diff --git a/Makefile b/Makefile index 63b0bc92a0fa6..42073a4c6e2e3 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 19 -SUBLEVEL = 196 +SUBLEVEL = 197 EXTRAVERSION = NAME = "People's Front" diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 0c0781a37c5a7..7f1fe4a724472 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -48,6 +48,7 @@ timer { compatible = "arm,armv7-timer"; + status = "disabled"; /* See ARM architected timer wrap erratum i940 */ interrupts = , , , @@ -910,6 +911,8 @@ reg = <0x48032000 0x80>; interrupts = ; ti,hwmods = "timer2"; + clock-names = "fck"; + clocks = <&l4per_clkctrl DRA7_TIMER2_CLKCTRL 24>; }; timer3: timer@48034000 { @@ -917,6 +920,10 @@ reg = <0x48034000 0x80>; interrupts = ; ti,hwmods = "timer3"; + clock-names = "fck"; + clocks = <&l4per_clkctrl DRA7_TIMER3_CLKCTRL 24>; + assigned-clocks = <&l4per_clkctrl DRA7_TIMER3_CLKCTRL 24>; + assigned-clock-parents = <&timer_sys_clk_div>; }; timer4: timer@48036000 { @@ -924,6 +931,10 @@ reg = <0x48036000 0x80>; interrupts = ; ti,hwmods = "timer4"; + clock-names = "fck"; + clocks = <&l4per_clkctrl DRA7_TIMER4_CLKCTRL 24>; + assigned-clocks = <&l4per_clkctrl DRA7_TIMER4_CLKCTRL 24>; + assigned-clock-parents = <&timer_sys_clk_div>; }; timer5: timer@48820000 { diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi index 41384bbd2f60c..03357d39870ee 100644 --- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi @@ -675,10 +675,6 @@ vin-supply = <&vgen5_reg>; }; -®_vdd3p0 { - vin-supply = <&sw2_reg>; -}; - ®_vdd2p5 { vin-supply = <&vgen5_reg>; }; diff --git a/arch/arm/mach-omap1/pm.c b/arch/arm/mach-omap1/pm.c index 3e1de14805e48..65b91a8379c90 100644 --- a/arch/arm/mach-omap1/pm.c +++ b/arch/arm/mach-omap1/pm.c @@ -610,11 +610,6 @@ static irqreturn_t omap_wakeup_interrupt(int irq, void *dev) return IRQ_HANDLED; } -static struct irqaction omap_wakeup_irq = { - .name = "peripheral wakeup", - .handler = omap_wakeup_interrupt -}; - static const struct platform_suspend_ops omap_pm_ops = { @@ -627,6 +622,7 @@ static const struct platform_suspend_ops omap_pm_ops = { static int __init omap_pm_init(void) { int error = 0; + int irq; if (!cpu_class_is_omap1()) return -ENODEV; @@ -670,9 +666,12 @@ static int __init omap_pm_init(void) arm_pm_idle = omap1_pm_idle; if (cpu_is_omap7xx()) - setup_irq(INT_7XX_WAKE_UP_REQ, &omap_wakeup_irq); + irq = INT_7XX_WAKE_UP_REQ; else if (cpu_is_omap16xx()) - setup_irq(INT_1610_WAKE_UP_REQ, &omap_wakeup_irq); + irq = INT_1610_WAKE_UP_REQ; + if (request_irq(irq, omap_wakeup_interrupt, 0, "peripheral wakeup", + NULL)) + pr_err("Failed to request irq %d (peripheral wakeup)\n", irq); /* Program new power ramp-up time * (0 for most boards since we don't lower voltage when in deep sleep) diff --git a/arch/arm/mach-omap1/time.c b/arch/arm/mach-omap1/time.c index 524977a31a49c..de590a85a42b3 100644 --- a/arch/arm/mach-omap1/time.c +++ b/arch/arm/mach-omap1/time.c @@ -155,15 +155,11 @@ static irqreturn_t omap_mpu_timer1_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction omap_mpu_timer1_irq = { - .name = "mpu_timer1", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = omap_mpu_timer1_interrupt, -}; - static __init void omap_init_mpu_timer(unsigned long rate) { - setup_irq(INT_TIMER1, &omap_mpu_timer1_irq); + if (request_irq(INT_TIMER1, omap_mpu_timer1_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, "mpu_timer1", NULL)) + pr_err("Failed to request irq %d (mpu_timer1)\n", INT_TIMER1); omap_mpu_timer_start(0, (rate / HZ) - 1, 1); clockevent_mpu_timer1.cpumask = cpumask_of(0); diff --git a/arch/arm/mach-omap1/timer32k.c b/arch/arm/mach-omap1/timer32k.c index 0ae6c52a7d70b..780fdf03c3cee 100644 --- a/arch/arm/mach-omap1/timer32k.c +++ b/arch/arm/mach-omap1/timer32k.c @@ -148,15 +148,11 @@ static irqreturn_t omap_32k_timer_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irqaction omap_32k_timer_irq = { - .name = "32KHz timer", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = omap_32k_timer_interrupt, -}; - static __init void omap_init_32k_timer(void) { - setup_irq(INT_OS_TIMER, &omap_32k_timer_irq); + if (request_irq(INT_OS_TIMER, omap_32k_timer_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, "32KHz timer", NULL)) + pr_err("Failed to request irq %d(32KHz timer)\n", INT_OS_TIMER); clockevent_32k_timer.cpumask = cpumask_of(0); clockevents_config_and_register(&clockevent_32k_timer, diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 6b4f4975cf7a6..6e59c11131c48 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -330,7 +330,7 @@ DT_MACHINE_START(DRA74X_DT, "Generic DRA74X (Flattened Device Tree)") .init_late = dra7xx_init_late, .init_irq = omap_gic_of_init, .init_machine = omap_generic_init, - .init_time = omap5_realtime_timer_init, + .init_time = omap3_gptimer_timer_init, .dt_compat = dra74x_boards_compat, .restart = omap44xx_restart, MACHINE_END @@ -353,7 +353,7 @@ DT_MACHINE_START(DRA72X_DT, "Generic DRA72X (Flattened Device Tree)") .init_late = dra7xx_init_late, .init_irq = omap_gic_of_init, .init_machine = omap_generic_init, - .init_time = omap5_realtime_timer_init, + .init_time = omap3_gptimer_timer_init, .dt_compat = dra72x_boards_compat, .restart = omap44xx_restart, MACHINE_END diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index 98ed5ac073bc1..c4ba848e8af62 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -64,15 +65,28 @@ /* Clockevent code */ -static struct omap_dm_timer clkev; -static struct clock_event_device clockevent_gpt; - /* Clockevent hwmod for am335x and am437x suspend */ static struct omap_hwmod *clockevent_gpt_hwmod; /* Clockesource hwmod for am437x suspend */ static struct omap_hwmod *clocksource_gpt_hwmod; +struct dmtimer_clockevent { + struct clock_event_device dev; + struct omap_dm_timer timer; +}; + +static struct dmtimer_clockevent clockevent; + +static struct omap_dm_timer *to_dmtimer(struct clock_event_device *clockevent) +{ + struct dmtimer_clockevent *clkevt = + container_of(clockevent, struct dmtimer_clockevent, dev); + struct omap_dm_timer *timer = &clkevt->timer; + + return timer; +} + #ifdef CONFIG_SOC_HAS_REALTIME_COUNTER static unsigned long arch_timer_freq; @@ -84,24 +98,21 @@ void set_cntfreq(void) static irqreturn_t omap2_gp_timer_interrupt(int irq, void *dev_id) { - struct clock_event_device *evt = &clockevent_gpt; - - __omap_dm_timer_write_status(&clkev, OMAP_TIMER_INT_OVERFLOW); + struct dmtimer_clockevent *clkevt = dev_id; + struct clock_event_device *evt = &clkevt->dev; + struct omap_dm_timer *timer = &clkevt->timer; + __omap_dm_timer_write_status(timer, OMAP_TIMER_INT_OVERFLOW); evt->event_handler(evt); return IRQ_HANDLED; } -static struct irqaction omap2_gp_timer_irq = { - .name = "gp_timer", - .flags = IRQF_TIMER | IRQF_IRQPOLL, - .handler = omap2_gp_timer_interrupt, -}; - static int omap2_gp_timer_set_next_event(unsigned long cycles, struct clock_event_device *evt) { - __omap_dm_timer_load_start(&clkev, OMAP_TIMER_CTRL_ST, + struct omap_dm_timer *timer = to_dmtimer(evt); + + __omap_dm_timer_load_start(timer, OMAP_TIMER_CTRL_ST, 0xffffffff - cycles, OMAP_TIMER_POSTED); return 0; @@ -109,22 +120,26 @@ static int omap2_gp_timer_set_next_event(unsigned long cycles, static int omap2_gp_timer_shutdown(struct clock_event_device *evt) { - __omap_dm_timer_stop(&clkev, OMAP_TIMER_POSTED, clkev.rate); + struct omap_dm_timer *timer = to_dmtimer(evt); + + __omap_dm_timer_stop(timer, OMAP_TIMER_POSTED, timer->rate); + return 0; } static int omap2_gp_timer_set_periodic(struct clock_event_device *evt) { + struct omap_dm_timer *timer = to_dmtimer(evt); u32 period; - __omap_dm_timer_stop(&clkev, OMAP_TIMER_POSTED, clkev.rate); + __omap_dm_timer_stop(timer, OMAP_TIMER_POSTED, timer->rate); - period = clkev.rate / HZ; + period = timer->rate / HZ; period -= 1; /* Looks like we need to first set the load value separately */ - __omap_dm_timer_write(&clkev, OMAP_TIMER_LOAD_REG, 0xffffffff - period, + __omap_dm_timer_write(timer, OMAP_TIMER_LOAD_REG, 0xffffffff - period, OMAP_TIMER_POSTED); - __omap_dm_timer_load_start(&clkev, + __omap_dm_timer_load_start(timer, OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST, 0xffffffff - period, OMAP_TIMER_POSTED); return 0; @@ -138,25 +153,16 @@ static void omap_clkevt_idle(struct clock_event_device *unused) omap_hwmod_idle(clockevent_gpt_hwmod); } -static void omap_clkevt_unidle(struct clock_event_device *unused) +static void omap_clkevt_unidle(struct clock_event_device *evt) { + struct omap_dm_timer *timer = to_dmtimer(evt); + if (!clockevent_gpt_hwmod) return; omap_hwmod_enable(clockevent_gpt_hwmod); - __omap_dm_timer_int_enable(&clkev, OMAP_TIMER_INT_OVERFLOW); -} - -static struct clock_event_device clockevent_gpt = { - .features = CLOCK_EVT_FEAT_PERIODIC | - CLOCK_EVT_FEAT_ONESHOT, - .rating = 300, - .set_next_event = omap2_gp_timer_set_next_event, - .set_state_shutdown = omap2_gp_timer_shutdown, - .set_state_periodic = omap2_gp_timer_set_periodic, - .set_state_oneshot = omap2_gp_timer_shutdown, - .tick_resume = omap2_gp_timer_shutdown, -}; + __omap_dm_timer_int_enable(timer, OMAP_TIMER_INT_OVERFLOW); +} static const struct of_device_id omap_timer_match[] __initconst = { { .compatible = "ti,omap2420-timer", }, @@ -363,47 +369,104 @@ void tick_broadcast(const struct cpumask *mask) } #endif -static void __init omap2_gp_clockevent_init(int gptimer_id, - const char *fck_source, - const char *property) +static void __init dmtimer_clkevt_init_common(struct dmtimer_clockevent *clkevt, + int gptimer_id, + const char *fck_source, + unsigned int features, + const struct cpumask *cpumask, + const char *property, + int rating, const char *name) { + struct omap_dm_timer *timer = &clkevt->timer; int res; - clkev.id = gptimer_id; - clkev.errata = omap_dm_timer_get_errata(); + timer->id = gptimer_id; + timer->errata = omap_dm_timer_get_errata(); + clkevt->dev.features = features; + clkevt->dev.rating = rating; + clkevt->dev.set_next_event = omap2_gp_timer_set_next_event; + clkevt->dev.set_state_shutdown = omap2_gp_timer_shutdown; + clkevt->dev.set_state_periodic = omap2_gp_timer_set_periodic; + clkevt->dev.set_state_oneshot = omap2_gp_timer_shutdown; + clkevt->dev.tick_resume = omap2_gp_timer_shutdown; /* * For clock-event timers we never read the timer counter and * so we are not impacted by errata i103 and i767. Therefore, * we can safely ignore this errata for clock-event timers. */ - __omap_dm_timer_override_errata(&clkev, OMAP_TIMER_ERRATA_I103_I767); + __omap_dm_timer_override_errata(timer, OMAP_TIMER_ERRATA_I103_I767); - res = omap_dm_timer_init_one(&clkev, fck_source, property, - &clockevent_gpt.name, OMAP_TIMER_POSTED); + res = omap_dm_timer_init_one(timer, fck_source, property, + &clkevt->dev.name, OMAP_TIMER_POSTED); BUG_ON(res); - omap2_gp_timer_irq.dev_id = &clkev; - setup_irq(clkev.irq, &omap2_gp_timer_irq); + clkevt->dev.cpumask = cpumask; + clkevt->dev.irq = omap_dm_timer_get_irq(timer); - __omap_dm_timer_int_enable(&clkev, OMAP_TIMER_INT_OVERFLOW); + if (request_irq(clkevt->dev.irq, omap2_gp_timer_interrupt, + IRQF_TIMER | IRQF_IRQPOLL, name, clkevt)) + pr_err("Failed to request irq %d (gp_timer)\n", clkevt->dev.irq); - clockevent_gpt.cpumask = cpu_possible_mask; - clockevent_gpt.irq = omap_dm_timer_get_irq(&clkev); - clockevents_config_and_register(&clockevent_gpt, clkev.rate, - 3, /* Timer internal resynch latency */ - 0xffffffff); + __omap_dm_timer_int_enable(timer, OMAP_TIMER_INT_OVERFLOW); if (soc_is_am33xx() || soc_is_am43xx()) { - clockevent_gpt.suspend = omap_clkevt_idle; - clockevent_gpt.resume = omap_clkevt_unidle; + clkevt->dev.suspend = omap_clkevt_idle; + clkevt->dev.resume = omap_clkevt_unidle; clockevent_gpt_hwmod = - omap_hwmod_lookup(clockevent_gpt.name); + omap_hwmod_lookup(clkevt->dev.name); + } + + pr_info("OMAP clockevent source: %s at %lu Hz\n", clkevt->dev.name, + timer->rate); +} + +static DEFINE_PER_CPU(struct dmtimer_clockevent, dmtimer_percpu_timer); + +static int omap_gptimer_starting_cpu(unsigned int cpu) +{ + struct dmtimer_clockevent *clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu); + struct clock_event_device *dev = &clkevt->dev; + struct omap_dm_timer *timer = &clkevt->timer; + + clockevents_config_and_register(dev, timer->rate, 3, ULONG_MAX); + irq_force_affinity(dev->irq, cpumask_of(cpu)); + + return 0; +} + +static int __init dmtimer_percpu_quirk_init(void) +{ + struct dmtimer_clockevent *clkevt; + struct clock_event_device *dev; + struct device_node *arm_timer; + struct omap_dm_timer *timer; + int cpu = 0; + + arm_timer = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); + if (of_device_is_available(arm_timer)) { + pr_warn_once("ARM architected timer wrap issue i940 detected\n"); + return 0; + } + + for_each_possible_cpu(cpu) { + clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu); + dev = &clkevt->dev; + timer = &clkevt->timer; + + dmtimer_clkevt_init_common(clkevt, 0, "timer_sys_ck", + CLOCK_EVT_FEAT_ONESHOT, + cpumask_of(cpu), + "assigned-clock-parents", + 500, "percpu timer"); } - pr_info("OMAP clockevent source: %s at %lu Hz\n", clockevent_gpt.name, - clkev.rate); + cpuhp_setup_state(CPUHP_AP_OMAP_DM_TIMER_STARTING, + "clockevents/omap/gptimer:starting", + omap_gptimer_starting_cpu, NULL); + + return 0; } /* Clocksource code */ @@ -543,7 +606,15 @@ static void __init __omap_sync32k_timer_init(int clkev_nr, const char *clkev_src { omap_clk_init(); omap_dmtimer_init(); - omap2_gp_clockevent_init(clkev_nr, clkev_src, clkev_prop); + dmtimer_clkevt_init_common(&clockevent, clkev_nr, clkev_src, + CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT, + cpu_possible_mask, clkev_prop, 300, "clockevent"); + clockevents_config_and_register(&clockevent.dev, clockevent.timer.rate, + 3, /* Timer internal resynch latency */ + 0xffffffff); + + if (soc_is_dra7xx()) + dmtimer_percpu_quirk_init(); /* Enable the use of clocksource="gp_timer" kernel parameter */ if (use_gptimer_clksrc || gptimer) @@ -572,7 +643,7 @@ void __init omap3_secure_sync32k_timer_init(void) #endif /* CONFIG_ARCH_OMAP3 */ #if defined(CONFIG_ARCH_OMAP3) || defined(CONFIG_SOC_AM33XX) || \ - defined(CONFIG_SOC_AM43XX) + defined(CONFIG_SOC_AM43XX) || defined(CONFIG_SOC_DRA7XX) void __init omap3_gptimer_timer_init(void) { __omap_sync32k_timer_init(2, "timer_sys_ck", NULL, diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index ad24e67772778..bd463d6842370 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1791,9 +1791,25 @@ static void sev_asid_free(struct kvm *kvm) __sev_asid_free(sev->asid); } -static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +static void sev_decommission(unsigned int handle) { struct sev_data_decommission *decommission; + + if (!handle) + return; + + decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); + if (!decommission) + return; + + decommission->handle = handle; + sev_guest_decommission(decommission, NULL); + + kfree(decommission); +} + +static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) +{ struct sev_data_deactivate *data; if (!handle) @@ -1811,15 +1827,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) sev_guest_df_flush(NULL); kfree(data); - decommission = kzalloc(sizeof(*decommission), GFP_KERNEL); - if (!decommission) - return; - - /* decommission handle */ - decommission->handle = handle; - sev_guest_decommission(decommission, NULL); - - kfree(decommission); + sev_decommission(handle); } static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, @@ -1954,6 +1962,7 @@ static void sev_vm_destroy(struct kvm *kvm) list_for_each_safe(pos, q, head) { __unregister_enc_region_locked(kvm, list_entry(pos, struct enc_region, list)); + cond_resched(); } } @@ -6468,8 +6477,10 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Bind ASID to this guest */ ret = sev_bind_asid(kvm, start->handle, error); - if (ret) + if (ret) { + sev_decommission(start->handle); goto e_free_session; + } /* return handle to userspace */ params.handle = start->handle; diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c index 71a122b2dc67e..b6d1ec49fa01a 100644 --- a/drivers/clk/ti/clk-7xx.c +++ b/drivers/clk/ti/clk-7xx.c @@ -733,6 +733,7 @@ const struct omap_clkctrl_data dra7_clkctrl_data[] __initconst = { static struct ti_dt_clk dra7xx_clks[] = { DT_CLK(NULL, "timer_32k_ck", "sys_32k_ck"), DT_CLK(NULL, "sys_clkin_ck", "timer_sys_clk_div"), + DT_CLK(NULL, "timer_sys_ck", "timer_sys_clk_div"), DT_CLK(NULL, "sys_clkin", "sys_clkin1"), DT_CLK(NULL, "atl_dpll_clk_mux", "atl_cm:0000:24"), DT_CLK(NULL, "atl_gfclk_mux", "atl_cm:0000:26"), diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7214022dfb911..d230536e7086d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -512,7 +512,7 @@ nouveau_bo_sync_for_device(struct nouveau_bo *nvbo) struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm; int i; - if (!ttm_dma) + if (!ttm_dma || !ttm_dma->dma_address) return; /* Don't waste time looping if the object is coherent */ @@ -532,7 +532,7 @@ nouveau_bo_sync_for_cpu(struct nouveau_bo *nvbo) struct ttm_dma_tt *ttm_dma = (struct ttm_dma_tt *)nvbo->bo.ttm; int i; - if (!ttm_dma) + if (!ttm_dma || !ttm_dma->dma_address) return; /* Don't waste time looping if the object is coherent */ diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 45c8bf39ad238..acf0c244141f4 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -216,6 +216,8 @@ static unsigned int sr_get_events(struct scsi_device *sdev) return DISK_EVENT_EJECT_REQUEST; else if (med->media_event_code == 2) return DISK_EVENT_MEDIA_CHANGE; + else if (med->media_event_code == 3) + return DISK_EVENT_EJECT_REQUEST; return 0; } diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index b370144682ed5..a2f8130e18fec 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -524,6 +524,9 @@ static void xen_irq_lateeoi_locked(struct irq_info *info, bool spurious) } info->eoi_time = 0; + + /* is_active hasn't been reset yet, do it now. */ + smp_store_release(&info->is_active, 0); do_unmask(info, EVT_MASK_REASON_EOI_PENDING); } @@ -1780,10 +1783,22 @@ static void lateeoi_ack_dynirq(struct irq_data *data) struct irq_info *info = info_for_irq(data->irq); evtchn_port_t evtchn = info ? info->evtchn : 0; - if (VALID_EVTCHN(evtchn)) { - do_mask(info, EVT_MASK_REASON_EOI_PENDING); - ack_dynirq(data); - } + if (!VALID_EVTCHN(evtchn)) + return; + + do_mask(info, EVT_MASK_REASON_EOI_PENDING); + + if (unlikely(irqd_is_setaffinity_pending(data)) && + likely(!irqd_irq_disabled(data))) { + do_mask(info, EVT_MASK_REASON_TEMPORARY); + + clear_evtchn(evtchn); + + irq_move_masked_irq(data); + + do_unmask(info, EVT_MASK_REASON_TEMPORARY); + } else + clear_evtchn(evtchn); } static void lateeoi_mask_ack_dynirq(struct irq_data *data) diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 1ea8fc9ff048f..1bc65ecd4bd6d 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -171,8 +171,10 @@ static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, else if (start_blk >= (entry->start_blk + entry->count)) n = n->rb_right; else { + if (entry->ino == ino) + return 1; sbi->s_es->s_last_error_block = cpu_to_le64(start_blk); - return entry->ino == ino; + return 0; } } return 1; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d67c0035165c2..3d323c6c85260 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -118,6 +118,7 @@ enum cpuhp_state { CPUHP_AP_ARM_L2X0_STARTING, CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING, CPUHP_AP_ARM_ARCH_TIMER_STARTING, + CPUHP_AP_OMAP_DM_TIMER_STARTING, CPUHP_AP_ARM_GLOBAL_TIMER_STARTING, CPUHP_AP_JCORE_TIMER_STARTING, CPUHP_AP_ARM_TWD_STARTING, diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index e375f2249f520..becf9b1eae5a1 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -224,6 +224,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; +extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { @@ -232,7 +233,7 @@ static inline bool is_huge_zero_page(struct page *page) static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_page(pmd_page(pmd)); + return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) @@ -342,6 +343,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; } +static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return false; +} + static inline bool is_huge_zero_pud(pud_t pud) { return false; diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c129c1c14c5f2..2df83a6598182 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -477,17 +477,6 @@ static inline int hstate_index(struct hstate *h) return h - hstates; } -pgoff_t __basepage_index(struct page *page); - -/* Return page->index in PAGE_SIZE units */ -static inline pgoff_t basepage_index(struct page *page) -{ - if (!PageCompound(page)) - return page->index; - - return __basepage_index(page); -} - extern int dissolve_free_huge_page(struct page *page); extern int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn); @@ -582,11 +571,6 @@ static inline int hstate_index(struct hstate *h) return 0; } -static inline pgoff_t basepage_index(struct page *page) -{ - return page->index; -} - static inline int dissolve_free_huge_page(struct page *page) { return 0; diff --git a/include/linux/mm.h b/include/linux/mm.h index f6ecf41aea83d..c736c677b876d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1338,6 +1338,7 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ + struct page *single_page; /* Locked page to be unmapped */ }; struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1428,6 +1429,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); +void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1448,6 +1450,7 @@ static inline int fixup_user_fault(struct task_struct *tsk, BUG(); return -EFAULT; } +static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 2ad72d2c8cc52..5d0767cb424aa 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -37,6 +37,18 @@ void dump_mm(const struct mm_struct *mm); BUG(); \ } \ } while (0) +#define VM_WARN_ON_ONCE_PAGE(cond, page) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + dump_page(page, "VM_WARN_ON_ONCE_PAGE(" __stringify(cond)")");\ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) + #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) #define VM_WARN_ONCE(cond, format...) (void)WARN_ONCE(cond, format) @@ -48,6 +60,7 @@ void dump_mm(const struct mm_struct *mm); #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond) #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b1bd2186e6d2b..33b63b2a163f9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -403,7 +403,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping, } /* - * Get index of the page with in radix-tree + * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_index(struct page *page) @@ -422,15 +422,16 @@ static inline pgoff_t page_to_index(struct page *page) return pgoff; } +extern pgoff_t hugetlb_basepage_index(struct page *page); + /* - * Get the offset in PAGE_SIZE. - * (TODO: hugepage should have ->index in PAGE_SIZE) + * Get the offset in PAGE_SIZE (even for hugetlb pages). + * (TODO: hugetlb pages should have ->index in PAGE_SIZE) */ static inline pgoff_t page_to_pgoff(struct page *page) { - if (unlikely(PageHeadHuge(page))) - return page->index << compound_order(page); - + if (unlikely(PageHuge(page))) + return hugetlb_basepage_index(page); return page_to_index(page); } diff --git a/include/linux/rmap.h b/include/linux/rmap.h index d7d6d4eb17949..91ccae9467164 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -98,7 +98,8 @@ enum ttu_flags { * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ - TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ + TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ + TTU_SYNC = 0x200, /* avoid racy checks with PVMW_SYNC */ }; #ifdef CONFIG_MMU diff --git a/kernel/futex.c b/kernel/futex.c index 526ebcff5a0a9..3c67da9b84086 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -719,7 +719,7 @@ again: key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.i_seq = get_inode_sequence_number(inode); - key->shared.pgoff = basepage_index(tail); + key->shared.pgoff = page_to_pgoff(tail); rcu_read_unlock(); } diff --git a/kernel/kthread.c b/kernel/kthread.c index 81abfac351272..9750f4f7f9010 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -1010,8 +1010,38 @@ void kthread_flush_work(struct kthread_work *work) EXPORT_SYMBOL_GPL(kthread_flush_work); /* - * This function removes the work from the worker queue. Also it makes sure - * that it won't get queued later via the delayed work's timer. + * Make sure that the timer is neither set nor running and could + * not manipulate the work list_head any longer. + * + * The function is called under worker->lock. The lock is temporary + * released but the timer can't be set again in the meantime. + */ +static void kthread_cancel_delayed_work_timer(struct kthread_work *work, + unsigned long *flags) +{ + struct kthread_delayed_work *dwork = + container_of(work, struct kthread_delayed_work, work); + struct kthread_worker *worker = work->worker; + + /* + * del_timer_sync() must be called to make sure that the timer + * callback is not running. The lock must be temporary released + * to avoid a deadlock with the callback. In the meantime, + * any queuing is blocked by setting the canceling counter. + */ + work->canceling++; + spin_unlock_irqrestore(&worker->lock, *flags); + del_timer_sync(&dwork->timer); + spin_lock_irqsave(&worker->lock, *flags); + work->canceling--; +} + +/* + * This function removes the work from the worker queue. + * + * It is called under worker->lock. The caller must make sure that + * the timer used by delayed work is not running, e.g. by calling + * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. @@ -1019,28 +1049,8 @@ EXPORT_SYMBOL_GPL(kthread_flush_work); * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ -static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, - unsigned long *flags) +static bool __kthread_cancel_work(struct kthread_work *work) { - /* Try to cancel the timer if exists. */ - if (is_dwork) { - struct kthread_delayed_work *dwork = - container_of(work, struct kthread_delayed_work, work); - struct kthread_worker *worker = work->worker; - - /* - * del_timer_sync() must be called to make sure that the timer - * callback is not running. The lock must be temporary released - * to avoid a deadlock with the callback. In the meantime, - * any queuing is blocked by setting the canceling counter. - */ - work->canceling++; - spin_unlock_irqrestore(&worker->lock, *flags); - del_timer_sync(&dwork->timer); - spin_lock_irqsave(&worker->lock, *flags); - work->canceling--; - } - /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. @@ -1093,11 +1103,23 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); - /* Do not fight with another command that is canceling this work. */ + /* + * Temporary cancel the work but do not fight with another command + * that is canceling the work as well. + * + * It is a bit tricky because of possible races with another + * mod_delayed_work() and cancel_delayed_work() callers. + * + * The timer must be canceled first because worker->lock is released + * when doing so. But the work can be removed from the queue (list) + * only when it can be queued again so that the return value can + * be used for reference counting. + */ + kthread_cancel_delayed_work_timer(work, &flags); if (work->canceling) goto out; + ret = __kthread_cancel_work(work); - ret = __kthread_cancel_work(work, true, &flags); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: @@ -1119,7 +1141,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); - ret = __kthread_cancel_work(work, is_dwork, &flags); + if (is_dwork) + kthread_cancel_delayed_work_timer(work, &flags); + + ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 7c374c0fcf0c7..4400957d8e4e2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL; bool transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -93,6 +94,7 @@ retry: __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -142,6 +144,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -2125,7 +2128,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { - _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it @@ -2134,16 +2137,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, zap_deposited_table(mm, pmd); if (vma_is_dax(vma)) return; - page = pmd_page(_pmd); - if (!PageDirty(page) && pmd_dirty(_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(_pmd)) - SetPageReferenced(page); - page_remove_rmap(page, true); - put_page(page); + if (unlikely(is_pmd_migration_entry(old_pmd))) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = migration_entry_to_page(entry); + } else { + page = pmd_page(old_pmd); + if (!PageDirty(page) && pmd_dirty(old_pmd)) + set_page_dirty(page); + if (!PageReferenced(page) && pmd_young(old_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + } + + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2418,16 +2430,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | - TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; - bool unmap_success; + TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) ttu_flags |= TTU_SPLIT_FREEZE; - unmap_success = try_to_unmap(page, ttu_flags); - VM_BUG_ON_PAGE(!unmap_success, page); + try_to_unmap(page, ttu_flags); + + VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } static void remap_page(struct page *page) @@ -2686,7 +2698,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - int count, mapcount, extra_pins, ret; + int extra_pins, ret; bool mlocked; unsigned long flags; pgoff_t end; @@ -2748,7 +2760,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) mlocked = PageMlocked(page); unmap_page(head); - VM_BUG_ON_PAGE(compound_mapcount(head), head); /* Make sure the page is not on per-CPU pagevec as it takes pin */ if (mlocked) @@ -2774,9 +2785,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&pgdata->split_queue_lock); - count = page_count(head); - mapcount = total_mapcount(head); - if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { + if (page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { pgdata->split_queue_len--; list_del(page_deferred_list(head)); @@ -2792,16 +2801,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } else ret = 0; } else { - if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); - } spin_unlock(&pgdata->split_queue_lock); -fail: if (mapping) +fail: + if (mapping) xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); remap_page(head); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c69f12e4c1499..ebcf26bc4cd4b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1391,15 +1391,12 @@ int PageHeadHuge(struct page *page_head) return get_compound_page_dtor(page_head) == free_huge_page; } -pgoff_t __basepage_index(struct page *page) +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; - if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else diff --git a/mm/internal.h b/mm/internal.h index 397183c8fe47b..3a2e973138d36 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -331,27 +331,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + (1UL << compound_order(page)) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; } +/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + (1UL << compound_order(page)); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; } #else /* !CONFIG_MMU */ diff --git a/mm/memory.c b/mm/memory.c index c2011c51f15de..49b546cdce0d2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1439,7 +1439,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -2924,6 +2935,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } } +/** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + hpage_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + /** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 11df03e71288c..edca786093187 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -111,6 +111,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_in_hpage(pvmw->page, pfn); } +static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + /** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address @@ -139,6 +146,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; + unsigned long end; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -148,10 +156,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - if (pvmw->pte) - goto next_pte; + if (unlikely(PageHuge(page))) { + /* The only possible mapping was handled on last iteration */ + if (pvmw->pte) + return not_found(pvmw); - if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, PAGE_SIZE << compound_order(page)); @@ -164,78 +173,108 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); return true; } -restart: - pgd = pgd_offset(mm, pvmw->address); - if (!pgd_present(*pgd)) - return false; - p4d = p4d_offset(pgd, pvmw->address); - if (!p4d_present(*p4d)) - return false; - pud = pud_offset(p4d, pvmw->address); - if (!pud_present(*pud)) - return false; - pvmw->pmd = pmd_offset(pud, pvmw->address); + /* - * Make sure the pmd value isn't cached in a register by the - * compiler and used as a stale value after we've observed a - * subsequent update. + * Seek to next pte only makes sense for THP. + * But more important than that optimization, is to filter out + * any PageKsm page: whose page->index misleads vma_address() + * and vma_address_end() to disaster. */ - pmde = READ_ONCE(*pvmw->pmd); - if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { - pvmw->ptl = pmd_lock(mm, pvmw->pmd); - if (likely(pmd_trans_huge(*pvmw->pmd))) { - if (pvmw->flags & PVMW_MIGRATION) - return not_found(pvmw); - if (pmd_page(*pvmw->pmd) != page) - return not_found(pvmw); - return true; - } else if (!pmd_present(*pvmw->pmd)) { - if (thp_migration_supported()) { - if (!(pvmw->flags & PVMW_MIGRATION)) + end = PageTransCompound(page) ? + vma_address_end(page, pvmw->vma) : + pvmw->address + PAGE_SIZE; + if (pvmw->pte) + goto next_pte; +restart: + do { + pgd = pgd_offset(mm, pvmw->address); + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } + pud = pud_offset(p4d, pvmw->address); + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + } + + pvmw->pmd = pmd_offset(pud, pvmw->address); + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { + pvmw->ptl = pmd_lock(mm, pvmw->pmd); + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { + if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); + if (pmd_page(pmde) != page) + return not_found(pvmw); + return true; + } + if (!pmd_present(pmde)) { + swp_entry_t entry; - if (migration_entry_to_page(entry) != page) - return not_found(pvmw); - return true; - } + if (!thp_migration_supported() || + !(pvmw->flags & PVMW_MIGRATION)) + return not_found(pvmw); + entry = pmd_to_swp_entry(pmde); + if (!is_migration_entry(entry) || + migration_entry_to_page(entry) != page) + return not_found(pvmw); + return true; } - return not_found(pvmw); - } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; + } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } + step_forward(pvmw, PMD_SIZE); + continue; } - } else if (!pmd_present(pmde)) { - return false; - } - if (!map_pte(pvmw)) - goto next_pte; - while (1) { + if (!map_pte(pvmw)) + goto next_pte; +this_pte: if (check_pte(pvmw)) return true; next_pte: - /* Seek to next pte only makes sense for THP */ - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - hpage_nr_pages(pvmw->page) * PAGE_SIZE) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ - if (pvmw->address % PMD_SIZE == 0) { - pte_unmap(pvmw->pte); + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; goto restart; - } else { - pvmw->pte++; + } + pvmw->pte++; + if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); } } while (pte_none(*pvmw->pte)); @@ -243,7 +282,10 @@ next_pte: pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } - } + goto this_pte; + } while (pvmw->address < end); + + return false; } /** @@ -262,14 +304,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); - if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index cf2af04b34b97..36770fcdc3582 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -125,8 +125,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && - !pmd_devmap(*pmdp)) || !pmd_present(*pmdp)); + VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && + !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; diff --git a/mm/rmap.c b/mm/rmap.c index 1bd94ea62f7f1..699f445e3e78c 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -686,7 +686,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -696,15 +695,13 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping) { - if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) - return -EFAULT; - } else + } else if (!vma->vm_file) { return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; - return address; + } + + return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -896,7 +893,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, * We have to assume the worse case ie pmd for invalidation. Note that * the page can not be free from this function. */ - end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + end = vma_address_end(page, vma); mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { @@ -1348,6 +1345,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, unsigned long start = address, end; enum ttu_flags flags = (enum ttu_flags)arg; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; @@ -1369,7 +1375,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ - end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1682,9 +1689,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) return is_vma_temporary_stack(vma); } -static int page_mapcount_is_zero(struct page *page) +static int page_not_mapped(struct page *page) { - return !total_mapcount(page); + return !page_mapped(page); } /** @@ -1702,7 +1709,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, - .done = page_mapcount_is_zero, + .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; @@ -1723,14 +1730,15 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) else rmap_walk(page, &rwc); - return !page_mapcount(page) ? true : false; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + return !page_mapcount(page); } -static int page_not_mapped(struct page *page) -{ - return !page_mapped(page); -}; - /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked @@ -1825,6 +1833,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1879,6 +1888,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) diff --git a/mm/truncate.c b/mm/truncate.c index 71b65aab80775..43c73db17a0a6 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -175,13 +175,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1; - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, PAGE_SIZE); @@ -226,7 +223,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO; - truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -364,7 +361,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) - truncate_cleanup_page(mapping, locked_pvec.pages[i]); + truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); @@ -703,6 +700,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } + if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -710,23 +717,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page))