+#define SYS_ICH_AP0R3_EL2 __SYS__AP0Rx_EL2(3)
+
+#define __SYS__AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x)
+#define SYS_ICH_AP1R0_EL2 __SYS__AP1Rx_EL2(0)
+#define SYS_ICH_AP1R1_EL2 __SYS__AP1Rx_EL2(1)
+#define SYS_ICH_AP1R2_EL2 __SYS__AP1Rx_EL2(2)
+#define SYS_ICH_AP1R3_EL2 __SYS__AP1Rx_EL2(3)
+
+#define SYS_ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4)
+#define SYS_ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
+#define SYS_ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0)
+#define SYS_ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1)
+#define SYS_ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2)
+#define SYS_ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3)
+#define SYS_ICH_ELSR_EL2 sys_reg(3, 4, 12, 11, 5)
+#define SYS_ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7)
+
+#define __SYS__LR0_EL2(x) sys_reg(3, 4, 12, 12, x)
+#define SYS_ICH_LR0_EL2 __SYS__LR0_EL2(0)
+#define SYS_ICH_LR1_EL2 __SYS__LR0_EL2(1)
+#define SYS_ICH_LR2_EL2 __SYS__LR0_EL2(2)
+#define SYS_ICH_LR3_EL2 __SYS__LR0_EL2(3)
+#define SYS_ICH_LR4_EL2 __SYS__LR0_EL2(4)
+#define SYS_ICH_LR5_EL2 __SYS__LR0_EL2(5)
+#define SYS_ICH_LR6_EL2 __SYS__LR0_EL2(6)
+#define SYS_ICH_LR7_EL2 __SYS__LR0_EL2(7)
+
+#define __SYS__LR8_EL2(x) sys_reg(3, 4, 12, 13, x)
+#define SYS_ICH_LR8_EL2 __SYS__LR8_EL2(0)
+#define SYS_ICH_LR9_EL2 __SYS__LR8_EL2(1)
+#define SYS_ICH_LR10_EL2 __SYS__LR8_EL2(2)
+#define SYS_ICH_LR11_EL2 __SYS__LR8_EL2(3)
+#define SYS_ICH_LR12_EL2 __SYS__LR8_EL2(4)
+#define SYS_ICH_LR13_EL2 __SYS__LR8_EL2(5)
+#define SYS_ICH_LR14_EL2 __SYS__LR8_EL2(6)
+#define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7)
/* Common SCTLR_ELx flags. */
#define SCTLR_ELx_EE (1 << 25)
@@ -156,6 +304,11 @@
#define ID_AA64ISAR0_SHA1_SHIFT 8
#define ID_AA64ISAR0_AES_SHIFT 4
+/* id_aa64isar1 */
+#define ID_AA64ISAR1_LRCPC_SHIFT 20
+#define ID_AA64ISAR1_FCMA_SHIFT 16
+#define ID_AA64ISAR1_JSCVT_SHIFT 12
+
/* id_aa64pfr0 */
#define ID_AA64PFR0_GIC_SHIFT 24
#define ID_AA64PFR0_ASIMD_SHIFT 20
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 5308d696311b..ba497172610d 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -28,38 +28,12 @@
#include <linux/bitops.h>
#include <linux/kasan-checks.h>
#include <linux/string.h>
-#include <linux/thread_info.h>
#include <asm/cpufeature.h>
#include <asm/ptrace.h>
-#include <asm/errno.h>
#include <asm/memory.h>
#include <asm/compiler.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The exception table consists of pairs of relative offsets: the first
- * is the relative offset to an instruction that is allowed to fault,
- * and the second is the relative offset at which the program should
- * continue. No registers are modified, so it is entirely up to the
- * continuation code to figure out what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry
-{
- int insn, fixup;
-};
-
-#define ARCH_HAS_RELATIVE_EXTABLE
-
-extern int fixup_exception(struct pt_regs *regs);
+#include <asm/extable.h>
#define KERNEL_DS (-1UL)
#define get_ds() (KERNEL_DS)
@@ -357,58 +331,13 @@ do { \
})
extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n);
+#define raw_copy_from_user __arch_copy_from_user
extern unsigned long __must_check __arch_copy_to_user(void __user *to, const void *from, unsigned long n);
-extern unsigned long __must_check __copy_in_user(void __user *to, const void __user *from, unsigned long n);
+#define raw_copy_to_user __arch_copy_to_user
+extern unsigned long __must_check raw_copy_in_user(void __user *to, const void __user *from, unsigned long n);
extern unsigned long __must_check __clear_user(void __user *addr, unsigned long n);
-
-static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- kasan_check_write(to, n);
- check_object_size(to, n, false);
- return __arch_copy_from_user(to, from, n);
-}
-
-static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- kasan_check_read(from, n);
- check_object_size(from, n, true);
- return __arch_copy_to_user(to, from, n);
-}
-
-static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
-{
- unsigned long res = n;
- kasan_check_write(to, n);
- check_object_size(to, n, false);
-
- if (access_ok(VERIFY_READ, from, n)) {
- res = __arch_copy_from_user(to, from, n);
- }
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
-}
-
-static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long n)
-{
- kasan_check_read(from, n);
- check_object_size(from, n, true);
-
- if (access_ok(VERIFY_WRITE, to, n)) {
- n = __arch_copy_to_user(to, from, n);
- }
- return n;
-}
-
-static inline unsigned long __must_check copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
- if (access_ok(VERIFY_READ, from, n) && access_ok(VERIFY_WRITE, to, n))
- n = __copy_in_user(to, from, n);
- return n;
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
+#define INLINE_COPY_TO_USER
+#define INLINE_COPY_FROM_USER
static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
{
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index e78ac26324bd..a0baa9af5487 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,7 +14,6 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifdef CONFIG_COMPAT
-#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
#define __ARCH_WANT_COMPAT_STAT64
#define __ARCH_WANT_SYS_GETHOSTNAME
#define __ARCH_WANT_SYS_PAUSE
@@ -44,7 +43,7 @@
#define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2)
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5)
-#define __NR_compat_syscalls 394
+#define __NR_compat_syscalls 398
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index b7e8ef16ff0d..ef292160748c 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -456,7 +456,7 @@ __SYSCALL(__NR_setfsuid32, sys_setfsuid)
#define __NR_setfsgid32 216
__SYSCALL(__NR_setfsgid32, sys_setfsgid)
#define __NR_getdents64 217
-__SYSCALL(__NR_getdents64, compat_sys_getdents64)
+__SYSCALL(__NR_getdents64, sys_getdents64)
#define __NR_pivot_root 218
__SYSCALL(__NR_pivot_root, sys_pivot_root)
#define __NR_mincore 219
@@ -809,6 +809,14 @@ __SYSCALL(__NR_copy_file_range, sys_copy_file_range)
__SYSCALL(__NR_preadv2, compat_sys_preadv2)
#define __NR_pwritev2 393
__SYSCALL(__NR_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 394
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 395
+__SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
+#define __NR_pkey_free 396
+__SYSCALL(__NR_pkey_free, sys_pkey_free)
+#define __NR_statx 397
+__SYSCALL(__NR_statx, sys_statx)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h
index 439f6b5d31f6..c5f89442785c 100644
--- a/arch/arm64/include/asm/virt.h
+++ b/arch/arm64/include/asm/virt.h
@@ -19,25 +19,38 @@
#define __ASM__VIRT_H
/*
- * The arm64 hcall implementation uses x0 to specify the hcall type. A value
- * less than 0xfff indicates a special hcall, such as get/set vector.
- * Any other value is used as a pointer to the function to call.
+ * The arm64 hcall implementation uses x0 to specify the hcall
+ * number. A value less than HVC_STUB_HCALL_NR indicates a special
+ * hcall, such as set vector. Any other value is handled in a
+ * hypervisor specific way.
+ *
+ * The hypercall is allowed to clobber any of the caller-saved
+ * registers (x0-x18), so it is advisable to use it through the
+ * indirection of a function call (as implemented in hyp-stub.S).
*/
-/* HVC_GET_VECTORS - Return the value of the vbar_el2 register. */
-#define HVC_GET_VECTORS 0
-
/*
* HVC_SET_VECTORS - Set the value of the vbar_el2 register.
*
* @x1: Physical address of the new vector table.
*/
-#define HVC_SET_VECTORS 1
+#define HVC_SET_VECTORS 0
/*
* HVC_SOFT_RESTART - CPU soft reset, used by the cpu_soft_restart routine.
*/
-#define HVC_SOFT_RESTART 2
+#define HVC_SOFT_RESTART 1
+
+/*
+ * HVC_RESET_VECTORS - Restore the vectors to the original HYP stubs
+ */
+#define HVC_RESET_VECTORS 2
+
+/* Max number of HYP stub hypercalls */
+#define HVC_STUB_HCALL_NR 3
+
+/* Error returned when an invalid stub number is passed into x0 */
+#define HVC_STUB_ERR 0xbadca11
#define BOOT_CPU_MODE_EL1 (0xe11)
#define BOOT_CPU_MODE_EL2 (0xe12)
@@ -61,7 +74,7 @@
extern u32 __boot_cpu_mode[2];
void __hyp_set_vectors(phys_addr_t phys_vector_base);
-phys_addr_t __hyp_get_vectors(void);
+void __hyp_reset_vectors(void);
/* Reports the availability of HYP mode */
static inline bool is_hyp_mode_available(void)
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 61c263cba272..4e187ce2a811 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -32,5 +32,8 @@
#define HWCAP_ASIMDHP (1 << 10)
#define HWCAP_CPUID (1 << 11)
#define HWCAP_ASIMDRDM (1 << 12)
+#define HWCAP_JSCVT (1 << 13)
+#define HWCAP_FCMA (1 << 14)
+#define HWCAP_LRCPC (1 << 15)
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index c2860358ae3e..869ee480deed 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -39,6 +39,8 @@
#define __KVM_HAVE_IRQ_LINE
#define __KVM_HAVE_READONLY_MEM
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
#define KVM_REG_SIZE(id) \
(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -143,6 +145,8 @@ struct kvm_debug_exit_arch {
#define KVM_GUESTDBG_USE_HW (1 << 17)
struct kvm_sync_regs {
+ /* Used with KVM_CAP_ARM_USER_IRQ */
+ __u64 device_irq_level;
};
struct kvm_arch_memory_slot {
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 1606c6b2a280..1dcb69d3d0e5 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -50,6 +50,9 @@ arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o
arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \
cpu-reset.o
+arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o
+arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
+arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
obj-y += $(arm64-obj-y) vdso/ probes/
obj-m += $(arm64-obj-m)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 64d9cbd61678..e25c11e727fe 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -18,6 +18,7 @@
#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/cpumask.h>
+#include <linux/efi-bgrt.h>
#include <linux/init.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
@@ -233,6 +234,8 @@ done:
early_init_dt_scan_chosen_stdout();
} else {
parse_spcr(earlycon_init_is_deferred);
+ if (IS_ENABLED(CONFIG_ACPI_BGRT))
+ acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt);
}
}
diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 06d650f61da7..8840c109c5d6 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -105,11 +105,11 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
return insn;
}
-static void __apply_alternatives(void *alt_region)
+static void __apply_alternatives(void *alt_region, bool use_linear_alias)
{
struct alt_instr *alt;
struct alt_region *region = alt_region;
- u32 *origptr, *replptr;
+ u32 *origptr, *replptr, *updptr;
for (alt = region->begin; alt < region->end; alt++) {
u32 insn;
@@ -124,11 +124,12 @@ static void __apply_alternatives(void *alt_region)
origptr = ALT_ORIG_PTR(alt);
replptr = ALT_REPL_PTR(alt);
+ updptr = use_linear_alias ? (u32 *)lm_alias(origptr) : origptr;
nr_inst = alt->alt_len / sizeof(insn);
for (i = 0; i < nr_inst; i++) {
insn = get_alt_insn(alt, origptr + i, replptr + i);
- *(origptr + i) = cpu_to_le32(insn);
+ updptr[i] = cpu_to_le32(insn);
}
flush_icache_range((uintptr_t)origptr,
@@ -155,7 +156,7 @@ static int __apply_alternatives_multi_stop(void *unused)
isb();
} else {
BUG_ON(patched);
- __apply_alternatives(&region);
+ __apply_alternatives(&region, true);
/* Barriers provided by the cache flushing */
WRITE_ONCE(patched, 1);
}
@@ -176,5 +177,5 @@ void apply_alternatives(void *start, size_t length)
.end = start + length,
};
- __apply_alternatives(&region);
+ __apply_alternatives(&region, false);
}
diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c
index e9c4dc9e0ada..67368c7329c0 100644
--- a/arch/arm64/kernel/arm64ksyms.c
+++ b/arch/arm64/kernel/arm64ksyms.c
@@ -38,7 +38,7 @@ EXPORT_SYMBOL(clear_page);
EXPORT_SYMBOL(__arch_copy_from_user);
EXPORT_SYMBOL(__arch_copy_to_user);
EXPORT_SYMBOL(__clear_user);
-EXPORT_SYMBOL(__copy_in_user);
+EXPORT_SYMBOL(raw_copy_in_user);
/* physical memory */
EXPORT_SYMBOL(memstart_addr);
diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c
index 3f2250fc391b..380f2e2fbed5 100644
--- a/arch/arm64/kernel/cacheinfo.c
+++ b/arch/arm64/kernel/cacheinfo.c
@@ -17,15 +17,9 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
-#include <linux/bitops.h>
#include <linux/cacheinfo.h>
-#include <linux/cpu.h>
-#include <linux/compiler.h>
#include <linux/of.h>
-#include <asm/cachetype.h>
-#include <asm/processor.h>
-
#define MAX_CACHE_LEVEL 7 /* Max 7 level supported */
/* Ctypen, bits[3(n - 1) + 2 : 3(n - 1)], for n = 1 to 7 */
#define CLIDR_CTYPE_SHIFT(level) (3 * (level - 1))
@@ -43,43 +37,11 @@ static inline enum cache_type get_cache_type(int level)
return CLIDR_CTYPE(clidr, level);
}
-/*
- * Cache Size Selection Register(CSSELR) selects which Cache Size ID
- * Register(CCSIDR) is accessible by specifying the required cache
- * level and the cache type. We need to ensure that no one else changes
- * CSSELR by calling this in non-preemtible context
- */
-u64 __attribute_const__ cache_get_ccsidr(u64 csselr)
-{
- u64 ccsidr;
-
- WARN_ON(preemptible());
-
- write_sysreg(csselr, csselr_el1);
- isb();
- ccsidr = read_sysreg(ccsidr_el1);
-
- return ccsidr;
-}
-
static void ci_leaf_init(struct cacheinfo *this_leaf,
enum cache_type type, unsigned int level)
{
- bool is_icache = type & CACHE_TYPE_INST;
- u64 tmp = cache_get_ccsidr((level - 1) << 1 | is_icache);
-
this_leaf->level = level;
this_leaf->type = type;
- this_leaf->coherency_line_size = CACHE_LINESIZE(tmp);
- this_leaf->number_of_sets = CACHE_NUMSETS(tmp);
- this_leaf->ways_of_associativity = CACHE_ASSOCIATIVITY(tmp);
- this_leaf->size = this_leaf->number_of_sets *
- this_leaf->coherency_line_size * this_leaf->ways_of_associativity;
- this_leaf->attributes =
- ((tmp & CCSIDR_EL1_WRITE_THROUGH) ? CACHE_WRITE_THROUGH : 0) |
- ((tmp & CCSIDR_EL1_WRITE_BACK) ? CACHE_WRITE_BACK : 0) |
- ((tmp & CCSIDR_EL1_READ_ALLOCATE) ? CACHE_READ_ALLOCATE : 0) |
- ((tmp & CCSIDR_EL1_WRITE_ALLOCATE) ? CACHE_WRITE_ALLOCATE : 0);
}
static int __init_cache_level(unsigned int cpu)
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index f6cc67e7626e..2ed2a7657711 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -53,6 +53,13 @@ static int cpu_enable_trap_ctr_access(void *__unused)
.midr_range_min = min, \
.midr_range_max = max
+#define MIDR_ALL_VERSIONS(model) \
+ .def_scope = SCOPE_LOCAL_CPU, \
+ .matches = is_affected_midr_range, \
+ .midr_model = model, \
+ .midr_range_min = 0, \
+ .midr_range_max = (MIDR_VARIANT_MASK | MIDR_REVISION_MASK)
+
const struct arm64_cpu_capabilities arm64_errata[] = {
#if defined(CONFIG_ARM64_ERRATUM_826319) || \
defined(CONFIG_ARM64_ERRATUM_827319) || \
@@ -151,6 +158,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_CPU_VAR_REV(0, 0)),
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_858921
+ {
+ /* Cortex-A73 all versions */
+ .desc = "ARM erratum 858921",
+ .capability = ARM64_WORKAROUND_858921,
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
+ },
+#endif
{
}
};
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index abda8e861865..94b8f7fc3310 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -97,6 +97,13 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
ARM64_FTR_END,
};
+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_END,
+};
+
static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI),
@@ -153,9 +160,9 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
/*
* Linux can handle differing I-cache policies. Userspace JITs will
* make use of *minLine.
- * If we have differing I-cache policies, report it as the weakest - AIVIVT.
+ * If we have differing I-cache policies, report it as the weakest - VIPT.
*/
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT), /* L1Ip */
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT), /* L1Ip */
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0), /* IminLine */
ARM64_FTR_END,
};
@@ -314,7 +321,7 @@ static const struct __ftr_reg_entry {
/* Op1 = 0, CRn = 0, CRm = 6 */
ARM64_FTR_REG(SYS_ID_AA64ISAR0_EL1, ftr_id_aa64isar0),
- ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_raz),
+ ARM64_FTR_REG(SYS_ID_AA64ISAR1_EL1, ftr_id_aa64isar1),
/* Op1 = 0, CRn = 0, CRm = 7 */
ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0),
@@ -585,7 +592,7 @@ void update_cpu_features(int cpu,
* If we have AArch32, we care about 32-bit features for compat.
* If the system doesn't support AArch32, don't update them.
*/
- if (id_aa64pfr0_32bit_el0(read_system_reg(SYS_ID_AA64PFR0_EL1)) &&
+ if (id_aa64pfr0_32bit_el0(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) &&
id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
taint |= check_update_ftr_reg(SYS_ID_DFR0_EL1, cpu,
@@ -636,7 +643,7 @@ void update_cpu_features(int cpu,
"Unsupported CPU feature variation.\n");
}
-u64 read_system_reg(u32 id)
+u64 read_sanitised_ftr_reg(u32 id)
{
struct arm64_ftr_reg *regp = get_arm64_ftr_reg(id);
@@ -649,10 +656,10 @@ u64 read_system_reg(u32 id)
case r: return read_sysreg_s(r)
/*
- * __raw_read_system_reg() - Used by a STARTING cpu before cpuinfo is populated.
+ * __read_sysreg_by_encoding() - Used by a STARTING cpu before cpuinfo is populated.
* Read the system register on the current CPU
*/
-static u64 __raw_read_system_reg(u32 sys_id)
+static u64 __read_sysreg_by_encoding(u32 sys_id)
{
switch (sys_id) {
read_sysreg_case(SYS_ID_PFR0_EL1);
@@ -709,9 +716,9 @@ has_cpuid_feature(const struct arm64_cpu_capabilities *entry, int scope)
WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible());
if (scope == SCOPE_SYSTEM)
- val = read_system_reg(entry->sys_reg);
+ val = read_sanitised_ftr_reg(entry->sys_reg);
else
- val = __raw_read_system_reg(entry->sys_reg);
+ val = __read_sysreg_by_encoding(entry->sys_reg);
return feature_matches(val, entry);
}
@@ -761,7 +768,7 @@ static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unused)
{
- u64 pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1);
+ u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
return cpuid_feature_extract_signed_field(pfr0,
ID_AA64PFR0_FP_SHIFT) < 0;
@@ -888,6 +895,9 @@ 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_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),
{},
};
@@ -1090,20 +1100,29 @@ static void __init setup_feature_capabilities(void)
* Check if the current CPU has a given feature capability.
* Should be called from non-preemptible context.
*/
-bool this_cpu_has_cap(unsigned int cap)
+static bool __this_cpu_has_cap(const struct arm64_cpu_capabilities *cap_array,
+ unsigned int cap)
{
const struct arm64_cpu_capabilities *caps;
if (WARN_ON(preemptible()))
return false;
- for (caps = arm64_features; caps->desc; caps++)
+ for (caps = cap_array; caps->desc; caps++)
if (caps->capability == cap && caps->matches)
return caps->matches(caps, SCOPE_LOCAL_CPU);
return false;
}
+extern const struct arm64_cpu_capabilities arm64_errata[];
+
+bool this_cpu_has_cap(unsigned int cap)
+{
+ return (__this_cpu_has_cap(arm64_features, cap) ||
+ __this_cpu_has_cap(arm64_errata, cap));
+}
+
void __init setup_cpu_features(void)
{
u32 cwg;
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index 75a0f8acef66..fd691087dc9a 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -30,7 +30,7 @@ int arm_cpuidle_init(unsigned int cpu)
}
/**
- * cpu_suspend() - function to enter a low-power idle state
+ * arm_cpuidle_suspend() - function to enter a low-power idle state
* @arg: argument to pass to CPU suspend operations
*
* Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index 5b22c687f02a..68b1f364c515 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -15,7 +15,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <asm/arch_timer.h>
-#include <asm/cachetype.h>
+#include <asm/cache.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/cpufeature.h>
@@ -43,10 +43,10 @@ DEFINE_PER_CPU(struct cpuinfo_arm64, cpu_data);
static struct cpuinfo_arm64 boot_cpu_data;
static char *icache_policy_str[] = {
- [ICACHE_POLICY_RESERVED] = "RESERVED/UNKNOWN",
- [ICACHE_POLICY_AIVIVT] = "AIVIVT",
- [ICACHE_POLICY_VIPT] = "VIPT",
- [ICACHE_POLICY_PIPT] = "PIPT",
+ [0 ... ICACHE_POLICY_PIPT] = "RESERVED/UNKNOWN",
+ [ICACHE_POLICY_VIPT] = "VIPT",
+ [ICACHE_POLICY_PIPT] = "PIPT",
+ [ICACHE_POLICY_VPIPT] = "VPIPT",
};
unsigned long __icache_flags;
@@ -65,6 +65,9 @@ static const char *const hwcap_str[] = {
"asimdhp",
"cpuid",
"asimdrdm",
+ "jscvt",
+ "fcma",
+ "lrcpc",
NULL
};
@@ -289,20 +292,18 @@ static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info)
unsigned int cpu = smp_processor_id();
u32 l1ip = CTR_L1IP(info->reg_ctr);
- if (l1ip != ICACHE_POLICY_PIPT) {
- /*
- * VIPT caches are non-aliasing if the VA always equals the PA
- * in all bit positions that are covered by the index. This is
- * the case if the size of a way (# of sets * line size) does
- * not exceed PAGE_SIZE.
- */
- u32 waysize = icache_get_numsets() * icache_get_linesize();
-
- if (l1ip != ICACHE_POLICY_VIPT || waysize > PAGE_SIZE)
- set_bit(ICACHEF_ALIASING, &__icache_flags);
+ switch (l1ip) {
+ case ICACHE_POLICY_PIPT:
+ break;
+ case ICACHE_POLICY_VPIPT:
+ set_bit(ICACHEF_VPIPT, &__icache_flags);
+ break;
+ default:
+ /* Fallthrough */
+ case ICACHE_POLICY_VIPT:
+ /* Assume aliasing */
+ set_bit(ICACHEF_ALIASING, &__icache_flags);
}
- if (l1ip == ICACHE_POLICY_AIVIVT)
- set_bit(ICACHEF_AIVIVT, &__icache_flags);
pr_info("Detected %s I-cache on CPU%d\n", icache_policy_str[l1ip], cpu);
}
diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c
new file mode 100644
index 000000000000..f46d57c31443
--- /dev/null
+++ b/arch/arm64/kernel/crash_dump.c
@@ -0,0 +1,71 @@
+/*
+ * Routines for doing kexec-based kdump
+ *
+ * Copyright (C) 2017 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/crash_dump.h>
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/memblock.h>
+#include <linux/uaccess.h>
+#include <asm/memory.h>
+
+/**
+ * copy_oldmem_page() - copy one page from old kernel memory
+ * @pfn: page frame number to be copied
+ * @buf: buffer where the copied page is placed
+ * @csize: number of bytes to copy
+ * @offset: offset in bytes into the page
+ * @userbuf: if set, @buf is in a user address space
+ *
+ * This function copies one page from old kernel memory into buffer pointed by
+ * @buf. If @buf is in userspace, set @userbuf to %1. Returns number of bytes
+ * copied or negative error in case of failure.
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
+ size_t csize, unsigned long offset,
+ int userbuf)
+{
+ void *vaddr;
+
+ if (!csize)
+ return 0;
+
+ vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB);
+ if (!vaddr)
+ return -ENOMEM;
+
+ if (userbuf) {
+ if (copy_to_user((char __user *)buf, vaddr + offset, csize)) {
+ memunmap(vaddr);
+ return -EFAULT;
+ }
+ } else {
+ memcpy(buf, vaddr + offset, csize);
+ }
+
+ memunmap(vaddr);
+
+ return csize;
+}
+
+/**
+ * elfcorehdr_read - read from ELF core header
+ * @buf: buffer where the data is placed
+ * @csize: number of bytes to read
+ * @ppos: address in the memory
+ *
+ * This function reads @count bytes from elf core header which exists
+ * on crash dump kernel's memory.
+ */
+ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+ memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+ return count;
+}
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 32913567da08..d618e25c3de1 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -36,7 +36,7 @@
/* Determine debug architecture. */
u8 debug_monitors_arch(void)
{
- return cpuid_feature_extract_unsigned_field(read_system_reg(SYS_ID_AA64DFR0_EL1),
+ return cpuid_feature_extract_unsigned_field(read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1),
ID_AA64DFR0_DEBUGVER_SHIFT);
}
diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S
new file mode 100644
index 000000000000..613fc3000677
--- /dev/null
+++ b/arch/arm64/kernel/efi-header.S
@@ -0,0 +1,155 @@
+/*
+ * Copyright (C) 2013 - 2017 Linaro, Ltd.
+ * Copyright (C) 2013, 2014 Red Hat, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/pe.h>
+#include <linux/sizes.h>
+
+ .macro __EFI_PE_HEADER
+ .long PE_MAGIC
+coff_header:
+ .short IMAGE_FILE_MACHINE_ARM64 // Machine
+ .short section_count // NumberOfSections
+ .long 0 // TimeDateStamp
+ .long 0 // PointerToSymbolTable
+ .long 0 // NumberOfSymbols
+ .short section_table - optional_header // SizeOfOptionalHeader
+ .short IMAGE_FILE_DEBUG_STRIPPED | \
+ IMAGE_FILE_EXECUTABLE_IMAGE | \
+ IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics
+
+optional_header:
+ .short PE_OPT_MAGIC_PE32PLUS // PE32+ format
+ .byte 0x02 // MajorLinkerVersion
+ .byte 0x14 // MinorLinkerVersion
+ .long __initdata_begin - efi_header_end // SizeOfCode
+ .long __pecoff_data_size // SizeOfInitializedData
+ .long 0 // SizeOfUninitializedData
+ .long __efistub_entry - _head // AddressOfEntryPoint
+ .long efi_header_end - _head // BaseOfCode
+
+extra_header_fields:
+ .quad 0 // ImageBase
+ .long SZ_4K // SectionAlignment
+ .long PECOFF_FILE_ALIGNMENT // FileAlignment
+ .short 0 // MajorOperatingSystemVersion
+ .short 0 // MinorOperatingSystemVersion
+ .short 0 // MajorImageVersion
+ .short 0 // MinorImageVersion
+ .short 0 // MajorSubsystemVersion
+ .short 0 // MinorSubsystemVersion
+ .long 0 // Win32VersionValue
+
+ .long _end - _head // SizeOfImage
+
+ // Everything before the kernel image is considered part of the header
+ .long efi_header_end - _head // SizeOfHeaders
+ .long 0 // CheckSum
+ .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem
+ .short 0 // DllCharacteristics
+ .quad 0 // SizeOfStackReserve
+ .quad 0 // SizeOfStackCommit
+ .quad 0 // SizeOfHeapReserve
+ .quad 0 // SizeOfHeapCommit
+ .long 0 // LoaderFlags
+ .long (section_table - .) / 8 // NumberOfRvaAndSizes
+
+ .quad 0 // ExportTable
+ .quad 0 // ImportTable
+ .quad 0 // ResourceTable
+ .quad 0 // ExceptionTable
+ .quad 0 // CertificationTable
+ .quad 0 // BaseRelocationTable
+
+#ifdef CONFIG_DEBUG_EFI
+ .long efi_debug_table - _head // DebugTable
+ .long efi_debug_table_size
+#endif
+
+ // Section table
+section_table:
+ .ascii ".text\0\0\0"
+ .long __initdata_begin - efi_header_end // VirtualSize
+ .long efi_header_end - _head // VirtualAddress
+ .long __initdata_begin - efi_header_end // SizeOfRawData
+ .long efi_header_end - _head // PointerToRawData
+
+ .long 0 // PointerToRelocations
+ .long 0 // PointerToLineNumbers
+ .short 0 // NumberOfRelocations
+ .short 0 // NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_CODE | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_EXECUTE // Characteristics
+
+ .ascii ".data\0\0\0"
+ .long __pecoff_data_size // VirtualSize
+ .long __initdata_begin - _head // VirtualAddress
+ .long __pecoff_data_rawsize // SizeOfRawData
+ .long __initdata_begin - _head // PointerToRawData
+
+ .long 0 // PointerToRelocations
+ .long 0 // PointerToLineNumbers
+ .short 0 // NumberOfRelocations
+ .short 0 // NumberOfLineNumbers
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_WRITE // Characteristics
+
+ .set section_count, (. - section_table) / 40
+
+#ifdef CONFIG_DEBUG_EFI
+ /*
+ * The debug table is referenced via its Relative Virtual Address (RVA),
+ * which is only defined for those parts of the image that are covered
+ * by a section declaration. Since this header is not covered by any
+ * section, the debug table must be emitted elsewhere. So stick it in
+ * the .init.rodata section instead.
+ *
+ * Note that the EFI debug entry itself may legally have a zero RVA,
+ * which means we can simply put it right after the section headers.
+ */
+ __INITRODATA
+
+ .align 2
+efi_debug_table:
+ // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY
+ .long 0 // Characteristics
+ .long 0 // TimeDateStamp
+ .short 0 // MajorVersion
+ .short 0 // MinorVersion
+ .long IMAGE_DEBUG_TYPE_CODEVIEW // Type
+ .long efi_debug_entry_size // SizeOfData
+ .long 0 // RVA
+ .long efi_debug_entry - _head // FileOffset
+
+ .set efi_debug_table_size, . - efi_debug_table
+ .previous
+
+efi_debug_entry:
+ // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY
+ .ascii "NB10" // Signature
+ .long 0 // Unknown
+ .long 0 // Unknown2
+ .long 0 // Unknown3
+
+ .asciz VMLINUX_PATH
+
+ .set efi_debug_entry_size, . - efi_debug_entry
+#endif
+
+ /*
+ * EFI will load .text onwards at the 4k section alignment
+ * described in the PE/COFF header. To ensure that instruction
+ * sequences using an adrp and a :lo12: immediate will function
+ * correctly at this alignment, we must ensure that .text is
+ * placed at a 4k boundary in the Image to begin with.
+ */
+ .align 12
+efi_header_end:
+ .endm
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 4fb6ccd886d1..973df7de7bf8 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -42,6 +42,8 @@
#include <asm/thread_info.h>
#include <asm/virt.h>
+#include "efi-header.S"
+
#define __PHYS_OFFSET (KERNEL_START - TEXT_OFFSET)
#if (TEXT_OFFSET & 0xfff) != 0
@@ -89,166 +91,14 @@ _head:
.quad 0 // reserved
.quad 0 // reserved
.quad 0 // reserved
- .byte 0x41 // Magic number, "ARM\x64"
- .byte 0x52
- .byte 0x4d
- .byte 0x64
+ .ascii "ARM\x64" // Magic number
#ifdef CONFIG_EFI
.long pe_header - _head // Offset to the PE header.
-#else
- .word 0 // reserved
-#endif
-#ifdef CONFIG_EFI
- .align 3
pe_header:
- .ascii "PE"
- .short 0
-coff_header:
- .short 0xaa64 // AArch64
- .short 2 // nr_sections
- .long 0 // TimeDateStamp
- .long 0 // PointerToSymbolTable
- .long 1 // NumberOfSymbols
- .short section_table - optional_header // SizeOfOptionalHeader
- .short 0x206 // Characteristics.
- // IMAGE_FILE_DEBUG_STRIPPED |
- // IMAGE_FILE_EXECUTABLE_IMAGE |
- // IMAGE_FILE_LINE_NUMS_STRIPPED
-optional_header:
- .short 0x20b // PE32+ format
- .byte 0x02 // MajorLinkerVersion
- .byte 0x14 // MinorLinkerVersion
- .long _end - efi_header_end // SizeOfCode
- .long 0 // SizeOfInitializedData
- .long 0 // SizeOfUninitializedData
- .long __efistub_entry - _head // AddressOfEntryPoint
- .long efi_header_end - _head // BaseOfCode
-
-extra_header_fields:
- .quad 0 // ImageBase
- .long 0x1000 // SectionAlignment
- .long PECOFF_FILE_ALIGNMENT // FileAlignment
- .short 0 // MajorOperatingSystemVersion
- .short 0 // MinorOperatingSystemVersion
- .short 0 // MajorImageVersion
- .short 0 // MinorImageVersion
- .short 0 // MajorSubsystemVersion
- .short 0 // MinorSubsystemVersion
- .long 0 // Win32VersionValue
-
- .long _end - _head // SizeOfImage
-
- // Everything before the kernel image is considered part of the header
- .long efi_header_end - _head // SizeOfHeaders
- .long 0 // CheckSum
- .short 0xa // Subsystem (EFI application)
- .short 0 // DllCharacteristics
- .quad 0 // SizeOfStackReserve
- .quad 0 // SizeOfStackCommit
- .quad 0 // SizeOfHeapReserve
- .quad 0 // SizeOfHeapCommit
- .long 0 // LoaderFlags
- .long (section_table - .) / 8 // NumberOfRvaAndSizes
-
- .quad 0 // ExportTable
- .quad 0 // ImportTable
- .quad 0 // ResourceTable
- .quad 0 // ExceptionTable
- .quad 0 // CertificationTable
- .quad 0 // BaseRelocationTable
-
-#ifdef CONFIG_DEBUG_EFI
- .long efi_debug_table - _head // DebugTable
- .long efi_debug_table_size
-#endif
-
- // Section table
-section_table:
-
- /*
- * The EFI application loader requires a relocation section
- * because EFI applications must be relocatable. This is a
- * dummy section as far as we are concerned.
- */
- .ascii ".reloc"
- .byte 0
- .byte 0 // end of 0 padding of section name
- .long 0
- .long 0
- .long 0 // SizeOfRawData
- .long 0 // PointerToRawData
- .long 0 // PointerToRelocations
- .long 0 // PointerToLineNumbers
- .short 0 // NumberOfRelocations
- .short 0 // NumberOfLineNumbers
- .long 0x42100040 // Characteristics (section flags)
-
-
- .ascii ".text"
- .byte 0
- .byte 0
- .byte 0 // end of 0 padding of section name
- .long _end - efi_header_end // VirtualSize
- .long efi_header_end - _head // VirtualAddress
- .long _edata - efi_header_end // SizeOfRawData
- .long efi_header_end - _head // PointerToRawData
-
- .long 0 // PointerToRelocations (0 for executables)
- .long 0 // PointerToLineNumbers (0 for executables)
- .short 0 // NumberOfRelocations (0 for executables)
- .short 0 // NumberOfLineNumbers (0 for executables)
- .long 0xe0500020 // Characteristics (section flags)
-
-#ifdef CONFIG_DEBUG_EFI
- /*
- * The debug table is referenced via its Relative Virtual Address (RVA),
- * which is only defined for those parts of the image that are covered
- * by a section declaration. Since this header is not covered by any
- * section, the debug table must be emitted elsewhere. So stick it in
- * the .init.rodata section instead.
- *
- * Note that the EFI debug entry itself may legally have a zero RVA,
- * which means we can simply put it right after the section headers.
- */
- __INITRODATA
-
- .align 2
-efi_debug_table:
- // EFI_IMAGE_DEBUG_DIRECTORY_ENTRY
- .long 0 // Characteristics
- .long 0 // TimeDateStamp
- .short 0 // MajorVersion
- .short 0 // MinorVersion
- .long 2 // Type == EFI_IMAGE_DEBUG_TYPE_CODEVIEW
- .long efi_debug_entry_size // SizeOfData
- .long 0 // RVA
- .long efi_debug_entry - _head // FileOffset
-
- .set efi_debug_table_size, . - efi_debug_table
- .previous
-
-efi_debug_entry:
- // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY
- .ascii "NB10" // Signature
- .long 0 // Unknown
- .long 0 // Unknown2
- .long 0 // Unknown3
-
- .asciz VMLINUX_PATH
-
- .set efi_debug_entry_size, . - efi_debug_entry
-#endif
-
- /*
- * EFI will load .text onwards at the 4k section alignment
- * described in the PE/COFF header. To ensure that instruction
- * sequences using an adrp and a :lo12: immediate will function
- * correctly at this alignment, we must ensure that .text is
- * placed at a 4k boundary in the Image to begin with.
- */
- .align 12
-efi_header_end:
+ __EFI_PE_HEADER
+#else
+ .long 0 // reserved
#endif
__INIT
@@ -534,13 +384,8 @@ ENTRY(kimage_vaddr)
ENTRY(el2_setup)
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
- b.ne 1f
- mrs x0, sctlr_el2
-CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2
-CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
- msr sctlr_el2, x0
- b 2f
-1: mrs x0, sctlr_el1
+ b.eq 1f
+ mrs x0, sctlr_el1
CPU_BE( orr x0, x0, #(3 << 24) ) // Set the EE and E0E bits for EL1
CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
msr sctlr_el1, x0
@@ -548,7 +393,11 @@ CPU_LE( bic x0, x0, #(3 << 24) ) // Clear the EE and E0E bits for EL1
isb
ret
-2:
+1: mrs x0, sctlr_el2
+CPU_BE( orr x0, x0, #(1 << 25) ) // Set the EE bit for EL2
+CPU_LE( bic x0, x0, #(1 << 25) ) // Clear the EE bit for EL2
+ msr sctlr_el2, x0
+
#ifdef CONFIG_ARM64_VHE
/*
* Check for VHE being present. For the rest of the EL2 setup,
@@ -594,14 +443,14 @@ set_hcr:
cmp x0, #1
b.ne 3f
- mrs_s x0, ICC_SRE_EL2
+ mrs_s x0, SYS_ICC_SRE_EL2
orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1
orr x0, x0, #ICC_SRE_EL2_ENABLE // Set ICC_SRE_EL2.Enable==1
- msr_s ICC_SRE_EL2, x0
+ msr_s SYS_ICC_SRE_EL2, x0
isb // Make sure SRE is now set
- mrs_s x0, ICC_SRE_EL2 // Read SRE back,
+ mrs_s x0, SYS_ICC_SRE_EL2 // Read SRE back,
tbz x0, #0, 3f // and check that it sticks
- msr_s ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults
+ msr_s SYS_ICH_HCR_EL2, xzr // Reset ICC_HCR_EL2 to defaults
3:
#endif
@@ -612,26 +461,6 @@ set_hcr:
msr vpidr_el2, x0
msr vmpidr_el2, x1
- /*
- * When VHE is not in use, early init of EL2 and EL1 needs to be
- * done here.
- * When VHE _is_ in use, EL1 will not be used in the host and
- * requires no configuration, and all non-hyp-specific EL2 setup
- * will be done via the _EL1 system register aliases in __cpu_setup.
- */
- cbnz x2, 1f
-
- /* sctlr_el1 */
- mov x0, #0x0800 // Set/clear RES{1,0} bits
-CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems
-CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
- msr sctlr_el1, x0
-
- /* Coprocessor traps. */
- mov x0, #0x33ff
- msr cptr_el2, x0 // Disable copro. traps to EL2
-1:
-
#ifdef CONFIG_COMPAT
msr hstr_el2, xzr // Disable CP15 traps to EL2
#endif
@@ -668,6 +497,23 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
ret
install_el2_stub:
+ /*
+ * When VHE is not in use, early init of EL2 and EL1 needs to be
+ * done here.
+ * When VHE _is_ in use, EL1 will not be used in the host and
+ * requires no configuration, and all non-hyp-specific EL2 setup
+ * will be done via the _EL1 system register aliases in __cpu_setup.
+ */
+ /* sctlr_el1 */
+ mov x0, #0x0800 // Set/clear RES{1,0} bits
+CPU_BE( movk x0, #0x33d0, lsl #16 ) // Set EE and E0E on BE systems
+CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems
+ msr sctlr_el1, x0
+
+ /* Coprocessor traps. */
+ mov x0, #0x33ff
+ msr cptr_el2, x0 // Disable copro. traps to EL2
+
/* Hypervisor stub */
adr_l x0, __hyp_stub_vectors
msr vbar_el2, x0
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 97a7384100f3..a44e13942d30 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -28,6 +28,7 @@
#include <asm/cacheflush.h>
#include <asm/cputype.h>
#include <asm/irqflags.h>
+#include <asm/kexec.h>
#include <asm/memory.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
@@ -102,7 +103,8 @@ int pfn_is_nosave(unsigned long pfn)
unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin);
unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1);
- return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+ return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)) ||
+ crash_is_nosave(pfn);
}
void notrace save_processor_state(void)
@@ -286,6 +288,9 @@ int swsusp_arch_suspend(void)
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
+ /* make the crash dump kernel image visible/saveable */
+ crash_prepare_suspend();
+
sleep_cpu = smp_processor_id();
ret = swsusp_save();
} else {
@@ -297,6 +302,9 @@ int swsusp_arch_suspend(void)
if (el2_reset_needed())
dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+ /* make the crash dump kernel image protected again */
+ crash_post_resume();
+
/*
* Tell the hibernation core that we've just restored
* the memory
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index d3b5f75e652e..e1261fbaa374 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -55,18 +55,7 @@ ENDPROC(__hyp_stub_vectors)
.align 11
el1_sync:
- mrs x30, esr_el2
- lsr x30, x30, #ESR_ELx_EC_SHIFT
-
- cmp x30, #ESR_ELx_EC_HVC64
- b.ne 9f // Not an HVC trap
-
- cmp x0, #HVC_GET_VECTORS
- b.ne 1f
- mrs x0, vbar_el2
- b 9f
-
-1: cmp x0, #HVC_SET_VECTORS
+ cmp x0, #HVC_SET_VECTORS
b.ne 2f
msr vbar_el2, x1
b 9f
@@ -79,10 +68,15 @@ el1_sync:
mov x1, x3
br x4 // no return
+3: cmp x0, #HVC_RESET_VECTORS
+ beq 9f // Nothing to reset!
+
/* Someone called kvm_call_hyp() against the hyp-stub... */
-3: mov x0, #ARM_EXCEPTION_HYP_GONE
+ ldr x0, =HVC_STUB_ERR
+ eret
-9: eret
+9: mov x0, xzr
+ eret
ENDPROC(el1_sync)
.macro invalid_vector label
@@ -121,19 +115,15 @@ ENDPROC(\label)
* initialisation entry point.
*/
-ENTRY(__hyp_get_vectors)
- str lr, [sp, #-16]!
- mov x0, #HVC_GET_VECTORS
- hvc #0
- ldr lr, [sp], #16
- ret
-ENDPROC(__hyp_get_vectors)
-
ENTRY(__hyp_set_vectors)
- str lr, [sp, #-16]!
mov x1, x0
mov x0, #HVC_SET_VECTORS
hvc #0
- ldr lr, [sp], #16
ret
ENDPROC(__hyp_set_vectors)
+
+ENTRY(__hyp_reset_vectors)
+ mov x0, #HVC_RESET_VECTORS
+ hvc #0
+ ret
+ENDPROC(__hyp_reset_vectors)
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 3a63954a8b14..b884a926a632 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -474,6 +474,7 @@ static u32 aarch64_insn_encode_register(enum aarch64_insn_register_type type,
shift = 10;
break;
case AARCH64_INSN_REGTYPE_RM:
+ case AARCH64_INSN_REGTYPE_RS:
shift = 16;
break;
default:
@@ -757,6 +758,111 @@ u32 aarch64_insn_gen_load_store_pair(enum aarch64_insn_register reg1,
offset >> shift);
}
+u32 aarch64_insn_gen_load_store_ex(enum aarch64_insn_register reg,
+ enum aarch64_insn_register base,
+ enum aarch64_insn_register state,
+ enum aarch64_insn_size_type size,
+ enum aarch64_insn_ldst_type type)
+{
+ u32 insn;
+
+ switch (type) {
+ case AARCH64_INSN_LDST_LOAD_EX:
+ insn = aarch64_insn_get_load_ex_value();
+ break;
+ case AARCH64_INSN_LDST_STORE_EX:
+ insn = aarch64_insn_get_store_ex_value();
+ break;
+ default:
+ pr_err("%s: unknown load/store exclusive encoding %d\n", __func__, type);
+ return AARCH64_BREAK_FAULT;
+ }
+
+ insn = aarch64_insn_encode_ldst_size(size, insn);
+
+ insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT, insn,
+ reg);
+
+ insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+ base);
+
+ insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT2, insn,
+ AARCH64_INSN_REG_ZR);
+
+ return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RS, insn,
+ state);
+}
+
+static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type,
+ enum aarch64_insn_prfm_target target,
+ enum aarch64_insn_prfm_policy policy,
+ u32 insn)
+{
+ u32 imm_type = 0, imm_target = 0, imm_policy = 0;
+
+ switch (type) {
+ case AARCH64_INSN_PRFM_TYPE_PLD:
+ break;
+ case AARCH64_INSN_PRFM_TYPE_PLI:
+ imm_type = BIT(0);
+ break;
+ case AARCH64_INSN_PRFM_TYPE_PST:
+ imm_type = BIT(1);
+ break;
+ default:
+ pr_err("%s: unknown prfm type encoding %d\n", __func__, type);
+ return AARCH64_BREAK_FAULT;
+ }
+
+ switch (target) {
+ case AARCH64_INSN_PRFM_TARGET_L1:
+ break;
+ case AARCH64_INSN_PRFM_TARGET_L2:
+ imm_target = BIT(0);
+ break;
+ case AARCH64_INSN_PRFM_TARGET_L3:
+ imm_target = BIT(1);
+ break;
+ default:
+ pr_err("%s: unknown prfm target encoding %d\n", __func__, target);
+ return AARCH64_BREAK_FAULT;
+ }
+
+ switch (policy) {
+ case AARCH64_INSN_PRFM_POLICY_KEEP:
+ break;
+ case AARCH64_INSN_PRFM_POLICY_STRM:
+ imm_policy = BIT(0);
+ break;
+ default:
+ pr_err("%s: unknown prfm policy encoding %d\n", __func__, policy);
+ return AARCH64_BREAK_FAULT;
+ }
+
+ /* In this case, imm5 is encoded into Rt field. */
+ insn &= ~GENMASK(4, 0);
+ insn |= imm_policy | (imm_target << 1) | (imm_type << 3);
+
+ return insn;
+}
+
+u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
+ enum aarch64_insn_prfm_type type,
+ enum aarch64_insn_prfm_target target,
+ enum aarch64_insn_prfm_policy policy)
+{
+ u32 insn = aarch64_insn_get_prfm_value();
+
+ insn = aarch64_insn_encode_ldst_size(AARCH64_INSN_SIZE_64, insn);
+
+ insn = aarch64_insn_encode_prfm_imm(type, target, policy, insn);
+
+ insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn,
+ base);
+
+ return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, 0);
+}
+
u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst,
enum aarch64_insn_register src,
int imm, enum aarch64_insn_variant variant,
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index 769f24ef628c..d7e90d97f5c4 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -131,11 +131,15 @@ 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.
+ * happens, increase the KASLR offset by the size of the kernel image
+ * rounded up by SWAPPER_BLOCK_SIZE.
*/
if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) !=
- (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT))
- offset = (offset + (u64)(_end - _text)) & mask;
+ (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) {
+ u64 kimg_sz = _end - _text;
+ offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE))
+ & mask;
+ }
if (IS_ENABLED(CONFIG_KASAN))
/*
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index bc96c8a7fc79..481f54a866c5 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -9,12 +9,19 @@
* published by the Free Software Foundation.
*/
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
#include <linux/kexec.h>
+#include <linux/page-flags.h>
#include <linux/smp.h>
#include <asm/cacheflush.h>
#include <asm/cpu_ops.h>
+#include <asm/memory.h>
+#include <asm/mmu.h>
#include <asm/mmu_context.h>
+#include <asm/page.h>
#include "cpu-reset.h"
@@ -22,8 +29,6 @@
extern const unsigned char arm64_relocate_new_kernel[];
extern const unsigned long arm64_relocate_new_kernel_size;
-static unsigned long kimage_start;
-
/**
* kexec_image_info - For debugging output.
*/
@@ -64,8 +69,6 @@ void machine_kexec_cleanup(struct kimage *kimage)
*/
int machine_kexec_prepare(struct kimage *kimage)
{
- kimage_start = kimage->start;
-
kexec_image_info(kimage);
if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) {
@@ -144,11 +147,15 @@ void machine_kexec(struct kimage *kimage)
{
phys_addr_t reboot_code_buffer_phys;
void *reboot_code_buffer;
+ bool in_kexec_crash = (kimage == kexec_crash_image);
+ bool stuck_cpus = cpus_are_stuck_in_kernel();
/*
* New cpus may have become stuck_in_kernel after we loaded the image.
*/
- BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1));
+ BUG_ON(!in_kexec_crash && (stuck_cpus || (num_online_cpus() > 1)));
+ WARN(in_kexec_crash && (stuck_cpus || smp_crash_stop_failed()),
+ "Some CPUs may be stale, kdump will be unreliable.\n");
reboot_code_buffer_phys = page_to_phys(kimage->control_code_page);
reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys);
@@ -183,7 +190,7 @@ void machine_kexec(struct kimage *kimage)
kexec_list_flush(kimage);
/* Flush the new image if already in place. */
- if (kimage->head & IND_DONE)
+ if ((kimage != kexec_crash_image) && (kimage->head & IND_DONE))
kexec_segment_flush(kimage);
pr_info("Bye!\n");
@@ -200,13 +207,158 @@ void machine_kexec(struct kimage *kimage)
* relocation is complete.
*/
- cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head,
- kimage_start, 0);
+ cpu_soft_restart(kimage != kexec_crash_image,
+ reboot_code_buffer_phys, kimage->head, kimage->start, 0);
BUG(); /* Should never get here. */
}
+static void machine_kexec_mask_interrupts(void)
+{
+ unsigned int i;
+ struct irq_desc *desc;
+
+ for_each_irq_desc(i, desc) {
+ struct irq_chip *chip;
+ int ret;
+
+ chip = irq_desc_get_chip(desc);
+ if (!chip)
+ continue;
+
+ /*
+ * First try to remove the active state. If this
+ * fails, try to EOI the interrupt.
+ */
+ ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+
+ if (ret && irqd_irq_inprogress(&desc->irq_data) &&
+ chip->irq_eoi)
+ chip->irq_eoi(&desc->irq_data);
+
+ if (chip->irq_mask)
+ chip->irq_mask(&desc->irq_data);
+
+ if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
+ chip->irq_disable(&desc->irq_data);
+ }
+}
+
+/**
+ * machine_crash_shutdown - shutdown non-crashing cpus and save registers
+ */
void machine_crash_shutdown(struct pt_regs *regs)
{
- /* Empty routine needed to avoid build errors. */
+ local_irq_disable();
+
+ /* shutdown non-crashing cpus */
+ smp_send_crash_stop();
+
+ /* for crashing cpu */
+ crash_save_cpu(regs, smp_processor_id());
+ machine_kexec_mask_interrupts();
+
+ pr_info("Starting crashdump kernel...\n");
+}
+
+void arch_kexec_protect_crashkres(void)
+{
+ int i;
+
+ kexec_segment_flush(kexec_crash_image);
+
+ for (i = 0; i < kexec_crash_image->nr_segments; i++)
+ set_memory_valid(
+ __phys_to_virt(kexec_crash_image->segment[i].mem),
+ kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 0);
+}
+
+void arch_kexec_unprotect_crashkres(void)
+{
+ int i;
+
+ for (i = 0; i < kexec_crash_image->nr_segments; i++)
+ set_memory_valid(
+ __phys_to_virt(kexec_crash_image->segment[i].mem),
+ kexec_crash_image->segment[i].memsz >> PAGE_SHIFT, 1);
+}
+
+#ifdef CONFIG_HIBERNATION
+/*
+ * To preserve the crash dump kernel image, the relevant memory segments
+ * should be mapped again around the hibernation.
+ */
+void crash_prepare_suspend(void)
+{
+ if (kexec_crash_image)
+ arch_kexec_unprotect_crashkres();
+}
+
+void crash_post_resume(void)
+{
+ if (kexec_crash_image)
+ arch_kexec_protect_crashkres();
+}
+
+/*
+ * crash_is_nosave
+ *
+ * Return true only if a page is part of reserved memory for crash dump kernel,
+ * but does not hold any data of loaded kernel image.
+ *
+ * Note that all the pages in crash dump kernel memory have been initially
+ * marked as Reserved in kexec_reserve_crashkres_pages().
+ *
+ * In hibernation, the pages which are Reserved and yet "nosave" are excluded
+ * from the hibernation iamge. crash_is_nosave() does thich check for crash
+ * dump kernel and will reduce the total size of hibernation image.
+ */
+
+bool crash_is_nosave(unsigned long pfn)
+{
+ int i;
+ phys_addr_t addr;
+
+ if (!crashk_res.end)
+ return false;
+
+ /* in reserved memory? */
+ addr = __pfn_to_phys(pfn);
+ if ((addr < crashk_res.start) || (crashk_res.end < addr))
+ return false;
+
+ if (!kexec_crash_image)
+ return true;
+
+ /* not part of loaded kernel image? */
+ for (i = 0; i < kexec_crash_image->nr_segments; i++)
+ if (addr >= kexec_crash_image->segment[i].mem &&
+ addr < (kexec_crash_image->segment[i].mem +
+ kexec_crash_image->segment[i].memsz))
+ return false;
+
+ return true;
+}
+
+void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
+{
+ unsigned long addr;
+ struct page *page;
+
+ for (addr = begin; addr < end; addr += PAGE_SIZE) {
+ page = phys_to_page(addr);
+ ClearPageReserved(page);
+ free_reserved_page(page);
+ }
+}
+#endif /* CONFIG_HIBERNATION */
+
+void arch_crash_save_vmcoreinfo(void)
+{
+ VMCOREINFO_NUMBER(VA_BITS);
+ /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */
+ vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n",
+ kimage_voffset);
+ vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
+ PHYS_OFFSET);
}
diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c
index 1ce90d8450ae..d05dbe658409 100644
--- a/arch/arm64/kernel/module-plts.c
+++ b/arch/arm64/kernel/module-plts.c
@@ -1,5 +1,5 @@
/*
- * Copyright (C) 2014-2016 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
@@ -26,35 +26,21 @@ struct plt_entry {
__le32 br; /* br x16 */
};
-u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
+static bool in_init(const struct module *mod, void *loc)
+{
+ return (u64)loc - (u64)mod->init_layout.base < mod->init_layout.size;
+}
+
+u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela,
Elf64_Sym *sym)
{
- struct plt_entry *plt = (struct plt_entry *)mod->arch.plt->sh_addr;
- int i = mod->arch.plt_num_entries;
+ struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core :
+ &mod->arch.init;
+ struct plt_entry *plt = (struct plt_entry *)pltsec->plt->sh_addr;
+ int i = pltsec->plt_num_entries;
u64 val = sym->st_value + rela->r_addend;
/*
- * We only emit PLT entries against undefined (SHN_UNDEF) symbols,
- * which are listed in the ELF symtab section, but without a type
- * or a size.
- * So, similar to how the module loader uses the Elf64_Sym::st_value
- * field to store the resolved addresses of undefined symbols, let's
- * borrow the Elf64_Sym::st_size field (whose value is never used by
- * the module loader, even for symbols that are defined) to record
- * the address of a symbol's associated PLT entry as we emit it for a
- * zero addend relocation (which is the only kind we have to deal with
- * in practice). This allows us to find duplicates without having to
- * go through the table every time.
- */
- if (rela->r_addend == 0 && sym->st_size != 0) {
- BUG_ON(sym->st_size < (u64)plt || sym->st_size >= (u64)&plt[i]);
- return sym->st_size;
- }
-
- mod->arch.plt_num_entries++;
- BUG_ON(mod->arch.plt_num_entries > mod->arch.plt_max_entries);
-
- /*
* MOVK/MOVN/MOVZ opcode:
* +--------+------------+--------+-----------+-------------+---------+
* | sf[31] | opc[30:29] | 100101 | hw[22:21] | imm16[20:5] | Rd[4:0] |
@@ -72,8 +58,19 @@ u64 module_emit_plt_entry(struct module *mod, const Elf64_Rela *rela,
cpu_to_le32(0xd61f0200)
};
- if (rela->r_addend == 0)
- sym->st_size = (u64)&plt[i];
+ /*
+ * Check if the entry we just created is a duplicate. Given that the
+ * relocations are sorted, this will be the last entry we allocated.
+ * (if one exists).
+ */
+ if (i > 0 &&
+ plt[i].mov0 == plt[i - 1].mov0 &&
+ plt[i].mov1 == plt[i - 1].mov1 &&
+ plt[i].mov2 == plt[i - 1].mov2)
+ return (u64)&plt[i - 1];
+
+ pltsec->plt_num_entries++;
+ BUG_ON(pltsec->plt_num_entries > pltsec->plt_max_entries);
return (u64)&plt[i];
}
@@ -104,7 +101,8 @@ static bool duplicate_rel(const Elf64_Rela *rela, int num)
return num > 0 && cmp_rela(rela + num, rela + num - 1) == 0;
}
-static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
+static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num,
+ Elf64_Word dstidx)
{
unsigned int ret = 0;
Elf64_Sym *s;
@@ -116,13 +114,17 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
case R_AARCH64_CALL26:
/*
* We only have to consider branch targets that resolve
- * to undefined symbols. This is not simply a heuristic,
- * it is a fundamental limitation, since the PLT itself
- * is part of the module, and needs to be within 128 MB
- * as well, so modules can never grow beyond that limit.
+ * to symbols that are defined in a different section.
+ * This is not simply a heuristic, it is a fundamental
+ * limitation, since there is no guaranteed way to emit
+ * PLT entries sufficiently close to the branch if the
+ * section size exceeds the range of a branch
+ * instruction. So ignore relocations against defined
+ * symbols if they live in the same section as the
+ * relocation target.
*/
s = syms + ELF64_R_SYM(rela[i].r_info);
- if (s->st_shndx != SHN_UNDEF)
+ if (s->st_shndx == dstidx)
break;
/*
@@ -149,7 +151,8 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num)
int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
char *secstrings, struct module *mod)
{
- unsigned long plt_max_entries = 0;
+ unsigned long core_plts = 0;
+ unsigned long init_plts = 0;
Elf64_Sym *syms = NULL;
int i;
@@ -158,14 +161,16 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
* entries. Record the symtab address as well.
*/
for (i = 0; i < ehdr->e_shnum; i++) {
- if (strcmp(".plt", secstrings + sechdrs[i].sh_name) == 0)
- mod->arch.plt = sechdrs + i;
+ if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt"))
+ mod->arch.core.plt = sechdrs + i;
+ else if (!strcmp(secstrings + sechdrs[i].sh_name, ".init.plt"))
+ mod->arch.init.plt = sechdrs + i;
else if (sechdrs[i].sh_type == SHT_SYMTAB)
syms = (Elf64_Sym *)sechdrs[i].sh_addr;
}
- if (!mod->arch.plt) {
- pr_err("%s: module PLT section missing\n", mod->name);
+ if (!mod->arch.core.plt || !mod->arch.init.plt) {
+ pr_err("%s: module PLT section(s) missing\n", mod->name);
return -ENOEXEC;
}
if (!syms) {
@@ -188,14 +193,27 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
/* sort by type, symbol index and addend */
sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL);
- plt_max_entries += count_plts(syms, rels, numrels);
+ if (strncmp(secstrings + dstsec->sh_name, ".init", 5) != 0)
+ core_plts += count_plts(syms, rels, numrels,
+ sechdrs[i].sh_info);
+ else
+ init_plts += count_plts(syms, rels, numrels,
+ sechdrs[i].sh_info);
}
- mod->arch.plt->sh_type = SHT_NOBITS;
- mod->arch.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
- mod->arch.plt->sh_addralign = L1_CACHE_BYTES;
- mod->arch.plt->sh_size = plt_max_entries * sizeof(struct plt_entry);
- mod->arch.plt_num_entries = 0;
- mod->arch.plt_max_entries = plt_max_entries;
+ mod->arch.core.plt->sh_type = SHT_NOBITS;
+ mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.core.plt->sh_size = (core_plts + 1) * sizeof(struct plt_entry);
+ mod->arch.core.plt_num_entries = 0;
+ mod->arch.core.plt_max_entries = core_plts;
+
+ mod->arch.init.plt->sh_type = SHT_NOBITS;
+ mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC;
+ mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES;
+ mod->arch.init.plt->sh_size = (init_plts + 1) * sizeof(struct plt_entry);
+ mod->arch.init.plt_num_entries = 0;
+ mod->arch.init.plt_max_entries = init_plts;
+
return 0;
}
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 7f316982ce00..c9a2ab446dc6 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -380,7 +380,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
if (IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
ovf == -ERANGE) {
- val = module_emit_plt_entry(me, &rel[i], sym);
+ val = module_emit_plt_entry(me, loc, &rel[i], sym);
ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 2,
26, AARCH64_INSN_IMM_26);
}
diff --git a/arch/arm64/kernel/module.lds b/arch/arm64/kernel/module.lds
index 8949f6c6f729..f7c9781a9d48 100644
--- a/arch/arm64/kernel/module.lds
+++ b/arch/arm64/kernel/module.lds
@@ -1,3 +1,4 @@
SECTIONS {
.plt (NOLOAD) : { BYTE(0) }
+ .init.plt (NOLOAD) : { BYTE(0) }
}
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 57ae9d9ed9bb..bcc79471b38e 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -290,6 +290,12 @@ static const unsigned armv8_a53_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[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,
@@ -957,10 +963,26 @@ static int armv8_vulcan_map_event(struct perf_event *event)
ARMV8_PMU_EVTYPE_EVENT);
}
+struct armv8pmu_probe_info {
+ struct arm_pmu *pmu;
+ bool present;
+};
+
static void __armv8pmu_probe_pmu(void *info)
{
- struct arm_pmu *cpu_pmu = info;
+ struct armv8pmu_probe_info *probe = info;
+ struct arm_pmu *cpu_pmu = probe->pmu;
+ u64 dfr0;
u32 pmceid[2];
+ int pmuver;
+
+ dfr0 = read_sysreg(id_aa64dfr0_el1);
+ pmuver = cpuid_feature_extract_signed_field(dfr0,
+ ID_AA64DFR0_PMUVER_SHIFT);
+ if (pmuver < 1)
+ return;
+
+ probe->present = true;
/* Read the nb of CNTx counters supported from PMNC */
cpu_pmu->num_events = (armv8pmu_pmcr_read() >> ARMV8_PMU_PMCR_N_SHIFT)
@@ -979,13 +1001,27 @@ static void __armv8pmu_probe_pmu(void *info)
static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
{
- return smp_call_function_any(&cpu_pmu->supported_cpus,
+ struct armv8pmu_probe_info probe = {
+ .pmu = cpu_pmu,
+ .present = false,
+ };
+ int ret;
+
+ ret = smp_call_function_any(&cpu_pmu->supported_cpus,
__armv8pmu_probe_pmu,
- cpu_pmu, 1);
+ &probe, 1);
+ if (ret)
+ return ret;
+
+ return probe.present ? 0 : -ENODEV;
}
-static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
+static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
{
+ int ret = armv8pmu_probe_pmu(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->handle_irq = armv8pmu_handle_irq,
cpu_pmu->enable = armv8pmu_enable_event,
cpu_pmu->disable = armv8pmu_disable_event,
@@ -997,78 +1033,104 @@ static void armv8_pmu_init(struct arm_pmu *cpu_pmu)
cpu_pmu->reset = armv8pmu_reset,
cpu_pmu->max_period = (1LLU << 32) - 1,
cpu_pmu->set_event_filter = armv8pmu_set_event_filter;
+
+ return 0;
}
static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_pmuv3";
cpu_pmu->map_event = armv8_pmuv3_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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_cortex_a53";
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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_cortex_a57";
cpu_pmu->map_event = armv8_a57_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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_cortex_a72";
cpu_pmu->map_event = armv8_a57_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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_cavium_thunder";
cpu_pmu->map_event = armv8_thunder_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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
{
- armv8_pmu_init(cpu_pmu);
+ int ret = armv8_pmu_init(cpu_pmu);
+ if (ret)
+ return ret;
+
cpu_pmu->name = "armv8_brcm_vulcan";
cpu_pmu->map_event = armv8_vulcan_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 armv8pmu_probe_pmu(cpu_pmu);
+
+ return 0;
}
static const struct of_device_id armv8_pmu_of_device_ids[] = {
@@ -1081,24 +1143,9 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
{},
};
-/*
- * Non DT systems have their micro/arch events probed at run-time.
- * A fairly complete list of generic events are provided and ones that
- * aren't supported by the current PMU are disabled.
- */
-static const struct pmu_probe_info armv8_pmu_probe_table[] = {
- PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
- { /* sentinel value */ }
-};
-
static int armv8_pmu_device_probe(struct platform_device *pdev)
{
- if (acpi_disabled)
- return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
- NULL);
-
- return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
- armv8_pmu_probe_table);
+ return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
}
static struct platform_driver armv8_pmu_driver = {
@@ -1109,4 +1156,11 @@ static struct platform_driver armv8_pmu_driver = {
.probe = armv8_pmu_device_probe,
};
-builtin_platform_driver(armv8_pmu_driver);
+static int __init armv8_pmu_driver_init(void)
+{
+ if (acpi_disabled)
+ return platform_driver_register(&armv8_pmu_driver);
+ else
+ return arm_pmu_acpi_probe(armv8_pmuv3_init);
+}
+device_initcall(armv8_pmu_driver_init)
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 2a07aae5b8a2..c5c45942fb6e 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -372,12 +372,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
return 0;
}
-int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
- unsigned long val, void *data)
-{
- return NOTIFY_DONE;
-}
-
static void __kprobes kprobe_handler(struct pt_regs *regs)
{
struct kprobe *p, *cur_kprobe;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 043d373b8369..ae2a835898d7 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -205,12 +205,10 @@ void __show_regs(struct pt_regs *regs)
pr_cont("\n");
}
- printk("\n");
}
void show_regs(struct pt_regs * regs)
{
- printk("\n");
__show_regs(regs);
}
diff --git a/arch/arm64/kernel/reloc_test_core.c b/arch/arm64/kernel/reloc_test_core.c
new file mode 100644
index 000000000000..c124752a8bd3
--- /dev/null
+++ b/arch/arm64/kernel/reloc_test_core.c
@@ -0,0 +1,81 @@
+/*
+ * 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 <linux/module.h>
+
+int sym64_rel;
+
+#define SYM64_ABS_VAL 0xffff880000cccccc
+#define SYM32_ABS_VAL 0xf800cccc
+#define SYM16_ABS_VAL 0xf8cc
+
+#define __SET_ABS(name, val) asm(".globl " #name "; .set "#name ", " #val)
+#define SET_ABS(name, val) __SET_ABS(name, val)
+
+SET_ABS(sym64_abs, SYM64_ABS_VAL);
+SET_ABS(sym32_abs, SYM32_ABS_VAL);
+SET_ABS(sym16_abs, SYM16_ABS_VAL);
+
+asmlinkage u64 absolute_data64(void);
+asmlinkage u64 absolute_data32(void);
+asmlinkage u64 absolute_data16(void);
+asmlinkage u64 signed_movw(void);
+asmlinkage u64 unsigned_movw(void);
+asmlinkage u64 relative_adrp(void);
+asmlinkage u64 relative_adr(void);
+asmlinkage u64 relative_data64(void);
+asmlinkage u64 relative_data32(void);
+asmlinkage u64 relative_data16(void);
+
+static struct {
+ char name[32];
+ u64 (*f)(void);
+ u64 expect;
+} const funcs[] = {
+ { "R_AARCH64_ABS64", absolute_data64, UL(SYM64_ABS_VAL) },
+ { "R_AARCH64_ABS32", absolute_data32, UL(SYM32_ABS_VAL) },
+ { "R_AARCH64_ABS16", absolute_data16, UL(SYM16_ABS_VAL) },
+ { "R_AARCH64_MOVW_SABS_Gn", signed_movw, UL(SYM64_ABS_VAL) },
+ { "R_AARCH64_MOVW_UABS_Gn", unsigned_movw, UL(SYM64_ABS_VAL) },
+#ifndef CONFIG_ARM64_ERRATUM_843419
+ { "R_AARCH64_ADR_PREL_PG_HI21", relative_adrp, (u64)&sym64_rel },
+#endif
+ { "R_AARCH64_ADR_PREL_LO21", relative_adr, (u64)&sym64_rel },
+ { "R_AARCH64_PREL64", relative_data64, (u64)&sym64_rel },
+ { "R_AARCH64_PREL32", relative_data32, (u64)&sym64_rel },
+ { "R_AARCH64_PREL16", relative_data16, (u64)&sym64_rel },
+};
+
+static int reloc_test_init(void)
+{
+ int i;
+
+ pr_info("Relocation test:\n");
+ pr_info("-------------------------------------------------------\n");
+
+ for (i = 0; i < ARRAY_SIZE(funcs); i++) {
+ u64 ret = funcs[i].f();
+
+ pr_info("%-31s 0x%016llx %s\n", funcs[i].name, ret,
+ ret == funcs[i].expect ? "pass" : "fail");
+ if (ret != funcs[i].expect)
+ pr_err("Relocation failed, expected 0x%016llx, not 0x%016llx\n",
+ funcs[i].expect, ret);
+ }
+ return 0;
+}
+
+static void reloc_test_exit(void)
+{
+}
+
+module_init(reloc_test_init);
+module_exit(reloc_test_exit);
+
+MODULE_LICENSE("GPL v2");
diff --git a/arch/arm64/kernel/reloc_test_syms.S b/arch/arm64/kernel/reloc_test_syms.S
new file mode 100644
index 000000000000..e1edcefeb02d
--- /dev/null
+++ b/arch/arm64/kernel/reloc_test_syms.S
@@ -0,0 +1,83 @@
+/*
+ * 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 <linux/linkage.h>
+
+ENTRY(absolute_data64)
+ ldr x0, 0f
+ ret
+0: .quad sym64_abs
+ENDPROC(absolute_data64)
+
+ENTRY(absolute_data32)
+ ldr w0, 0f
+ ret
+0: .long sym32_abs
+ENDPROC(absolute_data32)
+
+ENTRY(absolute_data16)
+ adr x0, 0f
+ ldrh w0, [x0]
+ ret
+0: .short sym16_abs, 0
+ENDPROC(absolute_data16)
+
+ENTRY(signed_movw)
+ movz x0, #:abs_g2_s:sym64_abs
+ movk x0, #:abs_g1_nc:sym64_abs
+ movk x0, #:abs_g0_nc:sym64_abs
+ ret
+ENDPROC(signed_movw)
+
+ENTRY(unsigned_movw)
+ movz x0, #:abs_g3:sym64_abs
+ movk x0, #:abs_g2_nc:sym64_abs
+ movk x0, #:abs_g1_nc:sym64_abs
+ movk x0, #:abs_g0_nc:sym64_abs
+ ret
+ENDPROC(unsigned_movw)
+
+#ifndef CONFIG_ARM64_ERRATUM_843419
+
+ENTRY(relative_adrp)
+ adrp x0, sym64_rel
+ add x0, x0, #:lo12:sym64_rel
+ ret
+ENDPROC(relative_adrp)
+
+#endif
+
+ENTRY(relative_adr)
+ adr x0, sym64_rel
+ ret
+ENDPROC(relative_adr)
+
+ENTRY(relative_data64)
+ adr x1, 0f
+ ldr x0, [x1]
+ add x0, x0, x1
+ ret
+0: .quad sym64_rel - .
+ENDPROC(relative_data64)
+
+ENTRY(relative_data32)
+ adr x1, 0f
+ ldr w0, [x1]
+ add x0, x0, x1
+ ret
+0: .long sym64_rel - .
+ENDPROC(relative_data32)
+
+ENTRY(relative_data16)
+ adr x1, 0f
+ ldrsh w0, [x1]
+ add x0, x0, x1
+ ret
+0: .short sym64_rel - ., 0
+ENDPROC(relative_data16)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 42274bda0ccb..2c822ef94f34 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -31,7 +31,6 @@
#include <linux/screen_info.h>
#include <linux/init.h>
#include <linux/kexec.h>
-#include <linux/crash_dump.h>
#include <linux/root_dev.h>
#include <linux/cpu.h>
#include <linux/interrupt.h>
@@ -181,6 +180,7 @@ static void __init smp_build_mpidr_hash(void)
static void __init setup_machine_fdt(phys_addr_t dt_phys)
{
void *dt_virt = fixmap_remap_fdt(dt_phys);
+ const char *name;
if (!dt_virt || !early_init_dt_scan(dt_virt)) {
pr_crit("\n"
@@ -193,7 +193,9 @@ static void __init setup_machine_fdt(phys_addr_t dt_phys)
cpu_relax();
}
- dump_stack_set_arch_desc("%s (DT)", of_flat_dt_get_machine_name());
+ name = of_flat_dt_get_machine_name();
+ pr_info("Machine model: %s\n", name);
+ dump_stack_set_arch_desc("%s (DT)", name);
}
static void __init request_standard_resources(void)
@@ -226,6 +228,12 @@ static void __init request_standard_resources(void)
if (kernel_data.start >= res->start &&
kernel_data.end <= res->end)
request_resource(res, &kernel_data);
+#ifdef CONFIG_KEXEC_CORE
+ /* Userspace will find "Crash kernel" region in /proc/iomem. */
+ if (crashk_res.end && crashk_res.start >= res->start &&
+ crashk_res.end <= res->end)
+ request_resource(res, &crashk_res);
+#endif
}
}
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index ef1caae02110..6e0e16a3a7d4 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -39,6 +39,7 @@
#include <linux/completion.h>
#include <linux/of.h>
#include <linux/irq_work.h>
+#include <linux/kexec.h>
#include <asm/alternative.h>
#include <asm/atomic.h>
@@ -76,6 +77,7 @@ enum ipi_msg_type {
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
+ IPI_CPU_CRASH_STOP,
IPI_TIMER,
IPI_IRQ_WORK,
IPI_WAKEUP
@@ -434,6 +436,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
setup_cpu_features();
hyp_mode_check();
apply_alternatives_all();
+ mark_linear_text_alias_ro();
}
void __init smp_prepare_boot_cpu(void)
@@ -518,6 +521,13 @@ static bool bootcpu_valid __initdata;
static unsigned int cpu_count = 1;
#ifdef CONFIG_ACPI
+static struct acpi_madt_generic_interrupt cpu_madt_gicc[NR_CPUS];
+
+struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
+{
+ return &cpu_madt_gicc[cpu];
+}
+
/*
* acpi_map_gic_cpu_interface - parse processor MADT entry
*
@@ -552,6 +562,7 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
return;
}
bootcpu_valid = true;
+ cpu_madt_gicc[0] = *processor;
early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
return;
}
@@ -562,6 +573,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
/* map the logical cpu id to cpu MPIDR */
cpu_logical_map(cpu_count) = hwid;
+ cpu_madt_gicc[cpu_count] = *processor;
+
/*
* Set-up the ACPI parking protocol cpu entries
* while initializing the cpu_logical_map to
@@ -755,6 +768,7 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = {
S(IPI_RESCHEDULE, "Rescheduling interrupts"),
S(IPI_CALL_FUNC, "Function call interrupts"),
S(IPI_CPU_STOP, "CPU stop interrupts"),
+ S(IPI_CPU_CRASH_STOP, "CPU stop (for crash dump) interrupts"),
S(IPI_TIMER, "Timer broadcast interrupts"),
S(IPI_IRQ_WORK, "IRQ work interrupts"),
S(IPI_WAKEUP, "CPU wake-up interrupts"),
@@ -829,6 +843,29 @@ static void ipi_cpu_stop(unsigned int cpu)
cpu_relax();
}
+#ifdef CONFIG_KEXEC_CORE
+static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+#endif
+
+static void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+{
+#ifdef CONFIG_KEXEC_CORE
+ crash_save_cpu(regs, cpu);
+
+ atomic_dec(&waiting_for_crash_ipi);
+
+ local_irq_disable();
+
+#ifdef CONFIG_HOTPLUG_CPU
+ if (cpu_ops[cpu]->cpu_die)
+ cpu_ops[cpu]->cpu_die(cpu);
+#endif
+
+ /* just in case */
+ cpu_park_loop();
+#endif
+}
+
/*
* Main handler for inter-processor interrupts
*/
@@ -859,6 +896,15 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
irq_exit();
break;
+ case IPI_CPU_CRASH_STOP:
+ if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
+ irq_enter();
+ ipi_cpu_crash_stop(cpu, regs);
+
+ unreachable();
+ }
+ break;
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
case IPI_TIMER:
irq_enter();
@@ -931,6 +977,39 @@ void smp_send_stop(void)
cpumask_pr_args(cpu_online_mask));
}
+#ifdef CONFIG_KEXEC_CORE
+void smp_send_crash_stop(void)
+{
+ cpumask_t mask;
+ unsigned long timeout;
+
+ if (num_online_cpus() == 1)
+ return;
+
+ cpumask_copy(&mask, cpu_online_mask);
+ cpumask_clear_cpu(smp_processor_id(), &mask);
+
+ atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+
+ pr_crit("SMP: stopping secondary CPUs\n");
+ smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
+
+ /* Wait up to one second for other CPUs to stop */
+ timeout = USEC_PER_SEC;
+ while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+ udelay(1);
+
+ if (atomic_read(&waiting_for_crash_ipi) > 0)
+ pr_warning("SMP: failed to stop secondary CPUs %*pbl\n",
+ cpumask_pr_args(&mask));
+}
+
+bool smp_crash_stop_failed(void)
+{
+ return (atomic_read(&waiting_for_crash_ipi) > 0);
+}
+#endif
+
/*
* not supported here
*/
@@ -944,7 +1023,7 @@ static bool have_cpu_die(void)
#ifdef CONFIG_HOTPLUG_CPU
int any_cpu = raw_smp_processor_id();
- if (cpu_ops[any_cpu]->cpu_die)
+ if (cpu_ops[any_cpu] && cpu_ops[any_cpu]->cpu_die)
return true;
#endif
return false;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index e52be6aa44ee..d4d6ae02cd55 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -505,6 +505,22 @@ static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
regs->pc += 4;
}
+static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+ regs->pc += 4;
+}
+
+static void cntfrq_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+ int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+ pt_regs_write_reg(regs, rt, read_sysreg(cntfrq_el0));
+ regs->pc += 4;
+}
+
struct sys64_hook {
unsigned int esr_mask;
unsigned int esr_val;
@@ -523,6 +539,18 @@ static struct sys64_hook sys64_hooks[] = {
.esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
.handler = ctr_read_handler,
},
+ {
+ /* Trap read access to CNTVCT_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTVCT,
+ .handler = cntvct_read_handler,
+ },
+ {
+ /* Trap read access to CNTFRQ_EL0 */
+ .esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+ .esr_val = ESR_ELx_SYS64_ISS_SYS_CNTFRQ,
+ .handler = cntfrq_read_handler,
+ },
{},
};
diff --git a/arch/arm64/kernel/vdso/.gitignore b/arch/arm64/kernel/vdso/.gitignore
index b8cc94e9698b..f8b69d84238e 100644
--- a/arch/arm64/kernel/vdso/.gitignore
+++ b/arch/arm64/kernel/vdso/.gitignore
@@ -1,2 +1 @@
vdso.lds
-vdso-offsets.h
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index b8deffa9e1bf..987a00ee446c 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -143,12 +143,27 @@ SECTIONS
. = ALIGN(SEGMENT_ALIGN);
__init_begin = .;
+ __inittext_begin = .;
INIT_TEXT_SECTION(8)
.exit.text : {
ARM_EXIT_KEEP(EXIT_TEXT)
}
+ . = ALIGN(4);
+ .altinstructions : {
+ __alt_instructions = .;
+ *(.altinstructions)
+ __alt_instructions_end = .;
+ }
+ .altinstr_replacement : {
+ *(.altinstr_replacement)
+ }
+
+ . = ALIGN(PAGE_SIZE);
+ __inittext_end = .;
+ __initdata_begin = .;
+
.init.data : {
INIT_DATA
INIT_SETUP(16)
@@ -164,15 +179,6 @@ SECTIONS
PERCPU_SECTION(L1_CACHE_BYTES)
- . = ALIGN(4);
- .altinstructions : {
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
- .altinstr_replacement : {
- *(.altinstr_replacement)
- }
.rela : ALIGN(8) {
*(.rela .rela*)
}
@@ -181,6 +187,7 @@ SECTIONS
__rela_size = SIZEOF(.rela);
. = ALIGN(SEGMENT_ALIGN);
+ __initdata_end = .;
__init_end = .;
_data = .;
@@ -206,6 +213,7 @@ SECTIONS
}
PECOFF_EDATA_PADDING
+ __pecoff_data_rawsize = ABSOLUTE(. - __initdata_begin);
_edata = .;
BSS_SECTION(0, 0, 0)
@@ -221,6 +229,7 @@ SECTIONS
. += RESERVED_TTBR0_SIZE;
#endif
+ __pecoff_data_size = ABSOLUTE(. - __initdata_begin);
_end = .;
STABS_DEBUG
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 1bfe30dfbfe7..fa1b18e364fc 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -135,7 +135,19 @@ static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
return ret;
}
+static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+ u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+ kvm_pr_unimpl("Unknown exception class: hsr: %#08x -- %s\n",
+ hsr, esr_get_class_string(hsr));
+
+ kvm_inject_undefined(vcpu);
+ return 1;
+}
+
static exit_handle_fn arm_exit_handlers[] = {
+ [0 ... ESR_ELx_EC_MAX] = kvm_handle_unknown_ec,
[ESR_ELx_EC_WFx] = kvm_handle_wfx,
[ESR_ELx_EC_CP15_32] = kvm_handle_cp15_32,
[ESR_ELx_EC_CP15_64] = kvm_handle_cp15_64,
@@ -162,13 +174,6 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
u32 hsr = kvm_vcpu_get_hsr(vcpu);
u8 hsr_ec = ESR_ELx_EC(hsr);
- if (hsr_ec >= ARRAY_SIZE(arm_exit_handlers) ||
- !arm_exit_handlers[hsr_ec]) {
- kvm_err("Unknown exception class: hsr: %#08x -- %s\n",
- hsr, esr_get_class_string(hsr));
- BUG();
- }
-
return arm_exit_handlers[hsr_ec];
}
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 6b29d3d9e1f2..839425c24b1c 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -22,6 +22,7 @@
#include <asm/kvm_mmu.h>
#include <asm/pgtable-hwdef.h>
#include <asm/sysreg.h>
+#include <asm/virt.h>
.text
.pushsection .hyp.idmap.text, "ax"
@@ -58,6 +59,9 @@ __invalid:
* x2: HYP vectors
*/
__do_hyp_init:
+ /* Check for a stub HVC call */
+ cmp x0, #HVC_STUB_HCALL_NR
+ b.lo __kvm_handle_stub_hvc
msr ttbr0_el2, x0
@@ -119,23 +123,45 @@ __do_hyp_init:
eret
ENDPROC(__kvm_hyp_init)
+ENTRY(__kvm_handle_stub_hvc)
+ cmp x0, #HVC_SOFT_RESTART
+ b.ne 1f
+
+ /* This is where we're about to jump, staying at EL2 */
+ msr elr_el2, x1
+ mov x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h)
+ msr spsr_el2, x0
+
+ /* Shuffle the arguments, and don't come back */
+ mov x0, x2
+ mov x1, x3
+ mov x2, x4
+ b reset
+
+1: cmp x0, #HVC_RESET_VECTORS
+ b.ne 1f
+reset:
/*
- * Reset kvm back to the hyp stub.
+ * Reset kvm back to the hyp stub. Do not clobber x0-x4 in
+ * case we coming via HVC_SOFT_RESTART.
*/
-ENTRY(__kvm_hyp_reset)
- /* We're now in idmap, disable MMU */
- mrs x0, sctlr_el2
- ldr x1, =SCTLR_ELx_FLAGS
- bic x0, x0, x1 // Clear SCTL_M and etc
- msr sctlr_el2, x0
+ mrs x5, sctlr_el2
+ ldr x6, =SCTLR_ELx_FLAGS
+ bic x5, x5, x6 // Clear SCTL_M and etc
+ msr sctlr_el2, x5
isb
/* Install stub vectors */
- adr_l x0, __hyp_stub_vectors
- msr vbar_el2, x0
+ adr_l x5, __hyp_stub_vectors
+ msr vbar_el2, x5
+ mov x0, xzr
+ eret
+1: /* Bad stub call */
+ ldr x0, =HVC_STUB_ERR
eret
-ENDPROC(__kvm_hyp_reset)
+
+ENDPROC(__kvm_handle_stub_hvc)
.ltorg
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 2726635dceba..952f6cb9cf72 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -36,15 +36,12 @@
* passed in x0.
*
* A function pointer with a value less than 0xfff has a special meaning,
- * and is used to implement __hyp_get_vectors in the same way as in
+ * and is used to implement hyp stubs in the same way as in
* arch/arm64/kernel/hyp_stub.S.
- * HVC behaves as a 'bl' call and will clobber lr.
*/
ENTRY(__kvm_call_hyp)
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
- str lr, [sp, #-16]!
hvc #0
- ldr lr, [sp], #16
ret
alternative_else_nop_endif
b __vhe_hyp_call
diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S
index 5e9052f087f2..5170ce1021da 100644
--- a/arch/arm64/kvm/hyp/hyp-entry.S
+++ b/arch/arm64/kvm/hyp/hyp-entry.S
@@ -32,17 +32,17 @@
* Shuffle the parameters before calling the function
* pointed to in x0. Assumes parameters in x[1,2,3].
*/
+ str lr, [sp, #-16]!
mov lr, x0
mov x0, x1
mov x1, x2
mov x2, x3
blr lr
+ ldr lr, [sp], #16
.endm
ENTRY(__vhe_hyp_call)
- str lr, [sp, #-16]!
do_el2_call
- ldr lr, [sp], #16
/*
* We used to rely on having an exception return to get
* an implicit isb. In the E2H case, we don't have it anymore.
@@ -53,21 +53,6 @@ ENTRY(__vhe_hyp_call)
ret
ENDPROC(__vhe_hyp_call)
-/*
- * Compute the idmap address of __kvm_hyp_reset based on the idmap
- * start passed as a parameter, and jump there.
- *
- * x0: HYP phys_idmap_start
- */
-ENTRY(__kvm_hyp_teardown)
- mov x4, x0
- adr_l x3, __kvm_hyp_reset
-
- /* insert __kvm_hyp_reset()s offset into phys_idmap_start */
- bfi x4, x3, #0, #PAGE_SHIFT
- br x4
-ENDPROC(__kvm_hyp_teardown)
-
el1_sync: // Guest trapped into EL2
stp x0, x1, [sp, #-16]!
@@ -87,10 +72,24 @@ alternative_endif
/* Here, we're pretty sure the host called HVC. */
ldp x0, x1, [sp], #16
- cmp x0, #HVC_GET_VECTORS
- b.ne 1f
- mrs x0, vbar_el2
- b 2f
+ /* Check for a stub HVC call */
+ cmp x0, #HVC_STUB_HCALL_NR
+ b.hs 1f
+
+ /*
+ * Compute the idmap address of __kvm_handle_stub_hvc and
+ * jump there. Since we use kimage_voffset, do not use the
+ * HYP VA for __kvm_handle_stub_hvc, but the kernel VA instead
+ * (by loading it from the constant pool).
+ *
+ * Preserve x0-x4, which may contain stub parameters.
+ */
+ ldr x5, =__kvm_handle_stub_hvc
+ ldr_l x6, kimage_voffset
+
+ /* x5 = __pa(x5) */
+ sub x5, x5, x6
+ br x5
1:
/*
@@ -99,7 +98,7 @@ alternative_endif
kern_hyp_va x0
do_el2_call
-2: eret
+ eret
el1_trap:
/*
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index e8e7ba2bc11f..73464a96c365 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -18,14 +18,62 @@
#include <asm/kvm_hyp.h>
#include <asm/tlbflush.h>
+static void __hyp_text __tlb_switch_to_guest_vhe(struct kvm *kvm)
+{
+ u64 val;
+
+ /*
+ * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and
+ * most TLB operations target EL2/EL0. In order to affect the
+ * guest TLBs (EL1/EL0), we need to change one of these two
+ * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so
+ * let's flip TGE before executing the TLB operation.
+ */
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ val = read_sysreg(hcr_el2);
+ val &= ~HCR_TGE;
+ write_sysreg(val, hcr_el2);
+ isb();
+}
+
+static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm)
+{
+ write_sysreg(kvm->arch.vttbr, vttbr_el2);
+ isb();
+}
+
+static hyp_alternate_select(__tlb_switch_to_guest,
+ __tlb_switch_to_guest_nvhe,
+ __tlb_switch_to_guest_vhe,
+ ARM64_HAS_VIRT_HOST_EXTN);
+
+static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm)
+{
+ /*
+ * We're done with the TLB operation, let's restore the host's
+ * view of HCR_EL2.
+ */
+ write_sysreg(0, vttbr_el2);
+ write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+}
+
+static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm)
+{
+ write_sysreg(0, vttbr_el2);
+}
+
+static hyp_alternate_select(__tlb_switch_to_host,
+ __tlb_switch_to_host_nvhe,
+ __tlb_switch_to_host_vhe,
+ ARM64_HAS_VIRT_HOST_EXTN);
+
void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
{
dsb(ishst);
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
/*
* We could do so much better if we had the VA as well.
@@ -46,7 +94,29 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
dsb(ish);
isb();
- write_sysreg(0, vttbr_el2);
+ /*
+ * If the host is running at EL1 and we have a VPIPT I-cache,
+ * then we must perform I-cache maintenance at EL2 in order for
+ * it to have an effect on the guest. Since the guest cannot hit
+ * I-cache lines allocated with a different VMID, we don't need
+ * to worry about junk out of guest reset (we nuke the I-cache on
+ * VMID rollover), but we do need to be careful when remapping
+ * executable pages for the same guest. This can happen when KSM
+ * takes a CoW fault on an executable page, copies the page into
+ * a page that was previously mapped in the guest and then needs
+ * to invalidate the guest view of the I-cache for that page
+ * from EL1. To solve this, we invalidate the entire I-cache when
+ * unmapping a page from a guest if we have a VPIPT I-cache but
+ * the host is running at EL1. As above, we could do better if
+ * we had the VA.
+ *
+ * The moral of this story is: if you have a VPIPT I-cache, then
+ * you should be running with VHE enabled.
+ */
+ if (!has_vhe() && icache_is_vpipt())
+ __flush_icache_all();
+
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -55,14 +125,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
/* Switch to requested VMID */
kvm = kern_hyp_va(kvm);
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
__tlbi(vmalls12e1is);
dsb(ish);
isb();
- write_sysreg(0, vttbr_el2);
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -70,14 +139,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
struct kvm *kvm = kern_hyp_va(kern_hyp_va(vcpu)->kvm);
/* Switch to requested VMID */
- write_sysreg(kvm->arch.vttbr, vttbr_el2);
- isb();
+ __tlb_switch_to_guest()(kvm);
__tlbi(vmalle1);
dsb(nsh);
isb();
- write_sysreg(0, vttbr_el2);
+ __tlb_switch_to_host()(kvm);
}
void __hyp_text __kvm_flush_vm_context(void)
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index d9e9697de1b2..561badf93de8 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -60,7 +60,7 @@ static bool cpu_has_32bit_el1(void)
{
u64 pfr0;
- pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1);
+ pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
return !!(pfr0 & 0x20);
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 0e26f8c2b56f..efbe9e8e7a78 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -55,6 +55,15 @@
* 64bit interface.
*/
+static bool read_from_write_only(struct kvm_vcpu *vcpu,
+ const struct sys_reg_params *params)
+{
+ WARN_ONCE(1, "Unexpected sys_reg read to write-only register\n");
+ print_sys_reg_instr(params);
+ kvm_inject_undefined(vcpu);
+ return false;
+}
+
/* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */
static u32 cache_levels;
@@ -460,35 +469,35 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
vcpu_sys_reg(vcpu, PMCR_EL0) = val;
}
-static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
+static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
{
u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+ bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
- return !((reg & ARMV8_PMU_USERENR_EN) || vcpu_mode_priv(vcpu));
+ if (!enabled)
+ kvm_inject_undefined(vcpu);
+
+ return !enabled;
}
-static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+static bool pmu_access_el0_disabled(struct kvm_vcpu *vcpu)
{
- u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
+ return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_EN);
+}
- return !((reg & (ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN))
- || vcpu_mode_priv(vcpu));
+static bool pmu_write_swinc_el0_disabled(struct kvm_vcpu *vcpu)
+{
+ return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_SW | ARMV8_PMU_USERENR_EN);
}
static bool pmu_access_cycle_counter_el0_disabled(struct kvm_vcpu *vcpu)
{
- u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-
- return !((reg & (ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN))
- || vcpu_mode_priv(vcpu));
+ return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_EN);
}
static bool pmu_access_event_counter_el0_disabled(struct kvm_vcpu *vcpu)
{
- u64 reg = vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-
- return !((reg & (ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN))
- || vcpu_mode_priv(vcpu));
+ return check_pmu_access_disabled(vcpu, ARMV8_PMU_USERENR_ER | ARMV8_PMU_USERENR_EN);
}
static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -567,8 +576,10 @@ static bool pmu_counter_idx_valid(struct kvm_vcpu *vcpu, u64 idx)
pmcr = vcpu_sys_reg(vcpu, PMCR_EL0);
val = (pmcr >> ARMV8_PMU_PMCR_N_SHIFT) & ARMV8_PMU_PMCR_N_MASK;
- if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX)
+ if (idx >= val && idx != ARMV8_PMU_CYCLE_IDX) {
+ kvm_inject_undefined(vcpu);
return false;
+ }
return true;
}
@@ -707,8 +718,10 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (!kvm_arm_pmu_v3_ready(vcpu))
return trap_raz_wi(vcpu, p, r);
- if (!vcpu_mode_priv(vcpu))
+ if (!vcpu_mode_priv(vcpu)) {
+ kvm_inject_undefined(vcpu);
return false;
+ }
if (p->is_write) {
u64 val = p->regval & mask;
@@ -759,16 +772,15 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (!kvm_arm_pmu_v3_ready(vcpu))
return trap_raz_wi(vcpu, p, r);
+ if (!p->is_write)
+ return read_from_write_only(vcpu, p);
+
if (pmu_write_swinc_el0_disabled(vcpu))
return false;
- if (p->is_write) {
- mask = kvm_pmu_valid_counter_mask(vcpu);
- kvm_pmu_software_increment(vcpu, p->regval & mask);
- return true;
- }
-
- return false;
+ mask = kvm_pmu_valid_counter_mask(vcpu);
+ kvm_pmu_software_increment(vcpu, p->regval & mask);
+ return true;
}
static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -778,8 +790,10 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return trap_raz_wi(vcpu, p, r);
if (p->is_write) {
- if (!vcpu_mode_priv(vcpu))
+ if (!vcpu_mode_priv(vcpu)) {
+ kvm_inject_undefined(vcpu);
return false;
+ }
vcpu_sys_reg(vcpu, PMUSERENR_EL0) = p->regval
& ARMV8_PMU_USERENR_MASK;
@@ -793,31 +807,23 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
/* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
#define DBG_BCR_BVR_WCR_WVR_EL1(n) \
- /* DBGBVRn_EL1 */ \
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b100), \
+ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \
trap_bvr, reset_bvr, n, 0, get_bvr, set_bvr }, \
- /* DBGBCRn_EL1 */ \
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b101), \
+ { SYS_DESC(SYS_DBGBCRn_EL1(n)), \
trap_bcr, reset_bcr, n, 0, get_bcr, set_bcr }, \
- /* DBGWVRn_EL1 */ \
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b110), \
+ { SYS_DESC(SYS_DBGWVRn_EL1(n)), \
trap_wvr, reset_wvr, n, 0, get_wvr, set_wvr }, \
- /* DBGWCRn_EL1 */ \
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm((n)), Op2(0b111), \
+ { SYS_DESC(SYS_DBGWCRn_EL1(n)), \
trap_wcr, reset_wcr, n, 0, get_wcr, set_wcr }
/* Macro to expand the PMEVCNTRn_EL0 register */
#define PMU_PMEVCNTR_EL0(n) \
- /* PMEVCNTRn_EL0 */ \
- { Op0(0b11), Op1(0b011), CRn(0b1110), \
- CRm((0b1000 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \
+ { SYS_DESC(SYS_PMEVCNTRn_EL0(n)), \
access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
/* Macro to expand the PMEVTYPERn_EL0 register */
#define PMU_PMEVTYPER_EL0(n) \
- /* PMEVTYPERn_EL0 */ \
- { Op0(0b11), Op1(0b011), CRn(0b1110), \
- CRm((0b1100 | (((n) >> 3) & 0x3))), Op2(((n) & 0x7)), \
+ { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \
access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
static bool access_cntp_tval(struct kvm_vcpu *vcpu,
@@ -887,24 +893,14 @@ static bool access_cntp_cval(struct kvm_vcpu *vcpu,
* more demanding guest...
*/
static const struct sys_reg_desc sys_reg_descs[] = {
- /* DC ISW */
- { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b0110), Op2(0b010),
- access_dcsw },
- /* DC CSW */
- { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1010), Op2(0b010),
- access_dcsw },
- /* DC CISW */
- { Op0(0b01), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b010),
- access_dcsw },
+ { SYS_DESC(SYS_DC_ISW), access_dcsw },
+ { SYS_DESC(SYS_DC_CSW), access_dcsw },
+ { SYS_DESC(SYS_DC_CISW), access_dcsw },
DBG_BCR_BVR_WCR_WVR_EL1(0),
DBG_BCR_BVR_WCR_WVR_EL1(1),
- /* MDCCINT_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
- trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
- /* MDSCR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
- trap_debug_regs, reset_val, MDSCR_EL1, 0 },
+ { SYS_DESC(SYS_MDCCINT_EL1), trap_debug_regs, reset_val, MDCCINT_EL1, 0 },
+ { SYS_DESC(SYS_MDSCR_EL1), trap_debug_regs, reset_val, MDSCR_EL1, 0 },
DBG_BCR_BVR_WCR_WVR_EL1(2),
DBG_BCR_BVR_WCR_WVR_EL1(3),
DBG_BCR_BVR_WCR_WVR_EL1(4),
@@ -920,179 +916,77 @@ static const struct sys_reg_desc sys_reg_descs[] = {
DBG_BCR_BVR_WCR_WVR_EL1(14),
DBG_BCR_BVR_WCR_WVR_EL1(15),
- /* MDRAR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
- trap_raz_wi },
- /* OSLAR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b100),
- trap_raz_wi },
- /* OSLSR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0001), Op2(0b100),
- trap_oslsr_el1 },
- /* OSDLR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0011), Op2(0b100),
- trap_raz_wi },
- /* DBGPRCR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0001), CRm(0b0100), Op2(0b100),
- trap_raz_wi },
- /* DBGCLAIMSET_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1000), Op2(0b110),
- trap_raz_wi },
- /* DBGCLAIMCLR_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1001), Op2(0b110),
- trap_raz_wi },
- /* DBGAUTHSTATUS_EL1 */
- { Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
- trap_dbgauthstatus_el1 },
-
- /* MDCCSR_EL1 */
- { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
- trap_raz_wi },
- /* DBGDTR_EL0 */
- { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0100), Op2(0b000),
- trap_raz_wi },
- /* DBGDTR[TR]X_EL0 */
- { Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0101), Op2(0b000),
- trap_raz_wi },
-
- /* DBGVCR32_EL2 */
- { Op0(0b10), Op1(0b100), CRn(0b0000), CRm(0b0111), Op2(0b000),
- NULL, reset_val, DBGVCR32_EL2, 0 },
-
- /* MPIDR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b101),
- NULL, reset_mpidr, MPIDR_EL1 },
- /* SCTLR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b000),
- access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
- /* CPACR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b010),
- NULL, reset_val, CPACR_EL1, 0 },
- /* TTBR0_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b000),
- access_vm_reg, reset_unknown, TTBR0_EL1 },
- /* TTBR1_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b001),
- access_vm_reg, reset_unknown, TTBR1_EL1 },
- /* TCR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0010), CRm(0b0000), Op2(0b010),
- access_vm_reg, reset_val, TCR_EL1, 0 },
-
- /* AFSR0_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b000),
- access_vm_reg, reset_unknown, AFSR0_EL1 },
- /* AFSR1_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0001), Op2(0b001),
- access_vm_reg, reset_unknown, AFSR1_EL1 },
- /* ESR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0101), CRm(0b0010), Op2(0b000),
- access_vm_reg, reset_unknown, ESR_EL1 },
- /* FAR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000),
- access_vm_reg, reset_unknown, FAR_EL1 },
- /* PAR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000),
- NULL, reset_unknown, PAR_EL1 },
-
- /* PMINTENSET_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001),
- access_pminten, reset_unknown, PMINTENSET_EL1 },
- /* PMINTENCLR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b010),
- access_pminten, NULL, PMINTENSET_EL1 },
-
- /* MAIR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0010), Op2(0b000),
- access_vm_reg, reset_unknown, MAIR_EL1 },
- /* AMAIR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1010), CRm(0b0011), Op2(0b000),
- access_vm_reg, reset_amair_el1, AMAIR_EL1 },
-
- /* VBAR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b0000), Op2(0b000),
- NULL, reset_val, VBAR_EL1, 0 },
-
- /* ICC_SGI1R_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1011), Op2(0b101),
- access_gic_sgi },
- /* ICC_SRE_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1100), CRm(0b1100), Op2(0b101),
- access_gic_sre },
-
- /* CONTEXTIDR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b001),
- access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
- /* TPIDR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1101), CRm(0b0000), Op2(0b100),
- NULL, reset_unknown, TPIDR_EL1 },
-
- /* CNTKCTL_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b1110), CRm(0b0001), Op2(0b000),
- NULL, reset_val, CNTKCTL_EL1, 0},
-
- /* CSSELR_EL1 */
- { Op0(0b11), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
- NULL, reset_unknown, CSSELR_EL1 },
-
- /* PMCR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b000),
- access_pmcr, reset_pmcr, },
- /* PMCNTENSET_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b001),
- access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
- /* PMCNTENCLR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b010),
- access_pmcnten, NULL, PMCNTENSET_EL0 },
- /* PMOVSCLR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b011),
- access_pmovs, NULL, PMOVSSET_EL0 },
- /* PMSWINC_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b100),
- access_pmswinc, reset_unknown, PMSWINC_EL0 },
- /* PMSELR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b101),
- access_pmselr, reset_unknown, PMSELR_EL0 },
- /* PMCEID0_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b110),
- access_pmceid },
- /* PMCEID1_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1100), Op2(0b111),
- access_pmceid },
- /* PMCCNTR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b000),
- access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
- /* PMXEVTYPER_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b001),
- access_pmu_evtyper },
- /* PMXEVCNTR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1101), Op2(0b010),
- access_pmu_evcntr },
- /* PMUSERENR_EL0
- * This register resets as unknown in 64bit mode while it resets as zero
+ { SYS_DESC(SYS_MDRAR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_OSLAR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_OSLSR_EL1), trap_oslsr_el1 },
+ { SYS_DESC(SYS_OSDLR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_DBGPRCR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_DBGCLAIMSET_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_DBGCLAIMCLR_EL1), trap_raz_wi },
+ { SYS_DESC(SYS_DBGAUTHSTATUS_EL1), trap_dbgauthstatus_el1 },
+
+ { SYS_DESC(SYS_MDCCSR_EL0), trap_raz_wi },
+ { SYS_DESC(SYS_DBGDTR_EL0), trap_raz_wi },
+ // DBGDTR[TR]X_EL0 share the same encoding
+ { SYS_DESC(SYS_DBGDTRTX_EL0), trap_raz_wi },
+
+ { SYS_DESC(SYS_DBGVCR32_EL2), NULL, reset_val, DBGVCR32_EL2, 0 },
+
+ { SYS_DESC(SYS_MPIDR_EL1), NULL, reset_mpidr, MPIDR_EL1 },
+ { SYS_DESC(SYS_SCTLR_EL1), access_vm_reg, reset_val, SCTLR_EL1, 0x00C50078 },
+ { SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
+ { SYS_DESC(SYS_TTBR0_EL1), access_vm_reg, reset_unknown, TTBR0_EL1 },
+ { SYS_DESC(SYS_TTBR1_EL1), access_vm_reg, reset_unknown, TTBR1_EL1 },
+ { SYS_DESC(SYS_TCR_EL1), access_vm_reg, reset_val, TCR_EL1, 0 },
+
+ { SYS_DESC(SYS_AFSR0_EL1), access_vm_reg, reset_unknown, AFSR0_EL1 },
+ { SYS_DESC(SYS_AFSR1_EL1), access_vm_reg, reset_unknown, AFSR1_EL1 },
+ { SYS_DESC(SYS_ESR_EL1), access_vm_reg, reset_unknown, ESR_EL1 },
+ { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
+ { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
+
+ { SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
+ { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, NULL, PMINTENSET_EL1 },
+
+ { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
+ { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
+
+ { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 },
+
+ { SYS_DESC(SYS_ICC_SGI1R_EL1), access_gic_sgi },
+ { SYS_DESC(SYS_ICC_SRE_EL1), access_gic_sre },
+
+ { SYS_DESC(SYS_CONTEXTIDR_EL1), access_vm_reg, reset_val, CONTEXTIDR_EL1, 0 },
+ { SYS_DESC(SYS_TPIDR_EL1), NULL, reset_unknown, TPIDR_EL1 },
+
+ { SYS_DESC(SYS_CNTKCTL_EL1), NULL, reset_val, CNTKCTL_EL1, 0},
+
+ { SYS_DESC(SYS_CSSELR_EL1), NULL, reset_unknown, CSSELR_EL1 },
+
+ { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, },
+ { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
+ { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, NULL, PMCNTENSET_EL0 },
+ { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, NULL, PMOVSSET_EL0 },
+ { SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 },
+ { SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 },
+ { SYS_DESC(SYS_PMCEID0_EL0), access_pmceid },
+ { SYS_DESC(SYS_PMCEID1_EL0), access_pmceid },
+ { SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
+ { SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper },
+ { SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr },
+ /*
+ * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
* in 32bit mode. Here we choose to reset it as zero for consistency.
*/
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b000),
- access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
- /* PMOVSSET_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1001), CRm(0b1110), Op2(0b011),
- access_pmovs, reset_unknown, PMOVSSET_EL0 },
-
- /* TPIDR_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b010),
- NULL, reset_unknown, TPIDR_EL0 },
- /* TPIDRRO_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1101), CRm(0b0000), Op2(0b011),
- NULL, reset_unknown, TPIDRRO_EL0 },
-
- /* CNTP_TVAL_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b000),
- access_cntp_tval },
- /* CNTP_CTL_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b001),
- access_cntp_ctl },
- /* CNTP_CVAL_EL0 */
- { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b0010), Op2(0b010),
- access_cntp_cval },
+ { SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
+ { SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
+
+ { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
+ { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
+
+ { SYS_DESC(SYS_CNTP_TVAL_EL0), access_cntp_tval },
+ { SYS_DESC(SYS_CNTP_CTL_EL0), access_cntp_ctl },
+ { SYS_DESC(SYS_CNTP_CVAL_EL0), access_cntp_cval },
/* PMEVCNTRn_EL0 */
PMU_PMEVCNTR_EL0(0),
@@ -1158,22 +1052,15 @@ static const struct sys_reg_desc sys_reg_descs[] = {
PMU_PMEVTYPER_EL0(28),
PMU_PMEVTYPER_EL0(29),
PMU_PMEVTYPER_EL0(30),
- /* PMCCFILTR_EL0
- * This register resets as unknown in 64bit mode while it resets as zero
+ /*
+ * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
* in 32bit mode. Here we choose to reset it as zero for consistency.
*/
- { Op0(0b11), Op1(0b011), CRn(0b1110), CRm(0b1111), Op2(0b111),
- access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
-
- /* DACR32_EL2 */
- { Op0(0b11), Op1(0b100), CRn(0b0011), CRm(0b0000), Op2(0b000),
- NULL, reset_unknown, DACR32_EL2 },
- /* IFSR32_EL2 */
- { Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0000), Op2(0b001),
- NULL, reset_unknown, IFSR32_EL2 },
- /* FPEXC32_EL2 */
- { Op0(0b11), Op1(0b100), CRn(0b0101), CRm(0b0011), Op2(0b000),
- NULL, reset_val, FPEXC32_EL2, 0x70 },
+ { SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+
+ { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
+ { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
+ { SYS_DESC(SYS_FPEXC32_EL2), NULL, reset_val, FPEXC32_EL2, 0x70 },
};
static bool trap_dbgidr(struct kvm_vcpu *vcpu,
@@ -1183,8 +1070,8 @@ static bool trap_dbgidr(struct kvm_vcpu *vcpu,
if (p->is_write) {
return ignore_write(vcpu, p);
} else {
- u64 dfr = read_system_reg(SYS_ID_AA64DFR0_EL1);
- u64 pfr = read_system_reg(SYS_ID_AA64PFR0_EL1);
+ u64 dfr = read_sanitised_ftr_reg(SYS_ID_AA64DFR0_EL1);
+ u64 pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
u32 el3 = !!cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR0_EL3_SHIFT);
p->regval = ((((dfr >> ID_AA64DFR0_WRPS_SHIFT) & 0xf) << 28) |
@@ -1557,6 +1444,22 @@ int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu, struct kvm_run *run)
return 1;
}
+static void perform_access(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *params,
+ const struct sys_reg_desc *r)
+{
+ /*
+ * Not having an accessor means that we have configured a trap
+ * that we don't know how to handle. This certainly qualifies
+ * as a gross bug that should be fixed right away.
+ */
+ BUG_ON(!r->access);
+
+ /* Skip instruction if instructed so */
+ if (likely(r->access(vcpu, params, r)))
+ kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+}
+
/*
* emulate_cp -- tries to match a sys_reg access in a handling table, and
* call the corresponding trap handler.
@@ -1580,20 +1483,8 @@ static int emulate_cp(struct kvm_vcpu *vcpu,
r = find_reg(params, table, num);
if (r) {
- /*
- * Not having an accessor means that we have
- * configured a trap that we don't know how to
- * handle. This certainly qualifies as a gross bug
- * that should be fixed right away.
- */
- BUG_ON(!r->access);
-
- if (likely(r->access(vcpu, params, r))) {
- /* Skip instruction, since it was emulated */
- kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
- /* Handled */
- return 0;
- }
+ perform_access(vcpu, params, r);
+ return 0;
}
/* Not handled */
@@ -1660,20 +1551,25 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
params.regval |= vcpu_get_reg(vcpu, Rt2) << 32;
}
- if (!emulate_cp(vcpu, &params, target_specific, nr_specific))
- goto out;
- if (!emulate_cp(vcpu, &params, global, nr_global))
- goto out;
-
- unhandled_cp_access(vcpu, &params);
+ /*
+ * Try to emulate the coprocessor access using the target
+ * specific table first, and using the global table afterwards.
+ * If either of the tables contains a handler, handle the
+ * potential register operation in the case of a read and return
+ * with success.
+ */
+ if (!emulate_cp(vcpu, &params, target_specific, nr_specific) ||
+ !emulate_cp(vcpu, &params, global, nr_global)) {
+ /* Split up the value between registers for the read side */
+ if (!params.is_write) {
+ vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
+ vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
+ }
-out:
- /* Split up the value between registers for the read side */
- if (!params.is_write) {
- vcpu_set_reg(vcpu, Rt, lower_32_bits(params.regval));
- vcpu_set_reg(vcpu, Rt2, upper_32_bits(params.regval));
+ return 1;
}
+ unhandled_cp_access(vcpu, &params);
return 1;
}
@@ -1763,26 +1659,13 @@ static int emulate_sys_reg(struct kvm_vcpu *vcpu,
r = find_reg(params, sys_reg_descs, ARRAY_SIZE(sys_reg_descs));
if (likely(r)) {
- /*
- * Not having an accessor means that we have
- * configured a trap that we don't know how to
- * handle. This certainly qualifies as a gross bug
- * that should be fixed right away.
- */
- BUG_ON(!r->access);
-
- if (likely(r->access(vcpu, params, r))) {
- /* Skip instruction, since it was emulated */
- kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
- return 1;
- }
- /* If access function fails, it should complain. */
+ perform_access(vcpu, params, r);
} else {
kvm_err("Unsupported guest sys_reg access at: %lx\n",
*vcpu_pc(vcpu));
print_sys_reg_instr(params);
+ kvm_inject_undefined(vcpu);
}
- kvm_inject_undefined(vcpu);
return 1;
}
@@ -1932,44 +1815,25 @@ FUNCTION_INVARIANT(aidr_el1)
/* ->val is filled in by kvm_sys_reg_table_init() */
static struct sys_reg_desc invariant_sys_regs[] = {
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b000),
- NULL, get_midr_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0000), Op2(0b110),
- NULL, get_revidr_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b000),
- NULL, get_id_pfr0_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b001),
- NULL, get_id_pfr1_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b010),
- NULL, get_id_dfr0_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b011),
- NULL, get_id_afr0_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b100),
- NULL, get_id_mmfr0_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b101),
- NULL, get_id_mmfr1_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b110),
- NULL, get_id_mmfr2_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0001), Op2(0b111),
- NULL, get_id_mmfr3_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b000),
- NULL, get_id_isar0_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b001),
- NULL, get_id_isar1_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b010),
- NULL, get_id_isar2_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b011),
- NULL, get_id_isar3_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b100),
- NULL, get_id_isar4_el1 },
- { Op0(0b11), Op1(0b000), CRn(0b0000), CRm(0b0010), Op2(0b101),
- NULL, get_id_isar5_el1 },
- { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b001),
- NULL, get_clidr_el1 },
- { Op0(0b11), Op1(0b001), CRn(0b0000), CRm(0b0000), Op2(0b111),
- NULL, get_aidr_el1 },
- { Op0(0b11), Op1(0b011), CRn(0b0000), CRm(0b0000), Op2(0b001),
- NULL, get_ctr_el0 },
+ { SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 },
+ { SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 },
+ { SYS_DESC(SYS_ID_PFR0_EL1), NULL, get_id_pfr0_el1 },
+ { SYS_DESC(SYS_ID_PFR1_EL1), NULL, get_id_pfr1_el1 },
+ { SYS_DESC(SYS_ID_DFR0_EL1), NULL, get_id_dfr0_el1 },
+ { SYS_DESC(SYS_ID_AFR0_EL1), NULL, get_id_afr0_el1 },
+ { SYS_DESC(SYS_ID_MMFR0_EL1), NULL, get_id_mmfr0_el1 },
+ { SYS_DESC(SYS_ID_MMFR1_EL1), NULL, get_id_mmfr1_el1 },
+ { SYS_DESC(SYS_ID_MMFR2_EL1), NULL, get_id_mmfr2_el1 },
+ { SYS_DESC(SYS_ID_MMFR3_EL1), NULL, get_id_mmfr3_el1 },
+ { SYS_DESC(SYS_ID_ISAR0_EL1), NULL, get_id_isar0_el1 },
+ { SYS_DESC(SYS_ID_ISAR1_EL1), NULL, get_id_isar1_el1 },
+ { SYS_DESC(SYS_ID_ISAR2_EL1), NULL, get_id_isar2_el1 },
+ { SYS_DESC(SYS_ID_ISAR3_EL1), NULL, get_id_isar3_el1 },
+ { SYS_DESC(SYS_ID_ISAR4_EL1), NULL, get_id_isar4_el1 },
+ { SYS_DESC(SYS_ID_ISAR5_EL1), NULL, get_id_isar5_el1 },
+ { SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 },
+ { SYS_DESC(SYS_AIDR_EL1), NULL, get_aidr_el1 },
+ { SYS_DESC(SYS_CTR_EL0), NULL, get_ctr_el0 },
};
static int reg_from_user(u64 *val, const void __user *uaddr, u64 id)
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 9c6ffd0f0196..060f5348ef25 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -83,24 +83,6 @@ static inline bool read_zero(struct kvm_vcpu *vcpu,
return true;
}
-static inline bool write_to_read_only(struct kvm_vcpu *vcpu,
- const struct sys_reg_params *params)
-{
- kvm_debug("sys_reg write to read-only register at: %lx\n",
- *vcpu_pc(vcpu));
- print_sys_reg_instr(params);
- return false;
-}
-
-static inline bool read_from_write_only(struct kvm_vcpu *vcpu,
- const struct sys_reg_params *params)
-{
- kvm_debug("sys_reg read to write-only register at: %lx\n",
- *vcpu_pc(vcpu));
- print_sys_reg_instr(params);
- return false;
-}
-
/* Reset functions */
static inline void reset_unknown(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
@@ -147,4 +129,9 @@ const struct sys_reg_desc *find_reg_by_id(u64 id,
#define CRm(_x) .CRm = _x
#define Op2(_x) .Op2 = _x
+#define SYS_DESC(reg) \
+ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \
+ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \
+ Op2(sys_reg_Op2(reg))
+
#endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */
diff --git a/arch/arm64/kvm/sys_regs_generic_v8.c b/arch/arm64/kvm/sys_regs_generic_v8.c
index 46af7186bca6..969ade1d333d 100644
--- a/arch/arm64/kvm/sys_regs_generic_v8.c
+++ b/arch/arm64/kvm/sys_regs_generic_v8.c
@@ -52,9 +52,7 @@ static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
* Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
*/
static const struct sys_reg_desc genericv8_sys_regs[] = {
- /* ACTLR_EL1 */
- { Op0(0b11), Op1(0b000), CRn(0b0001), CRm(0b0000), Op2(0b001),
- access_actlr, reset_actlr, ACTLR_EL1 },
+ { SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
};
static const struct sys_reg_desc genericv8_cp15_regs[] = {
diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S
index 47184c3a97da..b24a830419ad 100644
--- a/arch/arm64/lib/copy_in_user.S
+++ b/arch/arm64/lib/copy_in_user.S
@@ -64,14 +64,14 @@
.endm
end .req x5
-ENTRY(__copy_in_user)
+ENTRY(raw_copy_in_user)
uaccess_enable_not_uao x3, x4
add end, x0, x2
#include "copy_template.S"
uaccess_disable_not_uao x3
mov x0, #0
ret
-ENDPROC(__copy_in_user)
+ENDPROC(raw_copy_in_user)
.section .fixup,"ax"
.align 2
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index 68634c630cdd..ab9f5f0fb2c7 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -119,9 +119,6 @@ static void flush_context(unsigned int cpu)
/* Queue a TLB invalidate and flush the I-cache if necessary. */
cpumask_setall(&tlb_flush_pending);
-
- if (icache_is_aivivt())
- __flush_icache_all();
}
static bool check_update_reserved_asid(u64 asid, u64 newasid)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 81cdb2e844ed..4dac4afc95a5 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -308,24 +308,15 @@ static void __swiotlb_sync_sg_for_device(struct device *dev,
sg->length, dir);
}
-static int __swiotlb_mmap(struct device *dev,
- struct vm_area_struct *vma,
- void *cpu_addr, dma_addr_t dma_addr, size_t size,
- unsigned long attrs)
+static int __swiotlb_mmap_pfn(struct vm_area_struct *vma,
+ unsigned long pfn, size_t size)
{
int ret = -ENXIO;
unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
PAGE_SHIFT;
unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
- unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
- vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
- is_device_dma_coherent(dev));
-
- if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
- return ret;
-
if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
ret = remap_pfn_range(vma, vma->vm_start,
pfn + off,
@@ -336,19 +327,43 @@ static int __swiotlb_mmap(struct device *dev,
return ret;
}
-static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
- void *cpu_addr, dma_addr_t handle, size_t size,
- unsigned long attrs)
+static int __swiotlb_mmap(struct device *dev,
+ struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size,
+ unsigned long attrs)
+{
+ int ret;
+ unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+
+ vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot,
+ is_device_dma_coherent(dev));
+
+ if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ return __swiotlb_mmap_pfn(vma, pfn, size);
+}
+
+static int __swiotlb_get_sgtable_page(struct sg_table *sgt,
+ struct page *page, size_t size)
{
int ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
if (!ret)
- sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)),
- PAGE_ALIGN(size), 0);
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
return ret;
}
+static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size,
+ unsigned long attrs)
+{
+ struct page *page = phys_to_page(dma_to_phys(dev, handle));
+
+ return __swiotlb_get_sgtable_page(sgt, page, size);
+}
+
static int __swiotlb_dma_supported(struct device *hwdev, u64 mask)
{
if (swiotlb)
@@ -584,20 +599,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
*/
gfp |= __GFP_ZERO;
- if (gfpflags_allow_blocking(gfp)) {
- struct page **pages;
- pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
-
- pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
- handle, flush_page);
- if (!pages)
- return NULL;
-
- addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
- __builtin_return_address(0));
- if (!addr)
- iommu_dma_free(dev, pages, iosize, handle);
- } else {
+ if (!gfpflags_allow_blocking(gfp)) {
struct page *page;
/*
* In atomic context we can't remap anything, so we'll only
@@ -621,6 +623,45 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
__free_from_pool(addr, size);
addr = NULL;
}
+ } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ struct page *page;
+
+ page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+ get_order(size), gfp);
+ if (!page)
+ return NULL;
+
+ *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
+ if (iommu_dma_mapping_error(dev, *handle)) {
+ dma_release_from_contiguous(dev, page,
+ size >> PAGE_SHIFT);
+ return NULL;
+ }
+ if (!coherent)
+ __dma_flush_area(page_to_virt(page), iosize);
+
+ addr = dma_common_contiguous_remap(page, size, VM_USERMAP,
+ prot,
+ __builtin_return_address(0));
+ if (!addr) {
+ iommu_dma_unmap_page(dev, *handle, iosize, 0, attrs);
+ dma_release_from_contiguous(dev, page,
+ size >> PAGE_SHIFT);
+ }
+ } else {
+ pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
+ struct page **pages;
+
+ pages = iommu_dma_alloc(dev, iosize, gfp, attrs, ioprot,
+ handle, flush_page);
+ if (!pages)
+ return NULL;
+
+ addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
+ __builtin_return_address(0));
+ if (!addr)
+ iommu_dma_free(dev, pages, iosize, handle);
}
return addr;
}
@@ -632,7 +673,8 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
size = PAGE_ALIGN(size);
/*
- * @cpu_addr will be one of 3 things depending on how it was allocated:
+ * @cpu_addr will be one of 4 things depending on how it was allocated:
+ * - A remapped array of pages for contiguous allocations.
* - A remapped array of pages from iommu_dma_alloc(), for all
* non-atomic allocations.
* - A non-cacheable alias from the atomic pool, for atomic
@@ -644,6 +686,12 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
if (__in_atomic_pool(cpu_addr, size)) {
iommu_dma_unmap_page(dev, handle, iosize, 0, 0);
__free_from_pool(cpu_addr, size);
+ } else if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ struct page *page = vmalloc_to_page(cpu_addr);
+
+ iommu_dma_unmap_page(dev, handle, iosize, 0, attrs);
+ dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
+ dma_common_free_remap(cpu_addr, size, VM_USERMAP);
} else if (is_vmalloc_addr(cpu_addr)){
struct vm_struct *area = find_vm_area(cpu_addr);
@@ -670,6 +718,15 @@ static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
return ret;
+ if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ /*
+ * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+ * hence in the vmalloc space.
+ */
+ unsigned long pfn = vmalloc_to_pfn(cpu_addr);
+ return __swiotlb_mmap_pfn(vma, pfn, size);
+ }
+
area = find_vm_area(cpu_addr);
if (WARN_ON(!area || !area->pages))
return -ENXIO;
@@ -684,6 +741,15 @@ static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
struct vm_struct *area = find_vm_area(cpu_addr);
+ if (attrs & DMA_ATTR_FORCE_CONTIGUOUS) {
+ /*
+ * DMA_ATTR_FORCE_CONTIGUOUS allocations are always remapped,
+ * hence in the vmalloc space.
+ */
+ struct page *page = vmalloc_to_page(cpu_addr);
+ return __swiotlb_get_sgtable_page(sgt, page, size);
+ }
+
if (WARN_ON(!area || !area->pages))
return -ENXIO;
@@ -977,4 +1043,11 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
dev->archdata.dma_coherent = coherent;
__iommu_setup_dma_ops(dev, dma_base, size, iommu);
+
+#ifdef CONFIG_XEN
+ if (xen_initial_domain()) {
+ dev->archdata.dev_dma_ops = dev->dma_ops;
+ dev->dma_ops = xen_dma_ops;
+ }
+#endif
}
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 4bf899fb451b..37b95dff0b07 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -42,7 +42,20 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
-static const char *fault_name(unsigned int esr);
+struct fault_info {
+ int (*fn)(unsigned long addr, unsigned int esr,
+ struct pt_regs *regs);
+ int sig;
+ int code;
+ const char *name;
+};
+
+static const struct fault_info fault_info[];
+
+static inline const struct fault_info *esr_to_fault_info(unsigned int esr)
+{
+ return fault_info + (esr & 63);
+}
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, unsigned int esr)
@@ -161,12 +174,33 @@ static bool is_el1_instruction_abort(unsigned int esr)
return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR;
}
+static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs,
+ unsigned long addr)
+{
+ unsigned int ec = ESR_ELx_EC(esr);
+ unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
+
+ if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+ return false;
+
+ if (fsc_type == ESR_ELx_FSC_PERM)
+ return true;
+
+ if (addr < USER_DS && system_uses_ttbr0_pan())
+ return fsc_type == ESR_ELx_FSC_FAULT &&
+ (regs->pstate & PSR_PAN_BIT);
+
+ return false;
+}
+
/*
* The kernel tried to access some page that wasn't present.
*/
static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
unsigned int esr, struct pt_regs *regs)
{
+ const char *msg;
+
/*
* Are we prepared to handle this kernel fault?
* We are almost certainly not prepared to handle instruction faults.
@@ -178,9 +212,20 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
- pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
- (addr < PAGE_SIZE) ? "NULL pointer dereference" :
- "paging request", addr);
+
+ if (is_permission_fault(esr, regs, addr)) {
+ if (esr & ESR_ELx_WNR)
+ msg = "write to read-only memory";
+ else
+ msg = "read from unreadable memory";
+ } else if (addr < PAGE_SIZE) {
+ msg = "NULL pointer dereference";
+ } else {
+ msg = "paging request";
+ }
+
+ pr_alert("Unable to handle kernel %s at virtual address %08lx\n", msg,
+ addr);
show_pte(mm, addr);
die("Oops", regs, esr);
@@ -197,10 +242,12 @@ static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
struct pt_regs *regs)
{
struct siginfo si;
+ const struct fault_info *inf;
if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
+ inf = esr_to_fault_info(esr);
pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
- tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
+ tsk->comm, task_pid_nr(tsk), inf->name, sig,
addr, esr);
show_pte(tsk->mm, addr);
show_regs(regs);
@@ -219,14 +266,16 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
+ const struct fault_info *inf;
/*
* If we are in kernel mode at this point, we have no context to
* handle this fault with.
*/
- if (user_mode(regs))
- __do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
- else
+ if (user_mode(regs)) {
+ inf = esr_to_fault_info(esr);
+ __do_user_fault(tsk, addr, esr, inf->sig, inf->code, regs);
+ } else
__do_kernel_fault(mm, addr, esr, regs);
}
@@ -270,21 +319,6 @@ out:
return fault;
}
-static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs)
-{
- unsigned int ec = ESR_ELx_EC(esr);
- unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
-
- if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
- return false;
-
- if (system_uses_ttbr0_pan())
- return fsc_type == ESR_ELx_FSC_FAULT &&
- (regs->pstate & PSR_PAN_BIT);
- else
- return fsc_type == ESR_ELx_FSC_PERM;
-}
-
static bool is_el0_instruction_abort(unsigned int esr)
{
return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW;
@@ -322,7 +356,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
mm_flags |= FAULT_FLAG_WRITE;
}
- if (addr < USER_DS && is_permission_fault(esr, regs)) {
+ if (addr < USER_DS && is_permission_fault(esr, regs, addr)) {
/* regs->orig_addr_limit may be 0 if we entered from EL0 */
if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
@@ -488,12 +522,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
return 1;
}
-static const struct fault_info {
- int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
- int sig;
- int code;
- const char *name;
-} fault_info[] = {
+static const struct fault_info fault_info[] = {
{ do_bad, SIGBUS, 0, "ttbr address size fault" },
{ do_bad, SIGBUS, 0, "level 1 address size fault" },
{ do_bad, SIGBUS, 0, "level 2 address size fault" },
@@ -560,19 +589,13 @@ static const struct fault_info {
{ do_bad, SIGBUS, 0, "unknown 63" },
};
-static const char *fault_name(unsigned int esr)
-{
- const struct fault_info *inf = fault_info + (esr & 63);
- return inf->name;
-}
-
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
- const struct fault_info *inf = fault_info + (esr & 63);
+ const struct fault_info *inf = esr_to_fault_info(esr);
struct siginfo info;
if (!inf->fn(addr, esr, regs))
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 554a2558c12e..21a8d828cbf4 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -22,7 +22,7 @@
#include <linux/pagemap.h>
#include <asm/cacheflush.h>
-#include <asm/cachetype.h>
+#include <asm/cache.h>
#include <asm/tlbflush.h>
void sync_icache_aliases(void *kaddr, unsigned long len)
@@ -65,8 +65,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
sync_icache_aliases(page_address(page),
PAGE_SIZE << compound_order(page));
- else if (icache_is_aivivt())
- __flush_icache_all();
}
/*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index e25584d72396..7514a000e361 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -294,10 +294,6 @@ static __init int setup_hugepagesz(char *opt)
hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
} else if (ps == PUD_SIZE) {
hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
- } else if (ps == (PAGE_SIZE * CONT_PTES)) {
- hugetlb_add_hstate(CONT_PTE_SHIFT);
- } else if (ps == (PMD_SIZE * CONT_PMDS)) {
- hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT);
} else {
hugetlb_bad_size();
pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
@@ -306,13 +302,3 @@ static __init int setup_hugepagesz(char *opt)
return 1;
}
__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/mm/init.c b/arch/arm64/mm/init.c
index e19e06593e37..5960bef0170d 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
#include <linux/gfp.h>
#include <linux/memblock.h>
#include <linux/sort.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
@@ -37,6 +38,8 @@
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
#include <asm/boot.h>
#include <asm/fixmap.h>
@@ -77,6 +80,142 @@ static int __init early_initrd(char *p)
early_param("initrd", early_initrd);
#endif
+#ifdef CONFIG_KEXEC_CORE
+/*
+ * reserve_crashkernel() - reserves memory for crash kernel
+ *
+ * This function reserves memory area given in "crashkernel=" kernel command
+ * line parameter. The memory reserved is used by dump capture kernel when
+ * primary kernel is crashing.
+ */
+static void __init reserve_crashkernel(void)
+{
+ unsigned long long crash_base, crash_size;
+ int ret;
+
+ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+ &crash_size, &crash_base);
+ /* no crashkernel= or invalid value specified */
+ if (ret || !crash_size)
+ return;
+
+ crash_size = PAGE_ALIGN(crash_size);
+
+ if (crash_base == 0) {
+ /* Current arm64 boot protocol requires 2MB alignment */
+ crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+ crash_size, SZ_2M);
+ if (crash_base == 0) {
+ pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
+ crash_size);
+ return;
+ }
+ } else {
+ /* User specifies base address explicitly. */
+ if (!memblock_is_region_memory(crash_base, crash_size)) {
+ pr_warn("cannot reserve crashkernel: region is not memory\n");
+ return;
+ }
+
+ if (memblock_is_region_reserved(crash_base, crash_size)) {
+ pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
+ return;
+ }
+
+ if (!IS_ALIGNED(crash_base, SZ_2M)) {
+ pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
+ return;
+ }
+ }
+ memblock_reserve(crash_base, crash_size);
+
+ pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+ crash_base, crash_base + crash_size, crash_size >> 20);
+
+ crashk_res.start = crash_base;
+ crashk_res.end = crash_base + crash_size - 1;
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+#ifdef CONFIG_HIBERNATION
+ phys_addr_t addr;
+ struct page *page;
+
+ if (!crashk_res.end)
+ return;
+
+ /*
+ * To reduce the size of hibernation image, all the pages are
+ * marked as Reserved initially.
+ */
+ for (addr = crashk_res.start; addr < (crashk_res.end + 1);
+ addr += PAGE_SIZE) {
+ page = phys_to_page(addr);
+ SetPageReserved(page);
+ }
+#endif
+}
+#else
+static void __init reserve_crashkernel(void)
+{
+}
+
+static void __init kexec_reserve_crashkres_pages(void)
+{
+}
+#endif /* CONFIG_KEXEC_CORE */
+
+#ifdef CONFIG_CRASH_DUMP
+static int __init early_init_dt_scan_elfcorehdr(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ const __be32 *reg;
+ int len;
+
+ if (depth != 1 || strcmp(uname, "chosen") != 0)
+ return 0;
+
+ reg = of_get_flat_dt_prop(node, "linux,elfcorehdr", &len);
+ if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+ return 1;
+
+ elfcorehdr_addr = dt_mem_next_cell(dt_root_addr_cells, &reg);
+ elfcorehdr_size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+ return 1;
+}
+
+/*
+ * reserve_elfcorehdr() - reserves memory for elf core header
+ *
+ * This function reserves the memory occupied by an elf core header
+ * described in the device tree. This region contains all the
+ * information about primary kernel's core image and is used by a dump
+ * capture kernel to access the system memory on primary kernel.
+ */
+static void __init reserve_elfcorehdr(void)
+{
+ of_scan_flat_dt(early_init_dt_scan_elfcorehdr, NULL);
+
+ if (!elfcorehdr_size)
+ return;
+
+ if (memblock_is_region_reserved(elfcorehdr_addr, elfcorehdr_size)) {
+ pr_warn("elfcorehdr is overlapped\n");
+ return;
+ }
+
+ memblock_reserve(elfcorehdr_addr, elfcorehdr_size);
+
+ pr_info("Reserving %lldKB of memory at 0x%llx for elfcorehdr\n",
+ elfcorehdr_size >> 10, elfcorehdr_addr);
+}
+#else
+static void __init reserve_elfcorehdr(void)
+{
+}
+#endif /* CONFIG_CRASH_DUMP */
/*
* Return the maximum physical address for ZONE_DMA (DMA_BIT_MASK(32)). It
* currently assumes that for memory starting above 4G, 32-bit devices will
@@ -188,10 +327,45 @@ static int __init early_mem(char *p)
}
early_param("mem", early_mem);
+static int __init early_init_dt_scan_usablemem(unsigned long node,
+ const char *uname, int depth, void *data)
+{
+ struct memblock_region *usablemem = data;
+ const __be32 *reg;
+ int len;
+
+ if (depth != 1 || strcmp(uname, "chosen") != 0)
+ return 0;
+
+ reg = of_get_flat_dt_prop(node, "linux,usable-memory-range", &len);
+ if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
+ return 1;
+
+ usablemem->base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+ usablemem->size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+ return 1;
+}
+
+static void __init fdt_enforce_memory_region(void)
+{
+ struct memblock_region reg = {
+ .size = 0,
+ };
+
+ of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+
+ if (reg.size)
+ memblock_cap_memory_range(reg.base, reg.size);
+}
+
void __init arm64_memblock_init(void)
{
const s64 linear_region_size = -(s64)PAGE_OFFSET;
+ /* Handle linux,usable-memory-range property */
+ fdt_enforce_memory_region();
+
/*
* Ensure that the linear region takes up exactly half of the kernel
* virtual address space. This way, we can distinguish a linear address
@@ -297,6 +471,11 @@ void __init arm64_memblock_init(void)
arm64_dma_phys_limit = max_zone_dma_phys();
else
arm64_dma_phys_limit = PHYS_MASK + 1;
+
+ reserve_crashkernel();
+
+ reserve_elfcorehdr();
+
dma_contiguous_reserve(arm64_dma_phys_limit);
memblock_allow_resize();
@@ -416,6 +595,8 @@ void __init mem_init(void)
/* this will put all unused low memory onto the freelists */
free_all_bootmem();
+ kexec_reserve_crashkres_pages();
+
mem_init_print_info(NULL);
#define MLK(b, t) b, t, ((t) - (b)) >> 10
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index 55d1e9205543..687a358a3733 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -162,7 +162,7 @@ void __init kasan_init(void)
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
vmemmap_populate(kimg_shadow_start, kimg_shadow_end,
- pfn_to_nid(virt_to_pfn(_text)));
+ pfn_to_nid(virt_to_pfn(lm_alias(_text))));
/*
* vmemmap_populate() has populated the shadow region that covers the
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index d28dbcf596b6..0c429ec6fde8 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -22,6 +22,8 @@
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/kexec.h>
#include <linux/libfdt.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
@@ -43,6 +45,9 @@
#include <asm/mmu_context.h>
#include <asm/ptdump.h>
+#define NO_BLOCK_MAPPINGS BIT(0)
+#define NO_CONT_MAPPINGS BIT(1)
+
u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
u64 kimage_voffset __ro_after_init;
@@ -103,33 +108,27 @@ static bool pgattr_change_is_safe(u64 old, u64 new)
*/
static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE;
- return old == 0 || new == 0 || ((old ^ new) & ~mask) == 0;
+ /* creating or taking down mappings is always safe */
+ if (old == 0 || new == 0)
+ return true;
+
+ /* live contiguous mappings may not be manipulated at all */
+ if ((old | new) & PTE_CONT)
+ return false;
+
+ return ((old ^ new) & ~mask) == 0;
}
-static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
- unsigned long end, unsigned long pfn,
- pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void))
+static void init_pte(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot)
{
pte_t *pte;
- BUG_ON(pmd_sect(*pmd));
- if (pmd_none(*pmd)) {
- phys_addr_t pte_phys;
- BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc();
- pte = pte_set_fixmap(pte_phys);
- __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
- pte_clear_fixmap();
- }
- BUG_ON(pmd_bad(*pmd));
-
pte = pte_set_fixmap_offset(pmd, addr);
do {
pte_t old_pte = *pte;
- set_pte(pte, pfn_pte(pfn, prot));
- pfn++;
+ set_pte(pte, pfn_pte(__phys_to_pfn(phys), prot));
/*
* After the PTE entry has been populated once, we
@@ -137,32 +136,51 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
*/
BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte)));
+ phys += PAGE_SIZE;
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_clear_fixmap();
}
-static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
- phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
- bool page_mappings_only)
+static void alloc_init_cont_pte(pmd_t *pmd, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void),
+ int flags)
{
- pmd_t *pmd;
unsigned long next;
- /*
- * Check for initial section mappings in the pgd/pud and remove them.
- */
- BUG_ON(pud_sect(*pud));
- if (pud_none(*pud)) {
- phys_addr_t pmd_phys;
+ BUG_ON(pmd_sect(*pmd));
+ if (pmd_none(*pmd)) {
+ phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc();
- pmd = pmd_set_fixmap(pmd_phys);
- __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
- pmd_clear_fixmap();
+ pte_phys = pgtable_alloc();
+ __pmd_populate(pmd, pte_phys, PMD_TYPE_TABLE);
}
- BUG_ON(pud_bad(*pud));
+ BUG_ON(pmd_bad(*pmd));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pte_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PTE_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pte(pmd, addr, next, phys, __prot);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
+static void init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys, pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void), int flags)
+{
+ unsigned long next;
+ pmd_t *pmd;
pmd = pmd_set_fixmap_offset(pud, addr);
do {
@@ -172,7 +190,7 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
/* try section mapping first */
if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
- !page_mappings_only) {
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
pmd_set_huge(pmd, phys, prot);
/*
@@ -182,8 +200,8 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
pmd_val(*pmd)));
} else {
- alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
- prot, pgtable_alloc);
+ alloc_init_cont_pte(pmd, addr, next, phys, prot,
+ pgtable_alloc, flags);
BUG_ON(pmd_val(old_pmd) != 0 &&
pmd_val(old_pmd) != pmd_val(*pmd));
@@ -194,6 +212,41 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
pmd_clear_fixmap();
}
+static void alloc_init_cont_pmd(pud_t *pud, unsigned long addr,
+ unsigned long end, phys_addr_t phys,
+ pgprot_t prot,
+ phys_addr_t (*pgtable_alloc)(void), int flags)
+{
+ unsigned long next;
+
+ /*
+ * Check for initial section mappings in the pgd/pud.
+ */
+ BUG_ON(pud_sect(*pud));
+ if (pud_none(*pud)) {
+ phys_addr_t pmd_phys;
+ BUG_ON(!pgtable_alloc);
+ pmd_phys = pgtable_alloc();
+ __pud_populate(pud, pmd_phys, PUD_TYPE_TABLE);
+ }
+ BUG_ON(pud_bad(*pud));
+
+ do {
+ pgprot_t __prot = prot;
+
+ next = pmd_cont_addr_end(addr, end);
+
+ /* use a contiguous mapping if the range is suitably aligned */
+ if ((((addr | next | phys) & ~CONT_PMD_MASK) == 0) &&
+ (flags & NO_CONT_MAPPINGS) == 0)
+ __prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+
+ init_pmd(pud, addr, next, phys, __prot, pgtable_alloc, flags);
+
+ phys += next - addr;
+ } while (addr = next, addr != end);
+}
+
static inline bool use_1G_block(unsigned long addr, unsigned long next,
unsigned long phys)
{
@@ -209,7 +262,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void),
- bool page_mappings_only)
+ int flags)
{
pud_t *pud;
unsigned long next;
@@ -231,7 +284,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
/*
* For 4K granule only, attempt to put down a 1GB block
*/
- if (use_1G_block(addr, next, phys) && !page_mappings_only) {
+ if (use_1G_block(addr, next, phys) &&
+ (flags & NO_BLOCK_MAPPINGS) == 0) {
pud_set_huge(pud, phys, prot);
/*
@@ -241,8 +295,8 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
pud_val(*pud)));
} else {
- alloc_init_pmd(pud, addr, next, phys, prot,
- pgtable_alloc, page_mappings_only);
+ alloc_init_cont_pmd(pud, addr, next, phys, prot,
+ pgtable_alloc, flags);
BUG_ON(pud_val(old_pud) != 0 &&
pud_val(old_pud) != pud_val(*pud));
@@ -257,7 +311,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
phys_addr_t (*pgtable_alloc)(void),
- bool page_mappings_only)
+ int flags)
{
unsigned long addr, length, end, next;
pgd_t *pgd = pgd_offset_raw(pgdir, virt);
@@ -277,7 +331,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
do {
next = pgd_addr_end(addr, end);
alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
- page_mappings_only);
+ flags);
phys += next - addr;
} while (pgd++, addr = next, addr != end);
}
@@ -306,82 +360,80 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
&phys, virt);
return;
}
- __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, false);
+ __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+ NO_CONT_MAPPINGS);
}
void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot, bool page_mappings_only)
{
+ int flags = 0;
+
BUG_ON(mm == &init_mm);
+ if (page_mappings_only)
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
- pgd_pgtable_alloc, page_mappings_only);
+ pgd_pgtable_alloc, flags);
}
-static void create_mapping_late(phys_addr_t phys, unsigned long virt,
- phys_addr_t size, pgprot_t prot)
+static void update_mapping_prot(phys_addr_t phys, unsigned long virt,
+ phys_addr_t size, pgprot_t prot)
{
if (virt < VMALLOC_START) {
- pr_warn("BUG: not creating mapping for %pa at 0x%016lx - outside kernel range\n",
+ pr_warn("BUG: not updating mapping for %pa at 0x%016lx - outside kernel range\n",
&phys, virt);
return;
}
- __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
- NULL, debug_pagealloc_enabled());
+ __create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL,
+ NO_CONT_MAPPINGS);
+
+ /* flush the TLBs after updating live kernel mappings */
+ flush_tlb_kernel_range(virt, virt + size);
}
-static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
+static void __init __map_memblock(pgd_t *pgd, phys_addr_t start,
+ phys_addr_t end, pgprot_t prot, int flags)
{
- phys_addr_t kernel_start = __pa_symbol(_text);
- phys_addr_t kernel_end = __pa_symbol(__init_begin);
-
- /*
- * Take care not to create a writable alias for the
- * read-only text and rodata sections of the kernel image.
- */
-
- /* No overlap with the kernel text/rodata */
- if (end < kernel_start || start >= kernel_end) {
- __create_pgd_mapping(pgd, start, __phys_to_virt(start),
- end - start, PAGE_KERNEL,
- early_pgtable_alloc,
- debug_pagealloc_enabled());
- return;
- }
-
- /*
- * This block overlaps the kernel text/rodata mappings.
- * Map the portion(s) which don't overlap.
- */
- if (start < kernel_start)
- __create_pgd_mapping(pgd, start,
- __phys_to_virt(start),
- kernel_start - start, PAGE_KERNEL,
- early_pgtable_alloc,
- debug_pagealloc_enabled());
- if (kernel_end < end)
- __create_pgd_mapping(pgd, kernel_end,
- __phys_to_virt(kernel_end),
- end - kernel_end, PAGE_KERNEL,
- early_pgtable_alloc,
- debug_pagealloc_enabled());
+ __create_pgd_mapping(pgd, start, __phys_to_virt(start), end - start,
+ prot, early_pgtable_alloc, flags);
+}
+void __init mark_linear_text_alias_ro(void)
+{
/*
- * Map the linear alias of the [_text, __init_begin) interval as
- * read-only/non-executable. This makes the contents of the
- * region accessible to subsystems such as hibernate, but
- * protects it from inadvertent modification or execution.
+ * Remove the write permissions from the linear alias of .text/.rodata
*/
- __create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
- kernel_end - kernel_start, PAGE_KERNEL_RO,
- early_pgtable_alloc, debug_pagealloc_enabled());
+ update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text),
+ (unsigned long)__init_begin - (unsigned long)_text,
+ PAGE_KERNEL_RO);
}
static void __init map_mem(pgd_t *pgd)
{
+ phys_addr_t kernel_start = __pa_symbol(_text);
+ phys_addr_t kernel_end = __pa_symbol(__init_begin);
struct memblock_region *reg;
+ int flags = 0;
+
+ if (debug_pagealloc_enabled())
+ flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+
+ /*
+ * Take care not to create a writable alias for the
+ * read-only text and rodata sections of the kernel image.
+ * So temporarily mark them as NOMAP to skip mappings in
+ * the following for-loop
+ */
+ memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
+#ifdef CONFIG_KEXEC_CORE
+ if (crashk_res.end)
+ memblock_mark_nomap(crashk_res.start,
+ resource_size(&crashk_res));
+#endif
/* map all the memory banks */
for_each_memblock(memory, reg) {
@@ -393,33 +445,57 @@ static void __init map_mem(pgd_t *pgd)
if (memblock_is_nomap(reg))
continue;
- __map_memblock(pgd, start, end);
+ __map_memblock(pgd, start, end, PAGE_KERNEL, flags);
+ }
+
+ /*
+ * Map the linear alias of the [_text, __init_begin) interval
+ * as non-executable now, and remove the write permission in
+ * mark_linear_text_alias_ro() below (which will be called after
+ * alternative patching has completed). This makes the contents
+ * of the region accessible to subsystems such as hibernate,
+ * but protects it from inadvertent modification or execution.
+ * Note that contiguous mappings cannot be remapped in this way,
+ * so we should avoid them here.
+ */
+ __map_memblock(pgd, kernel_start, kernel_end,
+ PAGE_KERNEL, NO_CONT_MAPPINGS);
+ memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+#ifdef CONFIG_KEXEC_CORE
+ /*
+ * Use page-level mappings here so that we can shrink the region
+ * in page granularity and put back unused memory to buddy system
+ * through /sys/kernel/kexec_crash_size interface.
+ */
+ if (crashk_res.end) {
+ __map_memblock(pgd, crashk_res.start, crashk_res.end + 1,
+ PAGE_KERNEL,
+ NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+ memblock_clear_nomap(crashk_res.start,
+ resource_size(&crashk_res));
}
+#endif
}
void mark_rodata_ro(void)
{
unsigned long section_size;
- section_size = (unsigned long)_etext - (unsigned long)_text;
- create_mapping_late(__pa_symbol(_text), (unsigned long)_text,
- section_size, PAGE_KERNEL_ROX);
/*
* mark .rodata as read only. Use __init_begin rather than __end_rodata
* to cover NOTES and EXCEPTION_TABLE.
*/
section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
- create_mapping_late(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
+ update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata,
section_size, PAGE_KERNEL_RO);
- /* flush the TLBs after updating live kernel mappings */
- flush_tlb_all();
-
debug_checkwx();
}
static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
- pgprot_t prot, struct vm_struct *vma)
+ pgprot_t prot, struct vm_struct *vma,
+ int flags)
{
phys_addr_t pa_start = __pa_symbol(va_start);
unsigned long size = va_end - va_start;
@@ -428,7 +504,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
BUG_ON(!PAGE_ALIGNED(size));
__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
- early_pgtable_alloc, debug_pagealloc_enabled());
+ early_pgtable_alloc, flags);
vma->addr = va_start;
vma->phys_addr = pa_start;
@@ -439,18 +515,39 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
vm_area_add_early(vma);
}
+static int __init parse_rodata(char *arg)
+{
+ return strtobool(arg, &rodata_enabled);
+}
+early_param("rodata", parse_rodata);
+
/*
* Create fine-grained mappings for the kernel.
*/
static void __init map_kernel(pgd_t *pgd)
{
- static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_init, vmlinux_data;
+ static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext,
+ vmlinux_initdata, vmlinux_data;
- map_kernel_segment(pgd, _text, _etext, PAGE_KERNEL_EXEC, &vmlinux_text);
- map_kernel_segment(pgd, __start_rodata, __init_begin, PAGE_KERNEL, &vmlinux_rodata);
- map_kernel_segment(pgd, __init_begin, __init_end, PAGE_KERNEL_EXEC,
- &vmlinux_init);
- map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data);
+ /*
+ * External debuggers may need to write directly to the text
+ * mapping to install SW breakpoints. Allow this (only) when
+ * explicitly requested with rodata=off.
+ */
+ pgprot_t text_prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC;
+
+ /*
+ * Only rodata will be remapped with different permissions later on,
+ * all other segments are allowed to use contiguous mappings.
+ */
+ map_kernel_segment(pgd, _text, _etext, text_prot, &vmlinux_text, 0);
+ map_kernel_segment(pgd, __start_rodata, __inittext_begin, PAGE_KERNEL,
+ &vmlinux_rodata, NO_CONT_MAPPINGS);
+ map_kernel_segment(pgd, __inittext_begin, __inittext_end, text_prot,
+ &vmlinux_inittext, 0);
+ map_kernel_segment(pgd, __initdata_begin, __initdata_end, PAGE_KERNEL,
+ &vmlinux_initdata, 0);
+ map_kernel_segment(pgd, _data, _end, PAGE_KERNEL, &vmlinux_data, 0);
if (!pgd_val(*pgd_offset_raw(pgd, FIXADDR_START))) {
/*
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 8def55e7249b..a682a0a2a0fa 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -17,6 +17,7 @@
#include <linux/vmalloc.h>
#include <asm/pgtable.h>
+#include <asm/set_memory.h>
#include <asm/tlbflush.h>
struct page_change_data {
@@ -125,20 +126,23 @@ int set_memory_x(unsigned long addr, int numpages)
}
EXPORT_SYMBOL_GPL(set_memory_x);
-#ifdef CONFIG_DEBUG_PAGEALLOC
-void __kernel_map_pages(struct page *page, int numpages, int enable)
+int set_memory_valid(unsigned long addr, int numpages, int enable)
{
- unsigned long addr = (unsigned long) page_address(page);
-
if (enable)
- __change_memory_common(addr, PAGE_SIZE * numpages,
+ return __change_memory_common(addr, PAGE_SIZE * numpages,
__pgprot(PTE_VALID),
__pgprot(0));
else
- __change_memory_common(addr, PAGE_SIZE * numpages,
+ return __change_memory_common(addr, PAGE_SIZE * numpages,
__pgprot(0),
__pgprot(PTE_VALID));
}
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+void __kernel_map_pages(struct page *page, int numpages, int enable)
+{
+ set_memory_valid((unsigned long)page_address(page), numpages, enable);
+}
#ifdef CONFIG_HIBERNATION
/*
* When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index 7c16e547ccb2..b02a9268dfbf 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -83,6 +83,25 @@
/* Rt = Rn[0]; Rt2 = Rn[8]; Rn += 16; */
#define A64_POP(Rt, Rt2, Rn) A64_LS_PAIR(Rt, Rt2, Rn, 16, LOAD, POST_INDEX)
+/* Load/store exclusive */
+#define A64_SIZE(sf) \
+ ((sf) ? AARCH64_INSN_SIZE_64 : AARCH64_INSN_SIZE_32)
+#define A64_LSX(sf, Rt, Rn, Rs, type) \
+ aarch64_insn_gen_load_store_ex(Rt, Rn, Rs, A64_SIZE(sf), \
+ AARCH64_INSN_LDST_##type)
+/* Rt = [Rn]; (atomic) */
+#define A64_LDXR(sf, Rt, Rn) \
+ A64_LSX(sf, Rt, Rn, A64_ZR, LOAD_EX)
+/* [Rn] = Rt; (atomic) Rs = [state] */
+#define A64_STXR(sf, Rt, Rn, Rs) \
+ A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
+
+/* Prefetch */
+#define A64_PRFM(Rn, type, target, policy) \
+ aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
+ AARCH64_INSN_PRFM_TARGET_##target, \
+ AARCH64_INSN_PRFM_POLICY_##policy)
+
/* Add/subtract (immediate) */
#define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index a785554916c0..c6e53580aefe 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -27,6 +27,7 @@
#include <asm/byteorder.h>
#include <asm/cacheflush.h>
#include <asm/debug-monitors.h>
+#include <asm/set_memory.h>
#include "bpf_jit.h"
@@ -321,6 +322,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
const s32 imm = insn->imm;
const int i = insn - ctx->prog->insnsi;
const bool is64 = BPF_CLASS(code) == BPF_ALU64;
+ const bool isdw = BPF_SIZE(code) == BPF_DW;
u8 jmp_cond;
s32 jmp_offset;
@@ -604,15 +606,6 @@ emit_cond_jmp:
const struct bpf_insn insn1 = insn[1];
u64 imm64;
- if (insn1.code != 0 || insn1.src_reg != 0 ||
- insn1.dst_reg != 0 || insn1.off != 0) {
- /* Note: verifier in BPF core must catch invalid
- * instructions.
- */
- pr_err_once("Invalid BPF_LD_IMM64 instruction\n");
- return -EINVAL;
- }
-
imm64 = (u64)insn1.imm << 32 | (u32)imm;
emit_a64_mov_i64(dst, imm64, ctx);
@@ -690,7 +683,16 @@ emit_cond_jmp:
case BPF_STX | BPF_XADD | BPF_W:
/* STX XADD: lock *(u64 *)(dst + off) += src */
case BPF_STX | BPF_XADD | BPF_DW:
- goto notyet;
+ emit_a64_mov_i(1, tmp, off, ctx);
+ emit(A64_ADD(1, tmp, tmp, dst), ctx);
+ emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
+ emit(A64_LDXR(isdw, tmp2, tmp), ctx);
+ emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
+ emit(A64_STXR(isdw, tmp2, tmp, tmp2), ctx);
+ jmp_offset = -3;
+ check_imm19(jmp_offset);
+ emit(A64_CBNZ(0, tmp2, jmp_offset), ctx);
+ break;
/* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */
case BPF_LD | BPF_ABS | BPF_W:
@@ -757,10 +759,6 @@ emit_cond_jmp:
}
break;
}
-notyet:
- pr_info_once("*** NOT YET: opcode %02x ***\n", code);
- return -EFAULT;
-
default:
pr_err_once("unknown opcode %02x\n", code);
return -EINVAL;
@@ -779,14 +777,14 @@ static int build_body(struct jit_ctx *ctx)
int ret;
ret = build_insn(insn, ctx);
-
- if (ctx->image == NULL)
- ctx->offset[i] = ctx->idx;
-
if (ret > 0) {
i++;
+ if (ctx->image == NULL)
+ ctx->offset[i] = ctx->idx;
continue;
}
+ if (ctx->image == NULL)
+ ctx->offset[i] = ctx->idx;
if (ret)
return ret;
}