diff options
Diffstat (limited to 'arch')
175 files changed, 1972 insertions, 1522 deletions
diff --git a/arch/alpha/include/uapi/asm/signal.h b/arch/alpha/include/uapi/asm/signal.h index 74c750bf1c1a..a69dd8d080a8 100644 --- a/arch/alpha/include/uapi/asm/signal.h +++ b/arch/alpha/include/uapi/asm/signal.h @@ -60,20 +60,6 @@ typedef unsigned long sigset_t; #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ - #define SA_ONSTACK 0x00000001 #define SA_RESTART 0x00000002 #define SA_NOCLDSTOP 0x00000004 diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 17fd1ed700cc..9152782444b5 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -67,7 +67,22 @@ sr r5, [ARC_REG_LPB_CTRL] 1: #endif /* CONFIG_ARC_LPB_DISABLE */ -#endif + + /* On HSDK, CCMs need to remapped super early */ +#ifdef CONFIG_ARC_SOC_HSDK + mov r6, 0x60000000 + lr r5, [ARC_REG_ICCM_BUILD] + breq r5, 0, 1f + sr r6, [ARC_REG_AUX_ICCM] +1: + lr r5, [ARC_REG_DCCM_BUILD] + breq r5, 0, 2f + sr r6, [ARC_REG_AUX_DCCM] +2: +#endif /* CONFIG_ARC_SOC_HSDK */ + +#endif /* CONFIG_ISA_ARCV2 */ + ; Config DSP_CTRL properly, so kernel may use integer multiply, ; multiply-accumulate, and divide operations DSP_EARLY_INIT diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index feba91c9d969..b23986f98450 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -112,7 +112,7 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, int (*consumer_fn) (unsigned int, void *), void *arg) { #ifdef CONFIG_ARC_DW2_UNWIND - int ret = 0; + int ret = 0, cnt = 0; unsigned int address; struct unwind_frame_info frame_info; @@ -132,6 +132,11 @@ arc_unwind_core(struct task_struct *tsk, struct pt_regs *regs, break; frame_info.regs.r63 = frame_info.regs.r31; + + if (cnt++ > 128) { + printk("unwinder looping too long, aborting !\n"); + return 0; + } } return address; /* return the last address it saw */ diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 0b63fc095b99..b3ea1fa11f87 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -17,22 +17,6 @@ int arc_hsdk_axi_dmac_coherent __section(".data") = 0; #define ARC_CCM_UNUSED_ADDR 0x60000000 -static void __init hsdk_init_per_cpu(unsigned int cpu) -{ - /* - * By default ICCM is mapped to 0x7z while this area is used for - * kernel virtual mappings, so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].iccm.sz) - write_aux_reg(ARC_REG_AUX_ICCM, ARC_CCM_UNUSED_ADDR); - - /* - * By default DCCM is mapped to 0x8z while this area is used by kernel, - * so move it to currently unused area. - */ - if (cpuinfo_arc700[cpu].dccm.sz) - write_aux_reg(ARC_REG_AUX_DCCM, ARC_CCM_UNUSED_ADDR); -} #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) @@ -339,5 +323,4 @@ static const char *hsdk_compat[] __initconst = { MACHINE_START(SIMULATION, "hsdk") .dt_compat = hsdk_compat, .init_early = hsdk_init_early, - .init_per_cpu = hsdk_init_per_cpu, MACHINE_END diff --git a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts index f1a41152e9dd..adde62d6fce7 100644 --- a/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts +++ b/arch/arm/boot/dts/mmp2-olpc-xo-1-75.dts @@ -227,12 +227,12 @@ /delete-property/ #size-cells; spi-slave; status = "okay"; - ready-gpio = <&gpio 125 GPIO_ACTIVE_HIGH>; + ready-gpios = <&gpio 125 GPIO_ACTIVE_HIGH>; slave { compatible = "olpc,xo1.75-ec"; spi-cpha; - cmd-gpio = <&gpio 155 GPIO_ACTIVE_HIGH>; + cmd-gpios = <&gpio 155 GPIO_ACTIVE_HIGH>; }; }; diff --git a/arch/arm/boot/dts/mmp3.dtsi b/arch/arm/boot/dts/mmp3.dtsi index cc4efd0efabd..4ae630d37d09 100644 --- a/arch/arm/boot/dts/mmp3.dtsi +++ b/arch/arm/boot/dts/mmp3.dtsi @@ -296,6 +296,7 @@ interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_CCIC0>; clock-names = "axi"; + power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>; #clock-cells = <0>; clock-output-names = "mclk"; status = "disabled"; @@ -307,6 +308,7 @@ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; clocks = <&soc_clocks MMP2_CLK_CCIC1>; clock-names = "axi"; + power-domains = <&soc_clocks MMP3_POWER_DOMAIN_CAMERA>; #clock-cells = <0>; clock-output-names = "mclk"; status = "disabled"; diff --git a/arch/arm/boot/dts/stm32mp157c-ed1.dts b/arch/arm/boot/dts/stm32mp157c-ed1.dts index ca109dc18238..2e77ccec3fc1 100644 --- a/arch/arm/boot/dts/stm32mp157c-ed1.dts +++ b/arch/arm/boot/dts/stm32mp157c-ed1.dts @@ -89,6 +89,14 @@ states = <1800000 0x1>, <2900000 0x0>; }; + + vin: vin { + compatible = "regulator-fixed"; + regulator-name = "vin"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; }; &adc { @@ -150,11 +158,18 @@ regulators { compatible = "st,stpmic1-regulators"; + buck1-supply = <&vin>; + buck2-supply = <&vin>; + buck3-supply = <&vin>; + buck4-supply = <&vin>; ldo1-supply = <&v3v3>; ldo2-supply = <&v3v3>; ldo3-supply = <&vdd_ddr>; + ldo4-supply = <&vin>; ldo5-supply = <&v3v3>; ldo6-supply = <&v3v3>; + vref_ddr-supply = <&vin>; + boost-supply = <&vin>; pwr_sw1-supply = <&bst_out>; pwr_sw2-supply = <&bst_out>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi index a5307745719a..93398cfae97e 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dkx.dtsi @@ -80,6 +80,14 @@ dais = <&sai2a_port &sai2b_port &i2s2_port>; status = "okay"; }; + + vin: vin { + compatible = "regulator-fixed"; + regulator-name = "vin"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; }; &adc { @@ -240,9 +248,18 @@ regulators { compatible = "st,stpmic1-regulators"; + buck1-supply = <&vin>; + buck2-supply = <&vin>; + buck3-supply = <&vin>; + buck4-supply = <&vin>; ldo1-supply = <&v3v3>; + ldo2-supply = <&vin>; ldo3-supply = <&vdd_ddr>; + ldo4-supply = <&vin>; + ldo5-supply = <&vin>; ldo6-supply = <&v3v3>; + vref_ddr-supply = <&vin>; + boost-supply = <&vin>; pwr_sw1-supply = <&bst_out>; pwr_sw2-supply = <&bst_out>; diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi index 0f95a6ef8543..1c5a666c54b5 100644 --- a/arch/arm/boot/dts/sun4i-a10.dtsi +++ b/arch/arm/boot/dts/sun4i-a10.dtsi @@ -143,7 +143,7 @@ trips { cpu_alert0: cpu-alert0 { /* milliCelsius */ - temperature = <850000>; + temperature = <85000>; hysteresis = <2000>; type = "passive"; }; diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index aeb1209e0804..bb70acc6b526 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -93,6 +93,7 @@ CONFIG_SPI=y CONFIG_SPI_IMX=y CONFIG_SPI_SPIDEV=y CONFIG_GPIO_SYSFS=y +CONFIG_GPIO_MXC=y CONFIG_W1=y CONFIG_W1_MASTER_MXC=y CONFIG_W1_SLAVE_THERM=y diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0fa79bd00219..221f5c340c86 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -217,6 +217,7 @@ CONFIG_GPIO_PCA953X=y CONFIG_GPIO_PCF857X=y CONFIG_GPIO_STMPE=y CONFIG_GPIO_74X164=y +CONFIG_GPIO_MXC=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_SYSCON=y CONFIG_POWER_RESET_SYSCON_POWEROFF=y diff --git a/arch/arm/configs/multi_v5_defconfig b/arch/arm/configs/multi_v5_defconfig index 70b709a669d2..e00be9faa23b 100644 --- a/arch/arm/configs/multi_v5_defconfig +++ b/arch/arm/configs/multi_v5_defconfig @@ -166,6 +166,7 @@ CONFIG_SPI_IMX=y CONFIG_SPI_ORION=y CONFIG_GPIO_ASPEED=m CONFIG_GPIO_ASPEED_SGPIO=y +CONFIG_GPIO_MXC=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_GPIO=y CONFIG_POWER_RESET_QNAP=y diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index e731cdf7c88c..a611b0c1e540 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -465,6 +465,7 @@ CONFIG_GPIO_PALMAS=y CONFIG_GPIO_TPS6586X=y CONFIG_GPIO_TPS65910=y CONFIG_GPIO_TWL4030=y +CONFIG_GPIO_MXC=y CONFIG_POWER_AVS=y CONFIG_ROCKCHIP_IODOMAIN=y CONFIG_POWER_RESET_AS3722=y diff --git a/arch/arm/include/asm/signal.h b/arch/arm/include/asm/signal.h index 65530a042009..430be7774402 100644 --- a/arch/arm/include/asm/signal.h +++ b/arch/arm/include/asm/signal.h @@ -17,6 +17,8 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +#define __ARCH_UAPI_SA_FLAGS (SA_THIRTYTWO | SA_RESTORER) + #define __ARCH_HAS_SA_RESTORER #include <asm/sigcontext.h> diff --git a/arch/arm/include/uapi/asm/signal.h b/arch/arm/include/uapi/asm/signal.h index 9b4185ba4f8a..c9a3ea1d8d41 100644 --- a/arch/arm/include/uapi/asm/signal.h +++ b/arch/arm/include/uapi/asm/signal.h @@ -60,33 +60,12 @@ typedef unsigned long sigset_t; #define SIGSWI 32 /* - * SA_FLAGS values: - * - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_SIGINFO deliver the signal with SIGINFO structs - * SA_THIRTYTWO delivers the signal in 32-bit mode, even if the task - * is running in 26-bit. - * SA_ONSTACK allows alternate signal stacks (see sigaltstack(2)). - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NODEFER prevents the current signal from being masked in the handler. - * SA_RESETHAND clears the handler when the signal is delivered. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. + * SA_THIRTYTWO historically meant deliver the signal in 32-bit mode, even if + * the task is running in 26-bit. But since the kernel no longer supports + * 26-bit mode, the flag has no effect. */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 -#define SA_SIGINFO 0x00000004 #define SA_THIRTYTWO 0x02000000 #define SA_RESTORER 0x04000000 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S index 5f4922e858d0..f7f4620d59c3 100644 --- a/arch/arm/kernel/vmlinux.lds.S +++ b/arch/arm/kernel/vmlinux.lds.S @@ -41,6 +41,10 @@ SECTIONS #ifndef CONFIG_SMP_ON_UP *(.alt.smp.init) #endif +#ifndef CONFIG_ARM_UNWIND + *(.ARM.exidx) *(.ARM.exidx.*) + *(.ARM.extab) *(.ARM.extab.*) +#endif } . = PAGE_OFFSET + TEXT_OFFSET; diff --git a/arch/arm/mach-mvebu/coherency_ll.S b/arch/arm/mach-mvebu/coherency_ll.S index 2d962fe48821..a3a64bf97250 100644 --- a/arch/arm/mach-mvebu/coherency_ll.S +++ b/arch/arm/mach-mvebu/coherency_ll.S @@ -35,13 +35,8 @@ ENTRY(ll_get_coherency_base) /* * MMU is disabled, use the physical address of the coherency - * base address. However, if the coherency fabric isn't mapped - * (i.e its virtual address is zero), it means coherency is - * not enabled, so we return 0. + * base address, (or 0x0 if the coherency fabric is not mapped) */ - ldr r1, =coherency_base - cmp r1, #0 - beq 2f adr r1, 3f ldr r3, [r1] ldr r1, [r1, r3] diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d57112a276f5..c23dbf8bebee 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -354,8 +354,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 1515f6f153a0..984ca3a6d2a0 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -170,6 +170,8 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS + select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API @@ -195,7 +197,6 @@ config ARM64 select PCI_SYSCALL if PCI select POWER_RESET select POWER_SUPPLY - select SET_FS select SPARSE_IRQ select SWIOTLB select SYSCTL_EXCEPTION_TRACE @@ -331,16 +332,16 @@ config BROKEN_GAS_INST config KASAN_SHADOW_OFFSET hex depends on KASAN - default 0xdfffa00000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS - default 0xdfffd00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS - default 0xdffffe8000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS - default 0xdfffffd000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS - default 0xdffffffa00000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS - default 0xefff900000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS - default 0xefffc80000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS - default 0xeffffe4000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS - default 0xefffffc800000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS - default 0xeffffff900000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS + default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS + default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS + default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS + default 0xdfffffc000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS + default 0xdffffff800000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS + default 0xefff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS + default 0xefffc00000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS + default 0xeffffe0000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS + default 0xefffffc000000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS + default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS default 0xffffffffffffffff source "arch/arm64/Kconfig.platforms" @@ -1388,6 +1389,9 @@ config ARM64_PAN The feature is detected at runtime, and will remain as a 'nop' instruction if the cpu does not implement the feature. +config AS_HAS_LDAPR + def_bool $(as-instr,.arch_extension rcpc) + config ARM64_LSE_ATOMICS bool default ARM64_USE_LSE_ATOMICS @@ -1425,27 +1429,6 @@ endmenu menu "ARMv8.2 architectural features" -config ARM64_UAO - bool "Enable support for User Access Override (UAO)" - default y - help - User Access Override (UAO; part of the ARMv8.2 Extensions) - causes the 'unprivileged' variant of the load/store instructions to - be overridden to be privileged. - - This option changes get_user() and friends to use the 'unprivileged' - variant of the load/store instructions. This ensures that user-space - really did have access to the supplied memory. When addr_limit is - set to kernel memory the UAO bit will be set, allowing privileged - access to kernel memory. - - Choosing this option will cause copy_to_user() et al to use user-space - memory permissions. - - The feature is detected at runtime, the kernel will use the - regular load/store instructions if the cpu does not implement the - feature. - config ARM64_PMEM bool "Enable support for persistent memory" select ARCH_HAS_PMEM_API @@ -1846,15 +1829,36 @@ config CMDLINE entering them here. As a minimum, you should specify the the root device (e.g. root=/dev/nfs). +choice + prompt "Kernel command line type" if CMDLINE != "" + default CMDLINE_FROM_BOOTLOADER + help + Choose how the kernel will handle the provided default kernel + command line string. + +config CMDLINE_FROM_BOOTLOADER + bool "Use bootloader kernel arguments if available" + help + Uses the command-line options passed by the boot loader. If + the boot loader doesn't provide any, the default kernel command + string provided in CMDLINE will be used. + +config CMDLINE_EXTEND + bool "Extend bootloader kernel arguments" + help + The command-line arguments provided by the boot loader will be + appended to the default kernel command string. + config CMDLINE_FORCE bool "Always use the default kernel command string" - depends on CMDLINE != "" help Always use the default kernel command string, even if the boot loader passes other arguments to the kernel. This is useful if you cannot or don't want to change the command-line options your boot loader passes to the kernel. +endchoice + config EFI_STUB bool diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 6f2494dd6d60..5c4ac1c9f4e0 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -54,6 +54,7 @@ config ARCH_BCM_IPROC config ARCH_BERLIN bool "Marvell Berlin SoC Family" select DW_APB_ICTL + select DW_APB_TIMER_OF select GPIOLIB select PINCTRL help diff --git a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts index cb1360ae1211..7740f97c240f 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts +++ b/arch/arm64/boot/dts/amlogic/meson-axg-s400.dts @@ -584,3 +584,9 @@ pinctrl-0 = <&uart_ao_a_pins>; pinctrl-names = "default"; }; + +&usb { + status = "okay"; + dr_mode = "otg"; + vbus-supply = <&usb_pwr>; +}; diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index b9efc8469265..724ee179b316 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -171,6 +171,46 @@ #size-cells = <2>; ranges; + usb: usb@ffe09080 { + compatible = "amlogic,meson-axg-usb-ctrl"; + reg = <0x0 0xffe09080 0x0 0x20>; + interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clocks = <&clkc CLKID_USB>, <&clkc CLKID_USB1_DDR_BRIDGE>; + clock-names = "usb_ctrl", "ddr"; + resets = <&reset RESET_USB_OTG>; + + dr_mode = "otg"; + + phys = <&usb2_phy1>; + phy-names = "usb2-phy1"; + + dwc2: usb@ff400000 { + compatible = "amlogic,meson-g12a-usb", "snps,dwc2"; + reg = <0x0 0xff400000 0x0 0x40000>; + interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clkc CLKID_USB1>; + clock-names = "otg"; + phys = <&usb2_phy1>; + dr_mode = "peripheral"; + g-rx-fifo-size = <192>; + g-np-tx-fifo-size = <128>; + g-tx-fifo-size = <128 128 16 16 16>; + }; + + dwc3: usb@ff500000 { + compatible = "snps,dwc3"; + reg = <0x0 0xff500000 0x0 0x100000>; + interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; + dr_mode = "host"; + maximum-speed = "high-speed"; + snps,dis_u2_susphy_quirk; + }; + }; + ethmac: ethernet@ff3f0000 { compatible = "amlogic,meson-axg-dwmac", "snps,dwmac-3.70a", @@ -187,6 +227,8 @@ "timing-adjustment"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; + resets = <&reset RESET_ETHERNET>; + reset-names = "stmmaceth"; status = "disabled"; }; @@ -1734,6 +1776,16 @@ clock-names = "core", "clkin0", "clkin1"; resets = <&reset RESET_SD_EMMC_C>; }; + + usb2_phy1: phy@9020 { + compatible = "amlogic,meson-gxl-usb2-phy"; + #phy-cells = <0>; + reg = <0x0 0x9020 0x0 0x20>; + clocks = <&clkc CLKID_USB>; + clock-names = "phy"; + resets = <&reset RESET_USB_OTG>; + reset-names = "phy"; + }; }; sram: sram@fffc0000 { diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 1e83ec5b8c91..8514fe6a275a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -209,7 +209,7 @@ }; ethmac: ethernet@ff3f0000 { - compatible = "amlogic,meson-axg-dwmac", + compatible = "amlogic,meson-g12a-dwmac", "snps,dwmac-3.70a", "snps,dwmac"; reg = <0x0 0xff3f0000 0x0 0x10000>, @@ -224,6 +224,8 @@ "timing-adjustment"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; + resets = <&reset RESET_ETHERNET>; + reset-names = "stmmaceth"; status = "disabled"; mdio0: mdio { @@ -282,6 +284,8 @@ hwrng: rng@218 { compatible = "amlogic,meson-rng"; reg = <0x0 0x218 0x0 0x4>; + clocks = <&clkc CLKID_RNG0>; + clock-names = "core"; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts index 5de2815ba99d..ce1198ad34e4 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-odroid-n2-plus.dts @@ -19,7 +19,7 @@ regulator-min-microvolt = <680000>; regulator-max-microvolt = <1040000>; - pwms = <&pwm_AO_cd 1 1500 0>; + pwms = <&pwm_ab 0 1500 0>; }; &vddcpu_b { diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 0edd137151f8..726b91d3a905 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -13,6 +13,7 @@ #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/power/meson-gxbb-power.h> +#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h> #include <dt-bindings/thermal/thermal.h> / { @@ -575,6 +576,8 @@ interrupt-names = "macirq"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; + resets = <&reset RESET_ETHERNET>; + reset-names = "stmmaceth"; power-domains = <&pwrc PWRC_GXBB_ETHERNET_MEM_ID>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts index 03733fd92732..215d2f702623 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7-emmc.dts @@ -20,17 +20,23 @@ compatible = "globalscale,espressobin-v7-emmc", "globalscale,espressobin-v7", "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710"; + + aliases { + /* ethernet1 is wan port */ + ethernet1 = &switch0port3; + ethernet3 = &switch0port1; + }; }; &switch0 { ports { - port@1 { + switch0port1: port@1 { reg = <1>; label = "lan1"; phy-handle = <&switch0phy0>; }; - port@3 { + switch0port3: port@3 { reg = <3>; label = "wan"; phy-handle = <&switch0phy2>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts index 8570c5f47d7d..b6f4af8ebafb 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin-v7.dts @@ -19,17 +19,23 @@ model = "Globalscale Marvell ESPRESSOBin Board V7"; compatible = "globalscale,espressobin-v7", "globalscale,espressobin", "marvell,armada3720", "marvell,armada3710"; + + aliases { + /* ethernet1 is wan port */ + ethernet1 = &switch0port3; + ethernet3 = &switch0port1; + }; }; &switch0 { ports { - port@1 { + switch0port1: port@1 { reg = <1>; label = "lan1"; phy-handle = <&switch0phy0>; }; - port@3 { + switch0port3: port@3 { reg = <3>; label = "wan"; phy-handle = <&switch0phy2>; diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi index b97218c72727..0775c16e0ec8 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi @@ -13,6 +13,10 @@ / { aliases { ethernet0 = ð0; + /* for dsa slave device */ + ethernet1 = &switch0port1; + ethernet2 = &switch0port2; + ethernet3 = &switch0port3; serial0 = &uart0; serial1 = &uart1; }; @@ -120,7 +124,7 @@ #address-cells = <1>; #size-cells = <0>; - port@0 { + switch0port0: port@0 { reg = <0>; label = "cpu"; ethernet = <ð0>; @@ -131,19 +135,19 @@ }; }; - port@1 { + switch0port1: port@1 { reg = <1>; label = "wan"; phy-handle = <&switch0phy0>; }; - port@2 { + switch0port2: port@2 { reg = <2>; label = "lan0"; phy-handle = <&switch0phy1>; }; - port@3 { + switch0port3: port@3 { reg = <3>; label = "lan1"; phy-handle = <&switch0phy2>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 17a2df6a263e..5cfe3cf6f2ac 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -500,6 +500,7 @@ CONFIG_GPIO_ALTERA=m CONFIG_GPIO_DWAPB=y CONFIG_GPIO_MB86S7X=y CONFIG_GPIO_MPC8XXX=y +CONFIG_GPIO_MXC=y CONFIG_GPIO_PL061=y CONFIG_GPIO_RCAR=y CONFIG_GPIO_UNIPHIER=y diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h new file mode 100644 index 000000000000..5df500dcc627 --- /dev/null +++ b/arch/arm64/include/asm/alternative-macros.h @@ -0,0 +1,217 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ALTERNATIVE_MACROS_H +#define __ASM_ALTERNATIVE_MACROS_H + +#include <asm/cpucaps.h> + +#define ARM64_CB_PATCH ARM64_NCAPS + +/* A64 instructions are always 32 bits. */ +#define AARCH64_INSN_SIZE 4 + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> + +#define ALTINSTR_ENTRY(feature) \ + " .word 661b - .\n" /* label */ \ + " .word 663f - .\n" /* new instruction */ \ + " .hword " __stringify(feature) "\n" /* feature bit */ \ + " .byte 662b-661b\n" /* source len */ \ + " .byte 664f-663f\n" /* replacement len */ + +#define ALTINSTR_ENTRY_CB(feature, cb) \ + " .word 661b - .\n" /* label */ \ + " .word " __stringify(cb) "- .\n" /* callback */ \ + " .hword " __stringify(feature) "\n" /* feature bit */ \ + " .byte 662b-661b\n" /* source len */ \ + " .byte 664f-663f\n" /* replacement len */ + +/* + * alternative assembly primitive: + * + * If any of these .org directive fail, it means that insn1 and insn2 + * don't have the same length. This used to be written as + * + * .if ((664b-663b) != (662b-661b)) + * .error "Alternatives instruction length mismatch" + * .endif + * + * but most assemblers die if insn1 or insn2 have a .inst. This should + * be fixed in a binutils release posterior to 2.25.51.0.2 (anything + * containing commit 4e4d08cf7399b606 or c1baaddf8861). + * + * Alternatives with callbacks do not generate replacement instructions. + */ +#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ + ".if "__stringify(cfg_enabled)" == 1\n" \ + "661:\n\t" \ + oldinstr "\n" \ + "662:\n" \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feature) \ + ".popsection\n" \ + ".subsection 1\n" \ + "663:\n\t" \ + newinstr "\n" \ + "664:\n\t" \ + ".org . - (664b-663b) + (662b-661b)\n\t" \ + ".org . - (662b-661b) + (664b-663b)\n\t" \ + ".previous\n" \ + ".endif\n" + +#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ + ".if "__stringify(cfg_enabled)" == 1\n" \ + "661:\n\t" \ + oldinstr "\n" \ + "662:\n" \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY_CB(feature, cb) \ + ".popsection\n" \ + "663:\n\t" \ + "664:\n\t" \ + ".endif\n" + +#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ + __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) + +#define ALTERNATIVE_CB(oldinstr, cb) \ + __ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb) +#else + +#include <asm/assembler.h> + +.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len + .word \orig_offset - . + .word \alt_offset - . + .hword \feature + .byte \orig_len + .byte \alt_len +.endm + +.macro alternative_insn insn1, insn2, cap, enable = 1 + .if \enable +661: \insn1 +662: .pushsection .altinstructions, "a" + altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f + .popsection + .subsection 1 +663: \insn2 +664: .previous + .org . - (664b-663b) + (662b-661b) + .org . - (662b-661b) + (664b-663b) + .endif +.endm + +/* + * Alternative sequences + * + * The code for the case where the capability is not present will be + * assembled and linked as normal. There are no restrictions on this + * code. + * + * The code for the case where the capability is present will be + * assembled into a special section to be used for dynamic patching. + * Code for that case must: + * + * 1. Be exactly the same length (in bytes) as the default code + * sequence. + * + * 2. Not contain a branch target that is used outside of the + * alternative sequence it is defined in (branches into an + * alternative sequence are not fixed up). + */ + +/* + * Begin an alternative code sequence. + */ +.macro alternative_if_not cap + .set .Lasm_alt_mode, 0 + .pushsection .altinstructions, "a" + altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f + .popsection +661: +.endm + +.macro alternative_if cap + .set .Lasm_alt_mode, 1 + .pushsection .altinstructions, "a" + altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f + .popsection + .subsection 1 + .align 2 /* So GAS knows label 661 is suitably aligned */ +661: +.endm + +.macro alternative_cb cb + .set .Lasm_alt_mode, 0 + .pushsection .altinstructions, "a" + altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0 + .popsection +661: +.endm + +/* + * Provide the other half of the alternative code sequence. + */ +.macro alternative_else +662: + .if .Lasm_alt_mode==0 + .subsection 1 + .else + .previous + .endif +663: +.endm + +/* + * Complete an alternative code sequence. + */ +.macro alternative_endif +664: + .if .Lasm_alt_mode==0 + .previous + .endif + .org . - (664b-663b) + (662b-661b) + .org . - (662b-661b) + (664b-663b) +.endm + +/* + * Callback-based alternative epilogue + */ +.macro alternative_cb_end +662: +.endm + +/* + * Provides a trivial alternative or default sequence consisting solely + * of NOPs. The number of NOPs is chosen automatically to match the + * previous case. + */ +.macro alternative_else_nop_endif +alternative_else + nops (662b-661b) / AARCH64_INSN_SIZE +alternative_endif +.endm + +#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ + alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) + +.macro user_alt, label, oldinstr, newinstr, cond +9999: alternative_insn "\oldinstr", "\newinstr", \cond + _asm_extable 9999b, \label +.endm + +#endif /* __ASSEMBLY__ */ + +/* + * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature)); + * + * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO)); + * N.B. If CONFIG_FOO is specified, but not selected, the whole block + * will be omitted, including oldinstr. + */ +#define ALTERNATIVE(oldinstr, newinstr, ...) \ + _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) + +#endif /* __ASM_ALTERNATIVE_MACROS_H */ diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 619db9b4c9d5..a38b92e11811 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -2,17 +2,13 @@ #ifndef __ASM_ALTERNATIVE_H #define __ASM_ALTERNATIVE_H -#include <asm/cpucaps.h> -#include <asm/insn.h> - -#define ARM64_CB_PATCH ARM64_NCAPS +#include <asm/alternative-macros.h> #ifndef __ASSEMBLY__ #include <linux/init.h> #include <linux/types.h> #include <linux/stddef.h> -#include <linux/stringify.h> struct alt_instr { s32 orig_offset; /* offset to original instruction */ @@ -35,264 +31,5 @@ void apply_alternatives_module(void *start, size_t length); static inline void apply_alternatives_module(void *start, size_t length) { } #endif -#define ALTINSTR_ENTRY(feature) \ - " .word 661b - .\n" /* label */ \ - " .word 663f - .\n" /* new instruction */ \ - " .hword " __stringify(feature) "\n" /* feature bit */ \ - " .byte 662b-661b\n" /* source len */ \ - " .byte 664f-663f\n" /* replacement len */ - -#define ALTINSTR_ENTRY_CB(feature, cb) \ - " .word 661b - .\n" /* label */ \ - " .word " __stringify(cb) "- .\n" /* callback */ \ - " .hword " __stringify(feature) "\n" /* feature bit */ \ - " .byte 662b-661b\n" /* source len */ \ - " .byte 664f-663f\n" /* replacement len */ - -/* - * alternative assembly primitive: - * - * If any of these .org directive fail, it means that insn1 and insn2 - * don't have the same length. This used to be written as - * - * .if ((664b-663b) != (662b-661b)) - * .error "Alternatives instruction length mismatch" - * .endif - * - * but most assemblers die if insn1 or insn2 have a .inst. This should - * be fixed in a binutils release posterior to 2.25.51.0.2 (anything - * containing commit 4e4d08cf7399b606 or c1baaddf8861). - * - * Alternatives with callbacks do not generate replacement instructions. - */ -#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ - ".if "__stringify(cfg_enabled)" == 1\n" \ - "661:\n\t" \ - oldinstr "\n" \ - "662:\n" \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature) \ - ".popsection\n" \ - ".subsection 1\n" \ - "663:\n\t" \ - newinstr "\n" \ - "664:\n\t" \ - ".org . - (664b-663b) + (662b-661b)\n\t" \ - ".org . - (662b-661b) + (664b-663b)\n\t" \ - ".previous\n" \ - ".endif\n" - -#define __ALTERNATIVE_CFG_CB(oldinstr, feature, cfg_enabled, cb) \ - ".if "__stringify(cfg_enabled)" == 1\n" \ - "661:\n\t" \ - oldinstr "\n" \ - "662:\n" \ - ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY_CB(feature, cb) \ - ".popsection\n" \ - "663:\n\t" \ - "664:\n\t" \ - ".endif\n" - -#define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ - __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) - -#define ALTERNATIVE_CB(oldinstr, cb) \ - __ALTERNATIVE_CFG_CB(oldinstr, ARM64_CB_PATCH, 1, cb) -#else - -#include <asm/assembler.h> - -.macro altinstruction_entry orig_offset alt_offset feature orig_len alt_len - .word \orig_offset - . - .word \alt_offset - . - .hword \feature - .byte \orig_len - .byte \alt_len -.endm - -.macro alternative_insn insn1, insn2, cap, enable = 1 - .if \enable -661: \insn1 -662: .pushsection .altinstructions, "a" - altinstruction_entry 661b, 663f, \cap, 662b-661b, 664f-663f - .popsection - .subsection 1 -663: \insn2 -664: .previous - .org . - (664b-663b) + (662b-661b) - .org . - (662b-661b) + (664b-663b) - .endif -.endm - -/* - * Alternative sequences - * - * The code for the case where the capability is not present will be - * assembled and linked as normal. There are no restrictions on this - * code. - * - * The code for the case where the capability is present will be - * assembled into a special section to be used for dynamic patching. - * Code for that case must: - * - * 1. Be exactly the same length (in bytes) as the default code - * sequence. - * - * 2. Not contain a branch target that is used outside of the - * alternative sequence it is defined in (branches into an - * alternative sequence are not fixed up). - */ - -/* - * Begin an alternative code sequence. - */ -.macro alternative_if_not cap - .set .Lasm_alt_mode, 0 - .pushsection .altinstructions, "a" - altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f - .popsection -661: -.endm - -.macro alternative_if cap - .set .Lasm_alt_mode, 1 - .pushsection .altinstructions, "a" - altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f - .popsection - .subsection 1 - .align 2 /* So GAS knows label 661 is suitably aligned */ -661: -.endm - -.macro alternative_cb cb - .set .Lasm_alt_mode, 0 - .pushsection .altinstructions, "a" - altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0 - .popsection -661: -.endm - -/* - * Provide the other half of the alternative code sequence. - */ -.macro alternative_else -662: - .if .Lasm_alt_mode==0 - .subsection 1 - .else - .previous - .endif -663: -.endm - -/* - * Complete an alternative code sequence. - */ -.macro alternative_endif -664: - .if .Lasm_alt_mode==0 - .previous - .endif - .org . - (664b-663b) + (662b-661b) - .org . - (662b-661b) + (664b-663b) -.endm - -/* - * Callback-based alternative epilogue - */ -.macro alternative_cb_end -662: -.endm - -/* - * Provides a trivial alternative or default sequence consisting solely - * of NOPs. The number of NOPs is chosen automatically to match the - * previous case. - */ -.macro alternative_else_nop_endif -alternative_else - nops (662b-661b) / AARCH64_INSN_SIZE -alternative_endif -.endm - -#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \ - alternative_insn insn1, insn2, cap, IS_ENABLED(cfg) - -.macro user_alt, label, oldinstr, newinstr, cond -9999: alternative_insn "\oldinstr", "\newinstr", \cond - _asm_extable 9999b, \label -.endm - -/* - * Generate the assembly for UAO alternatives with exception table entries. - * This is complicated as there is no post-increment or pair versions of the - * unprivileged instructions, and USER() only works for single instructions. - */ -#ifdef CONFIG_ARM64_UAO - .macro uao_ldp l, reg1, reg2, addr, post_inc - alternative_if_not ARM64_HAS_UAO -8888: ldp \reg1, \reg2, [\addr], \post_inc; -8889: nop; - nop; - alternative_else - ldtr \reg1, [\addr]; - ldtr \reg2, [\addr, #8]; - add \addr, \addr, \post_inc; - alternative_endif - - _asm_extable 8888b,\l; - _asm_extable 8889b,\l; - .endm - - .macro uao_stp l, reg1, reg2, addr, post_inc - alternative_if_not ARM64_HAS_UAO -8888: stp \reg1, \reg2, [\addr], \post_inc; -8889: nop; - nop; - alternative_else - sttr \reg1, [\addr]; - sttr \reg2, [\addr, #8]; - add \addr, \addr, \post_inc; - alternative_endif - - _asm_extable 8888b,\l; - _asm_extable 8889b,\l; - .endm - - .macro uao_user_alternative l, inst, alt_inst, reg, addr, post_inc - alternative_if_not ARM64_HAS_UAO -8888: \inst \reg, [\addr], \post_inc; - nop; - alternative_else - \alt_inst \reg, [\addr]; - add \addr, \addr, \post_inc; - alternative_endif - - _asm_extable 8888b,\l; - .endm -#else - .macro uao_ldp l, reg1, reg2, addr, post_inc - USER(\l, ldp \reg1, \reg2, [\addr], \post_inc) - .endm - .macro uao_stp l, reg1, reg2, addr, post_inc - USER(\l, stp \reg1, \reg2, [\addr], \post_inc) - .endm - .macro uao_user_alternative l, inst, alt_inst, reg, addr, post_inc - USER(\l, \inst \reg, [\addr], \post_inc) - .endm -#endif - -#endif /* __ASSEMBLY__ */ - -/* - * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature)); - * - * Usage: asm(ALTERNATIVE(oldinstr, newinstr, feature, CONFIG_FOO)); - * N.B. If CONFIG_FOO is specified, but not selected, the whole block - * will be omitted, including oldinstr. - */ -#define ALTERNATIVE(oldinstr, newinstr, ...) \ - _ALTERNATIVE_CFG(oldinstr, newinstr, __VA_ARGS__, 1) - +#endif /* __ASSEMBLY__ */ #endif /* __ASM_ALTERNATIVE_H */ diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h index f68a0e64482a..9990059be106 100644 --- a/arch/arm64/include/asm/asm-uaccess.h +++ b/arch/arm64/include/asm/asm-uaccess.h @@ -2,7 +2,7 @@ #ifndef __ASM_ASM_UACCESS_H #define __ASM_ASM_UACCESS_H -#include <asm/alternative.h> +#include <asm/alternative-macros.h> #include <asm/kernel-pgtable.h> #include <asm/mmu.h> #include <asm/sysreg.h> @@ -15,10 +15,10 @@ .macro __uaccess_ttbr0_disable, tmp1 mrs \tmp1, ttbr1_el1 // swapper_pg_dir bic \tmp1, \tmp1, #TTBR_ASID_MASK - sub \tmp1, \tmp1, #RESERVED_TTBR0_SIZE // reserved_ttbr0 just before swapper_pg_dir + sub \tmp1, \tmp1, #PAGE_SIZE // reserved_pg_dir just before swapper_pg_dir msr ttbr0_el1, \tmp1 // set reserved TTBR0_EL1 isb - add \tmp1, \tmp1, #RESERVED_TTBR0_SIZE + add \tmp1, \tmp1, #PAGE_SIZE msr ttbr1_el1, \tmp1 // set reserved ASID isb .endm @@ -58,4 +58,33 @@ alternative_else_nop_endif .endm #endif +/* + * Generate the assembly for LDTR/STTR with exception table entries. + * This is complicated as there is no post-increment or pair versions of the + * unprivileged instructions, and USER() only works for single instructions. + */ + .macro user_ldp l, reg1, reg2, addr, post_inc +8888: ldtr \reg1, [\addr]; +8889: ldtr \reg2, [\addr, #8]; + add \addr, \addr, \post_inc; + + _asm_extable 8888b,\l; + _asm_extable 8889b,\l; + .endm + + .macro user_stp l, reg1, reg2, addr, post_inc +8888: sttr \reg1, [\addr]; +8889: sttr \reg2, [\addr, #8]; + add \addr, \addr, \post_inc; + + _asm_extable 8888b,\l; + _asm_extable 8889b,\l; + .endm + + .macro user_ldst l, inst, reg, addr, post_inc +8888: \inst \reg, [\addr]; + add \addr, \addr, \post_inc; + + _asm_extable 8888b,\l; + .endm #endif diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index e7d98997c09c..a7242ef2a2cd 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -16,8 +16,6 @@ #define ARM64_WORKAROUND_CAVIUM_23154 6 #define ARM64_WORKAROUND_834220 7 #define ARM64_HAS_NO_HW_PREFETCH 8 -#define ARM64_HAS_UAO 9 -#define ARM64_ALT_PAN_NOT_UAO 10 #define ARM64_HAS_VIRT_HOST_EXTN 11 #define ARM64_WORKAROUND_CAVIUM_27456 12 #define ARM64_HAS_32BIT_EL0 13 @@ -66,7 +64,8 @@ #define ARM64_HAS_TLB_RANGE 56 #define ARM64_MTE 57 #define ARM64_WORKAROUND_1508412 58 +#define ARM64_HAS_LDAPR 59 -#define ARM64_NCAPS 59 +#define ARM64_NCAPS 60 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index c59c16a6ea8b..1c406e8ae27e 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -377,6 +377,23 @@ cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, return false; } +static __always_inline bool is_vhe_hyp_code(void) +{ + /* Only defined for code run in VHE hyp context */ + return __is_defined(__KVM_VHE_HYPERVISOR__); +} + +static __always_inline bool is_nvhe_hyp_code(void) +{ + /* Only defined for code run in NVHE hyp context */ + return __is_defined(__KVM_NVHE_HYPERVISOR__); +} + +static __always_inline bool is_hyp_code(void) +{ + return is_vhe_hyp_code() || is_nvhe_hyp_code(); +} + extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; @@ -430,35 +447,40 @@ static __always_inline bool __cpus_have_const_cap(int num) } /* - * Test for a capability, possibly with a runtime check. + * Test for a capability without a runtime check. * - * Before capabilities are finalized, this behaves as cpus_have_cap(). + * Before capabilities are finalized, this will BUG(). * After capabilities are finalized, this is patched to avoid a runtime check. * * @num must be a compile-time constant. */ -static __always_inline bool cpus_have_const_cap(int num) +static __always_inline bool cpus_have_final_cap(int num) { if (system_capabilities_finalized()) return __cpus_have_const_cap(num); else - return cpus_have_cap(num); + BUG(); } /* - * Test for a capability without a runtime check. + * Test for a capability, possibly with a runtime check for non-hyp code. * - * Before capabilities are finalized, this will BUG(). + * For hyp code, this behaves the same as cpus_have_final_cap(). + * + * For non-hyp code: + * Before capabilities are finalized, this behaves as cpus_have_cap(). * After capabilities are finalized, this is patched to avoid a runtime check. * * @num must be a compile-time constant. */ -static __always_inline bool cpus_have_final_cap(int num) +static __always_inline bool cpus_have_const_cap(int num) { - if (system_capabilities_finalized()) + if (is_hyp_code()) + return cpus_have_final_cap(num); + else if (system_capabilities_finalized()) return __cpus_have_const_cap(num); else - BUG(); + return cpus_have_cap(num); } static inline void cpus_set_cap(unsigned int num) @@ -647,10 +669,16 @@ static __always_inline bool system_supports_fpsimd(void) return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD); } +static inline bool system_uses_hw_pan(void) +{ + return IS_ENABLED(CONFIG_ARM64_PAN) && + cpus_have_const_cap(ARM64_HAS_PAN); +} + static inline bool system_uses_ttbr0_pan(void) { return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && - !cpus_have_const_cap(ARM64_HAS_PAN); + !system_uses_hw_pan(); } static __always_inline bool system_supports_sve(void) @@ -742,11 +770,26 @@ static inline bool cpu_has_hw_af(void) ID_AA64MMFR1_HADBS_SHIFT); } +static inline bool cpu_has_pan(void) +{ + u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_PAN_SHIFT); +} + #ifdef CONFIG_ARM64_AMU_EXTN /* Check whether the cpu supports the Activity Monitors Unit (AMU) */ extern bool cpu_has_amu_feat(int cpu); +#else +static inline bool cpu_has_amu_feat(int cpu) +{ + return false; +} #endif +/* Get a cpu that supports the Activity Monitors Unit (AMU) */ +extern int get_cpu_with_amu_feat(void); + static inline unsigned int get_vmid_bits(u64 mmfr1) { int vmid_bits; diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index 0756191f44f6..78537393b650 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -37,7 +37,7 @@ asmlinkage void enter_from_user_mode(void); asmlinkage void exit_to_user_mode(void); void arm64_enter_nmi(struct pt_regs *regs); void arm64_exit_nmi(struct pt_regs *regs); -void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs); +void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs); void do_undefinstr(struct pt_regs *regs); void do_bti(struct pt_regs *regs); asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr); diff --git a/arch/arm64/include/asm/exec.h b/arch/arm64/include/asm/exec.h index 1aae6f9962fc..9a1c22ce664b 100644 --- a/arch/arm64/include/asm/exec.h +++ b/arch/arm64/include/asm/exec.h @@ -10,6 +10,5 @@ #include <linux/sched.h> extern unsigned long arch_align_stack(unsigned long sp); -void uao_thread_switch(struct task_struct *next); #endif /* __ASM_EXEC_H */ diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h index 97f6a63810ec..8e41faa37c69 100644 --- a/arch/arm64/include/asm/futex.h +++ b/arch/arm64/include/asm/futex.h @@ -16,7 +16,7 @@ do { \ unsigned int loops = FUTEX_MAX_LOOPS; \ \ - uaccess_enable(); \ + uaccess_enable_privileged(); \ asm volatile( \ " prfm pstl1strm, %2\n" \ "1: ldxr %w1, %2\n" \ @@ -39,7 +39,7 @@ do { \ "+r" (loops) \ : "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN) \ : "memory"); \ - uaccess_disable(); \ + uaccess_disable_privileged(); \ } while (0) static inline int @@ -95,7 +95,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, return -EFAULT; uaddr = __uaccess_mask_ptr(_uaddr); - uaccess_enable(); + uaccess_enable_privileged(); asm volatile("// futex_atomic_cmpxchg_inatomic\n" " prfm pstl1strm, %2\n" "1: ldxr %w1, %2\n" @@ -118,7 +118,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr, : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops) : "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN) : "memory"); - uaccess_disable(); + uaccess_disable_privileged(); if (!ret) *uval = val; diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 4b39293d0f72..4ebb9c054ccc 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -10,8 +10,7 @@ #include <linux/build_bug.h> #include <linux/types.h> -/* A64 instructions are always 32 bits. */ -#define AARCH64_INSN_SIZE 4 +#include <asm/alternative.h> #ifndef __ASSEMBLY__ /* diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 19ca76ea60d9..587c504a4c8b 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -89,12 +89,6 @@ #define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end)) #define IDMAP_DIR_SIZE (IDMAP_PGTABLE_LEVELS * PAGE_SIZE) -#ifdef CONFIG_ARM64_SW_TTBR0_PAN -#define RESERVED_TTBR0_SIZE (PAGE_SIZE) -#else -#define RESERVED_TTBR0_SIZE (0) -#endif - /* Initial memory map size */ #if ARM64_SWAPPER_USES_SECTION_MAPS #define SWAPPER_BLOCK_SHIFT SECTION_SHIFT diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 8699ce30f587..5d38ff4a4806 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -28,18 +28,11 @@ struct prev_kprobe { unsigned int status; }; -/* Single step context for kprobe */ -struct kprobe_step_ctx { - unsigned long ss_pending; - unsigned long match_addr; -}; - /* per-cpu kprobe control block */ struct kprobe_ctlblk { unsigned int kprobe_status; unsigned long saved_irqflag; struct prev_kprobe prev_kprobe; - struct kprobe_step_ctx ss_ctx; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 0aecbab6a7fb..781d029b8aa8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -239,6 +239,7 @@ enum vcpu_sysreg { #define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) #define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) #define cp14_DBGDCCINT (MDCCINT_EL1 * 2) +#define cp14_DBGVCR (DBGVCR32_EL2 * 2) #define NR_COPRO_REGS (NR_SYS_REGS * 2) diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index cd61239bae8c..556cb2d62b5b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -30,8 +30,8 @@ * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) \ - >> (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT)) +#define VMEMMAP_SHIFT (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT) +#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) >> VMEMMAP_SHIFT) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the @@ -44,17 +44,17 @@ #define _PAGE_OFFSET(va) (-(UL(1) << (va))) #define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS)) #define KIMAGE_VADDR (MODULES_END) -#define BPF_JIT_REGION_START (KASAN_SHADOW_END) +#define BPF_JIT_REGION_START (_PAGE_END(VA_BITS_MIN)) #define BPF_JIT_REGION_SIZE (SZ_128M) #define BPF_JIT_REGION_END (BPF_JIT_REGION_START + BPF_JIT_REGION_SIZE) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (BPF_JIT_REGION_END) #define MODULES_VSIZE (SZ_128M) -#define VMEMMAP_START (-VMEMMAP_SIZE - SZ_2M) +#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT))) #define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE) -#define PCI_IO_END (VMEMMAP_START - SZ_2M) +#define PCI_IO_END (VMEMMAP_START - SZ_8M) #define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) -#define FIXADDR_TOP (PCI_IO_START - SZ_2M) +#define FIXADDR_TOP (VMEMMAP_START - SZ_32M) #if VA_BITS > 48 #define VA_BITS_MIN (48) @@ -76,10 +76,11 @@ #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) \ + KASAN_SHADOW_OFFSET) +#define PAGE_END (KASAN_SHADOW_END - (1UL << (vabits_actual - KASAN_SHADOW_SCALE_SHIFT))) #define KASAN_THREAD_SHIFT 1 #else #define KASAN_THREAD_SHIFT 0 -#define KASAN_SHADOW_END (_PAGE_END(VA_BITS_MIN)) +#define PAGE_END (_PAGE_END(VA_BITS_MIN)) #endif /* CONFIG_KASAN */ #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) @@ -167,7 +168,6 @@ #include <asm/bug.h> extern u64 vabits_actual; -#define PAGE_END (_PAGE_END(vabits_actual)) extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ @@ -238,11 +238,9 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address - * space. Testing the top bit for the start of the region is a - * sufficient check and avoids having to worry about the tag. + * The linear kernel range starts at the bottom of the virtual address space. */ -#define __is_lm_address(addr) (!(((u64)addr) & BIT(vabits_actual - 1))) +#define __is_lm_address(addr) (((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 0672236e1aea..5c72c20bd300 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -36,11 +36,11 @@ static inline void contextidr_thread_switch(struct task_struct *next) } /* - * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0. + * Set TTBR0 to reserved_pg_dir. No translations will be possible via TTBR0. */ static inline void cpu_set_reserved_ttbr0(void) { - unsigned long ttbr = phys_to_ttbr(__pa_symbol(empty_zero_page)); + unsigned long ttbr = phys_to_ttbr(__pa_symbol(reserved_pg_dir)); write_sysreg(ttbr, ttbr0_el1); isb(); @@ -195,7 +195,7 @@ static inline void update_saved_ttbr0(struct task_struct *tsk, return; if (mm == &init_mm) - ttbr = __pa_symbol(empty_zero_page); + ttbr = __pa_symbol(reserved_pg_dir); else ttbr = virt_to_phys(mm->pgd) | ASID(mm) << 48; diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 01a96d07ae74..42442a0ae2ab 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -260,6 +260,7 @@ #define TCR_TBI1 (UL(1) << 38) #define TCR_HA (UL(1) << 39) #define TCR_HD (UL(1) << 40) +#define TCR_TBID1 (UL(1) << 52) #define TCR_NFD0 (UL(1) << 53) #define TCR_NFD1 (UL(1) << 54) #define TCR_E0PD0 (UL(1) << 55) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 5628289b9d5e..005eb035fbfa 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -22,7 +22,7 @@ * and fixed mappings */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (- PUD_SIZE - VMEMMAP_SIZE - SZ_64K) +#define VMALLOC_END (VMEMMAP_START - SZ_256M) #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) @@ -527,6 +527,7 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; extern pgd_t idmap_pg_end[]; extern pgd_t tramp_pg_dir[PTRS_PER_PGD]; +extern pgd_t reserved_pg_dir[PTRS_PER_PGD]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fce8cbecd6bc..724249f37af5 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -8,9 +8,6 @@ #ifndef __ASM_PROCESSOR_H #define __ASM_PROCESSOR_H -#define KERNEL_DS UL(-1) -#define USER_DS ((UL(1) << VA_BITS) - 1) - /* * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is * no point in shifting all network buffers by 2 bytes just to make some IP @@ -48,6 +45,7 @@ #define DEFAULT_MAP_WINDOW_64 (UL(1) << VA_BITS_MIN) #define TASK_SIZE_64 (UL(1) << vabits_actual) +#define TASK_SIZE_MAX (UL(1) << VA_BITS) #ifdef CONFIG_COMPAT #if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS) diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 28c85b87b8cd..e58bca832dff 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -16,6 +16,11 @@ #define CurrentEL_EL1 (1 << 2) #define CurrentEL_EL2 (2 << 2) +#define INIT_PSTATE_EL1 \ + (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL1h) +#define INIT_PSTATE_EL2 \ + (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | PSR_MODE_EL2h) + /* * PMR values used to mask/unmask interrupts. * @@ -188,8 +193,7 @@ struct pt_regs { s32 syscallno; u32 unused2; #endif - - u64 orig_addr_limit; + u64 sdei_ttbr1; /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */ u64 pmr_save; u64 stackframe[2]; diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h new file mode 100644 index 000000000000..1bce62fa908a --- /dev/null +++ b/arch/arm64/include/asm/rwonce.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Google LLC. + */ +#ifndef __ASM_RWONCE_H +#define __ASM_RWONCE_H + +#ifdef CONFIG_LTO + +#include <linux/compiler_types.h> +#include <asm/alternative-macros.h> + +#ifndef BUILD_VDSO + +#ifdef CONFIG_AS_HAS_LDAPR +#define __LOAD_RCPC(sfx, regs...) \ + ALTERNATIVE( \ + "ldar" #sfx "\t" #regs, \ + ".arch_extension rcpc\n" \ + "ldapr" #sfx "\t" #regs, \ + ARM64_HAS_LDAPR) +#else +#define __LOAD_RCPC(sfx, regs...) "ldar" #sfx "\t" #regs +#endif /* CONFIG_AS_HAS_LDAPR */ + +/* + * When building with LTO, there is an increased risk of the compiler + * converting an address dependency headed by a READ_ONCE() invocation + * into a control dependency and consequently allowing for harmful + * reordering by the CPU. + * + * Ensure that such transformations are harmless by overriding the generic + * READ_ONCE() definition with one that provides RCpc acquire semantics + * when building with LTO. + */ +#define __READ_ONCE(x) \ +({ \ + typeof(&(x)) __x = &(x); \ + int atomic = 1; \ + union { __unqual_scalar_typeof(*__x) __val; char __c[1]; } __u; \ + switch (sizeof(x)) { \ + case 1: \ + asm volatile(__LOAD_RCPC(b, %w0, %1) \ + : "=r" (*(__u8 *)__u.__c) \ + : "Q" (*__x) : "memory"); \ + break; \ + case 2: \ + asm volatile(__LOAD_RCPC(h, %w0, %1) \ + : "=r" (*(__u16 *)__u.__c) \ + : "Q" (*__x) : "memory"); \ + break; \ + case 4: \ + asm volatile(__LOAD_RCPC(, %w0, %1) \ + : "=r" (*(__u32 *)__u.__c) \ + : "Q" (*__x) : "memory"); \ + break; \ + case 8: \ + asm volatile(__LOAD_RCPC(, %0, %1) \ + : "=r" (*(__u64 *)__u.__c) \ + : "Q" (*__x) : "memory"); \ + break; \ + default: \ + atomic = 0; \ + } \ + atomic ? (typeof(*__x))__u.__val : (*(volatile typeof(__x))__x);\ +}) + +#endif /* !BUILD_VDSO */ +#endif /* CONFIG_LTO */ + +#include <asm-generic/rwonce.h> + +#endif /* __ASM_RWONCE_H */ diff --git a/arch/arm64/include/asm/signal.h b/arch/arm64/include/asm/signal.h new file mode 100644 index 000000000000..ef449f5f4ba8 --- /dev/null +++ b/arch/arm64/include/asm/signal.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARM64_ASM_SIGNAL_H +#define __ARM64_ASM_SIGNAL_H + +#include <asm/memory.h> +#include <uapi/asm/signal.h> +#include <uapi/asm/siginfo.h> + +static inline void __user *arch_untagged_si_addr(void __user *addr, + unsigned long sig, + unsigned long si_code) +{ + /* + * For historical reasons, all bits of the fault address are exposed as + * address bits for watchpoint exceptions. New architectures should + * handle the tag bits consistently. + */ + if (sig == SIGTRAP && si_code == TRAP_BRKPT) + return addr; + + return untagged_addr(addr); +} +#define arch_untagged_si_addr arch_untagged_si_addr + +#endif diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index c8ab9900293f..9e53ca349d2f 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -98,6 +98,10 @@ #define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift)) #define SET_PSTATE_TCO(x) __emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift)) +#define set_pstate_pan(x) asm volatile(SET_PSTATE_PAN(x)) +#define set_pstate_uao(x) asm volatile(SET_PSTATE_UAO(x)) +#define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x)) + #define __SYS_BARRIER_INSN(CRm, op2, Rt) \ __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f)) @@ -578,6 +582,9 @@ #define ENDIAN_SET_EL2 0 #endif +#define INIT_SCTLR_EL2_MMU_OFF \ + (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) + /* SCTLR_EL1 specific flags. */ #define SCTLR_EL1_ATA0 (BIT(42)) @@ -611,12 +618,15 @@ #define ENDIAN_SET_EL1 0 #endif -#define SCTLR_EL1_SET (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA |\ - SCTLR_EL1_SA0 | SCTLR_EL1_SED | SCTLR_ELx_I |\ - SCTLR_EL1_DZE | SCTLR_EL1_UCT |\ - SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN |\ - SCTLR_ELx_ITFSB| SCTLR_ELx_ATA | SCTLR_EL1_ATA0 |\ - ENDIAN_SET_EL1 | SCTLR_EL1_UCI | SCTLR_EL1_RES1) +#define INIT_SCTLR_EL1_MMU_OFF \ + (ENDIAN_SET_EL1 | SCTLR_EL1_RES1) + +#define INIT_SCTLR_EL1_MMU_ON \ + (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_EL1_SA0 | \ + SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \ + SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \ + SCTLR_ELx_ATA | SCTLR_EL1_ATA0 | ENDIAN_SET_EL1 | SCTLR_EL1_UCI | \ + SCTLR_EL1_RES1) /* MAIR_ELx memory attributes (used by Linux) */ #define MAIR_ATTR_DEVICE_nGnRnE UL(0x00) diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index 1ab63cfbbaf1..673be2d1263c 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -22,7 +22,7 @@ void die(const char *msg, struct pt_regs *regs, int err); struct siginfo; void arm64_notify_die(const char *str, struct pt_regs *regs, - int signo, int sicode, void __user *addr, + int signo, int sicode, unsigned long far, int err); void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int, diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 1fbab854a51b..015beafe58f5 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -18,14 +18,11 @@ struct task_struct; #include <asm/stack_pointer.h> #include <asm/types.h> -typedef unsigned long mm_segment_t; - /* * low level task data that entry.S needs immediate access to. */ struct thread_info { unsigned long flags; /* low level flags */ - mm_segment_t addr_limit; /* address limit */ #ifdef CONFIG_ARM64_SW_TTBR0_PAN u64 ttbr0; /* saved TTBR0_EL1 */ #endif @@ -66,8 +63,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ -#define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ -#define TIF_MTE_ASYNC_FAULT 6 /* MTE Asynchronous Tag Check Fault */ +#define TIF_MTE_ASYNC_FAULT 5 /* MTE Asynchronous Tag Check Fault */ #define TIF_SYSCALL_TRACE 8 /* syscall trace active */ #define TIF_SYSCALL_AUDIT 9 /* syscall auditing */ #define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */ @@ -93,7 +89,6 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_UPROBE (1 << TIF_UPROBE) -#define _TIF_FSCHECK (1 << TIF_FSCHECK) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_32BIT (1 << TIF_32BIT) #define _TIF_SVE (1 << TIF_SVE) @@ -101,7 +96,7 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ - _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT) + _TIF_UPROBE | _TIF_MTE_ASYNC_FAULT) #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ @@ -119,7 +114,6 @@ void arch_release_task_struct(struct task_struct *tsk); { \ .flags = _TIF_FOREIGN_FPSTATE, \ .preempt_count = INIT_PREEMPT_COUNT, \ - .addr_limit = KERNEL_DS, \ INIT_SCS \ } diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 11a465243f66..3b8dca4eb08d 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -16,12 +16,14 @@ int pcibus_to_node(struct pci_bus *bus); #include <linux/arch_topology.h> +void update_freq_counters_refs(void); +void topology_scale_freq_tick(void); + #ifdef CONFIG_ARM64_AMU_EXTN /* * Replace task scheduler's default counter-based * frequency-invariance scale factor setting. */ -void topology_scale_freq_tick(void); #define arch_scale_freq_tick topology_scale_freq_tick #endif /* CONFIG_ARM64_AMU_EXTN */ diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index d96dc2c7c09d..54f32a0675df 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -26,9 +26,9 @@ void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); void force_signal_inject(int signal, int code, unsigned long address, unsigned int err); void arm64_notify_segfault(unsigned long addr); -void arm64_force_sig_fault(int signo, int code, void __user *addr, const char *str); -void arm64_force_sig_mceerr(int code, void __user *addr, short lsb, const char *str); -void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr, const char *str); +void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str); +void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str); +void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str); /* * Move regs->pc to next instruction and do necessary setup before it diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 991dd5f031e4..abb31aa1f8ca 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -24,44 +24,18 @@ #include <asm/memory.h> #include <asm/extable.h> -#define get_fs() (current_thread_info()->addr_limit) - -static inline void set_fs(mm_segment_t fs) -{ - current_thread_info()->addr_limit = fs; - - /* - * Prevent a mispredicted conditional call to set_fs from forwarding - * the wrong address limit to access_ok under speculation. - */ - spec_bar(); - - /* On user-mode return, check fs is correct */ - set_thread_flag(TIF_FSCHECK); - - /* - * Enable/disable UAO so that copy_to_user() etc can access - * kernel memory with the unprivileged instructions. - */ - if (IS_ENABLED(CONFIG_ARM64_UAO) && fs == KERNEL_DS) - asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO)); - else - asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO, - CONFIG_ARM64_UAO)); -} - -#define uaccess_kernel() (get_fs() == KERNEL_DS) +#define HAVE_GET_KERNEL_NOFAULT /* * Test whether a block of memory is a valid user space address. * Returns 1 if the range is valid, 0 otherwise. * * This is equivalent to the following test: - * (u65)addr + (u65)size <= (u65)current->addr_limit + 1 + * (u65)addr + (u65)size <= (u65)TASK_SIZE_MAX */ static inline unsigned long __range_ok(const void __user *addr, unsigned long size) { - unsigned long ret, limit = current_thread_info()->addr_limit; + unsigned long ret, limit = TASK_SIZE_MAX - 1; /* * Asynchronous I/O running in a kernel thread does not have the @@ -94,7 +68,6 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si } #define access_ok(addr, size) __range_ok(addr, size) -#define user_addr_max get_fs #define _ASM_EXTABLE(from, to) \ " .pushsection __ex_table, \"a\"\n" \ @@ -113,8 +86,8 @@ static inline void __uaccess_ttbr0_disable(void) local_irq_save(flags); ttbr = read_sysreg(ttbr1_el1); ttbr &= ~TTBR_ASID_MASK; - /* reserved_ttbr0 placed before swapper_pg_dir */ - write_sysreg(ttbr - RESERVED_TTBR0_SIZE, ttbr0_el1); + /* reserved_pg_dir placed before swapper_pg_dir */ + write_sysreg(ttbr - PAGE_SIZE, ttbr0_el1); isb(); /* Set reserved ASID */ write_sysreg(ttbr, ttbr1_el1); @@ -186,47 +159,26 @@ static inline void __uaccess_enable_hw_pan(void) CONFIG_ARM64_PAN)); } -#define __uaccess_disable(alt) \ -do { \ - if (!uaccess_ttbr0_disable()) \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt, \ - CONFIG_ARM64_PAN)); \ -} while (0) - -#define __uaccess_enable(alt) \ -do { \ - if (!uaccess_ttbr0_enable()) \ - asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt, \ - CONFIG_ARM64_PAN)); \ -} while (0) - -static inline void uaccess_disable(void) +static inline void uaccess_disable_privileged(void) { - __uaccess_disable(ARM64_HAS_PAN); -} + if (uaccess_ttbr0_disable()) + return; -static inline void uaccess_enable(void) -{ - __uaccess_enable(ARM64_HAS_PAN); + __uaccess_enable_hw_pan(); } -/* - * These functions are no-ops when UAO is present. - */ -static inline void uaccess_disable_not_uao(void) +static inline void uaccess_enable_privileged(void) { - __uaccess_disable(ARM64_ALT_PAN_NOT_UAO); -} + if (uaccess_ttbr0_enable()) + return; -static inline void uaccess_enable_not_uao(void) -{ - __uaccess_enable(ARM64_ALT_PAN_NOT_UAO); + __uaccess_disable_hw_pan(); } /* - * Sanitise a uaccess pointer such that it becomes NULL if above the - * current addr_limit. In case the pointer is tagged (has the top byte set), - * untag the pointer before checking. + * Sanitise a uaccess pointer such that it becomes NULL if above the maximum + * user address. In case the pointer is tagged (has the top byte set), untag + * the pointer before checking. */ #define uaccess_mask_ptr(ptr) (__typeof__(ptr))__uaccess_mask_ptr(ptr) static inline void __user *__uaccess_mask_ptr(const void __user *ptr) @@ -237,7 +189,7 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) " bics xzr, %3, %2\n" " csel %0, %1, xzr, eq\n" : "=&r" (safe_ptr) - : "r" (ptr), "r" (current_thread_info()->addr_limit), + : "r" (ptr), "r" (TASK_SIZE_MAX - 1), "r" (untagged_addr(ptr)) : "cc"); @@ -253,10 +205,9 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) * The "__xxx_error" versions set the third argument to -EFAULT if an error * occurs, and leave it unchanged on success. */ -#define __get_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ +#define __get_mem_asm(load, reg, x, addr, err) \ asm volatile( \ - "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ - alt_instr " " reg "1, [%2]\n", feature) \ + "1: " load " " reg "1, [%2]\n" \ "2:\n" \ " .section .fixup, \"ax\"\n" \ " .align 2\n" \ @@ -268,35 +219,36 @@ static inline void __user *__uaccess_mask_ptr(const void __user *ptr) : "+r" (err), "=&r" (x) \ : "r" (addr), "i" (-EFAULT)) -#define __raw_get_user(x, ptr, err) \ +#define __raw_get_mem(ldr, x, ptr, err) \ do { \ unsigned long __gu_val; \ - __chk_user_ptr(ptr); \ - uaccess_enable_not_uao(); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __get_mem_asm(ldr "b", "%w", __gu_val, (ptr), (err)); \ break; \ case 2: \ - __get_user_asm("ldrh", "ldtrh", "%w", __gu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __get_mem_asm(ldr "h", "%w", __gu_val, (ptr), (err)); \ break; \ case 4: \ - __get_user_asm("ldr", "ldtr", "%w", __gu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __get_mem_asm(ldr, "%w", __gu_val, (ptr), (err)); \ break; \ case 8: \ - __get_user_asm("ldr", "ldtr", "%x", __gu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __get_mem_asm(ldr, "%x", __gu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ } \ - uaccess_disable_not_uao(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) +#define __raw_get_user(x, ptr, err) \ +do { \ + __chk_user_ptr(ptr); \ + uaccess_ttbr0_enable(); \ + __raw_get_mem("ldtr", x, ptr, err); \ + uaccess_ttbr0_disable(); \ +} while (0) + #define __get_user_error(x, ptr, err) \ do { \ __typeof__(*(ptr)) __user *__p = (ptr); \ @@ -318,10 +270,19 @@ do { \ #define get_user __get_user -#define __put_user_asm(instr, alt_instr, reg, x, addr, err, feature) \ +#define __get_kernel_nofault(dst, src, type, err_label) \ +do { \ + int __gkn_err = 0; \ + \ + __raw_get_mem("ldr", *((type *)(dst)), \ + (__force type *)(src), __gkn_err); \ + if (unlikely(__gkn_err)) \ + goto err_label; \ +} while (0) + +#define __put_mem_asm(store, reg, x, addr, err) \ asm volatile( \ - "1:"ALTERNATIVE(instr " " reg "1, [%2]\n", \ - alt_instr " " reg "1, [%2]\n", feature) \ + "1: " store " " reg "1, [%2]\n" \ "2:\n" \ " .section .fixup,\"ax\"\n" \ " .align 2\n" \ @@ -332,32 +293,33 @@ do { \ : "+r" (err) \ : "r" (x), "r" (addr), "i" (-EFAULT)) -#define __raw_put_user(x, ptr, err) \ +#define __raw_put_mem(str, x, ptr, err) \ do { \ __typeof__(*(ptr)) __pu_val = (x); \ - __chk_user_ptr(ptr); \ - uaccess_enable_not_uao(); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __put_mem_asm(str "b", "%w", __pu_val, (ptr), (err)); \ break; \ case 2: \ - __put_user_asm("strh", "sttrh", "%w", __pu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __put_mem_asm(str "h", "%w", __pu_val, (ptr), (err)); \ break; \ case 4: \ - __put_user_asm("str", "sttr", "%w", __pu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __put_mem_asm(str, "%w", __pu_val, (ptr), (err)); \ break; \ case 8: \ - __put_user_asm("str", "sttr", "%x", __pu_val, (ptr), \ - (err), ARM64_HAS_UAO); \ + __put_mem_asm(str, "%x", __pu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ } \ - uaccess_disable_not_uao(); \ +} while (0) + +#define __raw_put_user(x, ptr, err) \ +do { \ + __chk_user_ptr(ptr); \ + uaccess_ttbr0_enable(); \ + __raw_put_mem("sttr", x, ptr, err); \ + uaccess_ttbr0_disable(); \ } while (0) #define __put_user_error(x, ptr, err) \ @@ -381,14 +343,24 @@ do { \ #define put_user __put_user +#define __put_kernel_nofault(dst, src, type, err_label) \ +do { \ + int __pkn_err = 0; \ + \ + __raw_put_mem("str", *((type *)(src)), \ + (__force type *)(dst), __pkn_err); \ + if (unlikely(__pkn_err)) \ + goto err_label; \ +} while(0) + extern unsigned long __must_check __arch_copy_from_user(void *to, const void __user *from, unsigned long n); #define raw_copy_from_user(to, from, n) \ ({ \ unsigned long __acfu_ret; \ - uaccess_enable_not_uao(); \ + uaccess_ttbr0_enable(); \ __acfu_ret = __arch_copy_from_user((to), \ __uaccess_mask_ptr(from), (n)); \ - uaccess_disable_not_uao(); \ + uaccess_ttbr0_disable(); \ __acfu_ret; \ }) @@ -396,10 +368,10 @@ extern unsigned long __must_check __arch_copy_to_user(void __user *to, const voi #define raw_copy_to_user(to, from, n) \ ({ \ unsigned long __actu_ret; \ - uaccess_enable_not_uao(); \ + uaccess_ttbr0_enable(); \ __actu_ret = __arch_copy_to_user(__uaccess_mask_ptr(to), \ (from), (n)); \ - uaccess_disable_not_uao(); \ + uaccess_ttbr0_disable(); \ __actu_ret; \ }) @@ -407,10 +379,10 @@ extern unsigned long __must_check __arch_copy_in_user(void __user *to, const voi #define raw_copy_in_user(to, from, n) \ ({ \ unsigned long __aciu_ret; \ - uaccess_enable_not_uao(); \ + uaccess_ttbr0_enable(); \ __aciu_ret = __arch_copy_in_user(__uaccess_mask_ptr(to), \ __uaccess_mask_ptr(from), (n)); \ - uaccess_disable_not_uao(); \ + uaccess_ttbr0_disable(); \ __aciu_ret; \ }) @@ -421,9 +393,9 @@ extern unsigned long __must_check __arch_clear_user(void __user *to, unsigned lo static inline unsigned long __must_check __clear_user(void __user *to, unsigned long n) { if (access_ok(to, n)) { - uaccess_enable_not_uao(); + uaccess_ttbr0_enable(); n = __arch_clear_user(__uaccess_mask_ptr(to), n); - uaccess_disable_not_uao(); + uaccess_ttbr0_disable(); } return n; } diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index 09977acc007d..6069be50baf9 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -86,13 +86,12 @@ static inline bool is_kernel_in_hyp_mode(void) static __always_inline bool has_vhe(void) { /* - * The following macros are defined for code specic to VHE/nVHE. - * If has_vhe() is inlined into those compilation units, it can - * be determined statically. Otherwise fall back to caps. + * Code only run in VHE/NVHE hyp context can assume VHE is present or + * absent. Otherwise fall back to caps. */ - if (__is_defined(__KVM_VHE_HYPERVISOR__)) + if (is_vhe_hyp_code()) return true; - else if (__is_defined(__KVM_NVHE_HYPERVISOR__)) + else if (is_nvhe_hyp_code()) return false; else return cpus_have_final_cap(ARM64_HAS_VIRT_HOST_EXTN); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index bbaf0bc4ad60..86364ab6f13f 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -58,7 +58,6 @@ obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_CRASH_CORE) += crash_core.o obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o -obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso/ probes/ diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 73039949b5ce..a57cffb752e8 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -21,7 +21,8 @@ #define ALT_ORIG_PTR(a) __ALT_PTR(a, orig_offset) #define ALT_REPL_PTR(a) __ALT_PTR(a, alt_offset) -static int all_alternatives_applied; +/* Volatile, as we may be patching the guts of READ_ONCE() */ +static volatile int all_alternatives_applied; static DECLARE_BITMAP(applied_alternatives, ARM64_NCAPS); @@ -205,7 +206,7 @@ static int __apply_alternatives_multi_stop(void *unused) /* We always have a CPU 0 at this point (__init) */ if (smp_processor_id()) { - while (!READ_ONCE(all_alternatives_applied)) + while (!all_alternatives_applied) cpu_relax(); isb(); } else { @@ -217,7 +218,7 @@ static int __apply_alternatives_multi_stop(void *unused) BUG_ON(all_alternatives_applied); __apply_alternatives(®ion, false, remaining_capabilities); /* Barriers provided by the cache flushing */ - WRITE_ONCE(all_alternatives_applied, 1); + all_alternatives_applied = 1; } return 0; diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 7364de008bab..0e86e8b9cedd 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -277,7 +277,7 @@ static void __init register_insn_emulation_sysctl(void) #define __user_swpX_asm(data, addr, res, temp, temp2, B) \ do { \ - uaccess_enable(); \ + uaccess_enable_privileged(); \ __asm__ __volatile__( \ " mov %w3, %w7\n" \ "0: ldxr"B" %w2, [%4]\n" \ @@ -302,7 +302,7 @@ do { \ "i" (-EFAULT), \ "i" (__SWP_LL_SC_LOOPS) \ : "memory"); \ - uaccess_disable(); \ + uaccess_disable_privileged(); \ } while (0) #define __user_swp_asm(data, addr, res, temp, temp2) \ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 7d32fc959b1a..679b19b8a7ff 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -30,7 +30,6 @@ int main(void) BLANK(); DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); - DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); #ifdef CONFIG_ARM64_SW_TTBR0_PAN DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); #endif @@ -70,7 +69,7 @@ int main(void) DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_PC, offsetof(struct pt_regs, pc)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); - DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit)); + DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6f36c4f62f69..39138f6d3ba2 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -153,10 +153,6 @@ EXPORT_SYMBOL(cpu_hwcap_keys); .width = 0, \ } -/* meta feature for alternatives */ -static bool __maybe_unused -cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused); - static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); static bool __system_matches_cap(unsigned int n); @@ -1528,8 +1524,10 @@ bool cpu_has_amu_feat(int cpu) return cpumask_test_cpu(cpu, &amu_cpus); } -/* Initialize the use of AMU counters for frequency invariance */ -extern void init_cpu_freq_invariance_counters(void); +int get_cpu_with_amu_feat(void) +{ + return cpumask_any(&amu_cpus); +} static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) { @@ -1537,7 +1535,7 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap) pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n", smp_processor_id()); cpumask_set_cpu(smp_processor_id(), &amu_cpus); - init_cpu_freq_invariance_counters(); + update_freq_counters_refs(); } } @@ -1559,6 +1557,11 @@ static bool has_amu(const struct arm64_cpu_capabilities *cap, return true; } +#else +int get_cpu_with_amu_feat(void) +{ + return nr_cpu_ids; +} #endif #ifdef CONFIG_ARM64_VHE @@ -1600,7 +1603,7 @@ static void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused) WARN_ON_ONCE(in_interrupt()); sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0); - asm(SET_PSTATE_PAN(1)); + set_pstate_pan(1); } #endif /* CONFIG_ARM64_PAN */ @@ -1770,28 +1773,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE, .matches = has_no_hw_prefetch, }, -#ifdef CONFIG_ARM64_UAO - { - .desc = "User Access Override", - .capability = ARM64_HAS_UAO, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .matches = has_cpuid_feature, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .field_pos = ID_AA64MMFR2_UAO_SHIFT, - .min_field_value = 1, - /* - * We rely on stop_machine() calling uao_thread_switch() to set - * UAO immediately after patching. - */ - }, -#endif /* CONFIG_ARM64_UAO */ -#ifdef CONFIG_ARM64_PAN - { - .capability = ARM64_ALT_PAN_NOT_UAO, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, - .matches = cpufeature_pan_not_uao, - }, -#endif /* CONFIG_ARM64_PAN */ #ifdef CONFIG_ARM64_VHE { .desc = "Virtualization Host Extensions", @@ -2138,6 +2119,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_enable_mte, }, #endif /* CONFIG_ARM64_MTE */ + { + .desc = "RCpc load-acquire (LDAPR)", + .capability = ARM64_HAS_LDAPR, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64ISAR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64ISAR1_LRCPC_SHIFT, + .matches = has_cpuid_feature, + .min_field_value = 1, + }, {}, }; @@ -2652,7 +2643,7 @@ bool this_cpu_has_cap(unsigned int n) * - The SYSTEM_FEATURE cpu_hwcaps may not have been set. * In all other cases cpus_have_{const_}cap() should be used. */ -static bool __system_matches_cap(unsigned int n) +static bool __maybe_unused __system_matches_cap(unsigned int n) { if (n < ARM64_NCAPS) { const struct arm64_cpu_capabilities *cap = cpu_hwcaps_ptrs[n]; @@ -2732,12 +2723,6 @@ void __init setup_cpu_features(void) ARCH_DMA_MINALIGN); } -static bool __maybe_unused -cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused) -{ - return (__system_matches_cap(ARM64_HAS_PAN) && !__system_matches_cap(ARM64_HAS_UAO)); -} - static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *cap) { cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index fa76151de6ff..4f3661eeb7ec 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -234,9 +234,8 @@ static void send_user_sigtrap(int si_code) if (interrupts_enabled(regs)) local_irq_enable(); - arm64_force_sig_fault(SIGTRAP, si_code, - (void __user *)instruction_pointer(regs), - "User debug trap"); + arm64_force_sig_fault(SIGTRAP, si_code, instruction_pointer(regs), + "User debug trap"); } static int single_step_handler(unsigned long unused, unsigned int esr, diff --git a/arch/arm64/kernel/efi-header.S b/arch/arm64/kernel/efi-header.S index a71844fb923e..28d8a5dca5f1 100644 --- a/arch/arm64/kernel/efi-header.S +++ b/arch/arm64/kernel/efi-header.S @@ -7,30 +7,48 @@ #include <linux/pe.h> #include <linux/sizes.h> + .macro efi_signature_nop +#ifdef CONFIG_EFI +.L_head: + /* + * This ccmp instruction has no meaningful effect except that + * its opcode forms the magic "MZ" signature required by UEFI. + */ + ccmp x18, #0, #0xd, pl +#else + /* + * Bootloaders may inspect the opcode at the start of the kernel + * image to decide if the kernel is capable of booting via UEFI. + * So put an ordinary NOP here, not the "MZ.." pseudo-nop above. + */ + nop +#endif + .endm + .macro __EFI_PE_HEADER +#ifdef CONFIG_EFI + .set .Lpe_header_offset, . - .L_head .long PE_MAGIC -coff_header: .short IMAGE_FILE_MACHINE_ARM64 // Machine - .short section_count // NumberOfSections + .short .Lsection_count // NumberOfSections .long 0 // TimeDateStamp .long 0 // PointerToSymbolTable .long 0 // NumberOfSymbols - .short section_table - optional_header // SizeOfOptionalHeader + .short .Lsection_table - .Loptional_header // SizeOfOptionalHeader .short IMAGE_FILE_DEBUG_STRIPPED | \ IMAGE_FILE_EXECUTABLE_IMAGE | \ IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics -optional_header: +.Loptional_header: .short PE_OPT_MAGIC_PE32PLUS // PE32+ format .byte 0x02 // MajorLinkerVersion .byte 0x14 // MinorLinkerVersion - .long __initdata_begin - efi_header_end // SizeOfCode + .long __initdata_begin - .Lefi_header_end // SizeOfCode .long __pecoff_data_size // SizeOfInitializedData .long 0 // SizeOfUninitializedData - .long __efistub_efi_pe_entry - _head // AddressOfEntryPoint - .long efi_header_end - _head // BaseOfCode + .long __efistub_efi_pe_entry - .L_head // AddressOfEntryPoint + .long .Lefi_header_end - .L_head // BaseOfCode -extra_header_fields: .quad 0 // ImageBase .long SEGMENT_ALIGN // SectionAlignment .long PECOFF_FILE_ALIGNMENT // FileAlignment @@ -42,10 +60,10 @@ extra_header_fields: .short 0 // MinorSubsystemVersion .long 0 // Win32VersionValue - .long _end - _head // SizeOfImage + .long _end - .L_head // SizeOfImage // Everything before the kernel image is considered part of the header - .long efi_header_end - _head // SizeOfHeaders + .long .Lefi_header_end - .L_head // SizeOfHeaders .long 0 // CheckSum .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem .short 0 // DllCharacteristics @@ -54,7 +72,7 @@ extra_header_fields: .quad 0 // SizeOfHeapReserve .quad 0 // SizeOfHeapCommit .long 0 // LoaderFlags - .long (section_table - .) / 8 // NumberOfRvaAndSizes + .long (.Lsection_table - .) / 8 // NumberOfRvaAndSizes .quad 0 // ExportTable .quad 0 // ImportTable @@ -64,17 +82,17 @@ extra_header_fields: .quad 0 // BaseRelocationTable #ifdef CONFIG_DEBUG_EFI - .long efi_debug_table - _head // DebugTable - .long efi_debug_table_size + .long .Lefi_debug_table - .L_head // DebugTable + .long .Lefi_debug_table_size #endif // Section table -section_table: +.Lsection_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 __initdata_begin - .Lefi_header_end // VirtualSize + .long .Lefi_header_end - .L_head // VirtualAddress + .long __initdata_begin - .Lefi_header_end // SizeOfRawData + .long .Lefi_header_end - .L_head // PointerToRawData .long 0 // PointerToRelocations .long 0 // PointerToLineNumbers @@ -86,9 +104,9 @@ section_table: .ascii ".data\0\0\0" .long __pecoff_data_size // VirtualSize - .long __initdata_begin - _head // VirtualAddress + .long __initdata_begin - .L_head // VirtualAddress .long __pecoff_data_rawsize // SizeOfRawData - .long __initdata_begin - _head // PointerToRawData + .long __initdata_begin - .L_head // PointerToRawData .long 0 // PointerToRelocations .long 0 // PointerToLineNumbers @@ -98,7 +116,7 @@ section_table: IMAGE_SCN_MEM_READ | \ IMAGE_SCN_MEM_WRITE // Characteristics - .set section_count, (. - section_table) / 40 + .set .Lsection_count, (. - .Lsection_table) / 40 #ifdef CONFIG_DEBUG_EFI /* @@ -114,21 +132,21 @@ section_table: __INITRODATA .align 2 -efi_debug_table: +.Lefi_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 .Lefi_debug_entry_size // SizeOfData .long 0 // RVA - .long efi_debug_entry - _head // FileOffset + .long .Lefi_debug_entry - .L_head // FileOffset - .set efi_debug_table_size, . - efi_debug_table + .set .Lefi_debug_table_size, . - .Lefi_debug_table .previous -efi_debug_entry: +.Lefi_debug_entry: // EFI_IMAGE_DEBUG_CODEVIEW_NB10_ENTRY .ascii "NB10" // Signature .long 0 // Unknown @@ -137,16 +155,12 @@ efi_debug_entry: .asciz VMLINUX_PATH - .set efi_debug_entry_size, . - efi_debug_entry + .set .Lefi_debug_entry_size, . - .Lefi_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. - */ .balign SEGMENT_ALIGN -efi_header_end: +.Lefi_header_end: +#else + .set .Lpe_header_offset, 0x0 +#endif .endm diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 70e0a7591245..5346953e4382 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -115,7 +115,6 @@ static void noinstr el1_abort(struct pt_regs *regs, unsigned long esr) enter_from_kernel_mode(regs); local_daif_inherit(regs); - far = untagged_addr(far); do_mem_abort(far, esr, regs); local_daif_mask(); exit_to_kernel_mode(regs); @@ -256,7 +255,6 @@ static void noinstr el0_da(struct pt_regs *regs, unsigned long esr) enter_from_user_mode(); local_daif_restore(DAIF_PROCCTX); - far = untagged_addr(far); do_mem_abort(far, esr, regs); } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index d72c818b019c..51c762156099 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -216,12 +216,6 @@ alternative_else_nop_endif .else add x21, sp, #S_FRAME_SIZE get_current_task tsk - /* Save the task's original addr_limit and set USER_DS */ - ldr x20, [tsk, #TSK_TI_ADDR_LIMIT] - str x20, [sp, #S_ORIG_ADDR_LIMIT] - mov x20, #USER_DS - str x20, [tsk, #TSK_TI_ADDR_LIMIT] - /* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */ .endif /* \el == 0 */ mrs x22, elr_el1 mrs x23, spsr_el1 @@ -279,12 +273,6 @@ alternative_else_nop_endif .macro kernel_exit, el .if \el != 0 disable_daif - - /* Restore the task's original addr_limit. */ - ldr x20, [sp, #S_ORIG_ADDR_LIMIT] - str x20, [tsk, #TSK_TI_ADDR_LIMIT] - - /* No need to restore UAO, it will be restored from SPSR_EL1 */ .endif /* Restore pmr */ @@ -438,7 +426,7 @@ SYM_CODE_END(__swpan_exit_el0) #ifdef CONFIG_SHADOW_CALL_STACK /* also switch to the irq shadow stack */ - adr_this_cpu scs_sp, irq_shadow_call_stack, x26 + ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x26 #endif 9998: @@ -773,9 +761,10 @@ SYM_CODE_END(ret_to_user) */ .pushsection ".entry.tramp.text", "ax" + // Move from tramp_pg_dir to swapper_pg_dir .macro tramp_map_kernel, tmp mrs \tmp, ttbr1_el1 - add \tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE) + add \tmp, \tmp, #(2 * PAGE_SIZE) bic \tmp, \tmp, #USER_ASID_FLAG msr ttbr1_el1, \tmp #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1003 @@ -792,9 +781,10 @@ alternative_else_nop_endif #endif /* CONFIG_QCOM_FALKOR_ERRATUM_1003 */ .endm + // Move from swapper_pg_dir to tramp_pg_dir .macro tramp_unmap_kernel, tmp mrs \tmp, ttbr1_el1 - sub \tmp, \tmp, #(PAGE_SIZE + RESERVED_TTBR0_SIZE) + sub \tmp, \tmp, #(2 * PAGE_SIZE) orr \tmp, \tmp, #USER_ASID_FLAG msr ttbr1_el1, \tmp /* @@ -965,10 +955,9 @@ SYM_CODE_START(__sdei_asm_entry_trampoline) mov x4, xzr /* - * Use reg->interrupted_regs.addr_limit to remember whether to unmap - * the kernel on exit. + * Remember whether to unmap the kernel on exit. */ -1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)] +1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] #ifdef CONFIG_RANDOMIZE_BASE adr x4, tramp_vectors + PAGE_SIZE @@ -989,7 +978,7 @@ NOKPROBE(__sdei_asm_entry_trampoline) * x4: struct sdei_registered_event argument from registration time. */ SYM_CODE_START(__sdei_asm_exit_trampoline) - ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_ORIG_ADDR_LIMIT)] + ldr x4, [x4, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] cbnz x4, 1f tramp_unmap_kernel tmp=x4 @@ -1063,9 +1052,9 @@ SYM_CODE_START(__sdei_asm_handler) #ifdef CONFIG_SHADOW_CALL_STACK /* Use a separate shadow call stack for normal and critical events */ cbnz w4, 3f - adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal, tmp=x6 + ldr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_normal_ptr, tmp=x6 b 4f -3: adr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical, tmp=x6 +3: ldr_this_cpu dst=scs_sp, sym=sdei_shadow_call_stack_critical_ptr, tmp=x6 4: #endif diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index d8d9caf02834..f2eb206920a2 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -58,21 +58,11 @@ * in the entry routines. */ __HEAD -_head: /* * DO NOT MODIFY. Image header expected by Linux boot-loaders. */ -#ifdef CONFIG_EFI - /* - * This add instruction has no meaningful effect except that - * its opcode forms the magic "MZ" signature required by UEFI. - */ - add x13, x18, #0x16 - b primary_entry -#else + efi_signature_nop // special NOP to identity as PE/COFF executable b primary_entry // branch to kernel start, magic - .long 0 // reserved -#endif .quad 0 // Image load offset from start of RAM, little-endian le64sym _kernel_size_le // Effective size of kernel image, little-endian le64sym _kernel_flags_le // Informative flags, little-endian @@ -80,14 +70,9 @@ _head: .quad 0 // reserved .quad 0 // reserved .ascii ARM64_IMAGE_MAGIC // Magic number -#ifdef CONFIG_EFI - .long pe_header - _head // Offset to the PE header. + .long .Lpe_header_offset // Offset to the PE header. -pe_header: __EFI_PE_HEADER -#else - .long 0 // reserved -#endif __INIT @@ -104,7 +89,7 @@ pe_header: */ SYM_CODE_START(primary_entry) bl preserve_boot_args - bl el2_setup // Drop to EL1, w0=cpu_boot_mode + bl init_kernel_el // w0=cpu_boot_mode adrp x23, __PHYS_OFFSET and x23, x23, MIN_KIMG_ALIGN - 1 // KASLR offset, defaults to 0 bl set_cpu_boot_mode_flag @@ -482,24 +467,33 @@ EXPORT_SYMBOL(kimage_vaddr) .section ".idmap.text","awx" /* - * If we're fortunate enough to boot at EL2, ensure that the world is - * sane before dropping to EL1. + * Starting from EL2 or EL1, configure the CPU to execute at the highest + * reachable EL supported by the kernel in a chosen default state. If dropping + * from EL2 to EL1, configure EL2 before configuring EL1. + * + * Since we cannot always rely on ERET synchronizing writes to sysregs (e.g. if + * SCTLR_ELx.EOS is clear), we place an ISB prior to ERET. * * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in w0 if * booted in EL1 or EL2 respectively. */ -SYM_FUNC_START(el2_setup) - msr SPsel, #1 // We want to use SP_EL{1,2} +SYM_FUNC_START(init_kernel_el) mrs x0, CurrentEL cmp x0, #CurrentEL_EL2 - b.eq 1f - mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1) + b.eq init_el2 + +SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) + mov_q x0, INIT_SCTLR_EL1_MMU_OFF msr sctlr_el1, x0 - mov w0, #BOOT_CPU_MODE_EL1 // This cpu booted in EL1 isb - ret + mov_q x0, INIT_PSTATE_EL1 + msr spsr_el1, x0 + msr elr_el1, lr + mov w0, #BOOT_CPU_MODE_EL1 + eret -1: mov_q x0, (SCTLR_EL2_RES1 | ENDIAN_SET_EL2) +SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) + mov_q x0, INIT_SCTLR_EL2_MMU_OFF msr sctlr_el2, x0 #ifdef CONFIG_ARM64_VHE @@ -608,9 +602,12 @@ set_hcr: cbz x2, install_el2_stub - mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 isb - ret + mov_q x0, INIT_PSTATE_EL2 + msr spsr_el2, x0 + msr elr_el2, lr + mov w0, #BOOT_CPU_MODE_EL2 + eret SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) /* @@ -620,7 +617,7 @@ SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) * requires no configuration, and all non-hyp-specific EL2 setup * will be done via the _EL1 system register aliases in __cpu_setup. */ - mov_q x0, (SCTLR_EL1_RES1 | ENDIAN_SET_EL1) + mov_q x0, INIT_SCTLR_EL1_MMU_OFF msr sctlr_el1, x0 /* Coprocessor traps. */ @@ -642,14 +639,13 @@ SYM_INNER_LABEL(install_el2_stub, SYM_L_LOCAL) 7: adr_l x0, __hyp_stub_vectors msr vbar_el2, x0 - /* spsr */ - mov x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ - PSR_MODE_EL1h) + isb + mov x0, #INIT_PSTATE_EL1 msr spsr_el2, x0 msr elr_el2, lr - mov w0, #BOOT_CPU_MODE_EL2 // This CPU booted in EL2 + mov w0, #BOOT_CPU_MODE_EL2 eret -SYM_FUNC_END(el2_setup) +SYM_FUNC_END(init_kernel_el) /* * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed @@ -699,7 +695,7 @@ SYM_DATA_END(__early_cpu_boot_status) * cores are held until we're ready for them to initialise. */ SYM_FUNC_START(secondary_holding_pen) - bl el2_setup // Drop to EL1, w0=cpu_boot_mode + bl init_kernel_el // w0=cpu_boot_mode bl set_cpu_boot_mode_flag mrs x0, mpidr_el1 mov_q x1, MPIDR_HWID_BITMASK @@ -717,7 +713,7 @@ SYM_FUNC_END(secondary_holding_pen) * be used where CPUs are brought online dynamically by the kernel. */ SYM_FUNC_START(secondary_entry) - bl el2_setup // Drop to EL1 + bl init_kernel_el // w0=cpu_boot_mode bl set_cpu_boot_mode_flag b secondary_startup SYM_FUNC_END(secondary_entry) diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 61684a500914..c615b285ff5b 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -87,7 +87,6 @@ KVM_NVHE_ALIAS(__icache_flags); /* Kernel symbols needed for cpus_have_final/const_caps checks. */ KVM_NVHE_ALIAS(arm64_const_caps_ready); KVM_NVHE_ALIAS(cpu_hwcap_keys); -KVM_NVHE_ALIAS(cpu_hwcaps); /* Static keys which are set if a vGIC trap should be handled in hyp. */ KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 60456a62da11..dfb1feab867d 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -17,6 +17,7 @@ #include <linux/init.h> #include <linux/irqchip.h> #include <linux/kprobes.h> +#include <linux/scs.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> @@ -27,6 +28,25 @@ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); + +DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); + +#ifdef CONFIG_SHADOW_CALL_STACK +DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); +#endif + +static void init_irq_scs(void) +{ + int cpu; + + if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK)) + return; + + for_each_possible_cpu(cpu) + per_cpu(irq_shadow_call_stack_ptr, cpu) = + scs_alloc(cpu_to_node(cpu)); +} + #ifdef CONFIG_VMAP_STACK static void init_irq_stacks(void) { @@ -54,6 +74,7 @@ static void init_irq_stacks(void) void __init init_IRQ(void) { init_irq_stacks(); + init_irq_scs(); irqchip_init(); if (!handle_arch_irq) panic("No interrupt controller found."); diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index b181e0544b79..0921aa1520b0 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -50,10 +50,16 @@ static __init u64 get_kaslr_seed(void *fdt) return ret; } -static __init const u8 *kaslr_get_cmdline(void *fdt) +static __init bool cmdline_contains_nokaslr(const u8 *cmdline) { - static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE; + const u8 *str; + str = strstr(cmdline, "nokaslr"); + return str == cmdline || (str > cmdline && *(str - 1) == ' '); +} + +static __init bool is_kaslr_disabled_cmdline(void *fdt) +{ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { int node; const u8 *prop; @@ -65,10 +71,17 @@ static __init const u8 *kaslr_get_cmdline(void *fdt) prop = fdt_getprop(fdt, node, "bootargs", NULL); if (!prop) goto out; - return prop; + + if (cmdline_contains_nokaslr(prop)) + return true; + + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND)) + goto out; + + return false; } out: - return default_cmdline; + return cmdline_contains_nokaslr(CONFIG_CMDLINE); } /* @@ -83,7 +96,6 @@ u64 __init kaslr_early_init(u64 dt_phys) { void *fdt; u64 seed, offset, mask, module_range; - const u8 *cmdline, *str; unsigned long raw; int size; @@ -115,9 +127,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * Check if 'nokaslr' appears on the command line, and * return 0 if that is the case. */ - cmdline = kaslr_get_cmdline(fdt); - str = strstr(cmdline, "nokaslr"); - if (str == cmdline || (str > cmdline && *(str - 1) == ' ')) { + if (is_kaslr_disabled_cmdline(fdt)) { kaslr_status = KASLR_DISABLED_CMDLINE; return 0; } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 3605f77ad4df..38bb07eff872 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,6 +23,8 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> +#include <linux/nmi.h> +#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1248,10 +1250,21 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { + int ret; + if (acpi_disabled) - return platform_driver_register(&armv8_pmu_driver); + ret = platform_driver_register(&armv8_pmu_driver); else - return arm_pmu_acpi_probe(armv8_pmuv3_init); + ret = arm_pmu_acpi_probe(armv8_pmuv3_init); + + /* + * Try to re-initialize lockup detector after PMU init in + * case PMU events are triggered via NMIs. + */ + if (ret == 0 && arm_pmu_irq_is_nmi()) + lockup_detector_init(); + + return ret; } device_initcall(armv8_pmu_driver_init) @@ -1309,3 +1322,27 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } + +#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF +/* + * Safe maximum CPU frequency in case a particular platform doesn't implement + * cpufreq driver. Although, architecture doesn't put any restrictions on + * maximum frequency but 5 GHz seems to be safe maximum given the available + * Arm CPUs in the market which are clocked much less than 5 GHz. On the other + * hand, we can't make it much higher as it would lead to a large hard-lockup + * detection timeout on parts which are running slower (eg. 1GHz on + * Developerbox) and doesn't possess a cpufreq driver. + */ +#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz +u64 hw_nmi_get_sample_period(int watchdog_thresh) +{ + unsigned int cpu = smp_processor_id(); + unsigned long max_cpu_freq; + + max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; + if (!max_cpu_freq) + max_cpu_freq = SAFE_MAX_CPU_FREQ; + + return (u64)max_cpu_freq * watchdog_thresh; +} +#endif diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index f11a1a1f7026..89c64ada8732 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -34,7 +34,7 @@ DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes -post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); +post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *); static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { @@ -68,7 +68,7 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) p->ainsn.api.handler((u32)p->opcode, (long)p->addr, regs); /* single step simulated, now go for post processing */ - post_kprobe_handler(kcb, regs); + post_kprobe_handler(p, kcb, regs); } int __kprobes arch_prepare_kprobe(struct kprobe *p) @@ -177,19 +177,6 @@ static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, regs->pstate |= kcb->saved_irqflag; } -static void __kprobes -set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr) -{ - kcb->ss_ctx.ss_pending = true; - kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t); -} - -static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb) -{ - kcb->ss_ctx.ss_pending = false; - kcb->ss_ctx.match_addr = 0; -} - static void __kprobes setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) @@ -209,7 +196,6 @@ static void __kprobes setup_singlestep(struct kprobe *p, /* prepare for single stepping */ slot = (unsigned long)p->ainsn.api.insn; - set_ss_context(kcb, slot); /* mark pending ss */ kprobes_save_local_irqflag(kcb, regs); instruction_pointer_set(regs, slot); } else { @@ -243,13 +229,8 @@ static int __kprobes reenter_kprobe(struct kprobe *p, } static void __kprobes -post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) +post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs) { - struct kprobe *cur = kprobe_running(); - - if (!cur) - return; - /* return addr restore if non-branching insn */ if (cur->ainsn.api.restore != 0) instruction_pointer_set(regs, cur->ainsn.api.restore); @@ -365,32 +346,22 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) } static int __kprobes -kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) -{ - if ((kcb->ss_ctx.ss_pending) - && (kcb->ss_ctx.match_addr == addr)) { - clear_ss_context(kcb); /* clear pending ss */ - return DBG_HOOK_HANDLED; - } - /* not ours, kprobes should ignore it */ - return DBG_HOOK_ERROR; -} - -static int __kprobes kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - int retval; - - /* return error if this is not our step */ - retval = kprobe_ss_hit(kcb, instruction_pointer(regs)); + unsigned long addr = instruction_pointer(regs); + struct kprobe *cur = kprobe_running(); - if (retval == DBG_HOOK_HANDLED) { + if (cur && (kcb->kprobe_status == KPROBE_HIT_SS) + && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { kprobes_restore_local_irqflag(kcb, regs); - post_kprobe_handler(kcb, regs); + post_kprobe_handler(cur, kcb, regs); + + return DBG_HOOK_HANDLED; } - return retval; + /* not ours, kprobes should ignore it */ + return DBG_HOOK_ERROR; } static struct break_hook kprobes_break_ss_hook = { diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 0c65a91f8f53..3834cfafbbc2 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -422,16 +422,15 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, if (clone_flags & CLONE_SETTLS) p->thread.uw.tp_value = tls; } else { + /* + * A kthread has no context to ERET to, so ensure any buggy + * ERET is treated as an illegal exception return. + * + * When a user task is created from a kthread, childregs will + * be initialized by start_thread() or start_compat_thread(). + */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->pstate = PSR_MODE_EL1h; - if (IS_ENABLED(CONFIG_ARM64_UAO) && - cpus_have_const_cap(ARM64_HAS_UAO)) - childregs->pstate |= PSR_UAO_BIT; - - spectre_v4_enable_task_mitigation(p); - - if (system_uses_irq_prio_masking()) - childregs->pmr_save = GIC_PRIO_IRQON; + childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT; p->thread.cpu_context.x19 = stack_start; p->thread.cpu_context.x20 = stk_sz; @@ -461,17 +460,6 @@ static void tls_thread_switch(struct task_struct *next) write_sysreg(*task_user_tls(next), tpidr_el0); } -/* Restore the UAO state depending on next's addr_limit */ -void uao_thread_switch(struct task_struct *next) -{ - if (IS_ENABLED(CONFIG_ARM64_UAO)) { - if (task_thread_info(next)->addr_limit == KERNEL_DS) - asm(ALTERNATIVE("nop", SET_PSTATE_UAO(1), ARM64_HAS_UAO)); - else - asm(ALTERNATIVE("nop", SET_PSTATE_UAO(0), ARM64_HAS_UAO)); - } -} - /* * Force SSBS state on context-switch, since it may be lost after migrating * from a CPU which treats the bit as RES0 in a heterogeneous system. @@ -554,7 +542,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, hw_breakpoint_thread_switch(next); contextidr_thread_switch(next); entry_task_switch(next); - uao_thread_switch(next); ssbs_thread_switch(next); erratum_1418040_thread_switch(prev, next); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index f6e4e3737405..4c25c008504f 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -24,6 +24,7 @@ #include <linux/prctl.h> #include <linux/sched/task_stack.h> +#include <asm/insn.h> #include <asm/spectre.h> #include <asm/traps.h> @@ -538,12 +539,12 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) if (spectre_v4_mitigations_off()) { sysreg_clear_set(sctlr_el1, 0, SCTLR_ELx_DSSBS); - asm volatile(SET_PSTATE_SSBS(1)); + set_pstate_ssbs(1); return SPECTRE_VULNERABLE; } /* SCTLR_EL1.DSSBS was initialised to 0 during boot */ - asm volatile(SET_PSTATE_SSBS(0)); + set_pstate_ssbs(0); return SPECTRE_MITIGATED; } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index f49b349e16a3..8ac487c84e37 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -192,14 +192,11 @@ static void ptrace_hbptriggered(struct perf_event *bp, break; } } - arm64_force_sig_ptrace_errno_trap(si_errno, - (void __user *)bkpt->trigger, + arm64_force_sig_ptrace_errno_trap(si_errno, bkpt->trigger, desc); } #endif - arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, - (void __user *)(bkpt->trigger), - desc); + arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } /* diff --git a/arch/arm64/kernel/scs.c b/arch/arm64/kernel/scs.c deleted file mode 100644 index e8f7ff45dd8f..000000000000 --- a/arch/arm64/kernel/scs.c +++ /dev/null @@ -1,16 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Shadow Call Stack support. - * - * Copyright (C) 2019 Google LLC - */ - -#include <linux/percpu.h> -#include <linux/scs.h> - -DEFINE_SCS(irq_shadow_call_stack); - -#ifdef CONFIG_ARM_SDE_INTERFACE -DEFINE_SCS(sdei_shadow_call_stack_normal); -DEFINE_SCS(sdei_shadow_call_stack_critical); -#endif diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index 793c46d6a447..2c7ca449dd51 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -7,6 +7,7 @@ #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched/task_stack.h> +#include <linux/scs.h> #include <linux/uaccess.h> #include <asm/alternative.h> @@ -38,6 +39,14 @@ DEFINE_PER_CPU(unsigned long *, sdei_stack_normal_ptr); DEFINE_PER_CPU(unsigned long *, sdei_stack_critical_ptr); #endif +DECLARE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr); +DECLARE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr); + +#ifdef CONFIG_SHADOW_CALL_STACK +DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_normal_ptr); +DEFINE_PER_CPU(unsigned long *, sdei_shadow_call_stack_critical_ptr); +#endif + static void _free_sdei_stack(unsigned long * __percpu *ptr, int cpu) { unsigned long *p; @@ -53,6 +62,9 @@ static void free_sdei_stacks(void) { int cpu; + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + return; + for_each_possible_cpu(cpu) { _free_sdei_stack(&sdei_stack_normal_ptr, cpu); _free_sdei_stack(&sdei_stack_critical_ptr, cpu); @@ -76,6 +88,9 @@ static int init_sdei_stacks(void) int cpu; int err = 0; + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + return 0; + for_each_possible_cpu(cpu) { err = _init_sdei_stack(&sdei_stack_normal_ptr, cpu); if (err) @@ -91,6 +106,62 @@ static int init_sdei_stacks(void) return err; } +static void _free_sdei_scs(unsigned long * __percpu *ptr, int cpu) +{ + void *s; + + s = per_cpu(*ptr, cpu); + if (s) { + per_cpu(*ptr, cpu) = NULL; + scs_free(s); + } +} + +static void free_sdei_scs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + _free_sdei_scs(&sdei_shadow_call_stack_normal_ptr, cpu); + _free_sdei_scs(&sdei_shadow_call_stack_critical_ptr, cpu); + } +} + +static int _init_sdei_scs(unsigned long * __percpu *ptr, int cpu) +{ + void *s; + + s = scs_alloc(cpu_to_node(cpu)); + if (!s) + return -ENOMEM; + per_cpu(*ptr, cpu) = s; + + return 0; +} + +static int init_sdei_scs(void) +{ + int cpu; + int err = 0; + + if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK)) + return 0; + + for_each_possible_cpu(cpu) { + err = _init_sdei_scs(&sdei_shadow_call_stack_normal_ptr, cpu); + if (err) + break; + err = _init_sdei_scs(&sdei_shadow_call_stack_critical_ptr, cpu); + if (err) + break; + } + + if (err) + free_sdei_scs(); + + return err; +} + static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info) { unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr); @@ -131,13 +202,14 @@ unsigned long sdei_arch_get_entry_point(int conduit) */ if (is_hyp_mode_available() && !is_kernel_in_hyp_mode()) { pr_err("Not supported on this hardware/boot configuration\n"); - return 0; + goto out_err; } - if (IS_ENABLED(CONFIG_VMAP_STACK)) { - if (init_sdei_stacks()) - return 0; - } + if (init_sdei_stacks()) + goto out_err; + + if (init_sdei_scs()) + goto out_err_free_stacks; sdei_exit_mode = (conduit == SMCCC_CONDUIT_HVC) ? SDEI_EXIT_HVC : SDEI_EXIT_SMC; @@ -152,6 +224,10 @@ unsigned long sdei_arch_get_entry_point(int conduit) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ return (unsigned long)__sdei_asm_handler; +out_err_free_stacks: + free_sdei_stacks(); +out_err: + return 0; } /* @@ -179,12 +255,6 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, sdei_api_event_context(i, ®s->regs[i]); } - /* - * We didn't take an exception to get here, set PAN. UAO will be cleared - * by sdei_event_handler()s force_uaccess_begin() call. - */ - __uaccess_enable_hw_pan(); - err = sdei_event_handler(regs, arg); if (err) return SDEI_EV_FAILED; @@ -223,12 +293,39 @@ static __kprobes unsigned long _sdei_handler(struct pt_regs *regs, return vbar + 0x480; } +static void __kprobes notrace __sdei_pstate_entry(void) +{ + /* + * The original SDEI spec (ARM DEN 0054A) can be read ambiguously as to + * whether PSTATE bits are inherited unchanged or generated from + * scratch, and the TF-A implementation always clears PAN and always + * clears UAO. There are no other known implementations. + * + * Subsequent revisions (ARM DEN 0054B) follow the usual rules for how + * PSTATE is modified upon architectural exceptions, and so PAN is + * either inherited or set per SCTLR_ELx.SPAN, and UAO is always + * cleared. + * + * We must explicitly reset PAN to the expected state, including + * clearing it when the host isn't using it, in case a VM had it set. + */ + if (system_uses_hw_pan()) + set_pstate_pan(1); + else if (cpu_has_pan()) + set_pstate_pan(0); +} asmlinkage noinstr unsigned long __sdei_handler(struct pt_regs *regs, struct sdei_registered_event *arg) { unsigned long ret; + /* + * We didn't take an exception to get here, so the HW hasn't + * set/cleared bits in PSTATE that we may rely on. Initialize PAN. + */ + __sdei_pstate_entry(); + arm64_enter_nmi(regs); ret = _sdei_handler(regs, arg); diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 133257ffd859..1a57a76e1cc2 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -206,7 +206,7 @@ static void __init request_standard_resources(void) unsigned long i = 0; size_t res_size; - kernel_code.start = __pa_symbol(_text); + kernel_code.start = __pa_symbol(_stext); kernel_code.end = __pa_symbol(__init_begin - 1); kernel_data.start = __pa_symbol(_sdata); kernel_data.end = __pa_symbol(_end - 1); @@ -283,7 +283,7 @@ u64 cpu_logical_map(int cpu) void __init __no_sanitize_address setup_arch(char **cmdline_p) { - init_mm.start_code = (unsigned long) _text; + init_mm.start_code = (unsigned long) _stext; init_mm.end_code = (unsigned long) _etext; init_mm.end_data = (unsigned long) _edata; init_mm.brk = (unsigned long) _end; @@ -366,7 +366,7 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) * faults in case uaccess_enable() is inadvertently called by the init * thread. */ - init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page); + init_task.thread_info.ttbr0 = __pa_symbol(reserved_pg_dir); #endif if (boot_args[1] || boot_args[2] || boot_args[3]) { diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index a8184cad8890..af5c6c6638f7 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -922,9 +922,6 @@ asmlinkage void do_notify_resume(struct pt_regs *regs, trace_hardirqs_off(); do { - /* Check valid user FS if needed */ - addr_limit_user_check(); - if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index ba40d57757d6..4be7f7eed875 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -99,7 +99,7 @@ SYM_FUNC_END(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" SYM_CODE_START(cpu_resume) - bl el2_setup // if in EL2 drop to EL1 cleanly + bl init_kernel_el bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 18e9727d3f64..2499b895efea 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -787,14 +787,13 @@ void __init smp_prepare_cpus(unsigned int max_cpus) } static const char *ipi_types[NR_IPI] __tracepoint_string = { -#define S(x,s) [x] = s - 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"), + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_WAKEUP] = "CPU wake-up interrupts", }; static void smp_cross_call(const struct cpumask *target, unsigned int ipinr); diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 96cd347c7a46..a67b37a7a47e 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -58,7 +58,6 @@ void notrace __cpu_suspend_exit(void) * features that might not have been set correctly. */ __uaccess_enable_hw_pan(); - uao_thread_switch(current); /* * Restore HW breakpoint registers to sane values diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 3c18c2454089..265fe3eb1069 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -68,7 +68,7 @@ do_compat_cache_op(unsigned long start, unsigned long end, int flags) */ long compat_arm_syscall(struct pt_regs *regs, int scno) { - void __user *addr; + unsigned long addr; switch (scno) { /* @@ -111,8 +111,7 @@ long compat_arm_syscall(struct pt_regs *regs, int scno) break; } - addr = (void __user *)instruction_pointer(regs) - - (compat_thumb_mode(regs) ? 2 : 4); + addr = instruction_pointer(regs) - (compat_thumb_mode(regs) ? 2 : 4); arm64_notify_die("Oops - bad compat syscall(2)", regs, SIGILL, ILL_ILLTRP, addr, scno); diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f8f758e4a306..f61e9d8cc55a 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -122,7 +122,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, cortex_a76_erratum_1463225_svc_handler(); local_daif_restore(DAIF_PROCCTX); - if (system_supports_mte() && (flags & _TIF_MTE_ASYNC_FAULT)) { + if (flags & _TIF_MTE_ASYNC_FAULT) { /* * Process the asynchronous tag check fault before the actual * syscall. do_notify_resume() will send a signal to userspace diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 543c67cae02f..b8026ec684ba 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -124,6 +124,12 @@ int __init parse_acpi_topology(void) #endif #ifdef CONFIG_ARM64_AMU_EXTN +#define read_corecnt() read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0) +#define read_constcnt() read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0) +#else +#define read_corecnt() (0UL) +#define read_constcnt() (0UL) +#endif #undef pr_fmt #define pr_fmt(fmt) "AMU: " fmt @@ -133,54 +139,58 @@ static DEFINE_PER_CPU(u64, arch_const_cycles_prev); static DEFINE_PER_CPU(u64, arch_core_cycles_prev); static cpumask_var_t amu_fie_cpus; -/* Initialize counter reference per-cpu variables for the current CPU */ -void init_cpu_freq_invariance_counters(void) +void update_freq_counters_refs(void) { - this_cpu_write(arch_core_cycles_prev, - read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0)); - this_cpu_write(arch_const_cycles_prev, - read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0)); + this_cpu_write(arch_core_cycles_prev, read_corecnt()); + this_cpu_write(arch_const_cycles_prev, read_constcnt()); } -static int validate_cpu_freq_invariance_counters(int cpu) +static inline bool freq_counters_valid(int cpu) { - u64 max_freq_hz, ratio; + if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask)) + return false; if (!cpu_has_amu_feat(cpu)) { pr_debug("CPU%d: counters are not supported.\n", cpu); - return -EINVAL; + return false; } if (unlikely(!per_cpu(arch_const_cycles_prev, cpu) || !per_cpu(arch_core_cycles_prev, cpu))) { pr_debug("CPU%d: cycle counters are not enabled.\n", cpu); - return -EINVAL; + return false; } - /* Convert maximum frequency from KHz to Hz and validate */ - max_freq_hz = cpufreq_get_hw_max_freq(cpu) * 1000; - if (unlikely(!max_freq_hz)) { - pr_debug("CPU%d: invalid maximum frequency.\n", cpu); + return true; +} + +static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) +{ + u64 ratio; + + if (unlikely(!max_rate || !ref_rate)) { + pr_debug("CPU%d: invalid maximum or reference frequency.\n", + cpu); return -EINVAL; } /* * Pre-compute the fixed ratio between the frequency of the constant - * counter and the maximum frequency of the CPU. + * reference counter and the maximum frequency of the CPU. * - * const_freq - * arch_max_freq_scale = ---------------- * SCHED_CAPACITY_SCALE² - * cpuinfo_max_freq + * ref_rate + * arch_max_freq_scale = ---------- * SCHED_CAPACITY_SCALE² + * max_rate * * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE² * in order to ensure a good resolution for arch_max_freq_scale for - * very low arch timer frequencies (down to the KHz range which should + * very low reference frequencies (down to the KHz range which should * be unlikely). */ - ratio = (u64)arch_timer_get_rate() << (2 * SCHED_CAPACITY_SHIFT); - ratio = div64_u64(ratio, max_freq_hz); + ratio = ref_rate << (2 * SCHED_CAPACITY_SHIFT); + ratio = div64_u64(ratio, max_rate); if (!ratio) { - WARN_ONCE(1, "System timer frequency too low.\n"); + WARN_ONCE(1, "Reference frequency too low.\n"); return -EINVAL; } @@ -227,8 +237,12 @@ static int __init init_amu_fie(void) } for_each_present_cpu(cpu) { - if (validate_cpu_freq_invariance_counters(cpu)) + if (!freq_counters_valid(cpu) || + freq_inv_set_max_ratio(cpu, + cpufreq_get_hw_max_freq(cpu) * 1000, + arch_timer_get_rate())) continue; + cpumask_set_cpu(cpu, valid_cpus); have_policy |= enable_policy_freq_counters(cpu, valid_cpus); } @@ -280,11 +294,14 @@ void topology_scale_freq_tick(void) if (!cpumask_test_cpu(cpu, amu_fie_cpus)) return; - const_cnt = read_sysreg_s(SYS_AMEVCNTR0_CONST_EL0); - core_cnt = read_sysreg_s(SYS_AMEVCNTR0_CORE_EL0); prev_const_cnt = this_cpu_read(arch_const_cycles_prev); prev_core_cnt = this_cpu_read(arch_core_cycles_prev); + update_freq_counters_refs(); + + const_cnt = this_cpu_read(arch_const_cycles_prev); + core_cnt = this_cpu_read(arch_core_cycles_prev); + if (unlikely(core_cnt <= prev_core_cnt || const_cnt <= prev_const_cnt)) goto store_and_exit; @@ -309,4 +326,71 @@ store_and_exit: this_cpu_write(arch_core_cycles_prev, core_cnt); this_cpu_write(arch_const_cycles_prev, const_cnt); } -#endif /* CONFIG_ARM64_AMU_EXTN */ + +#ifdef CONFIG_ACPI_CPPC_LIB +#include <acpi/cppc_acpi.h> + +static void cpu_read_corecnt(void *val) +{ + *(u64 *)val = read_corecnt(); +} + +static void cpu_read_constcnt(void *val) +{ + *(u64 *)val = read_constcnt(); +} + +static inline +int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val) +{ + /* + * Abort call on counterless CPU or when interrupts are + * disabled - can lead to deadlock in smp sync call. + */ + if (!cpu_has_amu_feat(cpu)) + return -EOPNOTSUPP; + + if (WARN_ON_ONCE(irqs_disabled())) + return -EPERM; + + smp_call_function_single(cpu, func, val, 1); + + return 0; +} + +/* + * Refer to drivers/acpi/cppc_acpi.c for the description of the functions + * below. + */ +bool cpc_ffh_supported(void) +{ + return freq_counters_valid(get_cpu_with_amu_feat()); +} + +int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val) +{ + int ret = -EOPNOTSUPP; + + switch ((u64)reg->address) { + case 0x0: + ret = counters_read_on_cpu(cpu, cpu_read_corecnt, val); + break; + case 0x1: + ret = counters_read_on_cpu(cpu, cpu_read_constcnt, val); + break; + } + + if (!ret) { + *val &= GENMASK_ULL(reg->bit_offset + reg->bit_width - 1, + reg->bit_offset); + *val >>= reg->bit_offset; + } + + return ret; +} + +int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val) +{ + return -EOPNOTSUPP; +} +#endif /* CONFIG_ACPI_CPPC_LIB */ diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 2059d8f43f55..08156be75569 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -171,32 +171,32 @@ static void arm64_show_signal(int signo, const char *str) __show_regs(regs); } -void arm64_force_sig_fault(int signo, int code, void __user *addr, +void arm64_force_sig_fault(int signo, int code, unsigned long far, const char *str) { arm64_show_signal(signo, str); if (signo == SIGKILL) force_sig(SIGKILL); else - force_sig_fault(signo, code, addr); + force_sig_fault(signo, code, (void __user *)far); } -void arm64_force_sig_mceerr(int code, void __user *addr, short lsb, +void arm64_force_sig_mceerr(int code, unsigned long far, short lsb, const char *str) { arm64_show_signal(SIGBUS, str); - force_sig_mceerr(code, addr, lsb); + force_sig_mceerr(code, (void __user *)far, lsb); } -void arm64_force_sig_ptrace_errno_trap(int errno, void __user *addr, +void arm64_force_sig_ptrace_errno_trap(int errno, unsigned long far, const char *str) { arm64_show_signal(SIGTRAP, str); - force_sig_ptrace_errno_trap(errno, addr); + force_sig_ptrace_errno_trap(errno, (void __user *)far); } void arm64_notify_die(const char *str, struct pt_regs *regs, - int signo, int sicode, void __user *addr, + int signo, int sicode, unsigned long far, int err) { if (user_mode(regs)) { @@ -204,7 +204,7 @@ void arm64_notify_die(const char *str, struct pt_regs *regs, current->thread.fault_address = 0; current->thread.fault_code = err; - arm64_force_sig_fault(signo, sicode, addr, str); + arm64_force_sig_fault(signo, sicode, far, str); } else { die(str, regs, err); } @@ -375,7 +375,7 @@ void force_signal_inject(int signal, int code, unsigned long address, unsigned i signal = SIGKILL; } - arm64_notify_die(desc, regs, signal, code, (void __user *)address, err); + arm64_notify_die(desc, regs, signal, code, address, err); } /* @@ -386,7 +386,7 @@ void arm64_notify_segfault(unsigned long addr) int code; mmap_read_lock(current->mm); - if (find_vma(current->mm, addr) == NULL) + if (find_vma(current->mm, untagged_addr(addr)) == NULL) code = SEGV_MAPERR; else code = SEGV_ACCERR; @@ -449,12 +449,13 @@ NOKPROBE_SYMBOL(do_ptrauth_fault); static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) { - unsigned long address; + unsigned long tagged_address, address; int rt = ESR_ELx_SYS64_ISS_RT(esr); int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; int ret = 0; - address = untagged_addr(pt_regs_read_reg(regs, rt)); + tagged_address = pt_regs_read_reg(regs, rt); + address = untagged_addr(tagged_address); switch (crm) { case ESR_ELx_SYS64_ISS_CRM_DC_CVAU: /* DC CVAU, gets promoted */ @@ -481,7 +482,7 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs) } if (ret) - arm64_notify_segfault(address); + arm64_notify_segfault(tagged_address); else arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE); } @@ -775,7 +776,7 @@ asmlinkage void notrace bad_mode(struct pt_regs *regs, int reason, unsigned int */ void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr) { - void __user *pc = (void __user *)instruction_pointer(regs); + unsigned long pc = instruction_pointer(regs); current->thread.fault_address = 0; current->thread.fault_code = esr; diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index d65f52264aba..a8f8e409e2bf 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -28,7 +28,7 @@ ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 -ccflags-y += -DDISABLE_BRANCH_PROFILING +ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS) KASAN_SANITIZE := n diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 79280c53b9a6..a1e0f91e6cea 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -48,7 +48,7 @@ cc32-as-instr = $(call try-run,\ # As a result we set our own flags here. # KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile -VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include) +VDSO_CPPFLAGS := -DBUILD_VDSO -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include) VDSO_CPPFLAGS += $(LINUXINCLUDE) # Common C and assembly flags diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 1bda604f4c70..5d5857c5b025 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -121,7 +121,7 @@ SECTIONS _text = .; HEAD_TEXT } - .text : { /* Real text segment */ + .text : ALIGN(SEGMENT_ALIGN) { /* Real text segment */ _stext = .; /* Text and read-only data */ IRQENTRY_TEXT SOFTIRQENTRY_TEXT @@ -164,13 +164,11 @@ SECTIONS . += PAGE_SIZE; #endif -#ifdef CONFIG_ARM64_SW_TTBR0_PAN - reserved_ttbr0 = .; - . += RESERVED_TTBR0_SIZE; -#endif + reserved_pg_dir = .; + . += PAGE_SIZE; + swapper_pg_dir = .; . += PAGE_SIZE; - swapper_pg_end = .; . = ALIGN(SEGMENT_ALIGN); __init_begin = .; @@ -201,7 +199,7 @@ SECTIONS INIT_CALLS CON_INITCALL INIT_RAM_FS - *(.init.rodata.* .init.bss) /* from the EFI stub */ + *(.init.altinstructions .init.bss) /* from the EFI stub */ } .exit.data : { EXIT_DATA diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 8f8fca47abfc..5750ec34960e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -808,6 +808,25 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) preempt_enable(); + /* + * The ARMv8 architecture doesn't give the hypervisor + * a mechanism to prevent a guest from dropping to AArch32 EL0 + * if implemented by the CPU. If we spot the guest in such + * state and that we decided it wasn't supposed to do so (like + * with the asymmetric AArch32 case), return to userspace with + * a fatal error. + */ + if (!system_supports_32bit_el0() && vcpu_mode_is_32bit(vcpu)) { + /* + * As we have caught the guest red-handed, decide that + * it isn't fit for purpose anymore by making the vcpu + * invalid. The VMM can try and fix it by issuing a + * KVM_ARM_VCPU_INIT if it really wants to. + */ + vcpu->arch.target = -1; + ret = ARM_EXCEPTION_IL; + } + ret = handle_exit(vcpu, ret); } diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index ff9a0f547b9f..ed27f06a31ba 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -17,8 +17,6 @@ SYM_FUNC_START(__host_exit) get_host_ctxt x0, x1 - ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN) - /* Store the host regs x2 and x3 */ stp x2, x3, [x0, #CPU_XREG_OFFSET(2)] diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 47224dc62c51..b11a9d7db677 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -57,16 +57,25 @@ __do_hyp_init: cmp x0, #HVC_STUB_HCALL_NR b.lo __kvm_handle_stub_hvc - /* Set tpidr_el2 for use by HYP to free a register */ - msr tpidr_el2, x2 - - mov x2, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) - cmp x0, x2 - b.eq 1f + // We only actively check bits [24:31], and everything + // else has to be zero, which we check at build time. +#if (KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) & 0xFFFFFFFF00FFFFFF) +#error Unexpected __KVM_HOST_SMCCC_FUNC___kvm_hyp_init value +#endif + + ror x0, x0, #24 + eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 24) & 0xF) + ror x0, x0, #4 + eor x0, x0, #((KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) >> 28) & 0xF) + cbz x0, 1f mov x0, #SMCCC_RET_NOT_SUPPORTED eret -1: phys_to_ttbr x0, x1 +1: + /* Set tpidr_el2 for use by HYP to free a register */ + msr tpidr_el2, x2 + + phys_to_ttbr x0, x1 alternative_if ARM64_HAS_CNP orr x0, x0, #TTBR_CNP_BIT alternative_else_nop_endif diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 39ca71ab8866..fbde89a2c6e8 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -128,7 +128,6 @@ void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu) struct tlb_inv_context cxt; /* Switch to requested VMID */ - mmu = kern_hyp_va(mmu); __tlb_switch_to_guest(mmu, &cxt); __tlbi(vmalle1); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 0cdf6e461cbd..0271b4a3b9fe 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -635,7 +635,7 @@ static void stage2_flush_dcache(void *addr, u64 size) static bool stage2_pte_cacheable(kvm_pte_t pte) { - u64 memattr = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR, pte); + u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR; return memattr == PAGE_S2_MEMATTR(NORMAL); } @@ -846,7 +846,7 @@ int kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm *kvm) u32 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; - pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL | __GFP_ZERO); + pgt->pgd = alloc_pages_exact(pgd_sz, GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!pgt->pgd) return -ENOMEM; diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 19aacc7d64de..1a01da9fdc99 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -787,14 +787,28 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_shift = PAGE_SHIFT; } - if (vma_shift == PUD_SHIFT && - !fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) - vma_shift = PMD_SHIFT; - - if (vma_shift == PMD_SHIFT && - !fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) { - force_pte = true; + switch (vma_shift) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SHIFT: + if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE)) + break; + fallthrough; +#endif + case CONT_PMD_SHIFT: + vma_shift = PMD_SHIFT; + fallthrough; + case PMD_SHIFT: + if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) + break; + fallthrough; + case CONT_PTE_SHIFT: vma_shift = PAGE_SHIFT; + force_pte = true; + fallthrough; + case PAGE_SHIFT: + break; + default: + WARN_ONCE(1, "Unknown vma_shift %d", vma_shift); } vma_pagesize = 1UL << vma_shift; @@ -839,6 +853,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (kvm_is_device_pfn(pfn)) { device = true; + force_pte = true; } else if (logging_active && !write_fault) { /* * Only actually map the page as writable if this was a write diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 41348a7781d9..fb12d3ef423a 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1897,9 +1897,9 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 1), Op2( 0), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(1), /* DBGDCCINT */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 0), trap_debug32, NULL, cp14_DBGDCCINT }, /* DBGDSCRext */ - { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 2), Op2( 2), trap_debug32, NULL, cp14_DBGDSCRext }, DBG_BCR_BVR_WCR_WVR(2), /* DBGDTR[RT]Xint */ { Op1( 0), CRn( 0), CRm( 3), Op2( 0), trap_raz_wi }, @@ -1914,7 +1914,7 @@ static const struct sys_reg_desc cp14_regs[] = { { Op1( 0), CRn( 0), CRm( 6), Op2( 2), trap_raz_wi }, DBG_BCR_BVR_WCR_WVR(6), /* DBGVCR */ - { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32 }, + { Op1( 0), CRn( 0), CRm( 7), Op2( 0), trap_debug32, NULL, cp14_DBGVCR }, DBG_BCR_BVR_WCR_WVR(7), DBG_BCR_BVR_WCR_WVR(8), DBG_BCR_BVR_WCR_WVR(9), diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 48a3a26eff66..af9afcbec92c 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -24,20 +24,20 @@ SYM_FUNC_START(__arch_clear_user) subs x1, x1, #8 b.mi 2f 1: -uao_user_alternative 9f, str, sttr, xzr, x0, 8 +user_ldst 9f, sttr, xzr, x0, 8 subs x1, x1, #8 b.pl 1b 2: adds x1, x1, #4 b.mi 3f -uao_user_alternative 9f, str, sttr, wzr, x0, 4 +user_ldst 9f, sttr, wzr, x0, 4 sub x1, x1, #4 3: adds x1, x1, #2 b.mi 4f -uao_user_alternative 9f, strh, sttrh, wzr, x0, 2 +user_ldst 9f, sttrh, wzr, x0, 2 sub x1, x1, #2 4: adds x1, x1, #1 b.mi 5f -uao_user_alternative 9f, strb, sttrb, wzr, x0, 0 +user_ldst 9f, sttrb, wzr, x0, 0 5: mov x0, #0 ret SYM_FUNC_END(__arch_clear_user) diff --git a/arch/arm64/lib/copy_from_user.S b/arch/arm64/lib/copy_from_user.S index 0f8a3a9e3795..95cd62d67371 100644 --- a/arch/arm64/lib/copy_from_user.S +++ b/arch/arm64/lib/copy_from_user.S @@ -21,7 +21,7 @@ */ .macro ldrb1 reg, ptr, val - uao_user_alternative 9998f, ldrb, ldtrb, \reg, \ptr, \val + user_ldst 9998f, ldtrb, \reg, \ptr, \val .endm .macro strb1 reg, ptr, val @@ -29,7 +29,7 @@ .endm .macro ldrh1 reg, ptr, val - uao_user_alternative 9998f, ldrh, ldtrh, \reg, \ptr, \val + user_ldst 9998f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val @@ -37,7 +37,7 @@ .endm .macro ldr1 reg, ptr, val - uao_user_alternative 9998f, ldr, ldtr, \reg, \ptr, \val + user_ldst 9998f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val @@ -45,7 +45,7 @@ .endm .macro ldp1 reg1, reg2, ptr, val - uao_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9998f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val diff --git a/arch/arm64/lib/copy_in_user.S b/arch/arm64/lib/copy_in_user.S index 80e37ada0ee1..1f61cd0df062 100644 --- a/arch/arm64/lib/copy_in_user.S +++ b/arch/arm64/lib/copy_in_user.S @@ -22,35 +22,35 @@ * x0 - bytes not copied */ .macro ldrb1 reg, ptr, val - uao_user_alternative 9998f, ldrb, ldtrb, \reg, \ptr, \val + user_ldst 9998f, ldtrb, \reg, \ptr, \val .endm .macro strb1 reg, ptr, val - uao_user_alternative 9998f, strb, sttrb, \reg, \ptr, \val + user_ldst 9998f, sttrb, \reg, \ptr, \val .endm .macro ldrh1 reg, ptr, val - uao_user_alternative 9998f, ldrh, ldtrh, \reg, \ptr, \val + user_ldst 9998f, ldtrh, \reg, \ptr, \val .endm .macro strh1 reg, ptr, val - uao_user_alternative 9998f, strh, sttrh, \reg, \ptr, \val + user_ldst 9998f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val - uao_user_alternative 9998f, ldr, ldtr, \reg, \ptr, \val + user_ldst 9998f, ldtr, \reg, \ptr, \val .endm .macro str1 reg, ptr, val - uao_user_alternative 9998f, str, sttr, \reg, \ptr, \val + user_ldst 9998f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val - uao_ldp 9998f, \reg1, \reg2, \ptr, \val + user_ldp 9998f, \reg1, \reg2, \ptr, \val .endm .macro stp1 reg1, reg2, ptr, val - uao_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9998f, \reg1, \reg2, \ptr, \val .endm end .req x5 diff --git a/arch/arm64/lib/copy_to_user.S b/arch/arm64/lib/copy_to_user.S index 4ec59704b8f2..043da90f5dd7 100644 --- a/arch/arm64/lib/copy_to_user.S +++ b/arch/arm64/lib/copy_to_user.S @@ -24,7 +24,7 @@ .endm .macro strb1 reg, ptr, val - uao_user_alternative 9998f, strb, sttrb, \reg, \ptr, \val + user_ldst 9998f, sttrb, \reg, \ptr, \val .endm .macro ldrh1 reg, ptr, val @@ -32,7 +32,7 @@ .endm .macro strh1 reg, ptr, val - uao_user_alternative 9998f, strh, sttrh, \reg, \ptr, \val + user_ldst 9998f, sttrh, \reg, \ptr, \val .endm .macro ldr1 reg, ptr, val @@ -40,7 +40,7 @@ .endm .macro str1 reg, ptr, val - uao_user_alternative 9998f, str, sttr, \reg, \ptr, \val + user_ldst 9998f, sttr, \reg, \ptr, \val .endm .macro ldp1 reg1, reg2, ptr, val @@ -48,7 +48,7 @@ .endm .macro stp1 reg1, reg2, ptr, val - uao_stp 9998f, \reg1, \reg2, \ptr, \val + user_stp 9998f, \reg1, \reg2, \ptr, \val .endm end .req x5 diff --git a/arch/arm64/lib/mte.S b/arch/arm64/lib/mte.S index 03ca6d8b8670..351537c12f36 100644 --- a/arch/arm64/lib/mte.S +++ b/arch/arm64/lib/mte.S @@ -4,7 +4,7 @@ */ #include <linux/linkage.h> -#include <asm/alternative.h> +#include <asm/asm-uaccess.h> #include <asm/assembler.h> #include <asm/mte.h> #include <asm/page.h> @@ -67,7 +67,7 @@ SYM_FUNC_START(mte_copy_tags_from_user) mov x3, x1 cbz x2, 2f 1: - uao_user_alternative 2f, ldrb, ldtrb, w4, x1, 0 + user_ldst 2f, ldtrb, w4, x1, 0 lsl x4, x4, #MTE_TAG_SHIFT stg x4, [x0], #MTE_GRANULE_SIZE add x1, x1, #1 @@ -94,7 +94,7 @@ SYM_FUNC_START(mte_copy_tags_to_user) 1: ldg x4, [x1] ubfx x4, x4, #MTE_TAG_SHIFT, #MTE_TAG_SIZE - uao_user_alternative 2f, strb, sttrb, w4, x0, 0 + user_ldst 2f, sttrb, w4, x0, 0 add x0, x0, #1 add x1, x1, #MTE_GRANULE_SIZE subs x2, x2, #1 diff --git a/arch/arm64/lib/uaccess_flushcache.c b/arch/arm64/lib/uaccess_flushcache.c index bfa30b75b2b8..c83bb5a4aad2 100644 --- a/arch/arm64/lib/uaccess_flushcache.c +++ b/arch/arm64/lib/uaccess_flushcache.c @@ -30,9 +30,7 @@ unsigned long __copy_user_flushcache(void *to, const void __user *from, { unsigned long rc; - uaccess_enable_not_uao(); - rc = __arch_copy_from_user(to, from, n); - uaccess_disable_not_uao(); + rc = raw_copy_from_user(to, from, n); /* See above */ __clean_dcache_area_pop(to, n - rc); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 795d224f184f..2848952b178d 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -40,7 +40,7 @@ #include <asm/traps.h> struct fault_info { - int (*fn)(unsigned long addr, unsigned int esr, + int (*fn)(unsigned long far, unsigned int esr, struct pt_regs *regs); int sig; int code; @@ -385,8 +385,11 @@ static void set_thread_esr(unsigned long address, unsigned int esr) current->thread.fault_code = esr; } -static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static void do_bad_area(unsigned long far, unsigned int esr, + struct pt_regs *regs) { + unsigned long addr = untagged_addr(far); + /* * If we are in kernel mode at this point, we have no context to * handle this fault with. @@ -395,8 +398,7 @@ static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *re const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); - arm64_force_sig_fault(inf->sig, inf->code, (void __user *)addr, - inf->name); + arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } @@ -448,7 +450,7 @@ static bool is_write_abort(unsigned int esr) return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } -static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, +static int __kprobes do_page_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf; @@ -456,6 +458,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, vm_fault_t fault; unsigned long vm_flags = VM_ACCESS_FLAGS; unsigned int mm_flags = FAULT_FLAG_DEFAULT; + unsigned long addr = untagged_addr(far); if (kprobe_page_fault(regs, esr)) return 0; @@ -479,11 +482,6 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { - /* regs->orig_addr_limit may be 0 if we entered from EL0 */ - if (regs->orig_addr_limit == KERNEL_DS) - die_kernel_fault("access to user memory with fs=KERNEL_DS", - addr, esr, regs); - if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); @@ -567,8 +565,7 @@ retry: * We had some memory, but were unable to successfully fix up * this page fault. */ - arm64_force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)addr, - inf->name); + arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; @@ -576,8 +573,7 @@ retry: if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); - arm64_force_sig_mceerr(BUS_MCEERR_AR, (void __user *)addr, lsb, - inf->name); + arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* * Something tried to access memory that isn't in our memory @@ -585,8 +581,7 @@ retry: */ arm64_force_sig_fault(SIGSEGV, fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR, - (void __user *)addr, - inf->name); + far, inf->name); } return 0; @@ -596,33 +591,35 @@ no_context: return 0; } -static int __kprobes do_translation_fault(unsigned long addr, +static int __kprobes do_translation_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { + unsigned long addr = untagged_addr(far); + if (is_ttbr0_addr(addr)) - return do_page_fault(addr, esr, regs); + return do_page_fault(far, esr, regs); - do_bad_area(addr, esr, regs); + do_bad_area(far, esr, regs); return 0; } -static int do_alignment_fault(unsigned long addr, unsigned int esr, +static int do_alignment_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { - do_bad_area(addr, esr, regs); + do_bad_area(far, esr, regs); return 0; } -static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static int do_bad(unsigned long far, unsigned int esr, struct pt_regs *regs) { return 1; /* "fault" */ } -static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) +static int do_sea(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf; - void __user *siaddr; + unsigned long siaddr; inf = esr_to_fault_info(esr); @@ -634,19 +631,30 @@ static int do_sea(unsigned long addr, unsigned int esr, struct pt_regs *regs) return 0; } - if (esr & ESR_ELx_FnV) - siaddr = NULL; - else - siaddr = (void __user *)addr; + if (esr & ESR_ELx_FnV) { + siaddr = 0; + } else { + /* + * The architecture specifies that the tag bits of FAR_EL1 are + * UNKNOWN for synchronous external aborts. Mask them out now + * so that userspace doesn't see them. + */ + siaddr = untagged_addr(far); + } arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } -static int do_tag_check_fault(unsigned long addr, unsigned int esr, +static int do_tag_check_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { - do_bad_area(addr, esr, regs); + /* + * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag + * check faults. Mask them out now so that userspace doesn't see them. + */ + far &= (1UL << 60) - 1; + do_bad_area(far, esr, regs); return 0; } @@ -717,11 +725,12 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; -void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) +void do_mem_abort(unsigned long far, unsigned int esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); + unsigned long addr = untagged_addr(far); - if (!inf->fn(addr, esr, regs)) + if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) { @@ -730,8 +739,12 @@ void do_mem_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) show_pte(addr); } - arm64_notify_die(inf->name, regs, - inf->sig, inf->code, (void __user *)addr, esr); + /* + * At this point we have an unrecognized fault type whose tag bits may + * have been defined as UNKNOWN. Therefore we only expose the untagged + * address to the signal handler. + */ + arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); @@ -744,8 +757,8 @@ NOKPROBE_SYMBOL(do_el0_irq_bp_hardening); void do_sp_pc_abort(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - arm64_notify_die("SP/PC alignment exception", regs, - SIGBUS, BUS_ADRALN, (void __user *)addr, esr); + arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, + addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); @@ -846,8 +859,7 @@ void do_debug_exception(unsigned long addr_if_watchpoint, unsigned int esr, arm64_apply_bp_hardening(); if (inf->fn(addr_if_watchpoint, esr, regs)) { - arm64_notify_die(inf->name, regs, - inf->sig, inf->code, (void __user *)pc, esr); + arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr); } debug_exception_exit(regs); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 095540667f0f..fbd452e12397 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -29,6 +29,7 @@ #include <linux/kexec.h> #include <linux/crash_dump.h> #include <linux/hugetlb.h> +#include <linux/acpi_iort.h> #include <asm/boot.h> #include <asm/fixmap.h> @@ -42,8 +43,6 @@ #include <asm/tlb.h> #include <asm/alternative.h> -#define ARM64_ZONE_DMA_BITS 30 - /* * We need to be able to catch inadvertent references to memstart_addr * that occur (potentially in generic code) before arm64_memblock_init() @@ -175,21 +174,34 @@ static void __init reserve_elfcorehdr(void) #endif /* CONFIG_CRASH_DUMP */ /* - * Return the maximum physical address for a zone with a given address size - * limit. It currently assumes that for memory starting above 4G, 32-bit - * devices will use a DMA offset. + * Return the maximum physical address for a zone accessible by the given bits + * limit. If DRAM starts above 32-bit, expand the zone to the maximum + * available memory, otherwise cap it at 32-bit. */ static phys_addr_t __init max_zone_phys(unsigned int zone_bits) { - phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits); - return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM()); + phys_addr_t zone_mask = DMA_BIT_MASK(zone_bits); + phys_addr_t phys_start = memblock_start_of_DRAM(); + + if (phys_start > U32_MAX) + zone_mask = PHYS_ADDR_MAX; + else if (phys_start > zone_mask) + zone_mask = U32_MAX; + + return min(zone_mask, memblock_end_of_DRAM() - 1) + 1; } static void __init zone_sizes_init(unsigned long min, unsigned long max) { unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; + unsigned int __maybe_unused acpi_zone_dma_bits; + unsigned int __maybe_unused dt_zone_dma_bits; #ifdef CONFIG_ZONE_DMA + acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); + dt_zone_dma_bits = fls64(of_dma_get_max_cpu_address(NULL)); + zone_dma_bits = min3(32U, dt_zone_dma_bits, acpi_zone_dma_bits); + arm64_dma_phys_limit = max_zone_phys(zone_dma_bits); max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 @@ -269,7 +281,7 @@ static void __init fdt_enforce_memory_region(void) void __init arm64_memblock_init(void) { - const s64 linear_region_size = BIT(vabits_actual - 1); + const s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual); /* Handle linux,usable-memory-range property */ fdt_enforce_memory_region(); @@ -348,15 +360,18 @@ void __init arm64_memblock_init(void) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; - u64 range = linear_region_size - - (memblock_end_of_DRAM() - memblock_start_of_DRAM()); + u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + int parange = cpuid_feature_extract_unsigned_field( + mmfr0, ID_AA64MMFR0_PARANGE_SHIFT); + s64 range = linear_region_size - + BIT(id_aa64mmfr0_parange_to_phys_shift(parange)); /* * If the size of the linear region exceeds, by a sufficient - * margin, the size of the region that the available physical - * memory spans, randomize the linear region as well. + * margin, the size of the region that the physical memory can + * span, randomize the linear region as well. */ - if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) { + if (memstart_offset_seed > 0 && range >= (s64)ARM64_MEMSTART_ALIGN) { range /= ARM64_MEMSTART_ALIGN; memstart_addr -= ARM64_MEMSTART_ALIGN * ((range * memstart_offset_seed) >> 16); @@ -367,7 +382,7 @@ void __init arm64_memblock_init(void) * Register the kernel text, kernel data, initrd, and initial * pagetables with memblock. */ - memblock_reserve(__pa_symbol(_text), _end - _text); + memblock_reserve(__pa_symbol(_stext), _end - _stext); if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && phys_initrd_size) { /* the generic initrd code expects virtual addresses */ initrd_start = __phys_to_virt(phys_initrd_start); @@ -376,18 +391,11 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA)) { - zone_dma_bits = ARM64_ZONE_DMA_BITS; - arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS); - } - if (IS_ENABLED(CONFIG_ZONE_DMA32)) arm64_dma32_phys_limit = max_zone_phys(32); else arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_crashkernel(); - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; @@ -427,6 +435,12 @@ void __init bootmem_init(void) sparse_init(); zone_sizes_init(min, max); + /* + * request_standard_resources() depends on crashkernel's memory being + * reserved, so do it here. + */ + reserve_crashkernel(); + memblock_dump_all(); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index ca692a815731..ae0c3d023824 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -464,20 +464,35 @@ void __init mark_linear_text_alias_ro(void) /* * Remove the write permissions from the linear alias of .text/.rodata */ - update_mapping_prot(__pa_symbol(_text), (unsigned long)lm_alias(_text), - (unsigned long)__init_begin - (unsigned long)_text, + update_mapping_prot(__pa_symbol(_stext), (unsigned long)lm_alias(_stext), + (unsigned long)__init_begin - (unsigned long)_stext, PAGE_KERNEL_RO); } +static bool crash_mem_map __initdata; + +static int __init enable_crash_mem_map(char *arg) +{ + /* + * Proper parameter parsing is done by reserve_crashkernel(). We only + * need to know if the linear map has to avoid block mappings so that + * the crashkernel reservations can be unmapped later. + */ + crash_mem_map = true; + + return 0; +} +early_param("crashkernel", enable_crash_mem_map); + static void __init map_mem(pgd_t *pgdp) { - phys_addr_t kernel_start = __pa_symbol(_text); + phys_addr_t kernel_start = __pa_symbol(_stext); phys_addr_t kernel_end = __pa_symbol(__init_begin); phys_addr_t start, end; int flags = 0; u64 i; - if (rodata_full || debug_pagealloc_enabled()) + if (rodata_full || crash_mem_map || debug_pagealloc_enabled()) flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS; /* @@ -487,11 +502,6 @@ static void __init map_mem(pgd_t *pgdp) * 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_mem_range(i, &start, &end) { @@ -506,7 +516,7 @@ static void __init map_mem(pgd_t *pgdp) } /* - * Map the linear alias of the [_text, __init_begin) interval + * Map the linear alias of the [_stext, __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 @@ -518,21 +528,6 @@ static void __init map_mem(pgd_t *pgdp) __map_memblock(pgdp, 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(pgdp, 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) @@ -665,7 +660,7 @@ static void __init map_kernel(pgd_t *pgdp) * Only rodata will be remapped with different permissions later on, * all other segments are allowed to use contiguous mappings. */ - map_kernel_segment(pgdp, _text, _etext, text_prot, &vmlinux_text, 0, + map_kernel_segment(pgdp, _stext, _etext, text_prot, &vmlinux_text, 0, VM_NO_GUARD); map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); @@ -1132,8 +1127,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, void *p = NULL; p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (!p) - return -ENOMEM; + if (!p) { + if (vmemmap_populate_basepages(addr, next, node, altmap)) + return -ENOMEM; + continue; + } pmd_set_huge(pmdp, __pa(p), __pgprot(PROT_SECT_NORMAL)); } else @@ -1510,13 +1508,43 @@ static int prevent_bootmem_remove_notifier(struct notifier_block *nb, unsigned long end_pfn = arg->start_pfn + arg->nr_pages; unsigned long pfn = arg->start_pfn; - if (action != MEM_GOING_OFFLINE) + if ((action != MEM_GOING_OFFLINE) && (action != MEM_OFFLINE)) return NOTIFY_OK; for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) { + unsigned long start = PFN_PHYS(pfn); + unsigned long end = start + (1UL << PA_SECTION_SHIFT); + ms = __pfn_to_section(pfn); - if (early_section(ms)) + if (!early_section(ms)) + continue; + + if (action == MEM_GOING_OFFLINE) { + /* + * Boot memory removal is not supported. Prevent + * it via blocking any attempted offline request + * for the boot memory and just report it. + */ + pr_warn("Boot memory [%lx %lx] offlining attempted\n", start, end); return NOTIFY_BAD; + } else if (action == MEM_OFFLINE) { + /* + * This should have never happened. Boot memory + * offlining should have been prevented by this + * very notifier. Probably some memory removal + * procedure might have changed which would then + * require further debug. + */ + pr_err("Boot memory [%lx %lx] offlined\n", start, end); + + /* + * Core memory hotplug does not process a return + * code from the notifier for MEM_OFFLINE events. + * The error condition has been reported. Return + * from here as if ignored. + */ + return NOTIFY_DONE; + } } return NOTIFY_OK; } @@ -1525,9 +1553,66 @@ static struct notifier_block prevent_bootmem_remove_nb = { .notifier_call = prevent_bootmem_remove_notifier, }; +/* + * This ensures that boot memory sections on the platform are online + * from early boot. Memory sections could not be prevented from being + * offlined, unless for some reason they are not online to begin with. + * This helps validate the basic assumption on which the above memory + * event notifier works to prevent boot memory section offlining and + * its possible removal. + */ +static void validate_bootmem_online(void) +{ + phys_addr_t start, end, addr; + struct mem_section *ms; + u64 i; + + /* + * Scanning across all memblock might be expensive + * on some big memory systems. Hence enable this + * validation only with DEBUG_VM. + */ + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return; + + for_each_mem_range(i, &start, &end) { + for (addr = start; addr < end; addr += (1UL << PA_SECTION_SHIFT)) { + ms = __pfn_to_section(PHYS_PFN(addr)); + + /* + * All memory ranges in the system at this point + * should have been marked as early sections. + */ + WARN_ON(!early_section(ms)); + + /* + * Memory notifier mechanism here to prevent boot + * memory offlining depends on the fact that each + * early section memory on the system is initially + * online. Otherwise a given memory section which + * is already offline will be overlooked and can + * be removed completely. Call out such sections. + */ + if (!online_section(ms)) + pr_err("Boot memory [%llx %llx] is offline, can be removed\n", + addr, addr + (1UL << PA_SECTION_SHIFT)); + } + } +} + static int __init prevent_bootmem_remove_init(void) { - return register_memory_notifier(&prevent_bootmem_remove_nb); + int ret = 0; + + if (!IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return ret; + + validate_bootmem_online(); + ret = register_memory_notifier(&prevent_bootmem_remove_nb); + if (ret) + pr_err("%s: Notifier registration failed %d\n", __func__, ret); + + return ret; } -device_initcall(prevent_bootmem_remove_init); +early_initcall(prevent_bootmem_remove_init); #endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 23c326a06b2d..a0831bf8a018 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -40,7 +40,7 @@ #define TCR_CACHE_FLAGS TCR_IRGN_WBWA | TCR_ORGN_WBWA #ifdef CONFIG_KASAN_SW_TAGS -#define TCR_KASAN_FLAGS TCR_TBI1 +#define TCR_KASAN_FLAGS TCR_TBI1 | TCR_TBID1 #else #define TCR_KASAN_FLAGS 0 #endif @@ -168,7 +168,7 @@ SYM_FUNC_END(cpu_do_resume) .pushsection ".idmap.text", "awx" .macro __idmap_cpu_set_reserved_ttbr1, tmp1, tmp2 - adrp \tmp1, empty_zero_page + adrp \tmp1, reserved_pg_dir phys_to_ttbr \tmp2, \tmp1 offset_ttbr1 \tmp2, \tmp1 msr ttbr1_el1, \tmp2 @@ -489,6 +489,6 @@ SYM_FUNC_START(__cpu_setup) /* * Prepare SCTLR */ - mov_q x0, SCTLR_EL1_SET + mov_q x0, INIT_SCTLR_EL1_MMU_ON ret // return to head.S SYM_FUNC_END(__cpu_setup) diff --git a/arch/h8300/include/uapi/asm/signal.h b/arch/h8300/include/uapi/asm/signal.h index e15521037348..2cd0dce2b6a6 100644 --- a/arch/h8300/include/uapi/asm/signal.h +++ b/arch/h8300/include/uapi/asm/signal.h @@ -57,30 +57,6 @@ typedef unsigned long sigset_t; #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 /* not supported yet */ -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000 #define MINSIGSTKSZ 2048 diff --git a/arch/ia64/include/uapi/asm/signal.h b/arch/ia64/include/uapi/asm/signal.h index aa98ff1b9e22..38166a88e4c9 100644 --- a/arch/ia64/include/uapi/asm/signal.h +++ b/arch/ia64/include/uapi/asm/signal.h @@ -53,30 +53,6 @@ #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000 /* diff --git a/arch/m68k/include/uapi/asm/signal.h b/arch/m68k/include/uapi/asm/signal.h index 915cc755a184..4619291df601 100644 --- a/arch/m68k/include/uapi/asm/signal.h +++ b/arch/m68k/include/uapi/asm/signal.h @@ -57,30 +57,6 @@ typedef unsigned long sigset_t; #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 diff --git a/arch/mips/include/uapi/asm/signal.h b/arch/mips/include/uapi/asm/signal.h index 53104b10aae2..e6c78a15cb2f 100644 --- a/arch/mips/include/uapi/asm/signal.h +++ b/arch/mips/include/uapi/asm/signal.h @@ -62,18 +62,6 @@ typedef unsigned long old_sigset_t; /* at least 32 bits */ #define SIGRTMAX _NSIG /* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - * * SA_RESTORER used to be defined as 0x04000000 but only the O32 ABI ever * supported its use and no libc was using it, so the entire sa-restorer * functionality was removed with lmo commit 39bffc12c3580ab for 2.5.48 diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h index 715c96ba2ec8..30dd1e43ef88 100644 --- a/arch/parisc/include/asm/signal.h +++ b/arch/parisc/include/asm/signal.h @@ -21,6 +21,8 @@ typedef struct { unsigned long sig[_NSIG_WORDS]; } sigset_t; +#define __ARCH_UAPI_SA_FLAGS _SA_SIGGFAULT + #include <asm/sigcontext.h> #endif /* !__ASSEMBLY */ diff --git a/arch/parisc/include/uapi/asm/signal.h b/arch/parisc/include/uapi/asm/signal.h index e605197b462c..e5a2657477ac 100644 --- a/arch/parisc/include/uapi/asm/signal.h +++ b/arch/parisc/include/uapi/asm/signal.h @@ -41,19 +41,6 @@ #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ #define SA_ONSTACK 0x00000001 #define SA_RESETHAND 0x00000004 #define SA_NOCLDSTOP 0x00000008 @@ -68,14 +55,7 @@ #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 - -#define SIG_BLOCK 0 /* for blocking signals */ -#define SIG_UNBLOCK 1 /* for unblocking signals */ -#define SIG_SETMASK 2 /* for setting the signal mask */ - -#define SIG_DFL ((__sighandler_t)0) /* default signal handling */ -#define SIG_IGN ((__sighandler_t)1) /* ignore signal */ -#define SIG_ERR ((__sighandler_t)-1) /* error return from signal */ +#include <asm-generic/signal-defs.h> # ifndef __ASSEMBLY__ @@ -84,18 +64,6 @@ /* Avoid too many header ordering problems. */ struct siginfo; -/* Type of a signal handler. */ -#if defined(__LP64__) -/* function pointers on 64-bit parisc are pointers to little structs and the - * compiler doesn't support code which changes or tests the address of - * the function in the little struct. This is really ugly -PB - */ -typedef char __user *__sighandler_t; -#else -typedef void __signalfn_t(int); -typedef __signalfn_t __user *__sighandler_t; -#endif - typedef struct sigaltstack { void __user *ss_sp; int ss_flags; diff --git a/arch/powerpc/include/asm/nohash/32/kup-8xx.h b/arch/powerpc/include/asm/nohash/32/kup-8xx.h index 85ed2390fb99..567cdc557402 100644 --- a/arch/powerpc/include/asm/nohash/32/kup-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/kup-8xx.h @@ -63,7 +63,7 @@ static inline void restore_user_access(unsigned long flags) static inline bool bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write) { - return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xf0000000), + return WARN(!((regs->kuap ^ MD_APG_KUAP) & 0xff000000), "Bug: fault blocked by AP register !"); } diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index 1d9ac0f9c794..0bd1b144eb76 100644 --- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -33,19 +33,18 @@ * respectively NA for All or X for Supervisor and no access for User. * Then we use the APG to say whether accesses are according to Page rules or * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MI_APG_INIT 0x40000000 - -/* - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MI_APG_KUEP 0x60000000 + * _PAGE_ACCESSED is also managed via APG. When _PAGE_ACCESSED is not set, say + * "all User" rules, that will lead to NA for all. + * Therefore, we define 4 APG groups. lsb is _PAGE_ACCESSED + * 0 => Kernel => 11 (all accesses performed according as user iaw page definition) + * 1 => Kernel+Accessed => 01 (all accesses performed according to page definition) + * 2 => User => 11 (all accesses performed according as user iaw page definition) + * 3 => User+Accessed => 00 (all accesses performed as supervisor iaw page definition) for INIT + * => 10 (all accesses performed according to swaped page definition) for KUEP + * 4-15 => Not Used + */ +#define MI_APG_INIT 0xdc000000 +#define MI_APG_KUEP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MI_RPN is written, bits in @@ -106,25 +105,9 @@ #define MD_Ks 0x80000000 /* Should not be set */ #define MD_Kp 0x40000000 /* Should always be set */ -/* - * All pages' PP data bits are set to either 000 or 011 or 001, which means - * respectively RW for Supervisor and no access for User, or RO for - * Supervisor and no access for user and NA for ALL. - * Then we use the APG to say whether accesses are according to Page rules or - * "all Supervisor" rules (Access to all) - * Therefore, we define 2 APG groups. lsb is _PMD_USER - * 0 => Kernel => 01 (all accesses performed according to page definition) - * 1 => User => 00 (all accesses performed as supervisor iaw page definition) - * 2-15 => Not Used - */ -#define MD_APG_INIT 0x40000000 - -/* - * 0 => No user => 01 (all accesses performed according to page definition) - * 1 => User => 10 (all accesses performed according to swaped page definition) - * 2-15 => Not Used - */ -#define MD_APG_KUAP 0x60000000 +/* See explanation above at the definition of MI_APG_INIT */ +#define MD_APG_INIT 0xdc000000 +#define MD_APG_KUAP 0xde000000 /* The effective page number register. When read, contains the information * about the last instruction TLB miss. When MD_RPN is written, bits in diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 66f403a7da44..1581204467e1 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -39,9 +39,9 @@ * into the TLB. */ #define _PAGE_GUARDED 0x0010 /* Copied to L1 G entry in DTLB */ -#define _PAGE_SPECIAL 0x0020 /* SW entry */ +#define _PAGE_ACCESSED 0x0020 /* Copied to L1 APG 1 entry in I/DTLB */ #define _PAGE_EXEC 0x0040 /* Copied to PP (bit 21) in ITLB */ -#define _PAGE_ACCESSED 0x0080 /* software: page referenced */ +#define _PAGE_SPECIAL 0x0080 /* SW entry */ #define _PAGE_NA 0x0200 /* Supervisor NA, User no access */ #define _PAGE_RO 0x0600 /* Supervisor RO, User no access */ @@ -59,11 +59,12 @@ #define _PMD_PRESENT 0x0001 #define _PMD_PRESENT_MASK _PMD_PRESENT -#define _PMD_BAD 0x0fd0 +#define _PMD_BAD 0x0f90 #define _PMD_PAGE_MASK 0x000c #define _PMD_PAGE_8M 0x000c #define _PMD_PAGE_512K 0x0004 -#define _PMD_USER 0x0020 /* APG 1 */ +#define _PMD_ACCESSED 0x0020 /* APG 1 */ +#define _PMD_USER 0x0040 /* APG 2 */ #define _PTE_NONE_MASK 0 diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 8728590f514a..3beeb030cd78 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -6,6 +6,7 @@ struct device; struct device_node; +struct drmem_lmb; #ifdef CONFIG_NUMA @@ -61,6 +62,9 @@ static inline int early_cpu_to_node(int cpu) */ return (nid < 0) ? 0 : nid; } + +int of_drconf_to_nid_single(struct drmem_lmb *lmb); + #else static inline int early_cpu_to_node(int cpu) { return 0; } @@ -84,10 +88,12 @@ static inline int cpu_distance(__be32 *cpu1_assoc, __be32 *cpu2_assoc) return 0; } -#endif /* CONFIG_NUMA */ +static inline int of_drconf_to_nid_single(struct drmem_lmb *lmb) +{ + return first_online_node; +} -struct drmem_lmb; -int of_drconf_to_nid_single(struct drmem_lmb *lmb); +#endif /* CONFIG_NUMA */ #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR) extern int find_and_online_cpu_nid(int cpu); diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index ef5bbb705c08..501c9a79038c 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -178,7 +178,7 @@ do { \ * are no aliasing issues. */ #define __put_user_asm_goto(x, addr, label, op) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ @@ -191,7 +191,7 @@ do { \ __put_user_asm_goto(x, ptr, label, "std") #else /* __powerpc64__ */ #define __put_user_asm2_goto(x, addr, label) \ - asm volatile goto( \ + asm_volatile_goto( \ "1: stw%X1 %0, %1\n" \ "2: stw%X1 %L0, %L1\n" \ EX_TABLE(1b, %l2) \ diff --git a/arch/powerpc/include/uapi/asm/signal.h b/arch/powerpc/include/uapi/asm/signal.h index 85b0a7aa43e7..04873dd311c2 100644 --- a/arch/powerpc/include/uapi/asm/signal.h +++ b/arch/powerpc/include/uapi/asm/signal.h @@ -60,30 +60,6 @@ typedef struct { #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK is not currently supported, but will allow sigaltstack(2). - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001U -#define SA_NOCLDWAIT 0x00000002U -#define SA_SIGINFO 0x00000004U -#define SA_ONSTACK 0x08000000U -#define SA_RESTART 0x10000000U -#define SA_NODEFER 0x40000000U -#define SA_RESETHAND 0x80000000U - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000U #define MINSIGSTKSZ 2048 diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c index 6b50bf15d8c1..bf3270426d82 100644 --- a/arch/powerpc/kernel/eeh_cache.c +++ b/arch/powerpc/kernel/eeh_cache.c @@ -264,8 +264,9 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) { struct pci_io_addr_range *piar; struct rb_node *n; + unsigned long flags; - spin_lock(&pci_io_addr_cache_root.piar_lock); + spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags); for (n = rb_first(&pci_io_addr_cache_root.rb_root); n; n = rb_next(n)) { piar = rb_entry(n, struct pci_io_addr_range, rb_node); @@ -273,7 +274,7 @@ static int eeh_addr_cache_show(struct seq_file *s, void *v) (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", &piar->addr_lo, &piar->addr_hi, pci_name(piar->pcidev)); } - spin_unlock(&pci_io_addr_cache_root.piar_lock); + spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags); return 0; } diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 44c9018aed1b..a1ae00689e0f 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -284,11 +284,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r9, _PAGE_PRESENT -#endif andc. r9, r9, r11 /* Check permission */ bne 5f @@ -369,11 +365,7 @@ _ENTRY(saved_ksp_limit) rlwimi r11, r10, 22, 20, 29 /* Compute PTE address */ lwz r11, 0(r11) /* Get Linux PTE */ -#ifdef CONFIG_SWAP li r9, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r9, _PAGE_PRESENT | _PAGE_EXEC -#endif andc. r9, r9, r11 /* Check permission */ bne 5f diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 9f359d3fba74..ee0bfebc375f 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -202,9 +202,7 @@ SystemCall: InstructionTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mtspr SPRN_SPRG_SCRATCH1, r11 -#endif /* If we are faulting a kernel address, we have to use the * kernel page tables. @@ -224,25 +222,13 @@ InstructionTLBMiss: 3: mtcr r11 #endif -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ mtspr SPRN_MD_TWC, r11 -#else - lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ - mtspr SPRN_MI_TWC, r10 /* Set segment attributes */ - mtspr SPRN_MD_TWC, r10 -#endif mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -#if defined(CONFIG_HUGETLBFS) || !defined(CONFIG_PIN_TLB_TEXT) + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MI_TWC, r11 -#endif -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. * Software indicator bits 22, 24, 25, 26, and 27 must be @@ -256,9 +242,7 @@ InstructionTLBMiss: /* Restore registers */ 0: mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) || defined(CONFIG_HUGETLBFS) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi patch_site 0b, patch__itlbmiss_exit_1 @@ -268,9 +252,7 @@ InstructionTLBMiss: addi r10, r10, 1 stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#endif rfi #endif @@ -297,30 +279,16 @@ DataStoreTLBMiss: mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ - /* Insert the Guarded flag into the TWC from the Linux PTE. + /* Insert Guarded and Accessed flags into the TWC from the Linux PTE. * It is bit 27 of both the Linux PTE and the TWC (at least * I got that right :-). It will be better when we can put * this into the Linux pgd/pmd and load it in the operation * above. */ - rlwimi r11, r10, 0, _PAGE_GUARDED + rlwimi r11, r10, 0, _PAGE_GUARDED | _PAGE_ACCESSED rlwimi r11, r10, 32 - 9, _PMD_PAGE_512K mtspr SPRN_MD_TWC, r11 - /* Both _PAGE_ACCESSED and _PAGE_PRESENT has to be set. - * We also need to know if the insn is a load/store, so: - * Clear _PAGE_PRESENT and load that which will - * trap into DTLB Error with store bit set accordinly. - */ - /* PRESENT=0x1, ACCESSED=0x20 - * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5)); - * r10 = (r10 & ~PRESENT) | r11; - */ -#ifdef CONFIG_SWAP - rlwinm r11, r10, 32-5, _PAGE_PRESENT - and r11, r11, r10 - rlwimi r10, r11, 0, _PAGE_PRESENT -#endif /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior @@ -711,7 +679,7 @@ initial_mmu: li r9, 4 /* up to 4 pages of 8M */ mtctr r9 lis r9, KERNELBASE@h /* Create vaddr for TLB */ - li r10, MI_PS8MEG | MI_SVALID /* Set 8M byte page */ + li r10, MI_PS8MEG | _PMD_ACCESSED | MI_SVALID li r11, MI_BOOTINIT /* Create RPN for address 0 */ 1: mtspr SPRN_MI_CTR, r8 /* Set instruction MMU control */ @@ -775,7 +743,7 @@ _GLOBAL(mmu_pin_tlb) #ifdef CONFIG_PIN_TLB_TEXT LOAD_REG_IMMEDIATE(r5, 28 << 8) LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) LOAD_REG_IMMEDIATE(r8, 0xf0 | _PAGE_RO | _PAGE_SPS | _PAGE_SH | _PAGE_PRESENT) LOAD_REG_ADDR(r9, _sinittext) li r0, 4 @@ -797,7 +765,7 @@ _GLOBAL(mmu_pin_tlb) LOAD_REG_IMMEDIATE(r5, 28 << 8 | MD_TWAM) #ifdef CONFIG_PIN_TLB_DATA LOAD_REG_IMMEDIATE(r6, PAGE_OFFSET) - LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG) + LOAD_REG_IMMEDIATE(r7, MI_SVALID | MI_PS8MEG | _PMD_ACCESSED) #ifdef CONFIG_PIN_TLB_IMMR li r0, 3 #else @@ -834,7 +802,7 @@ _GLOBAL(mmu_pin_tlb) #endif #ifdef CONFIG_PIN_TLB_IMMR LOAD_REG_IMMEDIATE(r0, VIRT_IMMR_BASE | MD_EVALID) - LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED) + LOAD_REG_IMMEDIATE(r7, MD_SVALID | MD_PS512K | MD_GUARDED | _PMD_ACCESSED) mfspr r8, SPRN_IMMR rlwinm r8, r8, 0, 0xfff80000 ori r8, r8, 0xf0 | _PAGE_DIRTY | _PAGE_SPS | _PAGE_SH | \ diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 5eb9eedac920..2aa16d5368e1 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -457,11 +457,7 @@ InstructionTLBMiss: cmplw 0,r1,r3 #endif mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC -#else - li r1,_PAGE_PRESENT | _PAGE_EXEC -#endif #if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC) bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ @@ -523,11 +519,7 @@ DataLoadTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ @@ -603,11 +595,7 @@ DataStoreTLBMiss: lis r1, TASK_SIZE@h /* check if kernel address */ cmplw 0,r1,r3 mfspr r2, SPRN_SPRG_PGDIR -#ifdef CONFIG_SWAP li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED -#else - li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT -#endif bgt- 112f lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */ addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */ diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 3c6b9822f978..8c2857cbd960 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1393,13 +1393,14 @@ static void add_cpu_to_masks(int cpu) /* Activate a secondary processor. */ void start_secondary(void *unused) { - unsigned int cpu = smp_processor_id(); + unsigned int cpu = raw_smp_processor_id(); mmgrab(&init_mm); current->active_mm = &init_mm; smp_store_cpu_info(cpu); set_dec(tb_ticks_per_jiffy); + rcu_cpu_starting(cpu); preempt_disable(); cpu_callin_map[cpu] = 1; diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index c47e6b35c551..824b2c9da75b 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -476,7 +476,7 @@ do { \ do { \ long __kr_err; \ \ - __put_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \ + __put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \ if (unlikely(__kr_err)) \ goto err_label; \ } while (0) diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 99e12faa5498..765b62434f30 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2013 Linaro Limited * Author: AKASHI Takahiro <takahiro.akashi@linaro.org> diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 11e2a4fe66e0..7e849797c9c3 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -35,6 +35,10 @@ ENTRY(_start) .word 0 #endif .balign 8 +#ifdef CONFIG_RISCV_M_MODE + /* Image load offset (0MB) from start of RAM for M-mode */ + .dword 0 +#else #if __riscv_xlen == 64 /* Image load offset(2MB) from start of RAM */ .dword 0x200000 @@ -42,6 +46,7 @@ ENTRY(_start) /* Image load offset(4MB) from start of RAM */ .dword 0x400000 #endif +#endif /* Effective size of kernel image */ .dword _end - _start .dword __HEAD_FLAGS diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore index 11ebee9e4c1d..3a19def868ec 100644 --- a/arch/riscv/kernel/vdso/.gitignore +++ b/arch/riscv/kernel/vdso/.gitignore @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only vdso.lds *.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 7d6a94d45ec9..cb8f9e4cfcbf 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -43,19 +43,14 @@ $(obj)/vdso.o: $(obj)/vdso.so SYSCFLAGS_vdso.so.dbg = $(c_flags) $(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso) FORCE $(call if_changed,vdsold) +SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ + -Wl,--build-id -Wl,--hash-style=both # We also create a special relocatable object that should mirror the symbol # table and layout of the linked DSO. With ld --just-symbols we can then # refer to these symbols in the kernel code rather than hand-coded addresses. - -SYSCFLAGS_vdso.so.dbg = -shared -s -Wl,-soname=linux-vdso.so.1 \ - -Wl,--build-id=sha1 -Wl,--hash-style=both -$(obj)/vdso-dummy.o: $(src)/vdso.lds $(obj)/rt_sigreturn.o FORCE - $(call if_changed,vdsold) - -LDFLAGS_vdso-syms.o := -r --just-symbols -$(obj)/vdso-syms.o: $(obj)/vdso-dummy.o FORCE - $(call if_changed,ld) +$(obj)/vdso-syms.S: $(obj)/vdso.so FORCE + $(call if_changed,so2s) # strip rule for the .so file $(obj)/%.so: OBJCOPYFLAGS := -S @@ -73,6 +68,11 @@ quiet_cmd_vdsold = VDSOLD $@ $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp +# Extracts symbol offsets from the VDSO, converting them into an assembly file +# that contains the same symbols at the same offsets. +quiet_cmd_so2s = SO2S $@ + cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ + # install commands for the unstripped file quiet_cmd_vdso_install = INSTALL $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ diff --git a/arch/riscv/kernel/vdso/so2s.sh b/arch/riscv/kernel/vdso/so2s.sh new file mode 100755 index 000000000000..e64cb6d9440e --- /dev/null +++ b/arch/riscv/kernel/vdso/so2s.sh @@ -0,0 +1,6 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# Copyright 2020 Palmer Dabbelt <palmerdabbelt@google.com> + +sed 's!\([0-9a-f]*\) T \([a-z0-9_]*\)\(@@LINUX_4.15\)*!.global \2\n.set \2,0x\1!' \ +| grep '^\.' diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 1359e21c0c62..3c8b9e433c67 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -86,6 +86,7 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a pmd_t *pmd, *pmd_k; pte_t *pte_k; int index; + unsigned long pfn; /* User mode accesses just cause a SIGSEGV */ if (user_mode(regs)) @@ -100,7 +101,8 @@ static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long a * of a task switch. */ index = pgd_index(addr); - pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index; + pfn = csr_read(CSR_SATP) & SATP_PPN; + pgd = (pgd_t *)pfn_to_virt(pfn) + index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ea933b789a88..8e577f14f120 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -154,9 +154,8 @@ disable: void __init setup_bootmem(void) { - phys_addr_t mem_size = 0; - phys_addr_t total_mem = 0; - phys_addr_t mem_start, start, end = 0; + phys_addr_t mem_start = 0; + phys_addr_t start, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); u64 i; @@ -164,21 +163,18 @@ void __init setup_bootmem(void) /* Find the memory region containing the kernel */ for_each_mem_range(i, &start, &end) { phys_addr_t size = end - start; - if (!total_mem) + if (!mem_start) mem_start = start; if (start <= vmlinux_start && vmlinux_end <= end) BUG_ON(size == 0); - total_mem = total_mem + size; } /* - * Remove memblock from the end of usable area to the - * end of region + * The maximal physical memory size is -PAGE_OFFSET. + * Make sure that any memory beyond mem_start + (-PAGE_OFFSET) is removed + * as it is unusable by kernel. */ - mem_size = min(total_mem, (phys_addr_t)-PAGE_OFFSET); - if (mem_start + mem_size < end) - memblock_remove(mem_start + mem_size, - end - mem_start - mem_size); + memblock_enforce_memory_limit(mem_start - PAGE_OFFSET); /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); @@ -297,6 +293,7 @@ pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; #define NUM_EARLY_PMDS (1UL + MAX_EARLY_MAPPING_SIZE / PGDIR_SIZE) #endif pmd_t early_pmd[PTRS_PER_PMD * NUM_EARLY_PMDS] __initdata __aligned(PAGE_SIZE); +pmd_t early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) { @@ -494,6 +491,18 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) load_pa + (va - PAGE_OFFSET), map_size, PAGE_KERNEL_EXEC); +#ifndef __PAGETABLE_PMD_FOLDED + /* Setup early PMD for DTB */ + create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, + (uintptr_t)early_dtb_pmd, PGDIR_SIZE, PAGE_TABLE); + /* Create two consecutive PMD mappings for FDT early scan */ + pa = dtb_pa & ~(PMD_SIZE - 1); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA, + pa, PMD_SIZE, PAGE_KERNEL); + create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE, + pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); + dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1)); +#else /* Create two consecutive PGD mappings for FDT early scan */ pa = dtb_pa & ~(PGDIR_SIZE - 1); create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA, @@ -501,6 +510,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA + PGDIR_SIZE, pa + PGDIR_SIZE, PGDIR_SIZE, PAGE_KERNEL); dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PGDIR_SIZE - 1)); +#endif dtb_early_pa = dtb_pa; /* diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 0784bf3caf43..a4d3c578fbd8 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -93,9 +93,10 @@ CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -378,7 +379,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_PCI_DEBUG=y @@ -386,7 +386,7 @@ CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -689,6 +689,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -709,7 +710,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -753,6 +753,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_CRC32_SELFTEST=y CONFIG_CRC4=m @@ -829,6 +830,7 @@ CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y CONFIG_FAIL_PAGE_ALLOC=y +CONFIG_FAULT_INJECTION_USERCOPY=y CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 905bc8c4cfaf..17d5df2c1eff 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -87,9 +87,10 @@ CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y +CONFIG_CMA_AREAS=7 CONFIG_MEM_SOFT_DIRTY=y CONFIG_ZSWAP=y -CONFIG_ZSMALLOC=m +CONFIG_ZSMALLOC=y CONFIG_ZSMALLOC_STAT=y CONFIG_DEFERRED_STRUCT_PAGE_INIT=y CONFIG_IDLE_PAGE_TRACKING=y @@ -371,7 +372,6 @@ CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y CONFIG_NET_PKTGEN=m -# CONFIG_NET_DROP_MONITOR is not set CONFIG_PCI=y # CONFIG_PCIEASPM is not set CONFIG_HOTPLUG_PCI=y @@ -379,7 +379,7 @@ CONFIG_HOTPLUG_PCI_S390=y CONFIG_UEVENT_HELPER=y CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=y -CONFIG_ZRAM=m +CONFIG_ZRAM=y CONFIG_BLK_DEV_LOOP=m CONFIG_BLK_DEV_CRYPTOLOOP=m CONFIG_BLK_DEV_DRBD=m @@ -680,6 +680,7 @@ CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_DH=m CONFIG_CRYPTO_ECDH=m CONFIG_CRYPTO_ECRDSA=m +CONFIG_CRYPTO_SM2=m CONFIG_CRYPTO_CURVE25519=m CONFIG_CRYPTO_GCM=y CONFIG_CRYPTO_CHACHA20POLY1305=m @@ -701,7 +702,6 @@ CONFIG_CRYPTO_RMD160=m CONFIG_CRYPTO_RMD256=m CONFIG_CRYPTO_RMD320=m CONFIG_CRYPTO_SHA3=m -CONFIG_CRYPTO_SM3=m CONFIG_CRYPTO_TGR192=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES_TI=m @@ -745,6 +745,7 @@ CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m CONFIG_CRYPTO_CRC32_S390=y +CONFIG_CRYPTO_DEV_VIRTIO=m CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRC4=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index 8f67c55625f9..a302630341ef 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -17,11 +17,11 @@ CONFIG_HZ_100=y # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y -# CONFIG_SECCOMP is not set # CONFIG_PFAULT is not set # CONFIG_S390_HYPFS_FS is not set # CONFIG_VIRTUALIZATION is not set # CONFIG_S390_GUEST is not set +# CONFIG_SECCOMP is not set CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 6b8d8c69b1a1..b5dbae78969b 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -692,16 +692,6 @@ static inline int pud_large(pud_t pud) return !!(pud_val(pud) & _REGION3_ENTRY_LARGE); } -static inline unsigned long pud_pfn(pud_t pud) -{ - unsigned long origin_mask; - - origin_mask = _REGION_ENTRY_ORIGIN; - if (pud_large(pud)) - origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; - return (pud_val(pud) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_leaf pmd_large static inline int pmd_large(pmd_t pmd) { @@ -747,16 +737,6 @@ static inline int pmd_none(pmd_t pmd) return pmd_val(pmd) == _SEGMENT_ENTRY_EMPTY; } -static inline unsigned long pmd_pfn(pmd_t pmd) -{ - unsigned long origin_mask; - - origin_mask = _SEGMENT_ENTRY_ORIGIN; - if (pmd_large(pmd)) - origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; - return (pmd_val(pmd) & origin_mask) >> PAGE_SHIFT; -} - #define pmd_write pmd_write static inline int pmd_write(pmd_t pmd) { @@ -1238,11 +1218,39 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) #define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD-1)) #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1)) -#define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN) -#define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN) #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN) #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN) +static inline unsigned long pmd_deref(pmd_t pmd) +{ + unsigned long origin_mask; + + origin_mask = _SEGMENT_ENTRY_ORIGIN; + if (pmd_large(pmd)) + origin_mask = _SEGMENT_ENTRY_ORIGIN_LARGE; + return pmd_val(pmd) & origin_mask; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return pmd_deref(pmd) >> PAGE_SHIFT; +} + +static inline unsigned long pud_deref(pud_t pud) +{ + unsigned long origin_mask; + + origin_mask = _REGION_ENTRY_ORIGIN; + if (pud_large(pud)) + origin_mask = _REGION3_ENTRY_ORIGIN_LARGE; + return pud_val(pud) & origin_mask; +} + +static inline unsigned long pud_pfn(pud_t pud) +{ + return pud_deref(pud) >> PAGE_SHIFT; +} + /* * The pgd_offset function *always* adds the index for the top-level * region/segment table. This is done to get a sequence like the diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h index a996d3990a02..0c2151451ba5 100644 --- a/arch/s390/include/asm/sections.h +++ b/arch/s390/include/asm/sections.h @@ -26,14 +26,14 @@ static inline int arch_is_kernel_initmem_freed(unsigned long addr) * final .boot.data section, which should be identical in the decompressor and * the decompressed kernel (that is checked during the build). */ -#define __bootdata(var) __section(".boot.data.var") var +#define __bootdata(var) __section(".boot.data." #var) var /* * .boot.preserved.data is similar to .boot.data, but it is not part of the * .init section and thus will be preserved for later use in the decompressed * kernel. */ -#define __bootdata_preserved(var) __section(".boot.preserved.data.var") var +#define __bootdata_preserved(var) __section(".boot.preserved.data." #var) var extern unsigned long __sdma, __edma; extern unsigned long __stext_dma, __etext_dma; diff --git a/arch/s390/include/asm/vdso/vdso.h b/arch/s390/include/asm/vdso/vdso.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/arch/s390/include/asm/vdso/vdso.h +++ /dev/null diff --git a/arch/s390/include/uapi/asm/signal.h b/arch/s390/include/uapi/asm/signal.h index 9a14a611ed82..0189f326aac5 100644 --- a/arch/s390/include/uapi/asm/signal.h +++ b/arch/s390/include/uapi/asm/signal.h @@ -65,30 +65,6 @@ typedef unsigned long sigset_t; #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000 #define MINSIGSTKSZ 2048 diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index ece58f2217cb..2012c1cf0853 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -61,14 +61,6 @@ int main(void) BLANK(); OFFSET(__VDSO_GETCPU_VAL, vdso_per_cpu_data, getcpu_val); BLANK(); - /* constants used by the vdso */ - DEFINE(__CLOCK_REALTIME, CLOCK_REALTIME); - DEFINE(__CLOCK_MONOTONIC, CLOCK_MONOTONIC); - DEFINE(__CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); - DEFINE(__CLOCK_MONOTONIC_COARSE, CLOCK_MONOTONIC_COARSE); - DEFINE(__CLOCK_THREAD_CPUTIME_ID, CLOCK_THREAD_CPUTIME_ID); - DEFINE(__CLOCK_COARSE_RES, LOW_RES_NSEC); - BLANK(); /* idle data offsets */ OFFSET(__CLOCK_IDLE_ENTER, s390_idle_data, clock_idle_enter); OFFSET(__CLOCK_IDLE_EXIT, s390_idle_data, clock_idle_exit); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index ebfe86d097f0..390d97daa2b3 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -855,13 +855,14 @@ void __init smp_detect_cpus(void) static void smp_init_secondary(void) { - int cpu = smp_processor_id(); + int cpu = raw_smp_processor_id(); S390_lowcore.last_update_clock = get_tod_clock(); restore_access_regs(S390_lowcore.access_regs_save_area); set_cpu_flag(CIF_ASCE_PRIMARY); set_cpu_flag(CIF_ASCE_SECONDARY); cpu_init(); + rcu_cpu_starting(cpu); preempt_disable(); init_cpu_timer(); vtime_init(); diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index d33f21545dfd..9a6bae503fe6 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -101,6 +101,10 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (ret) break; + /* the PCI function will be scanned once function 0 appears */ + if (!zdev->zbus->bus) + break; + pdev = pci_scan_single_device(zdev->zbus->bus, zdev->devfn); if (!pdev) break; diff --git a/arch/sparc/include/uapi/asm/signal.h b/arch/sparc/include/uapi/asm/signal.h index ff9505923b9a..53758d53ac0e 100644 --- a/arch/sparc/include/uapi/asm/signal.h +++ b/arch/sparc/include/uapi/asm/signal.h @@ -137,13 +137,11 @@ struct sigstack { #define SA_STACK _SV_SSTACK #define SA_ONSTACK _SV_SSTACK #define SA_RESTART _SV_INTR -#define SA_ONESHOT _SV_RESET +#define SA_RESETHAND _SV_RESET #define SA_NODEFER 0x20u #define SA_NOCLDWAIT 0x100u #define SA_SIGINFO 0x200u -#define SA_NOMASK SA_NODEFER - #define SIG_BLOCK 0x01 /* for blocking signals */ #define SIG_UNBLOCK 0x02 /* for unblocking signals */ #define SIG_SETMASK 0x04 /* for setting the signal mask */ diff --git a/arch/um/kernel/skas/clone.c b/arch/um/kernel/skas/clone.c index 95c355181dcd..bfb70c456b30 100644 --- a/arch/um/kernel/skas/clone.c +++ b/arch/um/kernel/skas/clone.c @@ -21,7 +21,7 @@ * on some systems. */ -void __section(".__syscall_stub") +void __attribute__ ((__section__ (".__syscall_stub"))) stub_clone_handler(void) { struct stub_data *data = (struct stub_data *) STUB_DATA; diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index a5e5db6ada3c..39b2eded7bc2 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -164,6 +164,7 @@ void initialize_identity_maps(void *rmode) add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); /* Load the new page-table. */ + sev_verify_cbit(top_level_pgt); write_cr3(top_level_pgt); } diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index dd07e7b41b11..aa561795efd1 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -68,6 +68,9 @@ SYM_FUNC_START(get_sev_encryption_bit) SYM_FUNC_END(get_sev_encryption_bit) .code64 + +#include "../../kernel/sev_verify_cbit.S" + SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp @@ -81,6 +84,19 @@ SYM_FUNC_START(set_sev_encryption_mask) bts %rax, sme_me_mask(%rip) /* Create the encryption mask */ + /* + * Read MSR_AMD64_SEV again and store it to sev_status. Can't do this in + * get_sev_encryption_bit() because this function is 32-bit code and + * shared between 64-bit and 32-bit boot path. + */ + movl $MSR_AMD64_SEV, %ecx /* Read the SEV MSR */ + rdmsr + + /* Store MSR value in sev_status */ + shlq $32, %rdx + orq %rdx, %rax + movq %rax, sev_status(%rip) + .Lno_sev_mask: movq %rbp, %rsp /* Restore original stack pointer */ @@ -96,5 +112,7 @@ SYM_FUNC_END(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 -SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sme_me_mask, .quad 0) +SYM_DATA(sev_status, .quad 0) +SYM_DATA(sev_check_data, .quad 0) #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 6d31f1b4c4d1..d9a631c5973c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -159,4 +159,6 @@ void boot_page_fault(void); void boot_stage1_vc(void); void boot_stage2_vc(void); +unsigned long sev_verify_cbit(unsigned long cr3); + #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index e508dbd91813..c44aba290fbb 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -158,6 +158,7 @@ static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx, dctx->s[1] = get_unaligned_le32(&inp[4]); dctx->s[2] = get_unaligned_le32(&inp[8]); dctx->s[3] = get_unaligned_le32(&inp[12]); + acc += POLY1305_BLOCK_SIZE; dctx->sset = true; } } diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 1f47e24fb65c..379819244b91 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -364,10 +364,10 @@ 440 common process_madvise sys_process_madvise # -# x32-specific system call numbers start at 512 to avoid cache impact -# for native 64-bit operation. The __x32_compat_sys stubs are created -# on-the-fly for compat_sys_*() compatibility system calls if X86_X32 -# is defined. +# Due to a historical design error, certain syscalls are numbered differently +# in x32 as compared to native x86_64. These syscalls have numbers 512-547. +# Do not add new syscalls to this range. Numbers 548 and above are available +# for non-x32 use. # 512 x32 rt_sigaction compat_sys_rt_sigaction 513 x32 rt_sigreturn compat_sys_x32_rt_sigreturn @@ -405,3 +405,5 @@ 545 x32 execveat compat_sys_execveat 546 x32 preadv2 compat_sys_preadv64v2 547 x32 pwritev2 compat_sys_pwritev64v2 +# This is the end of the legacy x32 range. Numbers 548 and above are +# not special and are not to be used for x32-specific syscalls. diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 40e0e322161d..284e73661a18 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -273,11 +273,15 @@ void __init hv_apic_init(void) pr_info("Hyper-V: Using enlightened APIC (%s mode)", x2apic_enabled() ? "x2apic" : "xapic"); /* - * With x2apic, architectural x2apic MSRs are equivalent to the - * respective synthetic MSRs, so there's no need to override - * the apic accessors. The only exception is - * hv_apic_eoi_write, because it benefits from lazy EOI when - * available, but it works for both xapic and x2apic modes. + * When in x2apic mode, don't use the Hyper-V specific APIC + * accessors since the field layout in the ICR register is + * different in x2apic mode. Furthermore, the architectural + * x2apic MSRs function just as well as the Hyper-V + * synthetic APIC MSRs, so there's no benefit in having + * separate Hyper-V accessors for x2apic mode. The only + * exception is hv_apic_eoi_write, because it benefits from + * lazy EOI when available, but the same accessor works for + * both xapic and x2apic because the field layout is the same. */ apic_set_eoi_write(hv_apic_eoi_write); if (!x2apic_enabled()) { diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 812e9b4c1114..950afebfba88 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -32,6 +32,7 @@ #define KVM_FEATURE_POLL_CONTROL 12 #define KVM_FEATURE_PV_SCHED_YIELD 13 #define KVM_FEATURE_ASYNC_PF_INT 14 +#define KVM_FEATURE_MSI_EXT_DEST_ID 15 #define KVM_HINTS_REALTIME 0 diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h index e5745d593dc7..164a22a72984 100644 --- a/arch/x86/include/uapi/asm/signal.h +++ b/arch/x86/include/uapi/asm/signal.h @@ -62,30 +62,6 @@ typedef unsigned long sigset_t; #define SIGRTMIN 32 #define SIGRTMAX _NSIG -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001u -#define SA_NOCLDWAIT 0x00000002u -#define SA_SIGINFO 0x00000004u -#define SA_ONSTACK 0x08000000u -#define SA_RESTART 0x10000000u -#define SA_NODEFER 0x40000000u -#define SA_RESETHAND 0x80000000u - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000 #define MINSIGSTKSZ 2048 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 4adbe65afe23..2400ad62f330 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -807,6 +807,15 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) temp_mm_state_t temp_state; lockdep_assert_irqs_disabled(); + + /* + * Make sure not to be in TLB lazy mode, as otherwise we'll end up + * with a stale address space WITHOUT being in lazy mode after + * restoring the previous mm. + */ + if (this_cpu_read(cpu_tlbstate.is_lazy)) + leave_mm(smp_processor_id()); + temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); switch_mm_irqs_off(NULL, mm, current); diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 714233cee0b5..3115caa7d7d0 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -290,6 +290,9 @@ static void __init uv_stringify(int len, char *to, char *from) { /* Relies on 'to' being NULL chars so result will be NULL terminated */ strncpy(to, from, len-1); + + /* Trim trailing spaces */ + (void)strim(to); } /* Find UV arch type entry in UVsystab */ @@ -366,7 +369,7 @@ static int __init early_get_arch_type(void) return ret; } -static int __init uv_set_system_type(char *_oem_id) +static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) { /* Save OEM_ID passed from ACPI MADT */ uv_stringify(sizeof(oem_id), oem_id, _oem_id); @@ -386,13 +389,23 @@ static int __init uv_set_system_type(char *_oem_id) /* (Not hubless), not a UV */ return 0; + /* Is UV hubless system */ + uv_hubless_system = 0x01; + + /* UV5 Hubless */ + if (strncmp(uv_archtype, "NSGI5", 5) == 0) + uv_hubless_system |= 0x20; + /* UV4 Hubless: CH */ - if (strncmp(uv_archtype, "NSGI4", 5) == 0) - uv_hubless_system = 0x11; + else if (strncmp(uv_archtype, "NSGI4", 5) == 0) + uv_hubless_system |= 0x10; /* UV3 Hubless: UV300/MC990X w/o hub */ else - uv_hubless_system = 0x9; + uv_hubless_system |= 0x8; + + /* Copy APIC type */ + uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n", oem_id, oem_table_id, uv_system_type, uv_hubless_system); @@ -456,7 +469,7 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; /* If not UV, return. */ - if (likely(uv_set_system_type(_oem_id) == 0)) + if (uv_set_system_type(_oem_id, _oem_table_id) == 0) return 0; /* Save and Decode OEM Table ID */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d3f0db463f96..581fb7223ad0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1254,6 +1254,14 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) return 0; } +static bool is_spec_ib_user_controlled(void) +{ + return spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || + spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || + spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP; +} + static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) { switch (ctrl) { @@ -1261,16 +1269,26 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return 0; + /* - * Indirect branch speculation is always disabled in strict - * mode. It can neither be enabled if it was force-disabled - * by a previous prctl call. + * With strict mode for both IBPB and STIBP, the instruction + * code paths avoid checking this task flag and instead, + * unconditionally run the instruction. However, STIBP and IBPB + * are independent and either can be set to conditionally + * enabled regardless of the mode of the other. + * + * If either is set to conditional, allow the task flag to be + * updated, unless it was force-disabled by a previous prctl + * call. Currently, this is possible on an AMD CPU which has the + * feature X86_FEATURE_AMD_STIBP_ALWAYS_ON. In this case, if the + * kernel is booted with 'spectre_v2_user=seccomp', then + * spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP and + * spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED. */ - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + if (!is_spec_ib_user_controlled() || task_spec_ib_force_disable(task)) return -EPERM; + task_clear_spec_ib_disable(task); task_update_spec_tif(task); break; @@ -1283,10 +1301,10 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return -EPERM; - if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + + if (!is_spec_ib_user_controlled()) return 0; + task_set_spec_ib_disable(task); if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); @@ -1351,20 +1369,17 @@ static int ib_prctl_get(struct task_struct *task) if (spectre_v2_user_ibpb == SPECTRE_V2_USER_NONE && spectre_v2_user_stibp == SPECTRE_V2_USER_NONE) return PR_SPEC_ENABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) - return PR_SPEC_DISABLE; - else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_ibpb == SPECTRE_V2_USER_SECCOMP || - spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL || - spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) { + else if (is_spec_ib_user_controlled()) { if (task_spec_ib_force_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; if (task_spec_ib_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - } else + } else if (spectre_v2_user_ibpb == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED) + return PR_SPEC_DISABLE; + else return PR_SPEC_NOT_AFFECTED; } diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7eb2a1c87969..3c417734790f 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -161,6 +161,21 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Setup early boot stage 4-/5-level pagetables. */ addq phys_base(%rip), %rax + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + * %rsi carries pointer to realmode data and is callee-clobbered. Save + * and restore it. + */ + pushq %rsi + movq %rax, %rdi + call sev_verify_cbit + popq %rsi + + /* Switch to new page-table */ movq %rax, %cr3 /* Ensure I am executing from virtual addresses */ @@ -279,6 +294,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" +#include "sev_verify_cbit.S" #ifdef CONFIG_HOTPLUG_CPU /* diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 57c2ecf43134..ce831f9448e7 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -200,8 +200,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, params->hdr.hardware_subarch = boot_params.hdr.hardware_subarch; /* Copying screen_info will do? */ - memcpy(¶ms->screen_info, &boot_params.screen_info, - sizeof(struct screen_info)); + memcpy(¶ms->screen_info, &screen_info, sizeof(struct screen_info)); /* Fill in memsize later */ params->screen_info.ext_mem_k = 0; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 5f83ccaab877..7d04b356d44d 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -178,6 +178,32 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) goto fail; regs->dx = val >> 32; + /* + * This is a VC handler and the #VC is only raised when SEV-ES is + * active, which means SEV must be active too. Do sanity checks on the + * CPUID results to make sure the hypervisor does not trick the kernel + * into the no-sev path. This could map sensitive data unencrypted and + * make it accessible to the hypervisor. + * + * In particular, check for: + * - Hypervisor CPUID bit + * - Availability of CPUID leaf 0x8000001f + * - SEV CPUID bit. + * + * The hypervisor might still report the wrong C-bit position, but this + * can't be checked here. + */ + + if ((fn == 1 && !(regs->cx & BIT(31)))) + /* Hypervisor bit */ + goto fail; + else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + /* SEV leaf check */ + goto fail; + else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) + /* SEV bit */ + goto fail; + /* Skip over the CPUID two-byte opcode */ regs->ip += 2; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 4a96726fbaf8..0bd1a0fc587e 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -374,8 +374,8 @@ fault: return ES_EXCEPTION; } -static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, - unsigned long vaddr, phys_addr_t *paddr) +static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long vaddr, phys_addr_t *paddr) { unsigned long va = (unsigned long)vaddr; unsigned int level; @@ -394,15 +394,19 @@ static bool vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt, if (user_mode(ctxt->regs)) ctxt->fi.error_code |= X86_PF_USER; - return false; + return ES_EXCEPTION; } + if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC)) + /* Emulated MMIO to/from encrypted memory not supported */ + return ES_UNSUPPORTED; + pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; pa |= va & ~page_level_mask(level); *paddr = pa; - return true; + return ES_OK; } /* Include code shared with pre-decompression boot stage */ @@ -731,6 +735,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, { u64 exit_code, exit_info_1, exit_info_2; unsigned long ghcb_pa = __pa(ghcb); + enum es_result res; phys_addr_t paddr; void __user *ref; @@ -740,11 +745,12 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt, exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE; - if (!vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr)) { - if (!read) + res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr); + if (res != ES_OK) { + if (res == ES_EXCEPTION && !read) ctxt->fi.error_code |= X86_PF_WRITE; - return ES_EXCEPTION; + return res; } exit_info_1 = paddr; diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S new file mode 100644 index 000000000000..ee04941a6546 --- /dev/null +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sev_verify_cbit.S - Code for verification of the C-bit position reported + * by the Hypervisor when running with SEV enabled. + * + * Copyright (c) 2020 Joerg Roedel (jroedel@suse.de) + * + * sev_verify_cbit() is called before switching to a new long-mode page-table + * at boot. + * + * Verify that the C-bit position is correct by writing a random value to + * an encrypted memory location while on the current page-table. Then it + * switches to the new page-table to verify the memory content is still the + * same. After that it switches back to the current page-table and when the + * check succeeded it returns. If the check failed the code invalidates the + * stack pointer and goes into a hlt loop. The stack-pointer is invalidated to + * make sure no interrupt or exception can get the CPU out of the hlt loop. + * + * New page-table pointer is expected in %rdi (first parameter) + * + */ +SYM_FUNC_START(sev_verify_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* First check if a C-bit was detected */ + movq sme_me_mask(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* sme_me_mask != 0 could mean SME or SEV - Check also for SEV */ + movq sev_status(%rip), %rsi + testq %rsi, %rsi + jz 3f + + /* Save CR4 in %rsi */ + movq %cr4, %rsi + + /* Disable Global Pages */ + movq %rsi, %rdx + andq $(~X86_CR4_PGE), %rdx + movq %rdx, %cr4 + + /* + * Verified that running under SEV - now get a random value using + * RDRAND. This instruction is mandatory when running as an SEV guest. + * + * Don't bail out of the loop if RDRAND returns errors. It is better to + * prevent forward progress than to work with a non-random value here. + */ +1: rdrand %rdx + jnc 1b + + /* Store value to memory and keep it in %rdx */ + movq %rdx, sev_check_data(%rip) + + /* Backup current %cr3 value to restore it later */ + movq %cr3, %rcx + + /* Switch to new %cr3 - This might unmap the stack */ + movq %rdi, %cr3 + + /* + * Compare value in %rdx with memory location. If C-bit is incorrect + * this would read the encrypted data and make the check fail. + */ + cmpq %rdx, sev_check_data(%rip) + + /* Restore old %cr3 */ + movq %rcx, %cr3 + + /* Restore previous CR4 */ + movq %rsi, %cr4 + + /* Check CMPQ result */ + je 3f + + /* + * The check failed, prevent any forward progress to prevent ROP + * attacks, invalidate the stack and go into a hlt loop. + */ + xorq %rsp, %rsp + subq $0x1000, %rsp +2: hlt + jmp 2b +3: +#endif + /* Return page-table pointer */ + movq %rdi, %rax + ret +SYM_FUNC_END(sev_verify_cbit) diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a7f3e12cfbdb..ddfd919be46c 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -165,16 +165,9 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) { signal_compat_build_tests(); - /* Don't leak in-kernel non-uapi flags to user-space */ - if (oact) - oact->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (!act) return; - /* Don't let flags to be set from userspace */ - act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (in_ia32_syscall()) act->sa.sa_flags |= SA_IA32_ABI; if (in_x32_syscall()) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3c70fb34028b..e19df6cde35d 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -793,19 +793,6 @@ static __always_inline unsigned long debug_read_clear_dr6(void) set_debugreg(DR6_RESERVED, 6); dr6 ^= DR6_RESERVED; /* Flip to positive polarity */ - /* - * Clear the virtual DR6 value, ptrace routines will set bits here for - * things we want signals for. - */ - current->thread.virtual_dr6 = 0; - - /* - * The SDM says "The processor clears the BTF flag when it - * generates a debug exception." Clear TIF_BLOCKSTEP to keep - * TIF_BLOCKSTEP in sync with the hardware BTF flag. - */ - clear_thread_flag(TIF_BLOCKSTEP); - return dr6; } @@ -873,6 +860,20 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, */ WARN_ON_ONCE(user_mode(regs)); + if (test_thread_flag(TIF_BLOCKSTEP)) { + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." but PTRACE_BLOCKSTEP requested + * it for userspace, but we just took a kernel #DB, so re-set + * BTF. + */ + unsigned long debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl |= DEBUGCTLMSR_BTF; + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + } + /* * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. @@ -936,6 +937,22 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, instrumentation_begin(); /* + * Start the virtual/ptrace DR6 value with just the DR_STEP mask + * of the real DR6. ptrace_triggered() will set the DR_TRAPn bits. + * + * Userspace expects DR_STEP to be visible in ptrace_get_debugreg(6) + * even if it is not the result of PTRACE_SINGLESTEP. + */ + current->thread.virtual_dr6 = (dr6 & DR_STEP); + + /* + * The SDM says "The processor clears the BTF flag when it + * generates a debug exception." Clear TIF_BLOCKSTEP to keep + * TIF_BLOCKSTEP in sync with the hardware BTF flag. + */ + clear_thread_flag(TIF_BLOCKSTEP); + + /* * If dr6 has no reason to give us about the origin of this trap, * then it's very likely the result of an icebp/int01 trap. * User wants a sigtrap for that. diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 6a339ce328e0..73f800100066 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -321,19 +321,12 @@ EXPORT_SYMBOL_GPL(unwind_get_return_address); unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) { - struct task_struct *task = state->task; - if (unwind_done(state)) return NULL; if (state->regs) return &state->regs->ip; - if (task != current && state->sp == task->thread.sp) { - struct inactive_task_frame *frame = (void *)task->thread.sp; - return &frame->ret_addr; - } - if (state->sp) return (unsigned long *)state->sp - 1; @@ -663,7 +656,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } else { struct inactive_task_frame *frame = (void *)task->thread.sp; - state->sp = task->thread.sp; + state->sp = task->thread.sp + sizeof(*frame); state->bp = READ_ONCE_NOCHECK(frame->bp); state->ip = READ_ONCE_NOCHECK(frame->ret_addr); state->signal = (void *)state->ip == ret_from_fork; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 17587f496ec7..1f96adff8dc4 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -225,7 +225,7 @@ static gfn_t get_mmio_spte_gfn(u64 spte) { u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask; - gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len) + gpa |= (spte >> SHADOW_NONPRESENT_OR_RSVD_MASK_LEN) & shadow_nonpresent_or_rsvd_mask; return gpa >> PAGE_SHIFT; @@ -591,15 +591,15 @@ static u64 mmu_spte_get_lockless(u64 *sptep) static u64 restore_acc_track_spte(u64 spte) { u64 new_spte = spte; - u64 saved_bits = (spte >> shadow_acc_track_saved_bits_shift) - & shadow_acc_track_saved_bits_mask; + u64 saved_bits = (spte >> SHADOW_ACC_TRACK_SAVED_BITS_SHIFT) + & SHADOW_ACC_TRACK_SAVED_BITS_MASK; WARN_ON_ONCE(spte_ad_enabled(spte)); WARN_ON_ONCE(!is_access_track_spte(spte)); new_spte &= ~shadow_acc_track_mask; - new_spte &= ~(shadow_acc_track_saved_bits_mask << - shadow_acc_track_saved_bits_shift); + new_spte &= ~(SHADOW_ACC_TRACK_SAVED_BITS_MASK << + SHADOW_ACC_TRACK_SAVED_BITS_SHIFT); new_spte |= saved_bits; return new_spte; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index d9c5665a55e9..fcac2cac78fe 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -55,7 +55,7 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access) mask |= shadow_mmio_value | access; mask |= gpa | shadow_nonpresent_or_rsvd_mask; mask |= (gpa & shadow_nonpresent_or_rsvd_mask) - << shadow_nonpresent_or_rsvd_mask_len; + << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN; return mask; } @@ -231,12 +231,12 @@ u64 mark_spte_for_access_track(u64 spte) !spte_can_locklessly_be_made_writable(spte), "kvm: Writable SPTE is not locklessly dirty-trackable\n"); - WARN_ONCE(spte & (shadow_acc_track_saved_bits_mask << - shadow_acc_track_saved_bits_shift), + WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK << + SHADOW_ACC_TRACK_SAVED_BITS_SHIFT), "kvm: Access Tracking saved bit locations are not zero\n"); - spte |= (spte & shadow_acc_track_saved_bits_mask) << - shadow_acc_track_saved_bits_shift; + spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) << + SHADOW_ACC_TRACK_SAVED_BITS_SHIFT; spte &= ~shadow_acc_track_mask; return spte; @@ -245,7 +245,7 @@ u64 mark_spte_for_access_track(u64 spte) void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask) { BUG_ON((u64)(unsigned)access_mask != access_mask); - WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << shadow_nonpresent_or_rsvd_mask_len)); + WARN_ON(mmio_value & (shadow_nonpresent_or_rsvd_mask << SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)); WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask); shadow_mmio_value = mmio_value | SPTE_MMIO_MASK; shadow_mmio_access_mask = access_mask; @@ -306,9 +306,9 @@ void kvm_mmu_reset_all_pte_masks(void) low_phys_bits = boot_cpu_data.x86_phys_bits; if (boot_cpu_has_bug(X86_BUG_L1TF) && !WARN_ON_ONCE(boot_cpu_data.x86_cache_bits >= - 52 - shadow_nonpresent_or_rsvd_mask_len)) { + 52 - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN)) { low_phys_bits = boot_cpu_data.x86_cache_bits - - shadow_nonpresent_or_rsvd_mask_len; + - SHADOW_NONPRESENT_OR_RSVD_MASK_LEN; shadow_nonpresent_or_rsvd_mask = rsvd_bits(low_phys_bits, boot_cpu_data.x86_cache_bits - 1); } diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 4ecf40e0b8fe..5c75a451c000 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -105,19 +105,19 @@ extern u64 __read_mostly shadow_acc_track_mask; extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; /* + * The number of high-order 1 bits to use in the mask above. + */ +#define SHADOW_NONPRESENT_OR_RSVD_MASK_LEN 5 + +/* * The mask/shift to use for saving the original R/X bits when marking the PTE * as not-present for access tracking purposes. We do not save the W bit as the * PTEs being access tracked also need to be dirty tracked, so the W bit will be * restored only when a write is attempted to the page. */ -static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK | - PT64_EPT_EXECUTABLE_MASK; -static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT; - -/* - * The number of high-order 1 bits to use in the mask above. - */ -static const u64 shadow_nonpresent_or_rsvd_mask_len = 5; +#define SHADOW_ACC_TRACK_SAVED_BITS_MASK (PT64_EPT_READABLE_MASK | \ + PT64_EPT_EXECUTABLE_MASK) +#define SHADOW_ACC_TRACK_SAVED_BITS_SHIFT PT64_SECOND_AVAIL_BITS_SHIFT /* * In some cases, we need to preserve the GFN of a non-present or reserved diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c index e5325bd0f304..f3199bb02f22 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/evmcs.c @@ -297,14 +297,13 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) { vmcs_conf->pin_based_exec_ctrl &= ~EVMCS1_UNSUPPORTED_PINCTRL; vmcs_conf->cpu_based_2nd_exec_ctrl &= ~EVMCS1_UNSUPPORTED_2NDEXEC; vmcs_conf->vmexit_ctrl &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; vmcs_conf->vmentry_ctrl &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; - } #endif diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/evmcs.h index e5f7a7ebf27d..bd41d9462355 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/evmcs.h @@ -185,7 +185,7 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +__init void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static inline void evmcs_write64(unsigned long field, u64 value) {} static inline void evmcs_write32(unsigned long field, u32 value) {} @@ -194,7 +194,6 @@ static inline u64 evmcs_read64(unsigned long field) { return 0; } static inline u32 evmcs_read32(unsigned long field) { return 0; } static inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} -static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {} static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d14c94d0aff1..47b8357b9751 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2560,8 +2560,10 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->vmexit_ctrl = _vmexit_control; vmcs_conf->vmentry_ctrl = _vmentry_control; - if (static_branch_unlikely(&enable_evmcs)) +#if IS_ENABLED(CONFIG_HYPERV) + if (enlightened_vmcs) evmcs_sanitize_exec_ctrls(vmcs_conf); +#endif return 0; } @@ -6834,7 +6836,6 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) static int vmx_create_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx; - unsigned long *msr_bitmap; int i, cpu, err; BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); @@ -6894,7 +6895,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS); bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS); - msr_bitmap = vmx->vmcs01.msr_bitmap; vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R); vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW); vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 397f599b20e5..f5ede41bf9e6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -265,13 +265,13 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, if (ignore_msrs) { if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored %s: 0x%x data 0x%llx\n", - op, msr, data); + kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n", + op, msr, data); /* Mask the error */ return 0; } else { - vcpu_debug_ratelimited(vcpu, "unhandled %s: 0x%x data 0x%llx\n", - op, msr, data); + kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n", + op, msr, data); return -ENOENT; } } diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 037faac46b0c..1e299ac73c86 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -16,8 +16,6 @@ * to a jmp to memcpy_erms which does the REP; MOVSB mem copy. */ -.weak memcpy - /* * memcpy - Copy a memory block. * @@ -30,7 +28,7 @@ * rax original destination */ SYM_FUNC_START_ALIAS(__memcpy) -SYM_FUNC_START_LOCAL(memcpy) +SYM_FUNC_START_WEAK(memcpy) ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \ "jmp memcpy_erms", X86_FEATURE_ERMS diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 7ff00ea64e4f..41902fe8b859 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -24,9 +24,7 @@ * Output: * rax: dest */ -.weak memmove - -SYM_FUNC_START_ALIAS(memmove) +SYM_FUNC_START_WEAK(memmove) SYM_FUNC_START(__memmove) mov %rdi, %rax diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 9ff15ee404a4..0bfd26e4ca9e 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -6,8 +6,6 @@ #include <asm/alternative-asm.h> #include <asm/export.h> -.weak memset - /* * ISO C memset - set a memory block to a byte value. This function uses fast * string to get better performance than the original function. The code is @@ -19,7 +17,7 @@ * * rax original destination */ -SYM_FUNC_START_ALIAS(memset) +SYM_FUNC_START_WEAK(memset) SYM_FUNC_START(__memset) /* * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index efbb3de472df..bc0833713be9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -39,6 +39,7 @@ */ u64 sme_me_mask __section(".data") = 0; u64 sev_status __section(".data") = 0; +u64 sev_check_data __section(".data") = 0; EXPORT_SYMBOL(sme_me_mask); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c index fdcd58af707a..27361cbb7ca9 100644 --- a/arch/x86/um/stub_segv.c +++ b/arch/x86/um/stub_segv.c @@ -8,7 +8,7 @@ #include <sysdep/mcontext.h> #include <sys/ucontext.h> -void __section(".__syscall_stub") +void __attribute__ ((__section__ (".__syscall_stub"))) stub_segv_handler(int sig, siginfo_t *info, void *p) { ucontext_t *uc = p; diff --git a/arch/xtensa/include/uapi/asm/signal.h b/arch/xtensa/include/uapi/asm/signal.h index 005dec5bfde4..79ddabaa4e5d 100644 --- a/arch/xtensa/include/uapi/asm/signal.h +++ b/arch/xtensa/include/uapi/asm/signal.h @@ -72,30 +72,6 @@ typedef struct { #define SIGRTMIN 32 #define SIGRTMAX (_NSIG-1) -/* - * SA_FLAGS values: - * - * SA_ONSTACK indicates that a registered stack_t will be used. - * SA_RESTART flag to get restarting signals (which were the default long ago) - * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop. - * SA_RESETHAND clears the handler when the signal is delivered. - * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies. - * SA_NODEFER prevents the current signal from being masked in the handler. - * - * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single - * Unix names RESETHAND and NODEFER respectively. - */ -#define SA_NOCLDSTOP 0x00000001 -#define SA_NOCLDWAIT 0x00000002 /* not supported yet */ -#define SA_SIGINFO 0x00000004 -#define SA_ONSTACK 0x08000000 -#define SA_RESTART 0x10000000 -#define SA_NODEFER 0x40000000 -#define SA_RESETHAND 0x80000000 - -#define SA_NOMASK SA_NODEFER -#define SA_ONESHOT SA_RESETHAND - #define SA_RESTORER 0x04000000 #define MINSIGSTKSZ 2048 diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index c6fc83efee0c..8731b7ad9308 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -89,8 +89,8 @@ static void __init free_highpages(void) /* set highmem page free */ for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &range_start, &range_end, NULL) { - unsigned long start = PHYS_PFN(range_start); - unsigned long end = PHYS_PFN(range_end); + unsigned long start = PFN_UP(range_start); + unsigned long end = PFN_DOWN(range_end); /* Ignore complete lowmem entries */ if (end <= max_low) |