diff options
| author | Tejun Heo <tj@kernel.org> | 2015-11-03 17:29:03 -0500 |
|---|---|---|
| committer | Tejun Heo <tj@kernel.org> | 2015-11-03 17:29:03 -0500 |
| commit | 159b5bb46492e4dcef2070b12861030bc360402b (patch) | |
| tree | 93de7d6e94a059aade50ee5437de6a50ccd1cf7b /include/linux | |
| parent | 56e74338a535cbcc2f2da08b1ea1a92920194364 (diff) | |
| parent | 469eabb3aec03d9defed3462df743a223a5c8f54 (diff) | |
| download | lwn-159b5bb46492e4dcef2070b12861030bc360402b.tar.gz lwn-159b5bb46492e4dcef2070b12861030bc360402b.zip | |
Merge branch 'for-4.3-fixes' into for-4.4
Diffstat (limited to 'include/linux')
81 files changed, 1908 insertions, 475 deletions
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h index 6a0a89ed7f81..0ddb5c02ad8b 100644 --- a/include/linux/amba/serial.h +++ b/include/linux/amba/serial.h @@ -33,14 +33,12 @@ #define UART01x_DR 0x00 /* Data read or written from the interface. */ #define UART01x_RSR 0x04 /* Receive status register (Read). */ #define UART01x_ECR 0x04 /* Error clear register (Write). */ -#define ZX_UART01x_DR 0x04 /* Data read or written from the interface. */ #define UART010_LCRH 0x08 /* Line control register, high byte. */ #define ST_UART011_DMAWM 0x08 /* DMA watermark configure register. */ #define UART010_LCRM 0x0C /* Line control register, middle byte. */ #define ST_UART011_TIMEOUT 0x0C /* Timeout period register. */ #define UART010_LCRL 0x10 /* Line control register, low byte. */ #define UART010_CR 0x14 /* Control register. */ -#define ZX_UART01x_FR 0x14 /* Flag register (Read only). */ #define UART01x_FR 0x18 /* Flag register (Read only). */ #define UART010_IIR 0x1C /* Interrupt identification register (Read). */ #define UART010_ICR 0x1C /* Interrupt clear register (Write). */ @@ -51,21 +49,13 @@ #define UART011_LCRH 0x2c /* Line control register. */ #define ST_UART011_LCRH_TX 0x2c /* Tx Line control register. */ #define UART011_CR 0x30 /* Control register. */ -#define ZX_UART011_LCRH_TX 0x30 /* Tx Line control register. */ #define UART011_IFLS 0x34 /* Interrupt fifo level select. */ -#define ZX_UART011_CR 0x34 /* Control register. */ -#define ZX_UART011_IFLS 0x38 /* Interrupt fifo level select. */ #define UART011_IMSC 0x38 /* Interrupt mask. */ #define UART011_RIS 0x3c /* Raw interrupt status. */ #define UART011_MIS 0x40 /* Masked interrupt status. */ -#define ZX_UART011_IMSC 0x40 /* Interrupt mask. */ #define UART011_ICR 0x44 /* Interrupt clear register. */ -#define ZX_UART011_RIS 0x44 /* Raw interrupt status. */ #define UART011_DMACR 0x48 /* DMA control register. */ -#define ZX_UART011_MIS 0x48 /* Masked interrupt status. */ -#define ZX_UART011_ICR 0x4c /* Interrupt clear register. */ #define ST_UART011_XFCR 0x50 /* XON/XOFF control register. */ -#define ZX_UART011_DMACR 0x50 /* DMA control register. */ #define ST_UART011_XON1 0x54 /* XON1 register. */ #define ST_UART011_XON2 0x58 /* XON2 register. */ #define ST_UART011_XOFF1 0x5C /* XON1 register. */ @@ -85,19 +75,15 @@ #define UART01x_RSR_PE 0x02 #define UART01x_RSR_FE 0x01 -#define ZX_UART01x_FR_BUSY 0x300 #define UART011_FR_RI 0x100 #define UART011_FR_TXFE 0x080 #define UART011_FR_RXFF 0x040 #define UART01x_FR_TXFF 0x020 #define UART01x_FR_RXFE 0x010 #define UART01x_FR_BUSY 0x008 -#define ZX_UART01x_FR_DSR 0x008 #define UART01x_FR_DCD 0x004 #define UART01x_FR_DSR 0x002 -#define ZX_UART01x_FR_CTS 0x002 #define UART01x_FR_CTS 0x001 -#define ZX_UART011_FR_RI 0x001 #define UART01x_FR_TMSK (UART01x_FR_TXFF + UART01x_FR_BUSY) #define UART011_CR_CTSEN 0x8000 /* CTS hardware flow control */ diff --git a/include/linux/asn1_ber_bytecode.h b/include/linux/asn1_ber_bytecode.h index 945d44ae529c..ab3a6c002f7b 100644 --- a/include/linux/asn1_ber_bytecode.h +++ b/include/linux/asn1_ber_bytecode.h @@ -45,23 +45,27 @@ enum asn1_opcode { ASN1_OP_MATCH_JUMP = 0x04, ASN1_OP_MATCH_JUMP_OR_SKIP = 0x05, ASN1_OP_MATCH_ANY = 0x08, + ASN1_OP_MATCH_ANY_OR_SKIP = 0x09, ASN1_OP_MATCH_ANY_ACT = 0x0a, + ASN1_OP_MATCH_ANY_ACT_OR_SKIP = 0x0b, /* Everything before here matches unconditionally */ ASN1_OP_COND_MATCH_OR_SKIP = 0x11, ASN1_OP_COND_MATCH_ACT_OR_SKIP = 0x13, ASN1_OP_COND_MATCH_JUMP_OR_SKIP = 0x15, ASN1_OP_COND_MATCH_ANY = 0x18, + ASN1_OP_COND_MATCH_ANY_OR_SKIP = 0x19, ASN1_OP_COND_MATCH_ANY_ACT = 0x1a, + ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP = 0x1b, /* Everything before here will want a tag from the data */ -#define ASN1_OP__MATCHES_TAG ASN1_OP_COND_MATCH_ANY_ACT +#define ASN1_OP__MATCHES_TAG ASN1_OP_COND_MATCH_ANY_ACT_OR_SKIP /* These are here to help fill up space */ - ASN1_OP_COND_FAIL = 0x1b, - ASN1_OP_COMPLETE = 0x1c, - ASN1_OP_ACT = 0x1d, - ASN1_OP_RETURN = 0x1e, + ASN1_OP_COND_FAIL = 0x1c, + ASN1_OP_COMPLETE = 0x1d, + ASN1_OP_ACT = 0x1e, + ASN1_OP_MAYBE_ACT = 0x1f, /* The following eight have bit 0 -> SET, 1 -> OF, 2 -> ACT */ ASN1_OP_END_SEQ = 0x20, @@ -76,6 +80,8 @@ enum asn1_opcode { #define ASN1_OP_END__OF 0x02 #define ASN1_OP_END__ACT 0x04 + ASN1_OP_RETURN = 0x28, + ASN1_OP__NR }; diff --git a/include/linux/audit.h b/include/linux/audit.h index c2e7e3a83965..b2abc996c25d 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -27,6 +27,9 @@ #include <linux/ptrace.h> #include <uapi/linux/audit.h> +#define AUDIT_INO_UNSET ((unsigned long)-1) +#define AUDIT_DEV_UNSET ((dev_t)-1) + struct audit_sig_info { uid_t uid; pid_t pid; @@ -59,6 +62,7 @@ struct audit_krule { struct audit_field *inode_f; /* quick access to an inode field */ struct audit_watch *watch; /* associated watch */ struct audit_tree *tree; /* associated watched tree */ + struct audit_fsnotify_mark *exe; struct list_head rlist; /* entry in audit_{watch,tree}.rules list */ struct list_head list; /* for AUDIT_LIST* purposes only */ u64 prio; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0fe9df983ab7..5a5d79ee256f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -286,7 +286,7 @@ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ - if (likely(wb && wb->blkcg_css == task_css(current, blkio_cgrp_id))) + if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } @@ -402,7 +402,7 @@ static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) } struct wb_iter { - int start_blkcg_id; + int start_memcg_id; struct radix_tree_iter tree_iter; void **slot; }; @@ -414,9 +414,9 @@ static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter, WARN_ON_ONCE(!rcu_read_lock_held()); - if (iter->start_blkcg_id >= 0) { - iter->slot = radix_tree_iter_init(titer, iter->start_blkcg_id); - iter->start_blkcg_id = -1; + if (iter->start_memcg_id >= 0) { + iter->slot = radix_tree_iter_init(titer, iter->start_memcg_id); + iter->start_memcg_id = -1; } else { iter->slot = radix_tree_next_slot(iter->slot, titer, 0); } @@ -430,30 +430,30 @@ static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter, static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter, struct backing_dev_info *bdi, - int start_blkcg_id) + int start_memcg_id) { - iter->start_blkcg_id = start_blkcg_id; + iter->start_memcg_id = start_memcg_id; - if (start_blkcg_id) + if (start_memcg_id) return __wb_iter_next(iter, bdi); else return &bdi->wb; } /** - * bdi_for_each_wb - walk all wb's of a bdi in ascending blkcg ID order + * bdi_for_each_wb - walk all wb's of a bdi in ascending memcg ID order * @wb_cur: cursor struct bdi_writeback pointer * @bdi: bdi to walk wb's of * @iter: pointer to struct wb_iter to be used as iteration buffer - * @start_blkcg_id: blkcg ID to start iteration from + * @start_memcg_id: memcg ID to start iteration from * * Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending - * blkcg ID order starting from @start_blkcg_id. @iter is struct wb_iter + * memcg ID order starting from @start_memcg_id. @iter is struct wb_iter * to be used as temp storage during iteration. rcu_read_lock() must be * held throughout iteration. */ -#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id) \ - for ((wb_cur) = __wb_iter_init(iter, bdi, start_blkcg_id); \ +#define bdi_for_each_wb(wb_cur, bdi, iter, start_memcg_id) \ + for ((wb_cur) = __wb_iter_init(iter, bdi, start_memcg_id); \ (wb_cur); (wb_cur) = __wb_iter_next(iter, bdi)) #else /* CONFIG_CGROUP_WRITEBACK */ diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a4cd1641e9e2..0a5cc7a1109b 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,12 +14,15 @@ */ #include <linux/cgroup.h> -#include <linux/u64_stats_sync.h> +#include <linux/percpu_counter.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> #include <linux/atomic.h> +/* percpu_counter batch for blkg_[rw]stats, per-cpu drift doesn't matter */ +#define BLKG_STAT_CPU_BATCH (INT_MAX / 2) + /* Max limits for throttle policy */ #define THROTL_IOPS_MAX UINT_MAX @@ -45,7 +48,7 @@ struct blkcg { struct blkcg_gq *blkg_hint; struct hlist_head blkg_list; - struct blkcg_policy_data *pd[BLKCG_MAX_POLS]; + struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK @@ -53,14 +56,19 @@ struct blkcg { #endif }; +/* + * blkg_[rw]stat->aux_cnt is excluded for local stats but included for + * recursive. Used to carry stats of dead children, and, for blkg_rwstat, + * to carry result values from read and sum operations. + */ struct blkg_stat { - struct u64_stats_sync syncp; - uint64_t cnt; + struct percpu_counter cpu_cnt; + atomic64_t aux_cnt; }; struct blkg_rwstat { - struct u64_stats_sync syncp; - uint64_t cnt[BLKG_RWSTAT_NR]; + struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; + atomic64_t aux_cnt[BLKG_RWSTAT_NR]; }; /* @@ -68,32 +76,28 @@ struct blkg_rwstat { * request_queue (q). This is used by blkcg policies which need to track * information per blkcg - q pair. * - * There can be multiple active blkcg policies and each has its private - * data on each blkg, the size of which is determined by - * blkcg_policy->pd_size. blkcg core allocates and frees such areas - * together with blkg and invokes pd_init/exit_fn() methods. - * - * Such private data must embed struct blkg_policy_data (pd) at the - * beginning and pd_size can't be smaller than pd. + * There can be multiple active blkcg policies and each blkg:policy pair is + * represented by a blkg_policy_data which is allocated and freed by each + * policy's pd_alloc/free_fn() methods. A policy can allocate private data + * area by allocating larger data structure which embeds blkg_policy_data + * at the beginning. */ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - - /* used during policy activation */ - struct list_head alloc_node; }; /* - * Policies that need to keep per-blkcg data which is independent - * from any request_queue associated to it must specify its size - * with the cpd_size field of the blkcg_policy structure and - * embed a blkcg_policy_data in it. cpd_init() is invoked to let - * each policy handle per-blkcg data. + * Policies that need to keep per-blkcg data which is independent from any + * request_queue associated to it should implement cpd_alloc/free_fn() + * methods. A policy can allocate private data area by allocating larger + * data structure which embeds blkcg_policy_data at the beginning. + * cpd_init() is invoked to let each policy handle per-blkcg data. */ struct blkcg_policy_data { - /* the policy id this per-policy data belongs to */ + /* the blkcg and policy id this per-policy data belongs to */ + struct blkcg *blkcg; int plid; }; @@ -123,40 +127,50 @@ struct blkcg_gq { /* is this blkg online? protected by both blkcg and q locks */ bool online; + struct blkg_rwstat stat_bytes; + struct blkg_rwstat stat_ios; + struct blkg_policy_data *pd[BLKCG_MAX_POLS]; struct rcu_head rcu_head; }; -typedef void (blkcg_pol_init_cpd_fn)(const struct blkcg *blkcg); -typedef void (blkcg_pol_init_pd_fn)(struct blkcg_gq *blkg); -typedef void (blkcg_pol_online_pd_fn)(struct blkcg_gq *blkg); -typedef void (blkcg_pol_offline_pd_fn)(struct blkcg_gq *blkg); -typedef void (blkcg_pol_exit_pd_fn)(struct blkcg_gq *blkg); -typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkcg_gq *blkg); +typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp); +typedef void (blkcg_pol_init_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_free_cpd_fn)(struct blkcg_policy_data *cpd); +typedef void (blkcg_pol_bind_cpd_fn)(struct blkcg_policy_data *cpd); +typedef struct blkg_policy_data *(blkcg_pol_alloc_pd_fn)(gfp_t gfp, int node); +typedef void (blkcg_pol_init_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd); +typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd); struct blkcg_policy { int plid; - /* policy specific private data size */ - size_t pd_size; - /* policy specific per-blkcg data size */ - size_t cpd_size; /* cgroup files for the policy */ - struct cftype *cftypes; + struct cftype *dfl_cftypes; + struct cftype *legacy_cftypes; /* operations */ + blkcg_pol_alloc_cpd_fn *cpd_alloc_fn; blkcg_pol_init_cpd_fn *cpd_init_fn; + blkcg_pol_free_cpd_fn *cpd_free_fn; + blkcg_pol_bind_cpd_fn *cpd_bind_fn; + + blkcg_pol_alloc_pd_fn *pd_alloc_fn; blkcg_pol_init_pd_fn *pd_init_fn; blkcg_pol_online_pd_fn *pd_online_fn; blkcg_pol_offline_pd_fn *pd_offline_fn; - blkcg_pol_exit_pd_fn *pd_exit_fn; + blkcg_pol_free_pd_fn *pd_free_fn; blkcg_pol_reset_pd_stats_fn *pd_reset_stats_fn; }; extern struct blkcg blkcg_root; extern struct cgroup_subsys_state * const blkcg_root_css; -struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q); +struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, + struct request_queue *q, bool update_hint); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -171,6 +185,7 @@ int blkcg_activate_policy(struct request_queue *q, void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); +const char *blkg_dev_name(struct blkcg_gq *blkg); void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, u64 (*prfill)(struct seq_file *, struct blkg_policy_data *, int), @@ -182,19 +197,24 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, u64 blkg_prfill_stat(struct seq_file *sf, struct blkg_policy_data *pd, int off); u64 blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, int off); +int blkg_print_stat_bytes(struct seq_file *sf, void *v); +int blkg_print_stat_ios(struct seq_file *sf, void *v); +int blkg_print_stat_bytes_recursive(struct seq_file *sf, void *v); +int blkg_print_stat_ios_recursive(struct seq_file *sf, void *v); -u64 blkg_stat_recursive_sum(struct blkg_policy_data *pd, int off); -struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkg_policy_data *pd, - int off); +u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); +struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, + struct blkcg_policy *pol, int off); struct blkg_conf_ctx { struct gendisk *disk; struct blkcg_gq *blkg; - u64 v; + char *body; }; int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, - const char *input, struct blkg_conf_ctx *ctx); + char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); @@ -205,7 +225,7 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) static inline struct blkcg *task_blkcg(struct task_struct *tsk) { - return css_to_blkcg(task_css(tsk, blkio_cgrp_id)); + return css_to_blkcg(task_css(tsk, io_cgrp_id)); } static inline struct blkcg *bio_blkcg(struct bio *bio) @@ -218,7 +238,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio) static inline struct cgroup_subsys_state * task_get_blkcg_css(struct task_struct *task) { - return task_get_css(task, blkio_cgrp_id); + return task_get_css(task, io_cgrp_id); } /** @@ -233,6 +253,52 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) } /** + * __blkg_lookup - internal version of blkg_lookup() + * @blkcg: blkcg of interest + * @q: request_queue of interest + * @update_hint: whether to update lookup hint with the result or not + * + * This is internal version and shouldn't be used by policy + * implementations. Looks up blkgs for the @blkcg - @q pair regardless of + * @q's bypass state. If @update_hint is %true, the caller should be + * holding @q->queue_lock and lookup hint is updated on success. + */ +static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, + struct request_queue *q, + bool update_hint) +{ + struct blkcg_gq *blkg; + + if (blkcg == &blkcg_root) + return q->root_blkg; + + blkg = rcu_dereference(blkcg->blkg_hint); + if (blkg && blkg->q == q) + return blkg; + + return blkg_lookup_slowpath(blkcg, q, update_hint); +} + +/** + * blkg_lookup - lookup blkg for the specified blkcg - q pair + * @blkcg: blkcg of interest + * @q: request_queue of interest + * + * Lookup blkg for the @blkcg - @q pair. This function should be called + * under RCU read lock and is guaranteed to return %NULL if @q is bypassing + * - see blk_queue_bypass_start() for details. + */ +static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, + struct request_queue *q) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (unlikely(blk_queue_bypass(q))) + return NULL; + return __blkg_lookup(blkcg, q, false); +} + +/** * blkg_to_pdata - get policy private data * @blkg: blkg of interest * @pol: policy of interest @@ -248,7 +314,7 @@ static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, static inline struct blkcg_policy_data *blkcg_to_cpd(struct blkcg *blkcg, struct blkcg_policy *pol) { - return blkcg ? blkcg->pd[pol->plid] : NULL; + return blkcg ? blkcg->cpd[pol->plid] : NULL; } /** @@ -262,6 +328,11 @@ static inline struct blkcg_gq *pd_to_blkg(struct blkg_policy_data *pd) return pd ? pd->blkg : NULL; } +static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) +{ + return cpd ? cpd->blkcg : NULL; +} + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest @@ -309,9 +380,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) call_rcu(&blkg->rcu_head, __blkg_release_rcu); } -struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, struct request_queue *q, - bool update_hint); - /** * blkg_for_each_descendant_pre - pre-order walk of a blkg's descendants * @d_blkg: loop cursor pointing to the current descendant @@ -373,8 +441,8 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, * or if either the blkcg or queue is going away. Fall back to * root_rl in such cases. */ - blkg = blkg_lookup_create(blkcg, q); - if (IS_ERR(blkg)) + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) goto root_rl; blkg_get(blkg); @@ -394,8 +462,7 @@ root_rl: */ static inline void blk_put_rl(struct request_list *rl) { - /* root_rl may not have blkg set */ - if (rl->blkg && rl->blkg->blkcg != &blkcg_root) + if (rl->blkg->blkcg != &blkcg_root) blkg_put(rl->blkg); } @@ -433,9 +500,21 @@ struct request_list *__blk_queue_next_rl(struct request_list *rl, #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q))) -static inline void blkg_stat_init(struct blkg_stat *stat) +static inline int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp) { - u64_stats_init(&stat->syncp); + int ret; + + ret = percpu_counter_init(&stat->cpu_cnt, 0, gfp); + if (ret) + return ret; + + atomic64_set(&stat->aux_cnt, 0); + return 0; +} + +static inline void blkg_stat_exit(struct blkg_stat *stat) +{ + percpu_counter_destroy(&stat->cpu_cnt); } /** @@ -443,34 +522,21 @@ static inline void blkg_stat_init(struct blkg_stat *stat) * @stat: target blkg_stat * @val: value to add * - * Add @val to @stat. The caller is responsible for synchronizing calls to - * this function. + * Add @val to @stat. The caller must ensure that IRQ on the same CPU + * don't re-enter this function for the same counter. */ static inline void blkg_stat_add(struct blkg_stat *stat, uint64_t val) { - u64_stats_update_begin(&stat->syncp); - stat->cnt += val; - u64_stats_update_end(&stat->syncp); + __percpu_counter_add(&stat->cpu_cnt, val, BLKG_STAT_CPU_BATCH); } /** * blkg_stat_read - read the current value of a blkg_stat * @stat: blkg_stat to read - * - * Read the current value of @stat. This function can be called without - * synchroniztion and takes care of u64 atomicity. */ static inline uint64_t blkg_stat_read(struct blkg_stat *stat) { - unsigned int start; - uint64_t v; - - do { - start = u64_stats_fetch_begin_irq(&stat->syncp); - v = stat->cnt; - } while (u64_stats_fetch_retry_irq(&stat->syncp, start)); - - return v; + return percpu_counter_sum_positive(&stat->cpu_cnt); } /** @@ -479,24 +545,46 @@ static inline uint64_t blkg_stat_read(struct blkg_stat *stat) */ static inline void blkg_stat_reset(struct blkg_stat *stat) { - stat->cnt = 0; + percpu_counter_set(&stat->cpu_cnt, 0); + atomic64_set(&stat->aux_cnt, 0); } /** - * blkg_stat_merge - merge a blkg_stat into another + * blkg_stat_add_aux - add a blkg_stat into another's aux count * @to: the destination blkg_stat * @from: the source * - * Add @from's count to @to. + * Add @from's count including the aux one to @to's aux count. */ -static inline void blkg_stat_merge(struct blkg_stat *to, struct blkg_stat *from) +static inline void blkg_stat_add_aux(struct blkg_stat *to, + struct blkg_stat *from) { - blkg_stat_add(to, blkg_stat_read(from)); + atomic64_add(blkg_stat_read(from) + atomic64_read(&from->aux_cnt), + &to->aux_cnt); } -static inline void blkg_rwstat_init(struct blkg_rwstat *rwstat) +static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) { - u64_stats_init(&rwstat->syncp); + int i, ret; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + ret = percpu_counter_init(&rwstat->cpu_cnt[i], 0, gfp); + if (ret) { + while (--i >= 0) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); + return ret; + } + atomic64_set(&rwstat->aux_cnt[i], 0); + } + return 0; +} + +static inline void blkg_rwstat_exit(struct blkg_rwstat *rwstat) +{ + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) + percpu_counter_destroy(&rwstat->cpu_cnt[i]); } /** @@ -511,39 +599,38 @@ static inline void blkg_rwstat_init(struct blkg_rwstat *rwstat) static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, int rw, uint64_t val) { - u64_stats_update_begin(&rwstat->syncp); + struct percpu_counter *cnt; if (rw & REQ_WRITE) - rwstat->cnt[BLKG_RWSTAT_WRITE] += val; + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else - rwstat->cnt[BLKG_RWSTAT_READ] += val; + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; + + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); + if (rw & REQ_SYNC) - rwstat->cnt[BLKG_RWSTAT_SYNC] += val; + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else - rwstat->cnt[BLKG_RWSTAT_ASYNC] += val; + cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - u64_stats_update_end(&rwstat->syncp); + __percpu_counter_add(cnt, val, BLKG_STAT_CPU_BATCH); } /** * blkg_rwstat_read - read the current values of a blkg_rwstat * @rwstat: blkg_rwstat to read * - * Read the current snapshot of @rwstat and return it as the return value. - * This function can be called without synchronization and takes care of - * u64 atomicity. + * Read the current snapshot of @rwstat and return it in the aux counts. */ static inline struct blkg_rwstat blkg_rwstat_read(struct blkg_rwstat *rwstat) { - unsigned int start; - struct blkg_rwstat tmp; - - do { - start = u64_stats_fetch_begin_irq(&rwstat->syncp); - tmp = *rwstat; - } while (u64_stats_fetch_retry_irq(&rwstat->syncp, start)); + struct blkg_rwstat result; + int i; - return tmp; + for (i = 0; i < BLKG_RWSTAT_NR; i++) + atomic64_set(&result.aux_cnt[i], + percpu_counter_sum_positive(&rwstat->cpu_cnt[i])); + return result; } /** @@ -558,7 +645,8 @@ static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) { struct blkg_rwstat tmp = blkg_rwstat_read(rwstat); - return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; + return atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) + + atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]); } /** @@ -567,26 +655,71 @@ static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) */ static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) { - memset(rwstat->cnt, 0, sizeof(rwstat->cnt)); + int i; + + for (i = 0; i < BLKG_RWSTAT_NR; i++) { + percpu_counter_set(&rwstat->cpu_cnt[i], 0); + atomic64_set(&rwstat->aux_cnt[i], 0); + } } /** - * blkg_rwstat_merge - merge a blkg_rwstat into another + * blkg_rwstat_add_aux - add a blkg_rwstat into another's aux count * @to: the destination blkg_rwstat * @from: the source * - * Add @from's counts to @to. + * Add @from's count including the aux one to @to's aux count. */ -static inline void blkg_rwstat_merge(struct blkg_rwstat *to, - struct blkg_rwstat *from) +static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, + struct blkg_rwstat *from) { struct blkg_rwstat v = blkg_rwstat_read(from); int i; - u64_stats_update_begin(&to->syncp); for (i = 0; i < BLKG_RWSTAT_NR; i++) - to->cnt[i] += v.cnt[i]; - u64_stats_update_end(&to->syncp); + atomic64_add(atomic64_read(&v.aux_cnt[i]) + + atomic64_read(&from->aux_cnt[i]), + &to->aux_cnt[i]); +} + +#ifdef CONFIG_BLK_DEV_THROTTLING +extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio); +#else +static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, + struct bio *bio) { return false; } +#endif + +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) +{ + struct blkcg *blkcg; + struct blkcg_gq *blkg; + bool throtl = false; + + rcu_read_lock(); + blkcg = bio_blkcg(bio); + + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } + + throtl = blk_throtl_bio(q, blkg, bio); + + if (!throtl) { + blkg = blkg ?: q->root_blkg; + blkg_rwstat_add(&blkg->stat_bytes, bio->bi_flags, + bio->bi_iter.bi_size); + blkg_rwstat_add(&blkg->stat_ios, bio->bi_flags, 1); + } + + rcu_read_unlock(); + return !throtl; } #else /* CONFIG_BLK_CGROUP */ @@ -642,6 +775,9 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } +static inline bool blkcg_bio_issue_check(struct request_queue *q, + struct bio *bio) { return true; } + #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a622f270f09e..38a5ff772a37 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 @@ -1569,8 +1569,8 @@ struct block_device_operations { int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - long (*direct_access)(struct block_device *, sector_t, - void **, unsigned long *pfn, long size); + long (*direct_access)(struct block_device *, sector_t, void __pmem **, + unsigned long *pfn); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ @@ -1588,8 +1588,8 @@ extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -extern long bdev_direct_access(struct block_device *, sector_t, void **addr, - unsigned long *pfn, long size); +extern long bdev_direct_access(struct block_device *, sector_t, + void __pmem **addr, unsigned long *pfn, long size); #else /* CONFIG_BLOCK */ struct block_device; 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..7e1252e97a30 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -248,6 +248,8 @@ struct ceph_connection { int in_base_pos; /* bytes read */ __le64 in_temp_ack; /* for reading an ack */ + struct timespec last_keepalive_ack; + struct delayed_work work; /* send|recv work */ unsigned long delay; /* current delay interval */ }; @@ -285,6 +287,8 @@ 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_subsys.h b/include/linux/cgroup_subsys.h index 1f36945fd23d..1a96fdaa33d5 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -27,7 +27,7 @@ SUBSYS(cpuacct) #endif #if IS_ENABLED(CONFIG_BLK_CGROUP) -SUBSYS(blkio) +SUBSYS(io) #endif #if IS_ENABLED(CONFIG_MEMCG) diff --git a/include/linux/dax.h b/include/linux/dax.h new file mode 100644 index 000000000000..b415e521528d --- /dev/null +++ b/include/linux/dax.h @@ -0,0 +1,39 @@ +#ifndef _LINUX_DAX_H +#define _LINUX_DAX_H + +#include <linux/fs.h> +#include <linux/mm.h> +#include <asm/pgtable.h> + +ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, + get_block_t, dio_iodone_t, int flags); +int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); +int dax_truncate_page(struct inode *, loff_t from, get_block_t); +int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, + dax_iodone_t); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +int dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +int __dax_pmd_fault(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned int flags, get_block_t, dax_iodone_t); +#else +static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags, get_block_t gb, + dax_iodone_t di) +{ + return VM_FAULT_FALLBACK; +} +#define __dax_pmd_fault dax_pmd_fault +#endif +int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); +#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod) +#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod) + +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} +#endif diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 420311bcee38..9beb636b97eb 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -116,6 +116,12 @@ struct dentry *debugfs_create_devm_seqfile(struct device *dev, const char *name, bool debugfs_initialized(void); +ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos); + +ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, + size_t count, loff_t *ppos); + #else #include <linux/err.h> @@ -282,6 +288,20 @@ static inline struct dentry *debugfs_create_devm_seqfile(struct device *dev, return ERR_PTR(-ENODEV); } +static inline ssize_t debugfs_read_file_bool(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + +static inline ssize_t debugfs_write_file_bool(struct file *file, + const char __user *user_buf, + size_t count, loff_t *ppos) +{ + return -ENODEV; +} + #endif #endif diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h index e1043f79122f..53ba737505df 100644 --- a/include/linux/dmapool.h +++ b/include/linux/dmapool.h @@ -24,6 +24,12 @@ void dma_pool_destroy(struct dma_pool *pool); void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags, dma_addr_t *handle); +static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags, + dma_addr_t *handle) +{ + return dma_pool_alloc(pool, mem_flags | __GFP_ZERO, handle); +} + void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); /* diff --git a/include/linux/fb.h b/include/linux/fb.h index 043f3283b71c..bc9afa74ee11 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -788,7 +788,7 @@ struct dmt_videomode { extern const char *fb_mode_option; extern const struct fb_videomode vesa_modes[]; -extern const struct fb_videomode cea_modes[64]; +extern const struct fb_videomode cea_modes[65]; extern const struct dmt_videomode dmt_modes[]; struct fb_modelist { diff --git a/include/linux/fs.h b/include/linux/fs.h index b2f9b9c25e41..72d8a844c692 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -52,7 +52,6 @@ struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; -struct vm_fault; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -2678,19 +2677,6 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset, extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); -ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, - get_block_t, dio_iodone_t, int flags); -int dax_clear_blocks(struct inode *, sector_t block, long size); -int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); -int dax_truncate_page(struct inode *, loff_t from, get_block_t); -int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, - dax_iodone_t); -int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, - dax_iodone_t); -int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); -#define dax_mkwrite(vma, vmf, gb, iod) dax_fault(vma, vmf, gb, iod) -#define __dax_mkwrite(vma, vmf, gb, iod) __dax_fault(vma, vmf, gb, iod) - #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index ad35f300b9a4..f92cbd2f4450 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -63,7 +63,10 @@ struct vm_area_struct; * but it is definitely preferable to use the flag rather than opencode endless * loop around allocator. * - * __GFP_NORETRY: The VM implementation must not retry indefinitely. + * __GFP_NORETRY: The VM implementation must not retry indefinitely and will + * return NULL when direct reclaim and memory compaction have failed to allow + * the allocation to succeed. The OOM killer is not called with the current + * implementation. * * __GFP_MOVABLE: Flag that this page will be movable by the page migration * mechanism or reclaimed @@ -300,22 +303,31 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL); } -static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, - unsigned int order) +/* + * Allocate pages, preferring the node given as nid. The node must be valid and + * online. For more general interface, see alloc_pages_node(). + */ +static inline struct page * +__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - /* Unknown node is current node */ - if (nid < 0) - nid = numa_node_id(); + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + VM_WARN_ON(!node_online(nid)); return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); } -static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask, +/* + * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, + * prefer the current CPU's closest node. Otherwise node must be valid and + * online. + */ +static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { - VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES || !node_online(nid)); + if (nid == NUMA_NO_NODE) + nid = numa_mem_id(); - return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask)); + return __alloc_pages_node(nid, gfp_mask, order); } #ifdef CONFIG_NUMA @@ -354,7 +366,6 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); -/* This is different from alloc_pages_exact_node !!! */ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f10b20f05159..ecb080d6ff42 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -33,6 +33,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma, extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); +int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *, + unsigned long pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, @@ -122,7 +124,7 @@ extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, #endif extern int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); -extern void __vma_adjust_trans_huge(struct vm_area_struct *vma, +extern void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); @@ -138,15 +140,6 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, else return 0; } -static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, - unsigned long start, - unsigned long end, - long adjust_next) -{ - if (!vma->anon_vma || vma->vm_ops) - return; - __vma_adjust_trans_huge(vma, start, end, adjust_next); -} static inline int hpage_nr_pages(struct page *page) { if (unlikely(PageTransHuge(page))) @@ -164,6 +157,13 @@ static inline bool is_huge_zero_page(struct page *page) return ACCESS_ONCE(huge_zero_page) == page; } +static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return is_huge_zero_page(pmd_page(pmd)); +} + +struct page *get_huge_zero_page(void); + #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d891f949466a..5e35379f58a5 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -35,6 +35,9 @@ struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; + long adds_in_progress; + struct list_head region_cache; + long region_cache_count; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); @@ -80,11 +83,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, int hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vm_flags_t vm_flags); -void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed); +long hugetlb_unreserve_pages(struct inode *inode, long start, long end, + long freed); int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); void free_huge_page(struct page *page); +void hugetlb_fix_reserve_counts(struct inode *inode, bool restore_reserve); +extern struct mutex *hugetlb_fault_mutex_table; +u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm, + struct vm_area_struct *vma, + struct address_space *mapping, + pgoff_t idx, unsigned long address); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); @@ -320,9 +330,13 @@ struct huge_bootmem_page { #endif }; +struct page *alloc_huge_page(struct vm_area_struct *vma, + unsigned long addr, int avoid_reserve); struct page *alloc_huge_page_node(struct hstate *h, int nid); struct page *alloc_huge_page_noerr(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve); +int huge_add_to_page_cache(struct page *page, struct address_space *mapping, + pgoff_t idx); /* arch callback */ int __init alloc_bootmem_huge_page(struct hstate *h); @@ -471,6 +485,7 @@ static inline spinlock_t *huge_pte_lockptr(struct hstate *h, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +#define alloc_huge_page(v, a, r) NULL #define alloc_huge_page_node(h, nid) NULL #define alloc_huge_page_noerr(v, a, r) NULL #define alloc_bootmem_huge_page(h) NULL diff --git a/include/linux/i2c.h b/include/linux/i2c.h index e83a738a3b87..768063baafbf 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -121,6 +121,9 @@ extern s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, extern s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); +extern s32 +i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, + u8 command, u8 length, u8 *values); #endif /* I2C */ /** @@ -550,11 +553,12 @@ void i2c_lock_adapter(struct i2c_adapter *); void i2c_unlock_adapter(struct i2c_adapter *); /*flags for the client struct: */ -#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ -#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ +#define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ +#define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ /* Must equal I2C_M_TEN below */ -#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ -#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ +#define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ +#define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ +#define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ /* i2c adapter classes (bitmask) */ @@ -638,6 +642,8 @@ extern struct i2c_client *of_find_i2c_device_by_node(struct device_node *node); /* must call put_device() when done with returned i2c_adapter device */ extern struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node); +/* must call i2c_put_adapter() when done with returned i2c_adapter device */ +struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node); #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) @@ -649,6 +655,11 @@ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node { return NULL; } + +static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) +{ + return NULL; +} #endif /* CONFIG_OF */ #endif /* _LINUX_I2C_H */ diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d9a366d24e3b..6240063bdcac 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -344,7 +344,7 @@ struct intel_iommu { #ifdef CONFIG_INTEL_IOMMU unsigned long *domain_ids; /* bitmap of domains */ - struct dmar_domain **domains; /* ptr to domains */ + struct dmar_domain ***domains; /* ptr to domains */ spinlock_t lock; /* protect context, domain ids */ struct root_entry *root_entry; /* virtual address */ diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index c27dde7215b5..e399029b68c5 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -21,7 +21,7 @@ #include <linux/types.h> #include <linux/slab.h> #include <linux/bug.h> -#include <asm/io.h> +#include <linux/io.h> #include <asm/page.h> /* diff --git a/include/linux/io.h b/include/linux/io.h index fb5a99800e77..de64c1e53612 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -20,10 +20,13 @@ #include <linux/types.h> #include <linux/init.h> +#include <linux/bug.h> +#include <linux/err.h> #include <asm/io.h> #include <asm/page.h> struct device; +struct resource; __visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count); void __iowrite64_copy(void __iomem *to, const void *from, size_t count); @@ -80,6 +83,27 @@ int check_signature(const volatile void __iomem *io_addr, const unsigned char *signature, int length); void devm_ioremap_release(struct device *dev, void *res); +void *devm_memremap(struct device *dev, resource_size_t offset, + size_t size, unsigned long flags); +void devm_memunmap(struct device *dev, void *addr); + +void *__devm_memremap_pages(struct device *dev, struct resource *res); + +#ifdef CONFIG_ZONE_DEVICE +void *devm_memremap_pages(struct device *dev, struct resource *res); +#else +static inline void *devm_memremap_pages(struct device *dev, struct resource *res) +{ + /* + * Fail attempts to call devm_memremap_pages() without + * ZONE_DEVICE support enabled, this requires callers to fall + * back to plain devm_memremap() based on config + */ + WARN_ON_ONCE(1); + return ERR_PTR(-ENXIO); +} +#endif + /* * Some systems do not have legacy ISA devices. * /dev/port is not a valid interface on these systems. @@ -121,4 +145,13 @@ static inline int arch_phys_wc_index(int handle) #endif #endif +enum { + /* See memremap() kernel-doc for usage description... */ + MEMREMAP_WB = 1 << 0, + MEMREMAP_WT = 1 << 1, +}; + +void *memremap(resource_size_t offset, size_t size, unsigned long flags); +void memunmap(void *addr); + #endif /* _LINUX_IO_H */ diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index 0b1e569f5ff5..f8cea14485dd 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -115,6 +115,11 @@ struct ipmi_smi_handlers { implement it. */ void (*set_need_watch)(void *send_info, bool enable); + /* + * Called when flushing all pending messages. + */ + void (*flush_messages)(void *send_info); + /* Called when the interface should go into "run to completion" mode. If this call sets the value to true, the interface should make sure that all messages are flushed @@ -207,7 +212,7 @@ static inline int ipmi_demangle_device_id(const unsigned char *data, upper layer until the start_processing() function in the handlers is called, and the lower layer must get the interface from that call. */ -int ipmi_register_smi(struct ipmi_smi_handlers *handlers, +int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, void *send_info, struct ipmi_device_id *device_id, struct device *dev, diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index bf982e021fbd..9eeeb9589acf 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -104,6 +104,8 @@ #define GICR_SYNCR 0x00C0 #define GICR_MOVLPIR 0x0100 #define GICR_MOVALLR 0x0110 +#define GICR_ISACTIVER GICD_ISACTIVER +#define GICR_ICACTIVER GICD_ICACTIVER #define GICR_IDREGS GICD_IDREGS #define GICR_PIDR2 GICD_PIDR2 @@ -268,9 +270,12 @@ #define ICH_LR_EOI (1UL << 41) #define ICH_LR_GROUP (1UL << 60) +#define ICH_LR_HW (1UL << 61) #define ICH_LR_STATE (3UL << 62) #define ICH_LR_PENDING_BIT (1UL << 62) #define ICH_LR_ACTIVE_BIT (1UL << 63) +#define ICH_LR_PHYS_ID_SHIFT 32 +#define ICH_LR_PHYS_ID_MASK (0x3ffUL << ICH_LR_PHYS_ID_SHIFT) #define ICH_MISR_EOI (1 << 0) #define ICH_MISR_U (1 << 1) @@ -288,6 +293,7 @@ #define ICH_VMCR_PMR_MASK (0xffUL << ICH_VMCR_PMR_SHIFT) #define ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1) +#define ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1) #define ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0) #define ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5) #define ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0) @@ -385,6 +391,12 @@ static inline void gic_write_eoir(u64 irq) isb(); } +static inline void gic_write_dir(u64 irq) +{ + asm volatile("msr_s " __stringify(ICC_DIR_EL1) ", %0" : : "r" (irq)); + isb(); +} + struct irq_domain; int its_cpu_init(void); int its_init(struct device_node *node, struct rdists *rdists, diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h index 65da435d01c1..b8901dfd9e95 100644 --- a/include/linux/irqchip/arm-gic.h +++ b/include/linux/irqchip/arm-gic.h @@ -20,9 +20,13 @@ #define GIC_CPU_ALIAS_BINPOINT 0x1c #define GIC_CPU_ACTIVEPRIO 0xd0 #define GIC_CPU_IDENT 0xfc +#define GIC_CPU_DEACTIVATE 0x1000 #define GICC_ENABLE 0x1 #define GICC_INT_PRI_THRESHOLD 0xf0 + +#define GIC_CPU_CTRL_EOImodeNS (1 << 9) + #define GICC_IAR_INT_ID_MASK 0x3ff #define GICC_INT_SPURIOUS 1023 #define GICC_DIS_BYPASS_MASK 0x1e0 @@ -71,11 +75,12 @@ #define GICH_LR_VIRTUALID (0x3ff << 0) #define GICH_LR_PHYSID_CPUID_SHIFT (10) -#define GICH_LR_PHYSID_CPUID (7 << GICH_LR_PHYSID_CPUID_SHIFT) +#define GICH_LR_PHYSID_CPUID (0x3ff << GICH_LR_PHYSID_CPUID_SHIFT) #define GICH_LR_STATE (3 << 28) #define GICH_LR_PENDING_BIT (1 << 28) #define GICH_LR_ACTIVE_BIT (1 << 29) #define GICH_LR_EOI (1 << 19) +#define GICH_LR_HW (1 << 31) #define GICH_VMCR_CTRL_SHIFT 0 #define GICH_VMCR_CTRL_MASK (0x21f << GICH_VMCR_CTRL_SHIFT) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 123be25ea15a..5d4e9c4b821d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -266,6 +266,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) } int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen); +size_t kernfs_path_len(struct kernfs_node *kn); char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen); void pr_cont_kernfs_name(struct kernfs_node *kn); @@ -332,6 +333,9 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn) static inline int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { return -ENOSYS; } +static inline size_t kernfs_path_len(struct kernfs_node *kn) +{ return 0; } + static inline char * __must_check kernfs_path(struct kernfs_node *kn, char *buf, size_t buflen) { return NULL; } diff --git a/include/linux/kexec.h b/include/linux/kexec.h index b63218f68c4b..d140b1e9faa7 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -16,7 +16,7 @@ #include <uapi/linux/kexec.h> -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE #include <linux/list.h> #include <linux/linkage.h> #include <linux/compat.h> @@ -318,13 +318,24 @@ int crash_shrink_memory(unsigned long new_size); size_t crash_get_memory_size(void); void crash_free_reserved_phys_range(unsigned long begin, unsigned long end); -#else /* !CONFIG_KEXEC */ +int __weak arch_kexec_kernel_image_probe(struct kimage *image, void *buf, + unsigned long buf_len); +void * __weak arch_kexec_kernel_image_load(struct kimage *image); +int __weak arch_kimage_file_post_load_cleanup(struct kimage *image); +int __weak arch_kexec_kernel_verify_sig(struct kimage *image, void *buf, + unsigned long buf_len); +int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr, + Elf_Shdr *sechdrs, unsigned int relsec); +int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + unsigned int relsec); + +#else /* !CONFIG_KEXEC_CORE */ struct pt_regs; struct task_struct; 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 -#endif /* CONFIG_KEXEC */ +#endif /* CONFIG_KEXEC_CORE */ #endif /* !defined(__ASSEBMLY__) */ diff --git a/include/linux/kmod.h b/include/linux/kmod.h index 0555cc66a15b..fcfd2bf14d3f 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -85,8 +85,6 @@ enum umh_disable_depth { UMH_DISABLED, }; -extern void usermodehelper_init(void); - extern int __usermodehelper_disable(enum umh_disable_depth depth); extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 81089cf1f0c1..1bef9e21e725 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -242,6 +242,7 @@ struct kvm_vcpu { int sigset_active; sigset_t sigset; struct kvm_vcpu_stat stat; + unsigned int halt_poll_ns; #ifdef CONFIG_HAS_IOMEM int mmio_needed; diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 75e3af01ee32..3f021dc5da8c 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -31,6 +31,9 @@ enum { ND_CMD_ARS_STATUS_MAX = SZ_4K, ND_MAX_MAPPINGS = 32, + /* region flag indicating to direct-map persistent memory by default */ + ND_REGION_PAGEMAP = 0, + /* mark newly adjusted resources as requiring a label update */ DPA_RESOURCE_ADJUSTED = 1 << 0, }; @@ -91,6 +94,7 @@ struct nd_region_desc { void *provider_data; int num_lanes; int numa_node; + unsigned long flags; }; struct nvdimm_bus; diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index 1cc89e9df480..ffb9c9da4f39 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -40,6 +40,11 @@ struct lsm_network_audit { } fam; }; +struct lsm_ioctlop_audit { + struct path path; + u16 cmd; +}; + /* Auxiliary data to use in generating the audit record. */ struct common_audit_data { char type; @@ -53,6 +58,7 @@ struct common_audit_data { #define LSM_AUDIT_DATA_KMOD 8 #define LSM_AUDIT_DATA_INODE 9 #define LSM_AUDIT_DATA_DENTRY 10 +#define LSM_AUDIT_DATA_IOCTL_OP 11 union { struct path path; struct dentry *dentry; @@ -68,6 +74,7 @@ struct common_audit_data { } key_struct; #endif char *kmod_name; + struct lsm_ioctlop_audit *op; } u; /* this union contains LSM specific data */ union { diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 9429f054c323..ec3a6bab29de 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1881,8 +1881,10 @@ static inline void security_delete_hooks(struct security_hook_list *hooks, extern int __init security_module_enable(const char *module); extern void __init capability_add_hooks(void); -#ifdef CONFIG_SECURITY_YAMA_STACKED -void __init yama_add_hooks(void); +#ifdef CONFIG_SECURITY_YAMA +extern void __init yama_add_hooks(void); +#else +static inline void __init yama_add_hooks(void) { } #endif #endif /* ! __LINUX_LSM_HOOKS_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index cc4b01972060..c518eb589260 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -77,6 +77,8 @@ int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); +bool memblock_overlaps_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); @@ -323,7 +325,7 @@ void memblock_enforce_memory_limit(phys_addr_t memory_limit); int memblock_is_memory(phys_addr_t addr); int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); int memblock_is_reserved(phys_addr_t addr); -int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); +bool memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void __memblock_dump_all(void); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 73b02b0a8f60..ad800e62cb7a 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -23,6 +23,11 @@ #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> +#include <linux/page_counter.h> +#include <linux/vmpressure.h> +#include <linux/eventfd.h> +#include <linux/mmzone.h> +#include <linux/writeback.h> struct mem_cgroup; struct page; @@ -67,12 +72,221 @@ enum mem_cgroup_events_index { MEMCG_NR_EVENTS, }; +/* + * Per memcg event counter is incremented at every pagein/pageout. With THP, + * it will be incremated by the number of pages. This counter is used for + * for trigger some periodic events. This is straightforward and better + * than using jiffies etc. to handle periodic memcg event. + */ +enum mem_cgroup_events_target { + MEM_CGROUP_TARGET_THRESH, + MEM_CGROUP_TARGET_SOFTLIMIT, + MEM_CGROUP_TARGET_NUMAINFO, + MEM_CGROUP_NTARGETS, +}; + +/* + * Bits in struct cg_proto.flags + */ +enum cg_proto_flags { + /* Currently active and new sockets should be assigned to cgroups */ + MEMCG_SOCK_ACTIVE, + /* It was ever activated; we must disarm static keys on destruction */ + MEMCG_SOCK_ACTIVATED, +}; + +struct cg_proto { + struct page_counter memory_allocated; /* Current allocated memory. */ + struct percpu_counter sockets_allocated; /* Current number of sockets. */ + int memory_pressure; + long sysctl_mem[3]; + unsigned long flags; + /* + * memcg field is used to find which memcg we belong directly + * Each memcg struct can hold more than one cg_proto, so container_of + * won't really cut. + * + * The elegant solution would be having an inverse function to + * proto_cgroup in struct proto, but that means polluting the structure + * for everybody, instead of just for memcg users. + */ + struct mem_cgroup *memcg; +}; + #ifdef CONFIG_MEMCG +struct mem_cgroup_stat_cpu { + long count[MEM_CGROUP_STAT_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; + unsigned long nr_page_events; + unsigned long targets[MEM_CGROUP_NTARGETS]; +}; + +struct mem_cgroup_reclaim_iter { + struct mem_cgroup *position; + /* scan generation, increased every round-trip */ + unsigned int generation; +}; + +/* + * per-zone information in memory controller. + */ +struct mem_cgroup_per_zone { + struct lruvec lruvec; + unsigned long lru_size[NR_LRU_LISTS]; + + struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; + + struct rb_node tree_node; /* RB tree node */ + unsigned long usage_in_excess;/* Set to the value by which */ + /* the soft limit is exceeded*/ + bool on_tree; + struct mem_cgroup *memcg; /* Back pointer, we cannot */ + /* use container_of */ +}; + +struct mem_cgroup_per_node { + struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; +}; + +struct mem_cgroup_threshold { + struct eventfd_ctx *eventfd; + unsigned long threshold; +}; + +/* For threshold */ +struct mem_cgroup_threshold_ary { + /* An array index points to threshold just below or equal to usage. */ + int current_threshold; + /* Size of entries[] */ + unsigned int size; + /* Array of thresholds */ + struct mem_cgroup_threshold entries[0]; +}; + +struct mem_cgroup_thresholds { + /* Primary thresholds array */ + struct mem_cgroup_threshold_ary *primary; + /* + * Spare threshold array. + * This is needed to make mem_cgroup_unregister_event() "never fail". + * It must be able to store at least primary->size - 1 entries. + */ + struct mem_cgroup_threshold_ary *spare; +}; + +/* + * The memory controller data structure. The memory controller controls both + * page cache and RSS per cgroup. We would eventually like to provide + * statistics based on the statistics developed by Rik Van Riel for clock-pro, + * to help the administrator determine what knobs to tune. + */ +struct mem_cgroup { + struct cgroup_subsys_state css; + + /* Accounted resources */ + struct page_counter memory; + struct page_counter memsw; + struct page_counter kmem; + + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + + unsigned long soft_limit; + + /* vmpressure notifications */ + struct vmpressure vmpressure; + + /* css_online() has been completed */ + int initialized; + + /* + * Should the accounting and control be hierarchical, per subtree? + */ + bool use_hierarchy; + + /* protected by memcg_oom_lock */ + bool oom_lock; + int under_oom; + + int swappiness; + /* OOM-Killer disable */ + int oom_kill_disable; + + /* protect arrays of thresholds */ + struct mutex thresholds_lock; + + /* thresholds for memory usage. RCU-protected */ + struct mem_cgroup_thresholds thresholds; + + /* thresholds for mem+swap usage. RCU-protected */ + struct mem_cgroup_thresholds memsw_thresholds; + + /* For oom notifier event fd */ + struct list_head oom_notify; + + /* + * Should we move charges of a task when a task is moved into this + * mem_cgroup ? And what type of charges should we move ? + */ + unsigned long move_charge_at_immigrate; + /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; + /* + * percpu counter. + */ + struct mem_cgroup_stat_cpu __percpu *stat; + spinlock_t pcp_counter_lock; + +#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) + struct cg_proto tcp_mem; +#endif +#if defined(CONFIG_MEMCG_KMEM) + /* Index in the kmem_cache->memcg_params.memcg_caches array */ + int kmemcg_id; + bool kmem_acct_activated; + bool kmem_acct_active; +#endif + + int last_scanned_node; +#if MAX_NUMNODES > 1 + nodemask_t scan_nodes; + atomic_t numainfo_events; + atomic_t numainfo_updating; +#endif + +#ifdef CONFIG_CGROUP_WRITEBACK + struct list_head cgwb_list; + struct wb_domain cgwb_domain; +#endif + + /* List of events which userspace want to receive */ + struct list_head event_list; + spinlock_t event_list_lock; + + struct mem_cgroup_per_node *nodeinfo[0]; + /* WARNING: nodeinfo must be the last member here */ +}; extern struct cgroup_subsys_state *mem_cgroup_root_css; -void mem_cgroup_events(struct mem_cgroup *memcg, +/** + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, - unsigned int nr); + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); +} bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -90,15 +304,29 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *); struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *); -bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, - struct mem_cgroup *root); bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg); +struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page); -extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); +static inline +struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ + return css ? container_of(css, struct mem_cgroup, css) : NULL; +} -extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg); -extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css); +struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, + struct mem_cgroup *, + struct mem_cgroup_reclaim_cookie *); +void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); + +static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, + struct mem_cgroup *root) +{ + if (root == memcg) + return true; + if (!root->use_hierarchy) + return false; + return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); +} static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) @@ -114,24 +342,68 @@ static inline bool mm_match_cgroup(struct mm_struct *mm, return match; } -extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg); -extern struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); +struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); +ino_t page_cgroup_ino(struct page *page); -struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, - struct mem_cgroup *, - struct mem_cgroup_reclaim_cookie *); -void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); +static inline bool mem_cgroup_disabled(void) +{ + if (memory_cgrp_subsys.disabled) + return true; + return false; +} /* * For memory reclaim. */ -int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec); -bool mem_cgroup_lruvec_online(struct lruvec *lruvec); int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); -unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list); -void mem_cgroup_update_lru_size(struct lruvec *, enum lru_list, int); -extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, - struct task_struct *p); + +void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, + int nr_pages); + +static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + +static inline +unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru) +{ + struct mem_cgroup_per_zone *mz; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + return mz->lru_size[lru]; +} + +static inline int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) +{ + unsigned long inactive_ratio; + unsigned long inactive; + unsigned long active; + unsigned long gb; + + inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON); + active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON); + + gb = (inactive + active) >> (30 - PAGE_SHIFT); + if (gb) + inactive_ratio = int_sqrt(10 * gb); + else + inactive_ratio = 1; + + return inactive * inactive_ratio < active; +} + +void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, + struct task_struct *p); static inline void mem_cgroup_oom_enable(void) { @@ -156,18 +428,26 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -static inline bool mem_cgroup_disabled(void) -{ - if (memory_cgrp_subsys.disabled) - return true; - return false; -} - struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page); -void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, - enum mem_cgroup_stat_index idx, int val); void mem_cgroup_end_page_stat(struct mem_cgroup *memcg); +/** + * mem_cgroup_update_page_stat - update page state statistics + * @memcg: memcg to account against + * @idx: page state item to account + * @val: number of pages (positive or negative) + * + * See mem_cgroup_begin_page_stat() for locking requirements. + */ +static inline void mem_cgroup_update_page_stat(struct mem_cgroup *memcg, + enum mem_cgroup_stat_index idx, int val) +{ + VM_BUG_ON(!rcu_read_lock_held()); + + if (memcg) + this_cpu_add(memcg->stat->count[idx], val); +} + static inline void mem_cgroup_inc_page_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx) { @@ -184,13 +464,31 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - __mem_cgroup_count_vm_event(mm, idx); + + rcu_read_lock(); + memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); + if (unlikely(!memcg)) + goto out; + + switch (idx) { + case PGFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]); + break; + case PGMAJFAULT: + this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]); + break; + default: + BUG(); + } +out: + rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); @@ -199,8 +497,6 @@ void mem_cgroup_split_huge_fixup(struct page *head); #else /* CONFIG_MEMCG */ struct mem_cgroup; -#define mem_cgroup_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) - static inline void mem_cgroup_events(struct mem_cgroup *memcg, enum mem_cgroup_events_index idx, unsigned int nr) @@ -258,11 +554,6 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, return &zone->lruvec; } -static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page) -{ - return NULL; -} - static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { @@ -275,12 +566,6 @@ static inline bool task_in_mem_cgroup(struct task_struct *task, return true; } -static inline struct cgroup_subsys_state - *mem_cgroup_css(struct mem_cgroup *memcg) -{ - return NULL; -} - static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, @@ -428,8 +713,8 @@ static inline void sock_release_memcg(struct sock *sk) extern struct static_key memcg_kmem_enabled_key; extern int memcg_nr_cache_ids; -extern void memcg_get_cache_ids(void); -extern void memcg_put_cache_ids(void); +void memcg_get_cache_ids(void); +void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still @@ -444,7 +729,10 @@ static inline bool memcg_kmem_enabled(void) return static_key_false(&memcg_kmem_enabled_key); } -bool memcg_kmem_is_active(struct mem_cgroup *memcg); +static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg) +{ + return memcg->kmem_acct_active; +} /* * In general, we'll do everything in our power to not incur in any overhead @@ -463,7 +751,15 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order); void __memcg_kmem_uncharge_pages(struct page *page, int order); -int memcg_cache_id(struct mem_cgroup *memcg); +/* + * helper for acessing a memcg's index. It will be used as an index in the + * child cache array in kmem_cache, and also to derive its name. This function + * will return -1 when this is not a kmem-limited memcg. + */ +static inline int memcg_cache_id(struct mem_cgroup *memcg) +{ + return memcg ? memcg->kmemcg_id : -1; +} struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep); void __memcg_kmem_put_cache(struct kmem_cache *cachep); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 6ffa0ac7f7d6..8f60e899b33c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -266,8 +266,9 @@ static inline void remove_memory(int nid, u64 start, u64 size) {} extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); -extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default); -extern int arch_add_memory(int nid, u64 start, u64 size); +extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default, + bool for_device); +extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); extern void remove_memory(int nid, u64 start, u64 size); diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h new file mode 100644 index 000000000000..eb492d47f717 --- /dev/null +++ b/include/linux/microchipphy.h @@ -0,0 +1,73 @@ +/* + * Copyright (C) 2015 Microchip Technology + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef _MICROCHIPPHY_H +#define _MICROCHIPPHY_H + +#define LAN88XX_INT_MASK (0x19) +#define LAN88XX_INT_MASK_MDINTPIN_EN_ (0x8000) +#define LAN88XX_INT_MASK_SPEED_CHANGE_ (0x4000) +#define LAN88XX_INT_MASK_LINK_CHANGE_ (0x2000) +#define LAN88XX_INT_MASK_FDX_CHANGE_ (0x1000) +#define LAN88XX_INT_MASK_AUTONEG_ERR_ (0x0800) +#define LAN88XX_INT_MASK_AUTONEG_DONE_ (0x0400) +#define LAN88XX_INT_MASK_POE_DETECT_ (0x0200) +#define LAN88XX_INT_MASK_SYMBOL_ERR_ (0x0100) +#define LAN88XX_INT_MASK_FAST_LINK_FAIL_ (0x0080) +#define LAN88XX_INT_MASK_WOL_EVENT_ (0x0040) +#define LAN88XX_INT_MASK_EXTENDED_INT_ (0x0020) +#define LAN88XX_INT_MASK_RESERVED_ (0x0010) +#define LAN88XX_INT_MASK_FALSE_CARRIER_ (0x0008) +#define LAN88XX_INT_MASK_LINK_SPEED_DS_ (0x0004) +#define LAN88XX_INT_MASK_MASTER_SLAVE_DONE_ (0x0002) +#define LAN88XX_INT_MASK_RX__ER_ (0x0001) + +#define LAN88XX_INT_STS (0x1A) +#define LAN88XX_INT_STS_INT_ACTIVE_ (0x8000) +#define LAN88XX_INT_STS_SPEED_CHANGE_ (0x4000) +#define LAN88XX_INT_STS_LINK_CHANGE_ (0x2000) +#define LAN88XX_INT_STS_FDX_CHANGE_ (0x1000) +#define LAN88XX_INT_STS_AUTONEG_ERR_ (0x0800) +#define LAN88XX_INT_STS_AUTONEG_DONE_ (0x0400) +#define LAN88XX_INT_STS_POE_DETECT_ (0x0200) +#define LAN88XX_INT_STS_SYMBOL_ERR_ (0x0100) +#define LAN88XX_INT_STS_FAST_LINK_FAIL_ (0x0080) +#define LAN88XX_INT_STS_WOL_EVENT_ (0x0040) +#define LAN88XX_INT_STS_EXTENDED_INT_ (0x0020) +#define LAN88XX_INT_STS_RESERVED_ (0x0010) +#define LAN88XX_INT_STS_FALSE_CARRIER_ (0x0008) +#define LAN88XX_INT_STS_LINK_SPEED_DS_ (0x0004) +#define LAN88XX_INT_STS_MASTER_SLAVE_DONE_ (0x0002) +#define LAN88XX_INT_STS_RX_ER_ (0x0001) + +#define LAN88XX_EXT_PAGE_ACCESS (0x1F) +#define LAN88XX_EXT_PAGE_SPACE_0 (0x0000) +#define LAN88XX_EXT_PAGE_SPACE_1 (0x0001) +#define LAN88XX_EXT_PAGE_SPACE_2 (0x0002) + +/* Extended Register Page 1 space */ +#define LAN88XX_EXT_MODE_CTRL (0x13) +#define LAN88XX_EXT_MODE_CTRL_MDIX_MASK_ (0x000C) +#define LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_ (0x0000) +#define LAN88XX_EXT_MODE_CTRL_MDI_ (0x0008) +#define LAN88XX_EXT_MODE_CTRL_MDI_X_ (0x000C) + +/* MMD 3 Registers */ +#define LAN88XX_MMD3_CHIP_ID (32877) +#define LAN88XX_MMD3_CHIP_REV (32878) + +#endif /* _MICROCHIPPHY_H */ diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index bcbf8c72a77b..baad4cb8e9b0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -79,7 +79,8 @@ enum { enum { MLX4_MAX_PORTS = 2, - MLX4_MAX_PORT_PKEYS = 128 + MLX4_MAX_PORT_PKEYS = 128, + MLX4_MAX_PORT_GIDS = 128 }; /* base qkey for use in sriov tunnel-qp/proxy-qp communication. diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index 9553a73d2049..5a06d969338e 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -59,6 +59,7 @@ struct mlx4_interface { void (*event) (struct mlx4_dev *dev, void *context, enum mlx4_dev_event event, unsigned long param); void * (*get_dev)(struct mlx4_dev *dev, void *context, u8 port); + void (*activate)(struct mlx4_dev *dev, void *context); struct list_head list; enum mlx4_protocol protocol; int flags; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 250b1ff8b48d..8eb3b19af2a4 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -402,6 +402,17 @@ struct mlx5_cmd_teardown_hca_mbox_out { u8 rsvd[8]; }; +struct mlx5_cmd_query_special_contexts_mbox_in { + struct mlx5_inbox_hdr hdr; + u8 rsvd[8]; +}; + +struct mlx5_cmd_query_special_contexts_mbox_out { + struct mlx5_outbox_hdr hdr; + __be32 dump_fill_mkey; + __be32 resd_lkey; +}; + struct mlx5_cmd_layout { u8 type; u8 rsvd0[3]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 8b6d6f2154a4..27b53f9a24ad 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -845,6 +845,7 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); +int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey); struct mlx5_profile { u64 mask; diff --git a/include/linux/mm.h b/include/linux/mm.h index 8b257c43855b..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; @@ -249,6 +250,8 @@ struct vm_operations_struct { void (*close)(struct vm_area_struct * area); int (*mremap)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*pmd_fault)(struct vm_area_struct *, unsigned long address, + pmd_t *, unsigned int flags); void (*map_pages)(struct vm_area_struct *vma, struct vm_fault *vmf); /* notification that a previously read-only page is about to become @@ -307,18 +310,6 @@ struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) -/* It's valid only if the page is free path or free_list */ -static inline void set_freepage_migratetype(struct page *page, int migratetype) -{ - page->index = migratetype; -} - -/* It's valid only if the page is free path or free_list */ -static inline int get_freepage_migratetype(struct page *page) -{ - return page->index; -} - /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -359,20 +350,15 @@ static inline int get_page_unless_zero(struct page *page) return atomic_inc_not_zero(&page->_count); } -/* - * Try to drop a ref unless the page has a refcount of one, return false if - * that is the case. - * This is to make sure that the refcount won't become zero after this drop. - * This can be called when MMU is off so it must not access - * any of the virtual mappings. - */ -static inline int put_page_unless_one(struct page *page) -{ - return atomic_add_unless(&page->_count, -1, 1); -} - extern int page_is_ram(unsigned long pfn); -extern int region_is_ram(resource_size_t phys_addr, unsigned long size); + +enum { + REGION_INTERSECTS, + REGION_DISJOINT, + REGION_MIXED, +}; + +int region_intersects(resource_size_t offset, size_t size, const char *type); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); @@ -1229,6 +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); @@ -1260,6 +1289,11 @@ static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); } +static inline bool vma_is_anonymous(struct vm_area_struct *vma) +{ + return !vma->vm_ops; +} + static inline int stack_guard_page_start(struct vm_area_struct *vma, unsigned long addr) { @@ -1883,11 +1917,19 @@ extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned lo extern unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); -extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, +extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate); + vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate); extern int do_munmap(struct mm_struct *, unsigned long, size_t); +static inline unsigned long +do_mmap_pgoff(struct file *file, unsigned long addr, + unsigned long len, unsigned long prot, unsigned long flags, + unsigned long pgoff, unsigned long *populate) +{ + return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate); +} + #ifdef CONFIG_MMU extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); @@ -2186,6 +2228,7 @@ extern int memory_failure(unsigned long pfn, int trapno, int flags); extern void memory_failure_queue(unsigned long pfn, int trapno, int flags); extern int unpoison_memory(unsigned long pfn); extern int get_hwpoison_page(struct page *page); +extern void put_hwpoison_page(struct page *page); extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c8d0a73d64c4..3d6baa7d4534 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -235,7 +235,7 @@ struct page_frag_cache { bool pfmemalloc; }; -typedef unsigned long __nocast vm_flags_t; +typedef unsigned long vm_flags_t; /* * A region containing a mapping of a non-memory backed file under NOMMU diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 4d3776d25925..fdd0779ccdfa 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -279,10 +279,13 @@ struct mmc_card { #define MMC_QUIRK_LONG_READ_TIME (1<<9) /* Data read time > CSD says */ #define MMC_QUIRK_SEC_ERASE_TRIM_BROKEN (1<<10) /* Skip secure for erase/trim */ #define MMC_QUIRK_BROKEN_IRQ_POLLING (1<<11) /* Polling SDIO_CCCR_INTx could create a fake interrupt */ +#define MMC_QUIRK_TRIM_BROKEN (1<<12) /* Skip trim */ + unsigned int erase_size; /* erase size in sectors */ unsigned int erase_shift; /* if erase unit is power 2 */ unsigned int pref_erase; /* in sectors */ + unsigned int eg_boundary; /* don't cross erase-group boundaries */ u8 erased_byte; /* value of erased bytes */ u32 raw_cid[4]; /* raw card CID */ diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h index 5be97676f1fa..134c57422740 100644 --- a/include/linux/mmc/dw_mmc.h +++ b/include/linux/mmc/dw_mmc.h @@ -98,6 +98,7 @@ struct mmc_data; * @irq_flags: The flags to be passed to request_irq. * @irq: The irq value to be passed to request_irq. * @sdio_id0: Number of slot0 in the SDIO interrupt registers. + * @dto_timer: Timer for broken data transfer over scheme. * * Locking * ======= @@ -153,11 +154,7 @@ struct dw_mci { dma_addr_t sg_dma; void *sg_cpu; const struct dw_mci_dma_ops *dma_ops; -#ifdef CONFIG_MMC_DW_IDMAC unsigned int ring_size; -#else - struct dw_mci_dma_data *dma_data; -#endif u32 cmd_status; u32 data_status; u32 stop_cmdr; @@ -204,6 +201,7 @@ struct dw_mci { int sdio_id0; struct timer_list cmd11_timer; + struct timer_list dto_timer; }; /* DMA ops for Internal/External DMAC interface */ @@ -226,6 +224,8 @@ struct dw_mci_dma_ops { #define DW_MCI_QUIRK_HIGHSPEED BIT(2) /* Unreliable card detection */ #define DW_MCI_QUIRK_BROKEN_CARD_DETECTION BIT(3) +/* Timer for broken data transfer over scheme */ +#define DW_MCI_QUIRK_BROKEN_DTO BIT(4) struct dma_pdata; @@ -259,7 +259,6 @@ struct dw_mci_board { struct dw_mci_dma_ops *dma_ops; struct dma_pdata *data; - struct block_settings *blk_settings; }; #endif /* LINUX_MMC_DW_MMC_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 1369e54faeb7..83b81fd865f3 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -412,7 +412,8 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host) { host->ops->enable_sdio_irq(host, 0); host->sdio_irq_pending = true; - wake_up_process(host->sdio_irq_thread); + if (host->sdio_irq_thread) + wake_up_process(host->sdio_irq_thread); } void sdio_run_irqs(struct mmc_host *host); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 61cd67f4d788..a1a210d59961 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -66,6 +66,16 @@ struct mmu_notifier_ops { unsigned long end); /* + * clear_young is a lightweight version of clear_flush_young. Like the + * latter, it is supposed to test-and-clear the young/accessed bitflag + * in the secondary pte, but it may omit flushing the secondary tlb. + */ + int (*clear_young)(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end); + + /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing @@ -203,6 +213,9 @@ extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); +extern int __mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, @@ -231,6 +244,15 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, return 0; } +static inline int mmu_notifier_clear_young(struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + if (mm_has_notifiers(mm)) + return __mmu_notifier_clear_young(mm, start, end); + return 0; +} + static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { @@ -311,6 +333,28 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) __young; \ }) +#define ptep_clear_young_notify(__vma, __address, __ptep) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ + __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ + ___address + PAGE_SIZE); \ + __young; \ +}) + +#define pmdp_clear_young_notify(__vma, __address, __pmdp) \ +({ \ + int __young; \ + struct vm_area_struct *___vma = __vma; \ + unsigned long ___address = __address; \ + __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ + __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ + ___address + PMD_SIZE); \ + __young; \ +}) + #define ptep_clear_flush_notify(__vma, __address, __ptep) \ ({ \ unsigned long ___addr = __address & PAGE_MASK; \ @@ -427,6 +471,8 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young +#define ptep_clear_young_notify ptep_test_and_clear_young +#define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pmdp_huge_get_and_clear_notify pmdp_huge_get_and_clear diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ac00e2050943..d94347737292 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -319,7 +319,11 @@ enum zone_type { ZONE_HIGHMEM, #endif ZONE_MOVABLE, +#ifdef CONFIG_ZONE_DEVICE + ZONE_DEVICE, +#endif __MAX_NR_ZONES + }; #ifndef __GENERATING_BOUNDS_H @@ -786,6 +790,25 @@ static inline bool pgdat_is_empty(pg_data_t *pgdat) return !pgdat->node_start_pfn && !pgdat->node_spanned_pages; } +static inline int zone_id(const struct zone *zone) +{ + struct pglist_data *pgdat = zone->zone_pgdat; + + return zone - pgdat->node_zones; +} + +#ifdef CONFIG_ZONE_DEVICE +static inline bool is_dev_zone(const struct zone *zone) +{ + return zone_id(zone) == ZONE_DEVICE; +} +#else +static inline bool is_dev_zone(const struct zone *zone) +{ + return false; +} +#endif + #include <linux/memory_hotplug.h> extern struct mutex zonelists_mutex; diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index 29975c73a953..366cf77953b5 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -27,9 +27,9 @@ #include <linux/string.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/io.h> #include <asm/unaligned.h> -#include <asm/io.h> #include <asm/barrier.h> #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1 diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 9120edb650a0..639e9b8b0e4d 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -68,8 +68,17 @@ extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size, - u32 dst_portid, gfp_t gfp_mask); + +extern struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size, + unsigned int ldiff, u32 dst_portid, + gfp_t gfp_mask); +static inline struct sk_buff * +netlink_alloc_skb(struct sock *ssk, unsigned int size, u32 dst_portid, + gfp_t gfp_mask) +{ + return __netlink_alloc_skb(ssk, size, 0, dst_portid, gfp_mask); +} + extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a91adf6e02f2..78488e099ce7 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -47,6 +47,12 @@ static inline bool trigger_allbutself_cpu_backtrace(void) arch_trigger_all_cpu_backtrace(false); return true; } + +/* generic implementation */ +void nmi_trigger_all_cpu_backtrace(bool include_self, + void (*raise)(cpumask_t *mask)); +bool nmi_cpu_backtrace(struct pt_regs *regs); + #else static inline bool trigger_all_cpu_backtrace(void) { 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/oid_registry.h b/include/linux/oid_registry.h index c2bbf672b84e..d2fa9ca42e9a 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -41,7 +41,7 @@ enum OID { OID_signed_data, /* 1.2.840.113549.1.7.2 */ /* PKCS#9 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-9(9)} */ OID_email_address, /* 1.2.840.113549.1.9.1 */ - OID_content_type, /* 1.2.840.113549.1.9.3 */ + OID_contentType, /* 1.2.840.113549.1.9.3 */ OID_messageDigest, /* 1.2.840.113549.1.9.4 */ OID_signingTime, /* 1.2.840.113549.1.9.5 */ OID_smimeCapabilites, /* 1.2.840.113549.1.9.15 */ @@ -54,6 +54,8 @@ enum OID { /* Microsoft Authenticode & Software Publishing */ OID_msIndirectData, /* 1.3.6.1.4.1.311.2.1.4 */ + OID_msStatementType, /* 1.3.6.1.4.1.311.2.1.11 */ + OID_msSpOpusInfo, /* 1.3.6.1.4.1.311.2.1.12 */ OID_msPeImageDataObjId, /* 1.3.6.1.4.1.311.2.1.15 */ OID_msIndividualSPKeyPurpose, /* 1.3.6.1.4.1.311.2.1.21 */ OID_msOutlookExpress, /* 1.3.6.1.4.1.311.16.4 */ @@ -61,6 +63,9 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ + OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ + OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ + OID_sha224, /* 2.16.840.1.101.3.4.2.4 */ /* Distinguished Name attribute IDs [RFC 2256] */ OID_commonName, /* 2.5.4.3 */ diff --git a/include/linux/oom.h b/include/linux/oom.h index 7deecb7bca5e..03e6257321f0 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -13,6 +13,27 @@ struct mem_cgroup; struct task_struct; /* + * Details of the page allocation that triggered the oom killer that are used to + * determine what should be killed. + */ +struct oom_control { + /* Used to determine cpuset */ + struct zonelist *zonelist; + + /* Used to determine mempolicy */ + nodemask_t *nodemask; + + /* Used to determine cpuset and node locality requirement */ + const gfp_t gfp_mask; + + /* + * order == -1 means the oom kill is required by sysrq, otherwise only + * for display purposes. + */ + const int order; +}; + +/* * Types of limitations to the nodes from which allocations may occur */ enum oom_constraint { @@ -57,21 +78,18 @@ extern unsigned long oom_badness(struct task_struct *p, extern int oom_kills_count(void); extern void note_oom_kill(void); -extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, +extern void oom_kill_process(struct oom_control *oc, struct task_struct *p, unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message); + struct mem_cgroup *memcg, const char *message); -extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, - int order, const nodemask_t *nodemask, +extern void check_panic_on_oom(struct oom_control *oc, + enum oom_constraint constraint, struct mem_cgroup *memcg); -extern enum oom_scan_t oom_scan_process_thread(struct task_struct *task, - unsigned long totalpages, const nodemask_t *nodemask, - bool force_kill); +extern enum oom_scan_t oom_scan_process_thread(struct oom_control *oc, + struct task_struct *task, unsigned long totalpages); -extern bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *mask, bool force_kill); +extern bool out_of_memory(struct oom_control *oc); extern void exit_oom_victim(void); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 41c93844fb1d..416509e26d6d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -109,6 +109,10 @@ enum pageflags { #ifdef CONFIG_TRANSPARENT_HUGEPAGE PG_compound_lock, #endif +#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) + PG_young, + PG_idle, +#endif __NR_PAGEFLAGS, /* Filesystems */ @@ -289,6 +293,13 @@ PAGEFLAG_FALSE(HWPoison) #define __PG_HWPOISON 0 #endif +#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT) +TESTPAGEFLAG(Young, young) +SETPAGEFLAG(Young, young) +TESTCLEARFLAG(Young, young) +PAGEFLAG(Idle, idle) +#endif + /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 2dc1e1697b45..047d64706f2a 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -65,11 +65,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, bool skip_hwpoisoned_pages); -/* - * Internal functions. Changes pageblock's migrate type. - */ -int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages); -void unset_migratetype_isolate(struct page *page, unsigned migratetype); struct page *alloc_migrate_target(struct page *page, unsigned long private, int **resultp); diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index c42981cd99aa..17f118a82854 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -26,6 +26,10 @@ enum page_ext_flags { PAGE_EXT_DEBUG_POISON, /* Page is poisoned */ PAGE_EXT_DEBUG_GUARD, PAGE_EXT_OWNER, +#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) + PAGE_EXT_YOUNG, + PAGE_EXT_IDLE, +#endif }; /* diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h new file mode 100644 index 000000000000..bf268fa92c5b --- /dev/null +++ b/include/linux/page_idle.h @@ -0,0 +1,110 @@ +#ifndef _LINUX_MM_PAGE_IDLE_H +#define _LINUX_MM_PAGE_IDLE_H + +#include <linux/bitops.h> +#include <linux/page-flags.h> +#include <linux/page_ext.h> + +#ifdef CONFIG_IDLE_PAGE_TRACKING + +#ifdef CONFIG_64BIT +static inline bool page_is_young(struct page *page) +{ + return PageYoung(page); +} + +static inline void set_page_young(struct page *page) +{ + SetPageYoung(page); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return TestClearPageYoung(page); +} + +static inline bool page_is_idle(struct page *page) +{ + return PageIdle(page); +} + +static inline void set_page_idle(struct page *page) +{ + SetPageIdle(page); +} + +static inline void clear_page_idle(struct page *page) +{ + ClearPageIdle(page); +} +#else /* !CONFIG_64BIT */ +/* + * If there is not enough space to store Idle and Young bits in page flags, use + * page ext flags instead. + */ +extern struct page_ext_operations page_idle_ops; + +static inline bool page_is_young(struct page *page) +{ + return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); +} + +static inline void set_page_young(struct page *page) +{ + set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return test_and_clear_bit(PAGE_EXT_YOUNG, + &lookup_page_ext(page)->flags); +} + +static inline bool page_is_idle(struct page *page) +{ + return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} + +static inline void set_page_idle(struct page *page) +{ + set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} + +static inline void clear_page_idle(struct page *page) +{ + clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); +} +#endif /* CONFIG_64BIT */ + +#else /* !CONFIG_IDLE_PAGE_TRACKING */ + +static inline bool page_is_young(struct page *page) +{ + return false; +} + +static inline void set_page_young(struct page *page) +{ +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return false; +} + +static inline bool page_is_idle(struct page *page) +{ + return false; +} + +static inline void set_page_idle(struct page *page) +{ +} + +static inline void clear_page_idle(struct page *page) +{ +} + +#endif /* CONFIG_IDLE_PAGE_TRACKING */ + +#endif /* _LINUX_MM_PAGE_IDLE_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 1a64733c48c7..e90eb22de628 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1227,6 +1227,8 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, dma_pool_create(name, &pdev->dev, size, align, allocation) #define pci_pool_destroy(pool) dma_pool_destroy(pool) #define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle) +#define pci_pool_zalloc(pool, flags, handle) \ + dma_pool_zalloc(pool, flags, handle) #define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr) struct msix_entry { diff --git a/include/linux/platform_data/i2c-mux-reg.h b/include/linux/platform_data/i2c-mux-reg.h new file mode 100644 index 000000000000..c68712aadf43 --- /dev/null +++ b/include/linux/platform_data/i2c-mux-reg.h @@ -0,0 +1,44 @@ +/* + * I2C multiplexer using a single register + * + * Copyright 2015 Freescale Semiconductor + * York Sun <yorksun@freescale.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __LINUX_PLATFORM_DATA_I2C_MUX_REG_H +#define __LINUX_PLATFORM_DATA_I2C_MUX_REG_H + +/** + * struct i2c_mux_reg_platform_data - Platform-dependent data for i2c-mux-reg + * @parent: Parent I2C bus adapter number + * @base_nr: Base I2C bus number to number adapters from or zero for dynamic + * @values: Array of value for each channel + * @n_values: Number of multiplexer channels + * @little_endian: Indicating if the register is in little endian + * @write_only: Reading the register is not allowed by hardware + * @classes: Optional I2C auto-detection classes + * @idle: Value to write to mux when idle + * @idle_in_use: indicate if idle value is in use + * @reg: Virtual address of the register to switch channel + * @reg_size: register size in bytes + */ +struct i2c_mux_reg_platform_data { + int parent; + int base_nr; + const unsigned int *values; + int n_values; + bool little_endian; + bool write_only; + const unsigned int *classes; + u32 idle; + bool idle_in_use; + void __iomem *reg; + resource_size_t reg_size; +}; + +#endif /* __LINUX_PLATFORM_DATA_I2C_MUX_REG_H */ diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h index e1571efa3f2b..95ccab3f454a 100644 --- a/include/linux/platform_data/mmc-esdhc-imx.h +++ b/include/linux/platform_data/mmc-esdhc-imx.h @@ -45,5 +45,6 @@ struct esdhc_platform_data { int max_bus_width; bool support_vsel; unsigned int delay_line; + unsigned int tuning_step; /* The delay cell steps in tuning procedure */ }; #endif /* __ASM_ARCH_IMX_ESDHC_H */ 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/pmem.h b/include/linux/pmem.h index d2114045a6c4..85f810b33917 100644 --- a/include/linux/pmem.h +++ b/include/linux/pmem.h @@ -14,28 +14,42 @@ #define __PMEM_H__ #include <linux/io.h> +#include <linux/uio.h> #ifdef CONFIG_ARCH_HAS_PMEM_API -#include <asm/cacheflush.h> +#define ARCH_MEMREMAP_PMEM MEMREMAP_WB +#include <asm/pmem.h> #else +#define ARCH_MEMREMAP_PMEM MEMREMAP_WT +/* + * These are simply here to enable compilation, all call sites gate + * calling these symbols with arch_has_pmem_api() and redirect to the + * implementation in asm/pmem.h. + */ +static inline bool __arch_has_wmb_pmem(void) +{ + return false; +} + static inline void arch_wmb_pmem(void) { BUG(); } -static inline bool __arch_has_wmb_pmem(void) +static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, + size_t n) { - return false; + BUG(); } -static inline void __pmem *arch_memremap_pmem(resource_size_t offset, - unsigned long size) +static inline size_t arch_copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) { - return NULL; + BUG(); + return 0; } -static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, - size_t n) +static inline void arch_clear_pmem(void __pmem *addr, size_t size) { BUG(); } @@ -43,18 +57,22 @@ static inline void arch_memcpy_to_pmem(void __pmem *dst, const void *src, /* * Architectures that define ARCH_HAS_PMEM_API must provide - * implementations for arch_memremap_pmem(), arch_memcpy_to_pmem(), - * arch_wmb_pmem(), and __arch_has_wmb_pmem(). + * implementations for arch_memcpy_to_pmem(), arch_wmb_pmem(), + * arch_copy_from_iter_pmem(), arch_clear_pmem() and arch_has_wmb_pmem(). */ - static inline void memcpy_from_pmem(void *dst, void __pmem const *src, size_t size) { memcpy(dst, (void __force const *) src, size); } -static inline void memunmap_pmem(void __pmem *addr) +static inline void memunmap_pmem(struct device *dev, void __pmem *addr) +{ + devm_memunmap(dev, (void __force *) addr); +} + +static inline bool arch_has_pmem_api(void) { - iounmap((void __force __iomem *) addr); + return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API); } /** @@ -68,14 +86,7 @@ static inline void memunmap_pmem(void __pmem *addr) */ static inline bool arch_has_wmb_pmem(void) { - if (IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API)) - return __arch_has_wmb_pmem(); - return false; -} - -static inline bool arch_has_pmem_api(void) -{ - return IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && arch_has_wmb_pmem(); + return arch_has_pmem_api() && __arch_has_wmb_pmem(); } /* @@ -85,16 +96,24 @@ static inline bool arch_has_pmem_api(void) * default_memremap_pmem + default_memcpy_to_pmem is sufficient for * making data durable relative to i/o completion. */ -static void default_memcpy_to_pmem(void __pmem *dst, const void *src, +static inline void default_memcpy_to_pmem(void __pmem *dst, const void *src, size_t size) { memcpy((void __force *) dst, src, size); } -static void __pmem *default_memremap_pmem(resource_size_t offset, - unsigned long size) +static inline size_t default_copy_from_iter_pmem(void __pmem *addr, + size_t bytes, struct iov_iter *i) +{ + return copy_from_iter_nocache((void __force *)addr, bytes, i); +} + +static inline void default_clear_pmem(void __pmem *addr, size_t size) { - return (void __pmem __force *)ioremap_wt(offset, size); + if (size == PAGE_SIZE && ((unsigned long)addr & ~PAGE_MASK) == 0) + clear_page((void __force *)addr); + else + memset((void __force *)addr, 0, size); } /** @@ -109,12 +128,11 @@ static void __pmem *default_memremap_pmem(resource_size_t offset, * wmb_pmem() arrange for the data to be written through the * cache to persistent media. */ -static inline void __pmem *memremap_pmem(resource_size_t offset, - unsigned long size) +static inline void __pmem *memremap_pmem(struct device *dev, + resource_size_t offset, unsigned long size) { - if (arch_has_pmem_api()) - return arch_memremap_pmem(offset, size); - return default_memremap_pmem(offset, size); + return (void __pmem *) devm_memremap(dev, offset, size, + ARCH_MEMREMAP_PMEM); } /** @@ -146,7 +164,42 @@ static inline void memcpy_to_pmem(void __pmem *dst, const void *src, size_t n) */ static inline void wmb_pmem(void) { - if (arch_has_pmem_api()) + if (arch_has_wmb_pmem()) arch_wmb_pmem(); + else + wmb(); +} + +/** + * copy_from_iter_pmem - copy data from an iterator to PMEM + * @addr: PMEM destination address + * @bytes: number of bytes to copy + * @i: iterator with source data + * + * Copy data from the iterator 'i' to the PMEM buffer starting at 'addr'. + * This function requires explicit ordering with a wmb_pmem() call. + */ +static inline size_t copy_from_iter_pmem(void __pmem *addr, size_t bytes, + struct iov_iter *i) +{ + if (arch_has_pmem_api()) + return arch_copy_from_iter_pmem(addr, bytes, i); + return default_copy_from_iter_pmem(addr, bytes, i); +} + +/** + * clear_pmem - zero a PMEM memory range + * @addr: virtual start address + * @size: number of bytes to zero + * + * Write zeros into the memory range starting at 'addr' for 'size' bytes. + * This function requires explicit ordering with a wmb_pmem() call. + */ +static inline void clear_pmem(void __pmem *addr, size_t size) +{ + if (arch_has_pmem_api()) + arch_clear_pmem(addr, size); + else + default_clear_pmem(addr, size); } #endif /* __PMEM_H__ */ diff --git a/include/linux/poison.h b/include/linux/poison.h index 2110a81c5e2a..317e16de09e5 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -19,8 +19,8 @@ * under normal circumstances, used to verify that nobody uses * non-initialized list entries. */ -#define LIST_POISON1 ((void *) 0x00100100 + POISON_POINTER_DELTA) -#define LIST_POISON2 ((void *) 0x00200200 + POISON_POINTER_DELTA) +#define LIST_POISON1 ((void *) 0x100 + POISON_POINTER_DELTA) +#define LIST_POISON2 ((void *) 0x200 + POISON_POINTER_DELTA) /********** include/linux/timer.h **********/ /* @@ -69,10 +69,6 @@ #define ATM_POISON_FREE 0x12 #define ATM_POISON 0xdeadbeef -/********** net/ **********/ -#define NEIGHBOR_DEAD 0xdeadbeef -#define NETFILTER_LINK_POISON 0xdead57ac - /********** kernel/mutexes **********/ #define MUTEX_DEBUG_INIT 0x11 #define MUTEX_DEBUG_FREE 0x22 @@ -83,7 +79,4 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd -/********** sound/oss/ **********/ -#define OSS_POISON_FREE 0xAB - #endif diff --git a/include/linux/printk.h b/include/linux/printk.h index a6298b27ac99..9729565c25ff 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -404,10 +404,10 @@ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ - DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ + DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, pr_fmt(fmt)); \ if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \ __ratelimit(&_rs)) \ - __dynamic_pr_debug(&descriptor, fmt, ##__VA_ARGS__); \ + __dynamic_pr_debug(&descriptor, pr_fmt(fmt), ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define pr_debug_ratelimited(fmt, ...) \ @@ -456,11 +456,17 @@ static inline void print_hex_dump_bytes(const char *prefix_str, int prefix_type, groupsize, buf, len, ascii) \ dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) -#else +#elif defined(DEBUG) #define print_hex_dump_debug(prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) \ print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, rowsize, \ groupsize, buf, len, ascii) -#endif /* defined(CONFIG_DYNAMIC_DEBUG) */ +#else +static inline void print_hex_dump_debug(const char *prefix_str, int prefix_type, + int rowsize, int groupsize, + const void *buf, size_t len, bool ascii) +{ +} +#endif #endif diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 987a73a40ef8..061265f92876 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -34,6 +34,7 @@ #define PT_TRACE_SECCOMP PT_EVENT_FLAG(PTRACE_EVENT_SECCOMP) #define PT_EXITKILL (PTRACE_O_EXITKILL << PT_OPT_FLAG_SHIFT) +#define PT_SUSPEND_SECCOMP (PTRACE_O_SUSPEND_SECCOMP << PT_OPT_FLAG_SHIFT) /* single stepping state bits (used on ARM and PA-RISC) */ #define PT_SINGLESTEP_BIT 31 diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 36262d08a9da..d681f6875aef 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -79,26 +79,43 @@ enum { PWMF_EXPORTED = 1 << 2, }; +/** + * struct pwm_device - PWM channel object + * @label: name of the PWM device + * @flags: flags associated with the PWM device + * @hwpwm: per-chip relative index of the PWM device + * @pwm: global index of the PWM device + * @chip: PWM chip providing this PWM device + * @chip_data: chip-private data associated with the PWM device + * @period: period of the PWM signal (in nanoseconds) + * @duty_cycle: duty cycle of the PWM signal (in nanoseconds) + * @polarity: polarity of the PWM signal + */ struct pwm_device { - const char *label; - unsigned long flags; - unsigned int hwpwm; - unsigned int pwm; - struct pwm_chip *chip; - void *chip_data; - - unsigned int period; /* in nanoseconds */ - unsigned int duty_cycle; /* in nanoseconds */ - enum pwm_polarity polarity; + const char *label; + unsigned long flags; + unsigned int hwpwm; + unsigned int pwm; + struct pwm_chip *chip; + void *chip_data; + + unsigned int period; + unsigned int duty_cycle; + enum pwm_polarity polarity; }; +static inline bool pwm_is_enabled(const struct pwm_device *pwm) +{ + return test_bit(PWMF_ENABLED, &pwm->flags); +} + static inline void pwm_set_period(struct pwm_device *pwm, unsigned int period) { if (pwm) pwm->period = period; } -static inline unsigned int pwm_get_period(struct pwm_device *pwm) +static inline unsigned int pwm_get_period(const struct pwm_device *pwm) { return pwm ? pwm->period : 0; } @@ -109,7 +126,7 @@ static inline void pwm_set_duty_cycle(struct pwm_device *pwm, unsigned int duty) pwm->duty_cycle = duty; } -static inline unsigned int pwm_get_duty_cycle(struct pwm_device *pwm) +static inline unsigned int pwm_get_duty_cycle(const struct pwm_device *pwm) { return pwm ? pwm->duty_cycle : 0; } @@ -119,6 +136,11 @@ static inline unsigned int pwm_get_duty_cycle(struct pwm_device *pwm) */ int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity); +static inline enum pwm_polarity pwm_get_polarity(const struct pwm_device *pwm) +{ + return pwm ? pwm->polarity : PWM_POLARITY_NORMAL; +} + /** * struct pwm_ops - PWM controller operations * @request: optional hook for requesting a PWM @@ -131,25 +153,18 @@ int pwm_set_polarity(struct pwm_device *pwm, enum pwm_polarity polarity); * @owner: helps prevent removal of modules exporting active PWMs */ struct pwm_ops { - int (*request)(struct pwm_chip *chip, - struct pwm_device *pwm); - void (*free)(struct pwm_chip *chip, - struct pwm_device *pwm); - int (*config)(struct pwm_chip *chip, - struct pwm_device *pwm, - int duty_ns, int period_ns); - int (*set_polarity)(struct pwm_chip *chip, - struct pwm_device *pwm, - enum pwm_polarity polarity); - int (*enable)(struct pwm_chip *chip, - struct pwm_device *pwm); - void (*disable)(struct pwm_chip *chip, - struct pwm_device *pwm); + int (*request)(struct pwm_chip *chip, struct pwm_device *pwm); + void (*free)(struct pwm_chip *chip, struct pwm_device *pwm); + int (*config)(struct pwm_chip *chip, struct pwm_device *pwm, + int duty_ns, int period_ns); + int (*set_polarity)(struct pwm_chip *chip, struct pwm_device *pwm, + enum pwm_polarity polarity); + int (*enable)(struct pwm_chip *chip, struct pwm_device *pwm); + void (*disable)(struct pwm_chip *chip, struct pwm_device *pwm); #ifdef CONFIG_DEBUG_FS - void (*dbg_show)(struct pwm_chip *chip, - struct seq_file *s); + void (*dbg_show)(struct pwm_chip *chip, struct seq_file *s); #endif - struct module *owner; + struct module *owner; }; /** @@ -160,22 +175,24 @@ struct pwm_ops { * @base: number of first PWM controlled by this chip * @npwm: number of PWMs controlled by this chip * @pwms: array of PWM devices allocated by the framework + * @of_xlate: request a PWM device given a device tree PWM specifier + * @of_pwm_n_cells: number of cells expected in the device tree PWM specifier * @can_sleep: must be true if the .config(), .enable() or .disable() * operations may sleep */ struct pwm_chip { - struct device *dev; - struct list_head list; - const struct pwm_ops *ops; - int base; - unsigned int npwm; - - struct pwm_device *pwms; - - struct pwm_device * (*of_xlate)(struct pwm_chip *pc, - const struct of_phandle_args *args); - unsigned int of_pwm_n_cells; - bool can_sleep; + struct device *dev; + struct list_head list; + const struct pwm_ops *ops; + int base; + unsigned int npwm; + + struct pwm_device *pwms; + + struct pwm_device * (*of_xlate)(struct pwm_chip *pc, + const struct of_phandle_args *args); + unsigned int of_pwm_n_cells; + bool can_sleep; }; #if IS_ENABLED(CONFIG_PWM) diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4a6759098769..8fc0bfd8edc4 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -17,6 +17,7 @@ #include <linux/rbtree.h> #include <linux/err.h> #include <linux/bug.h> +#include <linux/lockdep.h> struct module; struct device; @@ -51,14 +52,17 @@ struct reg_default { }; /** - * Register/value pairs for sequences of writes + * Register/value pairs for sequences of writes with an optional delay in + * microseconds to be applied after each write. * * @reg: Register address. * @def: Register value. + * @delay_us: Delay to be applied after the register write in microseconds */ struct reg_sequence { unsigned int reg; unsigned int def; + unsigned int delay_us; }; #ifdef CONFIG_REGMAP @@ -307,8 +311,12 @@ typedef void (*regmap_hw_free_context)(void *context); * if not implemented on a given device. * @async_write: Write operation which completes asynchronously, optional and * must serialise with respect to non-async I/O. + * @reg_write: Write a single register value to the given register address. This + * write operation has to complete when returning from the function. * @read: Read operation. Data is returned in the buffer used to transmit * data. + * @reg_read: Read a single register value from a given register address. + * @free_context: Free context. * @async_alloc: Allocate a regmap_async() structure. * @read_flag_mask: Mask to be set in the top byte of the register when doing * a read. @@ -318,7 +326,8 @@ typedef void (*regmap_hw_free_context)(void *context); * @val_format_endian_default: Default endianness for formatted register * values. Used when the regmap_config specifies DEFAULT. If this is * DEFAULT, BIG is assumed. - * @async_size: Size of struct used for async work. + * @max_raw_read: Max raw read size that can be used on the bus. + * @max_raw_write: Max raw write size that can be used on the bus. */ struct regmap_bus { bool fast_io; @@ -333,47 +342,186 @@ struct regmap_bus { u8 read_flag_mask; enum regmap_endian reg_format_endian_default; enum regmap_endian val_format_endian_default; + size_t max_raw_read; + size_t max_raw_write; }; -struct regmap *regmap_init(struct device *dev, - const struct regmap_bus *bus, - void *bus_context, - const struct regmap_config *config); +/* + * __regmap_init functions. + * + * These functions take a lock key and name parameter, and should not be called + * directly. Instead, use the regmap_init macros that generate a key and name + * for each call. + */ +struct regmap *__regmap_init(struct device *dev, + const struct regmap_bus *bus, + void *bus_context, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_i2c(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spi(struct spi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spmi_base(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_spmi_ext(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_mmio_clk(struct device *dev, const char *clk_id, + void __iomem *regs, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__regmap_init_ac97(struct snd_ac97 *ac97, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); + +struct regmap *__devm_regmap_init(struct device *dev, + const struct regmap_bus *bus, + void *bus_context, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spi(struct spi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spmi_base(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_spmi_ext(struct spmi_device *dev, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_mmio_clk(struct device *dev, + const char *clk_id, + void __iomem *regs, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); +struct regmap *__devm_regmap_init_ac97(struct snd_ac97 *ac97, + const struct regmap_config *config, + struct lock_class_key *lock_key, + const char *lock_name); + +/* + * Wrapper for regmap_init macros to include a unique lockdep key and name + * for each call. No-op if CONFIG_LOCKDEP is not set. + * + * @fn: Real function to call (in the form __[*_]regmap_init[_*]) + * @name: Config variable name (#config in the calling macro) + **/ +#ifdef CONFIG_LOCKDEP +#define __regmap_lockdep_wrapper(fn, name, ...) \ +( \ + ({ \ + static struct lock_class_key _key; \ + fn(__VA_ARGS__, &_key, \ + KBUILD_BASENAME ":" \ + __stringify(__LINE__) ":" \ + "(" name ")->lock"); \ + }) \ +) +#else +#define __regmap_lockdep_wrapper(fn, name, ...) fn(__VA_ARGS__, NULL, NULL) +#endif + +/** + * regmap_init(): Initialise register map + * + * @dev: Device that will be interacted with + * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. This function should generally not be called + * directly, it should be called by bus-specific init functions. + */ +#define regmap_init(dev, bus, bus_context, config) \ + __regmap_lockdep_wrapper(__regmap_init, #config, \ + dev, bus, bus_context, config) int regmap_attach_dev(struct device *dev, struct regmap *map, - const struct regmap_config *config); -struct regmap *regmap_init_i2c(struct i2c_client *i2c, - const struct regmap_config *config); -struct regmap *regmap_init_spi(struct spi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_spmi_base(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_spmi_ext(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *regmap_init_mmio_clk(struct device *dev, const char *clk_id, - void __iomem *regs, - const struct regmap_config *config); -struct regmap *regmap_init_ac97(struct snd_ac97 *ac97, - const struct regmap_config *config); - -struct regmap *devm_regmap_init(struct device *dev, - const struct regmap_bus *bus, - void *bus_context, - const struct regmap_config *config); -struct regmap *devm_regmap_init_i2c(struct i2c_client *i2c, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spi(struct spi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spmi_base(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_spmi_ext(struct spmi_device *dev, - const struct regmap_config *config); -struct regmap *devm_regmap_init_mmio_clk(struct device *dev, const char *clk_id, - void __iomem *regs, - const struct regmap_config *config); -struct regmap *devm_regmap_init_ac97(struct snd_ac97 *ac97, - const struct regmap_config *config); + const struct regmap_config *config); -bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); +/** + * regmap_init_i2c(): Initialise register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_i2c(i2c, config) \ + __regmap_lockdep_wrapper(__regmap_init_i2c, #config, \ + i2c, config) + +/** + * regmap_init_spi(): Initialise register map + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spi(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spi, #config, \ + dev, config) + +/** + * regmap_init_spmi_base(): Create regmap for the Base register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spmi_base(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spmi_base, #config, \ + dev, config) + +/** + * regmap_init_spmi_ext(): Create regmap for Ext register space + * @sdev: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_spmi_ext(dev, config) \ + __regmap_lockdep_wrapper(__regmap_init_spmi_ext, #config, \ + dev, config) + +/** + * regmap_init_mmio_clk(): Initialise register map with register clock + * + * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_mmio_clk(dev, clk_id, regs, config) \ + __regmap_lockdep_wrapper(__regmap_init_mmio_clk, #config, \ + dev, clk_id, regs, config) /** * regmap_init_mmio(): Initialise register map @@ -385,12 +533,109 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); * The return value will be an ERR_PTR() on error or a valid pointer to * a struct regmap. */ -static inline struct regmap *regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) -{ - return regmap_init_mmio_clk(dev, NULL, regs, config); -} +#define regmap_init_mmio(dev, regs, config) \ + regmap_init_mmio_clk(dev, NULL, regs, config) + +/** + * regmap_init_ac97(): Initialise AC'97 register map + * + * @ac97: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer to + * a struct regmap. + */ +#define regmap_init_ac97(ac97, config) \ + __regmap_lockdep_wrapper(__regmap_init_ac97, #config, \ + ac97, config) +bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg); + +/** + * devm_regmap_init(): Initialise managed register map + * + * @dev: Device that will be interacted with + * @bus: Bus-specific callbacks to use with device + * @bus_context: Data passed to bus-specific callbacks + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. This function should generally not be called + * directly, it should be called by bus-specific init functions. The + * map will be automatically freed by the device management code. + */ +#define devm_regmap_init(dev, bus, bus_context, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init, #config, \ + dev, bus, bus_context, config) + +/** + * devm_regmap_init_i2c(): Initialise managed register map + * + * @i2c: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_i2c(i2c, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config, \ + i2c, config) + +/** + * devm_regmap_init_spi(): Initialise register map + * + * @spi: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The map will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spi(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spi, #config, \ + dev, config) + +/** + * devm_regmap_init_spmi_base(): Create managed regmap for Base register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spmi_base(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spmi_base, #config, \ + dev, config) + +/** + * devm_regmap_init_spmi_ext(): Create managed regmap for Ext register space + * @sdev: SPMI device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_spmi_ext(dev, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_spmi_ext, #config, \ + dev, config) + +/** + * devm_regmap_init_mmio_clk(): Initialise managed register map with clock + * + * @dev: Device that will be interacted with + * @clk_id: register clock consumer ID + * @regs: Pointer to memory-mapped IO region + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_mmio_clk(dev, clk_id, regs, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_mmio_clk, #config, \ + dev, clk_id, regs, config) /** * devm_regmap_init_mmio(): Initialise managed register map @@ -403,12 +648,22 @@ static inline struct regmap *regmap_init_mmio(struct device *dev, * to a struct regmap. The regmap will be automatically freed by the * device management code. */ -static inline struct regmap *devm_regmap_init_mmio(struct device *dev, - void __iomem *regs, - const struct regmap_config *config) -{ - return devm_regmap_init_mmio_clk(dev, NULL, regs, config); -} +#define devm_regmap_init_mmio(dev, regs, config) \ + devm_regmap_init_mmio_clk(dev, NULL, regs, config) + +/** + * devm_regmap_init_ac97(): Initialise AC'97 register map + * + * @ac97: Device that will be interacted with + * @config: Configuration for register map + * + * The return value will be an ERR_PTR() on error or a valid pointer + * to a struct regmap. The regmap will be automatically freed by the + * device management code. + */ +#define devm_regmap_init_ac97(ac97, config) \ + __regmap_lockdep_wrapper(__devm_regmap_init_ac97, #config, \ + ac97, config) void regmap_exit(struct regmap *map); int regmap_reinit_cache(struct regmap *map, @@ -450,6 +705,8 @@ int regmap_get_max_register(struct regmap *map); int regmap_get_reg_stride(struct regmap *map); int regmap_async_complete(struct regmap *map); bool regmap_can_raw_write(struct regmap *map); +size_t regmap_get_raw_read_max(struct regmap *map); +size_t regmap_get_raw_write_max(struct regmap *map); int regcache_sync(struct regmap *map); int regcache_sync_region(struct regmap *map, unsigned int min, diff --git a/include/linux/reset.h b/include/linux/reset.h index da5602bd77d7..7f65f9cff951 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -74,6 +74,20 @@ static inline int device_reset_optional(struct device *dev) return -ENOSYS; } +static inline struct reset_control *__must_check reset_control_get( + struct device *dev, const char *id) +{ + WARN_ON(1); + return ERR_PTR(-EINVAL); +} + +static inline struct reset_control *__must_check devm_reset_control_get( + struct device *dev, const char *id) +{ + WARN_ON(1); + return ERR_PTR(-EINVAL); +} + static inline struct reset_control *reset_control_get_optional( struct device *dev, const char *id) { diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index a19ddacdac30..f4265039a94c 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -78,7 +78,7 @@ static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3) static inline int seccomp_mode(struct seccomp *s) { - return 0; + return SECCOMP_MODE_DISABLED; } #endif /* CONFIG_SECCOMP */ diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index d4c7271382cb..dde00defbaa5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -114,13 +114,22 @@ 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, + bool ascii); int seq_path(struct seq_file *, const struct path *, const char *); int seq_file_path(struct seq_file *, struct file *, const char *); @@ -134,10 +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/string_helpers.h b/include/linux/string_helpers.h index 71f711db4500..dabe643eb5fa 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -48,24 +48,24 @@ static inline int string_unescape_any_inplace(char *buf) #define ESCAPE_HEX 0x20 int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, - unsigned int flags, const char *esc); + unsigned int flags, const char *only); static inline int string_escape_mem_any_np(const char *src, size_t isz, - char *dst, size_t osz, const char *esc) + char *dst, size_t osz, const char *only) { - return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, esc); + return string_escape_mem(src, isz, dst, osz, ESCAPE_ANY_NP, only); } static inline int string_escape_str(const char *src, char *dst, size_t sz, - unsigned int flags, const char *esc) + unsigned int flags, const char *only) { - return string_escape_mem(src, strlen(src), dst, sz, flags, esc); + return string_escape_mem(src, strlen(src), dst, sz, flags, only); } static inline int string_escape_str_any_np(const char *src, char *dst, - size_t sz, const char *esc) + size_t sz, const char *only) { - return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, esc); + return string_escape_str(src, dst, sz, ESCAPE_ANY_NP, only); } #endif diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index d5ee6d8b7c58..7ccc961f33e9 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -132,6 +132,7 @@ struct svcxprt_rdma { struct list_head sc_accept_q; /* Conn. waiting accept */ int sc_ord; /* RDMA read limit */ int sc_max_sge; + int sc_max_sge_rd; /* max sge for read target */ int sc_sq_depth; /* Depth of SQ */ atomic_t sc_sq_count; /* Number of SQ WR on queue */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 31496d201fdc..7ba7dccaf0e7 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -351,7 +351,15 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages); extern int kswapd_run(int nid); extern void kswapd_stop(int nid); #ifdef CONFIG_MEMCG -extern int mem_cgroup_swappiness(struct mem_cgroup *mem); +static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) +{ + /* root ? */ + if (mem_cgroup_disabled() || !memcg->css.parent) + return vm_swappiness; + + return memcg->swappiness; +} + #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { @@ -398,6 +406,9 @@ extern void free_pages_and_swap_cache(struct page **, int); extern struct page *lookup_swap_cache(swp_entry_t); extern struct page *read_swap_cache_async(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); +extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t, + struct vm_area_struct *vma, unsigned long addr, + bool *new_page_allocated); extern struct page *swapin_readahead(swp_entry_t, gfp_t, struct vm_area_struct *vma, unsigned long addr); @@ -431,6 +442,7 @@ extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); +extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern int reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); @@ -522,6 +534,11 @@ static inline int page_swapcount(struct page *page) return 0; } +static inline int swp_swapcount(swp_entry_t entry) +{ + return 0; +} + #define reuse_swap_page(page) (page_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) diff --git a/include/linux/swapops.h b/include/linux/swapops.h index cedf3d3c373f..5c3a5f3e7eec 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -164,6 +164,9 @@ static inline int is_write_migration_entry(swp_entry_t entry) #endif #ifdef CONFIG_MEMORY_FAILURE + +extern atomic_long_t num_poisoned_pages __read_mostly; + /* * Support for hardware poisoned pages */ @@ -177,6 +180,31 @@ static inline int is_hwpoison_entry(swp_entry_t entry) { return swp_type(entry) == SWP_HWPOISON; } + +static inline bool test_set_page_hwpoison(struct page *page) +{ + return TestSetPageHWPoison(page); +} + +static inline void num_poisoned_pages_inc(void) +{ + atomic_long_inc(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_dec(void) +{ + atomic_long_dec(&num_poisoned_pages); +} + +static inline void num_poisoned_pages_add(long num) +{ + atomic_long_add(num, &num_poisoned_pages); +} + +static inline void num_poisoned_pages_sub(long num) +{ + atomic_long_sub(num, &num_poisoned_pages); +} #else static inline swp_entry_t make_hwpoison_entry(struct page *page) @@ -188,6 +216,15 @@ static inline int is_hwpoison_entry(swp_entry_t swp) { return 0; } + +static inline bool test_set_page_hwpoison(struct page *page) +{ + return false; +} + +static inline void num_poisoned_pages_inc(void) +{ +} #endif #if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) 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..17292fee8686 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); }; /** @@ -406,7 +402,7 @@ 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 *, @@ -457,7 +453,7 @@ 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/verify_pefile.h b/include/linux/verify_pefile.h index ac34819214f9..da2049b5161c 100644 --- a/include/linux/verify_pefile.h +++ b/include/linux/verify_pefile.h @@ -12,7 +12,11 @@ #ifndef _LINUX_VERIFY_PEFILE_H #define _LINUX_VERIFY_PEFILE_H +#include <crypto/public_key.h> + extern int verify_pefile_signature(const void *pebuf, unsigned pelen, - struct key *trusted_keyring, bool *_trusted); + struct key *trusted_keyring, + enum key_being_used_for usage, + bool *_trusted); #endif /* _LINUX_VERIFY_PEFILE_H */ diff --git a/include/linux/zbud.h b/include/linux/zbud.h index f9d41a6e361f..e183a0a65ac1 100644 --- a/include/linux/zbud.h +++ b/include/linux/zbud.h @@ -9,7 +9,7 @@ struct zbud_ops { int (*evict)(struct zbud_pool *pool, unsigned long handle); }; -struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops); +struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops); void zbud_destroy_pool(struct zbud_pool *pool); int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, unsigned long *handle); diff --git a/include/linux/zpool.h b/include/linux/zpool.h index d30eff3d84d5..42f8ec992452 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -36,8 +36,10 @@ enum zpool_mapmode { ZPOOL_MM_DEFAULT = ZPOOL_MM_RW }; +bool zpool_has_pool(char *type); + struct zpool *zpool_create_pool(char *type, char *name, - gfp_t gfp, struct zpool_ops *ops); + gfp_t gfp, const struct zpool_ops *ops); char *zpool_get_type(struct zpool *pool); @@ -81,7 +83,7 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops, + void *(*create)(char *name, gfp_t gfp, const struct zpool_ops *ops, struct zpool *zpool); void (*destroy)(void *pool); diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 1338190b5478..6398dfae53f1 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -34,6 +34,11 @@ enum zs_mapmode { */ }; +struct zs_pool_stats { + /* How many pages were migrated (freed) */ + unsigned long pages_compacted; +}; + struct zs_pool; struct zs_pool *zs_create_pool(char *name, gfp_t flags); @@ -49,4 +54,5 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle); unsigned long zs_get_total_pages(struct zs_pool *pool); unsigned long zs_compact(struct zs_pool *pool); +void zs_pool_stats(struct zs_pool *pool, struct zs_pool_stats *stats); #endif |