diff options
Diffstat (limited to 'include/linux')
68 files changed, 564 insertions, 362 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 054833939995..1991aea2ec4c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -870,8 +870,8 @@ static inline int acpi_dev_get_property(struct acpi_device *adev, } static inline int acpi_node_get_property_reference(struct fwnode_handle *fwnode, - const char *name, const char *cells_name, - size_t index, struct acpi_reference_args *args) + const char *name, size_t index, + struct acpi_reference_args *args) { return -ENXIO; } diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2b8ed123ad36..defeaac0745f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift) */ static inline __u32 rol32(__u32 word, unsigned int shift) { - return (word << shift) | (word >> (32 - shift)); + return (word << shift) | (word >> ((-shift) & 31)); } /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0d2b7927c1f..c70e3588a48c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -254,6 +254,7 @@ struct queue_limits { unsigned long virt_boundary_mask; unsigned int max_hw_sectors; + unsigned int max_dev_sectors; unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; @@ -773,7 +774,6 @@ extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, unsigned int len); -extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, @@ -797,6 +797,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int blk_queue_enter(struct request_queue *q, gfp_t gfp); extern void blk_queue_exit(struct request_queue *q); extern void blk_start_queue(struct request_queue *q); +extern void blk_start_queue_async(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); @@ -960,7 +961,6 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *, extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); -extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index de464e6683b6..83d1926c61e4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -40,6 +40,7 @@ struct bpf_map { struct user_struct *user; const struct bpf_map_ops *ops; struct work_struct work; + atomic_t usercnt; }; struct bpf_map_type_list { @@ -167,8 +168,10 @@ struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); -struct bpf_map *bpf_map_get(u32 ufd); +struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); +void bpf_map_inc(struct bpf_map *map, bool uref); +void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); extern int sysctl_unprivileged_bpf_disabled; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 60d44b26276d..06b77f9dd3f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -90,7 +90,6 @@ enum { */ struct cgroup_file { /* do not access any fields from outside cgroup core */ - struct list_head node; /* anchored at css->files */ struct kernfs_node *kn; }; @@ -134,9 +133,6 @@ struct cgroup_subsys_state { */ u64 serial_nr; - /* all cgroup_files associated with this css */ - struct list_head files; - /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; @@ -426,12 +422,9 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 22e3754f89c5..cb91b44f5f78 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); +void cgroup_file_notify(struct cgroup_file *cfile); char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); @@ -119,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it); @@ -235,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor + * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple - * processes. When there are multiple tasks in @tset, if a task of a - * process is in @tset, all tasks of the process are in @tset. Also, all - * are guaranteed to share the same source and destination csses. + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor + * @dst_css: the destination css * @tset: takset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ -#define cgroup_taskset_for_each_leader(leader, tset) \ - for ((leader) = cgroup_taskset_first((tset)); (leader); \ - (leader) = cgroup_taskset_next((tset))) \ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else @@ -516,19 +528,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -/** - * cgroup_file_notify - generate a file modified event for a cgroup_file - * @cfile: target cgroup_file - * - * @cfile must have been obtained by setting cftype->file_offset. - */ -static inline void cgroup_file_notify(struct cgroup_file *cfile) -{ - /* might not have been created due to one of the CFTYPE selector flags */ - if (cfile->kn) - kernfs_notify(cfile->kn); -} - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 4dac1036594f..00b042c49ccd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -299,6 +299,23 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s __u.__val; \ }) +/** + * smp_cond_acquire() - Spin wait for cond with ACQUIRE ordering + * @cond: boolean expression to wait for + * + * Equivalent to using smp_load_acquire() on the condition variable but employs + * the control dependency of the wait to reduce the barrier on many platforms. + * + * The control dependency provides a LOAD->STORE order, the additional RMB + * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order, + * aka. ACQUIRE. + */ +#define smp_cond_acquire(cond) do { \ + while (!(cond)) \ + cpu_relax(); \ + smp_rmb(); /* ctrl + rmb := acquire */ \ +} while (0) + #endif /* __KERNEL__ */ #endif /* __ASSEMBLY__ */ diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 68b575afe5f5..d259274238db 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -86,7 +86,7 @@ static inline void context_tracking_init(void) { } #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static inline void guest_enter(void) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_enter(current); else current->flags |= PF_VCPU; @@ -100,7 +100,7 @@ static inline void guest_exit(void) if (context_tracking_is_enabled()) __context_tracking_exit(CONTEXT_GUEST); - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index ee956c528fab..1d34fe68f48a 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -22,12 +22,12 @@ struct context_tracking { }; #ifdef CONFIG_CONTEXT_TRACKING -extern struct static_key context_tracking_enabled; +extern struct static_key_false context_tracking_enabled; DECLARE_PER_CPU(struct context_tracking, context_tracking); static inline bool context_tracking_is_enabled(void) { - return static_key_false(&context_tracking_enabled); + return static_branch_unlikely(&context_tracking_enabled); } static inline bool context_tracking_cpu_is_enabled(void) diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ef4c5b1a860f..177c7680c1a8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -77,6 +77,7 @@ struct cpufreq_policy { unsigned int suspend_freq; /* freq to set during suspend */ unsigned int policy; /* see above */ + unsigned int last_policy; /* policy before unplug */ struct cpufreq_governor *governor; /* see below */ void *governor_data; bool governor_enabled; /* governor start/stop flag */ diff --git a/include/linux/delayed_call.h b/include/linux/delayed_call.h new file mode 100644 index 000000000000..f7fa76ae1a9b --- /dev/null +++ b/include/linux/delayed_call.h @@ -0,0 +1,34 @@ +#ifndef _DELAYED_CALL_H +#define _DELAYED_CALL_H + +/* + * Poor man's closures; I wish we could've done them sanely polymorphic, + * but... + */ + +struct delayed_call { + void (*fn)(void *); + void *arg; +}; + +#define DEFINE_DELAYED_CALL(name) struct delayed_call name = {NULL, NULL} + +/* I really wish we had closures with sane typechecking... */ +static inline void set_delayed_call(struct delayed_call *call, + void (*fn)(void *), void *arg) +{ + call->fn = fn; + call->arg = arg; +} + +static inline void do_delayed_call(struct delayed_call *call) +{ + if (call->fn) + call->fn(call->arg); +} + +static inline void clear_delayed_call(struct delayed_call *call) +{ + call->fn = NULL; +} +#endif diff --git a/include/linux/dns_resolver.h b/include/linux/dns_resolver.h index cc92268af89a..6ac3cad9aef1 100644 --- a/include/linux/dns_resolver.h +++ b/include/linux/dns_resolver.h @@ -27,7 +27,7 @@ #ifdef __KERNEL__ extern int dns_query(const char *type, const char *name, size_t namelen, - const char *options, char **_result, time_t *_expiry); + const char *options, char **_result, time64_t *_expiry); #endif /* KERNEL */ diff --git a/include/linux/enclosure.h b/include/linux/enclosure.h index 7be22da321f3..a4cf57cd0f75 100644 --- a/include/linux/enclosure.h +++ b/include/linux/enclosure.h @@ -29,7 +29,11 @@ /* A few generic types ... taken from ses-2 */ enum enclosure_component_type { ENCLOSURE_COMPONENT_DEVICE = 0x01, + ENCLOSURE_COMPONENT_CONTROLLER_ELECTRONICS = 0x07, + ENCLOSURE_COMPONENT_SCSI_TARGET_PORT = 0x14, + ENCLOSURE_COMPONENT_SCSI_INITIATOR_PORT = 0x15, ENCLOSURE_COMPONENT_ARRAY_DEVICE = 0x17, + ENCLOSURE_COMPONENT_SAS_EXPANDER = 0x18, }; /* ses-2 common element status */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 4165e9ac9e36..5972ffe5719a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -493,6 +493,25 @@ static inline void bpf_jit_free(struct bpf_prog *fp) #define BPF_ANC BIT(15) +static inline bool bpf_needs_clear_a(const struct sock_filter *first) +{ + switch (first->code) { + case BPF_RET | BPF_K: + case BPF_LD | BPF_W | BPF_LEN: + return false; + + case BPF_LD | BPF_W | BPF_ABS: + case BPF_LD | BPF_H | BPF_ABS: + case BPF_LD | BPF_B | BPF_ABS: + if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) + return true; + return false; + + default: + return true; + } +} + static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..ef3cd36689f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -31,6 +31,7 @@ #include <linux/blk_types.h> #include <linux/workqueue.h> #include <linux/percpu-rwsem.h> +#include <linux/delayed_call.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -1633,12 +1634,11 @@ struct file_operations { struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); - const char * (*follow_link) (struct dentry *, void **); + const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); - void (*put_link) (struct inode *, void *); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); @@ -2736,14 +2736,14 @@ extern const struct file_operations generic_ro_fops; extern int readlink_copy(char __user *, int, const char *); extern int page_readlink(struct dentry *, char __user *, int); -extern const char *page_follow_link_light(struct dentry *, void **); -extern void page_put_link(struct inode *, void *); +extern const char *page_get_link(struct dentry *, struct inode *, + struct delayed_call *); +extern void page_put_link(void *); extern int __page_symlink(struct inode *inode, const char *symname, int len, int nofs); extern int page_symlink(struct inode *inode, const char *symname, int len); extern const struct inode_operations page_symlink_inode_operations; -extern void kfree_put_link(struct inode *, void *); -extern void free_page_put_link(struct inode *, void *); +extern void kfree_link(void *); extern int generic_readlink(struct dentry *, char __user *, int); extern void generic_fillattr(struct inode *, struct kstat *); int vfs_getattr_nosec(struct path *path, struct kstat *stat); @@ -2754,7 +2754,8 @@ void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); -const char *simple_follow_link(struct dentry *, void **); +const char *simple_get_link(struct dentry *, struct inode *, + struct delayed_call *); extern const struct inode_operations simple_symlink_inode_operations; extern int iterate_dir(struct file *, struct dir_context *); @@ -2764,8 +2765,6 @@ extern int vfs_lstat(const char __user *, struct kstat *); extern int vfs_fstat(unsigned int, struct kstat *); extern int vfs_fstatat(int , const char __user *, struct kstat *, int); -extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, - unsigned long arg); extern int __generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, loff_t start, loff_t len, @@ -3025,5 +3024,6 @@ static inline bool dir_relax(struct inode *inode) } extern bool path_noexec(const struct path *path); +extern void inode_nohighmem(struct inode *inode); #endif /* _LINUX_FS_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index eae6548efbf0..60048c50404e 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -586,6 +586,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); extern void ftrace_enable_daemon(void); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 1c1ff7e4faa4..f2cb8d45513d 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -150,7 +150,7 @@ extern struct task_group root_task_group; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN # define INIT_VTIME(tsk) \ - .vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock), \ + .vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount), \ .vtime_snap = 0, \ .vtime_snap_whence = VTIME_SYS, #else diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0ef2a97ccdb5..402753bccafa 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -227,7 +227,7 @@ struct ipv6_pinfo { struct ipv6_ac_socklist *ipv6_ac_list; struct ipv6_fl_socklist __rcu *ipv6_fl_list; - struct ipv6_txoptions *opt; + struct ipv6_txoptions __rcu *opt; struct sk_buff *pktoptions; struct sk_buff *rxpmtu; struct inet6_cork cork; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c9ae0c6ec050..d5d798b35c1f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -330,6 +330,7 @@ struct rdists { }; struct irq_domain; +struct device_node; int its_cpu_init(void); int its_init(struct device_node *node, struct rdists *rdists, struct irq_domain *domain); diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8dde55974f18..0536524bb9eb 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -5,7 +5,7 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> - * Copyright (C) 2011-2012 Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 350dfb08aee3..7311c3294e25 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -255,6 +255,7 @@ extern long (*panic_blink)(int state); __printf(1, 2) void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic_self_stop(struct pt_regs *); extern void oops_enter(void); extern void oops_exit(void); void print_oops_end_marker(void); @@ -446,6 +447,33 @@ extern int sysctl_panic_on_stackoverflow; extern bool crash_kexec_post_notifiers; /* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * A variant of panic() called from NMI context. We return if we've already + * panicked on this CPU. If another CPU already panicked, loop in + * nmi_panic_self_stop() which can provide architecture dependent code such + * as saving register state for crash dump. + */ +#define nmi_panic(regs, fmt, ...) \ +do { \ + int old_cpu, cpu; \ + \ + cpu = raw_smp_processor_id(); \ + old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, cpu); \ + \ + if (old_cpu == PANIC_CPU_INVALID) \ + panic(fmt, ##__VA_ARGS__); \ + else if (old_cpu != cpu) \ + nmi_panic_self_stop(regs); \ +} while (0) + +/* * Only to be used by arch init code. If the user over-wrote the default * CONFIG_PANIC_TIMEOUT, honor it. */ diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d140b1e9faa7..7b68d2788a56 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -237,6 +237,7 @@ extern int kexec_purgatory_get_set_symbol(struct kimage *image, unsigned int size, bool get_value); extern void *kexec_purgatory_get_symbol_addr(struct kimage *image, const char *name); +extern void __crash_kexec(struct pt_regs *); extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); @@ -332,6 +333,7 @@ int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, #else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; +static inline void __crash_kexec(struct pt_regs *regs) { } static inline void crash_kexec(struct pt_regs *regs) { } static inline int kexec_should_crash(struct task_struct *p) { return 0; } #define kexec_in_progress false diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index d0a1f99e24e3..4894c6888bc6 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -25,7 +25,7 @@ #ifdef CONFIG_DEBUG_KMEMLEAK -extern void kmemleak_init(void) __ref; +extern void kmemleak_init(void) __init; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, diff --git a/include/linux/kref.h b/include/linux/kref.h index 484604d184be..e15828fd71f1 100644 --- a/include/linux/kref.h +++ b/include/linux/kref.h @@ -19,7 +19,6 @@ #include <linux/atomic.h> #include <linux/kernel.h> #include <linux/mutex.h> -#include <linux/spinlock.h> struct kref { atomic_t refcount; @@ -99,38 +98,6 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref) return kref_sub(kref, 1, release); } -/** - * kref_put_spinlock_irqsave - decrement refcount for object. - * @kref: object. - * @release: pointer to the function that will clean up the object when the - * last reference to the object is released. - * This pointer is required, and it is not acceptable to pass kfree - * in as this function. - * @lock: lock to take in release case - * - * Behaves identical to kref_put with one exception. If the reference count - * drops to zero, the lock will be taken atomically wrt dropping the reference - * count. The release function has to call spin_unlock() without _irqrestore. - */ -static inline int kref_put_spinlock_irqsave(struct kref *kref, - void (*release)(struct kref *kref), - spinlock_t *lock) -{ - unsigned long flags; - - WARN_ON(release == NULL); - if (atomic_add_unless(&kref->refcount, -1, 1)) - return 0; - spin_lock_irqsave(lock, flags); - if (atomic_dec_and_test(&kref->refcount)) { - release(kref); - local_irq_restore(flags); - return 1; - } - spin_unlock_irqrestore(lock, flags); - return 0; -} - static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5706a2108f0a..c923350ca20a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -460,6 +460,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ idx++) +static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) + if (vcpu->vcpu_id == id) + return vcpu; + return NULL; +} + #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\ diff --git a/include/linux/libata.h b/include/linux/libata.h index 83577f8fd15b..600c1e0626a5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */ diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 69c9057e1ab8..034117b3be5f 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -50,15 +50,21 @@ enum { NVM_IO_DUAL_ACCESS = 0x1, NVM_IO_QUAD_ACCESS = 0x2, + /* NAND Access Modes */ NVM_IO_SUSPEND = 0x80, NVM_IO_SLC_MODE = 0x100, NVM_IO_SCRAMBLE_DISABLE = 0x200, + + /* Block Types */ + NVM_BLK_T_FREE = 0x0, + NVM_BLK_T_BAD = 0x1, + NVM_BLK_T_DEV = 0x2, + NVM_BLK_T_HOST = 0x4, }; struct nvm_id_group { u8 mtype; u8 fmtype; - u16 res16; u8 num_ch; u8 num_lun; u8 num_pln; @@ -74,9 +80,9 @@ struct nvm_id_group { u32 tbet; u32 tbem; u32 mpos; + u32 mccap; u16 cpar; - u8 res[913]; -} __packed; +}; struct nvm_addr_format { u8 ch_offset; @@ -91,19 +97,15 @@ struct nvm_addr_format { u8 pg_len; u8 sect_offset; u8 sect_len; - u8 res[4]; }; struct nvm_id { u8 ver_id; u8 vmnt; u8 cgrps; - u8 res[5]; u32 cap; u32 dom; struct nvm_addr_format ppaf; - u8 ppat; - u8 resv[224]; struct nvm_id_group groups[4]; } __packed; @@ -123,39 +125,28 @@ struct nvm_tgt_instance { #define NVM_VERSION_MINOR 0 #define NVM_VERSION_PATCH 0 -#define NVM_SEC_BITS (8) -#define NVM_PL_BITS (6) -#define NVM_PG_BITS (16) #define NVM_BLK_BITS (16) -#define NVM_LUN_BITS (10) +#define NVM_PG_BITS (16) +#define NVM_SEC_BITS (8) +#define NVM_PL_BITS (8) +#define NVM_LUN_BITS (8) #define NVM_CH_BITS (8) struct ppa_addr { + /* Generic structure for all addresses */ union { - /* Channel-based PPA format in nand 4x2x2x2x8x10 */ - struct { - u64 ch : 4; - u64 sec : 2; /* 4 sectors per page */ - u64 pl : 2; /* 4 planes per LUN */ - u64 lun : 2; /* 4 LUNs per channel */ - u64 pg : 8; /* 256 pages per block */ - u64 blk : 10;/* 1024 blocks per plane */ - u64 resved : 36; - } chnl; - - /* Generic structure for all addresses */ struct { + u64 blk : NVM_BLK_BITS; + u64 pg : NVM_PG_BITS; u64 sec : NVM_SEC_BITS; u64 pl : NVM_PL_BITS; - u64 pg : NVM_PG_BITS; - u64 blk : NVM_BLK_BITS; u64 lun : NVM_LUN_BITS; u64 ch : NVM_CH_BITS; } g; u64 ppa; }; -} __packed; +}; struct nvm_rq { struct nvm_tgt_instance *ins; @@ -191,18 +182,18 @@ static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) struct nvm_block; typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); -typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *); -typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *); -typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32, +typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *); +typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *); +typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, nvm_l2p_update_fn *, void *); -typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int, +typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int, nvm_bb_update_fn *, void *); -typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int); -typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *); -typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *); -typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *); +typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int); +typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *); +typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); -typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t, +typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, dma_addr_t *); typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); @@ -210,7 +201,7 @@ struct nvm_dev_ops { nvm_id_fn *identity; nvm_get_l2p_tbl_fn *get_l2p_tbl; nvm_op_bb_tbl_fn *get_bb_tbl; - nvm_op_set_bb_fn *set_bb; + nvm_op_set_bb_fn *set_bb_tbl; nvm_submit_io_fn *submit_io; nvm_erase_blk_fn *erase_block; @@ -220,7 +211,7 @@ struct nvm_dev_ops { nvm_dev_dma_alloc_fn *dev_dma_alloc; nvm_dev_dma_free_fn *dev_dma_free; - uint8_t max_phys_sect; + unsigned int max_phys_sect; }; struct nvm_lun { @@ -229,7 +220,9 @@ struct nvm_lun { int lun_id; int chnl_id; + unsigned int nr_inuse_blocks; /* Number of used blocks */ unsigned int nr_free_blocks; /* Number of unused blocks */ + unsigned int nr_bad_blocks; /* Number of bad blocks */ struct nvm_block *blocks; spinlock_t lock; @@ -263,8 +256,7 @@ struct nvm_dev { int blks_per_lun; int sec_size; int oob_size; - int addr_mode; - struct nvm_addr_format addr_format; + struct nvm_addr_format ppaf; /* Calculated/Cached values. These do not reflect the actual usable * blocks at run-time. @@ -290,118 +282,45 @@ struct nvm_dev { char name[DISK_NAME_LEN]; }; -/* fallback conversion */ -static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev, - struct ppa_addr r) +static inline struct ppa_addr generic_to_dev_addr(struct nvm_dev *dev, + struct ppa_addr r) { struct ppa_addr l; - l.ppa = r.g.sec + - r.g.pg * dev->sec_per_pg + - r.g.blk * (dev->pgs_per_blk * - dev->sec_per_pg) + - r.g.lun * (dev->blks_per_lun * - dev->pgs_per_blk * - dev->sec_per_pg) + - r.g.ch * (dev->blks_per_lun * - dev->pgs_per_blk * - dev->luns_per_chnl * - dev->sec_per_pg); + l.ppa = ((u64)r.g.blk) << dev->ppaf.blk_offset; + l.ppa |= ((u64)r.g.pg) << dev->ppaf.pg_offset; + l.ppa |= ((u64)r.g.sec) << dev->ppaf.sect_offset; + l.ppa |= ((u64)r.g.pl) << dev->ppaf.pln_offset; + l.ppa |= ((u64)r.g.lun) << dev->ppaf.lun_offset; + l.ppa |= ((u64)r.g.ch) << dev->ppaf.ch_offset; return l; } -/* fallback conversion */ -static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev, - struct ppa_addr r) +static inline struct ppa_addr dev_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) { struct ppa_addr l; - int secs, pgs, blks, luns; - sector_t ppa = r.ppa; - - l.ppa = 0; - - div_u64_rem(ppa, dev->sec_per_pg, &secs); - l.g.sec = secs; - sector_div(ppa, dev->sec_per_pg); - div_u64_rem(ppa, dev->sec_per_blk, &pgs); - l.g.pg = pgs; - - sector_div(ppa, dev->pgs_per_blk); - div_u64_rem(ppa, dev->blks_per_lun, &blks); - l.g.blk = blks; - - sector_div(ppa, dev->blks_per_lun); - div_u64_rem(ppa, dev->luns_per_chnl, &luns); - l.g.lun = luns; - - sector_div(ppa, dev->luns_per_chnl); - l.g.ch = ppa; - - return l; -} - -static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r) -{ - struct ppa_addr l; - - l.ppa = 0; - - l.chnl.sec = r.g.sec; - l.chnl.pl = r.g.pl; - l.chnl.pg = r.g.pg; - l.chnl.blk = r.g.blk; - l.chnl.lun = r.g.lun; - l.chnl.ch = r.g.ch; - - return l; -} - -static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r) -{ - struct ppa_addr l; - - l.ppa = 0; - - l.g.sec = r.chnl.sec; - l.g.pl = r.chnl.pl; - l.g.pg = r.chnl.pg; - l.g.blk = r.chnl.blk; - l.g.lun = r.chnl.lun; - l.g.ch = r.chnl.ch; + /* + * (r.ppa << X offset) & X len bitmask. X eq. blk, pg, etc. + */ + l.g.blk = (r.ppa >> dev->ppaf.blk_offset) & + (((1 << dev->ppaf.blk_len) - 1)); + l.g.pg |= (r.ppa >> dev->ppaf.pg_offset) & + (((1 << dev->ppaf.pg_len) - 1)); + l.g.sec |= (r.ppa >> dev->ppaf.sect_offset) & + (((1 << dev->ppaf.sect_len) - 1)); + l.g.pl |= (r.ppa >> dev->ppaf.pln_offset) & + (((1 << dev->ppaf.pln_len) - 1)); + l.g.lun |= (r.ppa >> dev->ppaf.lun_offset) & + (((1 << dev->ppaf.lun_len) - 1)); + l.g.ch |= (r.ppa >> dev->ppaf.ch_offset) & + (((1 << dev->ppaf.ch_len) - 1)); return l; } -static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev, - struct ppa_addr gppa) -{ - switch (dev->addr_mode) { - case NVM_ADDRMODE_LINEAR: - return __linear_to_generic_addr(dev, gppa); - case NVM_ADDRMODE_CHANNEL: - return __chnl_to_generic_addr(gppa); - default: - BUG(); - } - return gppa; -} - -static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev, - struct ppa_addr gppa) -{ - switch (dev->addr_mode) { - case NVM_ADDRMODE_LINEAR: - return __generic_to_linear_addr(dev, gppa); - case NVM_ADDRMODE_CHANNEL: - return __generic_to_chnl_addr(gppa); - default: - BUG(); - } - return gppa; -} - static inline int ppa_empty(struct ppa_addr ppa_addr) { return (ppa_addr.ppa == ADDR_EMPTY); @@ -468,7 +387,7 @@ typedef int (nvmm_end_io_fn)(struct nvm_rq *, int); typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, unsigned long); typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); -typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *); +typedef void (nvmm_lun_info_print_fn)(struct nvm_dev *); struct nvmm_type { const char *name; @@ -492,7 +411,7 @@ struct nvmm_type { nvmm_get_lun_fn *get_lun; /* Statistics */ - nvmm_free_blocks_print_fn *free_blocks_print; + nvmm_lun_info_print_fn *lun_info_print; struct list_head list; }; diff --git a/include/linux/list.h b/include/linux/list.h index 993395a2e55c..5356f4d661a7 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -24,7 +24,7 @@ static inline void INIT_LIST_HEAD(struct list_head *list) { - list->next = list; + WRITE_ONCE(list->next, list); list->prev = list; } @@ -42,7 +42,7 @@ static inline void __list_add(struct list_head *new, next->prev = new; new->next = next; new->prev = prev; - prev->next = new; + WRITE_ONCE(prev->next, new); } #else extern void __list_add(struct list_head *new, @@ -186,7 +186,7 @@ static inline int list_is_last(const struct list_head *list, */ static inline int list_empty(const struct list_head *head) { - return head->next == head; + return READ_ONCE(head->next) == head; } /** @@ -608,7 +608,7 @@ static inline int hlist_unhashed(const struct hlist_node *h) static inline int hlist_empty(const struct hlist_head *h) { - return !h->first; + return !READ_ONCE(h->first); } static inline void __hlist_del(struct hlist_node *n) @@ -642,7 +642,7 @@ static inline void hlist_add_head(struct hlist_node *n, struct hlist_head *h) n->next = first; if (first) first->pprev = &n->next; - h->first = n; + WRITE_ONCE(h->first, n); n->pprev = &h->first; } @@ -653,14 +653,14 @@ static inline void hlist_add_before(struct hlist_node *n, n->pprev = next->pprev; n->next = next; next->pprev = &n->next; - *(n->pprev) = n; + WRITE_ONCE(*(n->pprev), n); } static inline void hlist_add_behind(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; - prev->next = n; + WRITE_ONCE(prev->next, n); n->pprev = &prev->next; if (n->next) diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h index 8132214e8efd..ee7229a6c06a 100644 --- a/include/linux/list_bl.h +++ b/include/linux/list_bl.h @@ -70,7 +70,7 @@ static inline void hlist_bl_set_first(struct hlist_bl_head *h, static inline int hlist_bl_empty(const struct hlist_bl_head *h) { - return !((unsigned long)h->first & ~LIST_BL_LOCKMASK); + return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h index 444d2b1313bd..b01fe1009084 100644 --- a/include/linux/list_nulls.h +++ b/include/linux/list_nulls.h @@ -57,7 +57,7 @@ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { - return is_a_nulls(h->first); + return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 70400dc7660f..c57e424d914b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7501626ab529..d3133be12d92 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -427,6 +427,17 @@ enum { }; enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX4_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + +enum { MLX4_DEV_PMC_SUBTYPE_GUID_INFO = 0x14, MLX4_DEV_PMC_SUBTYPE_PORT_INFO = 0x15, MLX4_DEV_PMC_SUBTYPE_PKEY_TABLE = 0x16, diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 877ef226f90f..772362adf471 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -1,6 +1,7 @@ #ifndef LINUX_MM_DEBUG_H #define LINUX_MM_DEBUG_H 1 +#include <linux/bug.h> #include <linux/stringify.h> struct page; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index c8723b62c4cd..bc742dac7d3a 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -25,7 +25,7 @@ #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST -#define SNOR_MFR_WINBOND 0xef +#define SNOR_MFR_WINBOND 0xef /* Also used by some Spansion */ /* * Note on opcode nomenclature: some opcodes have a format like diff --git a/include/linux/net.h b/include/linux/net.h index 70ac5e28e6b7..0b4ac7da583a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -34,8 +34,12 @@ struct inode; struct file; struct net; -#define SOCK_ASYNC_NOSPACE 0 -#define SOCK_ASYNC_WAITDATA 1 +/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located + * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. + * Eventually all flags will be in sk->sk_wq_flags. + */ +#define SOCKWQ_ASYNC_NOSPACE 0 +#define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 @@ -89,6 +93,7 @@ struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; + unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; @@ -96,7 +101,7 @@ struct socket_wq { * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) - * @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc) + * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation @@ -202,7 +207,7 @@ enum { SOCK_WAKE_URG, }; -int sock_wake_async(struct socket *sk, int how, int band); +int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); int __sock_create(struct net *net, int family, int type, int proto, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 67bfac1abfc1..3143c847bddb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1398,7 +1398,8 @@ enum netdev_priv_flags { * @dma: DMA channel * @mtu: Interface MTU value * @type: Interface hardware type - * @hard_header_len: Hardware header length + * @hard_header_len: Hardware header length, which means that this is the + * minimum size of a packet. * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed @@ -2083,7 +2084,7 @@ struct pcpu_sw_netstats { }) #define netdev_alloc_pcpu_stats(type) \ - __netdev_alloc_pcpu_stats(type, GFP_KERNEL); + __netdev_alloc_pcpu_stats(type, GFP_KERNEL) #include <linux/notifier.h> diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 249d1bb01e03..5646b24bfc64 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -14,7 +14,7 @@ struct nfnl_callback { int (*call_rcu)(struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); - int (*call_batch)(struct sock *nl, struct sk_buff *skb, + int (*call_batch)(struct net *net, struct sock *nl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const cda[]); const struct nla_policy *policy; /* netlink attribute policy */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c0e961474a52..37a3d2981352 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -359,6 +359,7 @@ extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int nfs_revalidate_inode_rcu(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); +extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_revalidate_mapping_protected(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 570d630f98ae..11bbae44f4cb 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -251,6 +251,7 @@ struct nfs4_layoutget { struct nfs4_layoutget_res res; struct rpc_cred *cred; gfp_t gfp_flags; + long timeout; }; struct nfs4_getdeviceinfo_args { diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 039f2eec49ce..1e0deb8e8494 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -46,12 +46,14 @@ extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); +extern struct device_node *of_irq_find_parent(struct device_node *child); extern struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token); extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid); extern void of_msi_configure(struct device *dev, struct device_node *np); +u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -70,6 +72,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev, { return 0; } +static inline void *of_irq_find_parent(struct device_node *child) +{ + return NULL; +} + static inline struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token) @@ -84,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev static inline void of_msi_configure(struct device *dev, struct device_node *np) { } +static inline u32 of_msi_map_rid(struct device *dev, + struct device_node *msi_np, u32 rid_in) +{ + return rid_in; +} #endif #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC) @@ -93,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np) * so declare it here regardless of the CONFIG_OF_IRQ setting. */ extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else /* !CONFIG_OF && !CONFIG_SPARC */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, @@ -101,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, { return 0; } - -static inline u32 of_msi_map_rid(struct device *dev, - struct device_node *msi_np, u32 rid_in) -{ - return rid_in; -} #endif /* !CONFIG_OF */ #endif /* __OF_IRQ_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index e828e7b4afec..6ae25aae88fd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -412,9 +412,18 @@ struct pci_host_bridge { void (*release_fn)(struct pci_host_bridge *); void *release_data; unsigned int ignore_reset_delay:1; /* for entire hierarchy */ + /* Resource alignment requirements */ + resource_size_t (*align_resource)(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align); }; #define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) + +struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus); + void pci_set_host_bridge_release(struct pci_host_bridge *bridge, void (*release_fn)(struct pci_host_bridge *), void *release_data); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d841d33bcdc9..f9828a48f16a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -697,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ diff --git a/include/linux/platform_data/edma.h b/include/linux/platform_data/edma.h index e2878baeb90e..4299f4ba03bd 100644 --- a/include/linux/platform_data/edma.h +++ b/include/linux/platform_data/edma.h @@ -72,7 +72,7 @@ struct edma_soc_info { struct edma_rsv_info *rsv; /* List of channels allocated for memcpy, terminated with -1 */ - s16 *memcpy_channels; + s32 *memcpy_channels; s8 (*queue_priority_mapping)[2]; const s16 (*xbar_chans)[2]; diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index 6f14ee295822..e5e8ec40278d 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -9,16 +9,12 @@ #ifndef _POSIX_ACL_XATTR_H #define _POSIX_ACL_XATTR_H +#include <uapi/linux/xattr.h> #include <linux/posix_acl.h> -/* Extended attribute names */ -#define POSIX_ACL_XATTR_ACCESS "system.posix_acl_access" -#define POSIX_ACL_XATTR_DEFAULT "system.posix_acl_default" - /* Supported ACL a_version fields */ #define POSIX_ACL_XATTR_VERSION 0x0002 - /* An undefined entry e_id value */ #define ACL_UNDEFINED_ID (-1) diff --git a/include/linux/proportions.h b/include/linux/proportions.h index 5440f64d2942..21221338ad18 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 6a4347639c03..1d1ba2c5ee7a 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -9,6 +9,8 @@ #ifndef __COMMON_HSI__ #define __COMMON_HSI__ +#define CORE_SPQE_PAGE_SIZE_BYTES 4096 + #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 4 #define FW_REVISION_VERSION 2 diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index b920c3605c46..41b9049b57e2 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -111,7 +111,8 @@ static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) used = ((u32)0x10000u + (u32)(p_chain->prod_idx)) - (u32)p_chain->cons_idx; if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= (used / p_chain->elem_per_page); + used -= p_chain->prod_idx / p_chain->elem_per_page - + p_chain->cons_idx / p_chain->elem_per_page; return p_chain->capacity - used; } diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 5ed540986019..14ec1652daf4 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -179,32 +179,31 @@ static inline void list_replace_rcu(struct list_head *old, } /** - * list_splice_init_rcu - splice an RCU-protected list into an existing list. + * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice - * @head: the place in the list to splice the first list into + * @prev: points to the last element of the existing list + * @next: points to the first element of the existing list * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... * - * @head can be RCU-read traversed concurrently with this function. + * The list pointed to by @prev and @next can be RCU-read traversed + * concurrently with this function. * * Note that this function blocks. * - * Important note: the caller must take whatever action is necessary to - * prevent any other updates to @head. In principle, it is possible - * to modify the list as soon as sync() begins execution. - * If this sort of thing becomes necessary, an alternative version - * based on call_rcu() could be created. But only if -really- - * needed -- there is no shortage of RCU API members. + * Important note: the caller must take whatever action is necessary to prevent + * any other updates to the existing list. In principle, it is possible to + * modify the list as soon as sync() begins execution. If this sort of thing + * becomes necessary, an alternative version based on call_rcu() could be + * created. But only if -really- needed -- there is no shortage of RCU API + * members. */ -static inline void list_splice_init_rcu(struct list_head *list, - struct list_head *head, - void (*sync)(void)) +static inline void __list_splice_init_rcu(struct list_head *list, + struct list_head *prev, + struct list_head *next, + void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; - struct list_head *at = head->next; - - if (list_empty(list)) - return; /* * "first" and "last" tracking list, so initialize it. RCU readers @@ -231,10 +230,40 @@ static inline void list_splice_init_rcu(struct list_head *list, * this function. */ - last->next = at; - rcu_assign_pointer(list_next_rcu(head), first); - first->prev = head; - at->prev = last; + last->next = next; + rcu_assign_pointer(list_next_rcu(prev), first); + first->prev = prev; + next->prev = last; +} + +/** + * list_splice_init_rcu - splice an RCU-protected list into an existing list, + * designed for stacks. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head, head->next, sync); +} + +/** + * list_splice_tail_init_rcu - splice an RCU-protected list into an existing + * list, designed for queues. + * @list: the RCU-protected list to splice + * @head: the place in the existing list to splice the first list into + * @sync: function to sync: synchronize_rcu(), synchronize_sched(), ... + */ +static inline void list_splice_tail_init_rcu(struct list_head *list, + struct list_head *head, + void (*sync)(void)) +{ + if (!list_empty(list)) + __list_splice_init_rcu(list, head->prev, head, sync); } /** @@ -305,6 +334,42 @@ static inline void list_splice_init_rcu(struct list_head *list, pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** + * list_entry_lockless - get the struct for this entry + * @ptr: the &struct list_head pointer. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_entry_lockless(ptr, type, member) \ + container_of((typeof(ptr))lockless_dereference(ptr), type, member) + +/** + * list_for_each_entry_lockless - iterate over rcu list of given type + * @pos: the type * to use as a loop cursor. + * @head: the head for your list. + * @member: the name of the list_struct within the struct. + * + * This primitive may safely run concurrently with the _rcu list-mutation + * primitives such as list_add_rcu(), but requires some implicit RCU + * read-side guarding. One example is running within a special + * exception-time environment where preemption is disabled and where + * lockdep cannot be invoked (in which case updaters must use RCU-sched, + * as in synchronize_sched(), call_rcu_sched(), and friends). Another + * example is when items are added to the list, but never deleted. + */ +#define list_for_each_entry_lockless(pos, head, member) \ + for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ + &pos->member != (head); \ + pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) + +/** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index a0189ba67fde..14e6f47ee16f 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -48,10 +48,17 @@ #include <asm/barrier.h> +#ifndef CONFIG_TINY_RCU extern int rcu_expedited; /* for sysctl */ +extern int rcu_normal; /* also for sysctl */ +#endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_TINY_RCU /* Tiny RCU doesn't expedite, as its purpose in life is instead to be tiny. */ +static inline bool rcu_gp_is_normal(void) /* Internal RCU use. */ +{ + return true; +} static inline bool rcu_gp_is_expedited(void) /* Internal RCU use. */ { return false; @@ -65,6 +72,7 @@ static inline void rcu_unexpedite_gp(void) { } #else /* #ifdef CONFIG_TINY_RCU */ +bool rcu_gp_is_normal(void); /* Internal RCU use. */ bool rcu_gp_is_expedited(void); /* Internal RCU use. */ void rcu_expedite_gp(void); void rcu_unexpedite_gp(void); @@ -321,7 +329,6 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -void rcu_end_inkernel_boot(void); void rcu_sched_qs(void); void rcu_bh_qs(void); void rcu_check_callbacks(int user); @@ -329,6 +336,12 @@ struct notifier_block; int rcu_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu); +#ifndef CONFIG_TINY_RCU +void rcu_end_inkernel_boot(void); +#else /* #ifndef CONFIG_TINY_RCU */ +static inline void rcu_end_inkernel_boot(void) { } +#endif /* #ifndef CONFIG_TINY_RCU */ + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); @@ -379,9 +392,9 @@ static inline void rcu_init_nohz(void) */ #define RCU_NONIDLE(a) \ do { \ - rcu_irq_enter(); \ + rcu_irq_enter_irqson(); \ do { a; } while (0); \ - rcu_irq_exit(); \ + rcu_irq_exit_irqson(); \ } while (0) /* @@ -741,7 +754,7 @@ static inline void rcu_preempt_sleep_check(void) * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * - * The tracing version of rcu_dereference_raw() must not call + * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 4c1aaf9cce7b..64809aea661c 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -181,6 +181,14 @@ static inline void rcu_irq_enter(void) { } +static inline void rcu_irq_exit_irqson(void) +{ +} + +static inline void rcu_irq_enter_irqson(void) +{ +} + static inline void rcu_irq_exit(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 60d15a080d7c..ad1eda9fa4da 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -37,7 +37,7 @@ void rcu_cpu_stall_reset(void); /* * Note a virtualization-based context switch. This is simply a * wrapper around rcu_note_context_switch(), which allows TINY_RCU - * to save a few bytes. + * to save a few bytes. The caller must have disabled interrupts. */ static inline void rcu_virt_note_context_switch(int cpu) { @@ -97,6 +97,8 @@ void rcu_idle_enter(void); void rcu_idle_exit(void); void rcu_irq_enter(void); void rcu_irq_exit(void); +void rcu_irq_enter_irqson(void); +void rcu_irq_exit_irqson(void); void exit_rcu(void); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 843ceca9a21e..e50b31d18462 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -19,6 +19,7 @@ #include <linux/atomic.h> #include <linux/compiler.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/jhash.h> #include <linux/list_nulls.h> @@ -339,10 +340,11 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl, int rhashtable_init(struct rhashtable *ht, const struct rhashtable_params *params); -int rhashtable_insert_slow(struct rhashtable *ht, const void *key, - struct rhash_head *obj, - struct bucket_table *old_tbl); -int rhashtable_insert_rehash(struct rhashtable *ht); +struct bucket_table *rhashtable_insert_slow(struct rhashtable *ht, + const void *key, + struct rhash_head *obj, + struct bucket_table *old_tbl); +int rhashtable_insert_rehash(struct rhashtable *ht, struct bucket_table *tbl); int rhashtable_walk_init(struct rhashtable *ht, struct rhashtable_iter *iter); void rhashtable_walk_exit(struct rhashtable_iter *iter); @@ -598,9 +600,11 @@ restart: new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(new_tbl)) { - err = rhashtable_insert_slow(ht, key, obj, new_tbl); - if (err == -EAGAIN) + tbl = rhashtable_insert_slow(ht, key, obj, new_tbl); + if (!IS_ERR_OR_NULL(tbl)) goto slow_path; + + err = PTR_ERR(tbl); goto out; } @@ -611,7 +615,7 @@ restart: if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); - err = rhashtable_insert_rehash(ht); + err = rhashtable_insert_rehash(ht, tbl); rcu_read_unlock(); if (err) return err; diff --git a/include/linux/sched.h b/include/linux/sched.h index edad7a43edea..0c0e78102850 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -177,9 +177,9 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -extern void update_cpu_load_nohz(void); +extern void update_cpu_load_nohz(int active); #else -static inline void update_cpu_load_nohz(void) { } +static inline void update_cpu_load_nohz(int active) { } #endif extern unsigned long get_parent_ip(unsigned long addr); @@ -1268,8 +1268,13 @@ struct sched_entity { #endif #ifdef CONFIG_SMP - /* Per entity load average tracking */ - struct sched_avg avg; + /* + * Per entity load average tracking. + * + * Put into separate cache line so it does not + * collide with read-mostly values above. + */ + struct sched_avg avg ____cacheline_aligned_in_smp; #endif }; @@ -1455,14 +1460,15 @@ struct task_struct { /* Used for emulating ABI behavior of previous Linux versions */ unsigned int personality; - unsigned in_execve:1; /* Tell the LSMs that the process is doing an - * execve */ - unsigned in_iowait:1; - - /* Revert to default priority/policy when forking */ + /* scheduler bits, serialized by scheduler locks */ unsigned sched_reset_on_fork:1; unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; + unsigned :0; /* force alignment to the next boundary */ + + /* unserialized, strictly 'current' */ + unsigned in_execve:1; /* bit to tell LSMs we're in execve */ + unsigned in_iowait:1; #ifdef CONFIG_MEMCG unsigned memcg_may_oom:1; #endif @@ -1519,11 +1525,14 @@ struct task_struct { cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN - seqlock_t vtime_seqlock; + seqcount_t vtime_seqcount; unsigned long long vtime_snap; enum { - VTIME_SLEEPING = 0, + /* Task is sleeping or running in a CPU with VTIME inactive */ + VTIME_INACTIVE = 0, + /* Task runs in userspace in a CPU with VTIME active */ VTIME_USER, + /* Task runs in kernelspace in a CPU with VTIME active */ VTIME_SYS, } vtime_snap_whence; #endif @@ -2002,7 +2011,8 @@ static inline int pid_alive(const struct task_struct *p) } /** - * is_global_init - check if a task structure is init + * is_global_init - check if a task structure is init. Since init + * is free to have sub-threads we need to check tgid. * @tsk: Task structure to be checked. * * Check if a task structure is the first user space task the kernel created. @@ -2011,7 +2021,7 @@ static inline int pid_alive(const struct task_struct *p) */ static inline int is_global_init(struct task_struct *tsk) { - return tsk->pid == 1; + return task_tgid_nr(tsk) == 1; } extern struct pid *cad_pid; diff --git a/include/linux/scpi_protocol.h b/include/linux/scpi_protocol.h index 80af3cd35ae4..72ce932c69b2 100644 --- a/include/linux/scpi_protocol.h +++ b/include/linux/scpi_protocol.h @@ -71,7 +71,7 @@ struct scpi_ops { int (*sensor_get_value)(u16, u32 *); }; -#if IS_ENABLED(CONFIG_ARM_SCPI_PROTOCOL) +#if IS_REACHABLE(CONFIG_ARM_SCPI_PROTOCOL) struct scpi_ops *get_scpi_ops(void); #else static inline struct scpi_ops *get_scpi_ops(void) { return NULL; } diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0adedca24c5b..3cc9632dcc2a 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -29,7 +29,7 @@ struct cpu_stop_work { int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg); int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg); -void stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, +bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf); int stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); int try_stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg); @@ -65,7 +65,7 @@ static void stop_one_cpu_nowait_workfn(struct work_struct *work) preempt_enable(); } -static inline void stop_one_cpu_nowait(unsigned int cpu, +static inline bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg, struct cpu_stop_work *work_buf) { @@ -74,7 +74,10 @@ static inline void stop_one_cpu_nowait(unsigned int cpu, work_buf->fn = fn; work_buf->arg = arg; schedule_work(&work_buf->work); + return true; } + + return false; } static inline int stop_cpus(const struct cpumask *cpumask, @@ -99,7 +102,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * grabbing every spinlock (and more). So the "read" side to such a * lock is anything which disables preemption. */ -#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) /** * stop_machine: freeze the machine on all CPUs and run this function @@ -118,7 +121,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); -#else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ static inline int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) @@ -137,5 +140,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return stop_machine(fn, data, cpus); } -#endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a156b82dd14c..c2b66a277e98 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -524,7 +524,7 @@ asmlinkage long sys_chown(const char __user *filename, asmlinkage long sys_lchown(const char __user *filename, uid_t user, gid_t group); asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group); -#ifdef CONFIG_UID16 +#ifdef CONFIG_HAVE_UID16 asmlinkage long sys_chown16(const char __user *filename, old_uid_t user, old_gid_t group); asmlinkage long sys_lchown16(const char __user *filename, diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 4014a59828fc..613c29bd6baf 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -438,7 +438,8 @@ static inline void thermal_zone_device_unregister( static inline int thermal_zone_bind_cooling_device( struct thermal_zone_device *tz, int trip, struct thermal_cooling_device *cdev, - unsigned long upper, unsigned long lower) + unsigned long upper, unsigned long lower, + unsigned int weight) { return -ENODEV; } static inline int thermal_zone_unbind_cooling_device( struct thermal_zone_device *tz, int trip, diff --git a/include/linux/tracepoint-defs.h b/include/linux/tracepoint-defs.h new file mode 100644 index 000000000000..e1ee97c713bf --- /dev/null +++ b/include/linux/tracepoint-defs.h @@ -0,0 +1,27 @@ +#ifndef TRACEPOINT_DEFS_H +#define TRACEPOINT_DEFS_H 1 + +/* + * File can be included directly by headers who only want to access + * tracepoint->key to guard out of line trace calls. Otherwise + * linux/tracepoint.h should be used. + */ + +#include <linux/atomic.h> +#include <linux/static_key.h> + +struct tracepoint_func { + void *func; + void *data; + int prio; +}; + +struct tracepoint { + const char *name; /* Tracepoint name */ + struct static_key key; + void (*regfunc)(void); + void (*unregfunc)(void); + struct tracepoint_func __rcu *funcs; +}; + +#endif diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 696a339c592c..78e8397a1800 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -17,26 +17,12 @@ #include <linux/errno.h> #include <linux/types.h> #include <linux/rcupdate.h> -#include <linux/static_key.h> +#include <linux/tracepoint-defs.h> struct module; struct tracepoint; struct notifier_block; -struct tracepoint_func { - void *func; - void *data; - int prio; -}; - -struct tracepoint { - const char *name; /* Tracepoint name */ - struct static_key key; - void (*regfunc)(void); - void (*unregfunc)(void); - struct tracepoint_func __rcu *funcs; -}; - struct trace_enum_map { const char *system; const char *enum_string; @@ -171,8 +157,8 @@ extern void syscall_unregfunc(void); TP_PROTO(data_proto), \ TP_ARGS(data_args), \ TP_CONDITION(cond), \ - rcu_irq_enter(), \ - rcu_irq_exit()); \ + rcu_irq_enter_irqson(), \ + rcu_irq_exit_irqson()); \ } #else #define __DECLARE_TRACE_RCU(name, proto, args, cond, data_proto, data_args) diff --git a/include/linux/types.h b/include/linux/types.h index 70d8500bddf1..70dd3dfde631 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -35,7 +35,7 @@ typedef __kernel_gid16_t gid16_t; typedef unsigned long uintptr_t; -#ifdef CONFIG_UID16 +#ifdef CONFIG_HAVE_UID16 /* This is defined by include/asm-{arch}/posix_types.h */ typedef __kernel_old_uid_t old_uid_t; typedef __kernel_old_gid_t old_gid_t; diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0bdc72f36905..4a29c75b146e 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/errno.h> diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h index 1f6526c76ee8..3a375d07d0dc 100644 --- a/include/linux/usb/cdc_ncm.h +++ b/include/linux/usb/cdc_ncm.h @@ -138,6 +138,7 @@ struct cdc_ncm_ctx { }; u8 cdc_ncm_select_altsetting(struct usb_interface *intf); +int cdc_ncm_change_mtu(struct net_device *net, int new_mtu); int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags); void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf); struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign); diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 9948c874e3f1..1d0043dc34e4 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -47,4 +47,7 @@ /* device generates spurious wakeup, ignore remote wakeup capability */ #define USB_QUIRK_IGNORE_REMOTE_WAKEUP BIT(9) +/* device can't handle Link Power Management */ +#define USB_QUIRK_NO_LPM BIT(10) + #endif /* __LINUX_USB_QUIRKS_H */ diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 610a86a892b8..ddb440975382 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,9 +44,6 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; -extern struct iommu_group *vfio_iommu_group_get(struct device *dev); -extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); - extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 5dbc8b0ee567..3e5d9075960f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -176,11 +176,11 @@ extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp); #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d)) #ifdef CONFIG_SMP -void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int); +void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); -void mod_zone_page_state(struct zone *, enum zone_stat_item, int); +void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); @@ -205,7 +205,7 @@ void set_pgdat_percpu_threshold(pg_data_t *pgdat, * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, - enum zone_stat_item item, int delta) + enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } diff --git a/include/linux/vtime.h b/include/linux/vtime.h index c5165fd256f9..fa2196990f84 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -10,16 +10,27 @@ struct task_struct; /* - * vtime_accounting_enabled() definitions/declarations + * vtime_accounting_cpu_enabled() definitions/declarations */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -static inline bool vtime_accounting_enabled(void) { return true; } +static inline bool vtime_accounting_cpu_enabled(void) { return true; } #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN +/* + * Checks if vtime is enabled on some CPU. Cputime readers want to be careful + * in that case and compute the tickless cputime. + * For now vtime state is tied to context tracking. We might want to decouple + * those later if necessary. + */ static inline bool vtime_accounting_enabled(void) { - if (context_tracking_is_enabled()) { + return context_tracking_is_enabled(); +} + +static inline bool vtime_accounting_cpu_enabled(void) +{ + if (vtime_accounting_enabled()) { if (context_tracking_cpu_is_enabled()) return true; } @@ -29,7 +40,7 @@ static inline bool vtime_accounting_enabled(void) #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ #ifndef CONFIG_VIRT_CPU_ACCOUNTING -static inline bool vtime_accounting_enabled(void) { return false; } +static inline bool vtime_accounting_cpu_enabled(void) { return false; } #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ @@ -44,7 +55,7 @@ extern void vtime_task_switch(struct task_struct *prev); extern void vtime_common_task_switch(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_task_switch(prev); } #endif /* __ARCH_HAS_VTIME_TASK_SWITCH */ @@ -59,7 +70,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk); extern void vtime_common_account_irq_enter(struct task_struct *tsk); static inline void vtime_account_irq_enter(struct task_struct *tsk) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_common_account_irq_enter(tsk); } #endif /* __ARCH_HAS_VTIME_ACCOUNT */ @@ -78,7 +89,7 @@ extern void vtime_gen_account_irq_exit(struct task_struct *tsk); static inline void vtime_account_irq_exit(struct task_struct *tsk) { - if (vtime_accounting_enabled()) + if (vtime_accounting_cpu_enabled()) vtime_gen_account_irq_exit(tsk); } diff --git a/include/linux/wait.h b/include/linux/wait.h index 1e1bf9f963a9..d2f4ec7dba7c 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -102,6 +102,36 @@ init_waitqueue_func_entry(wait_queue_t *q, wait_queue_func_t func) q->func = func; } +/** + * waitqueue_active -- locklessly test for waiters on the queue + * @q: the waitqueue to test for waiters + * + * returns true if the wait list is not empty + * + * NOTE: this function is lockless and requires care, incorrect usage _will_ + * lead to sporadic and non-obvious failure. + * + * Use either while holding wait_queue_head_t::lock or when used for wakeups + * with an extra smp_mb() like: + * + * CPU0 - waker CPU1 - waiter + * + * for (;;) { + * @cond = true; prepare_to_wait(&wq, &wait, state); + * smp_mb(); // smp_mb() from set_current_state() + * if (waitqueue_active(wq)) if (@cond) + * wake_up(wq); break; + * schedule(); + * } + * finish_wait(&wq, &wait); + * + * Because without the explicit smp_mb() it's possible for the + * waitqueue_active() load to get hoisted over the @cond store such that we'll + * observe an empty wait list while the waiter might not observe @cond. + * + * Also note that this 'optimization' trades a spin_lock() for an smp_mb(), + * which (when the lock is uncontended) are of roughly equal cost. + */ static inline int waitqueue_active(wait_queue_head_t *q) { return !list_empty(&q->task_list); @@ -145,7 +175,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } -typedef int wait_bit_action_f(struct wait_bit_key *); +typedef int wait_bit_action_f(struct wait_bit_key *, int mode); 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, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); @@ -960,10 +990,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); } while (0) -extern int bit_wait(struct wait_bit_key *); -extern int bit_wait_io(struct wait_bit_key *); -extern int bit_wait_timeout(struct wait_bit_key *); -extern int bit_wait_io_timeout(struct wait_bit_key *); +extern int bit_wait(struct wait_bit_key *, int); +extern int bit_wait_io(struct wait_bit_key *, int); +extern int bit_wait_timeout(struct wait_bit_key *, int); +extern int bit_wait_io_timeout(struct wait_bit_key *, int); /** * wait_on_bit - wait for a bit to be cleared diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 89474b9d260c..4457541de3c9 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -19,12 +19,16 @@ struct inode; struct dentry; +/* + * struct xattr_handler: When @name is set, match attributes with exactly that + * name. When @prefix is set instead, match attributes with that prefix and + * with a non-empty suffix. + */ struct xattr_handler { + const char *name; const char *prefix; int flags; /* fs private flags */ - size_t (*list)(const struct xattr_handler *, struct dentry *dentry, - char *list, size_t list_size, const char *name, - size_t name_len); + bool (*list)(struct dentry *dentry); int (*get)(const struct xattr_handler *, struct dentry *dentry, const char *name, void *buffer, size_t size); int (*set)(const struct xattr_handler *, struct dentry *dentry, @@ -53,8 +57,11 @@ int generic_setxattr(struct dentry *dentry, const char *name, const void *value, int generic_removexattr(struct dentry *dentry, const char *name); ssize_t vfs_getxattr_alloc(struct dentry *dentry, const char *name, char **xattr_value, size_t size, gfp_t flags); -int vfs_xattr_cmp(struct dentry *dentry, const char *xattr_name, - const char *value, size_t size, gfp_t flags); + +static inline const char *xattr_prefix(const struct xattr_handler *handler) +{ + return handler->prefix ?: handler->name; +} struct simple_xattrs { struct list_head head; @@ -95,8 +102,7 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, void *buffer, size_t size); int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, const void *value, size_t size, int flags); -int simple_xattr_remove(struct simple_xattrs *xattrs, const char *name); -ssize_t simple_xattr_list(struct simple_xattrs *xattrs, char *buffer, +ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, char *buffer, size_t size); void simple_xattr_list_add(struct simple_xattrs *xattrs, struct simple_xattr *new_xattr); |