diff options
Diffstat (limited to 'include/linux')
31 files changed, 303 insertions, 164 deletions
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 5a5d79ee256f..d5eb4ad1c534 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <linux/blkdev.h> #include <linux/writeback.h> +#include <linux/memcontrol.h> #include <linux/blk-cgroup.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> @@ -252,13 +253,19 @@ int inode_congested(struct inode *inode, int cong_bits); * @inode: inode of interest * * cgroup writeback requires support from both the bdi and filesystem. - * Test whether @inode has both. + * Also, both memcg and iocg have to be on the default hierarchy. Test + * whether all conditions are met. + * + * Note that the test result may change dynamically on the same inode + * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); - return bdi_cap_account_dirty(bdi) && + return cgroup_on_dfl(mem_cgroup_root_css->cgroup) && + cgroup_on_dfl(blkcg_root_css->cgroup) && + bdi_cap_account_dirty(bdi) && (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 708923b9b623..99da9ebc7377 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -584,7 +584,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) +#define rq_data_dir(rq) ((int)((rq)->cmd_flags & 1)) /* * Driver can handle struct request, if it either has an old style @@ -1368,6 +1368,26 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } +static inline bool bio_will_gap(struct request_queue *q, struct bio *prev, + struct bio *next) +{ + if (!bio_has_data(prev)) + return false; + + return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1], + next->bi_io_vec[0].bv_offset); +} + +static inline bool req_gap_back_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, req->biotail, bio); +} + +static inline bool req_gap_front_merge(struct request *req, struct bio *bio) +{ + return bio_will_gap(req->q, bio, req->bio); +} + struct work_struct; int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); @@ -1494,6 +1514,26 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + struct bio_integrity_payload *bip = bio_integrity(req->bio); + struct bio_integrity_payload *bip_next = bio_integrity(next); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + struct bio_integrity_payload *bip = bio_integrity(bio); + struct bio_integrity_payload *bip_next = bio_integrity(req->bio); + + return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + bip_next->bip_vec[0].bv_offset); +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1560,6 +1600,16 @@ static inline bool blk_integrity_is_initialized(struct gendisk *g) { return 0; } +static inline bool integrity_req_gap_back_merge(struct request *req, + struct bio *next) +{ + return false; +} +static inline bool integrity_req_gap_front_merge(struct request *req, + struct bio *bio) +{ + return false; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 4763ad64e832..f89b31d45cc8 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -107,6 +107,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_OSDMAP_ENC | \ CEPH_FEATURE_CRUSH_TUNABLES3 | \ CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ + CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_CRUSH_V4) #define CEPH_FEATURES_REQUIRED_DEFAULT \ diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 9ebee53d3bf5..397c5cd09794 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -46,6 +46,7 @@ struct ceph_options { unsigned long mount_timeout; /* jiffies */ unsigned long osd_idle_ttl; /* jiffies */ unsigned long osd_keepalive_timeout; /* jiffies */ + unsigned long monc_ping_timeout; /* jiffies */ /* * any type that can't be simply compared or doesn't need need @@ -66,6 +67,7 @@ struct ceph_options { #define CEPH_MOUNT_TIMEOUT_DEFAULT msecs_to_jiffies(60 * 1000) #define CEPH_OSD_KEEPALIVE_DEFAULT msecs_to_jiffies(5 * 1000) #define CEPH_OSD_IDLE_TTL_DEFAULT msecs_to_jiffies(60 * 1000) +#define CEPH_MONC_PING_TIMEOUT_DEFAULT msecs_to_jiffies(30 * 1000) #define CEPH_MSG_MAX_FRONT_LEN (16*1024*1024) #define CEPH_MSG_MAX_MIDDLE_LEN (16*1024*1024) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 37753278987a..b2371d9b51fa 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -238,6 +238,8 @@ struct ceph_connection { bool out_kvec_is_msg; /* kvec refers to out_msg */ int out_more; /* there is more data after the kvecs */ __le64 out_temp_ack; /* for writing an ack */ + struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2 + stamp */ /* message in temps */ struct ceph_msg_header in_hdr; @@ -248,6 +250,8 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ + struct timespec last_keepalive_ack; /* keepalive2 ack stamp */ + struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ }; @@ -285,6 +289,8 @@ extern void ceph_msg_revoke(struct ceph_msg *msg); extern void ceph_msg_revoke_incoming(struct ceph_msg *msg); extern void ceph_con_keepalive(struct ceph_connection *con); +extern bool ceph_con_keepalive_expired(struct ceph_connection *con, + unsigned long interval); extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, size_t length, size_t alignment); diff --git a/include/linux/ceph/msgr.h b/include/linux/ceph/msgr.h index 1c1887206ffa..0fe2656ac415 100644 --- a/include/linux/ceph/msgr.h +++ b/include/linux/ceph/msgr.h @@ -84,10 +84,12 @@ struct ceph_entity_inst { #define CEPH_MSGR_TAG_MSG 7 /* message */ #define CEPH_MSGR_TAG_ACK 8 /* message ack */ #define CEPH_MSGR_TAG_KEEPALIVE 9 /* just a keepalive byte! */ -#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ +#define CEPH_MSGR_TAG_BADPROTOVER 10 /* bad protocol version */ #define CEPH_MSGR_TAG_BADAUTHORIZER 11 /* bad authorizer */ #define CEPH_MSGR_TAG_FEATURES 12 /* insufficient features */ #define CEPH_MSGR_TAG_SEQ 13 /* 64-bit int follows with seen seq number */ +#define CEPH_MSGR_TAG_KEEPALIVE2 14 /* keepalive2 byte + ceph_timespec */ +#define CEPH_MSGR_TAG_KEEPALIVE2_ACK 15 /* keepalive2 reply */ /* diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 4d8fcf2187dc..8492721b39be 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -473,31 +473,8 @@ struct cgroup_subsys { unsigned int depends_on; }; -extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - -/** - * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_begin() and allows cgroup operations to - * synchronize against threadgroup changes using a percpu_rw_semaphore. - */ -static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) -{ - percpu_down_read(&cgroup_threadgroup_rwsem); -} - -/** - * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups - * @tsk: target task - * - * Called from threadgroup_change_end(). Counterpart of - * cgroup_threadcgroup_change_begin(). - */ -static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) -{ - percpu_up_read(&cgroup_threadgroup_rwsem); -} +void cgroup_threadgroup_change_begin(struct task_struct *tsk); +void cgroup_threadgroup_change_end(struct task_struct *tsk); #else /* CONFIG_CGROUPS */ diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h index 31ce435981fe..bdcf358dfce2 100644 --- a/include/linux/clockchips.h +++ b/include/linux/clockchips.h @@ -18,15 +18,6 @@ struct clock_event_device; struct module; -/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */ -enum clock_event_mode { - CLOCK_EVT_MODE_UNUSED, - CLOCK_EVT_MODE_SHUTDOWN, - CLOCK_EVT_MODE_PERIODIC, - CLOCK_EVT_MODE_ONESHOT, - CLOCK_EVT_MODE_RESUME, -}; - /* * Possible states of a clock event device. * @@ -86,16 +77,14 @@ enum clock_event_state { * @min_delta_ns: minimum delta value in ns * @mult: nanosecond to cycles multiplier * @shift: nanoseconds to cycles divisor (power of two) - * @mode: operating mode, relevant only to ->set_mode(), OBSOLETE * @state_use_accessors:current state of the device, assigned by the core code * @features: features * @retries: number of forced programming retries - * @set_mode: legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME. - * @set_state_periodic: switch state to periodic, if !set_mode - * @set_state_oneshot: switch state to oneshot, if !set_mode - * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode - * @set_state_shutdown: switch state to shutdown, if !set_mode - * @tick_resume: resume clkevt device, if !set_mode + * @set_state_periodic: switch state to periodic + * @set_state_oneshot: switch state to oneshot + * @set_state_oneshot_stopped: switch state to oneshot_stopped + * @set_state_shutdown: switch state to shutdown + * @tick_resume: resume clkevt device * @broadcast: function to broadcast events * @min_delta_ticks: minimum delta value in ticks stored for reconfiguration * @max_delta_ticks: maximum delta value in ticks stored for reconfiguration @@ -116,18 +105,10 @@ struct clock_event_device { u64 min_delta_ns; u32 mult; u32 shift; - enum clock_event_mode mode; enum clock_event_state state_use_accessors; unsigned int features; unsigned long retries; - /* - * State transition callback(s): Only one of the two groups should be - * defined: - * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME. - * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume(). - */ - void (*set_mode)(enum clock_event_mode mode, struct clock_event_device *); int (*set_state_periodic)(struct clock_event_device *); int (*set_state_oneshot)(struct clock_event_device *); int (*set_state_oneshot_stopped)(struct clock_event_device *); diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 430efcbea48e..dca22de98d94 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -127,9 +127,14 @@ struct cpufreq_policy { #define CPUFREQ_SHARED_TYPE_ANY (3) /* Freq can be set from any dependent CPU*/ #ifdef CONFIG_CPU_FREQ +struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu); struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu); void cpufreq_cpu_put(struct cpufreq_policy *policy); #else +static inline struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu) +{ + return NULL; +} static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) { return NULL; diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h index ce447f0f1bad..68030e22af35 100644 --- a/include/linux/devfreq.h +++ b/include/linux/devfreq.h @@ -65,7 +65,10 @@ struct devfreq_dev_status { * The "flags" parameter's possible values are * explained above with "DEVFREQ_FLAG_*" macros. * @get_dev_status: The device should provide the current performance - * status to devfreq, which is used by governors. + * status to devfreq. Governors are recommended not to + * use this directly. Instead, governors are recommended + * to use devfreq_update_stats() along with + * devfreq.last_status. * @get_cur_freq: The device should provide the current frequency * at which it is operating. * @exit: An optional callback that is called when devfreq @@ -161,6 +164,7 @@ struct devfreq { struct delayed_work work; unsigned long previous_freq; + struct devfreq_dev_status last_status; void *data; /* private data for governors */ @@ -204,6 +208,19 @@ extern int devm_devfreq_register_opp_notifier(struct device *dev, extern void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq); +/** + * devfreq_update_stats() - update the last_status pointer in struct devfreq + * @df: the devfreq instance whose status needs updating + * + * Governors are recommended to use this function along with last_status, + * which allows other entities to reuse the last_status without affecting + * the values fetched later by governors. + */ +static inline int devfreq_update_stats(struct devfreq *df) +{ + return df->profile->get_dev_status(df->dev.parent, &df->last_status); +} + #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND) /** * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq @@ -289,6 +306,11 @@ static inline void devm_devfreq_unregister_opp_notifier(struct device *dev, struct devfreq *devfreq) { } + +static inline int devfreq_update_stats(struct devfreq *df) +{ + return -EINVAL; +} #endif /* CONFIG_PM_DEVFREQ */ #endif /* __LINUX_DEVFREQ_H__ */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index d0b380ee7d67..e38681f4912d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,6 +25,13 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; +#ifdef CONFIG_CGROUPS +#define INIT_GROUP_RWSEM(sig) \ + .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), +#else +#define INIT_GROUP_RWSEM(sig) +#endif + #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -57,6 +64,7 @@ extern struct fs_struct init_fs; INIT_PREV_CPUTIME(sig) \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ + INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/irq.h b/include/linux/irq.h index 6f8b34066442..11bf09288ddb 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -110,8 +110,8 @@ enum { /* * Return value for chip->irq_set_affinity() * - * IRQ_SET_MASK_OK - OK, core updates irq_data.affinity - * IRQ_SET_MASK_NOCPY - OK, chip did update irq_data.affinity + * IRQ_SET_MASK_OK - OK, core updates irq_common_data.affinity + * IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity * IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to * support stacked irqchips, which indicates skipping * all descendent irqchips. @@ -129,9 +129,19 @@ struct irq_domain; * struct irq_common_data - per irq data shared by all irqchips * @state_use_accessors: status information for irq chip functions. * Use accessor functions to deal with it + * @node: node index useful for balancing + * @handler_data: per-IRQ data for the irq_chip methods + * @affinity: IRQ affinity on SMP + * @msi_desc: MSI descriptor */ struct irq_common_data { unsigned int state_use_accessors; +#ifdef CONFIG_NUMA + unsigned int node; +#endif + void *handler_data; + struct msi_desc *msi_desc; + cpumask_var_t affinity; }; /** @@ -139,38 +149,26 @@ struct irq_common_data { * @mask: precomputed bitmask for accessing the chip registers * @irq: interrupt number * @hwirq: hardware interrupt number, local to the interrupt domain - * @node: node index useful for balancing * @common: point to data shared by all irqchips * @chip: low level interrupt hardware access * @domain: Interrupt translation domain; responsible for mapping * between hwirq number and linux irq number. * @parent_data: pointer to parent struct irq_data to support hierarchy * irq_domain - * @handler_data: per-IRQ data for the irq_chip methods * @chip_data: platform-specific per-chip private data for the chip * methods, to allow shared chip implementations - * @msi_desc: MSI descriptor - * @affinity: IRQ affinity on SMP - * - * The fields here need to overlay the ones in irq_desc until we - * cleaned up the direct references and switched everything over to - * irq_data. */ struct irq_data { u32 mask; unsigned int irq; unsigned long hwirq; - unsigned int node; struct irq_common_data *common; struct irq_chip *chip; struct irq_domain *domain; #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data *parent_data; #endif - void *handler_data; void *chip_data; - struct msi_desc *msi_desc; - cpumask_var_t affinity; }; /* @@ -190,6 +188,7 @@ struct irq_data { * IRQD_IRQ_MASKED - Masked state of the interrupt * IRQD_IRQ_INPROGRESS - In progress state of the interrupt * IRQD_WAKEUP_ARMED - Wakeup mode armed + * IRQD_FORWARDED_TO_VCPU - The interrupt is forwarded to a VCPU */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -204,6 +203,7 @@ enum { IRQD_IRQ_MASKED = (1 << 17), IRQD_IRQ_INPROGRESS = (1 << 18), IRQD_WAKEUP_ARMED = (1 << 19), + IRQD_FORWARDED_TO_VCPU = (1 << 20), }; #define __irqd_to_state(d) ((d)->common->state_use_accessors) @@ -282,6 +282,20 @@ static inline bool irqd_is_wakeup_armed(struct irq_data *d) return __irqd_to_state(d) & IRQD_WAKEUP_ARMED; } +static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU; +} + +static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU; +} /* * Functions for chained handlers which can be enabled/disabled by the @@ -461,14 +475,14 @@ static inline int irq_set_parent(int irq, int parent_irq) * Built-in IRQ handlers for various IRQ types, * callable via desc->handle_irq() */ -extern void handle_level_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc); -extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc); +extern void handle_level_irq(struct irq_desc *desc); +extern void handle_fasteoi_irq(struct irq_desc *desc); +extern void handle_edge_irq(struct irq_desc *desc); +extern void handle_edge_eoi_irq(struct irq_desc *desc); +extern void handle_simple_irq(struct irq_desc *desc); +extern void handle_percpu_irq(struct irq_desc *desc); +extern void handle_percpu_devid_irq(struct irq_desc *desc); +extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); @@ -627,23 +641,23 @@ static inline void *irq_data_get_irq_chip_data(struct irq_data *d) static inline void *irq_get_handler_data(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->handler_data : NULL; + return d ? d->common->handler_data : NULL; } static inline void *irq_data_get_irq_handler_data(struct irq_data *d) { - return d->handler_data; + return d->common->handler_data; } static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->msi_desc : NULL; + return d ? d->common->msi_desc : NULL; } static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d) { - return d->msi_desc; + return d->common->msi_desc; } static inline u32 irq_get_trigger_type(unsigned int irq) @@ -652,21 +666,30 @@ static inline u32 irq_get_trigger_type(unsigned int irq) return d ? irqd_get_trigger_type(d) : 0; } -static inline int irq_data_get_node(struct irq_data *d) +static inline int irq_common_data_get_node(struct irq_common_data *d) { +#ifdef CONFIG_NUMA return d->node; +#else + return 0; +#endif +} + +static inline int irq_data_get_node(struct irq_data *d) +{ + return irq_common_data_get_node(d->common); } static inline struct cpumask *irq_get_affinity_mask(int irq) { struct irq_data *d = irq_get_irq_data(irq); - return d ? d->affinity : NULL; + return d ? d->common->affinity : NULL; } static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d) { - return d->affinity; + return d->common->affinity; } unsigned int arch_dynirq_lower_bound(unsigned int from); diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 5acfa26602e1..a587a33363c7 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -98,11 +98,7 @@ extern struct irq_desc irq_desc[NR_IRQS]; static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) { -#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY - return irq_to_desc(data->irq); -#else - return container_of(data, struct irq_desc, irq_data); -#endif + return container_of(data->common, struct irq_desc, irq_common_data); } static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) @@ -127,23 +123,21 @@ static inline void *irq_desc_get_chip_data(struct irq_desc *desc) static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { - return desc->irq_data.handler_data; + return desc->irq_common_data.handler_data; } static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) { - return desc->irq_data.msi_desc; + return desc->irq_common_data.msi_desc; } /* * Architectures call this to let the generic IRQ layer - * handle an interrupt. If the descriptor is attached to an - * irqchip-style controller then we call the ->handle_irq() handler, - * and it calls __do_IRQ() if it's attached to an irqtype-style controller. + * handle an interrupt. */ -static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc) +static inline void generic_handle_irq_desc(struct irq_desc *desc) { - desc->handle_irq(irq, desc); + desc->handle_irq(desc); } int generic_handle_irq(unsigned int irq); @@ -176,29 +170,6 @@ static inline int irq_has_action(unsigned int irq) return irq_desc_has_action(irq_to_desc(irq)); } -/* caller has locked the irq_desc and both params are valid */ -static inline void __irq_set_handler_locked(unsigned int irq, - irq_flow_handler_t handler) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - desc->handle_irq = handler; -} - -/* caller has locked the irq_desc and both params are valid */ -static inline void -__irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip, - irq_flow_handler_t handler, const char *name) -{ - struct irq_desc *desc; - - desc = irq_to_desc(irq); - irq_desc_get_irq_data(desc)->chip = chip; - desc->handle_irq = handler; - desc->name = name; -} - /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h index 62d543004197..661bed0ed1f3 100644 --- a/include/linux/irqhandler.h +++ b/include/linux/irqhandler.h @@ -8,7 +8,7 @@ struct irq_desc; struct irq_data; -typedef void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc); +typedef void (*irq_flow_handler_t)(struct irq_desc *desc); typedef void (*irq_preflow_handler_t)(struct irq_data *data); #endif diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 7f653e8f6690..f1094238ab2a 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -21,8 +21,8 @@ * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); - * static_key_likely() - * statick_key_unlikely() + * static_branch_likely() + * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we @@ -45,12 +45,10 @@ * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * - * In addtion to static_branch_{enable,disable}, we can also reference count + * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and - * static_branch_dec() as a 'make more false'. The inc()/dec() - * interface is meant to be used exclusively from the inc()/dec() for a given - * key. + * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). diff --git a/include/linux/mm.h b/include/linux/mm.h index fda728e3c27d..91c08f6f0dc9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -20,6 +20,7 @@ #include <linux/shrinker.h> #include <linux/resource.h> #include <linux/page_ext.h> +#include <linux/err.h> struct mempolicy; struct anon_vma; @@ -1214,6 +1215,49 @@ long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, int write, int force, struct page **pages); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); + +/* Container for pinned pfns / pages */ +struct frame_vector { + unsigned int nr_allocated; /* Number of frames we have space for */ + unsigned int nr_frames; /* Number of frames stored in ptrs array */ + bool got_ref; /* Did we pin pages by getting page ref? */ + bool is_pfns; /* Does array contain pages or pfns? */ + void *ptrs[0]; /* Array of pinned pfns / pages. Use + * pfns_vector_pages() or pfns_vector_pfns() + * for access */ +}; + +struct frame_vector *frame_vector_create(unsigned int nr_frames); +void frame_vector_destroy(struct frame_vector *vec); +int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, + bool write, bool force, struct frame_vector *vec); +void put_vaddr_frames(struct frame_vector *vec); +int frame_vector_to_pages(struct frame_vector *vec); +void frame_vector_to_pfns(struct frame_vector *vec); + +static inline unsigned int frame_vector_count(struct frame_vector *vec) +{ + return vec->nr_frames; +} + +static inline struct page **frame_vector_pages(struct frame_vector *vec) +{ + if (vec->is_pfns) { + int err = frame_vector_to_pages(vec); + + if (err) + return ERR_PTR(err); + } + return (struct page **)(vec->ptrs); +} + +static inline unsigned long *frame_vector_pfns(struct frame_vector *vec) +{ + if (!vec->is_pfns) + frame_vector_to_pfns(vec); + return (unsigned long *)(vec->ptrs); +} + struct kvec; int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b791405958b4..d2ffeafc9998 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -507,6 +507,7 @@ static inline void napi_enable(struct napi_struct *n) BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state)); smp_mb__before_atomic(); clear_bit(NAPI_STATE_SCHED, &n->state); + clear_bit(NAPI_STATE_NPSVC, &n->state); } #ifdef CONFIG_SMP diff --git a/include/linux/ntb.h b/include/linux/ntb.h index b02f72bb8e32..f798e2afba88 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -522,10 +522,9 @@ static inline int ntb_mw_clear_trans(struct ntb_dev *ntb, int idx) * @speed: OUT - The link speed expressed as PCIe generation number. * @width: OUT - The link width expressed as the number of PCIe lanes. * - * Set the translation of a memory window. The peer may access local memory - * through the window starting at the address, up to the size. The address - * must be aligned to the alignment specified by ntb_mw_get_range(). The size - * must be aligned to the size alignment specified by ntb_mw_get_range(). + * Get the current state of the ntb link. It is recommended to query the link + * state once after every link event. It is safe to query the link state in + * the context of the link event callback. * * Return: One if the link is up, zero if the link is down, otherwise a * negative value indicating the error number. @@ -795,7 +794,7 @@ static inline int ntb_peer_db_set(struct ntb_dev *ntb, u64 db_bits) } /** - * ntb_peer_db_clear() - clear bits in the local doorbell register + * ntb_peer_db_clear() - clear bits in the peer doorbell register * @ntb: NTB device context. * @db_bits: Doorbell bits to clear. * diff --git a/include/linux/ntb_transport.h b/include/linux/ntb_transport.h index 2862861366a5..7243eb98a722 100644 --- a/include/linux/ntb_transport.h +++ b/include/linux/ntb_transport.h @@ -83,3 +83,4 @@ void *ntb_transport_rx_remove(struct ntb_transport_qp *qp, unsigned int *len); void ntb_transport_link_up(struct ntb_transport_qp *qp); void ntb_transport_link_down(struct ntb_transport_qp *qp); bool ntb_transport_link_query(struct ntb_transport_qp *qp); +unsigned int ntb_transport_tx_free_entry(struct ntb_transport_qp *qp); diff --git a/include/linux/phy.h b/include/linux/phy.h index 962387a192f1..4a4e3a092337 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -19,6 +19,7 @@ #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/mii.h> +#include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> @@ -153,6 +154,7 @@ struct sk_buff; * PHYs should register using this structure */ struct mii_bus { + struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; @@ -198,7 +200,8 @@ static inline struct mii_bus *mdiobus_alloc(void) return mdiobus_alloc_size(0); } -int mdiobus_register(struct mii_bus *bus); +int __mdiobus_register(struct mii_bus *bus, struct module *owner); +#define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); @@ -742,6 +745,7 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, int phy_id, struct phy_c45_device_ids *c45_ids); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); +void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index cab7ba55bedb..e817722ee3f0 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -34,6 +34,7 @@ bool dev_pm_opp_is_turbo(struct dev_pm_opp *opp); int dev_pm_opp_get_opp_count(struct device *dev); unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev); +struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev); struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, @@ -80,6 +81,11 @@ static inline unsigned long dev_pm_opp_get_max_clock_latency(struct device *dev) return 0; } +static inline struct dev_pm_opp *dev_pm_opp_get_suspend_opp(struct device *dev) +{ + return NULL; +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, unsigned long freq, bool available) { diff --git a/include/linux/sched.h b/include/linux/sched.h index a4ab9daa387c..b7b9501b41af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -762,6 +762,18 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif +#ifdef CONFIG_CGROUPS + /* + * group_rwsem prevents new tasks from entering the threadgroup and + * member tasks from exiting,a more specifically, setting of + * PF_EXITING. fork and exit paths are protected with this rwsem + * using threadgroup_change_begin/end(). Users which require + * threadgroup to remain stable should use threadgroup_[un]lock() + * which also takes care of exec path. Currently, cgroup is the + * only user. + */ + struct rw_semaphore group_rwsem; +#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ diff --git a/include/linux/security.h b/include/linux/security.h index 79d85ddf8093..2f4c1f7aa7db 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg4, unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5); + return cap_task_prctl(option, arg2, arg3, arg4, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index adeadbd6d7bf..dde00defbaa5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -114,13 +114,18 @@ int seq_open(struct file *, const struct seq_operations *); ssize_t seq_read(struct file *, char __user *, size_t, loff_t *); loff_t seq_lseek(struct file *, loff_t, int); int seq_release(struct inode *, struct file *); -int seq_escape(struct seq_file *, const char *, const char *); -int seq_putc(struct seq_file *m, char c); -int seq_puts(struct seq_file *m, const char *s); int seq_write(struct seq_file *seq, const void *data, size_t len); -__printf(2, 3) int seq_printf(struct seq_file *, const char *, ...); -__printf(2, 0) int seq_vprintf(struct seq_file *, const char *, va_list args); +__printf(2, 0) +void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); +__printf(2, 3) +void seq_printf(struct seq_file *m, const char *fmt, ...); +void seq_putc(struct seq_file *m, char c); +void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull(struct seq_file *m, char delimiter, + unsigned long long num); +void seq_put_decimal_ll(struct seq_file *m, char delimiter, long long num); +void seq_escape(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, @@ -138,10 +143,6 @@ int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); int seq_open_private(struct file *, const struct seq_operations *, int); int seq_release_private(struct inode *, struct file *); -int seq_put_decimal_ull(struct seq_file *m, char delimiter, - unsigned long long num); -int seq_put_decimal_ll(struct seq_file *m, char delimiter, - long long num); static inline struct user_namespace *seq_user_ns(struct seq_file *seq) { diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2738d355cdf9..2b0a30a6e31c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -179,6 +179,9 @@ struct nf_bridge_info { u8 bridged_dnat:1; __u16 frag_max_size; struct net_device *physindev; + + /* always valid & non-NULL from FORWARD on, for physdev match */ + struct net_device *physoutdev; union { /* prerouting: detect dnat in orig/reply direction */ __be32 ipv4_daddr; @@ -189,9 +192,6 @@ struct nf_bridge_info { * skb is out in neigh layer. */ char neigh_header[8]; - - /* always valid & non-NULL from FORWARD on, for physdev match */ - struct net_device *physoutdev; }; }; #endif @@ -2707,6 +2707,9 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, { if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) <= len) + skb->ip_summed = CHECKSUM_NONE; } unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 269e8afd3e2a..6b00f18f5e6b 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -34,7 +34,7 @@ extern struct bus_type spi_bus_type; /** * struct spi_statistics - statistics for spi transfers - * @clock: lock protecting this structure + * @lock: lock protecting this structure * * @messages: number of spi-messages handled * @transfers: number of spi_transfers handled diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7591788e9fbf..357e44c1a46b 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -42,6 +42,7 @@ struct sock_xprt { /* * Connection of transports */ + unsigned long sock_state; struct delayed_work connect_worker; struct sockaddr_storage srcaddr; unsigned short srcport; @@ -76,6 +77,8 @@ struct sock_xprt { */ #define TCP_RPC_REPLY (1UL << 6) +#define XPRT_SOCK_CONNECTING 1U + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_XPRTSOCK_H */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 08001317aee7..a460e2ef2843 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -885,4 +885,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); +asmlinkage long sys_membarrier(int cmd, int flags); + #endif diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 037e9df2f610..157d366e761b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -92,23 +92,19 @@ struct thermal_zone_device_ops { struct thermal_cooling_device *); int (*unbind) (struct thermal_zone_device *, struct thermal_cooling_device *); - int (*get_temp) (struct thermal_zone_device *, unsigned long *); + int (*get_temp) (struct thermal_zone_device *, int *); int (*get_mode) (struct thermal_zone_device *, enum thermal_device_mode *); int (*set_mode) (struct thermal_zone_device *, enum thermal_device_mode); int (*get_trip_type) (struct thermal_zone_device *, int, enum thermal_trip_type *); - int (*get_trip_temp) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_temp) (struct thermal_zone_device *, int, - unsigned long); - int (*get_trip_hyst) (struct thermal_zone_device *, int, - unsigned long *); - int (*set_trip_hyst) (struct thermal_zone_device *, int, - unsigned long); - int (*get_crit_temp) (struct thermal_zone_device *, unsigned long *); - int (*set_emul_temp) (struct thermal_zone_device *, unsigned long); + int (*get_trip_temp) (struct thermal_zone_device *, int, int *); + int (*set_trip_temp) (struct thermal_zone_device *, int, int); + int (*get_trip_hyst) (struct thermal_zone_device *, int, int *); + int (*set_trip_hyst) (struct thermal_zone_device *, int, int); + int (*get_crit_temp) (struct thermal_zone_device *, int *); + int (*set_emul_temp) (struct thermal_zone_device *, int); int (*get_trend) (struct thermal_zone_device *, int, enum thermal_trend *); int (*notify) (struct thermal_zone_device *, int, @@ -332,9 +328,9 @@ struct thermal_genl_event { * temperature. */ struct thermal_zone_of_device_ops { - int (*get_temp)(void *, long *); + int (*get_temp)(void *, int *); int (*get_trend)(void *, long *); - int (*set_emul_temp)(void *, unsigned long); + int (*set_emul_temp)(void *, int); }; /** @@ -364,7 +360,7 @@ static inline struct thermal_zone_device * thermal_zone_of_sensor_register(struct device *dev, int id, void *data, const struct thermal_zone_of_device_ops *ops) { - return NULL; + return ERR_PTR(-ENODEV); } static inline @@ -384,6 +380,8 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) int power_actor_get_max_power(struct thermal_cooling_device *, struct thermal_zone_device *tz, u32 *max_power); +int power_actor_get_min_power(struct thermal_cooling_device *, + struct thermal_zone_device *tz, u32 *min_power); int power_actor_set_power(struct thermal_cooling_device *, struct thermal_instance *, u32); struct thermal_zone_device *thermal_zone_device_register(const char *, int, int, @@ -406,7 +404,7 @@ thermal_of_cooling_device_register(struct device_node *np, char *, void *, const struct thermal_cooling_device_ops *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); -int thermal_zone_get_temp(struct thermal_zone_device *tz, unsigned long *temp); +int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); int get_tz_trend(struct thermal_zone_device *, int); struct thermal_instance *get_thermal_instance(struct thermal_zone_device *, @@ -419,6 +417,10 @@ static inline bool cdev_is_power_actor(struct thermal_cooling_device *cdev) static inline int power_actor_get_max_power(struct thermal_cooling_device *cdev, struct thermal_zone_device *tz, u32 *max_power) { return 0; } +static inline int power_actor_get_min_power(struct thermal_cooling_device *cdev, + struct thermal_zone_device *tz, + u32 *min_power) +{ return -ENODEV; } static inline int power_actor_set_power(struct thermal_cooling_device *cdev, struct thermal_instance *tz, u32 power) { return 0; } @@ -457,7 +459,7 @@ static inline struct thermal_zone_device *thermal_zone_get_zone_by_name( const char *name) { return ERR_PTR(-ENODEV); } static inline int thermal_zone_get_temp( - struct thermal_zone_device *tz, unsigned long *temp) + struct thermal_zone_device *tz, int *temp) { return -ENODEV; } static inline int get_tz_trend(struct thermal_zone_device *tz, int trip) { return -ENODEV; } diff --git a/include/linux/tick.h b/include/linux/tick.h index 48d901f83f92..e312219ff823 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -147,11 +147,20 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(void); #else +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } diff --git a/include/linux/wait.h b/include/linux/wait.h index d3d077228d4c..1e1bf9f963a9 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -147,8 +147,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) typedef int wait_bit_action_f(struct wait_bit_key *); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key); +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr); void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr); @@ -180,7 +179,7 @@ wait_queue_head_t *bit_waitqueue(void *, int); #define wake_up_poll(x, m) \ __wake_up(x, TASK_NORMAL, 1, (void *) (m)) #define wake_up_locked_poll(x, m) \ - __wake_up_locked_key((x), TASK_NORMAL, 1, (void *) (m)) + __wake_up_locked_key((x), TASK_NORMAL, (void *) (m)) #define wake_up_interruptible_poll(x, m) \ __wake_up(x, TASK_INTERRUPTIBLE, 1, (void *) (m)) #define wake_up_interruptible_sync_poll(x, m) \ |