diff options
340 files changed, 2993 insertions, 1972 deletions
diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst index fe46d4867e2d..18c1415e7bfa 100644 --- a/Documentation/networking/msg_zerocopy.rst +++ b/Documentation/networking/msg_zerocopy.rst @@ -7,7 +7,7 @@ Intro ===== The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. -The feature is currently implemented for TCP sockets. +The feature is currently implemented for TCP and UDP sockets. Opportunity and Caveats diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index 355c6d8ef8ad..b203d1334822 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -22,8 +22,9 @@ and changeable from userspace under certain rules. 2. Querying from userspace Both admin and operational state can be queried via the netlink -operation RTM_GETLINK. It is also possible to subscribe to RTMGRP_LINK -to be notified of updates. This is important for setting from userspace. +operation RTM_GETLINK. It is also possible to subscribe to RTNLGRP_LINK +to be notified of updates while the interface is admin up. This is +important for setting from userspace. These values contain interface state: @@ -101,8 +102,9 @@ because some driver controlled protocol establishment has to complete. Corresponding functions are netif_dormant_on() to set the flag, netif_dormant_off() to clear it and netif_dormant() to query. -On device allocation, networking core sets the flags equivalent to -netif_carrier_ok() and !netif_dormant(). +On device allocation, both flags __LINK_STATE_NOCARRIER and +__LINK_STATE_DORMANT are cleared, so the effective state is equivalent +to netif_carrier_ok() and !netif_dormant(). Whenever the driver CHANGES one of these flags, a workqueue event is @@ -133,11 +135,11 @@ netif_carrier_ok() && !netif_dormant() is set by the driver. Afterwards, the userspace application can set IFLA_OPERSTATE to IF_OPER_DORMANT or IF_OPER_UP as long as the driver does not set netif_carrier_off() or netif_dormant_on(). Changes made by userspace -are multicasted on the netlink group RTMGRP_LINK. +are multicasted on the netlink group RTNLGRP_LINK. So basically a 802.1X supplicant interacts with the kernel like this: --subscribe to RTMGRP_LINK +-subscribe to RTNLGRP_LINK -set IFLA_LINKMODE to 1 via RTM_SETLINK -query RTM_GETLINK once to get initial state -if initial flags are not (IFF_LOWER_UP && !IFF_DORMANT), wait until diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 58649bd4fcfc..ebc679bcb2dc 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -80,7 +80,9 @@ nonzero when shrink_dcache_pages() has been called and the dcache isn't pruned yet. nr_negative shows the number of unused dentries that are also -negative dentries which do not mapped to actual files. +negative dentries which do not map to any files. Instead, +they help speeding up rejection of non-existing files provided +by the users. ============================================================== diff --git a/MAINTAINERS b/MAINTAINERS index 9919840d54cd..41ce5f4ad838 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6151,7 +6151,7 @@ FREESCALE SOC SOUND DRIVERS M: Timur Tabi <timur@kernel.org> M: Nicolin Chen <nicoleotsuka@gmail.com> M: Xiubo Li <Xiubo.Lee@gmail.com> -R: Fabio Estevam <fabio.estevam@nxp.com> +R: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linuxppc-dev@lists.ozlabs.org S: Maintained @@ -10898,7 +10898,7 @@ F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h NXP SGTL5000 DRIVER -M: Fabio Estevam <fabio.estevam@nxp.com> +M: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/sound/sgtl5000.txt @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h index 4d17cacd1462..432402c8e47f 100644 --- a/arch/alpha/include/asm/irq.h +++ b/arch/alpha/include/asm/irq.h @@ -56,15 +56,15 @@ #elif defined(CONFIG_ALPHA_DP264) || \ defined(CONFIG_ALPHA_LYNX) || \ - defined(CONFIG_ALPHA_SHARK) || \ - defined(CONFIG_ALPHA_EIGER) + defined(CONFIG_ALPHA_SHARK) # define NR_IRQS 64 #elif defined(CONFIG_ALPHA_TITAN) #define NR_IRQS 80 #elif defined(CONFIG_ALPHA_RAWHIDE) || \ - defined(CONFIG_ALPHA_TAKARA) + defined(CONFIG_ALPHA_TAKARA) || \ + defined(CONFIG_ALPHA_EIGER) # define NR_IRQS 128 #elif defined(CONFIG_ALPHA_WILDFIRE) diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index d73dc473fbb9..188fc9256baf 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,7 +78,7 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+8 : (r)-10]) + (r) <= 18 ? (r)+10 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm/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/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index b16710a8a9e7..76e9bf88d3b9 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -79,8 +79,6 @@ enum reg_val_type { REG_64BIT_32BIT, /* 32-bit compatible, need truncation for 64-bit ops. */ REG_32BIT, - /* 32-bit zero extended. */ - REG_32BIT_ZERO_EX, /* 32-bit no sign/zero extension needed. */ REG_32BIT_POS }; @@ -343,12 +341,15 @@ static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg) const struct bpf_prog *prog = ctx->skf; int stack_adjust = ctx->stack_size; int store_offset = stack_adjust - 8; + enum reg_val_type td; int r0 = MIPS_R_V0; - if (dest_reg == MIPS_R_RA && - get_reg_val_type(ctx, prog->len, BPF_REG_0) == REG_32BIT_ZERO_EX) + if (dest_reg == MIPS_R_RA) { /* Don't let zero extended value escape. */ - emit_instr(ctx, sll, r0, r0, 0); + td = get_reg_val_type(ctx, prog->len, BPF_REG_0); + if (td == REG_64BIT) + emit_instr(ctx, sll, r0, r0, 0); + } if (ctx->flags & EBPF_SAVE_RA) { emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP); @@ -692,7 +693,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } @@ -707,7 +708,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } @@ -721,7 +722,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) + if (td == REG_64BIT) /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); if (insn->imm == 1) { @@ -860,13 +861,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (src < 0 || dst < 0) return -EINVAL; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } did_move = false; ts = get_reg_val_type(ctx, this_idx, insn->src_reg); - if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) { + if (ts == REG_64BIT) { int tmp_reg = MIPS_R_AT; if (bpf_op == BPF_MOV) { @@ -1254,8 +1255,7 @@ jeq_common: if (insn->imm == 64 && td == REG_32BIT) emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); - if (insn->imm != 64 && - (td == REG_64BIT || td == REG_32BIT_ZERO_EX)) { + if (insn->imm != 64 && td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index c9bfe526ca9d..d8c8d7c9df15 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -904,7 +904,7 @@ static inline int pud_none(pud_t pud) static inline int pud_present(pud_t pud) { - return (pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pud_raw(pud) & cpu_to_be64(_PAGE_PRESENT)); } extern struct page *pud_page(pud_t pud); @@ -951,7 +951,7 @@ static inline int pgd_none(pgd_t pgd) static inline int pgd_present(pgd_t pgd) { - return (pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); + return !!(pgd_raw(pgd) & cpu_to_be64(_PAGE_PRESENT)); } static inline pte_t pgd_pte(pgd_t pgd) diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 2fa2942be221..470755cb7558 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -35,6 +35,12 @@ #define _PAGE_SPECIAL _PAGE_SOFT #define _PAGE_TABLE _PAGE_PRESENT +/* + * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to + * distinguish them from swapped out pages + */ +#define _PAGE_PROT_NONE _PAGE_READ + #define _PAGE_PFN_SHIFT 10 /* Set of bits to preserve across pte_modify() */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 16301966d65b..a8179a8c1491 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -44,7 +44,7 @@ /* Page protection bits */ #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) -#define PAGE_NONE __pgprot(0) +#define PAGE_NONE __pgprot(_PAGE_PROT_NONE) #define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) #define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) @@ -98,7 +98,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; static inline int pmd_present(pmd_t pmd) { - return (pmd_val(pmd) & _PAGE_PRESENT); + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pmd_none(pmd_t pmd) @@ -178,7 +178,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr) static inline int pte_present(pte_t pte) { - return (pte_val(pte) & _PAGE_PRESENT); + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pte_none(pte_t pte) @@ -380,7 +380,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, * * Format of swap PTE: * bit 0: _PAGE_PRESENT (zero) - * bit 1: reserved for future use (zero) + * bit 1: _PAGE_PROT_NONE (zero) * bits 2 to 6: swap type * bits 7 to XLEN-1: swap offset */ diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 1e1395d63dab..65df1dfdc303 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -18,8 +18,6 @@ #include <asm/cache.h> #include <asm/thread_info.h> -#define MAX_BYTES_PER_LONG 0x10 - OUTPUT_ARCH(riscv) ENTRY(_start) @@ -76,6 +74,8 @@ SECTIONS *(.sbss*) } + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + EXCEPTION_TABLE(0x10) NOTES @@ -83,10 +83,6 @@ SECTIONS *(.rel.dyn*) } - BSS_SECTION(MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG) - _end = .; STABS_DEBUG diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index 537f97fde37f..b6796e616812 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -30,10 +30,10 @@ .section .text ENTRY(swsusp_arch_suspend) lg %r1,__LC_NODAT_STACK - aghi %r1,-STACK_FRAME_OVERHEAD stmg %r6,%r15,__SF_GPRS(%r1) + aghi %r1,-STACK_FRAME_OVERHEAD stg %r15,__SF_BACKCHAIN(%r1) - lgr %r1,%r15 + lgr %r15,%r1 /* Store FPU registers */ brasl %r14,save_fpu_regs diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index a966d7bfac57..4266a4de3160 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -382,7 +382,9 @@ static void zpci_irq_handler(struct airq_struct *airq) if (ai == -1UL) break; inc_irq_stat(IRQIO_MSI); + airq_iv_lock(aibv, ai); generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } } @@ -408,7 +410,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = aisb; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); if (!zdev->aibv) return -ENOMEM; diff --git a/arch/x86/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/block/blk-mq.c b/block/blk-mq.c index 8f5b533764ca..9437a5eb07cf 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -737,12 +737,20 @@ static void blk_mq_requeue_work(struct work_struct *work) spin_unlock_irq(&q->requeue_lock); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { - if (!(rq->rq_flags & RQF_SOFTBARRIER)) + if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP))) continue; rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); - blk_mq_sched_insert_request(rq, true, false, false); + /* + * If RQF_DONTPREP, rq has contained some driver specific + * data, so insert it to hctx dispatch list to avoid any + * merge. + */ + if (rq->rq_flags & RQF_DONTPREP) + blk_mq_request_bypass_insert(rq, false); + else + blk_mq_sched_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 17eb09d222ff..ec78a04eb136 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -122,8 +122,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private) int af_alg_release(struct socket *sock) { - if (sock->sk) + if (sock->sk) { sock_put(sock->sk); + sock->sk = NULL; + } return 0; } EXPORT_SYMBOL_GPL(af_alg_release); 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/block/floppy.c b/drivers/block/floppy.c index 6f2856c6d0f2..55481b40df9a 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4075,7 +4075,7 @@ static unsigned int floppy_check_events(struct gendisk *disk, if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) { if (lock_fdc(drive)) - return -EINTR; + return 0; poll_drive(false, 0); process_fd_request(); } 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/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index 8ada308d72ee..b0125ad65825 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -380,7 +380,7 @@ static int init_cc_resources(struct platform_device *plat_dev) rc = cc_ivgen_init(new_drvdata); if (rc) { dev_err(dev, "cc_ivgen_init failed\n"); - goto post_power_mgr_err; + goto post_buf_mgr_err; } /* Allocate crypto algs */ @@ -403,6 +403,9 @@ static int init_cc_resources(struct platform_device *plat_dev) goto post_hash_err; } + /* All set, we can allow autosuspend */ + cc_pm_go(new_drvdata); + /* If we got here and FIPS mode is enabled * it means all FIPS test passed, so let TEE * know we're good. @@ -417,8 +420,6 @@ post_cipher_err: cc_cipher_free(new_drvdata); post_ivgen_err: cc_ivgen_fini(new_drvdata); -post_power_mgr_err: - cc_pm_fini(new_drvdata); post_buf_mgr_err: cc_buffer_mgr_fini(new_drvdata); post_req_mgr_err: diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c index d990f472e89f..6ff7e75ad90e 100644 --- a/drivers/crypto/ccree/cc_pm.c +++ b/drivers/crypto/ccree/cc_pm.c @@ -100,20 +100,19 @@ int cc_pm_put_suspend(struct device *dev) int cc_pm_init(struct cc_drvdata *drvdata) { - int rc = 0; struct device *dev = drvdata_to_dev(drvdata); /* must be before the enabling to avoid resdundent suspending */ pm_runtime_set_autosuspend_delay(dev, CC_SUSPEND_TIMEOUT); pm_runtime_use_autosuspend(dev); /* activate the PM module */ - rc = pm_runtime_set_active(dev); - if (rc) - return rc; - /* enable the PM module*/ - pm_runtime_enable(dev); + return pm_runtime_set_active(dev); +} - return rc; +/* enable the PM module*/ +void cc_pm_go(struct cc_drvdata *drvdata) +{ + pm_runtime_enable(drvdata_to_dev(drvdata)); } void cc_pm_fini(struct cc_drvdata *drvdata) diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h index 020a5403c58b..f62624357020 100644 --- a/drivers/crypto/ccree/cc_pm.h +++ b/drivers/crypto/ccree/cc_pm.h @@ -16,6 +16,7 @@ extern const struct dev_pm_ops ccree_pm; int cc_pm_init(struct cc_drvdata *drvdata); +void cc_pm_go(struct cc_drvdata *drvdata); void cc_pm_fini(struct cc_drvdata *drvdata); int cc_pm_suspend(struct device *dev); int cc_pm_resume(struct device *dev); @@ -29,6 +30,8 @@ static inline int cc_pm_init(struct cc_drvdata *drvdata) return 0; } +static void cc_pm_go(struct cc_drvdata *drvdata) {} + static inline void cc_pm_fini(struct cc_drvdata *drvdata) {} static inline int cc_pm_suspend(struct device *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/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c index 00e954f22bc9..74401e0adb29 100644 --- a/drivers/gpio/gpio-mt7621.c +++ b/drivers/gpio/gpio-mt7621.c @@ -30,6 +30,7 @@ #define GPIO_REG_EDGE 0xA0 struct mtk_gc { + struct irq_chip irq_chip; struct gpio_chip chip; spinlock_t lock; int bank; @@ -189,13 +190,6 @@ mediatek_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static struct irq_chip mediatek_gpio_irq_chip = { - .irq_unmask = mediatek_gpio_irq_unmask, - .irq_mask = mediatek_gpio_irq_mask, - .irq_mask_ack = mediatek_gpio_irq_mask, - .irq_set_type = mediatek_gpio_irq_type, -}; - static int mediatek_gpio_xlate(struct gpio_chip *chip, const struct of_phandle_args *spec, u32 *flags) @@ -254,6 +248,13 @@ mediatek_gpio_bank_probe(struct device *dev, return ret; } + rg->irq_chip.name = dev_name(dev); + rg->irq_chip.parent_device = dev; + rg->irq_chip.irq_unmask = mediatek_gpio_irq_unmask; + rg->irq_chip.irq_mask = mediatek_gpio_irq_mask; + rg->irq_chip.irq_mask_ack = mediatek_gpio_irq_mask; + rg->irq_chip.irq_set_type = mediatek_gpio_irq_type; + if (mtk->gpio_irq) { /* * Manually request the irq here instead of passing @@ -270,14 +271,14 @@ mediatek_gpio_bank_probe(struct device *dev, return ret; } - ret = gpiochip_irqchip_add(&rg->chip, &mediatek_gpio_irq_chip, + ret = gpiochip_irqchip_add(&rg->chip, &rg->irq_chip, 0, handle_simple_irq, IRQ_TYPE_NONE); if (ret) { dev_err(dev, "failed to add gpiochip_irqchip\n"); return ret; } - gpiochip_set_chained_irqchip(&rg->chip, &mediatek_gpio_irq_chip, + gpiochip_set_chained_irqchip(&rg->chip, &rg->irq_chip, mtk->gpio_irq, NULL); } @@ -310,7 +311,6 @@ mediatek_gpio_probe(struct platform_device *pdev) mtk->gpio_irq = irq_of_parse_and_map(np, 0); mtk->dev = dev; platform_set_drvdata(pdev, mtk); - mediatek_gpio_irq_chip.name = dev_name(dev); for (i = 0; i < MTK_BANK_CNT; i++) { ret = mediatek_gpio_bank_probe(dev, np, i); diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index e9600b556f39..bcc6be4a5cb2 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -245,6 +245,7 @@ static bool pxa_gpio_has_pinctrl(void) { switch (gpio_type) { case PXA3XX_GPIO: + case MMP2_GPIO: return false; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8fab0d637ee5..3a9b48b227ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -90,8 +90,10 @@ static int psp_sw_fini(void *handle) adev->psp.sos_fw = NULL; release_firmware(adev->psp.asd_fw); adev->psp.asd_fw = NULL; - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; + if (adev->psp.ta_fw) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + } return 0; } @@ -435,6 +437,9 @@ static int psp_xgmi_initialize(struct psp_context *psp) struct ta_xgmi_shared_memory *xgmi_cmd; int ret; + if (!psp->adev->psp.ta_fw) + return -ENOENT; + if (!psp->xgmi_context.initialized) { ret = psp_xgmi_init_shared_buf(psp); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 0c6e7f9b143f..189fcb004579 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -152,18 +152,22 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); - if (err) - goto out2; - - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); - adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); - adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + if (err) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + dev_info(adev->dev, + "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); + } else { + err = amdgpu_ucode_validate(adev->psp.ta_fw); + if (err) + goto out2; + + ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; + adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); + adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); + adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + } return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 9a7ac58eb18e..ddd75a4d8ba5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -671,6 +671,25 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us return bytes_from_user; } +/* + * Returns the min and max vrr vfreq through the connector's debugfs file. + * Example usage: cat /sys/kernel/debug/dri/0/DP-1/vrr_range + */ +static int vrr_range_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + if (connector->status != connector_status_connected) + return -ENODEV; + + seq_printf(m, "Min: %u\n", (unsigned int)aconnector->min_vfreq); + seq_printf(m, "Max: %u\n", (unsigned int)aconnector->max_vfreq); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(vrr_range); + static const struct file_operations dp_link_settings_debugfs_fops = { .owner = THIS_MODULE, .read = dp_link_settings_read, @@ -697,7 +716,8 @@ static const struct { } dp_debugfs_entries[] = { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, - {"test_pattern", &dp_phy_test_pattern_fops} + {"test_pattern", &dp_phy_test_pattern_fops}, + {"vrr_range", &vrr_range_fops} }; int connector_debugfs_init(struct amdgpu_dm_connector *connector) diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 99cba8ea5d82..5df1256618cc 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -528,7 +528,8 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), object_count * sizeof(__u32)); + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); if (IS_ERR(object_ids)) return PTR_ERR(object_ids); diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 216f52b744a6..c882ea94172c 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1824,6 +1824,16 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, return 0; } +static inline bool +__vma_matches(struct vm_area_struct *vma, struct file *filp, + unsigned long addr, unsigned long size) +{ + if (vma->vm_file != filp) + return false; + + return vma->vm_start == addr && (vma->vm_end - vma->vm_start) == size; +} + /** * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address * it is mapped to. @@ -1882,7 +1892,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, return -EINTR; } vma = find_vma(mm, addr); - if (vma) + if (vma && __vma_matches(vma, obj->base.filp, addr, args->size)) vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); else diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d6c8f8fdfda5..017fc602a10e 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -594,7 +594,8 @@ static void i915_pmu_enable(struct perf_event *event) * Update the bitmask of enabled events and increment * the event reference counter. */ - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + BUILD_BUG_ON(ARRAY_SIZE(i915->pmu.enable_count) != I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == ~0); i915->pmu.enable |= BIT_ULL(bit); i915->pmu.enable_count[bit]++; @@ -615,11 +616,16 @@ static void i915_pmu_enable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - engine->pmu.enable |= BIT(sample); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.enable_count) != + I915_ENGINE_SAMPLE_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.sample) != + I915_ENGINE_SAMPLE_COUNT); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0); + + engine->pmu.enable |= BIT(sample); engine->pmu.enable_count[sample]++; } @@ -649,9 +655,11 @@ static void i915_pmu_disable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == 0); + /* * Decrement the reference count and clear the enabled * bitmask when the last listener on an event goes away. @@ -660,7 +668,7 @@ static void i915_pmu_disable(struct perf_event *event) engine->pmu.enable &= ~BIT(sample); } - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == 0); /* * Decrement the reference count and clear the enabled diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 7f164ca3db12..b3728c5f13e7 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -31,6 +31,8 @@ enum { ((1 << I915_PMU_SAMPLE_BITS) + \ (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0))) +#define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1) + struct i915_pmu_sample { u64 cur; }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a7d60509ca7..067054cf4a86 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1790,7 +1790,7 @@ enum i915_power_well_id { #define _CNL_PORT_TX_C_LN0_OFFSET 0x162C40 #define _CNL_PORT_TX_D_LN0_OFFSET 0x162E40 #define _CNL_PORT_TX_F_LN0_OFFSET 0x162840 -#define _CNL_PORT_TX_DW_GRP(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_GRP(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ @@ -1798,7 +1798,7 @@ enum i915_power_well_id { _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_F_GRP_OFFSET) + \ 4 * (dw)) -#define _CNL_PORT_TX_DW_LN0(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_LN0(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ @@ -1834,9 +1834,9 @@ enum i915_power_well_id { #define _CNL_PORT_TX_DW4_LN0_AE 0x162450 #define _CNL_PORT_TX_DW4_LN1_AE 0x1624D0 -#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 4)) -#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4)) -#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \ +#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(4, (port))) +#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port))) +#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port)) + \ ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \ _CNL_PORT_TX_DW4_LN0_AE))) #define ICL_PORT_TX_DW4_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(4, port)) @@ -1864,8 +1864,12 @@ enum i915_power_well_id { #define RTERM_SELECT(x) ((x) << 3) #define RTERM_SELECT_MASK (0x7 << 3) -#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 7)) -#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 7)) +#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(7, (port))) +#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(7, (port))) +#define ICL_PORT_TX_DW7_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(7, port)) +#define ICL_PORT_TX_DW7_GRP(port) _MMIO(_ICL_PORT_TX_DW_GRP(7, port)) +#define ICL_PORT_TX_DW7_LN0(port) _MMIO(_ICL_PORT_TX_DW_LN(7, 0, port)) +#define ICL_PORT_TX_DW7_LN(port, ln) _MMIO(_ICL_PORT_TX_DW_LN(7, ln, port)) #define N_SCALAR(x) ((x) << 24) #define N_SCALAR_MASK (0x7F << 24) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 4079050f9d6c..7edce1b7b348 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -494,103 +494,58 @@ static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = { { 0x2, 0x7F, 0x3F, 0x00, 0x00 }, /* 400 400 0.0 */ }; -struct icl_combo_phy_ddi_buf_trans { - u32 dw2_swing_select; - u32 dw2_swing_scalar; - u32 dw4_scaling; -}; - -/* Voltage Swing Programming for VccIO 0.85V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_85V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0xB, 0x70, 0x0018 }, /* 600 0.0 */ - { 0xB, 0x70, 0x3015 }, /* 600 3.5 */ - { 0xB, 0x70, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x00, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x00, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ -}; - -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.85V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_85V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ -}; - -/* Voltage Swing Programming for VccIO 0.95V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_95V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x76, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x76, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +/* icl_combo_phy_ddi_translations */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.95V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_95V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2[] = { + /* NT mV Trans mV db */ + { 0x0, 0x7F, 0x3F, 0x00, 0x00 }, /* 200 200 0.0 */ + { 0x8, 0x7F, 0x38, 0x00, 0x07 }, /* 200 250 1.9 */ + { 0x1, 0x7F, 0x33, 0x00, 0x0C }, /* 200 300 3.5 */ + { 0x9, 0x7F, 0x31, 0x00, 0x0E }, /* 200 350 4.9 */ + { 0x8, 0x7F, 0x3F, 0x00, 0x00 }, /* 250 250 0.0 */ + { 0x1, 0x7F, 0x38, 0x00, 0x07 }, /* 250 300 1.6 */ + { 0x9, 0x7F, 0x35, 0x00, 0x0A }, /* 250 350 2.9 */ + { 0x1, 0x7F, 0x3F, 0x00, 0x00 }, /* 300 300 0.0 */ + { 0x9, 0x7F, 0x38, 0x00, 0x07 }, /* 300 350 1.3 */ + { 0x9, 0x7F, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ }; -/* Voltage Swing Programming for VccIO 1.05V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_1_05V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x71, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x71, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr3[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 1.05V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_1_05V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = { + /* NT mV Trans mV db */ + { 0xA, 0x60, 0x3F, 0x00, 0x00 }, /* 450 450 0.0 */ + { 0xB, 0x73, 0x36, 0x00, 0x09 }, /* 450 650 3.2 */ + { 0x6, 0x7F, 0x31, 0x00, 0x0E }, /* 450 850 5.5 */ + { 0xB, 0x73, 0x3F, 0x00, 0x00 }, /* 650 650 0.0 ALS */ + { 0x6, 0x7F, 0x37, 0x00, 0x08 }, /* 650 850 2.3 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 850 850 0.0 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 850 3.0 */ }; struct icl_mg_phy_ddi_buf_trans { @@ -871,43 +826,23 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) } } -static const struct icl_combo_phy_ddi_buf_trans * +static const struct cnl_ddi_buf_trans * icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port, - int type, int *n_entries) + int type, int rate, int *n_entries) { - u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK; - - if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V); - return icl_combo_phy_ddi_translations_edp_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V); - return icl_combo_phy_ddi_translations_edp_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V); - return icl_combo_phy_ddi_translations_edp_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } - } else { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V); - return icl_combo_phy_ddi_translations_dp_hdmi_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } + if (type == INTEL_OUTPUT_HDMI) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + } else if (rate > 540000 && type == INTEL_OUTPUT_EDP) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; } + + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2); + return icl_combo_phy_ddi_translations_dp_hbr2; } static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) @@ -918,8 +853,8 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) - icl_get_combo_buf_trans(dev_priv, port, - INTEL_OUTPUT_HDMI, &n_entries); + icl_get_combo_buf_trans(dev_priv, port, INTEL_OUTPUT_HDMI, + 0, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); default_entry = n_entries - 1; @@ -2275,13 +2210,14 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder, u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = encoder->port; int n_entries; if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) icl_get_combo_buf_trans(dev_priv, port, encoder->type, - &n_entries); + intel_dp->link_rate, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); } else if (IS_CANNONLAKE(dev_priv)) { @@ -2462,14 +2398,15 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, } static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) + u32 level, enum port port, int type, + int rate) { - const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL; + const struct cnl_ddi_buf_trans *ddi_translations = NULL; u32 n_entries, val; int ln; ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type, - &n_entries); + rate, &n_entries); if (!ddi_translations) return; @@ -2478,34 +2415,23 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, level = n_entries - 1; } - /* Set PORT_TX_DW5 Rterm Sel to 110b. */ + /* Set PORT_TX_DW5 */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - val &= ~RTERM_SELECT_MASK; + val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | + TAP2_DISABLE | TAP3_DISABLE); + val |= SCALING_MODE_SEL(0x2); val |= RTERM_SELECT(0x6); - I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); - - /* Program PORT_TX_DW5 */ - val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - /* Set DisableTap2 and DisableTap3 if MIPI DSI - * Clear DisableTap2 and DisableTap3 for all other Ports - */ - if (type == INTEL_OUTPUT_DSI) { - val |= TAP2_DISABLE; - val |= TAP3_DISABLE; - } else { - val &= ~TAP2_DISABLE; - val &= ~TAP3_DISABLE; - } + val |= TAP3_DISABLE; I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* Program PORT_TX_DW2 */ val = I915_READ(ICL_PORT_TX_DW2_LN0(port)); val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select); - val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select); + val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel); + val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel); /* Program Rcomp scalar for every table entry */ - val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar); + val |= RCOMP_SCALAR(0x98); I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val); /* Program PORT_TX_DW4 */ @@ -2514,9 +2440,17 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK); - val |= ddi_translations[level].dw4_scaling; + val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1); + val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2); + val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff); I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); } + + /* Program PORT_TX_DW7 */ + val = I915_READ(ICL_PORT_TX_DW7_LN0(port)); + val &= ~N_SCALAR_MASK; + val |= N_SCALAR(ddi_translations[level].dw7_n_scalar); + I915_WRITE(ICL_PORT_TX_DW7_GRP(port), val); } static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, @@ -2581,7 +2515,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* 5. Program swing and de-emphasis */ - icl_ddi_combo_vswing_program(dev_priv, level, port, type); + icl_ddi_combo_vswing_program(dev_priv, level, port, type, rate); /* 6. Set training enable to trigger update */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index fdd2cbc56fa3..22a74608c6e4 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -304,9 +304,11 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp) static int icl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); enum port port = dig_port->base.port; - if (port == PORT_B) + if (intel_port_is_combophy(dev_priv, port) && + !intel_dp_is_edp(intel_dp)) return 540000; return 810000; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f94a04b4ad87..e9ddeaf05a14 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -209,6 +209,16 @@ struct intel_fbdev { unsigned long vma_flags; async_cookie_t cookie; int preferred_bpp; + + /* Whether or not fbdev hpd processing is temporarily suspended */ + bool hpd_suspended : 1; + /* Set when a hotplug was received while HPD processing was + * suspended + */ + bool hpd_waiting : 1; + + /* Protects hpd_suspended */ + struct mutex hpd_lock; }; struct intel_encoder { diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index fb5bb5b32a60..7f365ac0b549 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -679,6 +679,7 @@ int intel_fbdev_init(struct drm_device *dev) if (ifbdev == NULL) return -ENOMEM; + mutex_init(&ifbdev->hpd_lock); drm_fb_helper_prepare(dev, &ifbdev->helper, &intel_fb_helper_funcs); if (!intel_fbdev_init_bios(dev, ifbdev)) @@ -752,6 +753,26 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv) intel_fbdev_destroy(ifbdev); } +/* Suspends/resumes fbdev processing of incoming HPD events. When resuming HPD + * processing, fbdev will perform a full connector reprobe if a hotplug event + * was received while HPD was suspended. + */ +static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state) +{ + bool send_hpd = false; + + mutex_lock(&ifbdev->hpd_lock); + ifbdev->hpd_suspended = state == FBINFO_STATE_SUSPENDED; + send_hpd = !ifbdev->hpd_suspended && ifbdev->hpd_waiting; + ifbdev->hpd_waiting = false; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd) { + DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n"); + drm_fb_helper_hotplug_event(&ifbdev->helper); + } +} + void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -773,6 +794,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous */ if (state != FBINFO_STATE_RUNNING) flush_work(&dev_priv->fbdev_suspend_work); + console_lock(); } else { /* @@ -800,17 +822,26 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous drm_fb_helper_set_suspend(&ifbdev->helper, state); console_unlock(); + + intel_fbdev_hpd_set_suspend(ifbdev, state); } void intel_fbdev_output_poll_changed(struct drm_device *dev) { struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + bool send_hpd; if (!ifbdev) return; intel_fbdev_sync(ifbdev); - if (ifbdev->vma || ifbdev->helper.deferred_setup) + + mutex_lock(&ifbdev->hpd_lock); + send_hpd = !ifbdev->hpd_suspended; + ifbdev->hpd_waiting = true; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd && (ifbdev->vma || ifbdev->helper.deferred_setup)) drm_fb_helper_hotplug_event(&ifbdev->helper); } diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index b8f106d9ecf8..3ac20153705a 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -55,7 +55,12 @@ struct opregion_header { u8 signature[16]; u32 size; - u32 opregion_ver; + struct { + u8 rsvd; + u8 revision; + u8 minor; + u8 major; + } __packed over; u8 bios_ver[32]; u8 vbios_ver[16]; u8 driver_ver[16]; @@ -119,7 +124,8 @@ struct opregion_asle { u64 fdss; u32 fdsp; u32 stat; - u64 rvda; /* Physical address of raw vbt data */ + u64 rvda; /* Physical (2.0) or relative from opregion (2.1+) + * address of raw VBT data. */ u32 rvds; /* Size of raw vbt data */ u8 rsvd[58]; } __packed; @@ -925,6 +931,11 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) opregion->header = base; opregion->lid_state = base + ACPI_CLID; + DRM_DEBUG_DRIVER("ACPI OpRegion version %u.%u.%u\n", + opregion->header->over.major, + opregion->header->over.minor, + opregion->header->over.revision); + mboxes = opregion->header->mboxes; if (mboxes & MBOX_ACPI) { DRM_DEBUG_DRIVER("Public ACPI methods supported\n"); @@ -953,11 +964,26 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) if (dmi_check_system(intel_no_opregion_vbt)) goto out; - if (opregion->header->opregion_ver >= 2 && opregion->asle && + if (opregion->header->over.major >= 2 && opregion->asle && opregion->asle->rvda && opregion->asle->rvds) { - opregion->rvda = memremap(opregion->asle->rvda, - opregion->asle->rvds, + resource_size_t rvda = opregion->asle->rvda; + + /* + * opregion 2.0: rvda is the physical VBT address. + * + * opregion 2.1+: rvda is unsigned, relative offset from + * opregion base, and should never point within opregion. + */ + if (opregion->header->over.major > 2 || + opregion->header->over.minor >= 1) { + WARN_ON(rvda < OPREGION_SIZE); + + rvda += asls; + } + + opregion->rvda = memremap(rvda, opregion->asle->rvds, MEMREMAP_WB); + vbt = opregion->rvda; vbt_size = opregion->asle->rvds; if (intel_bios_is_valid_vbt(vbt, vbt_size)) { @@ -967,6 +993,8 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) goto out; } else { DRM_DEBUG_KMS("Invalid VBT in ACPI OpRegion (RVDA)\n"); + memunmap(opregion->rvda); + opregion->rvda = NULL; } } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 72edaa7ff411..a1a7cc29fdd1 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -415,16 +415,17 @@ struct intel_engine_cs { /** * @enable_count: Reference count for the enabled samplers. * - * Index number corresponds to the bit number from @enable. + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ - unsigned int enable_count[I915_PMU_SAMPLE_BITS]; + unsigned int enable_count[I915_ENGINE_SAMPLE_COUNT]; /** * @sample: Counter values for sampling events. * * Our internal timer stores the current counters in this field. + * + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ -#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1) - struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX]; + struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_COUNT]; } pmu; /* diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 2c5bbe317353..e31e263cf86b 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -643,8 +643,10 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) int bus_format; ret = of_property_read_u32(child, "reg", &i); - if (ret || i < 0 || i > 1) - return -EINVAL; + if (ret || i < 0 || i > 1) { + ret = -EINVAL; + goto free_child; + } if (!of_device_is_available(child)) continue; @@ -657,7 +659,6 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; - channel->child = child; /* * The output port is port@4 with an external 4-port mux or @@ -667,13 +668,13 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) imx_ldb->lvds_mux ? 4 : 2, 0, &channel->panel, &channel->bridge); if (ret && ret != -ENODEV) - return ret; + goto free_child; /* panel ddc only if there is no bridge */ if (!channel->bridge) { ret = imx_ldb_panel_ddc(dev, channel, child); if (ret) - return ret; + goto free_child; } bus_format = of_get_bus_format(dev, child); @@ -689,18 +690,26 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (bus_format < 0) { dev_err(dev, "could not determine data mapping: %d\n", bus_format); - return bus_format; + ret = bus_format; + goto free_child; } channel->bus_format = bus_format; + channel->child = child; ret = imx_ldb_register(drm, channel); - if (ret) - return ret; + if (ret) { + channel->child = NULL; + goto free_child; + } } dev_set_drvdata(dev, imx_ldb); return 0; + +free_child: + of_node_put(child); + return ret; } static void imx_ldb_unbind(struct device *dev, struct device *master, diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index c390924de93d..21e964f6ab5c 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -370,9 +370,9 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; - /* CRTC should be enabled */ + /* nothing to check when disabling or disabled */ if (!crtc_state->enable) - return -EINVAL; + return 0; switch (plane->type) { case DRM_PLANE_TYPE_PRIMARY: diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 4463d3826ecb..e2942c9a11a7 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -440,13 +440,10 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = sched->ops->dependency(sched_job, entity))) { + trace_drm_sched_job_wait_dep(sched_job, entity->dependency); - if (drm_sched_entity_add_dependency_cb(entity)) { - - trace_drm_sched_job_wait_dep(sched_job, - entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/vkms/vkms_crc.c b/drivers/gpu/drm/vkms/vkms_crc.c index 9d9e8146db90..d7b409a3c0f8 100644 --- a/drivers/gpu/drm/vkms/vkms_crc.c +++ b/drivers/gpu/drm/vkms/vkms_crc.c @@ -1,4 +1,5 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ + #include "vkms_drv.h" #include <linux/crc32.h> #include <drm/drm_atomic.h> diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c index 177bbcb38306..eb56ee893761 100644 --- a/drivers/gpu/drm/vkms/vkms_crtc.c +++ b/drivers/gpu/drm/vkms/vkms_crtc.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 83087877565c..7dcbecb5fac2 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -1,9 +1,4 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ /** * DOC: vkms (Virtual Kernel Modesetting) diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index e4469cd3d254..81f1cfbeb936 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + #ifndef _VKMS_DRV_H_ #define _VKMS_DRV_H_ diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c index 80311daed47a..138b0bb325cf 100644 --- a/drivers/gpu/drm/vkms/vkms_gem.c +++ b/drivers/gpu/drm/vkms/vkms_gem.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include <linux/shmem_fs.h> diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c index 271a0eb9042c..4173e4f48334 100644 --- a/drivers/gpu/drm/vkms/vkms_output.c +++ b/drivers/gpu/drm/vkms/vkms_output.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_crtc_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c index 418817600ad1..0e67d2d42f0c 100644 --- a/drivers/gpu/drm/vkms/vkms_plane.c +++ b/drivers/gpu/drm/vkms/vkms_plane.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_plane_helper.h> diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 474b00e19697..0a7d4395d427 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -898,8 +898,8 @@ static struct ipu_devtype ipu_type_imx51 = { .cpmem_ofs = 0x1f000000, .srm_ofs = 0x1f040000, .tpm_ofs = 0x1f060000, - .csi0_ofs = 0x1f030000, - .csi1_ofs = 0x1f038000, + .csi0_ofs = 0x1e030000, + .csi1_ofs = 0x1e038000, .ic_ofs = 0x1e020000, .disp0_ofs = 0x1e040000, .disp1_ofs = 0x1e048000, @@ -914,8 +914,8 @@ static struct ipu_devtype ipu_type_imx53 = { .cpmem_ofs = 0x07000000, .srm_ofs = 0x07040000, .tpm_ofs = 0x07060000, - .csi0_ofs = 0x07030000, - .csi1_ofs = 0x07038000, + .csi0_ofs = 0x06030000, + .csi1_ofs = 0x06038000, .ic_ofs = 0x06020000, .disp0_ofs = 0x06040000, .disp1_ofs = 0x06048000, diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index 2f8db9d62551..4a28f3fbb0a2 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -106,6 +106,7 @@ struct ipu_pre { void *buffer_virt; bool in_use; unsigned int safe_window_end; + unsigned int last_bufaddr; }; static DEFINE_MUTEX(ipu_pre_list_mutex); @@ -185,6 +186,7 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF); writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; val = IPU_PRE_PREF_ENG_CTRL_INPUT_PIXEL_FORMAT(0) | IPU_PRE_PREF_ENG_CTRL_INPUT_ACTIVE_BPP(active_bpp) | @@ -242,7 +244,11 @@ void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr) unsigned short current_yblock; u32 val; + if (bufaddr == pre->last_bufaddr) + return; + writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; do { if (time_after(jiffies, timeout)) { diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 4adec4ab7d06..59ee01f3d022 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -3594,7 +3594,8 @@ nct6775_check_fan_inputs(struct nct6775_data *data) fan5pin |= cr1b & BIT(5); fan5pin |= creb & BIT(5); - fan6pin = creb & BIT(3); + fan6pin = !dsw_en && (cr2d & BIT(1)); + fan6pin |= creb & BIT(3); pwm5pin |= cr2d & BIT(7); pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); 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/md/dm-crypt.c b/drivers/md/dm-crypt.c index 47d4e0d30bf0..dd538e6b2748 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -932,7 +932,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) if (IS_ERR(bip)) return PTR_ERR(bip); - tag_len = io->cc->on_disk_tag_size * bio_sectors(bio); + tag_len = io->cc->on_disk_tag_size * (bio_sectors(bio) >> io->cc->sector_shift); bip->bip_iter.bi_size = tag_len; bip->bip_iter.bi_sector = io->cc->start + io->sector; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ca8af21bf644..e83b63608262 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -257,6 +257,7 @@ struct pool { spinlock_t lock; struct bio_list deferred_flush_bios; + struct bio_list deferred_flush_completions; struct list_head prepared_mappings; struct list_head prepared_discards; struct list_head prepared_discards_pt2; @@ -956,6 +957,39 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) mempool_free(m, &m->tc->pool->mapping_pool); } +static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + /* + * If the bio has the REQ_FUA flag set we must commit the metadata + * before signaling its completion. + */ + if (!bio_triggers_commit(tc, bio)) { + bio_endio(bio); + return; + } + + /* + * Complete bio with an error if earlier I/O caused changes to the + * metadata that can't be committed, e.g, due to I/O errors on the + * metadata device. + */ + if (dm_thin_aborted_changes(tc->td)) { + bio_io_error(bio); + return; + } + + /* + * Batch together any bios that trigger commits and then issue a + * single commit for them in process_deferred_bios(). + */ + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_flush_completions, bio); + spin_unlock_irqrestore(&pool->lock, flags); +} + static void process_prepared_mapping(struct dm_thin_new_mapping *m) { struct thin_c *tc = m->tc; @@ -988,7 +1022,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) */ if (bio) { inc_remap_and_issue_cell(tc, m->cell, m->data_block); - bio_endio(bio); + complete_overwrite_bio(tc, bio); } else { inc_all_io_entry(tc->pool, m->cell->holder); remap_and_issue(tc, m->cell->holder, m->data_block); @@ -2317,7 +2351,7 @@ static void process_deferred_bios(struct pool *pool) { unsigned long flags; struct bio *bio; - struct bio_list bios; + struct bio_list bios, bio_completions; struct thin_c *tc; tc = get_first_thin(pool); @@ -2328,26 +2362,36 @@ static void process_deferred_bios(struct pool *pool) } /* - * If there are any deferred flush bios, we must commit - * the metadata before issuing them. + * If there are any deferred flush bios, we must commit the metadata + * before issuing them or signaling their completion. */ bio_list_init(&bios); + bio_list_init(&bio_completions); + spin_lock_irqsave(&pool->lock, flags); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); + + bio_list_merge(&bio_completions, &pool->deferred_flush_completions); + bio_list_init(&pool->deferred_flush_completions); spin_unlock_irqrestore(&pool->lock, flags); - if (bio_list_empty(&bios) && + if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) return; if (commit(pool)) { + bio_list_merge(&bios, &bio_completions); + while ((bio = bio_list_pop(&bios))) bio_io_error(bio); return; } pool->last_commit_jiffies = jiffies; + while ((bio = bio_list_pop(&bio_completions))) + bio_endio(bio); + while ((bio = bio_list_pop(&bios))) generic_make_request(bio); } @@ -2954,6 +2998,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout); spin_lock_init(&pool->lock); bio_list_init(&pool->deferred_flush_bios); + bio_list_init(&pool->deferred_flush_completions); INIT_LIST_HEAD(&pool->prepared_mappings); INIT_LIST_HEAD(&pool->prepared_discards); INIT_LIST_HEAD(&pool->prepared_discards_pt2); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 1d54109071cc..fa47249fa3e4 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1863,6 +1863,20 @@ static void end_sync_read(struct bio *bio) reschedule_retry(r1_bio); } +static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) +{ + sector_t sync_blocks = 0; + sector_t s = r1_bio->sector; + long sectors_to_go = r1_bio->sectors; + + /* make sure these bits don't get cleared. */ + do { + md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); + s += sync_blocks; + sectors_to_go -= sync_blocks; + } while (sectors_to_go > 0); +} + static void end_sync_write(struct bio *bio) { int uptodate = !bio->bi_status; @@ -1874,15 +1888,7 @@ static void end_sync_write(struct bio *bio) struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; if (!uptodate) { - sector_t sync_blocks = 0; - sector_t s = r1_bio->sector; - long sectors_to_go = r1_bio->sectors; - /* make sure these bits doesn't get cleared. */ - do { - md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); - s += sync_blocks; - sectors_to_go -= sync_blocks; - } while (sectors_to_go > 0); + abort_sync_write(mddev, r1_bio); set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -2172,8 +2178,10 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) (i == r1_bio->read_disk || !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)))) continue; - if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) + if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) { + abort_sync_write(mddev, r1_bio); continue; + } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index aef1185f383d..14f3fdb8c6bb 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2112,7 +2112,7 @@ static void mmc_blk_mq_req_done(struct mmc_request *mrq) if (waiting) wake_up(&mq->wait); else - kblockd_schedule_work(&mq->complete_work); + queue_work(mq->card->complete_wq, &mq->complete_work); return; } @@ -2924,6 +2924,13 @@ static int mmc_blk_probe(struct mmc_card *card) mmc_fixup_device(card, mmc_blk_fixups); + card->complete_wq = alloc_workqueue("mmc_complete", + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + if (unlikely(!card->complete_wq)) { + pr_err("Failed to create mmc completion workqueue"); + return -ENOMEM; + } + md = mmc_blk_alloc(card); if (IS_ERR(md)) return PTR_ERR(md); @@ -2987,6 +2994,7 @@ static void mmc_blk_remove(struct mmc_card *card) pm_runtime_put_noidle(&card->dev); mmc_blk_remove_req(md); dev_set_drvdata(&card->dev, NULL); + destroy_workqueue(card->complete_wq); } static int _mmc_blk_suspend(struct mmc_card *card) diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index f19ec60bcbdc..2eba507790e4 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1338,7 +1338,8 @@ static int meson_mmc_probe(struct platform_device *pdev) host->regs + SD_EMMC_IRQ_EN); ret = request_threaded_irq(host->irq, meson_mmc_irq, - meson_mmc_irq_thread, IRQF_SHARED, NULL, host); + meson_mmc_irq_thread, IRQF_SHARED, + dev_name(&pdev->dev), host); if (ret) goto err_init_clk; diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 279e326e397e..70fadc976795 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1399,13 +1399,37 @@ static int sunxi_mmc_probe(struct platform_device *pdev) mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ; - if (host->cfg->clk_delays || host->use_new_timings) + /* + * Some H5 devices do not have signal traces precise enough to + * use HS DDR mode for their eMMC chips. + * + * We still enable HS DDR modes for all the other controller + * variants that support them. + */ + if ((host->cfg->clk_delays || host->use_new_timings) && + !of_device_is_compatible(pdev->dev.of_node, + "allwinner,sun50i-h5-emmc")) mmc->caps |= MMC_CAP_1_8V_DDR | MMC_CAP_3_3V_DDR; ret = mmc_of_parse(mmc); if (ret) goto error_free_dma; + /* + * If we don't support delay chains in the SoC, we can't use any + * of the higher speed modes. Mask them out in case the device + * tree specifies the properties for them, which gets added to + * the caps by mmc_of_parse() above. + */ + if (!(host->cfg->clk_delays || host->use_new_timings)) { + mmc->caps &= ~(MMC_CAP_3_3V_DDR | MMC_CAP_1_8V_DDR | + MMC_CAP_1_2V_DDR | MMC_CAP_UHS); + mmc->caps2 &= ~MMC_CAP2_HS200; + } + + /* TODO: This driver doesn't support HS400 mode yet */ + mmc->caps2 &= ~MMC_CAP2_HS400; + ret = sunxi_mmc_init_host(host); if (ret) goto error_free_dma; diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c index 22f753e555ac..83f88b8b5d9f 100644 --- a/drivers/mtd/devices/powernv_flash.c +++ b/drivers/mtd/devices/powernv_flash.c @@ -212,7 +212,7 @@ static int powernv_flash_set_driver_info(struct device *dev, * Going to have to check what details I need to set and how to * get them */ - mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFn", dev->of_node); + mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); mtd->type = MTD_NORFLASH; mtd->flags = MTD_WRITEABLE; mtd->size = size; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 999b705769a8..3ef01baef9b6 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -507,6 +507,7 @@ static int mtd_nvmem_add(struct mtd_info *mtd) { struct nvmem_config config = {}; + config.id = -1; config.dev = &mtd->dev; config.name = mtd->name; config.owner = THIS_MODULE; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index edb1c023a753..21bf8ac78380 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -197,9 +197,9 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" - depends on INET && NET_UDP_TUNNEL + depends on INET depends on IPV6 || !IPV6 - select NET_IP_TUNNEL + select NET_UDP_TUNNEL select GRO_CELLS ---help--- This allows one to create geneve virtual interfaces that provide diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 0e4bbdcc614f..c76892ac4e69 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -344,7 +344,8 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); } -static void b53_enable_vlan(struct b53_device *dev, bool enable) +static void b53_enable_vlan(struct b53_device *dev, bool enable, + bool enable_filtering) { u8 mgmt, vc0, vc1, vc4 = 0, vc5; @@ -369,8 +370,13 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID; vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; - vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; - vc5 |= VC5_DROP_VTABLE_MISS; + if (enable_filtering) { + vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; + vc5 |= VC5_DROP_VTABLE_MISS; + } else { + vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S; + vc5 &= ~VC5_DROP_VTABLE_MISS; + } if (is5325(dev)) vc0 &= ~VC0_RESERVED_1; @@ -420,6 +426,9 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) } b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt); + + dev->vlan_enabled = enable; + dev->vlan_filtering_enabled = enable_filtering; } static int b53_set_jumbo(struct b53_device *dev, bool enable, bool allow_10_100) @@ -632,25 +641,35 @@ static void b53_enable_mib(struct b53_device *dev) b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc); } +static u16 b53_default_pvid(struct b53_device *dev) +{ + if (is5325(dev) || is5365(dev)) + return 1; + else + return 0; +} + int b53_configure_vlan(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; struct b53_vlan vl = { 0 }; - int i; + int i, def_vid; + + def_vid = b53_default_pvid(dev); /* clear all vlan entries */ if (is5325(dev) || is5365(dev)) { - for (i = 1; i < dev->num_vlans; i++) + for (i = def_vid; i < dev->num_vlans; i++) b53_set_vlan_entry(dev, i, &vl); } else { b53_do_vlan_op(dev, VTA_CMD_CLEAR); } - b53_enable_vlan(dev, false); + b53_enable_vlan(dev, false, dev->vlan_filtering_enabled); b53_for_each_port(dev, i) b53_write16(dev, B53_VLAN_PAGE, - B53_VLAN_PORT_DEF_TAG(i), 1); + B53_VLAN_PORT_DEF_TAG(i), def_vid); if (!is5325(dev) && !is5365(dev)) b53_set_jumbo(dev, dev->enable_jumbo, false); @@ -1255,6 +1274,46 @@ EXPORT_SYMBOL(b53_phylink_mac_link_up); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) { + struct b53_device *dev = ds->priv; + struct net_device *bridge_dev; + unsigned int i; + u16 pvid, new_pvid; + + /* Handle the case were multiple bridges span the same switch device + * and one of them has a different setting than what is being requested + * which would be breaking filtering semantics for any of the other + * bridge devices. + */ + b53_for_each_port(dev, i) { + bridge_dev = dsa_to_port(ds, i)->bridge_dev; + if (bridge_dev && + bridge_dev != dsa_to_port(ds, port)->bridge_dev && + br_vlan_enabled(bridge_dev) != vlan_filtering) { + netdev_err(bridge_dev, + "VLAN filtering is global to the switch!\n"); + return -EINVAL; + } + } + + b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid); + new_pvid = pvid; + if (dev->vlan_filtering_enabled && !vlan_filtering) { + /* Filtering is currently enabled, use the default PVID since + * the bridge does not expect tagging anymore + */ + dev->ports[port].pvid = pvid; + new_pvid = b53_default_pvid(dev); + } else if (!dev->vlan_filtering_enabled && vlan_filtering) { + /* Filtering is currently disabled, restore the previous PVID */ + new_pvid = dev->ports[port].pvid; + } + + if (pvid != new_pvid) + b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), + new_pvid); + + b53_enable_vlan(dev, dev->vlan_enabled, vlan_filtering); + return 0; } EXPORT_SYMBOL(b53_vlan_filtering); @@ -1270,7 +1329,7 @@ int b53_vlan_prepare(struct dsa_switch *ds, int port, if (vlan->vid_end > dev->num_vlans) return -ERANGE; - b53_enable_vlan(dev, true); + b53_enable_vlan(dev, true, dev->vlan_filtering_enabled); return 0; } @@ -1300,7 +1359,7 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_fast_age_vlan(dev, vid); } - if (pvid) { + if (pvid && !dsa_is_cpu_port(ds, port)) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), vlan->vid_end); b53_fast_age_vlan(dev, vid); @@ -1326,12 +1385,8 @@ int b53_vlan_del(struct dsa_switch *ds, int port, vl->members &= ~BIT(port); - if (pvid == vid) { - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; - } + if (pvid == vid) + pvid = b53_default_pvid(dev); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag &= ~(BIT(port)); @@ -1644,10 +1699,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan); dev->ports[port].vlan_ctl_mask = pvlan; - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; + pvid = b53_default_pvid(dev); /* Make this port join all VLANs without VLAN entries */ if (is58xx(dev)) { diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index ec796482792d..4dc7ee38b258 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -91,6 +91,7 @@ enum { struct b53_port { u16 vlan_ctl_mask; struct ethtool_eee eee; + u16 pvid; }; struct b53_vlan { @@ -137,6 +138,8 @@ struct b53_device { unsigned int num_vlans; struct b53_vlan *vlans; + bool vlan_enabled; + bool vlan_filtering_enabled; unsigned int num_ports; struct b53_port *ports; }; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 361fbde76654..14138d423cf1 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) * port, the other ones have already been disabled during * bcm_sf2_sw_setup */ - for (port = 0; port < DSA_MAX_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port)) bcm_sf2_port_disable(ds, port, NULL); } @@ -726,10 +726,11 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, { struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; /* Get the parent device WoL settings */ - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); /* Advertise the parent device supported settings */ wol->supported = pwol.supported; @@ -750,9 +751,10 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->ports[port].cpu_dp->index; - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); if (wol->wolopts & ~pwol.supported) return -EINVAL; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8dca2c949e73..12fd7ce3f1ff 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) unsigned int sub_irq; unsigned int n; u16 reg; + u16 ctl1; int err; mutex_lock(&chip->reg_lock); @@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) if (err) goto out; - for (n = 0; n < chip->g1_irq.nirqs; ++n) { - if (reg & (1 << n)) { - sub_irq = irq_find_mapping(chip->g1_irq.domain, n); - handle_nested_irq(sub_irq); - ++nhandled; + do { + for (n = 0; n < chip->g1_irq.nirqs; ++n) { + if (reg & (1 << n)) { + sub_irq = irq_find_mapping(chip->g1_irq.domain, + n); + handle_nested_irq(sub_irq); + ++nhandled; + } } - } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); + if (err) + goto unlock; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, ®); +unlock: + mutex_unlock(&chip->reg_lock); + if (err) + goto out; + ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); + } while (reg & ctl1); + out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a70bb1bb90e7..a6eacf2099c3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter) goto err_device_destroy; } - clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); - /* Make sure we don't have a race with AENQ Links state handler */ - if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) - netif_carrier_on(adapter->netdev); - rc = ena_enable_msix_and_set_admin_interrupts(adapter, adapter->num_queues); if (rc) { @@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter) } set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); + + clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); + if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) + netif_carrier_on(adapter->netdev); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully, Driver info: %s\n", diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index dc8b6173d8d8..63870072cbbd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,7 +45,7 @@ #define DRV_MODULE_VER_MAJOR 2 #define DRV_MODULE_VER_MINOR 0 -#define DRV_MODULE_VER_SUBMINOR 2 +#define DRV_MODULE_VER_SUBMINOR 3 #define DRV_MODULE_NAME "ena" #ifndef DRV_MODULE_VERSION diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 28c9b0bdf2f6..bc3ac369cbe3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -134,6 +134,10 @@ static void bcm_sysport_set_rx_csum(struct net_device *dev, priv->rx_chk_en = !!(wanted & NETIF_F_RXCSUM); reg = rxchk_readl(priv, RXCHK_CONTROL); + /* Clear L2 header checks, which would prevent BPDUs + * from being received. + */ + reg &= ~RXCHK_L2_HDR_DIS; if (priv->rx_chk_en) reg |= RXCHK_EN; else diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2370dc204202..697c2427f2b7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2098,6 +2098,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +static __u32 fec_enet_register_version = 2; static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2128,6 +2129,7 @@ static u32 fec_enet_register_offset[] = { IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; #else +static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0, FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0, @@ -2149,6 +2151,8 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; + regs->version = fec_enet_register_version; + memset(buf, 0, regs->len); for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 3b9e74be5fbd..ac55db065f16 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3081,6 +3081,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_dev = dev_get_drvdata(&pdev->dev); if (!dsaf_dev) { dev_err(&pdev->dev, "dsaf_dev is NULL\n"); + put_device(&pdev->dev); return -ENODEV; } @@ -3088,6 +3089,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) if (AE_IS_VER1(dsaf_dev->dsaf_ver)) { dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n", dsaf_dev->ae_dev.name); + put_device(&pdev->dev); return -ENODEV; } @@ -3126,6 +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/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 2f427271a793..292a668ce88e 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2879,7 +2879,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) ret = mv643xx_eth_shared_of_probe(pdev); if (ret) - return ret; + goto err_put_clk; pd = dev_get_platdata(&pdev->dev); msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ? @@ -2887,6 +2887,11 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) infer_hw_params(msp); return 0; + +err_put_clk: + if (!IS_ERR(msp->clk)) + clk_disable_unprepare(msp->clk); + return ret; } static int mv643xx_eth_shared_remove(struct platform_device *pdev) 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/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 6b88881b8e35..c1438ae52a11 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3360,7 +3360,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->addr_len = ETH_ALEN; mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]); if (!is_valid_ether_addr(dev->dev_addr)) { - en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", + en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n", priv->port, dev->dev_addr); err = -EINVAL; goto out; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9a0881cb7f51..6c01314e87b0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, } #endif +#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) + /* We reach this function only after checking that any of * the (IPv4 | IPv6) bits are set in cqe->status. */ @@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, netdev_features_t dev_features) { __wsum hw_checksum = 0; + void *hdr; + + /* CQE csum doesn't cover padding octets in short ethernet + * frames. And the pad field is appended prior to calculating + * and appending the FCS field. + * + * Detecting these padded frames requires to verify and parse + * IP headers, so we simply force all those small frames to skip + * checksum complete. + */ + if (short_frame(skb->len)) + return -EINVAL; - void *hdr = (u8 *)va + sizeof(struct ethhdr); - + hdr = (u8 *)va + sizeof(struct ethhdr); hw_checksum = csum_unfold((__force __sum16)cqe->checksum); if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) && @@ -819,6 +832,11 @@ xdp_drop_no_cnt: skb_record_rx_queue(skb, cq_ring); if (likely(dev->features & NETIF_F_RXCSUM)) { + /* TODO: For IP non TCP/UDP packets when csum complete is + * not an option (not supported or any other reason) we can + * actually check cqe IPOK status bit and report + * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE + */ if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3e0fa8a8077b..e267ff93e8a8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1583,6 +1583,24 @@ no_trig: spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); } +void mlx5_cmd_flush(struct mlx5_core_dev *dev) +{ + struct mlx5_cmd *cmd = &dev->cmd; + int i; + + for (i = 0; i < cmd->max_reg_cmds; i++) + while (down_trylock(&cmd->sem)) + mlx5_cmd_trigger_completions(dev); + + while (down_trylock(&cmd->pages_sem)) + mlx5_cmd_trigger_completions(dev); + + /* Unlock cmdif */ + up(&cmd->pages_sem); + for (i = 0; i < cmd->max_reg_cmds; i++) + up(&cmd->sem); +} + static int status_to_err(u8 status) { return status ? -1 : 0; /* TBD more meaningful codes */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8fa8fdd30b85..448a92561567 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -657,6 +657,7 @@ struct mlx5e_channel_stats { enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, + MLX5E_STATE_XDP_TX_ENABLED, }; struct mlx5e_rqt { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 3740177eed09..03b2a9f9c589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int sq_num; int i; - if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state))) + /* this flag is sufficient, no need to test internal sq state */ + if (unlikely(!mlx5e_xdp_tx_is_enabled(priv))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, sq = &priv->channels.c[sq_num]->xdpsq; - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return -ENETDOWN; - for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; struct mlx5e_xdp_info xdpi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3a67cb3cd179..ee27a7c8cd87 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq); int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + +static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + /* let other device's napi(s) see our new state */ + synchronize_rcu(); +} + +static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 3bbccead2f63..47233b9a4f81 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -354,9 +354,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -372,6 +369,10 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (arfs_enabled) mlx5e_arfs_disable(priv); + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + /* Switch to new channels, set new parameters and close old ones */ mlx5e_switch_priv_channels(priv, &new_channels, NULL); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 01819e5c9975..93e50ccd44c3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2938,6 +2938,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); + mlx5e_xdp_tx_enable(priv); netif_tx_start_all_queues(priv->netdev); if (mlx5e_is_vport_rep(priv)) @@ -2959,6 +2960,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) */ netif_tx_stop_all_queues(priv->netdev); netif_tx_disable(priv->netdev); + mlx5e_xdp_tx_disable(priv); mlx5e_deactivate_channels(&priv->channels); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index fbc42b7252a9..503035469d2d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -211,11 +211,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data enum port_module_event_status_type module_status; enum port_module_event_error_type error_type; struct mlx5_eqe_port_module *module_event_eqe; - const char *status_str, *error_str; + const char *status_str; u8 module_num; module_event_eqe = &eqe->data.port_module; - module_num = module_event_eqe->module; module_status = module_event_eqe->module_status & PORT_MODULE_EVENT_MODULE_STATUS_MASK; error_type = module_event_eqe->error_type & @@ -223,25 +222,27 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data if (module_status < MLX5_MODULE_STATUS_NUM) events->pme_stats.status_counters[module_status]++; - status_str = mlx5_pme_status_to_string(module_status); - if (module_status == MLX5_MODULE_STATUS_ERROR) { + if (module_status == MLX5_MODULE_STATUS_ERROR) if (error_type < MLX5_MODULE_EVENT_ERROR_NUM) events->pme_stats.error_counters[error_type]++; - error_str = mlx5_pme_error_to_string(error_type); - } if (!printk_ratelimit()) return NOTIFY_OK; - if (module_status == MLX5_MODULE_STATUS_ERROR) + module_num = module_event_eqe->module; + status_str = mlx5_pme_status_to_string(module_status); + if (module_status == MLX5_MODULE_STATUS_ERROR) { + const char *error_str = mlx5_pme_error_to_string(error_type); + mlx5_core_err(events->dev, "Port module event[error]: module %u, %s, %s\n", module_num, status_str, error_str); - else + } else { mlx5_core_info(events->dev, "Port module event: module %u, %s\n", module_num, status_str); + } return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 196c07383082..cb9fa3430c53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -103,7 +103,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mlx5_core_err(dev, "start\n"); if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - mlx5_cmd_trigger_completions(dev); + mlx5_cmd_flush(dev); } mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 5300b0b6d836..4fdac020b795 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -126,6 +126,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts); void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); +void mlx5_cmd_flush(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 32519c93df17..b65e274b02e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -862,8 +862,9 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { bool configure = false; bool pfc = false; + u16 thres_cells; + u16 delay_cells; bool lossy; - u16 thres; for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) { if (prio_tc[j] == i) { @@ -877,10 +878,11 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, continue; lossy = !(pfc || pause_en); - thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, - pause_en); - mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy); + thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, + pfc, pause_en); + mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres_cells + delay_cells, + thres_cells, lossy); } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl); 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/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index abb94c543aa2..6e36b88ca7c9 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1286,11 +1286,13 @@ static u16 rtl_get_events(struct rtl8169_private *tp) static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) { RTL_W16(tp, IntrStatus, bits); + mmiowb(); } static void rtl_irq_disable(struct rtl8169_private *tp) { RTL_W16(tp, IntrMask, 0); + mmiowb(); } #define RTL_EVENT_NAPI_RX (RxOK | RxErr) @@ -6072,7 +6074,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; - bool stop_queue; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -6114,6 +6115,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); + netdev_sent_queue(dev, skb->len); + skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ @@ -6126,14 +6129,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); - if (unlikely(stop_queue)) - netif_stop_queue(dev); + RTL_W8(tp, TxPoll, NPQ); - if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) - RTL_W8(tp, TxPoll, NPQ); + mmiowb(); - if (unlikely(stop_queue)) { + if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must + * not miss a ring update when it notices a stopped queue. + */ + smp_wmb(); + netif_stop_queue(dev); /* Sync with rtl_tx: * - publish queue status and cur_tx ring index (write barrier) * - refresh dirty_tx ring index (read barrier). @@ -6483,7 +6488,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); + rtl_irq_enable(tp); + mmiowb(); } return work_done; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 2f2bda68d861..c08034154a9a 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -6115,7 +6115,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx, static int efx_ef10_mtd_probe(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX); - DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT); + DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 }; struct efx_mcdi_mtd_partition *parts; size_t outlen, n_parts_total, i, n_parts; unsigned int type; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 20299f6f65fc..736e29635b77 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts) static int dwmac4_rx_check_timestamp(void *desc) { struct dma_desc *p = (struct dma_desc *)desc; + unsigned int rdes0 = le32_to_cpu(p->des0); + unsigned int rdes1 = le32_to_cpu(p->des1); + unsigned int rdes3 = le32_to_cpu(p->des3); u32 own, ctxt; int ret = 1; - own = p->des3 & RDES3_OWN; - ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + own = rdes3 & RDES3_OWN; + ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR) >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); if (likely(!own && ctxt)) { - if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff)) /* Corrupted value */ ret = -EINVAL; else 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/phy/phy.c b/drivers/net/phy/phy.c index 189cd2048c3a..c5675df5fc6f 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -553,7 +553,7 @@ int phy_start_aneg(struct phy_device *phydev) if (err < 0) goto out_unlock; - if (__phy_is_started(phydev)) { + if (phy_is_started(phydev)) { if (phydev->autoneg == AUTONEG_ENABLE) { err = phy_check_link_status(phydev); } else { @@ -709,7 +709,7 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (__phy_is_started(phydev)) + if (phy_is_started(phydev)) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); } @@ -762,9 +762,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; - if (!phy_is_started(phydev)) - return IRQ_NONE; /* It can't be ours. */ - if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev)) return IRQ_NONE; @@ -842,15 +839,14 @@ EXPORT_SYMBOL(phy_stop_interrupts); */ void phy_stop(struct phy_device *phydev) { - mutex_lock(&phydev->lock); - - if (!__phy_is_started(phydev)) { + if (!phy_is_started(phydev)) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); - mutex_unlock(&phydev->lock); return; } + mutex_lock(&phydev->lock); + if (phy_interrupt_is_valid(phydev)) phy_disable_interrupts(phydev); @@ -989,8 +985,10 @@ void phy_state_machine(struct work_struct *work) * state machine would be pointless and possibly error prone when * called from phy_disconnect() synchronously. */ + mutex_lock(&phydev->lock); if (phy_polling_mode(phydev) && phy_is_started(phydev)) phy_queue_state_machine(phydev, PHY_STATE_TIME); + mutex_unlock(&phydev->lock); } /** diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index e7becc7379d7..938803237d7f 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -474,6 +474,17 @@ static void phylink_run_resolve(struct phylink *pl) queue_work(system_power_efficient_wq, &pl->resolve); } +static void phylink_run_resolve_and_disable(struct phylink *pl, int bit) +{ + unsigned long state = pl->phylink_disable_state; + + set_bit(bit, &pl->phylink_disable_state); + if (state == 0) { + queue_work(system_power_efficient_wq, &pl->resolve); + flush_work(&pl->resolve); + } +} + static void phylink_fixed_poll(struct timer_list *t) { struct phylink *pl = container_of(t, struct phylink, link_poll); @@ -924,9 +935,7 @@ void phylink_stop(struct phylink *pl) if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) del_timer_sync(&pl->link_poll); - set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED); } EXPORT_SYMBOL_GPL(phylink_stop); @@ -1632,9 +1641,7 @@ static void phylink_sfp_link_down(void *upstream) ASSERT_RTNL(); - set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_LINK); } static void phylink_sfp_link_up(void *upstream) diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index ad9db652874d..fef701bfad62 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus) return ret; } } + bus->socket_ops->attach(bus->sfp); if (bus->started) bus->socket_ops->start(bus->sfp); bus->netdev->sfp_bus = bus; @@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->registered) { if (bus->started) bus->socket_ops->stop(bus->sfp); + bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index fd8bb998ae52..68c8fbf099f8 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -184,6 +184,7 @@ struct sfp { struct gpio_desc *gpio[GPIO_MAX]; + bool attached; unsigned int state; struct delayed_work poll; struct delayed_work timeout; @@ -1475,7 +1476,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) */ switch (sfp->sm_mod_state) { default: - if (event == SFP_E_INSERT) { + if (event == SFP_E_INSERT && sfp->attached) { sfp_module_tx_disable(sfp); sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT); } @@ -1607,6 +1608,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) mutex_unlock(&sfp->sm_mutex); } +static void sfp_attach(struct sfp *sfp) +{ + sfp->attached = true; + if (sfp->state & SFP_F_PRESENT) + sfp_sm_event(sfp, SFP_E_INSERT); +} + +static void sfp_detach(struct sfp *sfp) +{ + sfp->attached = false; + sfp_sm_event(sfp, SFP_E_REMOVE); +} + static void sfp_start(struct sfp *sfp) { sfp_sm_event(sfp, SFP_E_DEV_UP); @@ -1667,6 +1681,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, } static const struct sfp_socket_ops sfp_module_ops = { + .attach = sfp_attach, + .detach = sfp_detach, .start = sfp_start, .stop = sfp_stop, .module_info = sfp_module_info, @@ -1834,10 +1850,6 @@ static int sfp_probe(struct platform_device *pdev) dev_info(sfp->dev, "Host maximum power %u.%uW\n", sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10); - sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); - if (!sfp->sfp_bus) - return -ENOMEM; - /* Get the initial state, and always signal TX disable, * since the network interface will not be up. */ @@ -1848,10 +1860,6 @@ static int sfp_probe(struct platform_device *pdev) sfp->state |= SFP_F_RATE_SELECT; sfp_set_state(sfp, sfp->state); sfp_module_tx_disable(sfp); - rtnl_lock(); - if (sfp->state & SFP_F_PRESENT) - sfp_sm_event(sfp, SFP_E_INSERT); - rtnl_unlock(); for (i = 0; i < GPIO_MAX; i++) { if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i]) @@ -1884,6 +1892,10 @@ static int sfp_probe(struct platform_device *pdev) dev_warn(sfp->dev, "No tx_disable pin: SFP modules will always be emitting.\n"); + sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); + if (!sfp->sfp_bus) + return -ENOMEM; + return 0; } diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h index 31b0acf337e2..64f54b0bbd8c 100644 --- a/drivers/net/phy/sfp.h +++ b/drivers/net/phy/sfp.h @@ -7,6 +7,8 @@ struct sfp; struct sfp_socket_ops { + void (*attach)(struct sfp *sfp); + void (*detach)(struct sfp *sfp); void (*start)(struct sfp *sfp); void (*stop)(struct sfp *sfp); int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo); diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 74a8782313cf..bd6084e315de 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -44,7 +44,10 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev) u16 val = 0; int err; - err = priv->phy_drv->read_status(phydev); + if (priv->phy_drv->read_status) + err = priv->phy_drv->read_status(phydev); + else + err = genphy_read_status(phydev); if (err < 0) return err; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index afd9d25d1992..958f1cf67282 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team, } } -static bool __team_option_inst_tmp_find(const struct list_head *opts, - const struct team_option_inst *needle) -{ - struct team_option_inst *opt_inst; - - list_for_each_entry(opt_inst, opts, tmp_list) - if (opt_inst == needle) - return true; - return false; -} - static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) @@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) int err = 0; int i; struct nlattr *nl_option; - LIST_HEAD(opt_inst_list); rtnl_lock(); @@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; + LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; @@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) if (err) goto team_put; opt_inst->changed = true; - - /* dumb/evil user-space can send us duplicate opt, - * keep only the last one - */ - if (__team_option_inst_tmp_find(&opt_inst_list, - opt_inst)) - continue; - list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } - } - err = team_nl_send_event_options_get(team, &opt_inst_list); + err = team_nl_send_event_options_get(team, &opt_inst_list); + if (err) + break; + } team_put: team_nl_team_put(team); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 735ad838e2ba..18af2f8eee96 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1201,8 +1201,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354 */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 10)}, /* Sierra Wireless MC7304/MC7354 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354, WP76xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 10)},/* Sierra Wireless MC7304/MC7354 */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ {QMI_FIXED_INTF(0x1199, 0x901f, 8)}, /* Sierra Wireless EM7355 */ {QMI_FIXED_INTF(0x1199, 0x9041, 8)}, /* Sierra Wireless MC7305/MC7355 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 60dd1ec1665f..ada6baf8847a 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)) { netif_dbg(tp, probe, tp->netdev, "Invalid variant for MAC pass through\n"); return -ENODEV; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 5209ee9aac47..2aae11feff0c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2219,7 +2219,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; - struct net_device *dev = skb->dev; + struct net_device *dev; int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); @@ -2239,9 +2239,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif } + rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0, - vni); + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -2254,8 +2260,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { +drop: dev->stats.rx_dropped++; } + rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, 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/nvme/host/pci.c b/drivers/nvme/host/pci.c index 022ea1ee63f8..7fee665ec45e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2560,15 +2560,15 @@ static void nvme_reset_work(struct work_struct *work) mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) - goto out; + goto out_unlock; result = nvme_pci_configure_admin_queue(dev); if (result) - goto out; + goto out_unlock; result = nvme_alloc_admin_tags(dev); if (result) - goto out; + goto out_unlock; /* * Limit the max command size to prevent iod->sg allocations going @@ -2651,6 +2651,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_ctrl(&dev->ctrl); return; + out_unlock: + mutex_unlock(&dev->shutdown_lock); out: nvme_remove_dead_ctrl(dev, result); } diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c index c69ca95b1ad5..0f140a802137 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8b.c +++ b/drivers/pinctrl/meson/pinctrl-meson8b.c @@ -693,7 +693,7 @@ static const char * const sd_a_groups[] = { static const char * const sdxc_a_groups[] = { "sdxc_d0_0_a", "sdxc_d13_0_a", "sdxc_d47_a", "sdxc_clk_a", - "sdxc_cmd_a", "sdxc_d0_1_a", "sdxc_d0_13_1_a" + "sdxc_cmd_a", "sdxc_d0_1_a", "sdxc_d13_1_a" }; static const char * const pcm_a_groups[] = { diff --git a/drivers/pinctrl/qcom/pinctrl-qcs404.c b/drivers/pinctrl/qcom/pinctrl-qcs404.c index 7aae52a09ff0..4ffd56ff809e 100644 --- a/drivers/pinctrl/qcom/pinctrl-qcs404.c +++ b/drivers/pinctrl/qcom/pinctrl-qcs404.c @@ -79,7 +79,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ - .tile = NORTH, \ + .tile = SOUTH, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 4e7b55a14b1a..6e294b4d3635 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4469,6 +4469,14 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) usrparm.psf_data &= 0x7fffffffULL; usrparm.rssd_result &= 0x7fffffffULL; } + /* at least 2 bytes are accessed and should be allocated */ + if (usrparm.psf_data_len < 2) { + DBF_DEV_EVENT(DBF_WARNING, device, + "Symmetrix ioctl invalid data length %d", + usrparm.psf_data_len); + rc = -EINVAL; + goto out; + } /* alloc I/O data area */ psf_data = kzalloc(usrparm.psf_data_len, GFP_KERNEL | GFP_DMA); rssd_result = kzalloc(usrparm.rssd_result_len, GFP_KERNEL | GFP_DMA); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 48ea0004a56d..5a699746c357 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -248,7 +248,8 @@ static inline int ap_test_config(unsigned int *field, unsigned int nr) static inline int ap_test_config_card_id(unsigned int id) { if (!ap_configuration) /* QCI not supported */ - return 1; + /* only ids 0...3F may be probed */ + return id < 0x40 ? 1 : 0; return ap_test_config(ap_configuration->apm, id); } 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/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index dfd23245f778..6fff16113628 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -774,7 +774,7 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) cdev = __cpufreq_cooling_register(np, policy, capacitance); if (IS_ERR(cdev)) { - pr_err("cpu_cooling: cpu%d is not running as cooling device: %ld\n", + pr_err("cpu_cooling: cpu%d failed to register as cooling device: %ld\n", policy->cpu, PTR_ERR(cdev)); cdev = NULL; } diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 4bfdb4a1e47d..2df059cc07e2 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -867,14 +867,14 @@ __init *thermal_of_build_thermal_zone(struct device_node *np) ret = of_property_read_u32(np, "polling-delay-passive", &prop); if (ret < 0) { - pr_err("missing polling-delay-passive property\n"); + pr_err("%pOFn: missing polling-delay-passive property\n", np); goto free_tz; } tz->passive_delay = prop; ret = of_property_read_u32(np, "polling-delay", &prop); if (ret < 0) { - pr_err("missing polling-delay property\n"); + pr_err("%pOFn: missing polling-delay property\n", np); goto free_tz; } tz->polling_delay = prop; 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 d0078cbb718b..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; @@ -33,23 +50,41 @@ 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; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) + /* + * 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; - if (!*cp || (*cp == '\n')) - break; + cp = buf_end; } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> -#include <linux/blkdev.h> -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + +/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) diff --git a/fs/inode.c b/fs/inode.c index 0cd47fe0dbe5..73432e64f874 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 885363ca8569..2f6b447cdd82 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -229,6 +229,8 @@ static struct inode *nfs_delegation_grab_inode(struct nfs_delegation *delegation spin_lock(&delegation->lock); if (delegation->inode != NULL) inode = igrab(delegation->inode); + if (!inode) + set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags); spin_unlock(&delegation->lock); return inode; } @@ -681,7 +683,7 @@ void nfs_expire_all_delegations(struct nfs_client *clp) /** * nfs_super_return_all_delegations - return delegations for one superblock - * @sb: sb to process + * @server: pointer to nfs_server to process * */ void nfs_server_return_all_delegations(struct nfs_server *server) @@ -944,10 +946,11 @@ restart: list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - if (test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags)) - continue; - if (test_bit(NFS_DELEGATION_NEED_RECLAIM, + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) continue; if (!nfs_sb_active(server->super)) @@ -1053,10 +1056,11 @@ restart: list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { list_for_each_entry_rcu(delegation, &server->delegations, super_list) { - if (test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags)) - continue; - if (test_bit(NFS_DELEGATION_TEST_EXPIRED, + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags) == 0) continue; if (!nfs_sb_active(server->super)) diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index dcbf3394ba0e..35b4b02c1ae0 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -34,6 +34,7 @@ enum { NFS_DELEGATION_RETURNING, NFS_DELEGATION_REVOKED, NFS_DELEGATION_TEST_EXPIRED, + NFS_DELEGATION_INODE_FREEING, }; int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 6bf4471850c8..a71d0b42d160 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -139,12 +139,19 @@ struct nfs_cache_array { struct nfs_cache_array_entry array[0]; }; +struct readdirvec { + unsigned long nr; + unsigned long index; + struct page *pages[NFS_MAX_READDIR_RAPAGES]; +}; + typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool); typedef struct { struct file *file; struct page *page; struct dir_context *ctx; unsigned long page_index; + struct readdirvec pvec; u64 *dir_cookie; u64 last_cookie; loff_t current_index; @@ -524,6 +531,10 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en struct nfs_cache_array *array; unsigned int count = 0; int status; + int max_rapages = NFS_MAX_READDIR_RAPAGES; + + desc->pvec.index = desc->page_index; + desc->pvec.nr = 0; scratch = alloc_page(GFP_KERNEL); if (scratch == NULL) @@ -548,20 +559,40 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en if (desc->plus) nfs_prime_dcache(file_dentry(desc->file), entry); - status = nfs_readdir_add_to_array(entry, page); + status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]); + if (status == -ENOSPC) { + desc->pvec.nr++; + if (desc->pvec.nr == max_rapages) + break; + status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]); + } if (status != 0) break; } while (!entry->eof); + /* + * page and desc->pvec.pages[0] are valid, don't need to check + * whether or not to be NULL. + */ + copy_highpage(page, desc->pvec.pages[0]); + out_nopages: if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) { - array = kmap(page); + array = kmap_atomic(desc->pvec.pages[desc->pvec.nr]); array->eof_index = array->size; status = 0; - kunmap(page); + kunmap_atomic(array); } put_page(scratch); + + /* + * desc->pvec.nr > 0 means at least one page was completely filled, + * we should return -ENOSPC. Otherwise function + * nfs_readdir_xdr_to_array will enter infinite loop. + */ + if (desc->pvec.nr > 0) + return -ENOSPC; return status; } @@ -574,8 +605,8 @@ void nfs_readdir_free_pages(struct page **pages, unsigned int npages) } /* - * nfs_readdir_large_page will allocate pages that must be freed with a call - * to nfs_readdir_free_pagearray + * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call + * to nfs_readdir_free_pages() */ static int nfs_readdir_alloc_pages(struct page **pages, unsigned int npages) @@ -595,6 +626,24 @@ out_freepages: return -ENOMEM; } +/* + * nfs_readdir_rapages_init initialize rapages by nfs_cache_array structure. + */ +static +void nfs_readdir_rapages_init(nfs_readdir_descriptor_t *desc) +{ + struct nfs_cache_array *array; + int max_rapages = NFS_MAX_READDIR_RAPAGES; + int index; + + for (index = 0; index < max_rapages; index++) { + array = kmap_atomic(desc->pvec.pages[index]); + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; + kunmap_atomic(array); + } +} + static int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode) { @@ -605,6 +654,12 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, int status = -ENOMEM; unsigned int array_size = ARRAY_SIZE(pages); + /* + * This means we hit readdir rdpages miss, the preallocated rdpages + * are useless, the preallocate rdpages should be reinitialized. + */ + nfs_readdir_rapages_init(desc); + entry.prev_cookie = 0; entry.cookie = desc->last_cookie; entry.eof = 0; @@ -664,9 +719,24 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) struct inode *inode = file_inode(desc->file); int ret; - ret = nfs_readdir_xdr_to_array(desc, page, inode); - if (ret < 0) - goto error; + /* + * If desc->page_index in range desc->pvec.index and + * desc->pvec.index + desc->pvec.nr, we get readdir cache hit. + */ + if (desc->page_index >= desc->pvec.index && + desc->page_index < (desc->pvec.index + desc->pvec.nr)) { + /* + * page and desc->pvec.pages[x] are valid, don't need to check + * whether or not to be NULL. + */ + copy_highpage(page, desc->pvec.pages[desc->page_index - desc->pvec.index]); + ret = 0; + } else { + ret = nfs_readdir_xdr_to_array(desc, page, inode); + if (ret < 0) + goto error; + } + SetPageUptodate(page); if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { @@ -831,6 +901,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) *desc = &my_desc; struct nfs_open_dir_context *dir_ctx = file->private_data; int res = 0; + int max_rapages = NFS_MAX_READDIR_RAPAGES; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", file, (long long)ctx->pos); @@ -850,6 +921,12 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->decode = NFS_PROTO(inode)->decode_dirent; desc->plus = nfs_use_readdirplus(inode, ctx); + res = nfs_readdir_alloc_pages(desc->pvec.pages, max_rapages); + if (res < 0) + return -ENOMEM; + + nfs_readdir_rapages_init(desc); + if (ctx->pos == 0 || nfs_attribute_cache_expired(inode)) res = nfs_revalidate_mapping(inode, file->f_mapping); if (res < 0) @@ -885,6 +962,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) break; } while (!desc->eof); out: + nfs_readdir_free_pages(desc->pvec.pages, max_rapages); if (res > 0) res = 0; dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res); @@ -945,7 +1023,7 @@ static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, /** * nfs_force_lookup_revalidate - Mark the directory as having changed - * @dir - pointer to directory inode + * @dir: pointer to directory inode * * This forces the revalidation code in nfs_lookup_revalidate() to do a * full lookup on all child dentries of 'dir' whenever a change occurs @@ -1649,7 +1727,7 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_dentry(dir, dentry, inode);; + return nfs_lookup_revalidate_dentry(dir, dentry, inode); full_reval: return nfs_do_lookup_revalidate(dir, dentry, flags); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 33824a0a57bf..0fd811ac08b5 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -428,7 +428,7 @@ out_put: hdr->release(hdr); } -static void nfs_read_sync_pgio_error(struct list_head *head) +static void nfs_read_sync_pgio_error(struct list_head *head, int error) { struct nfs_page *req; @@ -664,8 +664,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) list_for_each_entry_safe(req, tmp, &reqs, wb_list) { if (!nfs_pageio_add_request(&desc, req)) { - nfs_list_remove_request(req); - nfs_list_add_request(req, &failed); + nfs_list_move_request(req, &failed); spin_lock(&cinfo.inode->i_lock); dreq->flags = 0; if (desc.pg_error < 0) @@ -821,7 +820,7 @@ out_put: hdr->release(hdr); } -static void nfs_write_sync_pgio_error(struct list_head *head) +static void nfs_write_sync_pgio_error(struct list_head *head, int error) { struct nfs_page *req; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 29553fdba8af..4899b85f9b3c 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -89,8 +89,8 @@ EXPORT_SYMBOL_GPL(nfs_file_release); /** * nfs_revalidate_size - Revalidate the file size - * @inode - pointer to inode struct - * @file - pointer to struct file + * @inode: pointer to inode struct + * @filp: pointer to struct file * * Revalidates the file length. This is basically a wrapper around * nfs_revalidate_inode() that takes into account the fact that we may @@ -276,6 +276,12 @@ EXPORT_SYMBOL_GPL(nfs_file_fsync); * then a modify/write/read cycle when writing to a page in the * page cache. * + * Some pNFS layout drivers can only read/write at a certain block + * granularity like all block devices and therefore we must perform + * read/modify/write whenever a page hasn't read yet and the data + * to be written there is not aligned to a block boundary and/or + * smaller than the block size. + * * The modify/write/read cycle may occur if a page is read before * being completely filled by the writer. In this situation, the * page must be completely written to stable storage on the server @@ -291,26 +297,32 @@ EXPORT_SYMBOL_GPL(nfs_file_fsync); * and that the new data won't completely replace the old data in * that range of the file. */ -static int nfs_want_read_modify_write(struct file *file, struct page *page, - loff_t pos, unsigned len) +static bool nfs_full_page_write(struct page *page, loff_t pos, unsigned int len) { unsigned int pglen = nfs_page_length(page); unsigned int offset = pos & (PAGE_SIZE - 1); unsigned int end = offset + len; - if (pnfs_ld_read_whole_page(file->f_mapping->host)) { - if (!PageUptodate(page)) - return 1; - return 0; - } + return !pglen || (end >= pglen && !offset); +} - if ((file->f_mode & FMODE_READ) && /* open for read? */ - !PageUptodate(page) && /* Uptodate? */ - !PagePrivate(page) && /* i/o request already? */ - pglen && /* valid bytes of file? */ - (end < pglen || offset)) /* replace all valid bytes? */ - return 1; - return 0; +static bool nfs_want_read_modify_write(struct file *file, struct page *page, + loff_t pos, unsigned int len) +{ + /* + * Up-to-date pages, those with ongoing or full-page write + * don't need read/modify/write + */ + if (PageUptodate(page) || PagePrivate(page) || + nfs_full_page_write(page, pos, len)) + return false; + + if (pnfs_ld_read_whole_page(file->f_mapping->host)) + return true; + /* Open for reading too? */ + if (file->f_mode & FMODE_READ) + return true; + return false; } /* diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index 11766a74216d..ca7a6203b3cb 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -483,9 +483,15 @@ ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx, } /** -* Find or create a DS rpc client with th MDS server rpc client auth flavor -* in the nfs_client cl_ds_clients list. -*/ + * nfs4_ff_find_or_create_ds_client - Find or create a DS rpc client + * @lseg: pointer to layout segment + * @ds_idx: mirror index + * @ds_clp: nfs_client for the DS + * @inode: pointer to inode + * + * Find or create a DS rpc client with th MDS server rpc client auth flavor + * in the nfs_client cl_ds_clients list. + */ struct rpc_clnt * nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg, u32 ds_idx, struct nfs_client *ds_clp, struct inode *inode) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 094775ea0781..414a90d48493 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -143,6 +143,7 @@ EXPORT_SYMBOL_GPL(nfs_sync_inode); /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk + * @mapping: pointer to struct address_space */ int nfs_sync_mapping(struct address_space *mapping) { @@ -1184,8 +1185,8 @@ int nfs_attribute_cache_expired(struct inode *inode) /** * nfs_revalidate_inode - Revalidate the inode attributes - * @server - pointer to nfs_server struct - * @inode - pointer to inode struct + * @server: pointer to nfs_server struct + * @inode: pointer to inode struct * * Updates inode attribute information by retrieving the data from the server. */ @@ -1255,8 +1256,8 @@ out: /** * nfs_revalidate_mapping - Revalidate the pagecache - * @inode - pointer to host inode - * @mapping - pointer to mapping + * @inode: pointer to host inode + * @mapping: pointer to mapping */ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) @@ -1371,8 +1372,8 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) /** * nfs_check_inode_attributes - verify consistency of the inode attribute cache - * @inode - pointer to inode - * @fattr - updated attributes + * @inode: pointer to inode + * @fattr: updated attributes * * Verifies the attribute cache. If we have just changed the attributes, * so that fattr carries weak cache consistency data, then it may @@ -1572,8 +1573,8 @@ EXPORT_SYMBOL_GPL(_nfs_display_fhandle); /** * nfs_inode_attrs_need_update - check if the inode attributes need updating - * @inode - pointer to inode - * @fattr - attributes + * @inode: pointer to inode + * @fattr: attributes * * Attempt to divine whether or not an RPC call reply carrying stale * attributes got scheduled after another call carrying updated ones. @@ -1614,8 +1615,8 @@ static int nfs_refresh_inode_locked(struct inode *inode, struct nfs_fattr *fattr /** * nfs_refresh_inode - try to update the inode attribute cache - * @inode - pointer to inode - * @fattr - updated attributes + * @inode: pointer to inode + * @fattr: updated attributes * * Check that an RPC call that returned attributes has not overlapped with * other recent updates of the inode metadata, then decide whether it is @@ -1649,8 +1650,8 @@ static int nfs_post_op_update_inode_locked(struct inode *inode, /** * nfs_post_op_update_inode - try to update the inode attribute cache - * @inode - pointer to inode - * @fattr - updated attributes + * @inode: pointer to inode + * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. @@ -1679,8 +1680,8 @@ EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc_locked - update the inode attribute cache - * @inode - pointer to inode - * @fattr - updated attributes + * @inode: pointer to inode + * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up @@ -1731,8 +1732,8 @@ out_noforce: /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache - * @inode - pointer to inode - * @fattr - updated attributes + * @inode: pointer to inode + * @fattr: updated attributes * * After an operation that has changed the inode metadata, mark the * attribute cache as being invalid, then try to update it. Fake up diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index b1e577302518..c7cf23ae6597 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -69,7 +69,8 @@ struct nfs_clone_mount { * Maximum number of pages that readdir can use for creating * a vmapped array of pages. */ -#define NFS_MAX_READDIR_PAGES 8 +#define NFS_MAX_READDIR_PAGES 64 +#define NFS_MAX_READDIR_RAPAGES 8 struct nfs_client_initdata { unsigned long init_flags; @@ -755,6 +756,7 @@ static inline bool nfs_error_is_fatal(int err) { switch (err) { case -ERESTARTSYS: + case -EINTR: case -EACCES: case -EDQUOT: case -EFBIG: @@ -763,6 +765,7 @@ static inline bool nfs_error_is_fatal(int err) case -EROFS: case -ESTALE: case -E2BIG: + case -ENOMEM: return true; default: return false; diff --git a/fs/nfs/io.c b/fs/nfs/io.c index 9034b4926909..5088fda9b453 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -25,7 +25,7 @@ static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) /** * nfs_start_io_read - declare the file is being used for buffered reads - * @inode - file inode + * @inode: file inode * * Declare that a buffered read operation is about to start, and ensure * that we block all direct I/O. @@ -56,7 +56,7 @@ nfs_start_io_read(struct inode *inode) /** * nfs_end_io_read - declare that the buffered read operation is done - * @inode - file inode + * @inode: file inode * * Declare that a buffered read operation is done, and release the shared * lock on inode->i_rwsem. @@ -69,7 +69,7 @@ nfs_end_io_read(struct inode *inode) /** * nfs_start_io_write - declare the file is being used for buffered writes - * @inode - file inode + * @inode: file inode * * Declare that a buffered read operation is about to start, and ensure * that we block all direct I/O. @@ -83,7 +83,7 @@ nfs_start_io_write(struct inode *inode) /** * nfs_end_io_write - declare that the buffered write operation is done - * @inode - file inode + * @inode: file inode * * Declare that a buffered write operation is done, and release the * lock on inode->i_rwsem. @@ -105,7 +105,7 @@ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) /** * nfs_end_io_direct - declare the file is being used for direct i/o - * @inode - file inode + * @inode: file inode * * Declare that a direct I/O operation is about to start, and ensure * that we block all buffered I/O. @@ -136,7 +136,7 @@ nfs_start_io_direct(struct inode *inode) /** * nfs_end_io_direct - declare that the direct i/o operation is done - * @inode - file inode + * @inode: file inode * * Declare that a direct I/O operation is done, and release the shared * lock on inode->i_rwsem. diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index e5686be67be8..15f099a24c29 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -221,10 +221,10 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, /** * nfs_do_submount - set up mountpoint when crossing a filesystem boundary - * @dentry - parent directory - * @fh - filehandle for new root dentry - * @fattr - attributes for new root inode - * @authflavor - security flavor to use when performing the mount + * @dentry: parent directory + * @fh: filehandle for new root dentry + * @fattr: attributes for new root inode + * @authflavor: security flavor to use when performing the mount * */ struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh, diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 9fce18548f7e..c5c3fc6e6c60 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -222,8 +222,6 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, switch (status) { case 0: status = nfs_refresh_inode(inode, fattr); - set_cached_acl(inode, ACL_TYPE_ACCESS, acl); - set_cached_acl(inode, ACL_TYPE_DEFAULT, dfacl); break; case -EPFNOSUPPORT: case -EPROTONOSUPPORT: diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 2548405da1f7..1339ede979af 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -42,7 +42,7 @@ static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) } #ifdef CONFIG_NFS_V4_1 -/** +/* * Per auth flavor data server rpc clients */ struct nfs4_ds_server { @@ -51,7 +51,9 @@ struct nfs4_ds_server { }; /** - * Common lookup case for DS I/O + * nfs4_find_ds_client - Common lookup case for DS I/O + * @ds_clp: pointer to the DS's nfs_client + * @flavor: rpc auth flavour to match */ static struct nfs4_ds_server * nfs4_find_ds_client(struct nfs_client *ds_clp, rpc_authflavor_t flavor) @@ -118,9 +120,13 @@ nfs4_free_ds_server(struct nfs4_ds_server *dss) } /** -* Find or create a DS rpc client with th MDS server rpc client auth flavor -* in the nfs_client cl_ds_clients list. -*/ + * nfs4_find_or_create_ds_client - Find or create a DS rpc client + * @ds_clp: pointer to the DS's nfs_client + * @inode: pointer to the inode + * + * Find or create a DS rpc client with th MDS server rpc client auth flavor + * in the nfs_client cl_ds_clients list. + */ struct rpc_clnt * nfs4_find_or_create_ds_client(struct nfs_client *ds_clp, struct inode *inode) { @@ -145,7 +151,6 @@ static void nfs4_shutdown_ds_clients(struct nfs_client *clp) { struct nfs4_ds_server *dss; - LIST_HEAD(shutdown_list); while (!list_empty(&clp->cl_ds_clients)) { dss = list_entry(clp->cl_ds_clients.next, @@ -284,7 +289,7 @@ static int nfs4_init_callback(struct nfs_client *clp) /** * nfs40_init_client - nfs_client initialization tasks for NFSv4.0 - * @clp - nfs_client to initialize + * @clp: nfs_client to initialize * * Returns zero on success, or a negative errno if some error occurred. */ @@ -312,7 +317,7 @@ int nfs40_init_client(struct nfs_client *clp) /** * nfs41_init_client - nfs_client initialization tasks for NFSv4.1+ - * @clp - nfs_client to initialize + * @clp: nfs_client to initialize * * Returns zero on success, or a negative errno if some error occurred. */ @@ -360,9 +365,7 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp) * nfs4_init_client - Initialise an NFS4 client record * * @clp: nfs_client to initialise - * @timeparms: timeout parameters for underlying RPC transport - * @ip_addr: callback IP address in presentation format - * @authflavor: authentication flavor for underlying RPC transport + * @cl_init: pointer to nfs_client_initdata * * Returns pointer to an NFS client, or an ERR_PTR value. */ @@ -649,13 +652,13 @@ nfs4_check_server_scope(struct nfs41_server_scope *s1, /** * nfs4_detect_session_trunking - Checks for session trunking. - * - * Called after a successful EXCHANGE_ID on a multi-addr connection. - * Upon success, add the transport. - * * @clp: original mount nfs_client * @res: result structure from an exchange_id using the original mount * nfs_client with a new multi_addr transport + * @xprt: pointer to the transport to add. + * + * Called after a successful EXCHANGE_ID on a multi-addr connection. + * Upon success, add the transport. * * Returns zero on success, otherwise -EINVAL * diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 3f23b6840547..bf34ddaa2ad7 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -44,6 +44,7 @@ #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> +#include <keys/request_key_auth-type.h> #include <linux/module.h> #include "internal.h" @@ -59,7 +60,7 @@ static struct key_type key_type_id_resolver_legacy; struct idmap_legacy_upcalldata { struct rpc_pipe_msg pipe_msg; struct idmap_msg idmap_msg; - struct key_construction *key_cons; + struct key *authkey; struct idmap *idmap; }; @@ -384,7 +385,7 @@ static const match_table_t nfs_idmap_tokens = { { Opt_find_err, NULL } }; -static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); +static int nfs_idmap_legacy_upcall(struct key *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_release_pipe(struct inode *); @@ -549,11 +550,12 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, static void nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) { - struct key_construction *cons = idmap->idmap_upcall_data->key_cons; + struct key *authkey = idmap->idmap_upcall_data->authkey; kfree(idmap->idmap_upcall_data); idmap->idmap_upcall_data = NULL; - complete_request_key(cons, ret); + complete_request_key(authkey, ret); + key_put(authkey); } static void @@ -563,15 +565,14 @@ nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) nfs_idmap_complete_pipe_upcall_locked(idmap, ret); } -static int nfs_idmap_legacy_upcall(struct key_construction *cons, - const char *op, - void *aux) +static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) { struct idmap_legacy_upcalldata *data; + struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; - struct key *key = cons->key; + struct key *key = rka->target_key; int ret = -ENOKEY; if (!aux) @@ -586,7 +587,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, msg = &data->pipe_msg; im = &data->idmap_msg; data->idmap = idmap; - data->key_cons = cons; + data->authkey = key_get(authkey); ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) @@ -604,7 +605,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, out2: kfree(data); out1: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); return ret; } @@ -651,9 +652,10 @@ out: static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { + struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; - struct key_construction *cons; + struct key *authkey; struct idmap_msg im; size_t namelen_in; int ret = -ENOKEY; @@ -665,7 +667,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (idmap->idmap_upcall_data == NULL) goto out_noupcall; - cons = idmap->idmap_upcall_data->key_cons; + authkey = idmap->idmap_upcall_data->authkey; + rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { ret = -ENOSPC; @@ -690,9 +693,9 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) ret = nfs_idmap_read_and_verify_message(&im, &idmap->idmap_upcall_data->idmap_msg, - cons->key, cons->authkey); + rka->target_key, authkey); if (ret >= 0) { - key_set_timeout(cons->key, nfs_idmap_cache_timeout); + key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index 24f06dcc2b08..2e460c33ae48 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -137,6 +137,7 @@ static size_t nfs_parse_server_name(char *string, size_t len, /** * nfs_find_best_sec - Find a security mechanism supported locally + * @clnt: pointer to rpc_clnt * @server: NFS server struct * @flavors: List of security tuples returned by SECINFO procedure * @@ -288,8 +289,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata, /** * nfs_follow_referral - set up mountpoint when hitting a referral on moved error - * @dentry - parent directory - * @locations - array of NFSv4 server location information + * @dentry: parent directory + * @locations: array of NFSv4 server location information * */ static struct vfsmount *nfs_follow_referral(struct dentry *dentry, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 557a5d636183..77c6e2d3f3fc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -730,13 +730,25 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) res->sr_slot = NULL; } +static void nfs4_slot_sequence_record_sent(struct nfs4_slot *slot, + u32 seqnr) +{ + if ((s32)(seqnr - slot->seq_nr_highest_sent) > 0) + slot->seq_nr_highest_sent = seqnr; +} +static void nfs4_slot_sequence_acked(struct nfs4_slot *slot, + u32 seqnr) +{ + slot->seq_nr_highest_sent = seqnr; + slot->seq_nr_last_acked = seqnr; +} + static int nfs41_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) { struct nfs4_session *session; struct nfs4_slot *slot = res->sr_slot; struct nfs_client *clp; - bool interrupted = false; int ret = 1; if (slot == NULL) @@ -747,16 +759,12 @@ static int nfs41_sequence_process(struct rpc_task *task, session = slot->table->session; - if (slot->interrupted) { - if (res->sr_status != -NFS4ERR_DELAY) - slot->interrupted = 0; - interrupted = true; - } - trace_nfs4_sequence_done(session, res); /* Check the SEQUENCE operation status */ switch (res->sr_status) { case 0: + /* Mark this sequence number as having been acked */ + nfs4_slot_sequence_acked(slot, slot->seq_nr); /* Update the slot's sequence and clientid lease timer */ slot->seq_done = 1; clp = session->clp; @@ -771,9 +779,9 @@ static int nfs41_sequence_process(struct rpc_task *task, * sr_status remains 1 if an RPC level error occurred. * The server may or may not have processed the sequence * operation.. - * Mark the slot as having hosted an interrupted RPC call. */ - slot->interrupted = 1; + nfs4_slot_sequence_record_sent(slot, slot->seq_nr); + slot->seq_done = 1; goto out; case -NFS4ERR_DELAY: /* The server detected a resend of the RPC call and @@ -784,6 +792,7 @@ static int nfs41_sequence_process(struct rpc_task *task, __func__, slot->slot_nr, slot->seq_nr); + nfs4_slot_sequence_acked(slot, slot->seq_nr); goto out_retry; case -NFS4ERR_RETRY_UNCACHED_REP: case -NFS4ERR_SEQ_FALSE_RETRY: @@ -791,6 +800,7 @@ static int nfs41_sequence_process(struct rpc_task *task, * The server thinks we tried to replay a request. * Retry the call after bumping the sequence ID. */ + nfs4_slot_sequence_acked(slot, slot->seq_nr); goto retry_new_seq; case -NFS4ERR_BADSLOT: /* @@ -801,21 +811,28 @@ static int nfs41_sequence_process(struct rpc_task *task, goto session_recover; goto retry_nowait; case -NFS4ERR_SEQ_MISORDERED: + nfs4_slot_sequence_record_sent(slot, slot->seq_nr); /* - * Was the last operation on this sequence interrupted? - * If so, retry after bumping the sequence number. - */ - if (interrupted) - goto retry_new_seq; - /* - * Could this slot have been previously retired? - * If so, then the server may be expecting seq_nr = 1! + * Were one or more calls using this slot interrupted? + * If the server never received the request, then our + * transmitted slot sequence number may be too high. */ - if (slot->seq_nr != 1) { - slot->seq_nr = 1; + if ((s32)(slot->seq_nr - slot->seq_nr_last_acked) > 1) { + slot->seq_nr--; goto retry_nowait; } - goto session_recover; + /* + * RFC5661: + * A retry might be sent while the original request is + * still in progress on the replier. The replier SHOULD + * deal with the issue by returning NFS4ERR_DELAY as the + * reply to SEQUENCE or CB_SEQUENCE operation, but + * implementations MAY return NFS4ERR_SEQ_MISORDERED. + * + * Restart the search after a delay. + */ + slot->seq_nr = slot->seq_nr_highest_sent; + goto out_retry; default: /* Just update the slot sequence no. */ slot->seq_done = 1; @@ -906,17 +923,6 @@ static const struct rpc_call_ops nfs41_call_sync_ops = { .rpc_call_done = nfs41_call_sync_done, }; -static void -nfs4_sequence_process_interrupted(struct nfs_client *client, - struct nfs4_slot *slot, const struct cred *cred) -{ - struct rpc_task *task; - - task = _nfs41_proc_sequence(client, cred, slot, true); - if (!IS_ERR(task)) - rpc_put_task_async(task); -} - #else /* !CONFIG_NFS_V4_1 */ static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res) @@ -937,14 +943,6 @@ int nfs4_sequence_done(struct rpc_task *task, } EXPORT_SYMBOL_GPL(nfs4_sequence_done); -static void -nfs4_sequence_process_interrupted(struct nfs_client *client, - struct nfs4_slot *slot, const struct cred *cred) -{ - WARN_ON_ONCE(1); - slot->interrupted = 0; -} - #endif /* !CONFIG_NFS_V4_1 */ static @@ -982,26 +980,19 @@ int nfs4_setup_sequence(struct nfs_client *client, task->tk_timeout = 0; } - for (;;) { - spin_lock(&tbl->slot_tbl_lock); - /* The state manager will wait until the slot table is empty */ - if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) - goto out_sleep; - - slot = nfs4_alloc_slot(tbl); - if (IS_ERR(slot)) { - /* Try again in 1/4 second */ - if (slot == ERR_PTR(-ENOMEM)) - task->tk_timeout = HZ >> 2; - goto out_sleep; - } - spin_unlock(&tbl->slot_tbl_lock); + spin_lock(&tbl->slot_tbl_lock); + /* The state manager will wait until the slot table is empty */ + if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged) + goto out_sleep; - if (likely(!slot->interrupted)) - break; - nfs4_sequence_process_interrupted(client, - slot, task->tk_msg.rpc_cred); + slot = nfs4_alloc_slot(tbl); + if (IS_ERR(slot)) { + /* Try again in 1/4 second */ + if (slot == ERR_PTR(-ENOMEM)) + task->tk_timeout = HZ >> 2; + goto out_sleep; } + spin_unlock(&tbl->slot_tbl_lock); nfs4_sequence_attach_slot(args, res, slot); @@ -1555,6 +1546,10 @@ static void nfs_clear_open_stateid(struct nfs4_state *state, static void nfs_set_open_stateid_locked(struct nfs4_state *state, const nfs4_stateid *stateid, nfs4_stateid *freeme) + __must_hold(&state->owner->so_lock) + __must_hold(&state->seqlock) + __must_hold(RCU) + { DEFINE_WAIT(wait); int status = 0; @@ -5963,7 +5958,7 @@ out: /** * nfs4_proc_setclientid_confirm - Confirm client ID * @clp: state data structure - * @res: result of a previous SETCLIENTID + * @arg: result of a previous SETCLIENTID * @cred: credential to use for this call * * Returns zero, a negative errno, or a negative NFS4ERR status code. @@ -7527,7 +7522,7 @@ int nfs4_proc_fsid_present(struct inode *inode, const struct cred *cred) return status; } -/** +/* * If 'use_integrity' is true and the state managment nfs_client * cl_rpcclient is using krb5i/p, use the integrity protected cl_rpcclient * and the machine credential as per RFC3530bis and RFC5661 Security @@ -9219,7 +9214,7 @@ nfs4_proc_layoutcommit(struct nfs4_layoutcommit_data *data, bool sync) return status; } -/** +/* * Use the state managment nfs_client cl_rpcclient, which uses krb5i (if * possible) as per RFC3530bis and RFC5661 Security Considerations sections */ @@ -9484,7 +9479,7 @@ static const struct rpc_call_ops nfs41_free_stateid_ops = { * @server: server / transport on which to perform the operation * @stateid: state ID to release * @cred: credential - * @is_recovery: set to true if this call needs to be privileged + * @privileged: set to true if this call needs to be privileged * * Note: this function is always asynchronous. */ diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c index a5489d70a724..bcb532def9e2 100644 --- a/fs/nfs/nfs4session.c +++ b/fs/nfs/nfs4session.c @@ -55,7 +55,7 @@ static void nfs4_shrink_slot_table(struct nfs4_slot_table *tbl, u32 newsize) /** * nfs4_slot_tbl_drain_complete - wake waiters when drain is complete - * @tbl - controlling slot table + * @tbl: controlling slot table * */ void nfs4_slot_tbl_drain_complete(struct nfs4_slot_table *tbl) @@ -110,6 +110,8 @@ static struct nfs4_slot *nfs4_new_slot(struct nfs4_slot_table *tbl, slot->table = tbl; slot->slot_nr = slotid; slot->seq_nr = seq_init; + slot->seq_nr_highest_sent = seq_init; + slot->seq_nr_last_acked = seq_init - 1; } return slot; } @@ -276,7 +278,8 @@ static void nfs4_reset_slot_table(struct nfs4_slot_table *tbl, p = &tbl->slots; while (*p) { (*p)->seq_nr = ivalue; - (*p)->interrupted = 0; + (*p)->seq_nr_highest_sent = ivalue; + (*p)->seq_nr_last_acked = ivalue - 1; p = &(*p)->next; } tbl->highest_used_slotid = NFS4_NO_SLOT; diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h index 3c550f297561..230509b77121 100644 --- a/fs/nfs/nfs4session.h +++ b/fs/nfs/nfs4session.h @@ -23,8 +23,9 @@ struct nfs4_slot { unsigned long generation; u32 slot_nr; u32 seq_nr; - unsigned int interrupted : 1, - privileged : 1, + u32 seq_nr_last_acked; + u32 seq_nr_highest_sent; + unsigned int privileged : 1, seq_done : 1; }; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 02488b50534a..3de36479ed7a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -563,6 +563,7 @@ static void nfs4_gc_state_owners(struct nfs_server *server) * nfs4_get_state_owner - Look up a state owner given a credential * @server: nfs_server to search * @cred: RPC credential to match + * @gfp_flags: allocation mode * * Returns a pointer to an instantiated nfs4_state_owner struct, or NULL. */ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index e54d899c1848..e9f39fa5964b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -350,7 +350,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page, /** * nfs_unlock_request - Unlock request and wake up sleepers. - * @req: + * @req: pointer to request */ void nfs_unlock_request(struct nfs_page *req) { @@ -368,7 +368,7 @@ void nfs_unlock_request(struct nfs_page *req) /** * nfs_unlock_and_release_request - Unlock request and release the nfs_page - * @req: + * @req: pointer to request */ void nfs_unlock_and_release_request(struct nfs_page *req) { @@ -531,7 +531,6 @@ EXPORT_SYMBOL_GPL(nfs_pgio_header_free); * nfs_pgio_rpcsetup - Set up arguments for a pageio call * @hdr: The pageio hdr * @count: Number of bytes to read - * @offset: Initial offset * @how: How to commit data (writes only) * @cinfo: Commit information for the call (writes only) */ @@ -634,7 +633,6 @@ EXPORT_SYMBOL_GPL(nfs_initiate_pgio); /** * nfs_pgio_error - Clean up from a pageio error - * @desc: IO descriptor * @hdr: pageio header */ static void nfs_pgio_error(struct nfs_pgio_header *hdr) @@ -768,8 +766,7 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc, pageused = 0; while (!list_empty(head)) { req = nfs_list_entry(head->next); - nfs_list_remove_request(req); - nfs_list_add_request(req, &hdr->pages); + nfs_list_move_request(req, &hdr->pages); if (!last_page || last_page != req->wb_page) { pageused++; @@ -893,6 +890,7 @@ static bool nfs_match_lock_context(const struct nfs_lock_context *l1, * nfs_can_coalesce_requests - test two requests for compatibility * @prev: pointer to nfs_page * @req: pointer to nfs_page + * @pgio: pointer to nfs_pagio_descriptor * * The nfs_page structures 'prev' and 'req' are compared to ensure that the * page data area they describe is contiguous, and that their RPC @@ -961,8 +959,7 @@ static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc, } if (!nfs_can_coalesce_requests(prev, req, desc)) return 0; - nfs_list_remove_request(req); - nfs_list_add_request(req, &mirror->pg_list); + nfs_list_move_request(req, &mirror->pg_list); mirror->pg_count += req->wb_bytes; return 1; } @@ -988,6 +985,16 @@ static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc) } } +static void +nfs_pageio_cleanup_request(struct nfs_pageio_descriptor *desc, + struct nfs_page *req) +{ + LIST_HEAD(head); + + nfs_list_move_request(req, &head); + desc->pg_completion_ops->error_cleanup(&head, desc->pg_error); +} + /** * nfs_pageio_add_request - Attempt to coalesce a request into a page list. * @desc: destination io descriptor @@ -1025,10 +1032,8 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, nfs_page_group_unlock(req); desc->pg_moreio = 1; nfs_pageio_doio(desc); - if (desc->pg_error < 0) - return 0; - if (mirror->pg_recoalesce) - return 0; + if (desc->pg_error < 0 || mirror->pg_recoalesce) + goto out_cleanup_subreq; /* retry add_request for this subreq */ nfs_page_group_lock(req); continue; @@ -1061,6 +1066,10 @@ err_ptr: desc->pg_error = PTR_ERR(subreq); nfs_page_group_unlock(req); return 0; +out_cleanup_subreq: + if (req != subreq) + nfs_pageio_cleanup_request(desc, subreq); + return 0; } static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) @@ -1079,7 +1088,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc) struct nfs_page *req; req = list_first_entry(&head, struct nfs_page, wb_list); - nfs_list_remove_request(req); if (__nfs_pageio_add_request(desc, req)) continue; if (desc->pg_error < 0) { @@ -1120,7 +1128,8 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc) for (midx = 0; midx < desc->pg_mirror_count; midx++) { mirror = &desc->pg_mirrors[midx]; - desc->pg_completion_ops->error_cleanup(&mirror->pg_list); + desc->pg_completion_ops->error_cleanup(&mirror->pg_list, + desc->pg_error); } } @@ -1168,11 +1177,14 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, if (nfs_pgio_has_mirroring(desc)) desc->pg_mirror_idx = midx; if (!nfs_pageio_add_request_mirror(desc, dupreq)) - goto out_failed; + goto out_cleanup_subreq; } return 1; +out_cleanup_subreq: + if (req != dupreq) + nfs_pageio_cleanup_request(desc, dupreq); out_failed: nfs_pageio_error_cleanup(desc); return 0; @@ -1194,7 +1206,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc, desc->pg_mirror_idx = mirror_idx; for (;;) { nfs_pageio_doio(desc); - if (!mirror->pg_recoalesce) + if (desc->pg_error < 0 || !mirror->pg_recoalesce) break; if (!nfs_do_recoalesce(desc)) break; @@ -1222,9 +1234,8 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc, while (!list_empty(&hdr->pages)) { struct nfs_page *req = nfs_list_entry(hdr->pages.next); - nfs_list_remove_request(req); if (!nfs_pageio_add_request(desc, req)) - nfs_list_add_request(req, &failed); + nfs_list_move_request(req, &failed); } nfs_pageio_complete(desc); if (!list_empty(&failed)) { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 53726da5c010..8247bd1634cb 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -758,22 +758,35 @@ static int pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp, struct nfs_server *server, struct list_head *layout_list) + __must_hold(&clp->cl_lock) + __must_hold(RCU) { struct pnfs_layout_hdr *lo, *next; struct inode *inode; list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) { - if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) + if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) || + test_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags) || + !list_empty(&lo->plh_bulk_destroy)) continue; + /* If the sb is being destroyed, just bail */ + if (!nfs_sb_active(server->super)) + break; inode = igrab(lo->plh_inode); - if (inode == NULL) - continue; - list_del_init(&lo->plh_layouts); - if (pnfs_layout_add_bulk_destroy_list(inode, layout_list)) - continue; - rcu_read_unlock(); - spin_unlock(&clp->cl_lock); - iput(inode); + if (inode != NULL) { + list_del_init(&lo->plh_layouts); + if (pnfs_layout_add_bulk_destroy_list(inode, + layout_list)) + continue; + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + iput(inode); + } else { + rcu_read_unlock(); + spin_unlock(&clp->cl_lock); + set_bit(NFS_LAYOUT_INODE_FREEING, &lo->plh_flags); + } + nfs_sb_deactive(server->super); spin_lock(&clp->cl_lock); rcu_read_lock(); return -EAGAIN; @@ -811,7 +824,7 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, /* Free all lsegs that are attached to commit buckets */ nfs_commit_inode(inode, 0); pnfs_put_layout_hdr(lo); - iput(inode); + nfs_iput_and_deactive(inode); } return ret; } diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 5e80a07b7bea..56659ccce1d8 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -104,6 +104,7 @@ enum { NFS_LAYOUT_RETURN_REQUESTED, /* Return this layout ASAP */ NFS_LAYOUT_INVALID_STID, /* layout stateid id is invalid */ NFS_LAYOUT_FIRST_LAYOUTGET, /* Serialize first layoutget */ + NFS_LAYOUT_INODE_FREEING, /* The inode is being freed */ }; enum layoutdriver_policy_flags { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index f9f19784db82..1d95a60b2586 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -205,7 +205,7 @@ static void nfs_initiate_read(struct nfs_pgio_header *hdr, } static void -nfs_async_read_error(struct list_head *head) +nfs_async_read_error(struct list_head *head, int error) { struct nfs_page *req; diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 0570391eaa16..23790c7b2289 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1919,7 +1919,7 @@ static int nfs_parse_devname(const char *dev_name, /* kill possible hostname list: not supported */ comma = strchr(dev_name, ','); if (comma != NULL && comma < end) - *comma = 0; + len = comma - dev_name; } if (len > maxnamlen) diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 79b97b3c4427..52d533967485 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -39,6 +39,7 @@ nfs_free_unlinkdata(struct nfs_unlinkdata *data) /** * nfs_async_unlink_done - Sillydelete post-processing * @task: rpc_task of the sillydelete + * @calldata: pointer to nfs_unlinkdata * * Do the directory attribute update. */ @@ -54,7 +55,7 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata) /** * nfs_async_unlink_release - Release the sillydelete data. - * @task: rpc_task of the sillydelete + * @calldata: struct nfs_unlinkdata to release * * We need to call nfs_put_unlinkdata as a 'tk_release' task since the * rpc_task would be freed too. @@ -159,8 +160,8 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf /** * nfs_async_unlink - asynchronous unlinking of a file - * @dir: parent directory of dentry - * @dentry: dentry to unlink + * @dentry: parent directory of dentry + * @name: name of dentry to unlink */ static int nfs_async_unlink(struct dentry *dentry, const struct qstr *name) @@ -324,6 +325,7 @@ static const struct rpc_call_ops nfs_rename_ops = { * @new_dir: target directory for the rename * @old_dentry: original dentry to be renamed * @new_dentry: dentry to which the old_dentry should be renamed + * @complete: Function to run on successful completion * * It's expected that valid references to the dentries and inodes are held */ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index f12cb31a41e5..f3ebabaa291d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -26,6 +26,7 @@ #include <linux/iversion.h> #include <linux/uaccess.h> +#include <linux/sched/mm.h> #include "delegation.h" #include "internal.h" @@ -238,9 +239,9 @@ 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); } /* @@ -712,11 +713,13 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; struct nfs_pageio_descriptor pgio; - struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS); + struct nfs_io_completion *ioc; + unsigned int pflags = memalloc_nofs_save(); int err; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); + ioc = nfs_io_completion_alloc(GFP_NOFS); if (ioc) nfs_io_completion_init(ioc, nfs_io_completion_commit, inode); @@ -727,6 +730,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_pageio_complete(&pgio); nfs_io_completion_put(ioc); + memalloc_nofs_restore(pflags); + if (err < 0) goto out_err; err = pgio.pg_error; @@ -865,7 +870,6 @@ EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked); /** * nfs_request_add_commit_list - add request to a commit list * @req: pointer to a struct nfs_page - * @dst: commit list head * @cinfo: holds list lock and accounting info * * This sets the PG_CLEAN bit, updates the cinfo count of @@ -994,7 +998,7 @@ 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 +1352,8 @@ 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 +1371,7 @@ 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: @@ -1411,20 +1416,27 @@ static void nfs_redirty_request(struct nfs_page *req) nfs_release_request(req); } -static void nfs_async_write_error(struct list_head *head) +static void nfs_async_write_error(struct list_head *head, int error) { struct nfs_page *req; while (!list_empty(head)) { req = nfs_list_entry(head->next); nfs_list_remove_request(req); + if (nfs_error_is_fatal(error)) { + nfs_context_set_write_error(req->wb_context, error); + if (nfs_error_is_fatal_on_server(error)) { + nfs_write_error_remove_page(req); + continue; + } + } nfs_redirty_request(req); } } static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) { - nfs_async_write_error(&hdr->pages); + nfs_async_write_error(&hdr->pages, 0); filemap_fdatawrite_range(hdr->inode->i_mapping, hdr->args.offset, hdr->args.offset + hdr->args.count - 1); } 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/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..85b0ef890b28 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; } #define SEQ_PUT_DEC(str, val) \ diff --git a/include/uapi/asm-generic/shmparam.h b/include/asm-generic/shmparam.h index 8b78c0ba08b1..8b78c0ba08b1 100644 --- a/include/uapi/asm-generic/shmparam.h +++ b/include/asm-generic/shmparam.h diff --git a/include/keys/request_key_auth-type.h b/include/keys/request_key_auth-type.h new file mode 100644 index 000000000000..a726dd3f1dc6 --- /dev/null +++ b/include/keys/request_key_auth-type.h @@ -0,0 +1,36 @@ +/* request_key authorisation token key type + * + * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _KEYS_REQUEST_KEY_AUTH_TYPE_H +#define _KEYS_REQUEST_KEY_AUTH_TYPE_H + +#include <linux/key.h> + +/* + * Authorisation record for request_key(). + */ +struct request_key_auth { + struct key *target_key; + struct key *dest_keyring; + const struct cred *cred; + void *callout_info; + size_t callout_len; + pid_t pid; + char op[8]; +} __randomize_layout; + +static inline struct request_key_auth *get_request_key_auth(const struct key *key) +{ + return key->payload.data[0]; +} + + +#endif /* _KEYS_REQUEST_KEY_AUTH_TYPE_H */ 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/key-type.h b/include/linux/key-type.h index bc9af551fc83..e49d1de0614e 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -21,15 +21,6 @@ struct kernel_pkey_query; struct kernel_pkey_params; /* - * key under-construction record - * - passed to the request_key actor if supplied - */ -struct key_construction { - struct key *key; /* key being constructed */ - struct key *authkey;/* authorisation for key being constructed */ -}; - -/* * Pre-parsed payload, used by key add, update and instantiate. * * This struct will be cleared and data and datalen will be set with the data @@ -50,8 +41,7 @@ struct key_preparsed_payload { time64_t expiry; /* Expiry time of key */ } __randomize_layout; -typedef int (*request_key_actor_t)(struct key_construction *key, - const char *op, void *aux); +typedef int (*request_key_actor_t)(struct key *auth_key, void *aux); /* * Preparsed matching criterion. @@ -181,20 +171,20 @@ extern int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, - struct key *instkey); + struct key *authkey); extern int key_reject_and_link(struct key *key, unsigned timeout, unsigned error, struct key *keyring, - struct key *instkey); -extern void complete_request_key(struct key_construction *cons, int error); + struct key *authkey); +extern void complete_request_key(struct key *authkey, int error); static inline int key_negate_and_link(struct key *key, unsigned timeout, struct key *keyring, - struct key *instkey) + struct key *authkey) { - return key_reject_and_link(key, timeout, ENOKEY, keyring, instkey); + return key_reject_and_link(key, timeout, ENOKEY, keyring, authkey); } extern int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep); 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/mmc/card.h b/include/linux/mmc/card.h index de7377815b6b..8ef330027b13 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -308,6 +308,7 @@ struct mmc_card { unsigned int nr_parts; unsigned int bouncesz; /* Bounce buffer size */ + struct workqueue_struct *complete_wq; /* Private workqueue */ }; static inline bool mmc_large_sector(struct mmc_card *card) 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/netdev_features.h b/include/linux/netdev_features.h index 2b2a6dce1630..4c76fe2c8488 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -11,6 +11,8 @@ #define _LINUX_NETDEV_FEATURES_H #include <linux/types.h> +#include <linux/bitops.h> +#include <asm/byteorder.h> typedef u64 netdev_features_t; @@ -154,8 +156,26 @@ enum { #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) -#define for_each_netdev_feature(mask_addr, bit) \ - for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) +/* Finds the next feature with the highest number of the range of start till 0. + */ +static inline int find_next_netdev_feature(u64 feature, unsigned long start) +{ + /* like BITMAP_LAST_WORD_MASK() for u64 + * this sets the most significant 64 - start to 0. + */ + feature &= ~0ULL >> (-start & ((sizeof(feature) * 8) - 1)); + + return fls64(feature) - 1; +} + +/* This goes for the MSB to the LSB through the set feature bits, + * mask_addr should be a u64 and bit an int + */ +#define for_each_netdev_feature(mask_addr, bit) \ + for ((bit) = find_next_netdev_feature((mask_addr), \ + NETDEV_FEATURE_COUNT); \ + (bit) >= 0; \ + (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index e27572d30d97..ad69430fd0eb 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -164,6 +164,16 @@ nfs_list_add_request(struct nfs_page *req, struct list_head *head) list_add_tail(&req->wb_list, head); } +/** + * nfs_list_move_request - Move a request to a new list + * @req: request + * @head: head of list into which to insert the request. + */ +static inline void +nfs_list_move_request(struct nfs_page *req, struct list_head *head) +{ + list_move_tail(&req->wb_list, head); +} /** * nfs_list_remove_request - Remove a request from its wb_list diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 441a93ebcac0..b4bd2bf5f585 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1549,7 +1549,7 @@ struct nfs_commit_data { }; struct nfs_pgio_completion_ops { - void (*error_cleanup)(struct list_head *head); + void (*error_cleanup)(struct list_head *head, int); void (*init_hdr)(struct nfs_pgio_header *hdr); void (*completion)(struct nfs_pgio_header *hdr); void (*reschedule_io)(struct nfs_pgio_header *hdr); 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/phy.h b/include/linux/phy.h index ef20aeea10cc..127fcc9c3778 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -674,26 +674,13 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); -static inline bool __phy_is_started(struct phy_device *phydev) -{ - WARN_ON(!mutex_is_locked(&phydev->lock)); - - return phydev->state >= PHY_UP; -} - /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { - bool started; - - mutex_lock(&phydev->lock); - started = __phy_is_started(phydev); - mutex_unlock(&phydev->lock); - - return started; + return phydev->state >= PHY_UP; } void phy_resolve_aneg_linkmode(struct phy_device *phydev); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 95d25b010a25..bdb9563c64a0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2434,7 +2434,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); - else + else if (offset_hint >= 0) skb_set_transport_header(skb, offset_hint); } @@ -4212,6 +4212,12 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } +static inline bool skb_is_gso_tcp(const struct sk_buff *skb) +{ + return skb_is_gso(skb) && + skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); +} + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index cb462f9ab7dd..71f2394abbf7 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -57,6 +57,15 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + } else { + /* 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) { + skb_probe_transport_header(skb, -1); + if (!skb_transport_header_was_set(skb)) + return -EINVAL; + } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 00b5e7825508..74ff688568a0 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -39,6 +39,7 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field diff --git a/include/net/sock.h b/include/net/sock.h index 2b229f7be8eb..f43f935cb113 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1277,7 +1277,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk) percpu_counter_inc(sk->sk_prot->sockets_allocated); } -static inline int +static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 14565d703291..e8baca85bac6 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -137,15 +137,21 @@ enum { INET_DIAG_TCLASS, INET_DIAG_SKMEMINFO, INET_DIAG_SHUTDOWN, - INET_DIAG_DCTCPINFO, - INET_DIAG_PROTOCOL, /* response attribute only */ + + /* + * Next extenstions cannot be requested in struct inet_diag_req_v2: + * its field idiag_ext has only 8 bits. + */ + + INET_DIAG_DCTCPINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_PROTOCOL, /* response attribute only */ INET_DIAG_SKV6ONLY, INET_DIAG_LOCALS, INET_DIAG_PEERS, INET_DIAG_PAD, - INET_DIAG_MARK, - INET_DIAG_BBRINFO, - INET_DIAG_CLASS_ID, + INET_DIAG_MARK, /* only with CAP_NET_ADMIN */ + INET_DIAG_BBRINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_CLASS_ID, /* request as INET_DIAG_TCLASS */ INET_DIAG_MD5SIG, __INET_DIAG_MAX, }; diff --git a/init/main.c b/init/main.c index e2e80ca3165a..c86a1c8f19f4 100644 --- a/init/main.c +++ b/init/main.c @@ -695,7 +695,6 @@ asmlinkage __visible void __init start_kernel(void) initrd_start = 0; } #endif - page_ext_init(); kmemleak_init(); setup_per_cpu_pageset(); numa_policy_init(); @@ -1131,6 +1130,8 @@ static noinline void __init kernel_init_freeable(void) sched_init_smp(); page_alloc_init_late(); + /* Initialize page ext after all struct pages are initialized. */ + page_ext_init(); do_basic_setup(); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index d43b14535827..950ab2f28922 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry) struct stack_map_irq_work *work; work = container_of(entry, struct stack_map_irq_work, irq_work); - up_read(work->sem); + up_read_non_owner(work->sem); work->sem = NULL; } @@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } else { work->sem = ¤t->mm->mmap_sem; irq_work_queue(&work->irq_work); + /* + * The irq_work will release the mmap_sem with + * up_read_non_owner(). The rwsem_release() is called + * here to release the lock from lockdep's perspective. + */ + rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); } } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56674a7c3778..8f295b790297 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1617,12 +1617,13 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } -static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, enum bpf_access_type t) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; - struct bpf_insn_access_aux info; + struct bpf_insn_access_aux info = {}; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", @@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + return 0; } @@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "cannot write into socket\n"); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { 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/signal.c b/kernel/signal.c index 99fa8ff06fd9..57b7771e20d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2436,9 +2436,12 @@ relock: } /* Has this task already been marked for death? */ - ksig->info.si_signo = signr = SIGKILL; - if (signal_group_exit(signal)) + if (signal_group_exit(signal)) { + ksig->info.si_signo = signr = SIGKILL; + sigdelset(¤t->pending.signal, SIGKILL); + recalc_sigpending(); goto fatal; + } for (;;) { struct k_sigaction *ka; 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/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5c56afc17cf8..4737bb8c07a3 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs, if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); ret = process_fetch_insn(arg->code, regs, dl, base); - if (unlikely(ret < 0 && arg->dynamic)) + if (unlikely(ret < 0 && arg->dynamic)) { *dl = make_data_loc(0, dyndata - base); - else + } else { dyndata += ret; + maxlen -= ret; + } } } diff --git a/lib/assoc_array.c b/lib/assoc_array.c index c6659cb37033..59875eb278ea 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -768,9 +768,11 @@ all_leaves_cluster_together: new_s0->index_key[i] = ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE); - blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); - pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); - new_s0->index_key[keylen - 1] &= ~blank; + if (level & ASSOC_ARRAY_KEY_CHUNK_MASK) { + blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); + pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); + new_s0->index_key[keylen - 1] &= ~blank; + } /* This now reduces to a node splitting exercise for which we'll need * to regenerate the disparity table. 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. @@ -1674,7 +1674,8 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they 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/mm/page_alloc.c b/mm/page_alloc.c index 35fdde041f5c..7f79b78bc829 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4675,11 +4675,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size - 1); + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; nc->offset = size; } @@ -4695,10 +4695,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size); + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; } diff --git a/mm/page_ext.c b/mm/page_ext.c index ae44f7adbe07..8c78b8d45117 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -398,10 +398,8 @@ void __init page_ext_init(void) * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... - * - * Take into account DEFERRED_STRUCT_PAGE_INIT. */ - if (early_pfn_to_nid(pfn) != nid) + if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; diff --git a/mm/vmscan.c b/mm/vmscan.c index a714c4f800e9..e979705bbf32 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -491,16 +491,6 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - /* - * Make sure we apply some minimal pressure on default priority - * even on small cgroups. Stale objects are not only consuming memory - * by themselves, but can also hold a reference to a dying cgroup, - * preventing it from being reclaimed. A dying cgroup with all - * corresponding structures like per-cpu stats and kmem caches - * can be really big, so it may lead to a significant waste of memory. - */ - delta = max_t(unsigned long long, delta, min(freeable, batch_size)); - total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index b85ca809e509..ffc83bebfe40 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -227,6 +227,8 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, switch (ntohs(ethhdr->h_proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, sizeof(*vhdr))) + goto dropped; vhdr = vlan_eth_hdr(skb); /* drop batman-in-batman packets to prevent loops */ diff --git a/net/core/dev.c b/net/core/dev.c index 8e276e0192a1..5d03889502eb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8152,7 +8152,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { @@ -8172,7 +8172,7 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", diff --git a/net/core/filter.c b/net/core/filter.c index 7a54dc11ac2d..f7d0004fc160 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2789,8 +2789,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2831,8 +2830,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2957,8 +2955,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2987,8 +2984,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26d848484912..2415d9cb9b89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) */ void *netdev_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -369,6 +371,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) void *napi_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); diff --git a/net/core/sock.c b/net/core/sock.c index 6aa2e7e0b4fb..bc3512f230a3 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2380,7 +2380,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) } if (sk_has_memory_pressure(sk)) { - int alloc; + u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 1a4e9ff02762..5731670c560b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk, + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d..be778599bfed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 2687db015b6f..fa2ba7c500e4 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index a0aa13bcabda..0a8a60c1bf9a 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset) int snmp_version(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { + if (datalen != 1) + return -EINVAL; if (*(unsigned char *)data > 1) return -ENOTSUPP; return 1; @@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { struct snmp_ctx *ctx = (struct snmp_ctx *)context; - __be32 *pdata = (__be32 *)data; + __be32 *pdata; + if (datalen != 4) + return -EINVAL; + pdata = (__be32 *)data; if (*pdata == ctx->from) { pr_debug("%s: %pI4 to %pI4\n", __func__, (void *)&ctx->from, (void *)&ctx->to); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ce92f73cf104..5163b64f8fb3 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2079145a3b7c..cf3c5095c10e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2528,6 +2528,7 @@ void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; + inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2576,7 +2577,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; - icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index efc6fef692ff..ec3cea9d6828 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -536,12 +536,15 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sock_owned_by_user(sk)) break; + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + break; + icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_rtx_queue_head(sk); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 84c358804355..72ffd3d760ff 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1165,7 +1165,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 801a9a0c217e..43890898b0b5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1719,6 +1719,24 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static void ip6erspan_set_version(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + parms->erspan_ver = 1; + if (data[IFLA_GRE_ERSPAN_VER]) + parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); + + if (parms->erspan_ver == 1) { + if (data[IFLA_GRE_ERSPAN_INDEX]) + parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + } else if (parms->erspan_ver == 2) { + if (data[IFLA_GRE_ERSPAN_DIR]) + parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); + if (data[IFLA_GRE_ERSPAN_HWID]) + parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); + } +} + static void ip6gre_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { @@ -1767,20 +1785,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; - - parms->erspan_ver = 1; - if (data[IFLA_GRE_ERSPAN_VER]) - parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - - if (parms->erspan_ver == 1) { - if (data[IFLA_GRE_ERSPAN_INDEX]) - parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); - } else if (parms->erspan_ver == 2) { - if (data[IFLA_GRE_ERSPAN_DIR]) - parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); - if (data[IFLA_GRE_ERSPAN_HWID]) - parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); - } } static int ip6gre_tap_init(struct net_device *dev) @@ -2203,6 +2207,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, int err; ip6gre_netlink_parms(data, &nt->parms); + ip6erspan_set_version(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { @@ -2248,6 +2253,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (IS_ERR(t)) return PTR_ERR(t); + ip6erspan_set_version(data, &p); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 23022447eb49..7a41ee3c11b4 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -226,6 +226,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 8d0ba757a46c..9b2f272ca164 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); - genlmsg_reply(msg, info); - - return 0; + return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..54821fb1a960 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2493c74c2d37..96496b2c1670 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -941,6 +941,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER; int err; + int prev_beacon_int; old = sdata_dereference(sdata->u.ap.beacon, sdata); if (old) @@ -963,6 +964,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->needed_rx_chains = sdata->local->rx_chains; + prev_beacon_int = sdata->vif.bss_conf.beacon_int; sdata->vif.bss_conf.beacon_int = params->beacon_interval; if (params->he_cap) @@ -974,8 +976,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (!err) ieee80211_vif_copy_chanctx_to_vlans(sdata, false); mutex_unlock(&local->mtx); - if (err) + if (err) { + sdata->vif.bss_conf.beacon_int = prev_beacon_int; return err; + } /* * Apply control port protocol, this allows us to diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..2ec7011a4d07 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -70,6 +70,7 @@ enum mesh_deferred_task_flags { * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer + * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be @@ -105,6 +106,7 @@ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; + struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; @@ -133,12 +135,16 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containging all mesh_path objects + * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ struct mesh_table { struct hlist_head known_gates; spinlock_t gates_lock; struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ }; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index a5125624a76d..88a6d5e18ccc 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -59,8 +59,10 @@ static struct mesh_table *mesh_table_alloc(void) return NULL; INIT_HLIST_HEAD(&newtbl->known_gates); + INIT_HLIST_HEAD(&newtbl->walk_head); atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); + spin_lock_init(&newtbl->walk_lock); return newtbl; } @@ -249,28 +251,15 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) static struct mesh_path * __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) { - int i = 0, ret; - struct mesh_path *mpath = NULL; - struct rhashtable_iter iter; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return NULL; - - rhashtable_walk_start(&iter); + int i = 0; + struct mesh_path *mpath; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (i++ == idx) break; } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); - if (IS_ERR(mpath) || !mpath) + if (!mpath) return NULL; if (mpath_expired(mpath)) { @@ -432,6 +421,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, return ERR_PTR(-ENOMEM); tbl = sdata->u.mesh.mesh_paths; + spin_lock_bh(&tbl->walk_lock); do { ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -441,20 +431,20 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, mpath = rhashtable_lookup_fast(&tbl->rhead, dst, mesh_rht_params); - + else if (!ret) + hlist_add_head(&new_mpath->walk_list, &tbl->walk_head); } while (unlikely(ret == -EEXIST && !mpath)); + spin_unlock_bh(&tbl->walk_lock); - if (ret && ret != -EEXIST) - return ERR_PTR(ret); - - /* At this point either new_mpath was added, or we found a - * matching entry already in the table; in the latter case - * free the unnecessary new entry. - */ - if (ret == -EEXIST) { + if (ret) { kfree(new_mpath); + + if (ret != -EEXIST) + return ERR_PTR(ret); + new_mpath = mpath; } + sdata->u.mesh.mesh_paths_generation++; return new_mpath; } @@ -480,9 +470,17 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, memcpy(new_mpath->mpp, mpp, ETH_ALEN); tbl = sdata->u.mesh.mpp_paths; + + spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, mesh_rht_params); + if (!ret) + hlist_add_head_rcu(&new_mpath->walk_list, &tbl->walk_head); + spin_unlock_bh(&tbl->walk_lock); + + if (ret) + kfree(new_mpath); sdata->u.mesh.mpp_paths_generation++; return ret; @@ -503,20 +501,9 @@ void mesh_plink_broken(struct sta_info *sta) struct mesh_table *tbl = sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + rcu_read_lock(); + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { @@ -530,8 +517,7 @@ void mesh_plink_broken(struct sta_info *sta) WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + rcu_read_unlock(); } static void mesh_path_free_rcu(struct mesh_table *tbl, @@ -551,6 +537,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) { + hlist_del_rcu(&mpath->walk_list); rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params); mesh_path_free_rcu(tbl, mpath); } @@ -571,27 +558,14 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct mesh_table *tbl = sdata->u.mesh.mesh_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, @@ -599,51 +573,26 @@ static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, { struct mesh_table *tbl = sdata->u.mesh.mpp_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (ether_addr_equal(mpath->mpp, proxy)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void table_flush_by_iface(struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); + struct hlist_node *n; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } /** @@ -675,15 +624,15 @@ static int table_path_del(struct mesh_table *tbl, { struct mesh_path *mpath; - rcu_read_lock(); + 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; } __mesh_path_del(tbl, mpath); - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return 0; } @@ -854,28 +803,16 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; + struct hlist_node *n; - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } void mesh_path_expire(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d0eb38b890aa..ba950ae974fc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2146,6 +2146,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; + case NL80211_IFTYPE_ADHOC: + if (sdata->vif.bss_conf.ibss_joined) + WARN_ON(drv_join_ibss(local, sdata)); + /* fall through */ default: ieee80211_reconfig_stations(sdata); /* fall through */ diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index cad48d07c818..8401cefd9f65 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,6 +29,7 @@ config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 select IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 ---help--- Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index fe9abf3cc10a..235205c93e14 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1536,14 +1536,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); - if (iph->fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + + /* Fragment couldn't be mapped to a conn entry */ + if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); - } + *verdict = NF_ACCEPT; return 0; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 7d6318664eb2..ac8d848d7624 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -43,6 +43,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> @@ -900,11 +901,17 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, #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) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; + + ret = nf_defrag_ipv6_enable(svc->ipvs->net); + if (ret) + return ret; } else #endif { @@ -1228,6 +1235,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -EINVAL; goto out_err; } + + ret = nf_defrag_ipv6_enable(ipvs->net); + if (ret) + goto out_err; } #endif 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/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index fe64df848365..0a4bad55a8aa 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -315,6 +315,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); + struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; @@ -325,7 +326,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) par.target->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(target->me); + module_put(me); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index aecadd471e1d..13e1ac333fa4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1899,7 +1899,7 @@ static int __init xt_init(void) seqcount_init(&per_cpu(xt_recseq, i)); } - xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); + xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3b1a78906bc0..1cd1d83a4be0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; - if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 9ccc93f257db..38bb882bb958 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -48,7 +48,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_head rcu; + struct rcu_work rwork; }; static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) @@ -221,17 +221,11 @@ found: return 0; } -static int tcindex_destroy_element(struct tcf_proto *tp, - void *arg, struct tcf_walker *walker) -{ - bool last; - - return tcindex_delete(tp, arg, &last, NULL); -} - -static void __tcindex_destroy(struct rcu_head *head) +static void tcindex_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p->h); @@ -258,9 +252,11 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r) return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } -static void __tcindex_partial_destroy(struct rcu_head *head) +static void tcindex_partial_destroy_work(struct work_struct *work) { - struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); + struct tcindex_data *p = container_of(to_rcu_work(work), + struct tcindex_data, + rwork); kfree(p->perfect); kfree(p); @@ -275,7 +271,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp) kfree(cp->perfect); } -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) { int i, err = 0; @@ -289,6 +285,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; +#ifdef CONFIG_NET_CLS_ACT + cp->perfect[i].exts.net = net; +#endif } return 0; @@ -305,9 +304,9 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; @@ -337,7 +336,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) cp->perfect[i].res = p->perfect[i].res; @@ -348,11 +347,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result); if (err < 0) goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; if (old_r) - cr.res = r->res; + cr = r->res; if (tb[TCA_TCINDEX_HASH]) cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -406,7 +402,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout_alloc; balloc = 1; } else { @@ -443,8 +439,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); + cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); + tcf_bind_filter(tp, &cr, base); } if (old_r && old_r != r) { @@ -456,7 +452,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } oldp = p; - r->res = cr.res; + r->res = cr; tcf_exts_change(&r->exts, &e); rcu_assign_pointer(tp->root, cp); @@ -475,10 +471,12 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, ; /* nothing */ rcu_assign_pointer(*fp, f); + } else { + tcf_exts_destroy(&new_filter_result.exts); } if (oldp) - call_rcu(&oldp->rcu, __tcindex_partial_destroy); + tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); return 0; errout_alloc: @@ -487,7 +485,6 @@ errout_alloc: else if (balloc == 2) kfree(cp->h); errout1: - tcf_exts_destroy(&cr.exts); tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -562,15 +559,34 @@ static void tcindex_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcf_walker walker; + int i; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - walker.count = 0; - walker.skip = 0; - walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); - call_rcu(&p->rcu, __tcindex_destroy); + if (p->perfect) { + for (i = 0; i < p->hash; i++) { + struct tcindex_filter_result *r = p->perfect + i; + + tcf_unbind_filter(tp, &r->res); + if (tcf_exts_get_net(&r->exts)) + tcf_queue_work(&r->rwork, + tcindex_destroy_rexts_work); + else + __tcindex_destroy_rexts(r); + } + } + + for (i = 0; p->h && i < p->hash; i++) { + struct tcindex_filter *f, *next; + bool last; + + for (f = rtnl_dereference(p->h[i]); f; f = next) { + next = rtnl_dereference(f->next); + tcindex_delete(tp, &f->result, &last, NULL); + } + } + + tcf_queue_work(&p->rwork, tcindex_destroy_work); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 66ba2ce2320f..968a85fe4d4a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -500,7 +500,7 @@ static void dev_watchdog_down(struct net_device *dev) * netif_carrier_on - set carrier * @dev: network device * - * Device has detected that carrier. + * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 078f01a8d582..435847d98b51 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 123e9f2dc226..edfcf16e704c 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; + gso_reset_checksum(skb, ~0); return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f24633114dfd..2936ed17bf9e 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -144,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, } } - for (i = outcnt; i < stream->outcnt; i++) + for (i = outcnt; i < stream->outcnt; i++) { kfree(SCTP_SO(stream, i)->ext); + SCTP_SO(stream, i)->ext = NULL; + } } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a712c9f8699b..fb07ad8d69a6 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -101,9 +101,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->tx_cdc_seq++; conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; - smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, - &conn->local_tx_ctrl, conn); - smc_curs_copy(&cfed, &((struct smc_host_cdc_msg *)wr_buf)->cons, conn); + smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); if (!rc) smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index 271e2524dc8f..f1cdde9d4b89 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -211,26 +211,27 @@ static inline int smc_curs_diff_large(unsigned int size, static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, + union smc_host_cursor *save, struct smc_connection *conn) { - union smc_host_cursor temp; - - smc_curs_copy(&temp, local, conn); - peer->count = htonl(temp.count); - peer->wrap = htons(temp.wrap); + smc_curs_copy(save, local, conn); + peer->count = htonl(save->count); + peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, - struct smc_host_cdc_msg *local, - struct smc_connection *conn) + struct smc_connection *conn, + union smc_host_cursor *save) { + struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; + peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); - smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn); - smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn); + smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); + smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } 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/auth_unix.c b/net/sunrpc/auth_unix.c index c048eb6deaaf..d4018e5a24c5 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -80,7 +80,7 @@ unx_match(struct auth_cred *acred, struct rpc_cred *cred, int flags) if (!uid_eq(cred->cr_cred->fsuid, acred->cred->fsuid) || !gid_eq(cred->cr_cred->fsgid, acred->cred->fsgid)) return 0; - if (acred->cred && acred->cred->group_info != NULL) + if (acred->cred->group_info != NULL) groups = acred->cred->group_info->ngroups; if (groups > UNX_NGROUPS) groups = UNX_NGROUPS; diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index ec451b8114b0..b9313c15ee3a 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -252,7 +252,6 @@ static struct rpc_rqst *xprt_alloc_bc_request(struct rpc_xprt *xprt, __be32 xid) req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst, rq_bc_pa_list); req->rq_reply_bytes_recvd = 0; - req->rq_bytes_sent = 0; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(req->rq_private_buf)); req->rq_xid = xid; 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/sched.c b/net/sunrpc/sched.c index adc3c40cc733..2168d4d9c09f 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -19,6 +19,7 @@ #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/freezer.h> +#include <linux/sched/mm.h> #include <linux/sunrpc/clnt.h> @@ -902,7 +903,10 @@ void rpc_execute(struct rpc_task *task) static void rpc_async_schedule(struct work_struct *work) { + unsigned int pflags = memalloc_nofs_save(); + __rpc_execute(container_of(work, struct rpc_task, u.tk_work)); + memalloc_nofs_restore(pflags); } /** @@ -1067,7 +1071,10 @@ static void rpc_free_task(struct rpc_task *task) static void rpc_async_release(struct work_struct *work) { + unsigned int pflags = memalloc_nofs_save(); + rpc_free_task(container_of(work, struct rpc_task, u.tk_work)); + memalloc_nofs_restore(pflags); } static void rpc_release_resources_task(struct rpc_task *task) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index bc7489f1fe55..1cf4e379be7b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -49,6 +49,7 @@ #include <linux/sunrpc/metrics.h> #include <linux/sunrpc/bc_xprt.h> #include <linux/rcupdate.h> +#include <linux/sched/mm.h> #include <trace/events/sunrpc.h> @@ -643,11 +644,13 @@ static void xprt_autoclose(struct work_struct *work) { struct rpc_xprt *xprt = container_of(work, struct rpc_xprt, task_cleanup); + unsigned int pflags = memalloc_nofs_save(); clear_bit(XPRT_CLOSE_WAIT, &xprt->state); xprt->ops->close(xprt); xprt_release_write(xprt, NULL); wake_up_bit(&xprt->state, XPRT_LOCKED); + memalloc_nofs_restore(pflags); } /** @@ -1601,7 +1604,6 @@ xprt_request_init(struct rpc_task *task) req->rq_buffer = NULL; req->rq_xid = xprt_alloc_xid(xprt); xprt_init_connect_cookie(req, xprt); - req->rq_bytes_sent = 0; req->rq_snd_buf.len = 0; req->rq_snd_buf.buflen = 0; req->rq_rcv_buf.len = 0; @@ -1723,6 +1725,7 @@ void xprt_release(struct rpc_task *task) xprt->ops->buf_free(task); xprt_inject_disconnect(xprt); xdr_free_bvec(&req->rq_rcv_buf); + xdr_free_bvec(&req->rq_snd_buf); if (req->rq_cred != NULL) put_rpccred(req->rq_cred); task->tk_rqstp = NULL; @@ -1751,7 +1754,6 @@ xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task) */ xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + xbufp->tail[0].iov_len; - req->rq_bytes_sent = 0; } #endif diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index 98c1e43eb7b1..d79b18c1f4cd 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -267,7 +267,6 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, /* Prepare rqst */ rqst->rq_reply_bytes_recvd = 0; - rqst->rq_bytes_sent = 0; rqst->rq_xid = *p; rqst->rq_private_buf.len = size; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index e7274dc10120..5d261353bd90 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -737,7 +737,6 @@ xprt_rdma_send_request(struct rpc_rqst *rqst) goto drop_connection; rqst->rq_xmit_bytes_sent += rqst->rq_snd_buf.len; - rqst->rq_bytes_sent = 0; /* An RPC with no reply will throw off credit accounting, * so drop the connection to reset the credit grant. diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b4e997d53ec7..89a63391d4d4 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/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ae09d850cd11..53de72d2dded 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -50,6 +50,7 @@ #include <linux/bvec.h> #include <linux/highmem.h> #include <linux/uio.h> +#include <linux/sched/mm.h> #include <trace/events/sunrpc.h> @@ -404,8 +405,8 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, size_t want, seek_init = seek, offset = 0; ssize_t ret; - if (seek < buf->head[0].iov_len) { - want = min_t(size_t, count, buf->head[0].iov_len); + want = min_t(size_t, count, buf->head[0].iov_len); + if (seek < want) { ret = xs_read_kvec(sock, msg, flags, &buf->head[0], want, seek); if (ret <= 0) goto sock_err; @@ -416,8 +417,8 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, goto out; seek = 0; } else { - seek -= buf->head[0].iov_len; - offset += buf->head[0].iov_len; + seek -= want; + offset += want; } want = xs_alloc_sparse_pages(buf, @@ -442,8 +443,8 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, offset += want; } - if (seek < buf->tail[0].iov_len) { - want = min_t(size_t, count - offset, buf->tail[0].iov_len); + want = min_t(size_t, count - offset, buf->tail[0].iov_len); + if (seek < want) { ret = xs_read_kvec(sock, msg, flags, &buf->tail[0], want, seek); if (ret <= 0) goto sock_err; @@ -453,7 +454,7 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags, if (ret != want) goto out; } else - offset += buf->tail[0].iov_len; + offset = seek_init; ret = -EMSGSIZE; out: *read = offset - seek_init; @@ -481,6 +482,14 @@ xs_read_stream_request_done(struct sock_xprt *transport) return transport->recv.fraghdr & cpu_to_be32(RPC_LAST_STREAM_FRAGMENT); } +static void +xs_read_stream_check_eor(struct sock_xprt *transport, + struct msghdr *msg) +{ + if (xs_read_stream_request_done(transport)) + msg->msg_flags |= MSG_EOR; +} + static ssize_t xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, int flags, struct rpc_rqst *req) @@ -492,17 +501,21 @@ xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg, xs_read_header(transport, buf); want = transport->recv.len - transport->recv.offset; - ret = xs_read_xdr_buf(transport->sock, msg, flags, buf, - transport->recv.copied + want, transport->recv.copied, - &read); - transport->recv.offset += read; - transport->recv.copied += read; - if (transport->recv.offset == transport->recv.len) { - if (xs_read_stream_request_done(transport)) - msg->msg_flags |= MSG_EOR; - return read; + if (want != 0) { + ret = xs_read_xdr_buf(transport->sock, msg, flags, buf, + transport->recv.copied + want, + transport->recv.copied, + &read); + transport->recv.offset += read; + transport->recv.copied += read; } + if (transport->recv.offset == transport->recv.len) + xs_read_stream_check_eor(transport, msg); + + if (want == 0) + return 0; + switch (ret) { default: break; @@ -655,13 +668,34 @@ out_err: return ret != 0 ? ret : -ESHUTDOWN; } +static __poll_t xs_poll_socket(struct sock_xprt *transport) +{ + return transport->sock->ops->poll(NULL, transport->sock, NULL); +} + +static bool xs_poll_socket_readable(struct sock_xprt *transport) +{ + __poll_t events = xs_poll_socket(transport); + + return (events & (EPOLLIN | EPOLLRDNORM)) && !(events & EPOLLRDHUP); +} + +static void xs_poll_check_readable(struct sock_xprt *transport) +{ + + clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); + if (!xs_poll_socket_readable(transport)) + return; + if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) + queue_work(xprtiod_workqueue, &transport->recv_worker); +} + static void xs_stream_data_receive(struct sock_xprt *transport) { size_t read = 0; ssize_t ret = 0; mutex_lock(&transport->recv_mutex); - clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); if (transport->sock == NULL) goto out; for (;;) { @@ -671,6 +705,10 @@ static void xs_stream_data_receive(struct sock_xprt *transport) read += ret; cond_resched(); } + if (ret == -ESHUTDOWN) + kernel_sock_shutdown(transport->sock, SHUT_RDWR); + else + xs_poll_check_readable(transport); out: mutex_unlock(&transport->recv_mutex); trace_xs_stream_read_data(&transport->xprt, ret, read); @@ -680,7 +718,10 @@ static void xs_stream_data_receive_workfn(struct work_struct *work) { struct sock_xprt *transport = container_of(work, struct sock_xprt, recv_worker); + unsigned int pflags = memalloc_nofs_save(); + xs_stream_data_receive(transport); + memalloc_nofs_restore(pflags); } static void @@ -690,99 +731,65 @@ xs_stream_reset_connect(struct sock_xprt *transport) transport->recv.len = 0; transport->recv.copied = 0; transport->xmit.offset = 0; +} + +static void +xs_stream_start_connect(struct sock_xprt *transport) +{ transport->xprt.stat.connect_count++; transport->xprt.stat.connect_start = jiffies; } #define XS_SENDMSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL) +static int xs_sendmsg(struct socket *sock, struct msghdr *msg, size_t seek) +{ + if (seek) + iov_iter_advance(&msg->msg_iter, seek); + return sock_sendmsg(sock, msg); +} + +static int xs_send_kvec(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t seek) +{ + iov_iter_kvec(&msg->msg_iter, WRITE, vec, 1, vec->iov_len); + return xs_sendmsg(sock, msg, seek); +} + +static int xs_send_pagedata(struct socket *sock, struct msghdr *msg, struct xdr_buf *xdr, size_t base) +{ + int err; + + err = xdr_alloc_bvec(xdr, GFP_KERNEL); + if (err < 0) + return err; + + iov_iter_bvec(&msg->msg_iter, WRITE, xdr->bvec, + xdr_buf_pagecount(xdr), + xdr->page_len + xdr->page_base); + return xs_sendmsg(sock, msg, base + xdr->page_base); +} + +#define xs_record_marker_len() sizeof(rpc_fraghdr) + /* Common case: * - stream transport * - sending from byte 0 of the message * - the message is wholly contained in @xdr's head iovec */ -static int xs_send_rm_and_kvec(struct socket *sock, struct xdr_buf *xdr, - unsigned int remainder) +static int xs_send_rm_and_kvec(struct socket *sock, struct msghdr *msg, + rpc_fraghdr marker, struct kvec *vec, size_t base) { - struct msghdr msg = { - .msg_flags = XS_SENDMSG_FLAGS | (remainder ? MSG_MORE : 0) - }; - rpc_fraghdr marker = cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | - (u32)xdr->len); struct kvec iov[2] = { - { + [0] = { .iov_base = &marker, .iov_len = sizeof(marker) }, - { - .iov_base = xdr->head[0].iov_base, - .iov_len = xdr->head[0].iov_len - }, - }; - int ret; - - ret = kernel_sendmsg(sock, &msg, iov, 2, - iov[0].iov_len + iov[1].iov_len); - if (ret < 0) - return ret; - if (ret < iov[0].iov_len) - return -EPIPE; - return ret - iov[0].iov_len; -} - -static int xs_send_kvec(struct socket *sock, struct sockaddr *addr, int addrlen, struct kvec *vec, unsigned int base, int more) -{ - struct msghdr msg = { - .msg_name = addr, - .msg_namelen = addrlen, - .msg_flags = XS_SENDMSG_FLAGS | (more ? MSG_MORE : 0), - }; - struct kvec iov = { - .iov_base = vec->iov_base + base, - .iov_len = vec->iov_len - base, + [1] = *vec, }; + size_t len = iov[0].iov_len + iov[1].iov_len; - if (iov.iov_len != 0) - return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len); - return kernel_sendmsg(sock, &msg, NULL, 0, 0); -} - -static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned int base, int more, bool zerocopy, int *sent_p) -{ - ssize_t (*do_sendpage)(struct socket *sock, struct page *page, - int offset, size_t size, int flags); - struct page **ppage; - unsigned int remainder; - int err; - - remainder = xdr->page_len - base; - base += xdr->page_base; - ppage = xdr->pages + (base >> PAGE_SHIFT); - base &= ~PAGE_MASK; - do_sendpage = sock->ops->sendpage; - if (!zerocopy) - do_sendpage = sock_no_sendpage; - for(;;) { - unsigned int len = min_t(unsigned int, PAGE_SIZE - base, remainder); - int flags = XS_SENDMSG_FLAGS; - - remainder -= len; - if (more) - flags |= MSG_MORE; - if (remainder != 0) - flags |= MSG_SENDPAGE_NOTLAST | MSG_MORE; - err = do_sendpage(sock, *ppage, base, len, flags); - if (remainder == 0 || err != len) - break; - *sent_p += err; - ppage++; - base = 0; - } - if (err > 0) { - *sent_p += err; - err = 0; - } - return err; + iov_iter_kvec(&msg->msg_iter, WRITE, iov, 2, len); + return xs_sendmsg(sock, msg, base); } /** @@ -792,53 +799,60 @@ static int xs_send_pagedata(struct socket *sock, struct xdr_buf *xdr, unsigned i * @addrlen: UDP only -- length of destination address * @xdr: buffer containing this request * @base: starting position in the buffer - * @zerocopy: true if it is safe to use sendpage() + * @rm: stream record marker field * @sent_p: return the total number of bytes successfully queued for sending * */ -static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, bool zerocopy, int *sent_p) +static int xs_sendpages(struct socket *sock, struct sockaddr *addr, int addrlen, struct xdr_buf *xdr, unsigned int base, rpc_fraghdr rm, int *sent_p) { - unsigned int remainder = xdr->len - base; + struct msghdr msg = { + .msg_name = addr, + .msg_namelen = addrlen, + .msg_flags = XS_SENDMSG_FLAGS | MSG_MORE, + }; + unsigned int rmsize = rm ? sizeof(rm) : 0; + unsigned int remainder = rmsize + xdr->len - base; + unsigned int want; int err = 0; - int sent = 0; if (unlikely(!sock)) return -ENOTSOCK; - if (base != 0) { - addr = NULL; - addrlen = 0; - } - - if (base < xdr->head[0].iov_len || addr != NULL) { - unsigned int len = xdr->head[0].iov_len - base; + want = xdr->head[0].iov_len + rmsize; + if (base < want) { + unsigned int len = want - base; remainder -= len; - if (!base && !addr) - err = xs_send_rm_and_kvec(sock, xdr, remainder); + if (remainder == 0) + msg.msg_flags &= ~MSG_MORE; + if (rmsize) + err = xs_send_rm_and_kvec(sock, &msg, rm, + &xdr->head[0], base); else - err = xs_send_kvec(sock, addr, addrlen, &xdr->head[0], - base, remainder != 0); + err = xs_send_kvec(sock, &msg, &xdr->head[0], base); if (remainder == 0 || err != len) goto out; *sent_p += err; base = 0; } else - base -= xdr->head[0].iov_len; + base -= want; if (base < xdr->page_len) { unsigned int len = xdr->page_len - base; remainder -= len; - err = xs_send_pagedata(sock, xdr, base, remainder != 0, zerocopy, &sent); - *sent_p += sent; - if (remainder == 0 || sent != len) + if (remainder == 0) + msg.msg_flags &= ~MSG_MORE; + err = xs_send_pagedata(sock, &msg, xdr, base); + if (remainder == 0 || err != len) goto out; + *sent_p += err; base = 0; } else base -= xdr->page_len; if (base >= xdr->tail[0].iov_len) return 0; - err = xs_send_kvec(sock, NULL, 0, &xdr->tail[0], base, 0); + msg.msg_flags &= ~MSG_MORE; + err = xs_send_kvec(sock, &msg, &xdr->tail[0], base); out: if (err > 0) { *sent_p += err; @@ -907,6 +921,17 @@ xs_send_request_was_aborted(struct sock_xprt *transport, struct rpc_rqst *req) return transport->xmit.offset != 0 && req->rq_bytes_sent == 0; } +/* + * Return the stream record marker field for a record of length < 2^31-1 + */ +static rpc_fraghdr +xs_stream_record_marker(struct xdr_buf *xdr) +{ + if (!xdr->len) + return 0; + return cpu_to_be32(RPC_LAST_STREAM_FRAGMENT | (u32)xdr->len); +} + /** * xs_local_send_request - write an RPC request to an AF_LOCAL socket * @req: pointer to RPC request @@ -939,7 +964,8 @@ static int xs_local_send_request(struct rpc_rqst *req) req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, NULL, 0, xdr, transport->xmit.offset, - true, &sent); + xs_stream_record_marker(xdr), + &sent); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - transport->xmit.offset, status); @@ -951,7 +977,6 @@ static int xs_local_send_request(struct rpc_rqst *req) req->rq_bytes_sent = transport->xmit.offset; if (likely(req->rq_bytes_sent >= req->rq_slen)) { req->rq_xmit_bytes_sent += transport->xmit.offset; - req->rq_bytes_sent = 0; transport->xmit.offset = 0; return 0; } @@ -1007,7 +1032,7 @@ static int xs_udp_send_request(struct rpc_rqst *req) req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, - xdr, 0, true, &sent); + xdr, 0, 0, &sent); dprintk("RPC: xs_udp_send_request(%u) = %d\n", xdr->len, status); @@ -1071,7 +1096,6 @@ static int xs_tcp_send_request(struct rpc_rqst *req) struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; - bool zerocopy = true; bool vm_wait = false; int status; int sent; @@ -1086,12 +1110,6 @@ static int xs_tcp_send_request(struct rpc_rqst *req) xs_pktdump("packet data:", req->rq_svec->iov_base, req->rq_svec->iov_len); - /* Don't use zero copy if this is a resend. If the RPC call - * completes while the socket holds a reference to the pages, - * then we may end up resending corrupted data. - */ - if (req->rq_task->tk_flags & RPC_TASK_SENT) - zerocopy = false; if (test_bit(XPRT_SOCK_UPD_TIMEOUT, &transport->sock_state)) xs_tcp_set_socket_timeouts(xprt, transport->sock); @@ -1104,7 +1122,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) sent = 0; status = xs_sendpages(transport->sock, NULL, 0, xdr, transport->xmit.offset, - zerocopy, &sent); + xs_stream_record_marker(xdr), + &sent); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - transport->xmit.offset, status); @@ -1115,7 +1134,6 @@ static int xs_tcp_send_request(struct rpc_rqst *req) req->rq_bytes_sent = transport->xmit.offset; if (likely(req->rq_bytes_sent >= req->rq_slen)) { req->rq_xmit_bytes_sent += transport->xmit.offset; - req->rq_bytes_sent = 0; transport->xmit.offset = 0; return 0; } @@ -1255,6 +1273,8 @@ static void xs_reset_transport(struct sock_xprt *transport) xprt_clear_connected(xprt); write_unlock_bh(&sk->sk_callback_lock); xs_sock_reset_connection_flags(xprt); + /* Reset stream record info */ + xs_stream_reset_connect(transport); mutex_unlock(&transport->recv_mutex); trace_rpc_socket_close(xprt, sock); @@ -1382,7 +1402,6 @@ static void xs_udp_data_receive(struct sock_xprt *transport) int err; mutex_lock(&transport->recv_mutex); - clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); sk = transport->inet; if (sk == NULL) goto out; @@ -1394,6 +1413,7 @@ static void xs_udp_data_receive(struct sock_xprt *transport) consume_skb(skb); cond_resched(); } + xs_poll_check_readable(transport); out: mutex_unlock(&transport->recv_mutex); } @@ -1402,7 +1422,10 @@ static void xs_udp_data_receive_workfn(struct work_struct *work) { struct sock_xprt *transport = container_of(work, struct sock_xprt, recv_worker); + unsigned int pflags = memalloc_nofs_save(); + xs_udp_data_receive(transport); + memalloc_nofs_restore(pflags); } /** @@ -1893,7 +1916,6 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, sk->sk_write_space = xs_udp_write_space; sock_set_flag(sk, SOCK_FASYNC); sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_NOIO; xprt_clear_connected(xprt); @@ -1904,7 +1926,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, write_unlock_bh(&sk->sk_callback_lock); } - xs_stream_reset_connect(transport); + xs_stream_start_connect(transport); return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0); } @@ -2081,7 +2103,6 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_data_ready = xs_data_ready; sk->sk_write_space = xs_udp_write_space; sock_set_flag(sk, SOCK_FASYNC); - sk->sk_allocation = GFP_NOIO; xprt_set_connected(xprt); @@ -2244,7 +2265,6 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) sk->sk_write_space = xs_tcp_write_space; sock_set_flag(sk, SOCK_FASYNC); sk->sk_error_report = xs_error_report; - sk->sk_allocation = GFP_NOIO; /* socket options */ sock_reset_flag(sk, SOCK_LINGER); @@ -2264,8 +2284,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) xs_set_memalloc(xprt); - /* Reset TCP record info */ - xs_stream_reset_connect(transport); + xs_stream_start_connect(transport); /* Tell the socket layer to start connecting... */ set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); diff --git a/net/tipc/link.c b/net/tipc/link.c index 2792a3cae682..85ad5c0678d0 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1145,7 +1145,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); - return false; + return true; }; } @@ -1425,6 +1425,10 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ + if (mtyp == ACTIVATE_MSG) { + msg_set_dest_session_valid(hdr, 1); + msg_set_dest_session(hdr, l->peer_session); + } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); @@ -1642,6 +1646,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } + + /* If this endpoint was re-created while peer was ESTABLISHING + * it doesn't know current session number. Force re-synch. + */ + if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && + l->session != msg_dest_session(hdr)) { + if (less(l->session, msg_dest_session(hdr))) + l->session = msg_dest_session(hdr) + 1; + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a0924956bb61..d7e4b8b93f9d 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -360,6 +360,28 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) msg_set_bits(m, 1, 0, 0xffff, n); } +/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch + * link peer session number + */ +static inline bool msg_dest_session_valid(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0x1); +} + +static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) +{ + msg_set_bits(m, 1, 16, 0x1, valid); +} + +static inline u16 msg_dest_session(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} /* * Word 2 diff --git a/net/tipc/node.c b/net/tipc/node.c index db2a6c3e0be9..2dc4919ab23c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -830,15 +830,16 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_node_write_lock(n); if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); - if (delete) { - kfree(l); - le->link = NULL; - n->link_cnt--; - } } else { /* Defuse pending tipc_node_link_up() */ + tipc_link_reset(l); tipc_link_fsm_evt(l, LINK_RESET_EVT); } + if (delete) { + kfree(l); + le->link = NULL; + n->link_cnt--; + } trace_tipc_node_link_down(n, true, "node link down or deleted!"); tipc_node_write_unlock(n); if (delete) diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c361ce782412..c3d5ab01fba7 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work) static void vmci_transport_destruct(struct vsock_sock *vsk) { + /* transport can be NULL if we hit a failure at init() time */ + if (!vmci_trans(vsk)) + return; + /* Ensure that the detach callback doesn't use the sk/vsk * we are about to destruct. */ diff --git a/net/wireless/core.c b/net/wireless/core.c index 623dfe5e211c..b36ad8efb5e5 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1068,6 +1068,8 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) ASSERT_RTNL(); + flush_work(&wdev->pmsr_free_wk); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); list_del_rcu(&wdev->list); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 74150ad95823..d91a408db113 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -250,7 +250,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = - NLA_POLICY_MAX(NLA_U8, 15), + NLA_POLICY_MAX(NLA_U8, 31), [NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG }, diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index de9286703280..0216ab555249 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -256,8 +256,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) if (err) goto out_err; } else { - memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]), - ETH_ALEN); + memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN); memset(req->mac_addr_mask, 0xff, ETH_ALEN); } @@ -272,6 +271,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req->n_peers = count; req->cookie = cfg80211_assign_cookie(rdev); + req->nl_portid = info->snd_portid; err = rdev_start_pmsr(rdev, wdev, req); if (err) @@ -530,14 +530,14 @@ free: } EXPORT_SYMBOL_GPL(cfg80211_pmsr_report); -void cfg80211_pmsr_free_wk(struct work_struct *work) +static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) { - struct wireless_dev *wdev = container_of(work, struct wireless_dev, - pmsr_free_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *req, *tmp; LIST_HEAD(free_list); + lockdep_assert_held(&wdev->mtx); + spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) { if (req->nl_portid) @@ -547,14 +547,22 @@ void cfg80211_pmsr_free_wk(struct work_struct *work) spin_unlock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &free_list, list) { - wdev_lock(wdev); rdev_abort_pmsr(rdev, wdev, req); - wdev_unlock(wdev); kfree(req); } } +void cfg80211_pmsr_free_wk(struct work_struct *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + pmsr_free_wk); + + wdev_lock(wdev); + cfg80211_pmsr_process_abort(wdev); + wdev_unlock(wdev); +} + void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) { struct cfg80211_pmsr_request *req; @@ -568,8 +576,8 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) spin_unlock_bh(&wdev->pmsr_lock); if (found) - schedule_work(&wdev->pmsr_free_wk); - flush_work(&wdev->pmsr_free_wk); + cfg80211_pmsr_process_abort(wdev); + WARN_ON(!list_empty(&wdev->pmsr_list)); } diff --git a/net/wireless/util.c b/net/wireless/util.c index cd48cdd582c0..ec30e3732c7b 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -19,6 +19,7 @@ #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> +#include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" @@ -715,20 +716,25 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, { unsigned int dscp; unsigned char vlan_priority; + unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ - if (skb->priority >= 256 && skb->priority <= 263) - return skb->priority - 256; + if (skb->priority >= 256 && skb->priority <= 263) { + ret = skb->priority - 256; + goto out; + } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - if (vlan_priority > 0) - return vlan_priority; + if (vlan_priority > 0) { + ret = vlan_priority; + goto out; + } } switch (skb->protocol) { @@ -747,8 +753,9 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, if (!mpls) return 0; - return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; + goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ @@ -761,18 +768,24 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { - if (tmp_dscp == qos_map->dscp_exception[i].dscp) - return qos_map->dscp_exception[i].up; + if (tmp_dscp == qos_map->dscp_exception[i].dscp) { + ret = qos_map->dscp_exception[i].up; + goto out; + } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && - tmp_dscp <= qos_map->up[i].high) - return i; + tmp_dscp <= qos_map->up[i].high) { + ret = i; + goto out; + } } } - return dscp >> 5; + ret = dscp >> 5; +out: + return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5121729b8b63..ec3a828672ef 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) unsigned int lci = 1; struct sock *sk; - read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); } - read_unlock_bh(&x25_list_lock); return lci; } diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index d4de871e7d4d..37e1fe180769 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -125,9 +125,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; err_unreg_umem: - xdp_clear_umem_at_qid(dev, queue_id); if (!force_zc) err = 0; /* fallback to copy mode */ + if (err) + xdp_clear_umem_at_qid(dev, queue_id); out_rtnl_unlock: rtnl_unlock(); return err; @@ -259,10 +260,10 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem) if (!umem->pgs) return -ENOMEM; - down_write(¤t->mm->mmap_sem); - npgs = get_user_pages(umem->address, umem->npgs, - gup_flags, &umem->pgs[0], NULL); - up_write(¤t->mm->mmap_sem); + down_read(¤t->mm->mmap_sem); + npgs = get_user_pages_longterm(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_read(¤t->mm->mmap_sem); if (npgs != umem->npgs) { if (npgs >= 0) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a03268454a27..45f3b528dc09 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -669,6 +669,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!umem) return -EINVAL; + /* Matches the smp_wmb() in XDP_UMEM_REG */ + smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) q = READ_ONCE(umem->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) @@ -678,6 +680,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!q) return -EINVAL; + /* Matches the smp_wmb() in xsk_init_queue */ + smp_rmb(); qpg = virt_to_head_page(q->ring); if (size > (PAGE_SIZE << compound_order(qpg))) return -EINVAL; diff --git a/security/keys/internal.h b/security/keys/internal.h index 479909b858c7..8f533c81aa8d 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -186,20 +186,9 @@ static inline int key_permission(const key_ref_t key_ref, unsigned perm) return key_task_permission(key_ref, current_cred(), perm); } -/* - * Authorisation record for request_key(). - */ -struct request_key_auth { - struct key *target_key; - struct key *dest_keyring; - const struct cred *cred; - void *callout_info; - size_t callout_len; - pid_t pid; -} __randomize_layout; - extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, + const char *op, const void *callout_info, size_t callout_len, struct key *dest_keyring); diff --git a/security/keys/key.c b/security/keys/key.c index 44a80d6741a1..696f1c092c50 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -265,8 +265,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, spin_lock(&user->lock); if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) { - if (user->qnkeys + 1 >= maxkeys || - user->qnbytes + quotalen >= maxbytes || + if (user->qnkeys + 1 > maxkeys || + user->qnbytes + quotalen > maxbytes || user->qnbytes + quotalen < user->qnbytes) goto no_quota; } @@ -297,6 +297,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->gid = gid; key->perm = perm; key->restrict_link = restrict_link; + key->last_used_at = ktime_get_real_seconds(); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index e8093d025966..7bbe03593e58 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -25,6 +25,7 @@ #include <linux/security.h> #include <linux/uio.h> #include <linux/uaccess.h> +#include <keys/request_key_auth-type.h> #include "internal.h" #define KEY_MAX_DESC_SIZE 4096 diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 02c77e928f68..0e0b9ccad2f8 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> +#include <keys/request_key_auth-type.h> #include "internal.h" /* Session keyring create vs join semaphore */ diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 301f0e300dbd..3f56a312dd35 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -18,31 +18,30 @@ #include <linux/keyctl.h> #include <linux/slab.h> #include "internal.h" +#include <keys/request_key_auth-type.h> #define key_negative_timeout 60 /* default timeout on a negative key's existence */ /** * complete_request_key - Complete the construction of a key. - * @cons: The key construction record. + * @auth_key: The authorisation key. * @error: The success or failute of the construction. * * Complete the attempt to construct a key. The key will be negated * if an error is indicated. The authorisation key will be revoked * unconditionally. */ -void complete_request_key(struct key_construction *cons, int error) +void complete_request_key(struct key *authkey, int error) { - kenter("{%d,%d},%d", cons->key->serial, cons->authkey->serial, error); + struct request_key_auth *rka = get_request_key_auth(authkey); + struct key *key = rka->target_key; + + kenter("%d{%d},%d", authkey->serial, key->serial, error); if (error < 0) - key_negate_and_link(cons->key, key_negative_timeout, NULL, - cons->authkey); + key_negate_and_link(key, key_negative_timeout, NULL, authkey); else - key_revoke(cons->authkey); - - key_put(cons->key); - key_put(cons->authkey); - kfree(cons); + key_revoke(authkey); } EXPORT_SYMBOL(complete_request_key); @@ -91,21 +90,19 @@ static int call_usermodehelper_keys(const char *path, char **argv, char **envp, * Request userspace finish the construction of a key * - execute "/sbin/request-key <op> <key> <uid> <gid> <keyring> <keyring> <keyring>" */ -static int call_sbin_request_key(struct key_construction *cons, - const char *op, - void *aux) +static int call_sbin_request_key(struct key *authkey, void *aux) { static char const request_key[] = "/sbin/request-key"; + struct request_key_auth *rka = get_request_key_auth(authkey); const struct cred *cred = current_cred(); key_serial_t prkey, sskey; - struct key *key = cons->key, *authkey = cons->authkey, *keyring, - *session; + struct key *key = rka->target_key, *keyring, *session; char *argv[9], *envp[3], uid_str[12], gid_str[12]; char key_str[12], keyring_str[3][12]; char desc[20]; int ret, i; - kenter("{%d},{%d},%s", key->serial, authkey->serial, op); + kenter("{%d},{%d},%s", key->serial, authkey->serial, rka->op); ret = install_user_keyrings(); if (ret < 0) @@ -163,7 +160,7 @@ static int call_sbin_request_key(struct key_construction *cons, /* set up the argument list */ i = 0; argv[i++] = (char *)request_key; - argv[i++] = (char *) op; + argv[i++] = (char *)rka->op; argv[i++] = key_str; argv[i++] = uid_str; argv[i++] = gid_str; @@ -191,7 +188,7 @@ error_link: key_put(keyring); error_alloc: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); kleave(" = %d", ret); return ret; } @@ -205,42 +202,31 @@ static int construct_key(struct key *key, const void *callout_info, size_t callout_len, void *aux, struct key *dest_keyring) { - struct key_construction *cons; request_key_actor_t actor; struct key *authkey; int ret; kenter("%d,%p,%zu,%p", key->serial, callout_info, callout_len, aux); - cons = kmalloc(sizeof(*cons), GFP_KERNEL); - if (!cons) - return -ENOMEM; - /* allocate an authorisation key */ - authkey = request_key_auth_new(key, callout_info, callout_len, + authkey = request_key_auth_new(key, "create", callout_info, callout_len, dest_keyring); - if (IS_ERR(authkey)) { - kfree(cons); - ret = PTR_ERR(authkey); - authkey = NULL; - } else { - cons->authkey = key_get(authkey); - cons->key = key_get(key); + if (IS_ERR(authkey)) + return PTR_ERR(authkey); - /* make the call */ - actor = call_sbin_request_key; - if (key->type->request_key) - actor = key->type->request_key; + /* Make the call */ + actor = call_sbin_request_key; + if (key->type->request_key) + actor = key->type->request_key; - ret = actor(cons, "create", aux); + ret = actor(authkey, aux); - /* check that the actor called complete_request_key() prior to - * returning an error */ - WARN_ON(ret < 0 && - !test_bit(KEY_FLAG_REVOKED, &authkey->flags)); - key_put(authkey); - } + /* check that the actor called complete_request_key() prior to + * returning an error */ + WARN_ON(ret < 0 && + !test_bit(KEY_FLAG_REVOKED, &authkey->flags)); + key_put(authkey); kleave(" = %d", ret); return ret; } @@ -275,7 +261,7 @@ static int construct_get_dest_keyring(struct key **_dest_keyring) if (cred->request_key_auth) { authkey = cred->request_key_auth; down_read(&authkey->sem); - rka = authkey->payload.data[0]; + rka = get_request_key_auth(authkey); if (!test_bit(KEY_FLAG_REVOKED, &authkey->flags)) dest_keyring = diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index 87ea2f54dedc..afc304e8b61e 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include "internal.h" -#include <keys/user-type.h> +#include <keys/request_key_auth-type.h> static int request_key_auth_preparse(struct key_preparsed_payload *); static void request_key_auth_free_preparse(struct key_preparsed_payload *); @@ -68,7 +68,7 @@ static int request_key_auth_instantiate(struct key *key, static void request_key_auth_describe(const struct key *key, struct seq_file *m) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); seq_puts(m, "key:"); seq_puts(m, key->description); @@ -83,7 +83,7 @@ static void request_key_auth_describe(const struct key *key, static long request_key_auth_read(const struct key *key, char __user *buffer, size_t buflen) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); size_t datalen; long ret; @@ -109,7 +109,7 @@ static long request_key_auth_read(const struct key *key, */ static void request_key_auth_revoke(struct key *key) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); kenter("{%d}", key->serial); @@ -136,7 +136,7 @@ static void free_request_key_auth(struct request_key_auth *rka) */ static void request_key_auth_destroy(struct key *key) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); kenter("{%d}", key->serial); @@ -147,8 +147,9 @@ static void request_key_auth_destroy(struct key *key) * Create an authorisation token for /sbin/request-key or whoever to gain * access to the caller's security data. */ -struct key *request_key_auth_new(struct key *target, const void *callout_info, - size_t callout_len, struct key *dest_keyring) +struct key *request_key_auth_new(struct key *target, const char *op, + const void *callout_info, size_t callout_len, + struct key *dest_keyring) { struct request_key_auth *rka, *irka; const struct cred *cred = current->cred; @@ -166,6 +167,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, if (!rka->callout_info) goto error_free_rka; rka->callout_len = callout_len; + strlcpy(rka->op, op, sizeof(rka->op)); /* see if the calling process is already servicing the key request of * another process */ diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 6c99fa8ac5fa..6c0b30391ba9 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2112,13 +2112,6 @@ int pcm_lib_apply_appl_ptr(struct snd_pcm_substream *substream, return 0; } -/* allow waiting for a capture stream that hasn't been started */ -#if IS_ENABLED(CONFIG_SND_PCM_OSS) -#define wait_capture_start(substream) ((substream)->oss.oss) -#else -#define wait_capture_start(substream) false -#endif - /* the common loop for read/write data */ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, void *data, bool interleaved, @@ -2184,16 +2177,11 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, snd_pcm_update_hw_ptr(substream); if (!is_playback && - runtime->status->state == SNDRV_PCM_STATE_PREPARED) { - if (size >= runtime->start_threshold) { - err = snd_pcm_start(substream); - if (err < 0) - goto _end_unlock; - } else if (!wait_capture_start(substream)) { - /* nothing to do */ - err = 0; + runtime->status->state == SNDRV_PCM_STATE_PREPARED && + size >= runtime->start_threshold) { + err = snd_pcm_start(substream); + if (err < 0) goto _end_unlock; - } } avail = snd_pcm_avail(substream); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 152f54137082..a4ee7656d9ee 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -924,6 +924,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x83b2, "HP EliteBook 840 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83d3, "HP ProBook 640 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6df758adff84..1ffa36e987b4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1855,6 +1855,8 @@ enum { ALC887_FIXUP_BASS_CHMAP, ALC1220_FIXUP_GB_DUAL_CODECS, ALC1220_FIXUP_CLEVO_P950, + ALC1220_FIXUP_SYSTEM76_ORYP5, + ALC1220_FIXUP_SYSTEM76_ORYP5_PINS, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -2056,6 +2058,17 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec, snd_hda_override_conn_list(codec, 0x1b, 1, conn1); } +static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action); + +static void alc1220_fixup_system76_oryp5(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + alc1220_fixup_clevo_p950(codec, fix, action); + alc_fixup_headset_mode_no_hp_mic(codec, fix, action); +} + static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { .type = HDA_FIXUP_PINS, @@ -2300,6 +2313,19 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc1220_fixup_clevo_p950, }, + [ALC1220_FIXUP_SYSTEM76_ORYP5] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc1220_fixup_system76_oryp5, + }, + [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + {} + }, + .chained = true, + .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5, + }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2376,6 +2402,8 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), + SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), @@ -5632,6 +5660,7 @@ enum { ALC294_FIXUP_ASUS_SPK, ALC225_FIXUP_HEADSET_JACK, ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, + ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6587,6 +6616,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable PCBEEP-IN passthrough */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_LENOVO_HEADPHONE_NOISE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7272,7 +7312,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x19, 0x03a11020}, {0x21, 0x0321101f}), - SND_HDA_PIN_QUIRK(0x10ec0285, 0x17aa, "Lenovo", ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, + SND_HDA_PIN_QUIRK(0x10ec0285, 0x17aa, "Lenovo", ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, {0x12, 0x90a60130}, {0x14, 0x90170110}, {0x19, 0x04a11040}, diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index d00734d31e04..e5b6769b9797 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -795,6 +795,8 @@ static int hdmi_codec_probe(struct platform_device *pdev) if (hcd->spdif) hcp->daidrv[i] = hdmi_spdif_dai; + dev_set_drvdata(dev, hcp); + ret = devm_snd_soc_register_component(dev, &hdmi_driver, hcp->daidrv, dai_count); if (ret) { @@ -802,8 +804,6 @@ static int hdmi_codec_probe(struct platform_device *pdev) __func__, ret); return ret; } - - dev_set_drvdata(dev, hcp); return 0; } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 89c43b26c379..a9b91bcfcc09 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1778,7 +1778,9 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { {"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc}, {"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc}, {"ADC STO1 ASRC", NULL, "AD ASRC"}, + {"ADC STO1 ASRC", NULL, "DA ASRC"}, {"ADC STO1 ASRC", NULL, "CLKDET"}, + {"DAC STO1 ASRC", NULL, "AD ASRC"}, {"DAC STO1 ASRC", NULL, "DA ASRC"}, {"DAC STO1 ASRC", NULL, "CLKDET"}, diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 37e001cf9cd1..3fe34417ec89 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -462,7 +462,7 @@ static int asoc_simple_card_parse_of(struct simple_card_data *priv) conf_idx = 0; node = of_get_child_by_name(top, PREFIX "dai-link"); if (!node) { - node = dev->of_node; + node = of_node_get(top); loop = 0; } diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index d6c62aa13041..d4bde4834ce5 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -604,6 +604,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct i2s_dai *i2s = to_info(dai); + struct i2s_dai *other = get_other_dai(i2s); int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave; u32 mod, tmp = 0; unsigned long flags; @@ -661,7 +662,8 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, * CLK_I2S_RCLK_SRC clock is not exposed so we ensure any * clock configuration assigned in DT is not overwritten. */ - if (i2s->rclk_srcrate == 0 && i2s->clk_data.clks == NULL) + if (i2s->rclk_srcrate == 0 && i2s->clk_data.clks == NULL && + other->clk_data.clks == NULL) i2s_set_sysclk(dai, SAMSUNG_I2S_RCLKSRC_0, 0, SND_SOC_CLOCK_IN); break; @@ -699,7 +701,9 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); + struct i2s_dai *other = get_other_dai(i2s); u32 mod, mask = 0, val = 0; + struct clk *rclksrc; unsigned long flags; WARN_ON(!pm_runtime_active(dai->dev)); @@ -782,6 +786,13 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, i2s->frmclk = params_rate(params); + rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; + if (!rclksrc || IS_ERR(rclksrc)) + rclksrc = other->clk_table[CLK_I2S_RCLK_SRC]; + + if (rclksrc && !IS_ERR(rclksrc)) + i2s->rclk_srcrate = clk_get_rate(rclksrc); + return 0; } @@ -886,11 +897,6 @@ static int config_setup(struct i2s_dai *i2s) return 0; if (!(i2s->quirks & QUIRK_NO_MUXPSR)) { - struct clk *rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; - - if (rclksrc && !IS_ERR(rclksrc)) - i2s->rclk_srcrate = clk_get_rate(rclksrc); - psr = i2s->rclk_srcrate / i2s->frmclk / rfs; writel(((psr - 1) << 8) | PSR_PSREN, i2s->addr + I2SPSR); dev_dbg(&i2s->pdev->dev, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 59e250cc2e9d..e819e965e1db 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1526,14 +1526,14 @@ int rsnd_kctrl_new(struct rsnd_mod *mod, int ret; /* - * 1) Avoid duplicate register (ex. MIXer case) - * 2) re-register if card was rebinded + * 1) Avoid duplicate register for DVC with MIX case + * 2) Allow duplicate register for MIX + * 3) re-register if card was rebinded */ list_for_each_entry(kctrl, &card->controls, list) { struct rsnd_kctrl_cfg *c = kctrl->private_data; - if (strcmp(kctrl->id.name, name) == 0 && - c->mod == mod) + if (c == cfg) return 0; } diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 45ef295743ec..f5afab631abb 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -286,7 +286,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->usrcnt > 1) { + if (ssi->usrcnt > 0) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c index c5934adcfd01..c74991dd18ab 100644 --- a/sound/soc/sh/rcar/ssiu.c +++ b/sound/soc/sh/rcar/ssiu.c @@ -79,7 +79,7 @@ static int rsnd_ssiu_init(struct rsnd_mod *mod, break; case 9: for (i = 0; i < 4; i++) - rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << (id * 4)); + rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << 4); break; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index aae450ba4f08..50617db05c46 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -735,12 +735,17 @@ static struct snd_soc_component *soc_find_component( const struct device_node *of_node, const char *name) { struct snd_soc_component *component; + struct device_node *component_of_node; lockdep_assert_held(&client_mutex); for_each_component(component) { if (of_node) { - if (component->dev->of_node == of_node) + component_of_node = component->dev->of_node; + if (!component_of_node && component->dev->parent) + component_of_node = component->dev->parent->of_node; + + if (component_of_node == of_node) return component; } else if (name && strcmp(component->name, name) == 0) { return component; @@ -951,7 +956,7 @@ static void soc_remove_dai(struct snd_soc_dai *dai, int order) { int err; - if (!dai || !dai->probed || + if (!dai || !dai->probed || !dai->driver || dai->driver->remove_order != order) return; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 2c4c13419539..20bad755888b 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -70,12 +70,16 @@ static int dapm_up_seq[] = { [snd_soc_dapm_clock_supply] = 1, [snd_soc_dapm_supply] = 2, [snd_soc_dapm_micbias] = 3, + [snd_soc_dapm_vmid] = 3, [snd_soc_dapm_dai_link] = 2, [snd_soc_dapm_dai_in] = 4, [snd_soc_dapm_dai_out] = 4, [snd_soc_dapm_aif_in] = 4, [snd_soc_dapm_aif_out] = 4, [snd_soc_dapm_mic] = 5, + [snd_soc_dapm_siggen] = 5, + [snd_soc_dapm_input] = 5, + [snd_soc_dapm_output] = 5, [snd_soc_dapm_mux] = 6, [snd_soc_dapm_demux] = 6, [snd_soc_dapm_dac] = 7, @@ -83,11 +87,19 @@ static int dapm_up_seq[] = { [snd_soc_dapm_mixer] = 8, [snd_soc_dapm_mixer_named_ctl] = 8, [snd_soc_dapm_pga] = 9, + [snd_soc_dapm_buffer] = 9, + [snd_soc_dapm_scheduler] = 9, + [snd_soc_dapm_effect] = 9, + [snd_soc_dapm_src] = 9, + [snd_soc_dapm_asrc] = 9, + [snd_soc_dapm_encoder] = 9, + [snd_soc_dapm_decoder] = 9, [snd_soc_dapm_adc] = 10, [snd_soc_dapm_out_drv] = 11, [snd_soc_dapm_hp] = 11, [snd_soc_dapm_spk] = 11, [snd_soc_dapm_line] = 11, + [snd_soc_dapm_sink] = 11, [snd_soc_dapm_kcontrol] = 12, [snd_soc_dapm_post] = 13, }; @@ -100,13 +112,25 @@ static int dapm_down_seq[] = { [snd_soc_dapm_spk] = 3, [snd_soc_dapm_line] = 3, [snd_soc_dapm_out_drv] = 3, + [snd_soc_dapm_sink] = 3, [snd_soc_dapm_pga] = 4, + [snd_soc_dapm_buffer] = 4, + [snd_soc_dapm_scheduler] = 4, + [snd_soc_dapm_effect] = 4, + [snd_soc_dapm_src] = 4, + [snd_soc_dapm_asrc] = 4, + [snd_soc_dapm_encoder] = 4, + [snd_soc_dapm_decoder] = 4, [snd_soc_dapm_switch] = 5, [snd_soc_dapm_mixer_named_ctl] = 5, [snd_soc_dapm_mixer] = 5, [snd_soc_dapm_dac] = 6, [snd_soc_dapm_mic] = 7, + [snd_soc_dapm_siggen] = 7, + [snd_soc_dapm_input] = 7, + [snd_soc_dapm_output] = 7, [snd_soc_dapm_micbias] = 8, + [snd_soc_dapm_vmid] = 8, [snd_soc_dapm_mux] = 9, [snd_soc_dapm_demux] = 9, [snd_soc_dapm_aif_in] = 10, diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 045ef136903d..731b963b6995 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -502,6 +502,7 @@ static void remove_dai(struct snd_soc_component *comp, { struct snd_soc_dai_driver *dai_drv = container_of(dobj, struct snd_soc_dai_driver, dobj); + struct snd_soc_dai *dai; if (pass != SOC_TPLG_PASS_PCM_DAI) return; @@ -509,6 +510,10 @@ static void remove_dai(struct snd_soc_component *comp, if (dobj->ops && dobj->ops->dai_unload) dobj->ops->dai_unload(comp, dobj); + list_for_each_entry(dai, &comp->dai_list, list) + if (dai->driver == dai_drv) + dai->driver = NULL; + kfree(dai_drv->name); list_del(&dobj->list); kfree(dai_drv); @@ -2482,6 +2487,7 @@ int snd_soc_tplg_component_load(struct snd_soc_component *comp, struct snd_soc_tplg_ops *ops, const struct firmware *fw, u32 id) { struct soc_tplg tplg; + int ret; /* setup parsing context */ memset(&tplg, 0, sizeof(tplg)); @@ -2495,7 +2501,12 @@ int snd_soc_tplg_component_load(struct snd_soc_component *comp, tplg.bytes_ext_ops = ops->bytes_ext_ops; tplg.bytes_ext_ops_count = ops->bytes_ext_ops_count; - return soc_tplg_load(&tplg); + ret = soc_tplg_load(&tplg); + /* free the created components if fail to load topology */ + if (ret) + snd_soc_tplg_component_remove(comp, SND_SOC_TPLG_INDEX_ALL); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_tplg_component_load); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 382847154227..db114f3977e0 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -314,6 +314,9 @@ static int search_roland_implicit_fb(struct usb_device *dev, int ifnum, return 0; } +/* Setup an implicit feedback endpoint from a quirk. Returns 0 if no quirk + * applies. Returns 1 if a quirk was found. + */ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, struct usb_device *dev, struct usb_interface_descriptor *altsd, @@ -384,7 +387,7 @@ add_sync_ep: subs->data_endpoint->sync_master = subs->sync_endpoint; - return 0; + return 1; } static int set_sync_endpoint(struct snd_usb_substream *subs, @@ -423,6 +426,10 @@ static int set_sync_endpoint(struct snd_usb_substream *subs, if (err < 0) return err; + /* endpoint set by quirk */ + if (err > 0) + return 0; + if (altsd->bNumEndpoints < 2) return 0; diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h index fd92ce8388fc..57aaeaf8e192 100644 --- a/tools/include/uapi/asm/bitsperlong.h +++ b/tools/include/uapi/asm/bitsperlong.h @@ -15,6 +15,8 @@ #include "../../arch/ia64/include/uapi/asm/bitsperlong.h" #elif defined(__riscv) #include "../../arch/riscv/include/uapi/asm/bitsperlong.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/bitsperlong.h" #else #include <asm-generic/bitsperlong.h> #endif diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index 9050eeea5f5f..1de8bd8ccf5d 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -9,6 +9,3 @@ all: $(TEST_PROGS) top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 include ../../lib.mk - -clean: - rm -fr $(TEST_GEN_FILES) 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; } - |