diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback index ecb7942ff146..ac2947b98950 100644 --- a/Documentation/ABI/testing/sysfs-driver-xen-blkback +++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback @@ -35,3 +35,12 @@ Description: controls the duration in milliseconds that blkback will not cache any page not backed by a grant mapping. The default is 10ms. + +What: /sys/module/xen_blkback/parameters/feature_persistent +Date: September 2020 +KernelVersion: 5.10 +Contact: SeongJae Park +Description: + Whether to enable the persistent grants feature or not. Note + that this option only takes effect on newly created backends. + The default is Y (enable). diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkfront b/Documentation/ABI/testing/sysfs-driver-xen-blkfront index c0a6cb7eb314..28008905615f 100644 --- a/Documentation/ABI/testing/sysfs-driver-xen-blkfront +++ b/Documentation/ABI/testing/sysfs-driver-xen-blkfront @@ -1,4 +1,4 @@ -What: /sys/module/xen_blkfront/parameters/max +What: /sys/module/xen_blkfront/parameters/max_indirect_segments Date: June 2013 KernelVersion: 3.11 Contact: Konrad Rzeszutek Wilk @@ -8,3 +8,12 @@ Description: is 32 - higher value means more potential throughput but more memory usage. The backend picks the minimum of the frontend and its default backend value. + +What: /sys/module/xen_blkfront/parameters/feature_persistent +Date: September 2020 +KernelVersion: 5.10 +Contact: SeongJae Park +Description: + Whether to enable the persistent grants feature or not. Note + that this option only takes effect on newly created frontends. + The default is Y (enable). diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 02d4adbf98d2..526d65d8573a 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5978,6 +5978,13 @@ After which time (jiffies) the event handling loop should start to delay EOI handling. Default is 2. + xen.fifo_events= [XEN] + Boolean parameter to disable using fifo event handling + even if available. Normally fifo event handling is + preferred over the 2-level event handling, as it is + fairer and the number of possible event channels is + much higher. Default is on (use fifo events). + nopv= [X86,XEN,KVM,HYPER_V,VMWARE] Disables the PV optimizations forcing the guest to run as generic guest with no PV drivers. Currently support diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 2097fa0ebdb5..c1b2f764b29a 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -88,14 +88,17 @@ int xen_smp_intr_init(unsigned int cpu) per_cpu(xen_callfunc_irq, cpu).irq = rc; per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; - debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); - rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, - IRQF_PERCPU | IRQF_NOBALANCING, - debug_name, NULL); - if (rc < 0) - goto fail; - per_cpu(xen_debug_irq, cpu).irq = rc; - per_cpu(xen_debug_irq, cpu).name = debug_name; + if (!xen_fifo_events) { + debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, + xen_debug_interrupt, + IRQF_PERCPU | IRQF_NOBALANCING, + debug_name, NULL); + if (rc < 0) + goto fail; + per_cpu(xen_debug_irq, cpu).irq = rc; + per_cpu(xen_debug_irq, cpu).name = debug_name; + } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 45d556f71858..9546c3384c75 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -29,6 +29,8 @@ extern struct start_info *xen_start_info; extern struct shared_info xen_dummy_shared_info; extern struct shared_info *HYPERVISOR_shared_info; +extern bool xen_fifo_events; + void xen_setup_mfn_list_list(void); void xen_build_mfn_list_list(void); void xen_setup_machphys_mapping(void); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 5e7c36d73dc6..f5705569e2a7 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -473,6 +473,12 @@ static void xen_vbd_free(struct xen_vbd *vbd) vbd->bdev = NULL; } +/* Enable the persistent grants feature. */ +static bool feature_persistent = true; +module_param(feature_persistent, bool, 0644); +MODULE_PARM_DESC(feature_persistent, + "Enables the persistent grants feature"); + static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, unsigned major, unsigned minor, int readonly, int cdrom) @@ -518,6 +524,8 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, if (q && blk_queue_secure_erase(q)) vbd->discard_secure = true; + vbd->feature_gnt_persistent = feature_persistent; + pr_debug("Successful creation of handle=%04x (dom=%u)\n", handle, blkif->domid); return 0; @@ -905,7 +913,8 @@ again: xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support); - err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u", 1); + err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u", + be->blkif->vbd.feature_gnt_persistent); if (err) { xenbus_dev_fatal(dev, err, "writing %s/feature-persistent", dev->nodename); @@ -1066,7 +1075,6 @@ static int connect_ring(struct backend_info *be) { struct xenbus_device *dev = be->dev; struct xen_blkif *blkif = be->blkif; - unsigned int pers_grants; char protocol[64] = ""; int err, i; char *xspath; @@ -1092,9 +1100,11 @@ static int connect_ring(struct backend_info *be) xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol); return -ENOSYS; } - pers_grants = xenbus_read_unsigned(dev->otherend, "feature-persistent", - 0); - blkif->vbd.feature_gnt_persistent = pers_grants; + if (blkif->vbd.feature_gnt_persistent) + blkif->vbd.feature_gnt_persistent = + xenbus_read_unsigned(dev->otherend, + "feature-persistent", 0); + blkif->vbd.overflow_max_grants = 0; /* @@ -1117,7 +1127,7 @@ static int connect_ring(struct backend_info *be) pr_info("%s: using %d queues, protocol %d (%s) %s\n", dev->nodename, blkif->nr_rings, blkif->blk_protocol, protocol, - pers_grants ? "persistent grants" : ""); + blkif->vbd.feature_gnt_persistent ? "persistent grants" : ""); ring_page_order = xenbus_read_unsigned(dev->otherend, "ring-page-order", 0); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 91de2e0755ae..48629d3433b4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1866,8 +1866,8 @@ again: message = "writing protocol"; goto abort_transaction; } - err = xenbus_printf(xbt, dev->nodename, - "feature-persistent", "%u", 1); + err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u", + info->feature_persistent); if (err) dev_warn(&dev->dev, "writing persistent grants feature to xenbus"); @@ -1941,6 +1941,13 @@ static int negotiate_mq(struct blkfront_info *info) } return 0; } + +/* Enable the persistent grants feature. */ +static bool feature_persistent = true; +module_param(feature_persistent, bool, 0644); +MODULE_PARM_DESC(feature_persistent, + "Enables the persistent grants feature"); + /** * Entry point to this code when a new device is created. Allocate the basic * structures and the ring buffer for communication with the backend, and @@ -2007,6 +2014,8 @@ static int blkfront_probe(struct xenbus_device *dev, info->vdevice = vdevice; info->connected = BLKIF_STATE_DISCONNECTED; + info->feature_persistent = feature_persistent; + /* Front end dir is a number, which is used as the id. */ info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0); dev_set_drvdata(&dev->dev, info); @@ -2316,9 +2325,10 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0)) blkfront_setup_discard(info); - info->feature_persistent = - !!xenbus_read_unsigned(info->xbdev->otherend, - "feature-persistent", 0); + if (info->feature_persistent) + info->feature_persistent = + !!xenbus_read_unsigned(info->xbdev->otherend, + "feature-persistent", 0); indirect_segments = xenbus_read_unsigned(info->xbdev->otherend, "feature-max-indirect-segments", 0); diff --git a/drivers/xen/events/events_2l.c b/drivers/xen/events/events_2l.c index fe5ad0e89cd8..da87f3a1e351 100644 --- a/drivers/xen/events/events_2l.c +++ b/drivers/xen/events/events_2l.c @@ -47,10 +47,11 @@ static unsigned evtchn_2l_max_channels(void) return EVTCHN_2L_NR_CHANNELS; } -static void evtchn_2l_bind_to_cpu(struct irq_info *info, unsigned cpu) +static void evtchn_2l_bind_to_cpu(evtchn_port_t evtchn, unsigned int cpu, + unsigned int old_cpu) { - clear_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, info->cpu))); - set_bit(info->evtchn, BM(per_cpu(cpu_evtchn_mask, cpu))); + clear_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, old_cpu))); + set_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, cpu))); } static void evtchn_2l_clear_pending(evtchn_port_t port) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index cc317739e786..6038c4c35db5 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -70,6 +70,57 @@ #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "xen." +/* Interrupt types. */ +enum xen_irq_type { + IRQT_UNBOUND = 0, + IRQT_PIRQ, + IRQT_VIRQ, + IRQT_IPI, + IRQT_EVTCHN +}; + +/* + * Packed IRQ information: + * type - enum xen_irq_type + * event channel - irq->event channel mapping + * cpu - cpu this event channel is bound to + * index - type-specific information: + * PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM + * guest, or GSI (real passthrough IRQ) of the device. + * VIRQ - virq number + * IPI - IPI vector + * EVTCHN - + */ +struct irq_info { + struct list_head list; + struct list_head eoi_list; + short refcnt; + short spurious_cnt; + enum xen_irq_type type; /* type */ + unsigned irq; + evtchn_port_t evtchn; /* event channel */ + unsigned short cpu; /* cpu bound */ + unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */ + unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */ + u64 eoi_time; /* Time in jiffies when to EOI. */ + + union { + unsigned short virq; + enum ipi_vector ipi; + struct { + unsigned short pirq; + unsigned short gsi; + unsigned char vector; + unsigned char flags; + uint16_t domid; + } pirq; + } u; +}; + +#define PIRQ_NEEDS_EOI (1 << 0) +#define PIRQ_SHAREABLE (1 << 1) +#define PIRQ_MSI_GROUP (1 << 2) + static uint __read_mostly event_loop_timeout = 2; module_param(event_loop_timeout, uint, 0644); @@ -110,7 +161,7 @@ static DEFINE_PER_CPU(int [NR_VIRQS], virq_to_irq) = {[0 ... NR_VIRQS-1] = -1}; /* IRQ <-> IPI mapping */ static DEFINE_PER_CPU(int [XEN_NR_IPIS], ipi_to_irq) = {[0 ... XEN_NR_IPIS-1] = -1}; -int **evtchn_to_irq; +static int **evtchn_to_irq; #ifdef CONFIG_X86 static unsigned long *pirq_eoi_map; #endif @@ -190,7 +241,7 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) } /* Get info for IRQ */ -struct irq_info *info_for_irq(unsigned irq) +static struct irq_info *info_for_irq(unsigned irq) { if (irq < nr_legacy_irqs()) return legacy_info_ptrs[irq]; @@ -228,7 +279,7 @@ static int xen_irq_info_common_setup(struct irq_info *info, irq_clear_status_flags(irq, IRQ_NOREQUEST|IRQ_NOAUTOEN); - return xen_evtchn_port_setup(info); + return xen_evtchn_port_setup(evtchn); } static int xen_irq_info_evtchn_setup(unsigned irq, @@ -351,7 +402,7 @@ static enum xen_irq_type type_from_irq(unsigned irq) return info_for_irq(irq)->type; } -unsigned cpu_from_irq(unsigned irq) +static unsigned cpu_from_irq(unsigned irq) { return info_for_irq(irq)->cpu; } @@ -391,7 +442,7 @@ static void bind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int cpu) #ifdef CONFIG_SMP cpumask_copy(irq_get_affinity_mask(irq), cpumask_of(cpu)); #endif - xen_evtchn_port_bind_to_cpu(info, cpu); + xen_evtchn_port_bind_to_cpu(evtchn, cpu, info->cpu); info->cpu = cpu; } @@ -745,7 +796,7 @@ static unsigned int __startup_pirq(unsigned int irq) info->evtchn = evtchn; bind_evtchn_to_cpu(evtchn, 0); - rc = xen_evtchn_port_setup(info); + rc = xen_evtchn_port_setup(evtchn); if (rc) goto err; @@ -1145,14 +1196,6 @@ static int bind_interdomain_evtchn_to_irq_chip(unsigned int remote_domain, chip); } -int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - evtchn_port_t remote_port) -{ - return bind_interdomain_evtchn_to_irq_chip(remote_domain, remote_port, - &xen_dynamic_chip); -} -EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irq); - int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port) { @@ -1320,19 +1363,6 @@ static int bind_interdomain_evtchn_to_irqhandler_chip( return irq; } -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - evtchn_port_t remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id) -{ - return bind_interdomain_evtchn_to_irqhandler_chip(remote_domain, - remote_port, handler, irqflags, devname, - dev_id, &xen_dynamic_chip); -} -EXPORT_SYMBOL_GPL(bind_interdomain_evtchn_to_irqhandler); - int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port, irq_handler_t handler, @@ -2020,8 +2050,8 @@ void xen_setup_callback_vector(void) {} static inline void xen_alloc_callback_vector(void) {} #endif -static bool fifo_events = true; -module_param(fifo_events, bool, 0); +bool xen_fifo_events = true; +module_param_named(fifo_events, xen_fifo_events, bool, 0); static int xen_evtchn_cpu_prepare(unsigned int cpu) { @@ -2050,10 +2080,12 @@ void __init xen_init_IRQ(void) int ret = -EINVAL; evtchn_port_t evtchn; - if (fifo_events) + if (xen_fifo_events) ret = xen_evtchn_fifo_init(); - if (ret < 0) + if (ret < 0) { xen_evtchn_2l_init(); + xen_fifo_events = false; + } xen_cpu_init_eoi(smp_processor_id()); diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c index 6085a808da95..b234f1766810 100644 --- a/drivers/xen/events/events_fifo.c +++ b/drivers/xen/events/events_fifo.c @@ -138,9 +138,8 @@ static void init_array_page(event_word_t *array_page) array_page[i] = 1 << EVTCHN_FIFO_MASKED; } -static int evtchn_fifo_setup(struct irq_info *info) +static int evtchn_fifo_setup(evtchn_port_t port) { - evtchn_port_t port = info->evtchn; unsigned new_array_pages; int ret; @@ -186,7 +185,8 @@ static int evtchn_fifo_setup(struct irq_info *info) return ret; } -static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu) +static void evtchn_fifo_bind_to_cpu(evtchn_port_t evtchn, unsigned int cpu, + unsigned int old_cpu) { /* no-op */ } @@ -237,6 +237,9 @@ static bool clear_masked_cond(volatile event_word_t *word) w = *word; do { + if (!(w & (1 << EVTCHN_FIFO_MASKED))) + return true; + if (w & (1 << EVTCHN_FIFO_PENDING)) return false; diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h index 82937d90d7d7..0a97c0549db7 100644 --- a/drivers/xen/events/events_internal.h +++ b/drivers/xen/events/events_internal.h @@ -7,65 +7,15 @@ #ifndef __EVENTS_INTERNAL_H__ #define __EVENTS_INTERNAL_H__ -/* Interrupt types. */ -enum xen_irq_type { - IRQT_UNBOUND = 0, - IRQT_PIRQ, - IRQT_VIRQ, - IRQT_IPI, - IRQT_EVTCHN -}; - -/* - * Packed IRQ information: - * type - enum xen_irq_type - * event channel - irq->event channel mapping - * cpu - cpu this event channel is bound to - * index - type-specific information: - * PIRQ - vector, with MSB being "needs EIO", or physical IRQ of the HVM - * guest, or GSI (real passthrough IRQ) of the device. - * VIRQ - virq number - * IPI - IPI vector - * EVTCHN - - */ -struct irq_info { - struct list_head list; - struct list_head eoi_list; - short refcnt; - short spurious_cnt; - enum xen_irq_type type; /* type */ - unsigned irq; - evtchn_port_t evtchn; /* event channel */ - unsigned short cpu; /* cpu bound */ - unsigned short eoi_cpu; /* EOI must happen on this cpu */ - unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */ - u64 eoi_time; /* Time in jiffies when to EOI. */ - - union { - unsigned short virq; - enum ipi_vector ipi; - struct { - unsigned short pirq; - unsigned short gsi; - unsigned char vector; - unsigned char flags; - uint16_t domid; - } pirq; - } u; -}; - -#define PIRQ_NEEDS_EOI (1 << 0) -#define PIRQ_SHAREABLE (1 << 1) -#define PIRQ_MSI_GROUP (1 << 2) - struct evtchn_loop_ctrl; struct evtchn_ops { unsigned (*max_channels)(void); unsigned (*nr_channels)(void); - int (*setup)(struct irq_info *info); - void (*bind_to_cpu)(struct irq_info *info, unsigned cpu); + int (*setup)(evtchn_port_t port); + void (*bind_to_cpu)(evtchn_port_t evtchn, unsigned int cpu, + unsigned int old_cpu); void (*clear_pending)(evtchn_port_t port); void (*set_pending)(evtchn_port_t port); @@ -83,12 +33,9 @@ struct evtchn_ops { extern const struct evtchn_ops *evtchn_ops; -extern int **evtchn_to_irq; int get_evtchn_to_irq(evtchn_port_t evtchn); void handle_irq_for_port(evtchn_port_t port, struct evtchn_loop_ctrl *ctrl); -struct irq_info *info_for_irq(unsigned irq); -unsigned cpu_from_irq(unsigned irq); unsigned int cpu_from_evtchn(evtchn_port_t evtchn); static inline unsigned xen_evtchn_max_channels(void) @@ -100,17 +47,18 @@ static inline unsigned xen_evtchn_max_channels(void) * Do any ABI specific setup for a bound event channel before it can * be unmasked and used. */ -static inline int xen_evtchn_port_setup(struct irq_info *info) +static inline int xen_evtchn_port_setup(evtchn_port_t evtchn) { if (evtchn_ops->setup) - return evtchn_ops->setup(info); + return evtchn_ops->setup(evtchn); return 0; } -static inline void xen_evtchn_port_bind_to_cpu(struct irq_info *info, - unsigned cpu) +static inline void xen_evtchn_port_bind_to_cpu(evtchn_port_t evtchn, + unsigned int cpu, + unsigned int old_cpu) { - evtchn_ops->bind_to_cpu(info, cpu); + evtchn_ops->bind_to_cpu(evtchn, cpu, old_cpu); } static inline void clear_evtchn(evtchn_port_t port) diff --git a/include/xen/events.h b/include/xen/events.h index 3b8155c2ea03..8ec418e30c7f 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -35,16 +35,8 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, unsigned long irqflags, const char *devname, void *dev_id); -int bind_interdomain_evtchn_to_irq(unsigned int remote_domain, - evtchn_port_t remote_port); int bind_interdomain_evtchn_to_irq_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port); -int bind_interdomain_evtchn_to_irqhandler(unsigned int remote_domain, - evtchn_port_t remote_port, - irq_handler_t handler, - unsigned long irqflags, - const char *devname, - void *dev_id); int bind_interdomain_evtchn_to_irqhandler_lateeoi(unsigned int remote_domain, evtchn_port_t remote_port, irq_handler_t handler,