diff options
163 files changed, 1360 insertions, 898 deletions
diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 82236a17b5e6..97b7ca8b9b86 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -92,11 +92,11 @@ device. Switch ID ^^^^^^^^^ -The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same -physical ID for each port of a switch. The ID must be unique between switches -on the same system. The ID does not need to be unique between switches on -different systems. +The switchdev driver must implement the net_device operation +ndo_get_port_parent_id for each port netdev, returning the same physical ID for +each port of a switch. The ID must be unique between switches on the same +system. The ID does not need to be unique between switches on different +systems. The switch ID is used to locate ports on a switch and to know if aggregated ports belong to the same switch. diff --git a/MAINTAINERS b/MAINTAINERS index d78f3714de08..65eb7207fcc3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3399,9 +3399,8 @@ F: Documentation/media/v4l-drivers/cafe_ccic* F: drivers/media/platform/marvell-ccic/ CAIF NETWORK LAYER -M: Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no> L: netdev@vger.kernel.org -S: Supported +S: Orphan F: Documentation/networking/caif/ F: drivers/net/caif/ F: include/uapi/linux/caif/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 664e918e2624..26524b75970a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1400,6 +1400,7 @@ config NR_CPUS config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" depends on SMP + select GENERIC_IRQ_MIGRATION help Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. 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/irq.h b/arch/arm/include/asm/irq.h index c883fcbe93b6..46d41140df27 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -25,7 +25,6 @@ #ifndef __ASSEMBLY__ struct irqaction; struct pt_regs; -extern void migrate_irqs(void); extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); 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/kernel/irq.c b/arch/arm/kernel/irq.c index 9908dacf9229..844861368cd5 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -31,7 +31,6 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/seq_file.h> -#include <linux/ratelimit.h> #include <linux/errno.h> #include <linux/list.h> #include <linux/kallsyms.h> @@ -109,64 +108,3 @@ int __init arch_probe_nr_irqs(void) return nr_irqs; } #endif - -#ifdef CONFIG_HOTPLUG_CPU -static bool migrate_one_irq(struct irq_desc *desc) -{ - struct irq_data *d = irq_desc_get_irq_data(desc); - const struct cpumask *affinity = irq_data_get_affinity_mask(d); - struct irq_chip *c; - bool ret = false; - - /* - * If this is a per-CPU interrupt, or the affinity does not - * include this CPU, then we have nothing to do. - */ - if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) - return false; - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - affinity = cpu_online_mask; - ret = true; - } - - c = irq_data_get_irq_chip(d); - if (!c->irq_set_affinity) - pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) - cpumask_copy(irq_data_get_affinity_mask(d), affinity); - - return ret; -} - -/* - * The current CPU has been marked offline. Migrate IRQs off this CPU. - * If the affinity settings do not allow other CPUs, force them onto any - * available CPU. - * - * Note: we must iterate over all IRQs, whether they have an attached - * action structure or not, as we need to get chained interrupts too. - */ -void migrate_irqs(void) -{ - unsigned int i; - struct irq_desc *desc; - unsigned long flags; - - local_irq_save(flags); - - for_each_irq_desc(i, desc) { - bool affinity_broken; - - raw_spin_lock(&desc->lock); - affinity_broken = migrate_one_irq(desc); - raw_spin_unlock(&desc->lock); - - if (affinity_broken) - pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", - i, smp_processor_id()); - } - - local_irq_restore(flags); -} -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 3bf82232b1be..1d6f5ea522f4 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -254,7 +254,7 @@ int __cpu_disable(void) /* * OK - migrate IRQs away from this CPU */ - migrate_irqs(); + irq_migrate_all_off_this_cpu(); /* * Flush user cache and TLB mappings, and then remove this CPU 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/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index f1e2922e447c..1e3e08a1c456 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2390,4 +2390,6 @@ void arch_teardown_dma_ops(struct device *dev) return; arm_teardown_iommu_dma_ops(dev); + /* Let arch_setup_dma_ops() start again from scratch upon re-probe */ + set_dma_ops(dev, NULL); } diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 2c118a6ab358..0dc23fc227ed 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -247,7 +247,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned char *)optprobe_template_entry, + memcpy(code, (unsigned long *)&optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ 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/include/asm/memory.h b/arch/arm64/include/asm/memory.h index e1ec947e7c0c..0c656850eeea 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -332,6 +332,17 @@ static inline void *phys_to_virt(phys_addr_t x) #define virt_addr_valid(kaddr) \ (_virt_addr_is_linear(kaddr) && _virt_addr_valid(kaddr)) +/* + * Given that the GIC architecture permits ITS implementations that can only be + * configured with a LPI table address once, GICv3 systems with many CPUs may + * end up reserving a lot of different regions after a kexec for their LPI + * tables (one per CPU), as we are forced to reuse the same memory after kexec + * (and thus reserve it persistently with EFI beforehand) + */ +#if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS) +# define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) +#endif + #include <asm-generic/memory_model.h> #endif diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 4b0e1231625c..d09ec76f08cf 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -313,7 +313,6 @@ void __init setup_arch(char **cmdline_p) arm64_memblock_init(); paging_init(); - efi_apply_persistent_mem_reservations(); acpi_table_upgrade(); 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/x86/events/core.c b/arch/x86/events/core.c index 374a19712e20..b684f0294f35 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2278,6 +2278,19 @@ void perf_check_microcode(void) x86_pmu.check_microcode(); } +static int x86_pmu_check_period(struct perf_event *event, u64 value) +{ + if (x86_pmu.check_period && x86_pmu.check_period(event, value)) + return -EINVAL; + + if (value && x86_pmu.limit_period) { + if (x86_pmu.limit_period(event, value) > value) + return -EINVAL; + } + + return 0; +} + static struct pmu pmu = { .pmu_enable = x86_pmu_enable, .pmu_disable = x86_pmu_disable, @@ -2302,6 +2315,7 @@ static struct pmu pmu = { .event_idx = x86_pmu_event_idx, .sched_task = x86_pmu_sched_task, .task_ctx_size = sizeof(struct x86_perf_task_context), + .check_period = x86_pmu_check_period, }; void arch_perf_update_userpage(struct perf_event *event, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index daafb893449b..730978dff63f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3587,6 +3587,11 @@ static void intel_pmu_sched_task(struct perf_event_context *ctx, intel_pmu_lbr_sched_task(ctx, sched_in); } +static int intel_pmu_check_period(struct perf_event *event, u64 value) +{ + return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; +} + PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); PMU_FORMAT_ATTR(ldlat, "config1:0-15"); @@ -3667,6 +3672,8 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, .cpu_dead = intel_pmu_cpu_dead, + + .check_period = intel_pmu_check_period, }; static struct attribute *intel_pmu_attrs[]; @@ -3711,6 +3718,8 @@ static __initconst const struct x86_pmu intel_pmu = { .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, + + .check_period = intel_pmu_check_period, }; static __init void intel_clovertown_quirk(void) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 78d7b7031bfc..d46fd6754d92 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -646,6 +646,11 @@ struct x86_pmu { * Intel host/guest support (KVM) */ struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr); + + /* + * Check period value for PERF_EVENT_IOC_PERIOD ioctl. + */ + int (*check_period) (struct perf_event *event, u64 period); }; struct x86_perf_task_context { @@ -857,7 +862,7 @@ static inline int amd_pmu_init(void) #ifdef CONFIG_CPU_SUP_INTEL -static inline bool intel_pmu_has_bts(struct perf_event *event) +static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period) { struct hw_perf_event *hwc = &event->hw; unsigned int hw_event, bts_event; @@ -868,7 +873,14 @@ static inline bool intel_pmu_has_bts(struct perf_event *event) hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - return hw_event == bts_event && hwc->sample_period == 1; + return hw_event == bts_event && period == 1; +} + +static inline bool intel_pmu_has_bts(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + + return intel_pmu_has_bts_period(event, hwc->sample_period); } int intel_pmu_save_and_restart(struct perf_event *event); diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index f65b78d32f5e..7dbbe9ffda17 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -51,7 +51,7 @@ static unsigned long get_dr(int n) /* * fill in the user structure for a core dump.. */ -static void dump_thread32(struct pt_regs *regs, struct user32 *dump) +static void fill_dump(struct pt_regs *regs, struct user32 *dump) { u32 fs, gs; memset(dump, 0, sizeof(*dump)); @@ -157,10 +157,12 @@ static int aout_core_dump(struct coredump_params *cprm) fs = get_fs(); set_fs(KERNEL_DS); has_dumped = 1; + + fill_dump(cprm->regs, &dump); + strncpy(dump.u_comm, current->comm, sizeof(current->comm)); dump.u_ar0 = offsetof(struct user32, regs); dump.signal = cprm->siginfo->si_signo; - dump_thread32(cprm->regs, &dump); /* * If the size of the dump file exceeds the rlimit, then see diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index d9a9993af882..9f15384c504a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -52,6 +52,8 @@ #define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_ICELAKE_MOBILE 0x7E + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index e652a7cc6186..3f697a9e3f59 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -48,7 +48,8 @@ enum { BIOS_STATUS_SUCCESS = 0, BIOS_STATUS_UNIMPLEMENTED = -ENOSYS, BIOS_STATUS_EINVAL = -EINVAL, - BIOS_STATUS_UNAVAIL = -EBUSY + BIOS_STATUS_UNAVAIL = -EBUSY, + BIOS_STATUS_ABORT = -EINTR, }; /* Address map parameters */ @@ -167,4 +168,9 @@ extern long system_serial_number; extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */ +/* + * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details + */ +extern struct semaphore __efi_uv_runtime_lock; + #endif /* _ASM_X86_UV_BIOS_H */ 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). * diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 4a6a5a26c582..eb33432f2f24 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -29,7 +29,8 @@ struct uv_systab *uv_systab; -s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) +static s64 __uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, + u64 a4, u64 a5) { struct uv_systab *tab = uv_systab; s64 ret; @@ -51,6 +52,19 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) return ret; } + +s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) +{ + s64 ret; + + if (down_interruptible(&__efi_uv_runtime_lock)) + return BIOS_STATUS_ABORT; + + ret = __uv_bios_call(which, a1, a2, a3, a4, a5); + up(&__efi_uv_runtime_lock); + + return ret; +} EXPORT_SYMBOL_GPL(uv_bios_call); s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, @@ -59,10 +73,15 @@ s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, unsigned long bios_flags; s64 ret; + if (down_interruptible(&__efi_uv_runtime_lock)) + return BIOS_STATUS_ABORT; + local_irq_save(bios_flags); - ret = uv_bios_call(which, a1, a2, a3, a4, a5); + ret = __uv_bios_call(which, a1, a2, a3, a4, a5); local_irq_restore(bios_flags); + up(&__efi_uv_runtime_lock); + return ret; } diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index a43276c76fc6..21393ec3b9a4 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -509,7 +509,7 @@ static int ht16k33_remove(struct i2c_client *client) struct ht16k33_priv *priv = i2c_get_clientdata(client); struct ht16k33_fbdev *fbdev = &priv->fbdev; - cancel_delayed_work(&fbdev->work); + cancel_delayed_work_sync(&fbdev->work); unregister_framebuffer(fbdev->info); framebuffer_release(fbdev->info); free_page((unsigned long) fbdev->buffer); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index f94d33525771..d299ec79e4c3 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -781,12 +781,12 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("smartreflex", 0, -1, 0x38, -1, 0x00000000, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), SYSC_QUIRK("timer", 0, 0, 0x10, 0x14, 0x00000015, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), + 0), /* Some timers on omap4 and later */ SYSC_QUIRK("timer", 0, 0, 0x10, -1, 0x50002100, 0xffffffff, - SYSC_QUIRK_LEGACY_IDLE), + 0), SYSC_QUIRK("timer", 0, 0, 0x10, -1, 0x4fff1301, 0xffff00ff, - SYSC_QUIRK_LEGACY_IDLE), + 0), SYSC_QUIRK("uart", 0, 0x50, 0x54, 0x58, 0x00000052, 0xffffffff, SYSC_QUIRK_LEGACY_IDLE), /* Uarts on omap4 and later */ diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c index 595124074821..c364027638e1 100644 --- a/drivers/clocksource/timer-ti-dm.c +++ b/drivers/clocksource/timer-ti-dm.c @@ -154,6 +154,10 @@ static int omap_dm_timer_of_set_source(struct omap_dm_timer *timer) if (IS_ERR(parent)) return -ENODEV; + /* Bail out if both clocks point to fck */ + if (clk_is_match(parent, timer->fclk)) + return 0; + ret = clk_set_parent(timer->fclk, parent); if (ret < 0) pr_err("%s: failed to set parent\n", __func__); @@ -864,7 +868,6 @@ static int omap_dm_timer_probe(struct platform_device *pdev) timer->pdev = pdev; pm_runtime_enable(dev); - pm_runtime_irq_safe(dev); if (!timer->reserved) { ret = pm_runtime_get_sync(dev); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 4c46ff6f2242..55b77c576c42 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -592,11 +592,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz, early_memunmap(tbl, sizeof(*tbl)); } - return 0; -} -int __init efi_apply_persistent_mem_reservations(void) -{ if (efi.mem_reserve != EFI_INVALID_TABLE_ADDR) { unsigned long prsv = efi.mem_reserve; diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c index eee42d5e25ee..c037c6c5d0b7 100644 --- a/drivers/firmware/efi/libstub/arm-stub.c +++ b/drivers/firmware/efi/libstub/arm-stub.c @@ -75,9 +75,6 @@ void install_memreserve_table(efi_system_table_t *sys_table_arg) efi_guid_t memreserve_table_guid = LINUX_EFI_MEMRESERVE_TABLE_GUID; efi_status_t status; - if (IS_ENABLED(CONFIG_ARM)) - return; - status = efi_call_early(allocate_pool, EFI_LOADER_DATA, sizeof(*rsv), (void **)&rsv); if (status != EFI_SUCCESS) { diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 8903b9ccfc2b..e2abfdb5cee6 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -147,6 +147,13 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call) static DEFINE_SEMAPHORE(efi_runtime_lock); /* + * Expose the EFI runtime lock to the UV platform + */ +#ifdef CONFIG_X86_UV +extern struct semaphore __efi_uv_runtime_lock __alias(efi_runtime_lock); +#endif + +/* * Calls the appropriate efi_runtime_service() with the appropriate * arguments. * diff --git a/drivers/i2c/busses/i2c-bcm2835.c b/drivers/i2c/busses/i2c-bcm2835.c index ec6e69aa3a8e..d2fbb4bb4a43 100644 --- a/drivers/i2c/busses/i2c-bcm2835.c +++ b/drivers/i2c/busses/i2c-bcm2835.c @@ -183,6 +183,15 @@ static void bcm2835_i2c_start_transfer(struct bcm2835_i2c_dev *i2c_dev) bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, c); } +static void bcm2835_i2c_finish_transfer(struct bcm2835_i2c_dev *i2c_dev) +{ + i2c_dev->curr_msg = NULL; + i2c_dev->num_msgs = 0; + + i2c_dev->msg_buf = NULL; + i2c_dev->msg_buf_remaining = 0; +} + /* * Note about I2C_C_CLEAR on error: * The I2C_C_CLEAR on errors will take some time to resolve -- if you were in @@ -283,6 +292,9 @@ static int bcm2835_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], time_left = wait_for_completion_timeout(&i2c_dev->completion, adap->timeout); + + bcm2835_i2c_finish_transfer(i2c_dev); + if (!time_left) { bcm2835_i2c_writel(i2c_dev, BCM2835_I2C_C, BCM2835_I2C_C_CLEAR); diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c index b13605718291..d917cefc5a19 100644 --- a/drivers/i2c/busses/i2c-cadence.c +++ b/drivers/i2c/busses/i2c-cadence.c @@ -382,8 +382,10 @@ static void cdns_i2c_mrecv(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if (id->recv_count > CDNS_I2C_FIFO_DEPTH) + if ((id->recv_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ctrl_reg |= CDNS_I2C_CR_HOLD; + else + ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); @@ -440,8 +442,11 @@ static void cdns_i2c_msend(struct cdns_i2c *id) * Check for the message size against FIFO depth and set the * 'hold bus' bit if it is greater than FIFO depth. */ - if (id->send_count > CDNS_I2C_FIFO_DEPTH) + if ((id->send_count > CDNS_I2C_FIFO_DEPTH) || id->bus_hold_flag) ctrl_reg |= CDNS_I2C_CR_HOLD; + else + ctrl_reg = ctrl_reg & ~CDNS_I2C_CR_HOLD; + cdns_i2c_writereg(ctrl_reg, CDNS_I2C_CR_OFFSET); /* Clear the interrupts in interrupt status register. */ diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 4713957b0cbb..a878351f1643 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -420,7 +420,7 @@ config KEYBOARD_MPR121 config KEYBOARD_SNVS_PWRKEY tristate "IMX SNVS Power Key Driver" - depends on SOC_IMX6SX + depends on SOC_IMX6SX || SOC_IMX7D depends on OF help This is the snvs powerkey driver for the Freescale i.MX application diff --git a/drivers/input/keyboard/cap11xx.c b/drivers/input/keyboard/cap11xx.c index 312916f99597..73686c2460ce 100644 --- a/drivers/input/keyboard/cap11xx.c +++ b/drivers/input/keyboard/cap11xx.c @@ -75,9 +75,7 @@ struct cap11xx_led { struct cap11xx_priv *priv; struct led_classdev cdev; - struct work_struct work; u32 reg; - enum led_brightness new_brightness; }; #endif @@ -233,30 +231,21 @@ static void cap11xx_input_close(struct input_dev *idev) } #ifdef CONFIG_LEDS_CLASS -static void cap11xx_led_work(struct work_struct *work) +static int cap11xx_led_set(struct led_classdev *cdev, + enum led_brightness value) { - struct cap11xx_led *led = container_of(work, struct cap11xx_led, work); + struct cap11xx_led *led = container_of(cdev, struct cap11xx_led, cdev); struct cap11xx_priv *priv = led->priv; - int value = led->new_brightness; /* - * All LEDs share the same duty cycle as this is a HW limitation. - * Brightness levels per LED are either 0 (OFF) and 1 (ON). + * All LEDs share the same duty cycle as this is a HW + * limitation. Brightness levels per LED are either + * 0 (OFF) and 1 (ON). */ - regmap_update_bits(priv->regmap, CAP11XX_REG_LED_OUTPUT_CONTROL, - BIT(led->reg), value ? BIT(led->reg) : 0); -} - -static void cap11xx_led_set(struct led_classdev *cdev, - enum led_brightness value) -{ - struct cap11xx_led *led = container_of(cdev, struct cap11xx_led, cdev); - - if (led->new_brightness == value) - return; - - led->new_brightness = value; - schedule_work(&led->work); + return regmap_update_bits(priv->regmap, + CAP11XX_REG_LED_OUTPUT_CONTROL, + BIT(led->reg), + value ? BIT(led->reg) : 0); } static int cap11xx_init_leds(struct device *dev, @@ -299,7 +288,7 @@ static int cap11xx_init_leds(struct device *dev, led->cdev.default_trigger = of_get_property(child, "linux,default-trigger", NULL); led->cdev.flags = 0; - led->cdev.brightness_set = cap11xx_led_set; + led->cdev.brightness_set_blocking = cap11xx_led_set; led->cdev.max_brightness = 1; led->cdev.brightness = LED_OFF; @@ -312,8 +301,6 @@ static int cap11xx_init_leds(struct device *dev, led->reg = reg; led->priv = priv; - INIT_WORK(&led->work, cap11xx_led_work); - error = devm_led_classdev_register(dev, &led->cdev); if (error) { of_node_put(child); diff --git a/drivers/input/keyboard/matrix_keypad.c b/drivers/input/keyboard/matrix_keypad.c index 403452ef00e6..3d1cb7bf5e35 100644 --- a/drivers/input/keyboard/matrix_keypad.c +++ b/drivers/input/keyboard/matrix_keypad.c @@ -222,7 +222,7 @@ static void matrix_keypad_stop(struct input_dev *dev) keypad->stopped = true; spin_unlock_irq(&keypad->lock); - flush_work(&keypad->work.work); + flush_delayed_work(&keypad->work); /* * matrix_keypad_scan() will leave IRQs enabled; * we should disable them now. diff --git a/drivers/input/keyboard/qt2160.c b/drivers/input/keyboard/qt2160.c index 43b86482dda0..d466bc07aebb 100644 --- a/drivers/input/keyboard/qt2160.c +++ b/drivers/input/keyboard/qt2160.c @@ -58,10 +58,9 @@ static unsigned char qt2160_key2code[] = { struct qt2160_led { struct qt2160_data *qt2160; struct led_classdev cdev; - struct work_struct work; char name[32]; int id; - enum led_brightness new_brightness; + enum led_brightness brightness; }; #endif @@ -74,7 +73,6 @@ struct qt2160_data { u16 key_matrix; #ifdef CONFIG_LEDS_CLASS struct qt2160_led leds[QT2160_NUM_LEDS_X]; - struct mutex led_lock; #endif }; @@ -83,46 +81,39 @@ static int qt2160_write(struct i2c_client *client, u8 reg, u8 data); #ifdef CONFIG_LEDS_CLASS -static void qt2160_led_work(struct work_struct *work) +static int qt2160_led_set(struct led_classdev *cdev, + enum led_brightness value) { - struct qt2160_led *led = container_of(work, struct qt2160_led, work); + struct qt2160_led *led = container_of(cdev, struct qt2160_led, cdev); struct qt2160_data *qt2160 = led->qt2160; struct i2c_client *client = qt2160->client; - int value = led->new_brightness; u32 drive, pwmen; - mutex_lock(&qt2160->led_lock); - - drive = qt2160_read(client, QT2160_CMD_DRIVE_X); - pwmen = qt2160_read(client, QT2160_CMD_PWMEN_X); - if (value != LED_OFF) { - drive |= (1 << led->id); - pwmen |= (1 << led->id); - - } else { - drive &= ~(1 << led->id); - pwmen &= ~(1 << led->id); - } - qt2160_write(client, QT2160_CMD_DRIVE_X, drive); - qt2160_write(client, QT2160_CMD_PWMEN_X, pwmen); + if (value != led->brightness) { + drive = qt2160_read(client, QT2160_CMD_DRIVE_X); + pwmen = qt2160_read(client, QT2160_CMD_PWMEN_X); + if (value != LED_OFF) { + drive |= BIT(led->id); + pwmen |= BIT(led->id); - /* - * Changing this register will change the brightness - * of every LED in the qt2160. It's a HW limitation. - */ - if (value != LED_OFF) - qt2160_write(client, QT2160_CMD_PWM_DUTY, value); + } else { + drive &= ~BIT(led->id); + pwmen &= ~BIT(led->id); + } + qt2160_write(client, QT2160_CMD_DRIVE_X, drive); + qt2160_write(client, QT2160_CMD_PWMEN_X, pwmen); - mutex_unlock(&qt2160->led_lock); -} + /* + * Changing this register will change the brightness + * of every LED in the qt2160. It's a HW limitation. + */ + if (value != LED_OFF) + qt2160_write(client, QT2160_CMD_PWM_DUTY, value); -static void qt2160_led_set(struct led_classdev *cdev, - enum led_brightness value) -{ - struct qt2160_led *led = container_of(cdev, struct qt2160_led, cdev); + led->brightness = value; + } - led->new_brightness = value; - schedule_work(&led->work); + return 0; } #endif /* CONFIG_LEDS_CLASS */ @@ -293,20 +284,16 @@ static int qt2160_register_leds(struct qt2160_data *qt2160) int ret; int i; - mutex_init(&qt2160->led_lock); - for (i = 0; i < QT2160_NUM_LEDS_X; i++) { struct qt2160_led *led = &qt2160->leds[i]; snprintf(led->name, sizeof(led->name), "qt2160:x%d", i); led->cdev.name = led->name; - led->cdev.brightness_set = qt2160_led_set; + led->cdev.brightness_set_blocking = qt2160_led_set; led->cdev.brightness = LED_OFF; led->id = i; led->qt2160 = qt2160; - INIT_WORK(&led->work, qt2160_led_work); - ret = led_classdev_register(&client->dev, &led->cdev); if (ret < 0) return ret; @@ -324,10 +311,8 @@ static void qt2160_unregister_leds(struct qt2160_data *qt2160) { int i; - for (i = 0; i < QT2160_NUM_LEDS_X; i++) { + for (i = 0; i < QT2160_NUM_LEDS_X; i++) led_classdev_unregister(&qt2160->leds[i].cdev); - cancel_work_sync(&qt2160->leds[i].work); - } } #else diff --git a/drivers/input/keyboard/st-keyscan.c b/drivers/input/keyboard/st-keyscan.c index babcfb165e4f..3b85631fde91 100644 --- a/drivers/input/keyboard/st-keyscan.c +++ b/drivers/input/keyboard/st-keyscan.c @@ -153,6 +153,8 @@ static int keyscan_probe(struct platform_device *pdev) input_dev->id.bustype = BUS_HOST; + keypad_data->input_dev = input_dev; + error = keypad_matrix_key_parse_dt(keypad_data); if (error) return error; @@ -168,8 +170,6 @@ static int keyscan_probe(struct platform_device *pdev) input_set_drvdata(input_dev, keypad_data); - keypad_data->input_dev = input_dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); keypad_data->base = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(keypad_data->base)) diff --git a/drivers/input/misc/apanel.c b/drivers/input/misc/apanel.c index 094bddf56755..c1e66f45d552 100644 --- a/drivers/input/misc/apanel.c +++ b/drivers/input/misc/apanel.c @@ -22,7 +22,6 @@ #include <linux/io.h> #include <linux/input-polldev.h> #include <linux/i2c.h> -#include <linux/workqueue.h> #include <linux/leds.h> #define APANEL_NAME "Fujitsu Application Panel" @@ -59,8 +58,6 @@ struct apanel { struct i2c_client *client; unsigned short keymap[MAX_PANEL_KEYS]; u16 nkeys; - u16 led_bits; - struct work_struct led_work; struct led_classdev mail_led; }; @@ -109,25 +106,13 @@ static void apanel_poll(struct input_polled_dev *ipdev) report_key(idev, ap->keymap[i]); } -/* Track state changes of LED */ -static void led_update(struct work_struct *work) -{ - struct apanel *ap = container_of(work, struct apanel, led_work); - - i2c_smbus_write_word_data(ap->client, 0x10, ap->led_bits); -} - -static void mail_led_set(struct led_classdev *led, +static int mail_led_set(struct led_classdev *led, enum led_brightness value) { struct apanel *ap = container_of(led, struct apanel, mail_led); + u16 led_bits = value != LED_OFF ? 0x8000 : 0x0000; - if (value != LED_OFF) - ap->led_bits |= 0x8000; - else - ap->led_bits &= ~0x8000; - - schedule_work(&ap->led_work); + return i2c_smbus_write_word_data(ap->client, 0x10, led_bits); } static int apanel_remove(struct i2c_client *client) @@ -179,7 +164,7 @@ static struct apanel apanel = { }, .mail_led = { .name = "mail:blue", - .brightness_set = mail_led_set, + .brightness_set_blocking = mail_led_set, }, }; @@ -235,7 +220,6 @@ static int apanel_probe(struct i2c_client *client, if (err) goto out3; - INIT_WORK(&ap->led_work, led_update); if (device_chip[APANEL_DEV_LED] != CHIP_NONE) { err = led_classdev_register(&client->dev, &ap->mail_led); if (err) diff --git a/drivers/input/misc/bma150.c b/drivers/input/misc/bma150.c index 1efcfdf9f8a8..dd9dd4e40827 100644 --- a/drivers/input/misc/bma150.c +++ b/drivers/input/misc/bma150.c @@ -481,13 +481,14 @@ static int bma150_register_input_device(struct bma150_data *bma150) idev->close = bma150_irq_close; input_set_drvdata(idev, bma150); + bma150->input = idev; + error = input_register_device(idev); if (error) { input_free_device(idev); return error; } - bma150->input = idev; return 0; } @@ -510,15 +511,15 @@ static int bma150_register_polled_device(struct bma150_data *bma150) bma150_init_input_device(bma150, ipoll_dev->input); + bma150->input_polled = ipoll_dev; + bma150->input = ipoll_dev->input; + error = input_register_polled_device(ipoll_dev); if (error) { input_free_polled_device(ipoll_dev); return error; } - bma150->input_polled = ipoll_dev; - bma150->input = ipoll_dev->input; - return 0; } diff --git a/drivers/input/misc/pwm-vibra.c b/drivers/input/misc/pwm-vibra.c index 55da191ae550..dbb6d9e1b947 100644 --- a/drivers/input/misc/pwm-vibra.c +++ b/drivers/input/misc/pwm-vibra.c @@ -34,6 +34,7 @@ struct pwm_vibrator { struct work_struct play_work; u16 level; u32 direction_duty_cycle; + bool vcc_on; }; static int pwm_vibrator_start(struct pwm_vibrator *vibrator) @@ -42,10 +43,13 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator) struct pwm_state state; int err; - err = regulator_enable(vibrator->vcc); - if (err) { - dev_err(pdev, "failed to enable regulator: %d", err); - return err; + if (!vibrator->vcc_on) { + err = regulator_enable(vibrator->vcc); + if (err) { + dev_err(pdev, "failed to enable regulator: %d", err); + return err; + } + vibrator->vcc_on = true; } pwm_get_state(vibrator->pwm, &state); @@ -76,11 +80,14 @@ static int pwm_vibrator_start(struct pwm_vibrator *vibrator) static void pwm_vibrator_stop(struct pwm_vibrator *vibrator) { - regulator_disable(vibrator->vcc); - if (vibrator->pwm_dir) pwm_disable(vibrator->pwm_dir); pwm_disable(vibrator->pwm); + + if (vibrator->vcc_on) { + regulator_disable(vibrator->vcc); + vibrator->vcc_on = false; + } } static void pwm_vibrator_play_work(struct work_struct *work) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index f322a1768fbb..225ae6980182 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1336,7 +1336,6 @@ MODULE_DEVICE_TABLE(i2c, elan_id); static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, - { "ELAN0501", 0 }, { "ELAN0600", 0 }, { "ELAN0602", 0 }, { "ELAN0605", 0 }, @@ -1346,6 +1345,7 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN060C", 0 }, { "ELAN0611", 0 }, { "ELAN0612", 0 }, + { "ELAN0617", 0 }, { "ELAN0618", 0 }, { "ELAN061C", 0 }, { "ELAN061D", 0 }, diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 9fe075c137dc..a7f8b1614559 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -1119,6 +1119,8 @@ static int elantech_get_resolution_v4(struct psmouse *psmouse, * Asus UX31 0x361f00 20, 15, 0e clickpad * Asus UX32VD 0x361f02 00, 15, 0e clickpad * Avatar AVIU-145A2 0x361f00 ? clickpad + * Fujitsu CELSIUS H760 0x570f02 40, 14, 0c 3 hw buttons (**) + * Fujitsu CELSIUS H780 0x5d0f02 41, 16, 0d 3 hw buttons (**) * Fujitsu LIFEBOOK E544 0x470f00 d0, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E546 0x470f00 50, 12, 09 2 hw buttons * Fujitsu LIFEBOOK E547 0x470f00 50, 12, 09 2 hw buttons @@ -1171,6 +1173,13 @@ static const struct dmi_system_id elantech_dmi_has_middle_button[] = { DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H760"), }, }, + { + /* Fujitsu H780 also has a middle button */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"), + DMI_MATCH(DMI_PRODUCT_NAME, "CELSIUS H780"), + }, + }, #endif { } }; diff --git a/drivers/input/serio/ps2-gpio.c b/drivers/input/serio/ps2-gpio.c index c62cceb97bb1..5e8d8384aa2a 100644 --- a/drivers/input/serio/ps2-gpio.c +++ b/drivers/input/serio/ps2-gpio.c @@ -76,6 +76,7 @@ static void ps2_gpio_close(struct serio *serio) { struct ps2_gpio_data *drvdata = serio->port_data; + flush_delayed_work(&drvdata->tx_work); disable_irq(drvdata->irq); } diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index d713271ebf7c..a64116586b4c 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1396,9 +1396,9 @@ static void flexrm_shutdown(struct mbox_chan *chan) /* Clear ring flush state */ timeout = 1000; /* timeout of 1s */ - writel_relaxed(0x0, ring + RING_CONTROL); + writel_relaxed(0x0, ring->regs + RING_CONTROL); do { - if (!(readl_relaxed(ring + RING_FLUSH_DONE) & + if (!(readl_relaxed(ring->regs + RING_FLUSH_DONE) & FLUSH_DONE_MASK)) break; mdelay(1); diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index c6a7d4582dc6..38d9df3fb199 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -310,6 +310,7 @@ int mbox_flush(struct mbox_chan *chan, unsigned long timeout) return ret; } +EXPORT_SYMBOL_GPL(mbox_flush); /** * mbox_request_channel - Request a mailbox channel. diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 485462d3087f..537c90c8eb0a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1183,29 +1183,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } } - /* Link-local multicast packets should be passed to the - * stack on the link they arrive as well as pass them to the - * bond-master device. These packets are mostly usable when - * stack receives it with the link on which they arrive - * (e.g. LLDP) they also must be available on master. Some of - * the use cases include (but are not limited to): LLDP agents - * that must be able to operate both on enslaved interfaces as - * well as on bonds themselves; linux bridges that must be able - * to process/pass BPDUs from attached bonds when any kind of - * STP version is enabled on the network. + /* + * For packets determined by bond_should_deliver_exact_match() call to + * be suppressed we want to make an exception for link-local packets. + * This is necessary for e.g. LLDP daemons to be able to monitor + * inactive slave links without being forced to bind to them + * explicitly. + * + * At the same time, packets that are passed to the bonding master + * (including link-local ones) can have their originating interface + * determined via PACKET_ORIGDEV socket option. */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (nskb) { - nskb->dev = bond->dev; - nskb->queue_mapping = 0; - netif_rx(nskb); - } - return RX_HANDLER_PASS; - } - if (bond_should_deliver_exact_match(skb, slave, bond)) + if (bond_should_deliver_exact_match(skb, slave, bond)) { + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + return RX_HANDLER_PASS; return RX_HANDLER_EXACT; + } skb->dev = bond->dev; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8bc7e495b027..d95730c6e0f2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3903,7 +3903,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, if (len) break; /* on first few passes, just barely sleep */ - if (i < DFLT_HWRM_CMD_TIMEOUT) + if (i < HWRM_SHORT_TIMEOUT_COUNTER) usleep_range(HWRM_SHORT_MIN_TIMEOUT, HWRM_SHORT_MAX_TIMEOUT); else @@ -3926,7 +3926,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, dma_rmb(); if (*valid) break; - udelay(1); + usleep_range(1, 5); } if (j >= HWRM_VALID_BIT_DELAY_USEC) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a451796deefe..2fb653e0048d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -582,7 +582,7 @@ struct nqe_cn { (HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT + \ ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT)) -#define HWRM_VALID_BIT_DELAY_USEC 20 +#define HWRM_VALID_BIT_DELAY_USEC 150 #define BNXT_HWRM_CHNL_CHIMP 0 #define BNXT_HWRM_CHNL_KONG 1 diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index f4d81765221e..62636c1ed141 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -271,7 +271,7 @@ struct xcast_addr_list { }; struct nicvf_work { - struct delayed_work work; + struct work_struct work; u8 mode; struct xcast_addr_list *mc; }; @@ -327,7 +327,11 @@ struct nicvf { struct nicvf_work rx_mode_work; /* spinlock to protect workqueue arguments from concurrent access */ spinlock_t rx_mode_wq_lock; - + /* workqueue for handling kernel ndo_set_rx_mode() calls */ + struct workqueue_struct *nicvf_rx_mode_wq; + /* mutex to protect VF's mailbox contents from concurrent access */ + struct mutex rx_mode_mtx; + struct delayed_work link_change_work; /* PTP timestamp */ struct cavium_ptp *ptp_clock; /* Inbound timestamping is on */ @@ -575,10 +579,8 @@ struct set_ptp { struct xcast { u8 msg; - union { - u8 mode; - u64 mac; - } data; + u8 mode; + u64 mac:48; }; /* 128 bit shared memory between PF and each VF */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 6c8dcb65ff03..c90252829ed3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -57,14 +57,8 @@ struct nicpf { #define NIC_GET_BGX_FROM_VF_LMAC_MAP(map) ((map >> 4) & 0xF) #define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map) (map & 0xF) u8 *vf_lmac_map; - struct delayed_work dwork; - struct workqueue_struct *check_link; - u8 *link; - u8 *duplex; - u32 *speed; u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; u16 rssi_base[MAX_NUM_VFS_SUPPORTED]; - bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; /* MSI-X */ u8 num_vec; @@ -929,6 +923,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp) nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val); } +/* Get BGX LMAC link status and update corresponding VF + * if there is a change, valid only if internal L2 switch + * is not present otherwise VF link is always treated as up + */ +static void nic_link_status_get(struct nicpf *nic, u8 vf) +{ + union nic_mbx mbx = {}; + struct bgx_link_status link; + u8 bgx, lmac; + + mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + + /* Get BGX, LMAC indices for the VF */ + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + /* Get interface link status */ + bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); + + /* Send a mbox message to VF with current link status */ + mbx.link_status.link_up = link.link_up; + mbx.link_status.duplex = link.duplex; + mbx.link_status.speed = link.speed; + mbx.link_status.mac_type = link.mac_type; + + /* reply with link status */ + nic_send_msg_to_vf(nic, vf, &mbx); +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -941,8 +964,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) int i; int ret = 0; - nic->mbx_lock[vf] = true; - mbx_addr = nic_get_mbx_addr(vf); mbx_data = (u64 *)&mbx; @@ -957,12 +978,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) switch (mbx.msg.msg) { case NIC_MBOX_MSG_READY: nic_mbx_send_ready(nic, vf); - if (vf < nic->num_vf_en) { - nic->link[vf] = 0; - nic->duplex[vf] = 0; - nic->speed[vf] = 0; - } - goto unlock; + return; case NIC_MBOX_MSG_QS_CFG: reg_addr = NIC_PF_QSET_0_127_CFG | (mbx.qs.num << NIC_QS_ID_SHIFT); @@ -1031,7 +1047,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_RSS_SIZE: nic_send_rss_size(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_RSS_CFG: case NIC_MBOX_MSG_RSS_CFG_CONT: nic_config_rss(nic, &mbx.rss_cfg); @@ -1039,7 +1055,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) case NIC_MBOX_MSG_CFG_DONE: /* Last message of VF config msg sequence */ nic_enable_vf(nic, vf, true); - goto unlock; + break; case NIC_MBOX_MSG_SHUTDOWN: /* First msg in VF teardown sequence */ if (vf >= nic->num_vf_en) @@ -1049,19 +1065,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_ALLOC_SQS: nic_alloc_sqs(nic, &mbx.sqs_alloc); - goto unlock; + return; case NIC_MBOX_MSG_NICVF_PTR: nic->nicvf[vf] = mbx.nicvf.nicvf; break; case NIC_MBOX_MSG_PNICVF_PTR: nic_send_pnicvf(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_SNICVF_PTR: nic_send_snicvf(nic, &mbx.nicvf); - goto unlock; + return; case NIC_MBOX_MSG_BGX_STATS: nic_get_bgx_stats(nic, &mbx.bgx_stats); - goto unlock; + return; case NIC_MBOX_MSG_LOOPBACK: ret = nic_config_loopback(nic, &mbx.lbk); break; @@ -1070,7 +1086,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_PFC: nic_pause_frame(nic, vf, &mbx.pfc); - goto unlock; + return; case NIC_MBOX_MSG_PTP_CFG: nic_config_timestamp(nic, vf, &mbx.ptp); break; @@ -1094,7 +1110,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); bgx_set_dmac_cam_filter(nic->node, bgx, lmac, - mbx.xcast.data.mac, + mbx.xcast.mac, vf < NIC_VF_PER_MBX_REG ? vf : vf - NIC_VF_PER_MBX_REG); break; @@ -1106,8 +1122,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) } bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode); + bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode); break; + case NIC_MBOX_MSG_BGX_LINK_CHANGE: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + break; + } + nic_link_status_get(nic, vf); + return; default: dev_err(&nic->pdev->dev, "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); @@ -1121,8 +1144,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) mbx.msg.msg, vf); nic_mbx_send_nack(nic, vf); } -unlock: - nic->mbx_lock[vf] = false; } static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) @@ -1270,52 +1291,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic) return 0; } -/* Poll for BGX LMAC link status and update corresponding VF - * if there is a change, valid only if internal L2 switch - * is not present otherwise VF link is always treated as up - */ -static void nic_poll_for_link(struct work_struct *work) -{ - union nic_mbx mbx = {}; - struct nicpf *nic; - struct bgx_link_status link; - u8 vf, bgx, lmac; - - nic = container_of(work, struct nicpf, dwork.work); - - mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; - - for (vf = 0; vf < nic->num_vf_en; vf++) { - /* Poll only if VF is UP */ - if (!nic->vf_enabled[vf]) - continue; - - /* Get BGX, LMAC indices for the VF */ - bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - /* Get interface link status */ - bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); - - /* Inform VF only if link status changed */ - if (nic->link[vf] == link.link_up) - continue; - - if (!nic->mbx_lock[vf]) { - nic->link[vf] = link.link_up; - nic->duplex[vf] = link.duplex; - nic->speed[vf] = link.speed; - - /* Send a mbox message to VF with current link status */ - mbx.link_status.link_up = link.link_up; - mbx.link_status.duplex = link.duplex; - mbx.link_status.speed = link.speed; - mbx.link_status.mac_type = link.mac_type; - nic_send_msg_to_vf(nic, vf, &mbx); - } - } - queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2); -} - static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct device *dev = &pdev->dev; @@ -1384,18 +1359,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!nic->vf_lmac_map) goto err_release_regions; - nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->link) - goto err_release_regions; - - nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->duplex) - goto err_release_regions; - - nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL); - if (!nic->speed) - goto err_release_regions; - /* Initialize hardware */ nic_init_hw(nic); @@ -1411,22 +1374,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_unregister_interrupts; - /* Register a physical link status poll fn() */ - nic->check_link = alloc_workqueue("check_link_status", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1); - if (!nic->check_link) { - err = -ENOMEM; - goto err_disable_sriov; - } - - INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link); - queue_delayed_work(nic->check_link, &nic->dwork, 0); - return 0; -err_disable_sriov: - if (nic->flags & NIC_SRIOV_ENABLED) - pci_disable_sriov(pdev); err_unregister_interrupts: nic_unregister_interrupts(nic); err_release_regions: @@ -1447,12 +1396,6 @@ static void nic_remove(struct pci_dev *pdev) if (nic->flags & NIC_SRIOV_ENABLED) pci_disable_sriov(pdev); - if (nic->check_link) { - /* Destroy work Queue */ - cancel_delayed_work_sync(&nic->dwork); - destroy_workqueue(nic->check_link); - } - nic_unregister_interrupts(nic); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 88f8a8fa93cd..503cfadff4ac 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -68,9 +68,6 @@ module_param(cpi_alg, int, 0444); MODULE_PARM_DESC(cpi_alg, "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); -/* workqueue for handling kernel ndo_set_rx_mode() calls */ -static struct workqueue_struct *nicvf_rx_mode_wq; - static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) { if (nic->sqs_mode) @@ -127,6 +124,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) { int timeout = NIC_MBOX_MSG_TIMEOUT; int sleep = 10; + int ret = 0; + + mutex_lock(&nic->rx_mode_mtx); nic->pf_acked = false; nic->pf_nacked = false; @@ -139,7 +139,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF NACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EINVAL; + ret = -EINVAL; + break; } msleep(sleep); if (nic->pf_acked) @@ -149,10 +150,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF didn't ACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EBUSY; + ret = -EBUSY; + break; } } - return 0; + mutex_unlock(&nic->rx_mode_mtx); + return ret; } /* Checks if VF is able to comminicate with PF @@ -172,6 +175,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic) return 1; } +static void nicvf_send_cfg_done(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + if (nicvf_send_msg_to_pf(nic, &mbx)) { + netdev_err(nic->netdev, + "PF didn't respond to CFG DONE msg\n"); + } +} + static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx) { if (bgx->rx) @@ -228,21 +242,24 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) break; case NIC_MBOX_MSG_BGX_LINK_CHANGE: nic->pf_acked = true; - nic->link_up = mbx.link_status.link_up; - nic->duplex = mbx.link_status.duplex; - nic->speed = mbx.link_status.speed; - nic->mac_type = mbx.link_status.mac_type; - if (nic->link_up) { - netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n", - nic->speed, - nic->duplex == DUPLEX_FULL ? - "Full" : "Half"); - netif_carrier_on(nic->netdev); - netif_tx_start_all_queues(nic->netdev); - } else { - netdev_info(nic->netdev, "Link is Down\n"); - netif_carrier_off(nic->netdev); - netif_tx_stop_all_queues(nic->netdev); + if (nic->link_up != mbx.link_status.link_up) { + nic->link_up = mbx.link_status.link_up; + nic->duplex = mbx.link_status.duplex; + nic->speed = mbx.link_status.speed; + nic->mac_type = mbx.link_status.mac_type; + if (nic->link_up) { + netdev_info(nic->netdev, + "Link is Up %d Mbps %s duplex\n", + nic->speed, + nic->duplex == DUPLEX_FULL ? + "Full" : "Half"); + netif_carrier_on(nic->netdev); + netif_tx_start_all_queues(nic->netdev); + } else { + netdev_info(nic->netdev, "Link is Down\n"); + netif_carrier_off(nic->netdev); + netif_tx_stop_all_queues(nic->netdev); + } } break; case NIC_MBOX_MSG_ALLOC_SQS: @@ -1311,6 +1328,11 @@ int nicvf_stop(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; union nic_mbx mbx = {}; + cancel_delayed_work_sync(&nic->link_change_work); + + /* wait till all queued set_rx_mode tasks completes */ + drain_workqueue(nic->nicvf_rx_mode_wq); + mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; nicvf_send_msg_to_pf(nic, &mbx); @@ -1410,13 +1432,27 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) return nicvf_send_msg_to_pf(nic, &mbx); } +static void nicvf_link_status_check_task(struct work_struct *work_arg) +{ + struct nicvf *nic = container_of(work_arg, + struct nicvf, + link_change_work.work); + union nic_mbx mbx = {}; + mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + nicvf_send_msg_to_pf(nic, &mbx); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 2 * HZ); +} + int nicvf_open(struct net_device *netdev) { int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - union nic_mbx mbx = {}; + + /* wait till all queued set_rx_mode tasks completes if any */ + drain_workqueue(nic->nicvf_rx_mode_wq); netif_carrier_off(netdev); @@ -1512,8 +1548,12 @@ int nicvf_open(struct net_device *netdev) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); /* Send VF config done msg to PF */ - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; - nicvf_write_to_mbx(nic, &mbx); + nicvf_send_cfg_done(nic); + + INIT_DELAYED_WORK(&nic->link_change_work, + nicvf_link_status_check_task); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 0); return 0; cleanup: @@ -1941,15 +1981,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* flush DMAC filters and reset RX mode */ mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST; - nicvf_send_msg_to_pf(nic, &mbx); + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; if (mode & BGX_XCAST_MCAST_FILTER) { /* once enabling filtering, we need to signal to PF to add * its' own LMAC to the filter to accept packets for it. */ mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = 0; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = 0; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } /* check if we have any specific MACs to be added to PF DMAC filter */ @@ -1957,23 +1999,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* now go through kernel list of MACs and add them one by one */ for (idx = 0; idx < mc_addrs->count; idx++) { mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = mc_addrs->mc[idx]; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = mc_addrs->mc[idx]; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } - kfree(mc_addrs); } /* and finally set rx mode for PF accordingly */ mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST; - mbx.xcast.data.mode = mode; + mbx.xcast.mode = mode; nicvf_send_msg_to_pf(nic, &mbx); +free_mc: + kfree(mc_addrs); } static void nicvf_set_rx_mode_task(struct work_struct *work_arg) { struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work, - work.work); + work); struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work); u8 mode; struct xcast_addr_list *mc; @@ -2030,7 +2074,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev) kfree(nic->rx_mode_work.mc); nic->rx_mode_work.mc = mc_list; nic->rx_mode_work.mode = mode; - queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0); + queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work); spin_unlock(&nic->rx_mode_wq_lock); } @@ -2187,8 +2231,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&nic->reset_task, nicvf_reset_task); - INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); + nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d", + WQ_MEM_RECLAIM, + nic->vf_id); + INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); spin_lock_init(&nic->rx_mode_wq_lock); + mutex_init(&nic->rx_mode_mtx); err = register_netdev(netdev); if (err) { @@ -2228,13 +2276,15 @@ static void nicvf_remove(struct pci_dev *pdev) nic = netdev_priv(netdev); pnetdev = nic->pnicvf->netdev; - cancel_delayed_work_sync(&nic->rx_mode_work.work); - /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. */ if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED)) unregister_netdev(pnetdev); + if (nic->nicvf_rx_mode_wq) { + destroy_workqueue(nic->nicvf_rx_mode_wq); + nic->nicvf_rx_mode_wq = NULL; + } nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); if (nic->drv_stats) @@ -2261,17 +2311,11 @@ static struct pci_driver nicvf_driver = { static int __init nicvf_init_module(void) { pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); - nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic", - WQ_MEM_RECLAIM); return pci_register_driver(&nicvf_driver); } static void __exit nicvf_cleanup_module(void) { - if (nicvf_rx_mode_wq) { - destroy_workqueue(nicvf_rx_mode_wq); - nicvf_rx_mode_wq = NULL; - } pci_unregister_driver(&nicvf_driver); } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index e337da6ba2a4..673c57b8023f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1217,7 +1217,7 @@ static void bgx_init_hw(struct bgx *bgx) /* Disable MAC steering (NCSI traffic) */ for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++) - bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00); + bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00); } static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index cbdd20b9ee6f..5cbc54e9eb19 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -60,7 +60,7 @@ #define RX_DMACX_CAM_EN BIT_ULL(48) #define RX_DMACX_CAM_LMACID(x) (((u64)x) << 49) #define RX_DMAC_COUNT 32 -#define BGX_CMR_RX_STREERING 0x300 +#define BGX_CMR_RX_STEERING 0x300 #define RX_TRAFFIC_STEER_RULE_COUNT 8 #define BGX_CMR_CHAN_MSK_AND 0x450 #define BGX_CMR_BIST_STATUS 0x460 diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index b8155f5e71b4..ac55db065f16 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3128,6 +3128,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1); dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit); } + + put_device(&pdev->dev); + return 0; } EXPORT_SYMBOL(hns_dsaf_roce_reset); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f52e2c46e6a7..e4ff531db14a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3289,8 +3289,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); if (!ok) { + /* Log this in case the user has forgotten to give the kernel + * any buffers, even later in the application. + */ dev_info(&vsi->back->pdev->dev, - "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", ring->xsk_umem ? "UMEM enabled " : "", ring->queue_index, pf_q); } @@ -6725,8 +6728,13 @@ void i40e_down(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) { i40e_clean_tx_ring(vsi->tx_rings[i]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit + * calls are completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[i]); + } i40e_clean_rx_ring(vsi->rx_rings[i]); } @@ -11895,6 +11903,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < vsi->num_queue_pairs; i++) + if (vsi->xdp_rings[i]->xsk_umem) + (void)i40e_xsk_async_xmit(vsi->netdev, i); + return 0; } @@ -11955,8 +11971,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair) static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair) { i40e_clean_tx_ring(vsi->tx_rings[queue_pair]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit calls are + * completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]); + } i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index a7e14e98889f..6c97667d20ef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3709,6 +3709,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct i40e_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_ring *xdp_ring; int drops = 0; int i; @@ -3716,7 +3717,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs) + if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 870cf654e436..3827f16e6923 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -183,6 +183,11 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, err = i40e_queue_pair_enable(vsi, qid); if (err) return err; + + /* Kick start the NAPI context so that receiving will start */ + err = i40e_xsk_async_xmit(vsi->netdev, qid); + if (err) + return err; } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index daff8183534b..cb35d8202572 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3953,8 +3953,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) else mrqc = IXGBE_MRQC_VMDQRSS64EN; - /* Enable L3/L4 for Tx Switched packets */ - mrqc |= IXGBE_MRQC_L3L4TXSWEN; + /* Enable L3/L4 for Tx Switched packets only for X550, + * older devices do not support this feature + */ + if (hw->mac.type >= ixgbe_mac_X550) + mrqc |= IXGBE_MRQC_L3L4TXSWEN; } else { if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; @@ -10225,6 +10228,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct ixgbe_adapter *adapter = netdev_priv(dev); struct bpf_prog *old_prog; + bool need_reset; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10247,9 +10251,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return -ENOMEM; old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); /* If transitioning XDP modes reconfigure rings */ - if (!!prog != !!old_prog) { + if (need_reset) { int err = ixgbe_setup_tc(dev, adapter->hw_tcs); if (err) { @@ -10265,6 +10270,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->xdp_ring[i]->xsk_umem) + (void)ixgbe_xsk_async_xmit(adapter->netdev, i); + return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 65c3e2c979d4..36a8879536a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -144,11 +144,19 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, ixgbe_txrx_ring_disable(adapter, qid); err = ixgbe_add_xsk_umem(adapter, umem, qid); + if (err) + return err; - if (if_running) + if (if_running) { ixgbe_txrx_ring_enable(adapter, qid); - return err; + /* Kick start the NAPI context so that receiving will start */ + err = ixgbe_xsk_async_xmit(adapter->netdev, qid); + if (err) + return err; + } + + return 0; } static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) @@ -634,7 +642,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + if (unlikely(!ixgbe_desc_unused(xdp_ring)) || + !netif_carrier_ok(xdp_ring->netdev)) { work_done = false; break; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 9d4568eb2297..8433fb9c3eee 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2146,7 +2146,7 @@ err_drop_frame: if (unlikely(!skb)) goto err_drop_frame_ret_pool; - dma_sync_single_range_for_cpu(dev->dev.parent, + dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev, rx_desc->buf_phys_addr, MVNETA_MH_SIZE + NET_SKB_PAD, rx_bytes, diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f3a5fa84860f..57727fe1501e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5073,7 +5073,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&hw->restart_work, sky2_restart); pci_set_drvdata(pdev, hw); - pdev->d3_delay = 200; + pdev->d3_delay = 300; return 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index beb8e5d6401a..ded556b7bab5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1688,6 +1688,15 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, eth_hlen = ETH_HLEN + (vlan_valid ? sizeof(u32) : 0); + if (!ether_addr_equal(ethh->h_dest, + p_hwfn->p_rdma_info->iwarp.mac_addr)) { + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "Got unexpected mac %pM instead of %pM\n", + ethh->h_dest, p_hwfn->p_rdma_info->iwarp.mac_addr); + return -EINVAL; + } + ether_addr_copy(remote_mac_addr, ethh->h_source); ether_addr_copy(local_mac_addr, ethh->h_dest); @@ -2605,7 +2614,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; - u32 mpa_buff_size; + u32 buff_size; u16 n_ooo_bufs; int rc = 0; int i; @@ -2632,7 +2641,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, memset(&data, 0, sizeof(data)); data.input.conn_type = QED_LL2_TYPE_IWARP; - data.input.mtu = QED_IWARP_MAX_SYN_PKT_SIZE; + data.input.mtu = params->max_mtu; data.input.rx_num_desc = QED_IWARP_LL2_SYN_RX_SIZE; data.input.tx_num_desc = QED_IWARP_LL2_SYN_TX_SIZE; data.input.tx_max_bds_per_packet = 1; /* will never be fragmented */ @@ -2654,9 +2663,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, goto err; } + buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, QED_IWARP_LL2_SYN_RX_SIZE, - QED_IWARP_MAX_SYN_PKT_SIZE, + buff_size, iwarp_info->ll2_syn_handle); if (rc) goto err; @@ -2710,10 +2720,9 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; - mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, data.input.rx_num_desc, - mpa_buff_size, + buff_size, iwarp_info->ll2_mpa_handle); if (rc) goto err; @@ -2726,7 +2735,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; - iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL); + iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); if (!iwarp_info->mpa_intermediate_buf) goto err; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index b8f612d00241..7ac959038324 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -46,7 +46,6 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_LL2_SYN_TX_SIZE (128) #define QED_IWARP_LL2_SYN_RX_SIZE (256) -#define QED_IWARP_MAX_SYN_PKT_SIZE (128) #define QED_IWARP_LL2_OOO_DEF_TX_SIZE (256) #define QED_IWARP_MAX_OOO (16) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 5d85742a2be0..3c749c327cbd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -696,25 +696,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_eee *edata) { struct stmmac_priv *priv = netdev_priv(dev); + int ret; - priv->eee_enabled = edata->eee_enabled; - - if (!priv->eee_enabled) + if (!edata->eee_enabled) { stmmac_disable_eee_mode(priv); - else { + } else { /* We are asking for enabling the EEE but it is safe * to verify all by invoking the eee_init function. * In case of failure it will return an error. */ - priv->eee_enabled = stmmac_eee_init(priv); - if (!priv->eee_enabled) + edata->eee_enabled = stmmac_eee_init(priv); + if (!edata->eee_enabled) return -EOPNOTSUPP; - - /* Do not change tx_lpi_timer in case of failure */ - priv->tx_lpi_timer = edata->tx_lpi_timer; } - return phy_ethtool_set_eee(dev->phydev, edata); + ret = phy_ethtool_set_eee(dev->phydev, edata); + if (ret) + return ret; + + priv->eee_enabled = edata->eee_enabled; + priv->tx_lpi_timer = edata->tx_lpi_timer; + return 0; } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 1f612268c998..d847f672a705 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -259,7 +259,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device, const char *name; char node_name[32]; - if (of_property_read_string(node, "label", &name) < 0) { + if (of_property_read_string(child, "label", &name) < 0) { snprintf(node_name, sizeof(node_name), "%pOFn", child); name = node_name; } diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 7cdac77d0c68..07e41c42bcf5 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -499,6 +499,8 @@ static int ipvlan_nl_changelink(struct net_device *dev, if (!data) return 0; + if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); @@ -601,6 +603,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; + if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 66b9cfe692fc..7368616286ae 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -379,7 +379,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); - put_device(&bus->dev); return -EINVAL; } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 958f1cf67282..6ce3f666d142 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1256,7 +1256,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); - __team_port_change_port_added(port, !!netif_carrier_ok(port_dev)); + __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); @@ -2915,7 +2915,7 @@ static int team_device_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: - if (netif_carrier_ok(dev)) + if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 60dd1ec1665f..86c8c64fbb0f 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -557,6 +557,7 @@ enum spd_duplex { /* MAC PASSTHRU */ #define AD_MASK 0xfee0 #define BND_MASK 0x0004 +#define BD_MASK 0x0001 #define EFUSE 0xcfdb #define PASS_THRU_MASK 0x1 @@ -1176,9 +1177,9 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) return -ENODEV; } } else { - /* test for RTL8153-BND */ + /* test for RTL8153-BND and RTL8153-BD */ ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_MISC_1); - if ((ocp_data & BND_MASK) == 0) { + if ((ocp_data & BND_MASK) == 0 && (ocp_data & BD_MASK) == 0) { netif_dbg(tp, probe, tp->netdev, "Invalid variant for MAC pass through\n"); return -ENODEV; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 95909e262ba4..7c1430ed0244 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1273,6 +1273,9 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; + + dev->min_mtu = 0; + dev->max_mtu = 0; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 320edcac4699..6359053bd0c7 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3554,7 +3554,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) goto out_err; } - genlmsg_reply(skb, info); + res = genlmsg_reply(skb, info); break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c index 0e6b43bb4678..a5ea3ba495a4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c @@ -158,39 +158,49 @@ static const struct ieee80211_ops mt76x0u_ops = { .get_txpower = mt76x02_get_txpower, }; -static int mt76x0u_register_device(struct mt76x02_dev *dev) +static int mt76x0u_init_hardware(struct mt76x02_dev *dev) { - struct ieee80211_hw *hw = dev->mt76.hw; int err; - err = mt76u_alloc_queues(&dev->mt76); - if (err < 0) - goto out_err; - - err = mt76u_mcu_init_rx(&dev->mt76); - if (err < 0) - goto out_err; - mt76x0_chip_onoff(dev, true, true); - if (!mt76x02_wait_for_mac(&dev->mt76)) { - err = -ETIMEDOUT; - goto out_err; - } + + if (!mt76x02_wait_for_mac(&dev->mt76)) + return -ETIMEDOUT; err = mt76x0u_mcu_init(dev); if (err < 0) - goto out_err; + return err; mt76x0_init_usb_dma(dev); err = mt76x0_init_hardware(dev); if (err < 0) - goto out_err; + return err; mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e); mt76_wr(dev, MT_TXOP_CTRL_CFG, FIELD_PREP(MT_TXOP_TRUN_EN, 0x3f) | FIELD_PREP(MT_TXOP_EXT_CCA_DLY, 0x58)); + return 0; +} + +static int mt76x0u_register_device(struct mt76x02_dev *dev) +{ + struct ieee80211_hw *hw = dev->mt76.hw; + int err; + + err = mt76u_alloc_queues(&dev->mt76); + if (err < 0) + goto out_err; + + err = mt76u_mcu_init_rx(&dev->mt76); + if (err < 0) + goto out_err; + + err = mt76x0u_init_hardware(dev); + if (err < 0) + goto out_err; + err = mt76x0_register_device(dev); if (err < 0) goto out_err; @@ -301,6 +311,8 @@ static int __maybe_unused mt76x0_suspend(struct usb_interface *usb_intf, mt76u_stop_queues(&dev->mt76); mt76x0u_mac_stop(dev); + clear_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state); + mt76x0_chip_onoff(dev, false, false); usb_kill_urb(usb->mcu.res.urb); return 0; @@ -328,7 +340,7 @@ static int __maybe_unused mt76x0_resume(struct usb_interface *usb_intf) tasklet_enable(&usb->rx_tasklet); tasklet_enable(&usb->tx_tasklet); - ret = mt76x0_init_hardware(dev); + ret = mt76x0u_init_hardware(dev); if (ret) goto err; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index aeeb0144bd55..8d1acc802a67 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1785,13 +1785,13 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint32_t lun, /* Issue Marker IOCB */ qla2x00_marker(vha, vha->hw->req_q_map[0], - vha->hw->rsp_q_map[0], sp->fcport->loop_id, lun, + vha->hw->rsp_q_map[0], fcport->loop_id, lun, flags == TCF_LUN_RESET ? MK_SYNC_ID_LUN : MK_SYNC_ID); } done_free_sp: sp->free(sp); - sp->fcport->flags &= ~FCF_ASYNC_SENT; + fcport->flags &= ~FCF_ASYNC_SENT; done: return rval; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index b2da8a00ec33..5464d467e23e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2951,9 +2951,6 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (rot == 1) { blk_queue_flag_set(QUEUE_FLAG_NONROT, q); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); - } else { - blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); - blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); } if (sdkp->device->type == TYPE_ZBC) { @@ -3090,6 +3087,15 @@ static int sd_revalidate_disk(struct gendisk *disk) if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); + /* + * set the default to rotational. All non-rotational devices + * support the block characteristics VPD page, which will + * cause this to be updated correctly and any device which + * doesn't support it should be treated as rotational. + */ + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + blk_queue_flag_set(QUEUE_FLAG_ADD_RANDOM, q); + if (scsi_device_supports_vpd(sdp)) { sd_read_block_provisioning(sdkp); sd_read_block_limits(sdkp); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 24a129fcdd61..a2e5dc7716e2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1788,7 +1788,7 @@ static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len) ret = translate_desc(vq, (uintptr_t)vq->used + used_offset, len, iov, 64, VHOST_ACCESS_WO); - if (ret) + if (ret < 0) return ret; for (i = 0; i < ret; i++) { diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index 7cde3f46ad26..e996174cbfc0 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -14,13 +14,30 @@ #include <linux/err.h> #include <linux/fs.h> +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline char *next_non_spacetab(char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline char *next_terminator(char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + static int load_script(struct linux_binprm *bprm) { const char *i_arg, *i_name; - char *cp; + char *cp, *buf_end; struct file *file; int retval; + /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; @@ -33,18 +50,40 @@ static int load_script(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - /* - * This section does the #! interpretation. - * Sorta complicated, but hopefully it will work. -TYT - */ - + /* Release since we are not mapping a binary into memory. */ allow_write_access(bprm->file); fput(bprm->file); bprm->file = NULL; - bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; - if ((cp = strchr(bprm->buf, '\n')) == NULL) - cp = bprm->buf+BINPRM_BUF_SIZE-1; + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!cp) { + cp = next_non_spacetab(bprm->buf + 2, buf_end); + if (!cp) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(cp, buf_end)) + return -ENOEXEC; + cp = buf_end; + } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; while (cp > bprm->buf) { cp--; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f12cb31a41e5..d09c9f878141 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -238,9 +238,9 @@ out: } /* A writeback failed: mark the page as bad, and invalidate the page cache */ -static void nfs_set_pageerror(struct page *page) +static void nfs_set_pageerror(struct address_space *mapping) { - nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); + nfs_zap_mapping(mapping->host, mapping); } /* @@ -994,7 +994,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) nfs_list_remove_request(req); if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes < bytes)) { - nfs_set_pageerror(req->wb_page); + nfs_set_pageerror(page_file_mapping(req->wb_page)); nfs_context_set_write_error(req->wb_context, hdr->error); goto remove_req; } @@ -1348,7 +1348,8 @@ int nfs_updatepage(struct file *file, struct page *page, unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct inode *inode = page_file_mapping(page)->host; + struct address_space *mapping = page_file_mapping(page); + struct inode *inode = mapping->host; int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -1366,7 +1367,7 @@ int nfs_updatepage(struct file *file, struct page *page, status = nfs_writepage_setup(ctx, page, offset, count); if (status < 0) - nfs_set_pageerror(page); + nfs_set_pageerror(mapping); else __set_page_dirty_nobuffers(page); out: diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index b33f9785b756..72a7681f4046 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1239,8 +1239,8 @@ static __net_init int nfsd_init_net(struct net *net) retval = nfsd_idmap_init(net); if (retval) goto out_idmap_error; - nn->nfsd4_lease = 45; /* default lease time */ - nn->nfsd4_grace = 45; + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->clverifier_counter = prandom_u32(); nn->clientid_counter = prandom_u32(); diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 4f31f96bbfab..c36c86f1ec9a 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -100,7 +100,7 @@ enum vgic_irq_config { }; struct vgic_irq { - spinlock_t irq_lock; /* Protects the content of the struct */ + raw_spinlock_t irq_lock; /* Protects the content of the struct */ struct list_head lpi_list; /* Used to link all LPIs together */ struct list_head ap_list; @@ -256,7 +256,7 @@ struct vgic_dist { u64 propbaser; /* Protects the lpi_list and the count value below. */ - spinlock_t lpi_list_lock; + raw_spinlock_t lpi_list_lock; struct list_head lpi_list_head; int lpi_list_count; @@ -307,7 +307,7 @@ struct vgic_cpu { unsigned int used_lrs; struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS]; - spinlock_t ap_list_lock; /* Protects the ap_list */ + raw_spinlock_t ap_list_lock; /* Protects the ap_list */ /* * List of IRQs that this VCPU should consider because they are either diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 19f32b0c29af..6b318efd8a74 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -34,6 +34,7 @@ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x # define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___noclone__ 1 @@ -101,6 +102,19 @@ #define __attribute_const__ __attribute__((__const__)) /* + * Optional: only supported since gcc >= 9 + * Optional: not supported by clang + * Optional: not supported by icc + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-copy-function-attribute + */ +#if __has_attribute(__copy__) +# define __copy(symbol) __attribute__((__copy__(symbol))) +#else +# define __copy(symbol) +#endif + +/* * Don't. Just don't. See commit 771c035372a0 ("deprecate the '__deprecated' * attribute warnings entirely and for good") for more information. * diff --git a/include/linux/efi.h b/include/linux/efi.h index 45ff763fba76..28604a8d0aa9 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1198,8 +1198,6 @@ static inline bool efi_enabled(int feature) extern void efi_reboot(enum reboot_mode reboot_mode, const char *__unused); extern bool efi_is_table_address(unsigned long phys_addr); - -extern int efi_apply_persistent_mem_reservations(void); #else static inline bool efi_enabled(int feature) { @@ -1218,11 +1216,6 @@ static inline bool efi_is_table_address(unsigned long phys_addr) { return false; } - -static inline int efi_apply_persistent_mem_reservations(void) -{ - return 0; -} #endif extern int efi_status_to_err(efi_status_t status); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 64c41cf45590..859b55b66db2 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -29,9 +29,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#define INIT_MEMBLOCK_REGIONS 128 -#define INIT_PHYSMEM_REGIONS 4 - /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request diff --git a/include/linux/module.h b/include/linux/module.h index 8fa38d3e7538..f5bc4c046461 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -129,13 +129,13 @@ extern void cleanup_module(void); #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ - int init_module(void) __attribute__((alias(#initfn))); + int init_module(void) __copy(initfn) __attribute__((alias(#initfn))); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ - void cleanup_module(void) __attribute__((alias(#exitfn))); + void cleanup_module(void) __copy(exitfn) __attribute__((alias(#exitfn))); #endif diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1d5c551a5add..e1a051724f7e 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -447,6 +447,11 @@ struct pmu { * Filter events for PMU-specific reasons. */ int (*filter_match) (struct perf_event *event); /* optional */ + + /* + * Check period value for PERF_EVENT_IOC_PERIOD ioctl. + */ + int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 71f2394abbf7..e0348cb0a1dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -61,10 +61,20 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ - if (gso_type) { + if (gso_type && skb->network_header) { + if (!skb->protocol) + virtio_net_hdr_set_proto(skb, hdr); +retry: skb_probe_transport_header(skb, -1); - if (!skb_transport_header_was_set(skb)) + if (!skb_transport_header_was_set(skb)) { + /* UFO does not specify ipv4 or 6: try both */ + if (gso_type & SKB_GSO_UDP && + skb->protocol == htons(ETH_P_IP)) { + skb->protocol = htons(ETH_P_IPV6); + goto retry; + } return -EINVAL; + } } } diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index b669fe6dbc3b..98f31c7ea23d 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -63,10 +63,11 @@ struct pnpipehdr { u8 state_after_reset; /* reset request */ u8 error_code; /* any response */ u8 pep_type; /* status indication */ - u8 data[1]; + u8 data0; /* anything else */ }; + u8 data[]; }; -#define other_pep_type data[1] +#define other_pep_type data[0] static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7298a53b9702..85386becbaea 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -853,7 +853,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *); +void __xfrm_state_destroy(struct xfrm_state *, bool); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -863,7 +863,13 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x); + __xfrm_state_destroy(x, false); +} + +static inline void xfrm_state_put_sync(struct xfrm_state *x) +{ + if (refcount_dec_and_test(&x->refcnt)) + __xfrm_state_destroy(x, true); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1590,7 +1596,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); diff --git a/kernel/events/core.c b/kernel/events/core.c index e5ede6918050..26d6edab051a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4963,6 +4963,11 @@ static void __perf_event_period(struct perf_event *event, } } +static int perf_event_check_period(struct perf_event *event, u64 value) +{ + return event->pmu->check_period(event, value); +} + static int perf_event_period(struct perf_event *event, u64 __user *arg) { u64 value; @@ -4979,6 +4984,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; + if (perf_event_check_period(event, value)) + return -EINVAL; + event_function_call(event, __perf_event_period, &value); return 0; @@ -9391,6 +9399,11 @@ static int perf_pmu_nop_int(struct pmu *pmu) return 0; } +static int perf_event_nop_int(struct perf_event *event, u64 value) +{ + return 0; +} + static DEFINE_PER_CPU(unsigned int, nop_txn_flags); static void perf_pmu_start_txn(struct pmu *pmu, unsigned int flags) @@ -9691,6 +9704,9 @@ got_cpu_context: pmu->pmu_disable = perf_pmu_nop_void; } + if (!pmu->check_period) + pmu->check_period = perf_event_nop_int; + if (!pmu->event_idx) pmu->event_idx = perf_event_idx_default; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 309ef5a64af5..5ab4fe3b1dcc 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,7 +734,7 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); - if (order_base_2(size) >= MAX_ORDER) + if (order_base_2(size) >= PAGE_SHIFT+MAX_ORDER) goto fail; rb = kzalloc(size, GFP_KERNEL); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c521b7347482..c4238b441624 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3384,6 +3384,8 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file const char tgid_space[] = " "; const char space[] = " "; + print_event_info(buf, m); + seq_printf(m, "# %s _-----=> irqs-off\n", tgid ? tgid_space : space); seq_printf(m, "# %s / _----=> need-resched\n", diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d5fb09ebba8b..9eaf07f99212 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -861,22 +861,14 @@ static const struct file_operations kprobe_profile_ops = { static nokprobe_inline int fetch_store_strlen(unsigned long addr) { - mm_segment_t old_fs; int ret, len = 0; u8 c; - old_fs = get_fs(); - set_fs(KERNEL_DS); - pagefault_disable(); - do { - ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); + ret = probe_mem_read(&c, (u8 *)addr + len, 1); len++; } while (c && ret == 0 && len < MAX_STRING_SIZE); - pagefault_enable(); - set_fs(old_fs); - return (ret < 0) ? ret : len; } diff --git a/lib/crc32.c b/lib/crc32.c index 45b1d67a1767..4a20455d1f61 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -206,8 +206,8 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len) EXPORT_SYMBOL(crc32_le); EXPORT_SYMBOL(__crc32c_le); -u32 crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); -u32 __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); +u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le); +u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le); /* * This multiplies the polynomials x and y modulo the given modulus. diff --git a/mm/memblock.c b/mm/memblock.c index 022d4cbb3618..ea31045ba704 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -26,6 +26,13 @@ #include "internal.h" +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_PHYSMEM_REGIONS 4 + +#ifndef INIT_MEMBLOCK_RESERVED_REGIONS +# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -92,7 +99,7 @@ unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; -static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; #endif @@ -105,7 +112,7 @@ struct memblock memblock __initdata_memblock = { .reserved.regions = memblock_reserved_init_regions, .reserved.cnt = 1, /* empty dummy entry */ - .reserved.max = INIT_MEMBLOCK_REGIONS, + .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..3d348198004f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen) { int err; - struct socket *sock = sockfd_lookup(fd, &err); + struct socket *sock; + + if (optlen > INT_MAX) + return -EINVAL; + sock = sockfd_lookup(fd, &err); if (sock) { err = security_socket_setsockopt(sock, level, optname); if (err) { diff --git a/net/dsa/port.c b/net/dsa/port.c index 2d7e01b23572..2a2a878b5ce3 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) { - u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) return err; } - dsa_port_set_state_now(dp, stp_state); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); return 0; } @@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy) struct dsa_switch *ds = dp->ds; int port = dp->index; - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_DISABLED); if (ds->ops->port_disable) ds->ops->port_disable(ds, port, phy); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5459f41fc26f..10e809b296ec 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3978f807fa8b..6ae89f2b541b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1457,9 +1457,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((t->erspan_ver == 1 || t->erspan_ver == 2) && - !t->collect_md) - o_flags |= TUNNEL_KEY; + if (t->erspan_ver == 1 || t->erspan_ver == 2) { + if (!t->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1495,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5c3cd5d84a6f..372fdc5381a9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); + const struct ip_tunnel_encap_ops *encap; - if (!iptun_encaps[i]) + encap = rcu_dereference(iptun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(iptun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5afe9f83374d..239d4a65ad6e 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index b858bd5280bf..867474abe269 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, static int gue6_err_proto_handler(int proto, struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { const struct inet6_protocol *ipprot; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 43890898b0b5..26f25b6e2833 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1722,6 +1722,9 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], static void ip6erspan_set_version(struct nlattr *data[], struct __ip6_tnl_parm *parms) { + if (!data) + return; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); @@ -2104,9 +2107,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((p->erspan_ver == 1 || p->erspan_ver == 2) && - !p->collect_md) - o_flags |= TUNNEL_KEY; + if (p->erspan_ver == 1 || p->erspan_ver == 2) { + if (!p->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) + goto nla_put_failure; + + if (p->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -2121,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) || - nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) || - nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, @@ -2140,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) - goto nla_put_failure; - - if (p->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) - goto nla_put_failure; - } else if (p->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 964491cf3672..ce15dc4ccbfa 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); + net->ipv6.rt6_stats->fib_rt_cache--; + + /* purge completely the exception to allow releasing the held resources: + * some [sk] cache may keep the dst around for unlimited time + */ + from = rcu_dereference_protected(rt6_ex->rt6i->from, + lockdep_is_held(&rt6_exception_lock)); + rcu_assign_pointer(rt6_ex->rt6i->from, NULL); + fib6_info_release(from); + dst_dev_put(&rt6_ex->rt6i->dst); + hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; - net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return; + struct fib6_info *from; rcu_read_lock(); + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + bucket = rcu_dereference(from->rt6i_exception_bucket); #ifdef CONFIG_IPV6_SUBTREES @@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) if (rt6_ex) rt6_ex->stamp = jiffies; +unlock: rcu_read_unlock(); } @@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net, u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; + struct fib6_info *from; struct rt6_info *grt; int err; err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { + rcu_read_lock(); + from = rcu_dereference(grt->from); if (!grt->dst.error && /* ignore match if it is the default route */ - grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && + from && !ipv6_addr_any(&from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } + rcu_read_unlock(); ip6_rt_put(grt); } @@ -4649,7 +4665,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2596ffdeebea..b444483cdb2b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; bool checksum_valid = false; - struct udp_mib *mib; int is_udp4; if (flags & MSG_ERRQUEUE) @@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable); */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info); + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; - if (!ip6tun_encaps[i]) + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(ip6tun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f5b4febeaa25..bc65db782bfb 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 655c787f9d54..5651c29cb5bd 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock) return 0; } -static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, - gfp_t allocation, struct sock *sk) +static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, + struct sock *sk) { int err = -ENOBUFS; - sock_hold(sk); - if (*skb2 == NULL) { - if (refcount_read(&skb->users) != 1) { - *skb2 = skb_clone(skb, allocation); - } else { - *skb2 = skb; - refcount_inc(&skb->users); - } - } - if (*skb2 != NULL) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_set_owner_r(*skb2, sk); - skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk); - *skb2 = NULL; - err = 0; - } + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return err; + + skb = skb_clone(skb, allocation); + + if (skb) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + err = 0; } - sock_put(sk); return err; } @@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct sk_buff *skb2 = NULL; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think @@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ @@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, allocation, one_sk); - kfree_skb(skb2); kfree_skb(skb); return err; } @@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..977dea436ee8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, * We need a bit of data queued to build aggregates properly, so * instruct the TCP stack to allow more than a single ms of data * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP + * second, so 7 is ~8ms of queued data. Only affects local TCP * sockets. * This is the default, anyhow - drivers may need to override it * for local reasons (longer buffers, longer completion time, or * similar). */ - local->hw.tx_sk_pacing_shift = 8; + local->hw.tx_sk_pacing_shift = 7; /* set up some defaults */ local->hw.queues = 1; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index c3a7396fb955..88a6d5e18ccc 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -627,7 +627,7 @@ static int table_path_del(struct mesh_table *tbl, spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params); if (!mpath) { - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return -ENXIO; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb4d71efb6fb..c2a6da5d80da 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 ac, q, hdrlen; + int tailroom = 0; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2732,8 +2733,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; + if (sdata->crypto_tx_tailroom_needed_cnt) + tailroom = IEEE80211_ENCRYPT_TAILROOM; + fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, 0, GFP_ATOMIC); + sdata->encrypt_headroom, + tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 86afacb07e5f..ac8d848d7624 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -896,12 +896,13 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, { struct ip_vs_dest *dest; unsigned int atype, i; - int ret = 0; EnterFunction(2); #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { + int ret; + atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5a92f23f179f..4893f248dfdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -313,6 +313,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) int err; list_for_each_entry(rule, &ctx->chain->rules, list) { + if (!nft_is_active_next(ctx->net, rule)) + continue; + err = nft_delrule(ctx, rule); if (err < 0) return err; diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9fc76b19cd3c..db3473540303 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code, ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code, ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { - oph->data[0], /* PEP type */ + oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; @@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; - ph->data[0] = oph->data[1]; /* CTRL id */ + ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); @@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) return -EINVAL; hdr = pnp_hdr(skb); - if (hdr->data[0] != PN_PEP_TYPE_COMMON) { + if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } - switch (hdr->data[1]) { + switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: - switch (hdr->data[4]) { + switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; @@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) } break; case PN_ONE_CREDIT_FLOW_CONTROL: - if (hdr->data[4] == PEP_IND_READY) + if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } @@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; - atomic_add(wake = hdr->data[4], &pn->tx_credits); + atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) @@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); - u8 n_sb = hdr->data[0]; + u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); @@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return -ECONNREFUSED; /* Parse sub-blocks */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk) ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = PAD; + ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } @@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; - ph->data[0] = 0; /* padding */ + ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 033696e6f74f..ad158d311ffa 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if (time_before(transport->hb_timer.expires, expires) && + if ((time_before(transport->hb_timer.expires, expires) || + !timer_pending(&transport->hb_timer)) && !mod_timer(&transport->hb_timer, expires + prandom_u32_max(transport->rto))) sctp_transport_hold(transport); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5721416d0605..adbdf195eb08 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ } __aligned(8); enum smc_urg_state { - SMC_URG_VALID, /* data present */ - SMC_URG_NOTYET, /* data pending */ - SMC_URG_READ /* data was already read */ + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ }; struct smc_connection { diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c index fb6656295204..507105127095 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c +++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c @@ -44,7 +44,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, unsigned char *cksum, unsigned char *buf) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -52,6 +52,10 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, if (IS_ERR(cipher)) return PTR_ERR(cipher); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) ((seqnum >> 24) & 0xff); plain[1] = (unsigned char) ((seqnum >> 16) & 0xff); plain[2] = (unsigned char) ((seqnum >> 8) & 0xff); @@ -67,6 +71,7 @@ krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum, code = krb5_encrypt(cipher, cksum, plain, buf, 8); out: + kfree(plain); crypto_free_sync_skcipher(cipher); return code; } @@ -77,12 +82,17 @@ krb5_make_seq_num(struct krb5_ctx *kctx, u32 seqnum, unsigned char *cksum, unsigned char *buf) { - unsigned char plain[8]; + unsigned char *plain; + s32 code; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_make_rc4_seq_num(kctx, direction, seqnum, cksum, buf); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; + plain[0] = (unsigned char) (seqnum & 0xff); plain[1] = (unsigned char) ((seqnum >> 8) & 0xff); plain[2] = (unsigned char) ((seqnum >> 16) & 0xff); @@ -93,7 +103,9 @@ krb5_make_seq_num(struct krb5_ctx *kctx, plain[6] = direction; plain[7] = direction; - return krb5_encrypt(key, cksum, plain, buf, 8); + code = krb5_encrypt(key, cksum, plain, buf, 8); + kfree(plain); + return code; } static s32 @@ -101,7 +113,7 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, unsigned char *buf, int *direction, s32 *seqnum) { struct crypto_sync_skcipher *cipher; - unsigned char plain[8]; + unsigned char *plain; s32 code; dprintk("RPC: %s:\n", __func__); @@ -113,20 +125,28 @@ krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum, if (code) goto out; + plain = kmalloc(8, GFP_NOFS); + if (!plain) { + code = -ENOMEM; + goto out; + } + code = krb5_decrypt(cipher, cksum, buf, plain, 8); if (code) - goto out; + goto out_plain; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || (plain[4] != plain[7])) { code = (s32)KG_BAD_SEQ; - goto out; + goto out_plain; } *direction = plain[4]; *seqnum = ((plain[0] << 24) | (plain[1] << 16) | (plain[2] << 8) | (plain[3])); +out_plain: + kfree(plain); out: crypto_free_sync_skcipher(cipher); return code; @@ -139,7 +159,7 @@ krb5_get_seq_num(struct krb5_ctx *kctx, int *direction, u32 *seqnum) { s32 code; - unsigned char plain[8]; + unsigned char *plain; struct crypto_sync_skcipher *key = kctx->seq; dprintk("RPC: krb5_get_seq_num:\n"); @@ -147,18 +167,25 @@ krb5_get_seq_num(struct krb5_ctx *kctx, if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) return krb5_get_rc4_seq_num(kctx, cksum, buf, direction, seqnum); + plain = kmalloc(8, GFP_NOFS); + if (!plain) + return -ENOMEM; if ((code = krb5_decrypt(key, cksum, buf, plain, 8))) - return code; + goto out; if ((plain[4] != plain[5]) || (plain[4] != plain[6]) || - (plain[4] != plain[7])) - return (s32)KG_BAD_SEQ; + (plain[4] != plain[7])) { + code = (s32)KG_BAD_SEQ; + goto out; + } *direction = plain[4]; *seqnum = ((plain[0]) | (plain[1] << 8) | (plain[2] << 16) | (plain[3] << 24)); - return 0; +out: + kfree(plain); + return code; } diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c index 45a033329cd4..19bb356230ed 100644 --- a/net/sunrpc/debugfs.c +++ b/net/sunrpc/debugfs.c @@ -146,7 +146,7 @@ rpc_clnt_debugfs_register(struct rpc_clnt *clnt) rcu_read_lock(); xprt = rcu_dereference(clnt->cl_xprt); /* no "debugfs" dentry? Don't bother with the symlink. */ - if (!xprt->debugfs) { + if (IS_ERR_OR_NULL(xprt->debugfs)) { rcu_read_unlock(); return; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 4994e75945b8..21113bfd4eca 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -527,7 +527,8 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, sendcq = ib_alloc_cq(ia->ri_device, NULL, ep->rep_attr.cap.max_send_wr + 1, - 1, IB_POLL_WORKQUEUE); + ia->ri_device->num_comp_vectors > 1 ? 1 : 0, + IB_POLL_WORKQUEUE); if (IS_ERR(sendcq)) { rc = PTR_ERR(sendcq); goto out1; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1217c90a363b..684f2125fc6b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -388,7 +388,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + add_wait_queue(sk_sleep(sk_), &wait_); \ release_sock(sk_); \ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ sched_annotate_sleep(); \ @@ -1677,7 +1677,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); long timeo = *timeop; int err = sock_error(sk); @@ -1685,15 +1685,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) return err; for (;;) { - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sk->sk_shutdown & RCV_SHUTDOWN) { err = -ENOTCONN; break; } + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + sched_annotate_sleep(); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -1709,7 +1711,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) if (err) break; } - finish_wait(sk_sleep(sk), &wait); *timeop = timeo; return err; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 74d1eed7cbd4..a95d479caeea 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -890,7 +890,7 @@ retry: addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1331,15 +1331,29 @@ restart: RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1453,7 +1467,7 @@ out: static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; err = sizeof(short); } else { - struct unix_address *addr = u->addr; - err = addr->len; memcpy(sunaddr, addr->name, addr->len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 6be8c7df15bb..dbb3c1945b5c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) int ifindex; struct xfrm_if *xi; - if (!skb->dev) + if (!secpath_exists(skb) || !skb->dev) return NULL; - xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); ifindex = skb->dev->ifindex; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ba0a4048c846..8d1a898d0ba5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3314,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (ifcb) { xi = ifcb->decode_session(skb); - if (xi) + if (xi) { if_id = xi->p.if_id; + net = xi->net; + } } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 23c92891758a..1bb971f46fc6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void xfrm_state_gc_destroy(struct xfrm_state *x) +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); -void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; @@ -730,7 +735,10 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++; @@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c6d26afcf89d..a131f9ff979e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0; diff --git a/security/lsm_audit.c b/security/lsm_audit.c index f84001019356..33028c098ef3 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -321,6 +321,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, if (a->u.net->sk) { struct sock *sk = a->u.net->sk; struct unix_sock *u; + struct unix_address *addr; int len = 0; char *p = NULL; @@ -351,14 +352,15 @@ static void dump_common_audit_data(struct audit_buffer *ab, #endif case AF_UNIX: u = unix_sk(sk); + addr = smp_load_acquire(&u->addr); + if (!addr) + break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } - if (!u->addr) - break; - len = u->addr->len-sizeof(short); - p = &u->addr->name->sun_path[0]; + len = addr->len-sizeof(short); + p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 9e350fd34504..9c486fad3f9f 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -626,6 +626,13 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu) /* Awaken to handle a signal, request we sleep again later. */ kvm_make_request(KVM_REQ_SLEEP, vcpu); } + + /* + * Make sure we will observe a potential reset request if we've + * observed a change to the power state. Pairs with the smp_wmb() in + * kvm_psci_vcpu_on(). + */ + smp_rmb(); } static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu) @@ -639,6 +646,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) vcpu_req_sleep(vcpu); + if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) + kvm_reset_vcpu(vcpu); + /* * Clear IRQ_PENDING requests that were made to guarantee * that a VCPU sees new virtual interrupts. diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index fbdf3ac2f001..30251e288629 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1695,11 +1695,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, vma_pagesize = vma_kernel_pagesize(vma); /* - * PUD level may not exist for a VM but PMD is guaranteed to - * exist. + * The stage2 has a minimum of 2 level table (For arm64 see + * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can + * use PMD_SIZE huge mappings (even when the PMD is folded into PGD). + * As for PUD huge maps, we must make sure that we have at least + * 3 levels, i.e, PMD is not folded. */ if ((vma_pagesize == PMD_SIZE || - (vma_pagesize == PUD_SIZE && kvm_stage2_has_pud(kvm))) && + (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) && !force_pte) { gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 9b73d3ad918a..34d08ee63747 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -104,12 +104,10 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu) static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) { + struct vcpu_reset_state *reset_state; struct kvm *kvm = source_vcpu->kvm; struct kvm_vcpu *vcpu = NULL; - struct swait_queue_head *wq; unsigned long cpu_id; - unsigned long context_id; - phys_addr_t target_pc; cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK; if (vcpu_mode_is_32bit(source_vcpu)) @@ -130,32 +128,30 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) return PSCI_RET_INVALID_PARAMS; } - target_pc = smccc_get_arg2(source_vcpu); - context_id = smccc_get_arg3(source_vcpu); + reset_state = &vcpu->arch.reset_state; - kvm_reset_vcpu(vcpu); - - /* Gracefully handle Thumb2 entry point */ - if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { - target_pc &= ~((phys_addr_t) 1); - vcpu_set_thumb(vcpu); - } + reset_state->pc = smccc_get_arg2(source_vcpu); /* Propagate caller endianness */ - if (kvm_vcpu_is_be(source_vcpu)) - kvm_vcpu_set_be(vcpu); + reset_state->be = kvm_vcpu_is_be(source_vcpu); - *vcpu_pc(vcpu) = target_pc; /* * NOTE: We always update r0 (or x0) because for PSCI v0.1 * the general puspose registers are undefined upon CPU_ON. */ - smccc_set_retval(vcpu, context_id, 0, 0, 0); - vcpu->arch.power_off = false; - smp_mb(); /* Make sure the above is visible */ + reset_state->r0 = smccc_get_arg3(source_vcpu); + + WRITE_ONCE(reset_state->reset, true); + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); - wq = kvm_arch_vcpu_wq(vcpu); - swake_up_one(wq); + /* + * Make sure the reset request is observed if the change to + * power_state is observed. + */ + smp_wmb(); + + vcpu->arch.power_off = false; + kvm_vcpu_wake_up(vcpu); return PSCI_RET_SUCCESS; } diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 07aa900bac56..1f62f2b8065d 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -251,9 +251,9 @@ static int vgic_debug_show(struct seq_file *s, void *v) return 0; } - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index c0c0b88af1d5..3bdb31eaed64 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -64,7 +64,7 @@ void kvm_vgic_early_init(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; INIT_LIST_HEAD(&dist->lpi_list_head); - spin_lock_init(&dist->lpi_list_lock); + raw_spin_lock_init(&dist->lpi_list_lock); } /* CREATION */ @@ -171,7 +171,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) irq->intid = i + VGIC_NR_PRIVATE_IRQS; INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->vcpu = NULL; irq->target_vcpu = vcpu0; kref_init(&irq->refcount); @@ -206,7 +206,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF; INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - spin_lock_init(&vgic_cpu->ap_list_lock); + raw_spin_lock_init(&vgic_cpu->ap_list_lock); /* * Enable and configure all SGIs to be edge-triggered and @@ -216,7 +216,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->intid = i; irq->vcpu = NULL; irq->target_vcpu = vcpu; @@ -231,13 +231,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) irq->config = VGIC_CONFIG_LEVEL; } - /* - * GICv3 can only be created via the KVM_DEVICE_CREATE API and - * so we always know the emulation type at this point as it's - * either explicitly configured as GICv3, or explicitly - * configured as GICv2, or not configured yet which also - * implies GICv2. - */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) irq->group = 1; else @@ -281,7 +274,7 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0, i, idx; if (vgic_initialized(kvm)) return 0; @@ -298,6 +291,19 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; + /* Initialize groups on CPUs created before the VGIC type was known */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) + irq->group = 1; + else + irq->group = 0; + } + } + if (vgic_has_its(kvm)) { ret = vgic_v4_init(kvm); if (ret) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index eb2a390a6c86..ab3f47745d9c 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -65,7 +65,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); + raw_spin_lock_init(&irq->irq_lock); irq->config = VGIC_CONFIG_EDGE; kref_init(&irq->refcount); @@ -73,7 +73,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->target_vcpu = vcpu; irq->group = 1; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -101,7 +101,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, dist->lpi_list_count++; out_unlock: - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); /* * We "cache" the configuration table entries in our struct vgic_irq's. @@ -287,7 +287,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, if (ret) return ret; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!filter_vcpu || filter_vcpu == irq->target_vcpu) { irq->priority = LPI_PROP_PRIORITY(prop); @@ -299,7 +299,7 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, } } - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) return its_prop_update_vlpi(irq->host_irq, prop, needs_inv); @@ -332,7 +332,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) if (!intids) return -ENOMEM; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (i == irq_count) break; @@ -341,7 +341,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr) continue; intids[i++] = irq->intid; } - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); *intid_ptr = intids; return i; @@ -352,9 +352,9 @@ static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) int ret = 0; unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; @@ -455,7 +455,7 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); @@ -612,7 +612,7 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, return irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; vgic_queue_irq_unlock(kvm, irq, flags); diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 738b65d2d0e7..b535fffc7400 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -147,7 +147,7 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, irq = vgic_get_irq(source_vcpu->kvm, vcpu, intid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = true; irq->source |= 1U << source_vcpu->vcpu_id; @@ -191,13 +191,13 @@ static void vgic_mmio_write_target(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid + i); int target; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->targets = (val >> (i * 8)) & cpu_mask; target = irq->targets ? __ffs(irq->targets) : 0; irq->target_vcpu = kvm_get_vcpu(vcpu->kvm, target); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -230,13 +230,13 @@ static void vgic_mmio_write_sgipendc(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->source &= ~((val >> (i * 8)) & 0xff); if (!irq->source) irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -252,7 +252,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->source |= (val >> (i * 8)) & 0xff; @@ -260,7 +260,7 @@ static void vgic_mmio_write_sgipends(struct kvm_vcpu *vcpu, irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index b3d1f0985117..4a12322bf7df 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -169,13 +169,13 @@ static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu, if (!irq) return; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* We only care about and preserve Aff0, Aff1 and Aff2. */ irq->mpidr = val & GENMASK(23, 0); irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -281,7 +281,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i, &val)) { /* * pending_latch is set irrespective of irq type @@ -292,7 +292,7 @@ static int vgic_v3_uaccess_write_pending(struct kvm_vcpu *vcpu, vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); @@ -957,7 +957,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * An access targetting Group0 SGIs can only generate @@ -968,7 +968,7 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) irq->pending_latch = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } else { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } vgic_put_irq(vcpu->kvm, irq); diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index ceeda7e04a4d..7de42fba05b5 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -77,7 +77,7 @@ void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -120,7 +120,7 @@ void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -139,11 +139,11 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -160,10 +160,10 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); unsigned long flags; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq_is_pending(irq)) value |= (1U << i); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -215,7 +215,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) vgic_hw_irq_spending(vcpu, irq, is_uaccess); else @@ -262,14 +262,14 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) vgic_hw_irq_cpending(vcpu, irq, is_uaccess); else irq->pending_latch = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -311,7 +311,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, unsigned long flags; struct kvm_vcpu *requester_vcpu = vgic_get_mmio_requester_vcpu(); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); @@ -342,7 +342,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } /* @@ -485,10 +485,10 @@ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } @@ -534,14 +534,14 @@ void vgic_mmio_write_config(struct kvm_vcpu *vcpu, continue; irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i * 2 + 1, &val)) irq->config = VGIC_CONFIG_EDGE; else irq->config = VGIC_CONFIG_LEVEL; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } @@ -590,12 +590,12 @@ void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, * restore irq config before line level. */ new_level = !!(val & (1U << i)); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->line_level = new_level; if (new_level) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c index 69b892abd7dc..d91a8938aa7c 100644 --- a/virt/kvm/arm/vgic/vgic-v2.c +++ b/virt/kvm/arm/vgic/vgic-v2.c @@ -84,7 +84,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit */ irq->active = !!(val & GICH_LR_ACTIVE_BIT); @@ -127,7 +127,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu) vgic_irq_set_phys_active(irq, false); } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 9c0dd234ebe8..4ee0aeb9a905 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -76,7 +76,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) if (!irq) /* An LPI could have been unmapped. */ continue; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit */ irq->active = !!(val & ICH_LR_ACTIVE_BIT); @@ -119,7 +119,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) vgic_irq_set_phys_active(irq, false); } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } @@ -347,9 +347,9 @@ retry: status = val & (1 << bit_nr); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 870b1185173b..abd9c7352677 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -54,11 +54,11 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * When taking more than one ap_list_lock at the same time, always take the * lowest numbered VCPU's ap_list_lock first, so: * vcpuX->vcpu_id < vcpuY->vcpu_id: - * spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); - * spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); + * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); + * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); * * Since the VGIC must support injecting virtual interrupts from ISRs, we have - * to use the spin_lock_irqsave/spin_unlock_irqrestore versions of outer + * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer * spinlocks for any lock that may be taken while injecting an interrupt. */ @@ -72,7 +72,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) struct vgic_irq *irq = NULL; unsigned long flags; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (irq->intid != intid) @@ -88,7 +88,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) irq = NULL; out_unlock: - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; } @@ -138,15 +138,15 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) if (irq->intid < VGIC_MIN_LPI) return; - spin_lock_irqsave(&dist->lpi_list_lock, flags); + raw_spin_lock_irqsave(&dist->lpi_list_lock, flags); if (!kref_put(&irq->refcount, vgic_irq_release)) { - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return; }; list_del(&irq->lpi_list); dist->lpi_list_count--; - spin_unlock_irqrestore(&dist->lpi_list_lock, flags); + raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags); kfree(irq); } @@ -244,8 +244,8 @@ static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) bool penda, pendb; int ret; - spin_lock(&irqa->irq_lock); - spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&irqa->irq_lock); + raw_spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING); if (irqa->active || irqb->active) { ret = (int)irqb->active - (int)irqa->active; @@ -263,8 +263,8 @@ static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b) /* Both pending and enabled, sort by priority */ ret = irqa->priority - irqb->priority; out: - spin_unlock(&irqb->irq_lock); - spin_unlock(&irqa->irq_lock); + raw_spin_unlock(&irqb->irq_lock); + raw_spin_unlock(&irqa->irq_lock); return ret; } @@ -325,7 +325,7 @@ retry: * not need to be inserted into an ap_list and there is also * no more work for us to do. */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* * We have to kick the VCPU here, because we could be @@ -347,12 +347,12 @@ retry: * We must unlock the irq lock to take the ap_list_lock where * we are going to insert this new pending interrupt. */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); /* someone can do stuff here, which we re-check below */ - spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); - spin_lock(&irq->irq_lock); + raw_spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_lock(&irq->irq_lock); /* * Did something change behind our backs? @@ -367,10 +367,11 @@ retry: */ if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) { - spin_unlock(&irq->irq_lock); - spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, + flags); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); goto retry; } @@ -382,8 +383,8 @@ retry: list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head); irq->vcpu = vcpu; - spin_unlock(&irq->irq_lock); - spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags); kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu); kvm_vcpu_kick(vcpu); @@ -430,11 +431,11 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid, if (!irq) return -EINVAL; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (!vgic_validate_injection(irq, level, owner)) { /* Nothing to see here, move along... */ - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } @@ -494,9 +495,9 @@ int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, BUG_ON(!irq); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return ret; @@ -519,11 +520,11 @@ void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid) if (!irq->hw) goto out; - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->active = false; irq->pending_latch = false; irq->line_level = false; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); out: vgic_put_irq(vcpu->kvm, irq); } @@ -539,9 +540,9 @@ int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid) irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); BUG_ON(!irq); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); kvm_vgic_unmap_irq(irq); - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return 0; @@ -571,12 +572,12 @@ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner) return -EINVAL; irq = vgic_get_irq(vcpu->kvm, vcpu, intid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->owner && irq->owner != owner) ret = -EEXIST; else irq->owner = owner; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); return ret; } @@ -597,13 +598,13 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); retry: - spin_lock(&vgic_cpu->ap_list_lock); + raw_spin_lock(&vgic_cpu->ap_list_lock); list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; bool target_vcpu_needs_kick = false; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); BUG_ON(vcpu != irq->vcpu); @@ -616,7 +617,7 @@ retry: */ list_del(&irq->ap_list); irq->vcpu = NULL; - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); /* * This vgic_put_irq call matches the @@ -631,14 +632,14 @@ retry: if (target_vcpu == vcpu) { /* We're on the right CPU */ - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); continue; } /* This interrupt looks like it has to be migrated. */ - spin_unlock(&irq->irq_lock); - spin_unlock(&vgic_cpu->ap_list_lock); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vgic_cpu->ap_list_lock); /* * Ensure locking order by always locking the smallest @@ -652,10 +653,10 @@ retry: vcpuB = vcpu; } - spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); - spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, - SINGLE_DEPTH_NESTING); - spin_lock(&irq->irq_lock); + raw_spin_lock(&vcpuA->arch.vgic_cpu.ap_list_lock); + raw_spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock, + SINGLE_DEPTH_NESTING); + raw_spin_lock(&irq->irq_lock); /* * If the affinity has been preserved, move the @@ -675,9 +676,9 @@ retry: target_vcpu_needs_kick = true; } - spin_unlock(&irq->irq_lock); - spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); - spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&irq->irq_lock); + raw_spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&vcpuA->arch.vgic_cpu.ap_list_lock); if (target_vcpu_needs_kick) { kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); @@ -687,7 +688,7 @@ retry: goto retry; } - spin_unlock(&vgic_cpu->ap_list_lock); + raw_spin_unlock(&vgic_cpu->ap_list_lock); } static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu) @@ -741,10 +742,10 @@ static int compute_ap_list_depth(struct kvm_vcpu *vcpu, list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { int w; - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* GICv2 SGIs can count for more than one... */ w = vgic_irq_get_lr_count(irq); - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); count += w; *multi_sgi |= (w > 1); @@ -770,7 +771,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) count = 0; list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); /* * If we have multi-SGIs in the pipeline, we need to @@ -780,7 +781,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) * the AP list has been sorted already. */ if (multi_sgi && irq->priority > prio) { - spin_unlock(&irq->irq_lock); + _raw_spin_unlock(&irq->irq_lock); break; } @@ -791,7 +792,7 @@ static void vgic_flush_lr_state(struct kvm_vcpu *vcpu) prio = irq->priority; } - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); if (count == kvm_vgic_global_state.nr_lr) { if (!list_is_last(&irq->ap_list, @@ -872,9 +873,9 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); - spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); + raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock); vgic_flush_lr_state(vcpu); - spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); + raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock); if (can_access_vgic_from_kernel()) vgic_restore_state(vcpu); @@ -918,20 +919,20 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) vgic_get_vmcr(vcpu, &vmcr); - spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); + raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags); list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) { - spin_lock(&irq->irq_lock); + raw_spin_lock(&irq->irq_lock); pending = irq_is_pending(irq) && irq->enabled && !irq->active && irq->priority < vmcr.pmr; - spin_unlock(&irq->irq_lock); + raw_spin_unlock(&irq->irq_lock); if (pending) break; } - spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); + raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags); return pending; } @@ -963,11 +964,10 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid) return false; irq = vgic_get_irq(vcpu->kvm, vcpu, vintid); - spin_lock_irqsave(&irq->irq_lock, flags); + raw_spin_lock_irqsave(&irq->irq_lock, flags); map_is_active = irq->hw && irq->active; - spin_unlock_irqrestore(&irq->irq_lock, flags); + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); return map_is_active; } - |
