diff options
Diffstat (limited to 'arch')
40 files changed, 326 insertions, 116 deletions
diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h index 4d17cacd1462..432402c8e47f 100644 --- a/arch/alpha/include/asm/irq.h +++ b/arch/alpha/include/asm/irq.h @@ -56,15 +56,15 @@ #elif defined(CONFIG_ALPHA_DP264) || \ defined(CONFIG_ALPHA_LYNX) || \ - defined(CONFIG_ALPHA_SHARK) || \ - defined(CONFIG_ALPHA_EIGER) + defined(CONFIG_ALPHA_SHARK) # define NR_IRQS 64 #elif defined(CONFIG_ALPHA_TITAN) #define NR_IRQS 80 #elif defined(CONFIG_ALPHA_RAWHIDE) || \ - defined(CONFIG_ALPHA_TAKARA) + defined(CONFIG_ALPHA_TAKARA) || \ + defined(CONFIG_ALPHA_EIGER) # define NR_IRQS 128 #elif defined(CONFIG_ALPHA_WILDFIRE) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index d73dc473fbb9..188fc9256baf 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,7 +78,7 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+8 : (r)-10]) + (r) <= 18 ? (r)+10 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 04758a2a87f0..67d77eee9433 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -644,6 +644,17 @@ }; }; +/* Configure pwm clock source for timers 8 & 9 */ +&timer8 { + assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>; + assigned-clock-parents = <&sys_clkin_ck>; +}; + +&timer9 { + assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>; + assigned-clock-parents = <&sys_clkin_ck>; +}; + /* * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for * uart1 wakeirq. diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi index bc853ebeda22..61a06f6add3c 100644 --- a/arch/arm/boot/dts/omap5-board-common.dtsi +++ b/arch/arm/boot/dts/omap5-board-common.dtsi @@ -317,7 +317,8 @@ palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { pinctrl-single,pins = < - OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) /* sys_nirq1 */ + /* sys_nirq1 is pulled down as the SoC is inverting it for GIC */ + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) >; }; @@ -385,7 +386,8 @@ palmas: palmas@48 { compatible = "ti,palmas"; - interrupts = <GIC_SPI 7 IRQ_TYPE_NONE>; /* IRQ_SYS_1N */ + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_LOW>; reg = <0x48>; interrupt-controller; #interrupt-cells = <2>; @@ -651,7 +653,8 @@ pinctrl-names = "default"; pinctrl-0 = <&twl6040_pins>; - interrupts = <GIC_SPI 119 IRQ_TYPE_NONE>; /* IRQ_SYS_2N cascaded to gic */ + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_LOW>; /* audpwron gpio defined in the board specific dts */ diff --git a/arch/arm/boot/dts/omap5-cm-t54.dts b/arch/arm/boot/dts/omap5-cm-t54.dts index 5e21fb430a65..e78d3718f145 100644 --- a/arch/arm/boot/dts/omap5-cm-t54.dts +++ b/arch/arm/boot/dts/omap5-cm-t54.dts @@ -181,6 +181,13 @@ OMAP5_IOPAD(0x0042, PIN_INPUT_PULLDOWN | MUX_MODE6) /* llib_wakereqin.gpio1_wk15 */ >; }; + + palmas_sys_nirq_pins: pinmux_palmas_sys_nirq_pins { + pinctrl-single,pins = < + /* sys_nirq1 is pulled down as the SoC is inverting it for GIC */ + OMAP5_IOPAD(0x068, PIN_INPUT_PULLUP | MUX_MODE0) + >; + }; }; &omap5_pmx_core { @@ -414,8 +421,11 @@ palmas: palmas@48 { compatible = "ti,palmas"; - interrupts = <GIC_SPI 7 IRQ_TYPE_NONE>; /* IRQ_SYS_1N */ reg = <0x48>; + pinctrl-0 = <&palmas_sys_nirq_pins>; + pinctrl-names = "default"; + /* sys_nirq/ext_sys_irq pins get inverted at mpuss wakeupgen */ + interrupts = <GIC_SPI 7 IRQ_TYPE_LEVEL_LOW>; interrupt-controller; #interrupt-cells = <2>; ti,system-power-controller; diff --git a/arch/arm/boot/dts/rk3188.dtsi b/arch/arm/boot/dts/rk3188.dtsi index 4acb501dd3f8..3ed49898f4b2 100644 --- a/arch/arm/boot/dts/rk3188.dtsi +++ b/arch/arm/boot/dts/rk3188.dtsi @@ -719,7 +719,6 @@ pm_qos = <&qos_lcdc0>, <&qos_lcdc1>, <&qos_cif0>, - <&qos_cif1>, <&qos_ipp>, <&qos_rga>; }; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index ca56537b61bc..50e89869178a 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -48,6 +48,7 @@ #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -147,6 +148,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +struct vcpu_reset_state { + unsigned long pc; + unsigned long r0; + bool be; + bool reset; +}; + struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; @@ -186,6 +194,8 @@ struct kvm_vcpu_arch { /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; + struct vcpu_reset_state reset_state; + /* Detect first run of a vcpu */ bool has_run_once; }; diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h index c4b1d4fb1797..de2089501b8b 100644 --- a/arch/arm/include/asm/stage2_pgtable.h +++ b/arch/arm/include/asm/stage2_pgtable.h @@ -76,4 +76,9 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm) #define S2_PMD_MASK PMD_MASK #define S2_PMD_SIZE PMD_SIZE +static inline bool kvm_stage2_has_pmd(struct kvm *kvm) +{ + return true; +} + #endif /* __ARM_S2_PGTABLE_H_ */ diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 222c1635bc7a..e8bd288fd5be 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -1450,6 +1450,6 @@ void kvm_reset_coprocs(struct kvm_vcpu *vcpu) reset_coproc_regs(vcpu, table, num); for (num = 1; num < NR_CP15_REGS; num++) - if (vcpu_cp15(vcpu, num) == 0x42424242) - panic("Didn't reset vcpu_cp15(vcpu, %zi)", num); + WARN(vcpu_cp15(vcpu, num) == 0x42424242, + "Didn't reset vcpu_cp15(vcpu, %zi)", num); } diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index 5ed0c3ee33d6..e53327912adc 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -26,6 +26,7 @@ #include <asm/cputype.h> #include <asm/kvm_arm.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> @@ -69,6 +70,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset CP15 registers */ kvm_reset_coprocs(vcpu); + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (READ_ONCE(vcpu->arch.reset_state.reset)) { + unsigned long target_pc = vcpu->arch.reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (target_pc & 1) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (vcpu->arch.reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); + + vcpu->arch.reset_state.reset = false; + } + /* Reset arch_timer context */ return kvm_timer_vcpu_reset(vcpu); } diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index a8b291f00109..dae514c8276a 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -152,6 +152,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) && (cx->mpu_logic_state == PWRDM_POWER_OFF); + /* Enter broadcast mode for periodic timers */ + tick_broadcast_enable(); + + /* Enter broadcast mode for one-shot timers */ tick_broadcast_enter(); /* @@ -218,15 +222,6 @@ fail: return index; } -/* - * For each cpu, setup the broadcast timer because local timers - * stops for the states above C1. - */ -static void omap_setup_broadcast_timer(void *arg) -{ - tick_broadcast_enable(); -} - static struct cpuidle_driver omap4_idle_driver = { .name = "omap4_idle", .owner = THIS_MODULE, @@ -319,8 +314,5 @@ int __init omap4_idle_init(void) if (!cpu_clkdm[0] || !cpu_clkdm[1]) return -ENODEV; - /* Configure the broadcast timer on each cpu */ - on_each_cpu(omap_setup_broadcast_timer, NULL, 1); - return cpuidle_register(idle_driver, cpu_online_mask); } diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c index f86b72d1d59e..1444b4b4bd9f 100644 --- a/arch/arm/mach-omap2/display.c +++ b/arch/arm/mach-omap2/display.c @@ -83,6 +83,7 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes) u32 enable_mask, enable_shift; u32 pipd_mask, pipd_shift; u32 reg; + int ret; if (dsi_id == 0) { enable_mask = OMAP4_DSI1_LANEENABLE_MASK; @@ -98,7 +99,11 @@ static int omap4_dsi_mux_pads(int dsi_id, unsigned lanes) return -ENODEV; } - regmap_read(omap4_dsi_mux_syscon, OMAP4_DSIPHY_SYSCON_OFFSET, ®); + ret = regmap_read(omap4_dsi_mux_syscon, + OMAP4_DSIPHY_SYSCON_OFFSET, + ®); + if (ret) + return ret; reg &= ~enable_mask; reg &= ~pipd_mask; diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c index fc5fb776a710..17558be4bf0a 100644 --- a/arch/arm/mach-omap2/omap-wakeupgen.c +++ b/arch/arm/mach-omap2/omap-wakeupgen.c @@ -50,6 +50,9 @@ #define OMAP4_NR_BANKS 4 #define OMAP4_NR_IRQS 128 +#define SYS_NIRQ1_EXT_SYS_IRQ_1 7 +#define SYS_NIRQ2_EXT_SYS_IRQ_2 119 + static void __iomem *wakeupgen_base; static void __iomem *sar_base; static DEFINE_RAW_SPINLOCK(wakeupgen_lock); @@ -153,6 +156,37 @@ static void wakeupgen_unmask(struct irq_data *d) irq_chip_unmask_parent(d); } +/* + * The sys_nirq pins bypass peripheral modules and are wired directly + * to MPUSS wakeupgen. They get automatically inverted for GIC. + */ +static int wakeupgen_irq_set_type(struct irq_data *d, unsigned int type) +{ + bool inverted = false; + + switch (type) { + case IRQ_TYPE_LEVEL_LOW: + type &= ~IRQ_TYPE_LEVEL_MASK; + type |= IRQ_TYPE_LEVEL_HIGH; + inverted = true; + break; + case IRQ_TYPE_EDGE_FALLING: + type &= ~IRQ_TYPE_EDGE_BOTH; + type |= IRQ_TYPE_EDGE_RISING; + inverted = true; + break; + default: + break; + } + + if (inverted && d->hwirq != SYS_NIRQ1_EXT_SYS_IRQ_1 && + d->hwirq != SYS_NIRQ2_EXT_SYS_IRQ_2) + pr_warn("wakeupgen: irq%li polarity inverted in dts\n", + d->hwirq); + + return irq_chip_set_type_parent(d, type); +} + #ifdef CONFIG_HOTPLUG_CPU static DEFINE_PER_CPU(u32 [MAX_NR_REG_BANKS], irqmasks); @@ -446,7 +480,7 @@ static struct irq_chip wakeupgen_chip = { .irq_mask = wakeupgen_mask, .irq_unmask = wakeupgen_unmask, .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_set_type = irq_chip_set_type_parent, + .irq_set_type = wakeupgen_irq_set_type, .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, #ifdef CONFIG_SMP .irq_set_affinity = irq_chip_set_affinity_parent, diff --git a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts index 64acccc4bfcb..f74b13aa5aa5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts @@ -227,34 +227,34 @@ pinctrl_usdhc1_100mhz: usdhc1-100grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x85 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc5 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc5 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc5 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc5 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc5 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc5 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc5 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc5 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc5 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x85 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x8d + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xcd + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xcd + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xcd + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xcd + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xcd + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xcd + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xcd + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xcd + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xcd + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x8d MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; pinctrl_usdhc1_200mhz: usdhc1-200grp { fsl,pins = < - MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x87 - MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xc7 - MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xc7 - MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xc7 - MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xc7 - MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xc7 - MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xc7 - MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xc7 - MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xc7 - MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xc7 - MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x87 + MX8MQ_IOMUXC_SD1_CLK_USDHC1_CLK 0x9f + MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0xdf + MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0xdf + MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0xdf + MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0xdf + MX8MQ_IOMUXC_SD1_DATA3_USDHC1_DATA3 0xdf + MX8MQ_IOMUXC_SD1_DATA4_USDHC1_DATA4 0xdf + MX8MQ_IOMUXC_SD1_DATA5_USDHC1_DATA5 0xdf + MX8MQ_IOMUXC_SD1_DATA6_USDHC1_DATA6 0xdf + MX8MQ_IOMUXC_SD1_DATA7_USDHC1_DATA7 0xdf + MX8MQ_IOMUXC_SD1_STROBE_USDHC1_STROBE 0x9f MX8MQ_IOMUXC_SD1_RESET_B_USDHC1_RESET_B 0xc1 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 8e9d6d5ed7b2..b6d31499fb43 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -360,6 +360,8 @@ <&clk IMX8MQ_CLK_NAND_USDHC_BUS>, <&clk IMX8MQ_CLK_USDHC1_ROOT>; clock-names = "ipg", "ahb", "per"; + assigned-clocks = <&clk IMX8MQ_CLK_USDHC1>; + assigned-clock-rates = <400000000>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; bus-width = <4>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index bd937d68ca3b..040b36ef0dd2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -40,6 +40,7 @@ pinctrl-0 = <&usb30_host_drv>; regulator-name = "vcc_host_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; @@ -51,6 +52,7 @@ pinctrl-0 = <&usb20_host_drv>; regulator-name = "vcc_host1_5v"; regulator-always-on; + regulator-boot-on; vin-supply = <&vcc_sys>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts index 1ee0dc0d9f10..d1cf404b8708 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-bob.dts @@ -22,7 +22,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts index 81e73103fa78..15e254a77391 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts @@ -43,7 +43,7 @@ backlight = <&backlight>; power-supply = <&pp3300_disp>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts index 0b8f1edbd746..b48a63c3efc3 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-sapphire-excavator.dts @@ -91,7 +91,7 @@ pinctrl-0 = <&lcd_panel_reset>; power-supply = <&vcc3v3_s0>; - ports { + port { panel_in_edp: endpoint { remote-endpoint = <&edp_out_panel>; }; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7732d0ba4e60..da3fc7324d68 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -48,6 +48,7 @@ #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); @@ -208,6 +209,13 @@ struct kvm_cpu_context { typedef struct kvm_cpu_context kvm_cpu_context_t; +struct vcpu_reset_state { + unsigned long pc; + unsigned long r0; + bool be; + bool reset; +}; + struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; @@ -297,6 +305,9 @@ struct kvm_vcpu_arch { /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; + /* Additional reset state */ + struct vcpu_reset_state reset_state; + /* True when deferrable sysregs are loaded on the physical CPU, * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ bool sysregs_loaded_on_cpu; diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index b0b1478094b4..421ebf6f7086 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -23,6 +23,7 @@ #include <kvm/arm_psci.h> #include <asm/cpufeature.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> @@ -107,6 +108,7 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) write_sysreg(kvm_get_hyp_vector(), vbar_el1); } +NOKPROBE_SYMBOL(activate_traps_vhe); static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) { @@ -154,6 +156,7 @@ static void deactivate_traps_vhe(void) write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); write_sysreg(vectors, vbar_el1); } +NOKPROBE_SYMBOL(deactivate_traps_vhe); static void __hyp_text __deactivate_traps_nvhe(void) { @@ -513,6 +516,7 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) return exit_code; } +NOKPROBE_SYMBOL(kvm_vcpu_run_vhe); /* Switch to the guest for legacy non-VHE systems */ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) @@ -620,6 +624,7 @@ static void __hyp_call_panic_vhe(u64 spsr, u64 elr, u64 par, read_sysreg_el2(esr), read_sysreg_el2(far), read_sysreg(hpfar_el2), par, vcpu); } +NOKPROBE_SYMBOL(__hyp_call_panic_vhe); void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) { diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 68d6f7c3b237..b426e2cf973c 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -18,6 +18,7 @@ #include <linux/compiler.h> #include <linux/kvm_host.h> +#include <asm/kprobes.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> @@ -98,12 +99,14 @@ void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_save_common_state(ctxt); __sysreg_save_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { @@ -188,12 +191,14 @@ void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) { __sysreg_restore_common_state(ctxt); __sysreg_restore_el2_return_state(ctxt); } +NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index b72a3dd56204..f16a5f8ff2b4 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -32,6 +32,7 @@ #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> /* Maximum phys_shift supported for any VM on this host */ @@ -105,16 +106,33 @@ int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext) * This function finds the right table above and sets the registers on * the virtual CPU struct to their architecturally defined reset * values. + * + * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT + * ioctl or as part of handling a request issued by another VCPU in the PSCI + * handling code. In the first case, the VCPU will not be loaded, and in the + * second case the VCPU will be loaded. Because this function operates purely + * on the memory-backed valus of system registers, we want to do a full put if + * we were loaded (handling a request) and load the values back at the end of + * the function. Otherwise we leave the state alone. In both cases, we + * disable preemption around the vcpu reset as we would otherwise race with + * preempt notifiers which also call put/load. */ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) { const struct kvm_regs *cpu_reset; + int ret = -EINVAL; + bool loaded; + + preempt_disable(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); switch (vcpu->arch.target) { default: if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) { if (!cpu_has_32bit_el1()) - return -EINVAL; + goto out; cpu_reset = &default_regs_reset32; } else { cpu_reset = &default_regs_reset; @@ -129,6 +147,29 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) /* Reset system registers */ kvm_reset_sys_regs(vcpu); + /* + * Additional reset state handling that PSCI may have imposed on us. + * Must be done after all the sys_reg reset. + */ + if (vcpu->arch.reset_state.reset) { + unsigned long target_pc = vcpu->arch.reset_state.pc; + + /* Gracefully handle Thumb2 entry point */ + if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { + target_pc &= ~1UL; + vcpu_set_thumb(vcpu); + } + + /* Propagate caller endianness */ + if (vcpu->arch.reset_state.be) + kvm_vcpu_set_be(vcpu); + + *vcpu_pc(vcpu) = target_pc; + vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0); + + vcpu->arch.reset_state.reset = false; + } + /* Reset PMU */ kvm_pmu_vcpu_reset(vcpu); @@ -137,7 +178,12 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG; /* Reset timer */ - return kvm_timer_vcpu_reset(vcpu); + ret = kvm_timer_vcpu_reset(vcpu); +out: + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + preempt_enable(); + return ret; } void kvm_set_ipa_limit(void) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e3e37228ae4e..c936aa40c3f4 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -314,12 +314,29 @@ static bool trap_raz_wi(struct kvm_vcpu *vcpu, return read_zero(vcpu, p); } -static bool trap_undef(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *r) +/* + * ARMv8.1 mandates at least a trivial LORegion implementation, where all the + * RW registers are RES0 (which we can implement as RAZ/WI). On an ARMv8.0 + * system, these registers should UNDEF. LORID_EL1 being a RO register, we + * treat it separately. + */ +static bool trap_loregion(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) { - kvm_inject_undefined(vcpu); - return false; + u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, + (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + + if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { + kvm_inject_undefined(vcpu); + return false; + } + + if (p->is_write && sr == SYS_LORID_EL1) + return write_to_read_only(vcpu, p, r); + + return trap_raz_wi(vcpu, p, r); } static bool trap_oslsr_el1(struct kvm_vcpu *vcpu, @@ -1048,11 +1065,6 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz) if (val & ptrauth_mask) kvm_debug("ptrauth unsupported for guests, suppressing\n"); val &= ~ptrauth_mask; - } else if (id == SYS_ID_AA64MMFR1_EL1) { - if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT)) - kvm_debug("LORegions unsupported for guests, suppressing\n"); - - val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT); } return val; @@ -1338,11 +1350,11 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, - { SYS_DESC(SYS_LORSA_EL1), trap_undef }, - { SYS_DESC(SYS_LOREA_EL1), trap_undef }, - { SYS_DESC(SYS_LORN_EL1), trap_undef }, - { SYS_DESC(SYS_LORC_EL1), trap_undef }, - { SYS_DESC(SYS_LORID_EL1), trap_undef }, + { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, + { SYS_DESC(SYS_LOREA_EL1), trap_loregion }, + { SYS_DESC(SYS_LORN_EL1), trap_loregion }, + { SYS_DESC(SYS_LORC_EL1), trap_loregion }, + { SYS_DESC(SYS_LORID_EL1), trap_loregion }, { SYS_DESC(SYS_VBAR_EL1), NULL, reset_val, VBAR_EL1, 0 }, { SYS_DESC(SYS_DISR_EL1), NULL, reset_val, DISR_EL1, 0 }, @@ -2596,7 +2608,9 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu) table = get_target_table(vcpu->arch.target, true, &num); reset_sys_reg_descs(vcpu, table, num); - for (num = 1; num < NR_SYS_REGS; num++) - if (__vcpu_sys_reg(vcpu, num) == 0x4242424242424242) - panic("Didn't reset __vcpu_sys_reg(%zi)", num); + for (num = 1; num < NR_SYS_REGS; num++) { + if (WARN(__vcpu_sys_reg(vcpu, num) == 0x4242424242424242, + "Didn't reset __vcpu_sys_reg(%zi)\n", num)) + break; + } } diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h index edfcbb25fd9f..dcea277c09ae 100644 --- a/arch/csky/include/asm/pgtable.h +++ b/arch/csky/include/asm/pgtable.h @@ -45,8 +45,8 @@ ((pte_t *)page_address(pmd_page(*(dir))) + __pte_offset_t(address)) #define pmd_page(pmd) (pfn_to_page(pmd_phys(pmd) >> PAGE_SHIFT)) #define pte_clear(mm, addr, ptep) set_pte((ptep), \ - (((unsigned int)addr&0x80000000)?__pte(1):__pte(0))) -#define pte_none(pte) (!(pte_val(pte)&0xfffffffe)) + (((unsigned int) addr & PAGE_OFFSET) ? __pte(_PAGE_GLOBAL) : __pte(0))) +#define pte_none(pte) (!(pte_val(pte) & ~_PAGE_GLOBAL)) #define pte_present(pte) (pte_val(pte) & _PAGE_PRESENT) #define pte_pfn(x) ((unsigned long)((x).pte_low >> PAGE_SHIFT)) #define pfn_pte(pfn, prot) __pte(((unsigned long long)(pfn) << PAGE_SHIFT) \ @@ -241,6 +241,11 @@ static inline pte_t pte_mkyoung(pte_t pte) #define pgd_index(address) ((address) >> PGDIR_SHIFT) +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); + /* * Macro to make mark a page protection value as "uncacheable". Note * that "protection" is really a misnomer here as the protection value diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 8f454810514f..21e0bd5293dd 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -49,7 +49,7 @@ struct thread_struct { }; #define INIT_THREAD { \ - .ksp = (unsigned long) init_thread_union.stack + THREAD_SIZE, \ + .ksp = sizeof(init_stack) + (unsigned long) &init_stack, \ .sr = DEFAULT_PSR_VALUE, \ } @@ -95,7 +95,7 @@ unsigned long get_wchan(struct task_struct *p); #define KSTK_ESP(tsk) (task_pt_regs(tsk)->usp) #define task_pt_regs(p) \ - ((struct pt_regs *)(THREAD_SIZE + p->stack) - 1) + ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) #define cpu_relax() barrier() diff --git a/arch/csky/kernel/dumpstack.c b/arch/csky/kernel/dumpstack.c index 659253e9989c..d67f9777cfd9 100644 --- a/arch/csky/kernel/dumpstack.c +++ b/arch/csky/kernel/dumpstack.c @@ -38,7 +38,11 @@ void show_stack(struct task_struct *task, unsigned long *stack) if (task) stack = (unsigned long *)thread_saved_fp(task); else +#ifdef CONFIG_STACKTRACE + asm volatile("mov %0, r8\n":"=r"(stack)::"memory"); +#else stack = (unsigned long *)&stack; +#endif } show_trace(stack); diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c index 57f1afe19a52..f2f12fff36f7 100644 --- a/arch/csky/kernel/ptrace.c +++ b/arch/csky/kernel/ptrace.c @@ -8,6 +8,7 @@ #include <linux/ptrace.h> #include <linux/regset.h> #include <linux/sched.h> +#include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/smp.h> #include <linux/uaccess.h> @@ -159,7 +160,7 @@ static int fpr_set(struct task_struct *target, static const struct user_regset csky_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, - .n = ELF_NGREG, + .n = sizeof(struct pt_regs) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .get = &gpr_get, diff --git a/arch/csky/kernel/smp.c b/arch/csky/kernel/smp.c index ddc4dd79f282..b07a534b3062 100644 --- a/arch/csky/kernel/smp.c +++ b/arch/csky/kernel/smp.c @@ -160,7 +160,8 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) { unsigned long mask = 1 << cpu; - secondary_stack = (unsigned int)tidle->stack + THREAD_SIZE - 8; + secondary_stack = + (unsigned int) task_stack_page(tidle) + THREAD_SIZE - 8; secondary_hint = mfcr("cr31"); secondary_ccr = mfcr("cr18"); diff --git a/arch/csky/mm/ioremap.c b/arch/csky/mm/ioremap.c index cb7c03e5cd21..8473b6bdf512 100644 --- a/arch/csky/mm/ioremap.c +++ b/arch/csky/mm/ioremap.c @@ -46,3 +46,17 @@ void iounmap(void __iomem *addr) vunmap((void *)((unsigned long)addr & PAGE_MASK)); } EXPORT_SYMBOL(iounmap); + +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot) +{ + if (!pfn_valid(pfn)) { + vma_prot.pgprot |= _PAGE_SO; + return pgprot_noncached(vma_prot); + } else if (file->f_flags & O_SYNC) { + return pgprot_noncached(vma_prot); + } + + return vma_prot; +} +EXPORT_SYMBOL(phys_mem_access_prot); diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c9bfe526ca9d..d8c8d7c9df15 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -904,7 +904,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -951,7 +951,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 2fa2942be221..470755cb7558 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -35,6 +35,12 @@ #define _PAGE_SPECIAL _PAGE_SOFT #define _PAGE_TABLE _PAGE_PRESENT +/* + * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to + * distinguish them from swapped out pages + */ +#define _PAGE_PROT_NONE _PAGE_READ + #define _PAGE_PFN_SHIFT 10 /* Set of bits to preserve across pte_modify() */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 16301966d65b..a8179a8c1491 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -44,7 +44,7 @@ /* Page protection bits */ #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) -#define PAGE_NONE __pgprot(0) +#define PAGE_NONE __pgprot(_PAGE_PROT_NONE) #define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) #define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) @@ -98,7 +98,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; static inline int pmd_present(pmd_t pmd) { - return (pmd_val(pmd) & _PAGE_PRESENT); + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pmd_none(pmd_t pmd) @@ -178,7 +178,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr) static inline int pte_present(pte_t pte) { - return (pte_val(pte) & _PAGE_PRESENT); + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pte_none(pte_t pte) @@ -380,7 +380,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, * * Format of swap PTE: * bit 0: _PAGE_PRESENT (zero) - * bit 1: reserved for future use (zero) + * bit 1: _PAGE_PROT_NONE (zero) * bits 2 to 6: swap type * bits 7 to XLEN-1: swap offset */ diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 1e1395d63dab..65df1dfdc303 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -18,8 +18,6 @@ #include <asm/cache.h> #include <asm/thread_info.h> -#define MAX_BYTES_PER_LONG 0x10 - OUTPUT_ARCH(riscv) ENTRY(_start) @@ -76,6 +74,8 @@ SECTIONS *(.sbss*) } + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + EXCEPTION_TABLE(0x10) NOTES @@ -83,10 +83,6 @@ SECTIONS *(.rel.dyn*) } - BSS_SECTION(MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG) - _end = .; STABS_DEBUG diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index 537f97fde37f..b6796e616812 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -30,10 +30,10 @@ .section .text ENTRY(swsusp_arch_suspend) lg %r1,__LC_NODAT_STACK - aghi %r1,-STACK_FRAME_OVERHEAD stmg %r6,%r15,__SF_GPRS(%r1) + aghi %r1,-STACK_FRAME_OVERHEAD stg %r15,__SF_BACKCHAIN(%r1) - lgr %r1,%r15 + lgr %r15,%r1 /* Store FPU registers */ brasl %r14,save_fpu_regs diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index a966d7bfac57..4266a4de3160 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -382,7 +382,9 @@ static void zpci_irq_handler(struct airq_struct *airq) if (ai == -1UL) break; inc_irq_stat(IRQIO_MSI); + airq_iv_lock(aibv, ai); generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } } @@ -408,7 +410,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = aisb; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); if (!zdev->aibv) return -ENOMEM; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d8ea4ebd79e7..d737a51a53ca 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2473,6 +2473,10 @@ static int nested_check_vm_execution_controls(struct kvm_vcpu *vcpu, (nested_cpu_has_vpid(vmcs12) && !vmcs12->virtual_processor_id)) return -EINVAL; + if (!nested_cpu_has_preemption_timer(vmcs12) && + nested_cpu_has_save_preemption_timer(vmcs12)) + return -EINVAL; + if (nested_cpu_has_ept(vmcs12) && !valid_ept_address(vcpu, vmcs12->ept_pointer)) return -EINVAL; @@ -5557,9 +5561,11 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps, * secondary cpu-based controls. Do not include those that * depend on CPUID bits, they are added later by vmx_cpuid_update. */ - rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, - msrs->secondary_ctls_low, - msrs->secondary_ctls_high); + if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2, + msrs->secondary_ctls_low, + msrs->secondary_ctls_high); + msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high &= SECONDARY_EXEC_DESC | diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 95d618045001..30a6bcd735ec 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -863,7 +863,8 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr, if (!entry_only) j = find_msr(&m->host, msr); - if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) { + if ((i < 0 && m->guest.nr == NR_AUTOLOAD_MSRS) || + (j < 0 && m->host.nr == NR_AUTOLOAD_MSRS)) { printk_once(KERN_WARNING "Not enough msr switch entries. " "Can't add msr %x\n", msr); return; @@ -1193,21 +1194,6 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) if (!pi_test_sn(pi_desc) && vcpu->cpu == cpu) return; - /* - * First handle the simple case where no cmpxchg is necessary; just - * allow posting non-urgent interrupts. - * - * If the 'nv' field is POSTED_INTR_WAKEUP_VECTOR, do not change - * PI.NDST: pi_post_block will do it for us and the wakeup_handler - * expects the VCPU to be on the blocked_vcpu_list that matches - * PI.NDST. - */ - if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR || - vcpu->cpu == cpu) { - pi_clear_sn(pi_desc); - return; - } - /* The full case. */ do { old.control = new.control = pi_desc->control; @@ -1222,6 +1208,17 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.sn = 0; } while (cmpxchg64(&pi_desc->control, old.control, new.control) != old.control); + + /* + * Clear SN before reading the bitmap. The VT-d firmware + * writes the bitmap and reads SN atomically (5.2.3 in the + * spec), so it doesn't really have a memory barrier that + * pairs with this, but we cannot do that and we need one. + */ + smp_mb__after_atomic(); + + if (!bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS)) + pi_set_on(pi_desc); } /* diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 99328954c2fc..0ac0a64c7790 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -337,16 +337,16 @@ static inline int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); } -static inline void pi_clear_sn(struct pi_desc *pi_desc) +static inline void pi_set_sn(struct pi_desc *pi_desc) { - return clear_bit(POSTED_INTR_SN, + return set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); } -static inline void pi_set_sn(struct pi_desc *pi_desc) +static inline void pi_set_on(struct pi_desc *pi_desc) { - return set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); + set_bit(POSTED_INTR_ON, + (unsigned long *)&pi_desc->control); } static inline void pi_clear_on(struct pi_desc *pi_desc) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e67ecf25e690..941f932373d0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7801,7 +7801,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * 1) We should set ->mode before checking ->requests. Please see * the comment in kvm_vcpu_exiting_guest_mode(). * - * 2) For APICv, we should set ->mode before checking PIR.ON. This + * 2) For APICv, we should set ->mode before checking PID.ON. This * pairs with the memory barrier implicit in pi_test_and_set_on * (see vmx_deliver_posted_interrupt). * |