diff options
Diffstat (limited to 'include/linux')
89 files changed, 2093 insertions, 1908 deletions
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 080012a6f025..59494df0f55b 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -45,6 +45,7 @@ #define ARM_SMCCC_OWNER_SIP 2 #define ARM_SMCCC_OWNER_OEM 3 #define ARM_SMCCC_OWNER_STANDARD 4 +#define ARM_SMCCC_OWNER_STANDARD_HYP 5 #define ARM_SMCCC_OWNER_TRUSTED_APP 48 #define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 #define ARM_SMCCC_OWNER_TRUSTED_OS 50 @@ -80,6 +81,22 @@ #include <linux/linkage.h> #include <linux/types.h> + +enum arm_smccc_conduit { + SMCCC_CONDUIT_NONE, + SMCCC_CONDUIT_SMC, + SMCCC_CONDUIT_HVC, +}; + +/** + * arm_smccc_1_1_get_conduit() + * + * Returns the conduit to be used for SMCCCv1.1 or later. + * + * When SMCCCv1.1 is not present, returns SMCCC_CONDUIT_NONE. + */ +enum arm_smccc_conduit arm_smccc_1_1_get_conduit(void); + /** * struct arm_smccc_res - Result from SMC/HVC call * @a0-a3 result values from registers 0 to 3 @@ -302,5 +319,63 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define SMCCC_RET_NOT_SUPPORTED -1 #define SMCCC_RET_NOT_REQUIRED -2 +/* + * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED. + * Used when the SMCCC conduit is not defined. The empty asm statement + * avoids compiler warnings about unused variables. + */ +#define __fail_smccc_1_1(...) \ + do { \ + __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ + asm ("" __constraints(__count_args(__VA_ARGS__))); \ + if (___res) \ + ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ + } while (0) + +/* + * arm_smccc_1_1_invoke() - make an SMCCC v1.1 compliant call + * + * This is a variadic macro taking one to eight source arguments, and + * an optional return structure. + * + * @a0-a7: arguments passed in registers 0 to 7 + * @res: result values from registers 0 to 3 + * + * This macro will make either an HVC call or an SMC call depending on the + * current SMCCC conduit. If no valid conduit is available then -1 + * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied). + * + * The return value also provides the conduit that was used. + */ +#define arm_smccc_1_1_invoke(...) ({ \ + int method = arm_smccc_1_1_get_conduit(); \ + switch (method) { \ + case SMCCC_CONDUIT_HVC: \ + arm_smccc_1_1_hvc(__VA_ARGS__); \ + break; \ + case SMCCC_CONDUIT_SMC: \ + arm_smccc_1_1_smc(__VA_ARGS__); \ + break; \ + default: \ + __fail_smccc_1_1(__VA_ARGS__); \ + method = SMCCC_CONDUIT_NONE; \ + break; \ + } \ + method; \ + }) + +/* Paravirtualised time calls (defined by ARM DEN0057A) */ +#define ARM_SMCCC_HV_PV_TIME_FEATURES \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x20) + +#define ARM_SMCCC_HV_PV_TIME_ST \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_64, \ + ARM_SMCCC_OWNER_STANDARD_HYP, \ + 0x21) + #endif /*__ASSEMBLY__*/ #endif /*__LINUX_ARM_SMCCC_H*/ diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h index 3305ea7f9dc7..0a241c5c911d 100644 --- a/include/linux/arm_sdei.h +++ b/include/linux/arm_sdei.h @@ -5,12 +5,6 @@ #include <uapi/linux/arm_sdei.h> -enum sdei_conduit_types { - CONDUIT_INVALID = 0, - CONDUIT_SMC, - CONDUIT_HVC, -}; - #include <acpi/ghes.h> #ifdef CONFIG_ARM_SDE_INTERFACE diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index bed9e43f9426..19394c77ed99 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -15,7 +15,9 @@ */ #include <linux/cgroup.h> +#include <linux/percpu.h> #include <linux/percpu_counter.h> +#include <linux/u64_stats_sync.h> #include <linux/seq_file.h> #include <linux/radix-tree.h> #include <linux/blkdev.h> @@ -31,15 +33,12 @@ #ifdef CONFIG_BLK_CGROUP -enum blkg_rwstat_type { - BLKG_RWSTAT_READ, - BLKG_RWSTAT_WRITE, - BLKG_RWSTAT_SYNC, - BLKG_RWSTAT_ASYNC, - BLKG_RWSTAT_DISCARD, +enum blkg_iostat_type { + BLKG_IOSTAT_READ, + BLKG_IOSTAT_WRITE, + BLKG_IOSTAT_DISCARD, - BLKG_RWSTAT_NR, - BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR, + BLKG_IOSTAT_NR, }; struct blkcg_gq; @@ -61,17 +60,15 @@ struct blkcg { #endif }; -/* - * blkg_[rw]stat->aux_cnt is excluded for local stats but included for - * recursive. Used to carry stats of dead children. - */ -struct blkg_rwstat { - struct percpu_counter cpu_cnt[BLKG_RWSTAT_NR]; - atomic64_t aux_cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat { + u64 bytes[BLKG_IOSTAT_NR]; + u64 ios[BLKG_IOSTAT_NR]; }; -struct blkg_rwstat_sample { - u64 cnt[BLKG_RWSTAT_NR]; +struct blkg_iostat_set { + struct u64_stats_sync sync; + struct blkg_iostat cur; + struct blkg_iostat last; }; /* @@ -127,8 +124,8 @@ 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_iostat_set __percpu *iostat_cpu; + struct blkg_iostat_set iostat; struct blkg_policy_data *pd[BLKCG_MAX_POLS]; @@ -202,13 +199,6 @@ int blkcg_activate_policy(struct request_queue *q, void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol); -static inline u64 blkg_rwstat_read_counter(struct blkg_rwstat *rwstat, - unsigned int idx) -{ - return atomic64_read(&rwstat->aux_cnt[idx]) + - percpu_counter_sum_positive(&rwstat->cpu_cnt[idx]); -} - 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 *, @@ -216,17 +206,6 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, const struct blkcg_policy *pol, int data, bool show_total); u64 __blkg_prfill_u64(struct seq_file *sf, struct blkg_policy_data *pd, u64 v); -u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd, - const struct blkg_rwstat_sample *rwstat); -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); - -void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, - int off, struct blkg_rwstat_sample *sum); struct blkg_conf_ctx { struct gendisk *disk; @@ -578,128 +557,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -static inline int blkg_rwstat_init(struct blkg_rwstat *rwstat, gfp_t gfp) -{ - 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]); -} - -/** - * blkg_rwstat_add - add a value to a blkg_rwstat - * @rwstat: target blkg_rwstat - * @op: REQ_OP and flags - * @val: value to add - * - * Add @val to @rwstat. The counters are chosen according to @rw. The - * caller is responsible for synchronizing calls to this function. - */ -static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - unsigned int op, uint64_t val) -{ - struct percpu_counter *cnt; - - if (op_is_discard(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; - else if (op_is_write(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; - - percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); - - if (op_is_sync(op)) - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; - else - cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; - - percpu_counter_add_batch(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 in the aux counts. - */ -static inline void blkg_rwstat_read(struct blkg_rwstat *rwstat, - struct blkg_rwstat_sample *result) -{ - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - result->cnt[i] = - percpu_counter_sum_positive(&rwstat->cpu_cnt[i]); -} - -/** - * blkg_rwstat_total - read the total count of a blkg_rwstat - * @rwstat: blkg_rwstat to read - * - * Return the total count of @rwstat regardless of the IO direction. This - * function can be called without synchronization and takes care of u64 - * atomicity. - */ -static inline uint64_t blkg_rwstat_total(struct blkg_rwstat *rwstat) -{ - struct blkg_rwstat_sample tmp = { }; - - blkg_rwstat_read(rwstat, &tmp); - return tmp.cnt[BLKG_RWSTAT_READ] + tmp.cnt[BLKG_RWSTAT_WRITE]; -} - -/** - * blkg_rwstat_reset - reset a blkg_rwstat - * @rwstat: blkg_rwstat to reset - */ -static inline void blkg_rwstat_reset(struct blkg_rwstat *rwstat) -{ - 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_add_aux - add a blkg_rwstat into another's aux count - * @to: the destination blkg_rwstat - * @from: the source - * - * Add @from's count including the aux one to @to's aux count. - */ -static inline void blkg_rwstat_add_aux(struct blkg_rwstat *to, - struct blkg_rwstat *from) -{ - u64 sum[BLKG_RWSTAT_NR]; - int i; - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum[i] = percpu_counter_sum_positive(&from->cpu_cnt[i]); - - for (i = 0; i < BLKG_RWSTAT_NR; i++) - atomic64_add(sum[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); @@ -745,15 +602,33 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + struct blkg_iostat_set *bis; + int rwd, cpu; + + if (op_is_discard(bio->bi_opf)) + rwd = BLKG_IOSTAT_DISCARD; + else if (op_is_write(bio->bi_opf)) + rwd = BLKG_IOSTAT_WRITE; + else + rwd = BLKG_IOSTAT_READ; + + cpu = get_cpu(); + bis = per_cpu_ptr(blkg->iostat_cpu, cpu); + u64_stats_update_begin(&bis->sync); + /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the * size of the bio. */ if (!bio_flagged(bio, BIO_QUEUE_ENTERED)) - blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf, - bio->bi_iter.bi_size); - blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); + bis->cur.bytes[rwd] += bio->bi_iter.bi_size; + bis->cur.ios[rwd]++; + + u64_stats_update_end(&bis->sync); + if (cgroup_subsys_on_dfl(io_cgrp_subsys)) + cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); + put_cpu(); } blkcg_bio_issue_init(bio); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 0bf056de5cc3..11cfd6470b1a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -10,103 +10,239 @@ struct blk_mq_tags; struct blk_flush_queue; /** - * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware block device + * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware + * block device */ struct blk_mq_hw_ctx { struct { + /** @lock: Protects the dispatch list. */ spinlock_t lock; + /** + * @dispatch: Used for requests that are ready to be + * dispatched to the hardware but for some reason (e.g. lack of + * resources) could not be sent to the hardware. As soon as the + * driver can send new requests, requests at this list will + * be sent first for a fairer dispatch. + */ struct list_head dispatch; - unsigned long state; /* BLK_MQ_S_* flags */ + /** + * @state: BLK_MQ_S_* flags. Defines the state of the hw + * queue (active, scheduled to restart, stopped). + */ + unsigned long state; } ____cacheline_aligned_in_smp; + /** + * @run_work: Used for scheduling a hardware queue run at a later time. + */ struct delayed_work run_work; + /** @cpumask: Map of available CPUs where this hctx can run. */ cpumask_var_t cpumask; + /** + * @next_cpu: Used by blk_mq_hctx_next_cpu() for round-robin CPU + * selection from @cpumask. + */ int next_cpu; + /** + * @next_cpu_batch: Counter of how many works left in the batch before + * changing to the next CPU. + */ int next_cpu_batch; - unsigned long flags; /* BLK_MQ_F_* flags */ + /** @flags: BLK_MQ_F_* flags. Defines the behaviour of the queue. */ + unsigned long flags; + /** + * @sched_data: Pointer owned by the IO scheduler attached to a request + * queue. It's up to the IO scheduler how to use this pointer. + */ void *sched_data; + /** + * @queue: Pointer to the request queue that owns this hardware context. + */ struct request_queue *queue; + /** @fq: Queue of requests that need to perform a flush operation. */ struct blk_flush_queue *fq; + /** + * @driver_data: Pointer to data owned by the block driver that created + * this hctx + */ void *driver_data; + /** + * @ctx_map: Bitmap for each software queue. If bit is on, there is a + * pending request in that software queue. + */ struct sbitmap ctx_map; + /** + * @dispatch_from: Software queue to be used when no scheduler was + * selected. + */ struct blk_mq_ctx *dispatch_from; + /** + * @dispatch_busy: Number used by blk_mq_update_dispatch_busy() to + * decide if the hw_queue is busy using Exponential Weighted Moving + * Average algorithm. + */ unsigned int dispatch_busy; + /** @type: HCTX_TYPE_* flags. Type of hardware queue. */ unsigned short type; + /** @nr_ctx: Number of software queues. */ unsigned short nr_ctx; + /** @ctxs: Array of software queues. */ struct blk_mq_ctx **ctxs; + /** @dispatch_wait_lock: Lock for dispatch_wait queue. */ spinlock_t dispatch_wait_lock; + /** + * @dispatch_wait: Waitqueue to put requests when there is no tag + * available at the moment, to wait for another try in the future. + */ wait_queue_entry_t dispatch_wait; + + /** + * @wait_index: Index of next available dispatch_wait queue to insert + * requests. + */ atomic_t wait_index; + /** + * @tags: Tags owned by the block driver. A tag at this set is only + * assigned when a request is dispatched from a hardware queue. + */ struct blk_mq_tags *tags; + /** + * @sched_tags: Tags owned by I/O scheduler. If there is an I/O + * scheduler associated with a request queue, a tag is assigned when + * that request is allocated. Else, this member is not used. + */ struct blk_mq_tags *sched_tags; + /** @queued: Number of queued requests. */ unsigned long queued; + /** @run: Number of dispatched requests. */ unsigned long run; #define BLK_MQ_MAX_DISPATCH_ORDER 7 + /** @dispatched: Number of dispatch requests by queue. */ unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; + /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; + /** @queue_num: Index of this hardware queue. */ unsigned int queue_num; + /** + * @nr_active: Number of active requests. Only used when a tag set is + * shared across request queues. + */ atomic_t nr_active; + /** @cpuhp_dead: List to store request if some CPU die. */ struct hlist_node cpuhp_dead; + /** @kobj: Kernel object for sysfs. */ struct kobject kobj; + /** @poll_considered: Count times blk_poll() was called. */ unsigned long poll_considered; + /** @poll_invoked: Count how many requests blk_poll() polled. */ unsigned long poll_invoked; + /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; #ifdef CONFIG_BLK_DEBUG_FS + /** + * @debugfs_dir: debugfs directory for this hardware queue. Named + * as cpu<cpu_number>. + */ struct dentry *debugfs_dir; + /** @sched_debugfs_dir: debugfs directory for the scheduler. */ struct dentry *sched_debugfs_dir; #endif + /** @hctx_list: List of all hardware queues. */ struct list_head hctx_list; - /* Must be the last member - see also blk_mq_hw_ctx_size(). */ + /** + * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is + * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also + * blk_mq_hw_ctx_size(). + */ struct srcu_struct srcu[0]; }; +/** + * struct blk_mq_queue_map - Map software queues to hardware queues + * @mq_map: CPU ID to hardware queue index map. This is an array + * with nr_cpu_ids elements. Each element has a value in the range + * [@queue_offset, @queue_offset + @nr_queues). + * @nr_queues: Number of hardware queues to map CPU IDs onto. + * @queue_offset: First hardware queue to map onto. Used by the PCIe NVMe + * driver to map each hardware queue type (enum hctx_type) onto a distinct + * set of hardware queues. + */ struct blk_mq_queue_map { unsigned int *mq_map; unsigned int nr_queues; unsigned int queue_offset; }; +/** + * enum hctx_type - Type of hardware queue + * @HCTX_TYPE_DEFAULT: All I/O not otherwise accounted for. + * @HCTX_TYPE_READ: Just for READ I/O. + * @HCTX_TYPE_POLL: Polled I/O of any kind. + * @HCTX_MAX_TYPES: Number of types of hctx. + */ enum hctx_type { - HCTX_TYPE_DEFAULT, /* all I/O not otherwise accounted for */ - HCTX_TYPE_READ, /* just for READ I/O */ - HCTX_TYPE_POLL, /* polled I/O of any kind */ + HCTX_TYPE_DEFAULT, + HCTX_TYPE_READ, + HCTX_TYPE_POLL, HCTX_MAX_TYPES, }; +/** + * struct blk_mq_tag_set - tag set that can be shared between request queues + * @map: One or more ctx -> hctx mappings. One map exists for each + * hardware queue type (enum hctx_type) that the driver wishes + * to support. There are no restrictions on maps being of the + * same size, and it's perfectly legal to share maps between + * types. + * @nr_maps: Number of elements in the @map array. A number in the range + * [1, HCTX_MAX_TYPES]. + * @ops: Pointers to functions that implement block driver behavior. + * @nr_hw_queues: Number of hardware queues supported by the block driver that + * owns this data structure. + * @queue_depth: Number of tags per hardware queue, reserved tags included. + * @reserved_tags: Number of tags to set aside for BLK_MQ_REQ_RESERVED tag + * allocations. + * @cmd_size: Number of additional bytes to allocate per request. The block + * driver owns these additional bytes. + * @numa_node: NUMA node the storage adapter has been connected to. + * @timeout: Request processing timeout in jiffies. + * @flags: Zero or more BLK_MQ_F_* flags. + * @driver_data: Pointer to data owned by the block driver that created this + * tag set. + * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues + * elements. + * @tag_list_lock: Serializes tag_list accesses. + * @tag_list: List of the request queues that use this tag set. See also + * request_queue.tag_set_list. + */ struct blk_mq_tag_set { - /* - * map[] holds ctx -> hctx mappings, one map exists for each type - * that the driver wishes to support. There are no restrictions - * on maps being of the same size, and it's perfectly legal to - * share maps between types. - */ struct blk_mq_queue_map map[HCTX_MAX_TYPES]; - unsigned int nr_maps; /* nr entries in map[] */ + unsigned int nr_maps; const struct blk_mq_ops *ops; - unsigned int nr_hw_queues; /* nr hw queues across maps */ - unsigned int queue_depth; /* max hw supported */ + unsigned int nr_hw_queues; + unsigned int queue_depth; unsigned int reserved_tags; - unsigned int cmd_size; /* per-request extra data */ + unsigned int cmd_size; int numa_node; unsigned int timeout; - unsigned int flags; /* BLK_MQ_F_* */ + unsigned int flags; void *driver_data; struct blk_mq_tags **tags; @@ -115,6 +251,12 @@ struct blk_mq_tag_set { struct list_head tag_list; }; +/** + * struct blk_mq_queue_data - Data about a request inserted in a queue + * + * @rq: Request pointer. + * @last: If it is the last request in the queue. + */ struct blk_mq_queue_data { struct request *rq; bool last; @@ -142,81 +284,101 @@ typedef bool (busy_fn)(struct request_queue *); typedef void (complete_fn)(struct request *); typedef void (cleanup_rq_fn)(struct request *); - +/** + * struct blk_mq_ops - Callback functions that implements block driver + * behaviour. + */ struct blk_mq_ops { - /* - * Queue request + /** + * @queue_rq: Queue a new request from block IO. */ queue_rq_fn *queue_rq; - /* - * If a driver uses bd->last to judge when to submit requests to - * hardware, it must define this function. In case of errors that - * make us stop issuing further requests, this hook serves the + /** + * @commit_rqs: If a driver uses bd->last to judge when to submit + * requests to hardware, it must define this function. In case of errors + * that make us stop issuing further requests, this hook serves the * purpose of kicking the hardware (which the last request otherwise * would have done). */ commit_rqs_fn *commit_rqs; - /* - * Reserve budget before queue request, once .queue_rq is + /** + * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ get_budget_fn *get_budget; + /** + * @put_budget: Release the reserved budget. + */ put_budget_fn *put_budget; - /* - * Called on request timeout + /** + * @timeout: Called on request timeout. */ timeout_fn *timeout; - /* - * Called to poll for completion of a specific tag. + /** + * @poll: Called to poll for completion of a specific tag. */ poll_fn *poll; + /** + * @complete: Mark the request as complete. + */ complete_fn *complete; - /* - * Called when the block layer side of a hardware queue has been - * set up, allowing the driver to allocate/init matching structures. - * Ditto for exit/teardown. + /** + * @init_hctx: Called when the block layer side of a hardware queue has + * been set up, allowing the driver to allocate/init matching + * structures. */ init_hctx_fn *init_hctx; + /** + * @exit_hctx: Ditto for exit/teardown. + */ exit_hctx_fn *exit_hctx; - /* - * Called for every command allocated by the block layer to allow - * the driver to set up driver specific data. + /** + * @init_request: Called for every command allocated by the block layer + * to allow the driver to set up driver specific data. * * Tag greater than or equal to queue_depth is for setting up * flush request. - * - * Ditto for exit/teardown. */ init_request_fn *init_request; + /** + * @exit_request: Ditto for exit/teardown. + */ exit_request_fn *exit_request; - /* Called from inside blk_get_request() */ + + /** + * @initialize_rq_fn: Called from inside blk_get_request(). + */ void (*initialize_rq_fn)(struct request *rq); - /* - * Called before freeing one request which isn't completed yet, - * and usually for freeing the driver private data + /** + * @cleanup_rq: Called before freeing one request which isn't completed + * yet, and usually for freeing the driver private data. */ cleanup_rq_fn *cleanup_rq; - /* - * If set, returns whether or not this queue currently is busy + /** + * @busy: If set, returns whether or not this queue currently is busy. */ busy_fn *busy; + /** + * @map_queues: This allows drivers specify their own queue mapping by + * overriding the setup-time function that builds the mq_map. + */ map_queues_fn *map_queues; #ifdef CONFIG_BLK_DEBUG_FS - /* - * Used by the debugfs implementation to show driver-specific + /** + * @show_rq: Used by the debugfs implementation to show driver-specific * information about a request. */ void (*show_rq)(struct seq_file *m, struct request *rq); @@ -262,7 +424,6 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_free_request(struct request *rq); -bool blk_mq_can_queue(struct blk_mq_hw_ctx *); bool blk_mq_queue_inflight(struct request_queue *q); @@ -301,9 +462,25 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag) return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; } +/** + * blk_mq_rq_state() - read the current MQ_RQ_* state of a request + * @rq: target request. + */ +static inline enum mq_rq_state blk_mq_rq_state(struct request *rq) +{ + return READ_ONCE(rq->state); +} + +static inline int blk_mq_request_started(struct request *rq) +{ + return blk_mq_rq_state(rq) != MQ_RQ_IDLE; +} + +static inline int blk_mq_request_completed(struct request *rq) +{ + return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE; +} -int blk_mq_request_started(struct request *rq); -int blk_mq_request_completed(struct request *rq); void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); @@ -324,7 +501,7 @@ void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); -bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); +void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_run_hw_queues(struct request_queue *q, bool async); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); @@ -343,14 +520,29 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); -/* +/** + * blk_mq_rq_from_pdu - cast a PDU to a request + * @pdu: the PDU (Protocol Data Unit) to be casted + * + * Return: request + * * Driver command data is immediately after the request. So subtract request - * size to get back to the original request, add request size to get the PDU. + * size to get back to the original request. */ static inline struct request *blk_mq_rq_from_pdu(void *pdu) { return pdu - sizeof(struct request); } + +/** + * blk_mq_rq_to_pdu - cast a request to a PDU + * @rq: the request to be casted + * + * Return: pointer to the PDU + * + * Driver command data is immediately after the request. So add request to get + * the PDU. + */ static inline void *blk_mq_rq_to_pdu(struct request *rq) { return rq + 1; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d688b96d1d63..70254ae11769 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -153,10 +153,10 @@ struct bio { unsigned short bi_write_hint; blk_status_t bi_status; u8 bi_partno; + atomic_t __bi_remaining; struct bvec_iter bi_iter; - atomic_t __bi_remaining; bio_end_io_t *bi_end_io; void *bi_private; @@ -290,6 +290,12 @@ enum req_opf { REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, + /* Open a zone */ + REQ_OP_ZONE_OPEN = 10, + /* Close a zone */ + REQ_OP_ZONE_CLOSE = 11, + /* Transition a zone to full */ + REQ_OP_ZONE_FINISH = 12, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, @@ -371,6 +377,7 @@ enum stat_group { STAT_READ, STAT_WRITE, STAT_DISCARD, + STAT_FLUSH, NR_STAT_GROUPS }; @@ -417,6 +424,25 @@ static inline bool op_is_discard(unsigned int op) return (op & REQ_OP_MASK) == REQ_OP_DISCARD; } +/* + * Check if a bio or request operation is a zone management operation, with + * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case + * due to its different handling in the block layer and device response in + * case of command failure. + */ +static inline bool op_is_zone_mgmt(enum req_opf op) +{ + switch (op & REQ_OP_MASK) { + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: + return true; + default: + return false; + } +} + static inline int op_stat_group(unsigned int op) { if (op_is_discard(op)) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3ea78b0c91c..397bb9bc230b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -349,25 +349,25 @@ struct queue_limits { enum blk_zoned_model zoned; }; +typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, + void *data); + #ifdef CONFIG_BLK_DEV_ZONED -/* - * Maximum number of zones to report with a single report zones command. - */ -#define BLK_ZONED_REPORT_MAX_ZONES 8192U +#define BLK_ALL_ZONES ((unsigned int)-1) +int blkdev_report_zones(struct block_device *bdev, sector_t sector, + unsigned int nr_zones, report_zones_cb cb, void *data); extern unsigned int blkdev_nr_zones(struct block_device *bdev); -extern int blkdev_report_zones(struct block_device *bdev, - sector_t sector, struct blk_zone *zones, - unsigned int *nr_zones); -extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, - sector_t nr_sectors, gfp_t gfp_mask); +extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, + sector_t sectors, sector_t nr_sectors, + gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); -extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); +extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ @@ -388,9 +388,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev, return -ENOTTY; } -static inline int blkdev_reset_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + fmode_t mode, unsigned int cmd, + unsigned long arg) { return -ENOTTY; } @@ -411,7 +411,6 @@ struct request_queue { /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; - unsigned int nr_queues; unsigned int queue_depth; @@ -1709,7 +1708,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); int (*report_zones)(struct gendisk *, sector_t sector, - struct blk_zone *zones, unsigned int *nr_zones); + unsigned int nr_zones, report_zones_cb cb, void *data); struct module *owner; const struct pr_ops *pr_ops; }; diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3bf3835d0e86..35903f148be5 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -12,17 +12,23 @@ #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> +#include <linux/mm_types.h> #include <linux/wait.h> #include <linux/u64_stats_sync.h> +#include <linux/refcount.h> +#include <linux/mutex.h> struct bpf_verifier_env; +struct bpf_verifier_log; struct perf_event; struct bpf_prog; +struct bpf_prog_aux; struct bpf_map; struct sock; struct seq_file; struct btf; struct btf_type; +struct exception_table_entry; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -59,11 +65,18 @@ struct bpf_map_ops { const struct btf_type *key_type, const struct btf_type *value_type); + /* Prog poke tracking helpers. */ + int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); + void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, + struct bpf_prog *new); + /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); + int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); }; struct bpf_map_memory { @@ -92,17 +105,19 @@ struct bpf_map { u32 btf_value_type_id; struct btf *btf; struct bpf_map_memory memory; + char name[BPF_OBJ_NAME_LEN]; bool unpriv_array; - bool frozen; /* write-once */ - /* 48 bytes hole */ + bool frozen; /* write-once; write-protected by freeze_mutex */ + /* 22 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ - atomic_t refcnt ____cacheline_aligned; - atomic_t usercnt; + atomic64_t refcnt ____cacheline_aligned; + atomic64_t usercnt; struct work_struct work; - char name[BPF_OBJ_NAME_LEN]; + struct mutex freeze_mutex; + u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -211,6 +226,7 @@ enum bpf_arg_type { ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ + ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ }; /* type of values returned from helper functions */ @@ -233,11 +249,17 @@ struct bpf_func_proto { bool gpl_only; bool pkt_access; enum bpf_return_type ret_type; - enum bpf_arg_type arg1_type; - enum bpf_arg_type arg2_type; - enum bpf_arg_type arg3_type; - enum bpf_arg_type arg4_type; - enum bpf_arg_type arg5_type; + union { + struct { + enum bpf_arg_type arg1_type; + enum bpf_arg_type arg2_type; + enum bpf_arg_type arg3_type; + enum bpf_arg_type arg4_type; + enum bpf_arg_type arg5_type; + }; + enum bpf_arg_type arg_type[5]; + }; + int *btf_id; /* BTF ids of arguments */ }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is @@ -281,6 +303,7 @@ enum bpf_reg_type { PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ + PTR_TO_BTF_ID, /* reg points to kernel struct */ }; /* The information passed from prog-specific *_is_valid_access @@ -288,7 +311,11 @@ enum bpf_reg_type { */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; - int ctx_field_size; + union { + int ctx_field_size; + u32 btf_id; + }; + struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void @@ -359,14 +386,135 @@ enum bpf_cgroup_storage_type { #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX +/* The longest tracepoint has 12 args. + * See include/trace/bpf_probe.h + */ +#define MAX_BPF_FUNC_ARGS 12 + struct bpf_prog_stats { u64 cnt; u64 nsecs; struct u64_stats_sync syncp; +} __aligned(2 * sizeof(u64)); + +struct btf_func_model { + u8 ret_size; + u8 nr_args; + u8 arg_size[MAX_BPF_FUNC_ARGS]; +}; + +/* Restore arguments before returning from trampoline to let original function + * continue executing. This flag is used for fentry progs when there are no + * fexit progs. + */ +#define BPF_TRAMP_F_RESTORE_REGS BIT(0) +/* Call original function after fentry progs, but before fexit progs. + * Makes sense for fentry/fexit, normal calls and indirect calls. + */ +#define BPF_TRAMP_F_CALL_ORIG BIT(1) +/* Skip current frame and return to parent. Makes sense for fentry/fexit + * programs only. Should not be used with normal calls and indirect calls. + */ +#define BPF_TRAMP_F_SKIP_FRAME BIT(2) + +/* Different use cases for BPF trampoline: + * 1. replace nop at the function entry (kprobe equivalent) + * flags = BPF_TRAMP_F_RESTORE_REGS + * fentry = a set of programs to run before returning from trampoline + * + * 2. replace nop at the function entry (kprobe + kretprobe equivalent) + * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME + * orig_call = fentry_ip + MCOUNT_INSN_SIZE + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + * + * 3. replace direct call instruction anywhere in the function body + * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) + * With flags = 0 + * fentry = a set of programs to run before returning from trampoline + * With flags = BPF_TRAMP_F_CALL_ORIG + * orig_call = original callback addr or direct function addr + * fentry = a set of program to run before calling original function + * fexit = a set of program to run after original function + */ +int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags, + struct bpf_prog **fentry_progs, int fentry_cnt, + struct bpf_prog **fexit_progs, int fexit_cnt, + void *orig_call); +/* these two functions are called from generated trampoline */ +u64 notrace __bpf_prog_enter(void); +void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); + +enum bpf_tramp_prog_type { + BPF_TRAMP_FENTRY, + BPF_TRAMP_FEXIT, + BPF_TRAMP_MAX +}; + +struct bpf_trampoline { + /* hlist for trampoline_table */ + struct hlist_node hlist; + /* serializes access to fields of this trampoline */ + struct mutex mutex; + refcount_t refcnt; + u64 key; + struct { + struct btf_func_model model; + void *addr; + } func; + /* list of BPF programs using this trampoline */ + struct hlist_head progs_hlist[BPF_TRAMP_MAX]; + /* Number of attached programs. A counter per kind. */ + int progs_cnt[BPF_TRAMP_MAX]; + /* Executable image of trampoline */ + void *image; + u64 selector; +}; +#ifdef CONFIG_BPF_JIT +struct bpf_trampoline *bpf_trampoline_lookup(u64 key); +int bpf_trampoline_link_prog(struct bpf_prog *prog); +int bpf_trampoline_unlink_prog(struct bpf_prog *prog); +void bpf_trampoline_put(struct bpf_trampoline *tr); +#else +static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key) +{ + return NULL; +} +static inline int bpf_trampoline_link_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog) +{ + return -ENOTSUPP; +} +static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} +#endif + +struct bpf_func_info_aux { + bool unreliable; +}; + +enum bpf_jit_poke_reason { + BPF_POKE_REASON_TAIL_CALL, +}; + +/* Descriptor of pokes pointing /into/ the JITed image. */ +struct bpf_jit_poke_descriptor { + void *ip; + union { + struct { + struct bpf_map *map; + u32 key; + } tail_call; + }; + bool ip_stable; + u8 adj_off; + u16 reason; }; struct bpf_prog_aux { - atomic_t refcnt; + atomic64_t refcnt; u32 used_map_cnt; u32 max_ctx_offset; u32 max_pkt_offset; @@ -375,10 +523,23 @@ struct bpf_prog_aux { u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ + u32 attach_btf_id; /* in-kernel BTF type id to attach to */ + struct bpf_prog *linked_prog; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool offload_requested; + bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ + bool func_proto_unreliable; + enum bpf_tramp_prog_type trampoline_prog_type; + struct bpf_trampoline *trampoline; + struct hlist_node tramp_hlist; + /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ + const struct btf_type *attach_func_proto; + /* function name for valid attach_btf_id */ + const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ + struct bpf_jit_poke_descriptor *poke_tab; + u32 size_poke_tab; struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; @@ -394,6 +555,7 @@ struct bpf_prog_aux { struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; + struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. @@ -416,6 +578,8 @@ struct bpf_prog_aux { * main prog always has linfo_idx == 0 */ u32 linfo_idx; + u32 num_exentries; + struct exception_table_entry *extable; struct bpf_prog_stats __percpu *stats; union { struct work_struct work; @@ -423,17 +587,26 @@ struct bpf_prog_aux { }; }; +struct bpf_array_aux { + /* 'Ownership' of prog array is claimed by the first program that + * is going to use this map or by the first program which FD is + * stored in the map to make sure that all callers and callees have + * the same prog type and JITed flag. + */ + enum bpf_prog_type type; + bool jited; + /* Programs with direct jumps into programs part of this array. */ + struct list_head poke_progs; + struct bpf_map *map; + struct mutex poke_mutex; + struct work_struct work; +}; + struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; - /* 'ownership' of prog_array is claimed by the first program that - * is going to use this map or by the first program which FD is stored - * in the map to make sure that all callers and callees have the same - * prog_type and JITed flag - */ - enum bpf_prog_type owner_prog_type; - bool owner_jited; + struct bpf_array_aux *aux; union { char value[0] __aligned(8); void *ptrs[0] __aligned(8); @@ -482,6 +655,7 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); +const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -620,7 +794,7 @@ DECLARE_PER_CPU(int, bpf_prog_active); extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; -#define BPF_PROG_TYPE(_id, _name) \ +#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ @@ -636,9 +810,9 @@ extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); -struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i); +void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); -struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog); +void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); int __bpf_prog_charge(struct user_struct *user, u32 pages); @@ -649,9 +823,9 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); -struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); -struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map, - bool uref); +void bpf_map_inc(struct bpf_map *map); +void bpf_map_inc_with_uref(struct bpf_map *map); +struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); @@ -661,6 +835,7 @@ void bpf_map_charge_finish(struct bpf_map_memory *mem); void bpf_map_charge_move(struct bpf_map_memory *dst, struct bpf_map_memory *src); void *bpf_map_area_alloc(u64 size, int numa_node); +void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); @@ -747,6 +922,24 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); +bool btf_ctx_access(int off, int size, enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info); +int btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, int size, + enum bpf_access_type atype, + u32 *next_btf_id); +int btf_resolve_helper_id(struct bpf_verifier_log *log, + const struct bpf_func_proto *fn, int); + +int btf_distill_func_proto(struct bpf_verifier_log *log, + struct btf *btf, + const struct btf_type *func_proto, + const char *func_name, + struct btf_func_model *m); + +int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -760,10 +953,8 @@ static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, return ERR_PTR(-EOPNOTSUPP); } -static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, - int i) +static inline void bpf_prog_add(struct bpf_prog *prog, int i) { - return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) @@ -774,9 +965,8 @@ static inline void bpf_prog_put(struct bpf_prog *prog) { } -static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog) +static inline void bpf_prog_inc(struct bpf_prog *prog) { - return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *__must_check @@ -877,6 +1067,10 @@ static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, { return -ENOTSUPP; } + +static inline void bpf_map_put(struct bpf_map *map) +{ +} #endif /* CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@ -972,31 +1166,6 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, } #endif -#if defined(CONFIG_XDP_SOCKETS) -struct xdp_sock; -struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); -int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs); -void __xsk_map_flush(struct bpf_map *map); -#else -struct xdp_sock; -static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, - u32 key) -{ - return NULL; -} - -static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, - struct xdp_sock *xs) -{ - return -EOPNOTSUPP; -} - -static inline void __xsk_map_flush(struct bpf_map *map) -{ -} -#endif - #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, @@ -1095,6 +1264,15 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, #endif #ifdef CONFIG_INET +struct sk_reuseport_kern { + struct sk_buff *skb; + struct sock *sk; + struct sock *selected_sk; + void *data_end; + u32 hash; + u32 reuseport_id; + bool bind_inany; +}; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); @@ -1145,4 +1323,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, } #endif /* CONFIG_INET */ +enum bpf_text_poke_type { + BPF_MOD_CALL, + BPF_MOD_JUMP, +}; + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, + void *addr1, void *addr2); + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 36a9c2325176..93740b3614d7 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -2,41 +2,68 @@ /* internal file - do not include directly */ #ifdef CONFIG_NET -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) -BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp, + struct xdp_md, struct xdp_buff) #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock, + struct bpf_sock, struct sock) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr, + struct bpf_sock_addr, struct bpf_sock_addr_kern) #endif -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) -BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local) -BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb) -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg) -BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops, + struct bpf_sock_ops, struct bpf_sock_ops_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb, + struct __sk_buff, struct sk_buff) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg, + struct sk_msg_md, struct sk_msg) +BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector, + struct __sk_buff, struct bpf_flow_dissector) #endif #ifdef CONFIG_BPF_EVENTS -BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe) -BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint) -BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) +BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe, + bpf_user_pt_regs_t, struct pt_regs) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint, + __u64, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event, + struct bpf_perf_event_data, struct bpf_perf_event_data_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable, + struct bpf_raw_tracepoint_args, u64) +BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing, + void *, void *) #endif #ifdef CONFIG_CGROUP_BPF -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) -BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev, + struct bpf_cgroup_dev_ctx, struct bpf_cgroup_dev_ctx) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl, + struct bpf_sysctl, struct bpf_sysctl_kern) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt, + struct bpf_sockopt, struct bpf_sockopt_kern) #endif #ifdef CONFIG_BPF_LIRC_MODE2 -BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) +BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2, + __u32, u32) #endif #ifdef CONFIG_INET -BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport) +BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport, + struct sk_reuseport_md, struct sk_reuseport_kern) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 26a6d58ca78c..26e40de9ef55 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -52,6 +52,8 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; + u32 btf_id; /* for PTR_TO_BTF_ID */ + /* Max size from any of the above. */ unsigned long raw; }; @@ -291,7 +293,7 @@ struct bpf_verifier_state_list { struct bpf_insn_aux_data { union { enum bpf_reg_type ptr_type; /* pointer type for load/store insns */ - unsigned long map_state; /* pointer/poison value for maps */ + unsigned long map_ptr_state; /* pointer/poison value for maps */ s32 call_imm; /* saved imm field of call insn */ u32 alu_limit; /* limit for add/sub register with pointer */ struct { @@ -299,6 +301,7 @@ struct bpf_insn_aux_data { u32 map_off; /* offset from value base address */ }; }; + u64 map_key_state; /* constant (32 bit) key tracking for maps */ int ctx_field_size; /* the ctx field size for load insn, maybe 0 */ int sanitize_stack_off; /* stack slot to be cleared */ bool seen; /* this insn was processed by the verifier */ @@ -330,15 +333,18 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_STATS 4 #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) +#define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { - return log->level && log->ubuf && !bpf_verifier_log_full(log); + return (log->level && log->ubuf && !bpf_verifier_log_full(log)) || + log->level == BPF_LOG_KERNEL; } #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { + /* 'start' has to be the first field otherwise find_subprog() won't work */ u32 start; /* insn idx of function entry point */ u32 linfo_idx; /* The idx to the main_prog->aux->linfo */ u16 stack_depth; /* max. stack depth used by this function */ @@ -397,6 +403,8 @@ __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt, va_list args); __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env, const char *fmt, ...); +__printf(2, 3) void bpf_log(struct bpf_verifier_log *log, + const char *fmt, ...); static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env) { diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6db2d9a6e503..b475e7f20d28 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -200,9 +200,15 @@ #define BCM5482_SHD_SSD 0x14 /* 10100: Secondary SerDes control */ #define BCM5482_SHD_SSD_LEDM 0x0008 /* SSD LED Mode enable */ #define BCM5482_SHD_SSD_EN 0x0001 /* SSD enable */ -#define BCM5482_SHD_MODE 0x1f /* 11111: Mode Control Register */ -#define BCM5482_SHD_MODE_1000BX 0x0001 /* Enable 1000BASE-X registers */ +/* 10011: SerDes 100-FX Control Register */ +#define BCM54616S_SHD_100FX_CTRL 0x13 +#define BCM54616S_100FX_MODE BIT(0) /* 100-FX SerDes Enable */ + +/* 11111: Mode Control Register */ +#define BCM54XX_SHD_MODE 0x1f +#define BCM54XX_SHD_INTF_SEL_MASK GENMASK(2, 1) /* INTERF_SEL[1:0] */ +#define BCM54XX_SHD_MODE_1000BX BIT(0) /* Enable 1000-X registers */ /* * EXPANSION SHADOW ACCESS REGISTERS. (PHY REG 0x15, 0x16, and 0x17) diff --git a/include/linux/btf.h b/include/linux/btf.h index 64cdf2a23d42..79d4abc2556a 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include <linux/types.h> +#include <uapi/linux/btf.h> struct btf; struct btf_member; @@ -53,9 +54,41 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); bool btf_type_is_void(const struct btf_type *t); +static inline bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static inline bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +static inline bool btf_type_is_enum(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; +} + +static inline bool btf_type_is_typedef(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF; +} + +static inline bool btf_type_is_func(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC; +} + +static inline bool btf_type_is_func_proto(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO; +} + #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); +struct btf *btf_parse_vmlinux(void); +struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog); #else static inline const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) diff --git a/include/linux/can/platform/mcp251x.h b/include/linux/can/platform/mcp251x.h deleted file mode 100644 index 9e5ac27fb6c1..000000000000 --- a/include/linux/can/platform/mcp251x.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CAN_PLATFORM_MCP251X_H -#define _CAN_PLATFORM_MCP251X_H - -/* - * - * CAN bus driver for Microchip 251x CAN Controller with SPI Interface - * - */ - -#include <linux/spi/spi.h> - -/* - * struct mcp251x_platform_data - MCP251X SPI CAN controller platform data - * @oscillator_frequency: - oscillator frequency in Hz - */ - -struct mcp251x_platform_data { - unsigned long oscillator_frequency; -}; - -#endif /* !_CAN_PLATFORM_MCP251X_H */ diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h index 01219f2902bf..1b78a0cfb615 100644 --- a/include/linux/can/rx-offload.h +++ b/include/linux/can/rx-offload.h @@ -15,9 +15,9 @@ struct can_rx_offload { struct net_device *dev; - unsigned int (*mailbox_read)(struct can_rx_offload *offload, - struct can_frame *cf, - u32 *timestamp, unsigned int mb); + struct sk_buff *(*mailbox_read)(struct can_rx_offload *offload, + unsigned int mb, u32 *timestamp, + bool drop); struct sk_buff_head skb_queue; u32 skb_queue_len_max; @@ -44,7 +44,6 @@ unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload, unsigned int idx, u32 timestamp); int can_rx_offload_queue_tail(struct can_rx_offload *offload, struct sk_buff *skb); -void can_rx_offload_reset(struct can_rx_offload *offload); void can_rx_offload_del(struct can_rx_offload *offload); void can_rx_offload_enable(struct can_rx_offload *offload); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 430e219e3aba..63097cb243cb 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -355,16 +355,6 @@ struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - - /* * The depth this cgroup is at. The root is at depth zero and each * step down the hierarchy increments the level. This along with * ancestor_ids[] can determine whether a given cgroup is a @@ -458,7 +448,7 @@ struct cgroup { struct list_head rstat_css_list; /* cgroup basic resource statistics */ - struct cgroup_base_stat pending_bstat; /* pending from children */ + struct cgroup_base_stat last_bstat; struct cgroup_base_stat bstat; struct prev_cputime prev_cputime; /* for printing out cputime */ @@ -488,7 +478,7 @@ struct cgroup { struct cgroup_freezer_state freezer; /* ids of the ancestors at each level including self */ - int ancestor_ids[]; + u64 ancestor_ids[]; }; /* @@ -509,7 +499,7 @@ struct cgroup_root { struct cgroup cgrp; /* for cgrp->ancestor_ids[0] */ - int cgrp_ancestor_id_storage; + u64 cgrp_ancestor_id_storage; /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ atomic_t nr_cgrps; @@ -520,9 +510,6 @@ struct cgroup_root { /* Hierarchy-specific flags */ unsigned int flags; - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - /* The path to use for release notifications. */ char release_agent_path[PATH_MAX]; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 3ba3e6da13a6..d7ddebd0cdec 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -150,7 +150,6 @@ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp); -void cgroup_enable_task_cg_lists(void); void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it); struct task_struct *css_task_iter_next(struct css_task_iter *it); @@ -305,6 +304,11 @@ void css_task_iter_end(struct css_task_iter *it); * Inline functions. */ +static inline u64 cgroup_id(struct cgroup *cgrp) +{ + return cgrp->kn->id; +} + /** * css_get - obtain a reference on the specified css * @css: target css @@ -566,7 +570,7 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp, { if (cgrp->root != ancestor->root || cgrp->level < ancestor->level) return false; - return cgrp->ancestor_ids[ancestor->level] == ancestor->id; + return cgrp->ancestor_ids[ancestor->level] == cgroup_id(ancestor); } /** @@ -617,7 +621,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp) /* returns ino associated with a cgroup */ static inline ino_t cgroup_ino(struct cgroup *cgrp) { - return cgrp->kn->id.ino; + return kernfs_ino(cgrp->kn); } /* cft/css accessors for cftype->write() operation */ @@ -688,18 +692,13 @@ static inline void cgroup_kthread_ready(void) current->no_cgroup_migration = 0; } -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return &cgrp->kn->id; -} - -void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen); +void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen); #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; struct cgroup; +static inline u64 cgroup_id(struct cgroup *cgrp) { return 1; } static inline void css_get(struct cgroup_subsys_state *css) {} static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, @@ -719,10 +718,6 @@ static inline int cgroup_init_early(void) { return 0; } static inline int cgroup_init(void) { return 0; } static inline void cgroup_init_kthreadd(void) {} static inline void cgroup_kthread_ready(void) {} -static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp) -{ - return NULL; -} static inline struct cgroup *cgroup_parent(struct cgroup *cgrp) { @@ -740,8 +735,8 @@ static inline bool task_under_cgroup_hierarchy(struct task_struct *task, return true; } -static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, - char *buf, size_t buflen) {} +static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) +{} #endif /* !CONFIG_CGROUPS */ #ifdef CONFIG_CGROUPS diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 068793a619ca..89d75edb5750 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -136,6 +136,7 @@ enum cpuhp_state { /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, + CPUHP_AP_ARM_KVMPV_STARTING, CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, diff --git a/include/linux/crypto.h b/include/linux/crypto.h index 19ea3a371d7b..23365a9d062e 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -41,8 +41,6 @@ #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 -#define CRYPTO_ALG_TYPE_BLKCIPHER 0x00000004 -#define CRYPTO_ALG_TYPE_ABLKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a @@ -55,7 +53,6 @@ #define CRYPTO_ALG_TYPE_HASH_MASK 0x0000000e #define CRYPTO_ALG_TYPE_AHASH_MASK 0x0000000e -#define CRYPTO_ALG_TYPE_BLKCIPHER_MASK 0x0000000c #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 @@ -139,9 +136,7 @@ #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct scatterlist; -struct crypto_ablkcipher; struct crypto_async_request; -struct crypto_blkcipher; struct crypto_tfm; struct crypto_type; @@ -163,25 +158,6 @@ struct crypto_async_request { u32 flags; }; -struct ablkcipher_request { - struct crypto_async_request base; - - unsigned int nbytes; - - void *info; - - struct scatterlist *src; - struct scatterlist *dst; - - void *__ctx[] CRYPTO_MINALIGN_ATTR; -}; - -struct blkcipher_desc { - struct crypto_blkcipher *tfm; - void *info; - u32 flags; -}; - /** * DOC: Block Cipher Algorithm Definitions * @@ -190,83 +166,6 @@ struct blkcipher_desc { */ /** - * struct ablkcipher_alg - asynchronous block cipher definition - * @min_keysize: Minimum key size supported by the transformation. This is the - * smallest key length supported by this transformation algorithm. - * This must be set to one of the pre-defined values as this is - * not hardware specific. Possible values for this field can be - * found via git grep "_MIN_KEY_SIZE" include/crypto/ - * @max_keysize: Maximum key size supported by the transformation. This is the - * largest key length supported by this transformation algorithm. - * This must be set to one of the pre-defined values as this is - * not hardware specific. Possible values for this field can be - * found via git grep "_MAX_KEY_SIZE" include/crypto/ - * @setkey: Set key for the transformation. This function is used to either - * program a supplied key into the hardware or store the key in the - * transformation context for programming it later. Note that this - * function does modify the transformation context. This function can - * be called multiple times during the existence of the transformation - * object, so one must make sure the key is properly reprogrammed into - * the hardware. This function is also responsible for checking the key - * length for validity. In case a software fallback was put in place in - * the @cra_init call, this function might need to use the fallback if - * the algorithm doesn't support all of the key sizes. - * @encrypt: Encrypt a scatterlist of blocks. This function is used to encrypt - * the supplied scatterlist containing the blocks of data. The crypto - * API consumer is responsible for aligning the entries of the - * scatterlist properly and making sure the chunks are correctly - * sized. In case a software fallback was put in place in the - * @cra_init call, this function might need to use the fallback if - * the algorithm doesn't support all of the key sizes. In case the - * key was stored in transformation context, the key might need to be - * re-programmed into the hardware in this function. This function - * shall not modify the transformation context, as this function may - * be called in parallel with the same transformation object. - * @decrypt: Decrypt a single block. This is a reverse counterpart to @encrypt - * and the conditions are exactly the same. - * @ivsize: IV size applicable for transformation. The consumer must provide an - * IV of exactly that size to perform the encrypt or decrypt operation. - * - * All fields except @ivsize are mandatory and must be filled. - */ -struct ablkcipher_alg { - int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct ablkcipher_request *req); - int (*decrypt)(struct ablkcipher_request *req); - - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - -/** - * struct blkcipher_alg - synchronous block cipher definition - * @min_keysize: see struct ablkcipher_alg - * @max_keysize: see struct ablkcipher_alg - * @setkey: see struct ablkcipher_alg - * @encrypt: see struct ablkcipher_alg - * @decrypt: see struct ablkcipher_alg - * @ivsize: see struct ablkcipher_alg - * - * All fields except @ivsize are mandatory and must be filled. - */ -struct blkcipher_alg { - int (*setkey)(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes); - int (*decrypt)(struct blkcipher_desc *desc, - struct scatterlist *dst, struct scatterlist *src, - unsigned int nbytes); - - unsigned int min_keysize; - unsigned int max_keysize; - unsigned int ivsize; -}; - -/** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is * the smallest key length supported by this transformation @@ -450,8 +349,6 @@ struct crypto_istat_rng { }; #endif /* CONFIG_CRYPTO_STATS */ -#define cra_ablkcipher cra_u.ablkcipher -#define cra_blkcipher cra_u.blkcipher #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress @@ -499,9 +396,8 @@ struct crypto_istat_rng { * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all - * transformation types. There are multiple options: - * &crypto_blkcipher_type, &crypto_ablkcipher_type, - * &crypto_ahash_type, &crypto_rng_type. + * transformation types. There are multiple options, such as + * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of @@ -520,10 +416,6 @@ struct crypto_istat_rng { * @cra_exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @cra_init, used to remove various changes set in * @cra_init. - * @cra_u.ablkcipher: Union member which contains an asynchronous block cipher - * definition. See @struct @ablkcipher_alg. - * @cra_u.blkcipher: Union member which contains a synchronous block cipher - * definition See @struct @blkcipher_alg. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. @@ -565,8 +457,6 @@ struct crypto_alg { const struct crypto_type *cra_type; union { - struct ablkcipher_alg ablkcipher; - struct blkcipher_alg blkcipher; struct cipher_alg cipher; struct compress_alg compress; } cra_u; @@ -594,8 +484,6 @@ struct crypto_alg { #ifdef CONFIG_CRYPTO_STATS void crypto_stats_init(struct crypto_alg *alg); void crypto_stats_get(struct crypto_alg *alg); -void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); -void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg); void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret); void crypto_stats_ahash_update(unsigned int nbytes, int ret, struct crypto_alg *alg); @@ -618,10 +506,6 @@ static inline void crypto_stats_init(struct crypto_alg *alg) {} static inline void crypto_stats_get(struct crypto_alg *alg) {} -static inline void crypto_stats_ablkcipher_encrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} -static inline void crypto_stats_ablkcipher_decrypt(unsigned int nbytes, int ret, struct crypto_alg *alg) -{} static inline void crypto_stats_aead_encrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) {} static inline void crypto_stats_aead_decrypt(unsigned int cryptlen, struct crypto_alg *alg, int ret) @@ -715,28 +599,6 @@ int crypto_has_alg(const char *name, u32 type, u32 mask); * crypto_free_*(), as well as the various helpers below. */ -struct ablkcipher_tfm { - int (*setkey)(struct crypto_ablkcipher *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct ablkcipher_request *req); - int (*decrypt)(struct ablkcipher_request *req); - - struct crypto_ablkcipher *base; - - unsigned int ivsize; - unsigned int reqsize; -}; - -struct blkcipher_tfm { - void *iv; - int (*setkey)(struct crypto_tfm *tfm, const u8 *key, - unsigned int keylen); - int (*encrypt)(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes); - int (*decrypt)(struct blkcipher_desc *desc, struct scatterlist *dst, - struct scatterlist *src, unsigned int nbytes); -}; - struct cipher_tfm { int (*cit_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); @@ -753,8 +615,6 @@ struct compress_tfm { u8 *dst, unsigned int *dlen); }; -#define crt_ablkcipher crt_u.ablkcipher -#define crt_blkcipher crt_u.blkcipher #define crt_cipher crt_u.cipher #define crt_compress crt_u.compress @@ -763,8 +623,6 @@ struct crypto_tfm { u32 crt_flags; union { - struct ablkcipher_tfm ablkcipher; - struct blkcipher_tfm blkcipher; struct cipher_tfm cipher; struct compress_tfm compress; } crt_u; @@ -776,14 +634,6 @@ struct crypto_tfm { void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; -struct crypto_ablkcipher { - struct crypto_tfm base; -}; - -struct crypto_blkcipher { - struct crypto_tfm base; -}; - struct crypto_cipher { struct crypto_tfm base; }; @@ -891,713 +741,6 @@ static inline unsigned int crypto_tfm_ctx_alignment(void) return __alignof__(tfm->__crt_ctx); } -/* - * API wrappers. - */ -static inline struct crypto_ablkcipher *__crypto_ablkcipher_cast( - struct crypto_tfm *tfm) -{ - return (struct crypto_ablkcipher *)tfm; -} - -static inline u32 crypto_skcipher_type(u32 type) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - return type; -} - -static inline u32 crypto_skcipher_mask(u32 mask) -{ - mask &= ~CRYPTO_ALG_TYPE_MASK; - mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK; - return mask; -} - -/** - * DOC: Asynchronous Block Cipher API - * - * Asynchronous block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_ABLKCIPHER (listed as type "ablkcipher" in /proc/crypto). - * - * Asynchronous cipher operations imply that the function invocation for a - * cipher request returns immediately before the completion of the operation. - * The cipher request is scheduled as a separate kernel thread and therefore - * load-balanced on the different CPUs via the process scheduler. To allow - * the kernel crypto API to inform the caller about the completion of a cipher - * request, the caller must provide a callback function. That function is - * invoked with the cipher handle when the request completes. - * - * To support the asynchronous operation, additional information than just the - * cipher handle must be supplied to the kernel crypto API. That additional - * information is given by filling in the ablkcipher_request data structure. - * - * For the asynchronous block cipher API, the state is maintained with the tfm - * cipher handle. A single tfm can be used across multiple calls and in - * parallel. For asynchronous block cipher calls, context data supplied and - * only used by the caller can be referenced the request data structure in - * addition to the IV used for the cipher request. The maintenance of such - * state information would be important for a crypto driver implementer to - * have, because when calling the callback function upon completion of the - * cipher operation, that callback function may need some information about - * which operation just finished if it invoked multiple in parallel. This - * state information is unused by the kernel crypto API. - */ - -static inline struct crypto_tfm *crypto_ablkcipher_tfm( - struct crypto_ablkcipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_ablkcipher() - zeroize and free cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_ablkcipher(struct crypto_ablkcipher *tfm) -{ - crypto_free_tfm(crypto_ablkcipher_tfm(tfm)); -} - -/** - * crypto_has_ablkcipher() - Search for the availability of an ablkcipher. - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * ablkcipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the ablkcipher is known to the kernel crypto API; false - * otherwise - */ -static inline int crypto_has_ablkcipher(const char *alg_name, u32 type, - u32 mask) -{ - return crypto_has_alg(alg_name, crypto_skcipher_type(type), - crypto_skcipher_mask(mask)); -} - -static inline struct ablkcipher_tfm *crypto_ablkcipher_crt( - struct crypto_ablkcipher *tfm) -{ - return &crypto_ablkcipher_tfm(tfm)->crt_ablkcipher; -} - -/** - * crypto_ablkcipher_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the ablkcipher referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_ablkcipher_ivsize( - struct crypto_ablkcipher *tfm) -{ - return crypto_ablkcipher_crt(tfm)->ivsize; -} - -/** - * crypto_ablkcipher_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the ablkcipher referenced with the cipher handle is - * returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation - * - * Return: block size of cipher - */ -static inline unsigned int crypto_ablkcipher_blocksize( - struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_ablkcipher_tfm(tfm)); -} - -static inline unsigned int crypto_ablkcipher_alignmask( - struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_ablkcipher_tfm(tfm)); -} - -static inline u32 crypto_ablkcipher_get_flags(struct crypto_ablkcipher *tfm) -{ - return crypto_tfm_get_flags(crypto_ablkcipher_tfm(tfm)); -} - -static inline void crypto_ablkcipher_set_flags(struct crypto_ablkcipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_ablkcipher_tfm(tfm), flags); -} - -static inline void crypto_ablkcipher_clear_flags(struct crypto_ablkcipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_ablkcipher_tfm(tfm), flags); -} - -/** - * crypto_ablkcipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the ablkcipher referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm, - const u8 *key, unsigned int keylen) -{ - struct ablkcipher_tfm *crt = crypto_ablkcipher_crt(tfm); - - return crt->setkey(crt->base, key, keylen); -} - -/** - * crypto_ablkcipher_reqtfm() - obtain cipher handle from request - * @req: ablkcipher_request out of which the cipher handle is to be obtained - * - * Return the crypto_ablkcipher handle when furnishing an ablkcipher_request - * data structure. - * - * Return: crypto_ablkcipher handle - */ -static inline struct crypto_ablkcipher *crypto_ablkcipher_reqtfm( - struct ablkcipher_request *req) -{ - return __crypto_ablkcipher_cast(req->base.tfm); -} - -/** - * crypto_ablkcipher_encrypt() - encrypt plaintext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Encrypt plaintext data using the ablkcipher_request handle. That data - * structure and how it is filled with data is discussed with the - * ablkcipher_request_* functions. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_encrypt(struct ablkcipher_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - struct crypto_alg *alg = crt->base->base.__crt_alg; - unsigned int nbytes = req->nbytes; - int ret; - - crypto_stats_get(alg); - ret = crt->encrypt(req); - crypto_stats_ablkcipher_encrypt(nbytes, ret, alg); - return ret; -} - -/** - * crypto_ablkcipher_decrypt() - decrypt ciphertext - * @req: reference to the ablkcipher_request handle that holds all information - * needed to perform the cipher operation - * - * Decrypt ciphertext data using the ablkcipher_request handle. That data - * structure and how it is filled with data is discussed with the - * ablkcipher_request_* functions. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_ablkcipher_decrypt(struct ablkcipher_request *req) -{ - struct ablkcipher_tfm *crt = - crypto_ablkcipher_crt(crypto_ablkcipher_reqtfm(req)); - struct crypto_alg *alg = crt->base->base.__crt_alg; - unsigned int nbytes = req->nbytes; - int ret; - - crypto_stats_get(alg); - ret = crt->decrypt(req); - crypto_stats_ablkcipher_decrypt(nbytes, ret, alg); - return ret; -} - -/** - * DOC: Asynchronous Cipher Request Handle - * - * The ablkcipher_request data structure contains all pointers to data - * required for the asynchronous cipher operation. This includes the cipher - * handle (which can be used by multiple ablkcipher_request instances), pointer - * to plaintext and ciphertext, asynchronous callback function, etc. It acts - * as a handle to the ablkcipher_request_* API calls in a similar way as - * ablkcipher handle to the crypto_ablkcipher_* API calls. - */ - -/** - * crypto_ablkcipher_reqsize() - obtain size of the request data structure - * @tfm: cipher handle - * - * Return: number of bytes - */ -static inline unsigned int crypto_ablkcipher_reqsize( - struct crypto_ablkcipher *tfm) -{ - return crypto_ablkcipher_crt(tfm)->reqsize; -} - -/** - * ablkcipher_request_set_tfm() - update cipher handle reference in request - * @req: request handle to be modified - * @tfm: cipher handle that shall be added to the request handle - * - * Allow the caller to replace the existing ablkcipher handle in the request - * data structure with a different one. - */ -static inline void ablkcipher_request_set_tfm( - struct ablkcipher_request *req, struct crypto_ablkcipher *tfm) -{ - req->base.tfm = crypto_ablkcipher_tfm(crypto_ablkcipher_crt(tfm)->base); -} - -static inline struct ablkcipher_request *ablkcipher_request_cast( - struct crypto_async_request *req) -{ - return container_of(req, struct ablkcipher_request, base); -} - -/** - * ablkcipher_request_alloc() - allocate request data structure - * @tfm: cipher handle to be registered with the request - * @gfp: memory allocation flag that is handed to kmalloc by the API call. - * - * Allocate the request data structure that must be used with the ablkcipher - * encrypt and decrypt API calls. During the allocation, the provided ablkcipher - * handle is registered in the request data structure. - * - * Return: allocated request handle in case of success, or NULL if out of memory - */ -static inline struct ablkcipher_request *ablkcipher_request_alloc( - struct crypto_ablkcipher *tfm, gfp_t gfp) -{ - struct ablkcipher_request *req; - - req = kmalloc(sizeof(struct ablkcipher_request) + - crypto_ablkcipher_reqsize(tfm), gfp); - - if (likely(req)) - ablkcipher_request_set_tfm(req, tfm); - - return req; -} - -/** - * ablkcipher_request_free() - zeroize and free request data structure - * @req: request data structure cipher handle to be freed - */ -static inline void ablkcipher_request_free(struct ablkcipher_request *req) -{ - kzfree(req); -} - -/** - * ablkcipher_request_set_callback() - set asynchronous callback function - * @req: request handle - * @flags: specify zero or an ORing of the flags - * CRYPTO_TFM_REQ_MAY_BACKLOG the request queue may back log and - * increase the wait queue beyond the initial maximum size; - * CRYPTO_TFM_REQ_MAY_SLEEP the request processing may sleep - * @compl: callback function pointer to be registered with the request handle - * @data: The data pointer refers to memory that is not used by the kernel - * crypto API, but provided to the callback function for it to use. Here, - * the caller can provide a reference to memory the callback function can - * operate on. As the callback function is invoked asynchronously to the - * related functionality, it may need to access data structures of the - * related functionality which can be referenced using this pointer. The - * callback function can access the memory via the "data" field in the - * crypto_async_request data structure provided to the callback function. - * - * This function allows setting the callback function that is triggered once the - * cipher operation completes. - * - * The callback function is registered with the ablkcipher_request handle and - * must comply with the following template:: - * - * void callback_function(struct crypto_async_request *req, int error) - */ -static inline void ablkcipher_request_set_callback( - struct ablkcipher_request *req, - u32 flags, crypto_completion_t compl, void *data) -{ - req->base.complete = compl; - req->base.data = data; - req->base.flags = flags; -} - -/** - * ablkcipher_request_set_crypt() - set data buffers - * @req: request handle - * @src: source scatter / gather list - * @dst: destination scatter / gather list - * @nbytes: number of bytes to process from @src - * @iv: IV for the cipher operation which must comply with the IV size defined - * by crypto_ablkcipher_ivsize - * - * This function allows setting of the source data and destination data - * scatter / gather lists. - * - * For encryption, the source is treated as the plaintext and the - * destination is the ciphertext. For a decryption operation, the use is - * reversed - the source is the ciphertext and the destination is the plaintext. - */ -static inline void ablkcipher_request_set_crypt( - struct ablkcipher_request *req, - struct scatterlist *src, struct scatterlist *dst, - unsigned int nbytes, void *iv) -{ - req->src = src; - req->dst = dst; - req->nbytes = nbytes; - req->info = iv; -} - -/** - * DOC: Synchronous Block Cipher API - * - * The synchronous block cipher API is used with the ciphers of type - * CRYPTO_ALG_TYPE_BLKCIPHER (listed as type "blkcipher" in /proc/crypto) - * - * Synchronous calls, have a context in the tfm. But since a single tfm can be - * used in multiple calls and in parallel, this info should not be changeable - * (unless a lock is used). This applies, for example, to the symmetric key. - * However, the IV is changeable, so there is an iv field in blkcipher_tfm - * structure for synchronous blkcipher api. So, its the only state info that can - * be kept for synchronous calls without using a big lock across a tfm. - * - * The block cipher API allows the use of a complete cipher, i.e. a cipher - * consisting of a template (a block chaining mode) and a single block cipher - * primitive (e.g. AES). - * - * The plaintext data buffer and the ciphertext data buffer are pointed to - * by using scatter/gather lists. The cipher operation is performed - * on all segments of the provided scatter/gather lists. - * - * The kernel crypto API supports a cipher operation "in-place" which means that - * the caller may provide the same scatter/gather list for the plaintext and - * cipher text. After the completion of the cipher operation, the plaintext - * data is replaced with the ciphertext data in case of an encryption and vice - * versa for a decryption. The caller must ensure that the scatter/gather lists - * for the output data point to sufficiently large buffers, i.e. multiples of - * the block size of the cipher. - */ - -static inline struct crypto_blkcipher *__crypto_blkcipher_cast( - struct crypto_tfm *tfm) -{ - return (struct crypto_blkcipher *)tfm; -} - -static inline struct crypto_blkcipher *crypto_blkcipher_cast( - struct crypto_tfm *tfm) -{ - BUG_ON(crypto_tfm_alg_type(tfm) != CRYPTO_ALG_TYPE_BLKCIPHER); - return __crypto_blkcipher_cast(tfm); -} - -/** - * crypto_alloc_blkcipher() - allocate synchronous block cipher handle - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * blkcipher cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Allocate a cipher handle for a block cipher. The returned struct - * crypto_blkcipher is the cipher handle that is required for any subsequent - * API invocation for that block cipher. - * - * Return: allocated cipher handle in case of success; IS_ERR() is true in case - * of an error, PTR_ERR() returns the error code. - */ -static inline struct crypto_blkcipher *crypto_alloc_blkcipher( - const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return __crypto_blkcipher_cast(crypto_alloc_base(alg_name, type, mask)); -} - -static inline struct crypto_tfm *crypto_blkcipher_tfm( - struct crypto_blkcipher *tfm) -{ - return &tfm->base; -} - -/** - * crypto_free_blkcipher() - zeroize and free the block cipher handle - * @tfm: cipher handle to be freed - */ -static inline void crypto_free_blkcipher(struct crypto_blkcipher *tfm) -{ - crypto_free_tfm(crypto_blkcipher_tfm(tfm)); -} - -/** - * crypto_has_blkcipher() - Search for the availability of a block cipher - * @alg_name: is the cra_name / name or cra_driver_name / driver name of the - * block cipher - * @type: specifies the type of the cipher - * @mask: specifies the mask for the cipher - * - * Return: true when the block cipher is known to the kernel crypto API; false - * otherwise - */ -static inline int crypto_has_blkcipher(const char *alg_name, u32 type, u32 mask) -{ - type &= ~CRYPTO_ALG_TYPE_MASK; - type |= CRYPTO_ALG_TYPE_BLKCIPHER; - mask |= CRYPTO_ALG_TYPE_MASK; - - return crypto_has_alg(alg_name, type, mask); -} - -/** - * crypto_blkcipher_name() - return the name / cra_name from the cipher handle - * @tfm: cipher handle - * - * Return: The character string holding the name of the cipher - */ -static inline const char *crypto_blkcipher_name(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_name(crypto_blkcipher_tfm(tfm)); -} - -static inline struct blkcipher_tfm *crypto_blkcipher_crt( - struct crypto_blkcipher *tfm) -{ - return &crypto_blkcipher_tfm(tfm)->crt_blkcipher; -} - -static inline struct blkcipher_alg *crypto_blkcipher_alg( - struct crypto_blkcipher *tfm) -{ - return &crypto_blkcipher_tfm(tfm)->__crt_alg->cra_blkcipher; -} - -/** - * crypto_blkcipher_ivsize() - obtain IV size - * @tfm: cipher handle - * - * The size of the IV for the block cipher referenced by the cipher handle is - * returned. This IV size may be zero if the cipher does not need an IV. - * - * Return: IV size in bytes - */ -static inline unsigned int crypto_blkcipher_ivsize(struct crypto_blkcipher *tfm) -{ - return crypto_blkcipher_alg(tfm)->ivsize; -} - -/** - * crypto_blkcipher_blocksize() - obtain block size of cipher - * @tfm: cipher handle - * - * The block size for the block cipher referenced with the cipher handle is - * returned. The caller may use that information to allocate appropriate - * memory for the data returned by the encryption or decryption operation. - * - * Return: block size of cipher - */ -static inline unsigned int crypto_blkcipher_blocksize( - struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_blocksize(crypto_blkcipher_tfm(tfm)); -} - -static inline unsigned int crypto_blkcipher_alignmask( - struct crypto_blkcipher *tfm) -{ - return crypto_tfm_alg_alignmask(crypto_blkcipher_tfm(tfm)); -} - -static inline u32 crypto_blkcipher_get_flags(struct crypto_blkcipher *tfm) -{ - return crypto_tfm_get_flags(crypto_blkcipher_tfm(tfm)); -} - -static inline void crypto_blkcipher_set_flags(struct crypto_blkcipher *tfm, - u32 flags) -{ - crypto_tfm_set_flags(crypto_blkcipher_tfm(tfm), flags); -} - -static inline void crypto_blkcipher_clear_flags(struct crypto_blkcipher *tfm, - u32 flags) -{ - crypto_tfm_clear_flags(crypto_blkcipher_tfm(tfm), flags); -} - -/** - * crypto_blkcipher_setkey() - set key for cipher - * @tfm: cipher handle - * @key: buffer holding the key - * @keylen: length of the key in bytes - * - * The caller provided key is set for the block cipher referenced by the cipher - * handle. - * - * Note, the key length determines the cipher type. Many block ciphers implement - * different cipher modes depending on the key size, such as AES-128 vs AES-192 - * vs. AES-256. When providing a 16 byte key for an AES cipher handle, AES-128 - * is performed. - * - * Return: 0 if the setting of the key was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_setkey(struct crypto_blkcipher *tfm, - const u8 *key, unsigned int keylen) -{ - return crypto_blkcipher_crt(tfm)->setkey(crypto_blkcipher_tfm(tfm), - key, keylen); -} - -/** - * crypto_blkcipher_encrypt() - encrypt plaintext - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * ciphertext - * @src: scatter/gather list that holds the plaintext - * @nbytes: number of bytes of the plaintext to encrypt. - * - * Encrypt plaintext data using the IV set by the caller with a preceding - * call of crypto_blkcipher_set_iv. - * - * The blkcipher_desc data structure must be filled by the caller and can - * reside on the stack. The caller must fill desc as follows: desc.tfm is filled - * with the block cipher handle; desc.flags is filled with either - * CRYPTO_TFM_REQ_MAY_SLEEP or 0. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_encrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - desc->info = crypto_blkcipher_crt(desc->tfm)->iv; - return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_encrypt_iv() - encrypt plaintext with dedicated IV - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * ciphertext - * @src: scatter/gather list that holds the plaintext - * @nbytes: number of bytes of the plaintext to encrypt. - * - * Encrypt plaintext data with the use of an IV that is solely used for this - * cipher operation. Any previously set IV is not used. - * - * The blkcipher_desc data structure must be filled by the caller and can - * reside on the stack. The caller must fill desc as follows: desc.tfm is filled - * with the block cipher handle; desc.info is filled with the IV to be used for - * the current operation; desc.flags is filled with either - * CRYPTO_TFM_REQ_MAY_SLEEP or 0. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_encrypt_iv(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - return crypto_blkcipher_crt(desc->tfm)->encrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_decrypt() - decrypt ciphertext - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * plaintext - * @src: scatter/gather list that holds the ciphertext - * @nbytes: number of bytes of the ciphertext to decrypt. - * - * Decrypt ciphertext data using the IV set by the caller with a preceding - * call of crypto_blkcipher_set_iv. - * - * The blkcipher_desc data structure must be filled by the caller as documented - * for the crypto_blkcipher_encrypt call above. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - * - */ -static inline int crypto_blkcipher_decrypt(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - desc->info = crypto_blkcipher_crt(desc->tfm)->iv; - return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_decrypt_iv() - decrypt ciphertext with dedicated IV - * @desc: reference to the block cipher handle with meta data - * @dst: scatter/gather list that is filled by the cipher operation with the - * plaintext - * @src: scatter/gather list that holds the ciphertext - * @nbytes: number of bytes of the ciphertext to decrypt. - * - * Decrypt ciphertext data with the use of an IV that is solely used for this - * cipher operation. Any previously set IV is not used. - * - * The blkcipher_desc data structure must be filled by the caller as documented - * for the crypto_blkcipher_encrypt_iv call above. - * - * Return: 0 if the cipher operation was successful; < 0 if an error occurred - */ -static inline int crypto_blkcipher_decrypt_iv(struct blkcipher_desc *desc, - struct scatterlist *dst, - struct scatterlist *src, - unsigned int nbytes) -{ - return crypto_blkcipher_crt(desc->tfm)->decrypt(desc, dst, src, nbytes); -} - -/** - * crypto_blkcipher_set_iv() - set IV for cipher - * @tfm: cipher handle - * @src: buffer holding the IV - * @len: length of the IV in bytes - * - * The caller provided IV is set for the block cipher referenced by the cipher - * handle. - */ -static inline void crypto_blkcipher_set_iv(struct crypto_blkcipher *tfm, - const u8 *src, unsigned int len) -{ - memcpy(crypto_blkcipher_crt(tfm)->iv, src, len); -} - -/** - * crypto_blkcipher_get_iv() - obtain IV from cipher - * @tfm: cipher handle - * @dst: buffer filled with the IV - * @len: length of the buffer dst - * - * The caller can obtain the IV set for the block cipher referenced by the - * cipher handle and store it into the user-provided buffer. If the buffer - * has an insufficient space, the IV is truncated to fit the buffer. - */ -static inline void crypto_blkcipher_get_iv(struct crypto_blkcipher *tfm, - u8 *dst, unsigned int len) -{ - memcpy(dst, crypto_blkcipher_crt(tfm)->iv, len); -} - /** * DOC: Single Block Cipher API * diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 399ad8632356..475668c69dbc 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -17,6 +17,7 @@ struct dm_dev; struct dm_target; struct dm_table; +struct dm_report_zones_args; struct mapped_device; struct bio_vec; @@ -93,9 +94,9 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv, typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev); -typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector, - struct blk_zone *zones, - unsigned int *nr_zones); +typedef int (*dm_report_zones_fn) (struct dm_target *ti, + struct dm_report_zones_args *args, + unsigned int nr_zones); /* * These iteration functions are typically used to check (and combine) @@ -422,10 +423,23 @@ struct gendisk *dm_disk(struct mapped_device *md); int dm_suspended(struct dm_target *ti); int dm_noflush_suspending(struct dm_target *ti); void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors); -void dm_remap_zone_report(struct dm_target *ti, sector_t start, - struct blk_zone *zones, unsigned int *nr_zones); union map_info *dm_get_rq_mapinfo(struct request *rq); +#ifdef CONFIG_BLK_DEV_ZONED +struct dm_report_zones_args { + struct dm_target *tgt; + sector_t next_sector; + + void *orig_data; + report_zones_cb orig_cb; + unsigned int zone_idx; + + /* must be filled by ->report_zones before calling dm_report_zones_cb */ + sector_t start; +}; +int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +#endif /* CONFIG_BLK_DEV_ZONED */ + /* * Device mapper functions to parse and create devices specified by the * parameter "dm-mod.create=" @@ -594,9 +608,6 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); */ #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz)) -#define dm_array_too_big(fixed, obj, num) \ - ((num) > (UINT_MAX - (fixed)) / (obj)) - /* * Sector offset taken relative to the start of the target instead of * relative to the start of the device. diff --git a/include/linux/dim.h b/include/linux/dim.h index 9fa4b3f88c39..b698266d0035 100644 --- a/include/linux/dim.h +++ b/include/linux/dim.h @@ -4,22 +4,26 @@ #ifndef DIM_H #define DIM_H +#include <linux/bits.h> +#include <linux/kernel.h> #include <linux/module.h> +#include <linux/types.h> +#include <linux/workqueue.h> -/** +/* * Number of events between DIM iterations. * Causes a moderation of the algorithm run. */ #define DIM_NEVENTS 64 -/** +/* * Is a difference between values justifies taking an action. * We consider 10% difference as significant. */ #define IS_SIGNIFICANT_DIFF(val, ref) \ (((100UL * abs((val) - (ref))) / (ref)) > 10) -/** +/* * Calculate the gap between two values. * Take wrap-around and variable size into consideration. */ @@ -27,12 +31,13 @@ & (BIT_ULL(bits) - 1)) /** - * Structure for CQ moderation values. + * struct dim_cq_moder - Structure for CQ moderation values. * Used for communications between DIM and its consumer. * * @usec: CQ timer suggestion (by DIM) * @pkts: CQ packet counter suggestion (by DIM) - * @cq_period_mode: CQ priod count mode (from CQE/EQE) + * @comps: Completion counter + * @cq_period_mode: CQ period count mode (from CQE/EQE) */ struct dim_cq_moder { u16 usec; @@ -42,13 +47,14 @@ struct dim_cq_moder { }; /** - * Structure for DIM sample data. + * struct dim_sample - Structure for DIM sample data. * Used for communications between DIM and its consumer. * * @time: Sample timestamp * @pkt_ctr: Number of packets * @byte_ctr: Number of bytes * @event_ctr: Number of events + * @comp_ctr: Current completion counter */ struct dim_sample { ktime_t time; @@ -59,12 +65,14 @@ struct dim_sample { }; /** - * Structure for DIM stats. + * struct dim_stats - Structure for DIM stats. * Used for holding current measured rates. * * @ppms: Packets per msec * @bpms: Bytes per msec * @epms: Events per msec + * @cpms: Completions per msec + * @cpe_ratio: Ratio of completions to events */ struct dim_stats { int ppms; /* packets per msec */ @@ -75,12 +83,13 @@ struct dim_stats { }; /** - * Main structure for dynamic interrupt moderation (DIM). + * struct dim - Main structure for dynamic interrupt moderation (DIM). * Used for holding all information about a specific DIM instance. * * @state: Algorithm state (see below) * @prev_stats: Measured rates from previous iteration (for comparison) * @start_sample: Sampled data at start of current iteration + * @measuring_sample: A &dim_sample that is used to update the current events * @work: Work to perform on action required * @priv: A pointer to the struct that points to dim * @profile_ix: Current moderation profile @@ -106,24 +115,21 @@ struct dim { }; /** - * enum dim_cq_period_mode - * - * These are the modes for CQ period count. + * enum dim_cq_period_mode - Modes for CQ period count * * @DIM_CQ_PERIOD_MODE_START_FROM_EQE: Start counting from EQE * @DIM_CQ_PERIOD_MODE_START_FROM_CQE: Start counting from CQE (implies timer reset) * @DIM_CQ_PERIOD_NUM_MODES: Number of modes */ -enum { +enum dim_cq_period_mode { DIM_CQ_PERIOD_MODE_START_FROM_EQE = 0x0, DIM_CQ_PERIOD_MODE_START_FROM_CQE = 0x1, DIM_CQ_PERIOD_NUM_MODES }; /** - * enum dim_state + * enum dim_state - DIM algorithm states * - * These are the DIM algorithm states. * These will determine if the algorithm is in a valid state to start an iteration. * * @DIM_START_MEASURE: This is the first iteration (also after applying a new profile) @@ -131,16 +137,15 @@ enum { * need to perform an action * @DIM_APPLY_NEW_PROFILE: DIM consumer is currently applying a profile - no need to measure */ -enum { +enum dim_state { DIM_START_MEASURE, DIM_MEASURE_IN_PROGRESS, DIM_APPLY_NEW_PROFILE, }; /** - * enum dim_tune_state + * enum dim_tune_state - DIM algorithm tune states * - * These are the DIM algorithm tune states. * These will determine which action the algorithm should perform. * * @DIM_PARKING_ON_TOP: Algorithm found a local top point - exit on significant difference @@ -148,7 +153,7 @@ enum { * @DIM_GOING_RIGHT: Algorithm is currently trying higher moderation levels * @DIM_GOING_LEFT: Algorithm is currently trying lower moderation levels */ -enum { +enum dim_tune_state { DIM_PARKING_ON_TOP, DIM_PARKING_TIRED, DIM_GOING_RIGHT, @@ -156,25 +161,23 @@ enum { }; /** - * enum dim_stats_state + * enum dim_stats_state - DIM algorithm statistics states * - * These are the DIM algorithm statistics states. * These will determine the verdict of current iteration. * * @DIM_STATS_WORSE: Current iteration shows worse performance than before - * @DIM_STATS_WORSE: Current iteration shows same performance than before - * @DIM_STATS_WORSE: Current iteration shows better performance than before + * @DIM_STATS_SAME: Current iteration shows same performance than before + * @DIM_STATS_BETTER: Current iteration shows better performance than before */ -enum { +enum dim_stats_state { DIM_STATS_WORSE, DIM_STATS_SAME, DIM_STATS_BETTER, }; /** - * enum dim_step_result + * enum dim_step_result - DIM algorithm step results * - * These are the DIM algorithm step results. * These describe the result of a step. * * @DIM_STEPPED: Performed a regular step @@ -182,7 +185,7 @@ enum { * tired parking * @DIM_ON_EDGE: Stepped to the most left/right profile */ -enum { +enum dim_step_result { DIM_STEPPED, DIM_TOO_TIRED, DIM_ON_EDGE, @@ -199,7 +202,7 @@ enum { bool dim_on_top(struct dim *dim); /** - * dim_turn - change profile alterning direction + * dim_turn - change profile altering direction * @dim: DIM context * * Go left if we were going right and vice-versa. @@ -238,7 +241,7 @@ void dim_calc_stats(struct dim_sample *start, struct dim_sample *end, struct dim_stats *curr_stats); /** - * dim_update_sample - set a sample's fields with give values + * dim_update_sample - set a sample's fields with given values * @event_ctr: number of events to set * @packets: number of packets to set * @bytes: number of bytes to set @@ -304,8 +307,8 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode); * @end_sample: Current data measurement * * Called by the consumer. - * This is the main logic of the algorithm, where data is processed in order to decide on next - * required action. + * This is the main logic of the algorithm, where data is processed in order + * to decide on next required action. */ void net_dim(struct dim *dim, struct dim_sample end_sample); diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index adf993a3bd58..d03af3605460 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -5,6 +5,8 @@ #include <linux/dma-mapping.h> #include <linux/mem_encrypt.h> +extern unsigned int zone_dma_bits; + #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA #include <asm/dma-direct.h> #else diff --git a/include/linux/edac.h b/include/linux/edac.h index c19483b90079..cc31b9742684 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -362,78 +362,6 @@ struct edac_mc_layer { */ #define EDAC_MAX_LAYERS 3 -/** - * EDAC_DIMM_OFF - Macro responsible to get a pointer offset inside a pointer - * array for the element given by [layer0,layer1,layer2] - * position - * - * @layers: a struct edac_mc_layer array, describing how many elements - * were allocated for each layer - * @nlayers: Number of layers at the @layers array - * @layer0: layer0 position - * @layer1: layer1 position. Unused if n_layers < 2 - * @layer2: layer2 position. Unused if n_layers < 3 - * - * For 1 layer, this macro returns "var[layer0] - var"; - * - * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "var[layer0][layer1] - var"; - * - * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "var[layer0][layer1][layer2] - var". - * - * A loop could be used here to make it more generic, but, as we only have - * 3 layers, this is a little faster. - * - * By design, layers can never be 0 or more than 3. If that ever happens, - * a NULL is returned, causing an OOPS during the memory allocation routine, - * with would point to the developer that he's doing something wrong. - */ -#define EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2) ({ \ - int __i; \ - if ((nlayers) == 1) \ - __i = layer0; \ - else if ((nlayers) == 2) \ - __i = (layer1) + ((layers[1]).size * (layer0)); \ - else if ((nlayers) == 3) \ - __i = (layer2) + ((layers[2]).size * ((layer1) + \ - ((layers[1]).size * (layer0)))); \ - else \ - __i = -EINVAL; \ - __i; \ -}) - -/** - * EDAC_DIMM_PTR - Macro responsible to get a pointer inside a pointer array - * for the element given by [layer0,layer1,layer2] position - * - * @layers: a struct edac_mc_layer array, describing how many elements - * were allocated for each layer - * @var: name of the var where we want to get the pointer - * (like mci->dimms) - * @nlayers: Number of layers at the @layers array - * @layer0: layer0 position - * @layer1: layer1 position. Unused if n_layers < 2 - * @layer2: layer2 position. Unused if n_layers < 3 - * - * For 1 layer, this macro returns "var[layer0]"; - * - * For 2 layers, this macro is similar to allocate a bi-dimensional array - * and to return "var[layer0][layer1]"; - * - * For 3 layers, this macro is similar to allocate a tri-dimensional array - * and to return "var[layer0][layer1][layer2]"; - */ -#define EDAC_DIMM_PTR(layers, var, nlayers, layer0, layer1, layer2) ({ \ - typeof(*var) __p; \ - int ___i = EDAC_DIMM_OFF(layers, nlayers, layer0, layer1, layer2); \ - if (___i < 0) \ - __p = NULL; \ - else \ - __p = (var)[___i]; \ - __p; \ -}) - struct dimm_info { struct device dev; @@ -443,6 +371,7 @@ struct dimm_info { unsigned int location[EDAC_MAX_LAYERS]; struct mem_ctl_info *mci; /* the parent */ + unsigned int idx; /* index within the parent dimm array */ u32 grain; /* granularity of reported error in bytes */ enum dev_type dtype; /* memory device type */ @@ -528,15 +457,10 @@ struct errcount_attribute_data { * (typically, a memory controller error) */ struct edac_raw_error_desc { - /* - * NOTE: everything before grain won't be cleaned by - * edac_raw_error_desc_clean() - */ char location[LOCATION_SIZE]; char label[(EDAC_MC_LABEL_LEN + 1 + sizeof(OTHER_LABEL)) * EDAC_MAX_LABELS]; long grain; - /* the vars below and grain will be cleaned on every new error report */ u16 error_count; int top_layer; int mid_layer; @@ -669,4 +593,70 @@ struct mem_ctl_info { bool fake_inject_ue; u16 fake_inject_count; }; -#endif + +#define mci_for_each_dimm(mci, dimm) \ + for ((dimm) = (mci)->dimms[0]; \ + (dimm); \ + (dimm) = (dimm)->idx + 1 < (mci)->tot_dimms \ + ? (mci)->dimms[(dimm)->idx + 1] \ + : NULL) + +/** + * edac_get_dimm_by_index - Get DIMM info at @index from a memory + * controller + * + * @mci: MC descriptor struct mem_ctl_info + * @index: index in the memory controller's DIMM array + * + * Returns a struct dimm_info * or NULL on failure. + */ +static inline struct dimm_info * +edac_get_dimm_by_index(struct mem_ctl_info *mci, int index) +{ + if (index < 0 || index >= mci->tot_dimms) + return NULL; + + if (WARN_ON_ONCE(mci->dimms[index]->idx != index)) + return NULL; + + return mci->dimms[index]; +} + +/** + * edac_get_dimm - Get DIMM info from a memory controller given by + * [layer0,layer1,layer2] position + * + * @mci: MC descriptor struct mem_ctl_info + * @layer0: layer0 position + * @layer1: layer1 position. Unused if n_layers < 2 + * @layer2: layer2 position. Unused if n_layers < 3 + * + * For 1 layer, this function returns "dimms[layer0]"; + * + * For 2 layers, this function is similar to allocating a two-dimensional + * array and returning "dimms[layer0][layer1]"; + * + * For 3 layers, this function is similar to allocating a tri-dimensional + * array and returning "dimms[layer0][layer1][layer2]"; + */ +static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci, + int layer0, int layer1, int layer2) +{ + int index; + + if (layer0 < 0 + || (mci->n_layers > 1 && layer1 < 0) + || (mci->n_layers > 2 && layer2 < 0)) + return NULL; + + index = layer0; + + if (mci->n_layers > 1) + index = index * mci->layers[1].size + layer1; + + if (mci->n_layers > 2) + index = index * mci->layers[2].size + layer2; + + return edac_get_dimm_by_index(mci, index); +} +#endif /* _LINUX_EDAC_H_ */ diff --git a/include/linux/errname.h b/include/linux/errname.h new file mode 100644 index 000000000000..e8576ad90cb7 --- /dev/null +++ b/include/linux/errname.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ERRNAME_H +#define _LINUX_ERRNAME_H + +#include <linux/stddef.h> + +#ifdef CONFIG_SYMBOLIC_ERRNAME +const char *errname(int err); +#else +static inline const char *errname(int err) +{ + return NULL; +} +#endif + +#endif /* _LINUX_ERRNAME_H */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index cf6571fc9c01..d896b8657085 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -105,6 +105,11 @@ enum fid_type { FILEID_LUSTRE = 0x97, /* + * 64 bit unique kernfs id + */ + FILEID_KERNFS = 0xfe, + + /* * Filesystems must not use 0xff file ID. */ FILEID_INVALID = 0xff, diff --git a/include/linux/extable.h b/include/linux/extable.h index 81ecfaa83ad3..4ab9e78f313b 100644 --- a/include/linux/extable.h +++ b/include/linux/extable.h @@ -33,4 +33,14 @@ search_module_extables(unsigned long addr) } #endif /*CONFIG_MODULES*/ +#ifdef CONFIG_BPF_JIT +const struct exception_table_entry *search_bpf_extables(unsigned long addr); +#else +static inline const struct exception_table_entry * +search_bpf_extables(unsigned long addr) +{ + return NULL; +} +#endif + #endif /* _LINUX_EXTABLE_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 0367a75f873b..1b1e8b8f88da 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -65,6 +65,9 @@ struct ctl_table_header; /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 +/* unused opcode to mark special load instruction. Same as BPF_ABS */ +#define BPF_PROBE_MEM 0x20 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 @@ -464,10 +467,11 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ - return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) @@ -511,10 +515,12 @@ struct sock_fprog_kern { struct sock_filter *filter; }; +/* Some arches need doubleword alignment for their instructions and/or data */ +#define BPF_IMAGE_ALIGNMENT 8 + struct bpf_binary_header { u32 pages; - /* Some arches need word alignment for their instructions */ - u8 image[] __aligned(4); + u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog { @@ -946,6 +952,9 @@ void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke); + int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); @@ -1044,11 +1053,23 @@ static inline bool ebpf_jit_enabled(void) return false; } +static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) +{ + return false; +} + static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } +static inline int +bpf_jit_add_poke_descriptor(struct bpf_prog *prog, + struct bpf_jit_poke_descriptor *poke) +{ + return -ENOTSUPP; +} + static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); diff --git a/include/linux/firmware/broadcom/tee_bnxt_fw.h b/include/linux/firmware/broadcom/tee_bnxt_fw.h new file mode 100644 index 000000000000..f24c82d6ef73 --- /dev/null +++ b/include/linux/firmware/broadcom/tee_bnxt_fw.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: BSD-2-Clause */ +/* + * Copyright 2019 Broadcom. + */ + +#ifndef _BROADCOM_TEE_BNXT_FW_H +#define _BROADCOM_TEE_BNXT_FW_H + +#include <linux/types.h> + +int tee_bnxt_fw_load(void); +int tee_bnxt_copy_coredump(void *buf, u32 offset, u32 size); + +#endif /* _BROADCOM_TEE_BNXT_FW_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index e0d909d35763..dde6dc4492a0 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -148,8 +148,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) -/* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ @@ -2632,8 +2630,6 @@ extern void bd_finish_claiming(struct block_device *bdev, extern void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); extern void blkdev_put(struct block_device *bdev, fmode_t mode); -extern int __blkdev_reread_part(struct block_device *bdev); -extern int blkdev_reread_part(struct block_device *bdev); #ifdef CONFIG_SYSFS extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); @@ -2703,8 +2699,6 @@ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); #ifdef CONFIG_BLOCK -extern void check_disk_size_change(struct gendisk *disk, - struct block_device *bdev, bool verbose); extern int revalidate_disk(struct gendisk *); extern int check_disk_change(struct block_device *); extern int __invalidate_device(struct block_device *, bool); diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index f622f7460ed8..1a7bffe78ed5 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -20,7 +20,6 @@ #define FS_CRYPTO_BLOCK_SIZE 16 -struct fscrypt_ctx; struct fscrypt_info; struct fscrypt_str { @@ -62,18 +61,9 @@ struct fscrypt_operations { bool (*dummy_context)(struct inode *); bool (*empty_dir)(struct inode *); unsigned int max_namelen; -}; - -/* Decryption work */ -struct fscrypt_ctx { - union { - struct { - struct bio *bio; - struct work_struct work; - }; - struct list_head free_list; /* Free list */ - }; - u8 flags; /* Flags */ + bool (*has_stable_inodes)(struct super_block *sb); + void (*get_ino_and_lblk_bits)(struct super_block *sb, + int *ino_bits_ret, int *lblk_bits_ret); }; static inline bool fscrypt_has_encryption_key(const struct inode *inode) @@ -102,8 +92,6 @@ static inline void fscrypt_handle_d_move(struct dentry *dentry) /* crypto.c */ extern void fscrypt_enqueue_decrypt_work(struct work_struct *); -extern struct fscrypt_ctx *fscrypt_get_ctx(gfp_t); -extern void fscrypt_release_ctx(struct fscrypt_ctx *); extern struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, @@ -244,8 +232,6 @@ static inline bool fscrypt_match_name(const struct fscrypt_name *fname, /* bio.c */ extern void fscrypt_decrypt_bio(struct bio *); -extern void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio); extern int fscrypt_zeroout_range(const struct inode *, pgoff_t, sector_t, unsigned int); @@ -295,16 +281,6 @@ static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work) { } -static inline struct fscrypt_ctx *fscrypt_get_ctx(gfp_t gfp_flags) -{ - return ERR_PTR(-EOPNOTSUPP); -} - -static inline void fscrypt_release_ctx(struct fscrypt_ctx *ctx) -{ - return; -} - static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page, unsigned int len, unsigned int offs, @@ -484,11 +460,6 @@ static inline void fscrypt_decrypt_bio(struct bio *bio) { } -static inline void fscrypt_enqueue_decrypt_bio(struct fscrypt_ctx *ctx, - struct bio *bio) -{ -} - static inline int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, sector_t pblk, unsigned int len) { diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 975553a9f75d..54d9436600c7 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -403,6 +403,8 @@ int __must_check fsl_mc_allocate_irqs(struct fsl_mc_device *mc_dev); void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev); +struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev); + extern struct bus_type fsl_mc_bus_type; extern struct device_type fsl_mc_bus_dprc_type; diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 8a8cb3c401b2..9141f2263286 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -499,7 +499,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } /** * ftrace_make_nop - convert code into nop * @mod: module structure if called by module load initialization - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should be calling * * This is a very sensitive operation and great care needs @@ -520,9 +520,38 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; } extern int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr); + +/** + * ftrace_init_nop - initialize a nop call site + * @mod: module structure if called by module load initialization + * @rec: the call site record (e.g. mcount/fentry) + * + * This is a very sensitive operation and great care needs + * to be taken by the arch. The operation should carefully + * read the location, check to see if what is read is indeed + * what we expect it to be, and then on success of the compare, + * it should write to the location. + * + * The code segment at @rec->ip should contain the contents created by + * the compiler + * + * Return must be: + * 0 on success + * -EFAULT on error reading the location + * -EINVAL on a failed compare of the contents + * -EPERM on error writing to the location + * Any other value will be considered a failure. + */ +#ifndef ftrace_init_nop +static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + return ftrace_make_nop(mod, rec, MCOUNT_ADDR); +} +#endif + /** * ftrace_make_call - convert a nop call site into a call to addr - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @addr: the address that the call site should call * * This is a very sensitive operation and great care needs @@ -545,7 +574,7 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS /** * ftrace_modify_call - convert from one addr to another (no nop) - * @rec: the mcount call site record + * @rec: the call site record (e.g. mcount/fentry) * @old_addr: the address expected to be currently called to * @addr: the address to change to * @@ -709,6 +738,11 @@ static inline unsigned long get_lock_parent_ip(void) #ifdef CONFIG_FTRACE_MCOUNT_RECORD extern void ftrace_init(void); +#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY +#define FTRACE_CALLSITE_SECTION "__patchable_function_entries" +#else +#define FTRACE_CALLSITE_SECTION "__mcount_loc" +#endif #else static inline void ftrace_init(void) { } #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 8b5330dd5ac0..8bb63027e4d6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -621,9 +621,10 @@ extern void blk_invalidate_devt(dev_t devt); extern dev_t blk_lookup_devt(const char *name, int partno); extern char *disk_name (struct gendisk *hd, int partno, char *buf); +int bdev_disk_changed(struct block_device *bdev, bool invalidate); +int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int blk_drop_partitions(struct gendisk *disk, struct block_device *bdev); extern int disk_expand_part_tbl(struct gendisk *disk, int target); -extern int rescan_partitions(struct gendisk *disk, struct block_device *bdev); -extern int invalidate_partitions(struct gendisk *disk, struct block_device *bdev); extern struct hd_struct * __must_check add_partition(struct gendisk *disk, int partno, sector_t start, sector_t len, int flags, diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index b70af921c614..5215fdba6b9a 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -176,11 +176,15 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, const char *propname, int index, enum gpiod_flags dflags, const char *label); -struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, - const char *con_id, int index, - struct fwnode_handle *child, - enum gpiod_flags flags, - const char *label); +struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label); +struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, + struct fwnode_handle *child, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label); #else /* CONFIG_GPIOLIB */ @@ -532,17 +536,48 @@ struct gpio_desc *fwnode_get_named_gpiod(struct fwnode_handle *fwnode, } static inline +struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + +static inline +struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev, + struct fwnode_handle *fwnode, + const char *con_id, int index, + enum gpiod_flags flags, + const char *label) +{ + return ERR_PTR(-ENOSYS); +} + +#endif /* CONFIG_GPIOLIB */ + +static inline +struct gpio_desc *devm_fwnode_gpiod_get(struct device *dev, + struct fwnode_handle *fwnode, + const char *con_id, + enum gpiod_flags flags, + const char *label) +{ + return devm_fwnode_gpiod_get_index(dev, fwnode, con_id, 0, + flags, label); +} + +static inline struct gpio_desc *devm_fwnode_get_index_gpiod_from_child(struct device *dev, const char *con_id, int index, struct fwnode_handle *child, enum gpiod_flags flags, const char *label) { - return ERR_PTR(-ENOSYS); + return devm_fwnode_gpiod_get_index(dev, child, con_id, index, + flags, label); } -#endif /* CONFIG_GPIOLIB */ - static inline struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, const char *con_id, @@ -550,8 +585,7 @@ struct gpio_desc *devm_fwnode_get_gpiod_from_child(struct device *dev, enum gpiod_flags flags, const char *label) { - return devm_fwnode_get_index_gpiod_from_child(dev, con_id, 0, child, - flags, label); + return devm_fwnode_gpiod_get_index(dev, child, con_id, 0, flags, label); } #if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_OF_GPIO) diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 2d8aaf7d4b9e..81ca84ce3119 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -20,4 +20,19 @@ static inline struct icmphdr *icmp_hdr(const struct sk_buff *skb) { return (struct icmphdr *)skb_transport_header(skb); } + +static inline bool icmp_is_err(int type) +{ + switch (type) { + case ICMP_DEST_UNREACH: + case ICMP_SOURCE_QUENCH: + case ICMP_REDIRECT: + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + return true; + } + + return false; +} + #endif /* _LINUX_ICMP_H */ diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index a8f888976137..ef1cbb5f454f 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -46,4 +46,18 @@ extern void icmpv6_flow_init(struct sock *sk, const struct in6_addr *saddr, const struct in6_addr *daddr, int oif); + +static inline bool icmpv6_is_err(int type) +{ + switch (type) { + case ICMPV6_DEST_UNREACH: + case ICMPV6_PKT_TOOBIG: + case ICMPV6_TIME_EXCEED: + case ICMPV6_PARAMPROB: + return true; + } + + return false; +} + #endif diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 5cc10cf7cb3e..a0bde9e12efa 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -487,6 +487,8 @@ #define ICC_CTLR_EL1_EOImode_MASK (1 << ICC_CTLR_EL1_EOImode_SHIFT) #define ICC_CTLR_EL1_CBPR_SHIFT 0 #define ICC_CTLR_EL1_CBPR_MASK (1 << ICC_CTLR_EL1_CBPR_SHIFT) +#define ICC_CTLR_EL1_PMHE_SHIFT 6 +#define ICC_CTLR_EL1_PMHE_MASK (1 << ICC_CTLR_EL1_PMHE_SHIFT) #define ICC_CTLR_EL1_PRI_BITS_SHIFT 8 #define ICC_CTLR_EL1_PRI_BITS_MASK (0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT) #define ICC_CTLR_EL1_ID_BITS_SHIFT 11 diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h index e6b155713b47..5dbcfc65f21e 100644 --- a/include/linux/irqchip/arm-gic-v4.h +++ b/include/linux/irqchip/arm-gic-v4.h @@ -32,9 +32,13 @@ struct its_vm { struct its_vpe { struct page *vpt_page; struct its_vm *its_vm; + /* per-vPE VLPI tracking */ + atomic_t vlpi_count; /* Doorbell interrupt */ int irq; irq_hw_number_t vpe_db_lpi; + /* VPE resident */ + bool resident; /* VPE proxy mapping */ int vpe_proxy_event; /* diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 936b61bd504e..dded2e5a9f42 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -104,21 +104,6 @@ struct kernfs_elem_attr { struct kernfs_node *notify_next; /* for kernfs_notify() */ }; -/* represent a kernfs node */ -union kernfs_node_id { - struct { - /* - * blktrace will export this struct as a simplified 'struct - * fid' (which is a big data struction), so userspace can use - * it to find kernfs node. The layout must match the first two - * fields of 'struct fid' exactly. - */ - u32 ino; - u32 generation; - }; - u64 id; -}; - /* * kernfs_node - the building block of kernfs hierarchy. Each and every * kernfs node is represented by single kernfs_node. Most fields are @@ -155,7 +140,12 @@ struct kernfs_node { void *priv; - union kernfs_node_id id; + /* + * 64bit unique ID. On 64bit ino setups, id is the ino. On 32bit, + * the low 32bits are ino and upper generation. + */ + u64 id; + unsigned short flags; umode_t mode; struct kernfs_iattrs *iattr; @@ -187,7 +177,8 @@ struct kernfs_root { /* private fields, do not use outside kernfs proper */ struct idr ino_idr; - u32 next_generation; + u32 last_id_lowbits; + u32 id_highbits; struct kernfs_syscall_ops *syscall_ops; /* list of kernfs_super_info of this root, protected by kernfs_mutex */ @@ -291,6 +282,34 @@ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) return kn->flags & KERNFS_TYPE_MASK; } +static inline ino_t kernfs_id_ino(u64 id) +{ + /* id is ino if ino_t is 64bit; otherwise, low 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return id; + else + return (u32)id; +} + +static inline u32 kernfs_id_gen(u64 id) +{ + /* gen is fixed at 1 if ino_t is 64bit; otherwise, high 32bits */ + if (sizeof(ino_t) >= sizeof(u64)) + return 1; + else + return id >> 32; +} + +static inline ino_t kernfs_ino(struct kernfs_node *kn) +{ + return kernfs_id_ino(kn->id); +} + +static inline ino_t kernfs_gen(struct kernfs_node *kn) +{ + return kernfs_id_gen(kn->id); +} + /** * kernfs_enable_ns - enable namespace under a directory * @kn: directory of interest, should be empty @@ -382,8 +401,8 @@ void kernfs_kill_sb(struct super_block *sb); void kernfs_init(void); -struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root, - const union kernfs_node_id *id); +struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, + u64 id); #else /* CONFIG_KERNFS */ static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index d41c521a39da..7ed1e2f8641e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -266,7 +266,8 @@ struct kvm_vcpu { struct preempt_notifier preempt_notifier; #endif int cpu; - int vcpu_id; + int vcpu_id; /* id given by userspace at creation */ + int vcpu_idx; /* index in kvm->vcpus array */ int srcu_idx; int mode; u64 requests; @@ -278,7 +279,6 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - int guest_xcr0_loaded; struct swait_queue_head wq; struct pid __rcu *pid; int sigset_active; @@ -571,13 +571,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) { - struct kvm_vcpu *tmp; - int idx; - - kvm_for_each_vcpu(idx, tmp, vcpu->kvm) - if (tmp == vcpu) - return idx; - BUG(); + return vcpu->vcpu_idx; } #define kvm_for_each_memslot(memslot, slots) \ @@ -622,6 +616,7 @@ void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); +void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { @@ -746,6 +741,28 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); + +#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + type __user *__uaddr = (type __user *)(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = put_user(value, __uaddr); \ + if (!__ret) \ + mark_page_dirty(kvm, gfn); \ + __ret; \ +}) + +#define kvm_put_guest(kvm, gpa, value, type) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), (value), type); \ +}) + int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); @@ -791,6 +808,8 @@ void kvm_reload_remote_mmus(struct kvm *kvm); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap); long kvm_arch_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg); @@ -1241,7 +1260,7 @@ extern unsigned int halt_poll_ns_grow_start; extern unsigned int halt_poll_ns_shrink; struct kvm_device { - struct kvm_device_ops *ops; + const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; @@ -1294,7 +1313,7 @@ struct kvm_device_ops { void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type); +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type); extern struct kvm_device_ops kvm_mpic_ops; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index bde5374ae021..1c88e69db3d9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -35,6 +35,8 @@ typedef unsigned long gva_t; typedef u64 gpa_t; typedef u64 gfn_t; +#define GPA_INVALID (~(gpa_t)0) + typedef unsigned long hva_t; typedef u64 hpa_t; typedef u64 hfn_t; diff --git a/include/linux/libata.h b/include/linux/libata.h index 207e7ee764ce..d3bbfddf616a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -484,6 +484,7 @@ enum hsm_task_states { }; enum ata_completion_errors { + AC_ERR_OK = 0, /* no error */ AC_ERR_DEV = (1 << 0), /* device reported error */ AC_ERR_HSM = (1 << 1), /* host state machine violation */ AC_ERR_TIMEOUT = (1 << 2), /* timeout */ @@ -891,9 +892,9 @@ struct ata_port_operations { /* * Command execution */ - int (*qc_defer)(struct ata_queued_cmd *qc); - int (*check_atapi_dma)(struct ata_queued_cmd *qc); - void (*qc_prep)(struct ata_queued_cmd *qc); + int (*qc_defer)(struct ata_queued_cmd *qc); + int (*check_atapi_dma)(struct ata_queued_cmd *qc); + enum ata_completion_errors (*qc_prep)(struct ata_queued_cmd *qc); unsigned int (*qc_issue)(struct ata_queued_cmd *qc); bool (*qc_fill_rtf)(struct ata_queued_cmd *qc); @@ -1161,7 +1162,7 @@ extern int ata_xfer_mode2shift(unsigned long xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); -extern void ata_noop_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); @@ -1893,9 +1894,9 @@ extern const struct ata_port_operations ata_bmdma_port_ops; .sg_tablesize = LIBATA_MAX_PRD, \ .dma_boundary = ATA_DMA_BOUNDARY -extern void ata_bmdma_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_qc_issue(struct ata_queued_cmd *qc); -extern void ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); +extern enum ata_completion_errors ata_bmdma_dumb_qc_prep(struct ata_queued_cmd *qc); extern unsigned int ata_bmdma_port_intr(struct ata_port *ap, struct ata_queued_cmd *qc); extern irqreturn_t ata_bmdma_interrupt(int irq, void *dev_instance); diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index a99c58866860..fe740031339d 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -82,4 +82,10 @@ static inline int linkmode_equal(const unsigned long *src1, return bitmap_equal(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline int linkmode_subset(const unsigned long *src1, + const unsigned long *src2) +{ + return bitmap_subset(src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); +} + #endif /* __LINKMODE_H */ diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 273400814020..e894e74905f3 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -131,9 +131,22 @@ struct klp_object { }; /** + * struct klp_state - state of the system modified by the livepatch + * @id: system state identifier (non-zero) + * @version: version of the change + * @data: custom data + */ +struct klp_state { + unsigned long id; + unsigned int version; + void *data; +}; + +/** * struct klp_patch - patch structure for live patching * @mod: reference to the live patch module * @objs: object entries for kernel objects to be patched + * @states: system states that can get modified * @replace: replace all actively used patches * @list: list node for global list of actively used patches * @kobj: kobject for sysfs resources @@ -147,6 +160,7 @@ struct klp_patch { /* external */ struct module *mod; struct klp_object *objs; + struct klp_state *states; bool replace; /* internal */ @@ -217,6 +231,9 @@ void *klp_shadow_get_or_alloc(void *obj, unsigned long id, void klp_shadow_free(void *obj, unsigned long id, klp_shadow_dtor_t dtor); void klp_shadow_free_all(unsigned long id, klp_shadow_dtor_t dtor); +struct klp_state *klp_get_state(struct klp_patch *patch, unsigned long id); +struct klp_state *klp_get_prev_state(unsigned long id); + #else /* !CONFIG_LIVEPATCH */ static inline int klp_module_coming(struct module *mod) { return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3e80f03a387f..1884513aac90 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1121,6 +1121,11 @@ static inline bool mlx5_core_is_pf(const struct mlx5_core_dev *dev) return dev->coredev_type == MLX5_COREDEV_PF; } +static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev) +{ + return dev->coredev_type == MLX5_COREDEV_VF; +} + static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) { return dev->caps.embedded_cpu; @@ -1186,4 +1191,15 @@ enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; +static inline bool mlx5_is_roce_enabled(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + + devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return val.vbool; +} + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 724d276ea133..4e5b84e66822 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -80,7 +80,8 @@ enum mlx5_flow_namespace_type { enum { FDB_BYPASS_PATH, - FDB_FAST_PATH, + FDB_TC_OFFLOAD, + FDB_FT_OFFLOAD, FDB_SLOW_PATH, }; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 0836fe232f97..5d54fccf87fc 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1110,6 +1110,7 @@ enum { }; enum { + MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, @@ -1153,7 +1154,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_srq[0x5]; u8 reserved_at_b0[0x10]; - u8 reserved_at_c0[0x8]; + u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; u8 reserved_at_d0[0xb]; u8 log_max_cq[0x5]; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index bda20282746b..b0a36d1580b6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -359,33 +359,40 @@ struct per_cpu_nodestat { #endif /* !__GENERATING_BOUNDS.H */ enum zone_type { -#ifdef CONFIG_ZONE_DMA /* - * ZONE_DMA is used when there are devices that are not able - * to do DMA to all of addressable memory (ZONE_NORMAL). Then we - * carve out the portion of memory that is needed for these devices. - * The range is arch specific. + * ZONE_DMA and ZONE_DMA32 are used when there are peripherals not able + * to DMA to all of the addressable memory (ZONE_NORMAL). + * On architectures where this area covers the whole 32 bit address + * space ZONE_DMA32 is used. ZONE_DMA is left for the ones with smaller + * DMA addressing constraints. This distinction is important as a 32bit + * DMA mask is assumed when ZONE_DMA32 is defined. Some 64-bit + * platforms may need both zones as they support peripherals with + * different DMA addressing limitations. + * + * Some examples: + * + * - i386 and x86_64 have a fixed 16M ZONE_DMA and ZONE_DMA32 for the + * rest of the lower 4G. + * + * - arm only uses ZONE_DMA, the size, up to 4G, may vary depending on + * the specific device. + * + * - arm64 has a fixed 1G ZONE_DMA and ZONE_DMA32 for the rest of the + * lower 4G. * - * Some examples + * - powerpc only uses ZONE_DMA, the size, up to 2G, may vary + * depending on the specific device. * - * Architecture Limit - * --------------------------- - * parisc, ia64, sparc <4G - * s390, powerpc <2G - * arm Various - * alpha Unlimited or 0-16MB. + * - s390 uses ZONE_DMA fixed to the lower 2G. * - * i386, x86_64 and multiple other arches - * <16M. + * - ia64 and riscv only use ZONE_DMA32. + * + * - parisc uses neither. */ +#ifdef CONFIG_ZONE_DMA ZONE_DMA, #endif #ifdef CONFIG_ZONE_DMA32 - /* - * x86_64 needs two ZONE_DMAs because it supports devices that are - * only able to do DMA to the lower 16M but also 32 bit devices that - * can only do DMA areas below 4G. - */ ZONE_DMA32, #endif /* diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 34de06b426ef..8071148f29a6 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -47,16 +47,16 @@ struct vif_entry_notifier_info { }; static inline int mr_call_vif_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, struct vif_device *vif, - unsigned short vif_index, u32 tb_id) + unsigned short vif_index, u32 tb_id, + struct netlink_ext_ack *extack) { struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, + .extack = extack, }, .dev = vif->dev, .vif_index = vif_index, @@ -64,7 +64,7 @@ static inline int mr_call_vif_notifier(struct notifier_block *nb, .tb_id = tb_id, }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_vif_notifiers(struct net *net, @@ -77,7 +77,6 @@ static inline int mr_call_vif_notifiers(struct net *net, struct vif_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .dev = vif->dev, .vif_index = vif_index, @@ -173,21 +172,21 @@ struct mfc_entry_notifier_info { }; static inline int mr_call_mfc_notifier(struct notifier_block *nb, - struct net *net, unsigned short family, enum fib_event_type event_type, - struct mr_mfc *mfc, u32 tb_id) + struct mr_mfc *mfc, u32 tb_id, + struct netlink_ext_ack *extack) { struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, + .extack = extack, }, .mfc = mfc, .tb_id = tb_id }; - return call_fib_notifier(nb, net, event_type, &info.info); + return call_fib_notifier(nb, event_type, &info.info); } static inline int mr_call_mfc_notifiers(struct net *net, @@ -199,7 +198,6 @@ static inline int mr_call_mfc_notifiers(struct net *net, struct mfc_entry_notifier_info info = { .info = { .family = family, - .net = net, }, .mfc = mfc, .tb_id = tb_id @@ -301,10 +299,11 @@ int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock); + rwlock_t *mrt_lock, struct netlink_ext_ack *extack); #else static inline void vif_device_init(struct vif_device *v, struct net_device *dev, @@ -355,10 +354,11 @@ mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, static inline int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, struct netlink_ext_ack *extack) { return -EINVAL; } diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index fc0b4b19c900..5a4623fc586b 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -22,6 +22,7 @@ #define SNOR_MFR_INTEL CFI_MFR_INTEL #define SNOR_MFR_ST CFI_MFR_ST /* ST Micro */ #define SNOR_MFR_MICRON CFI_MFR_MICRON /* Micron */ +#define SNOR_MFR_ISSI CFI_MFR_PMC #define SNOR_MFR_MACRONIX CFI_MFR_MACRONIX #define SNOR_MFR_SPANSION CFI_MFR_AMD #define SNOR_MFR_SST CFI_MFR_SST @@ -133,7 +134,7 @@ #define SR_E_ERR BIT(5) #define SR_P_ERR BIT(6) -#define SR_QUAD_EN_MX BIT(6) /* Macronix Quad I/O */ +#define SR1_QUAD_EN_BIT6 BIT(6) /* Enhanced Volatile Configuration Register bits */ #define EVCR_QUAD_EN_MICRON BIT(7) /* Micron Quad I/O */ @@ -144,10 +145,8 @@ #define FSR_P_ERR BIT(4) /* Program operation status */ #define FSR_PT_ERR BIT(1) /* Protection error bit */ -/* Configuration Register bits. */ -#define CR_QUAD_EN_SPAN BIT(1) /* Spansion Quad I/O */ - /* Status Register 2 bits. */ +#define SR2_QUAD_EN_BIT1 BIT(1) #define SR2_QUAD_EN_BIT7 BIT(7) /* Supported SPI protocols */ @@ -243,6 +242,9 @@ enum spi_nor_option_flags { SNOR_F_4B_OPCODES = BIT(6), SNOR_F_HAS_4BAIT = BIT(7), SNOR_F_HAS_LOCK = BIT(8), + SNOR_F_HAS_16BIT_SR = BIT(9), + SNOR_F_NO_READ_CR = BIT(10), + }; /** @@ -466,6 +468,34 @@ enum spi_nor_pp_command_index { struct spi_nor; /** + * struct spi_nor_controller_ops - SPI NOR controller driver specific + * operations. + * @prepare: [OPTIONAL] do some preparations for the + * read/write/erase/lock/unlock operations. + * @unprepare: [OPTIONAL] do some post work after the + * read/write/erase/lock/unlock operations. + * @read_reg: read out the register. + * @write_reg: write data to the register. + * @read: read data from the SPI NOR. + * @write: write data to the SPI NOR. + * @erase: erase a sector of the SPI NOR at the offset @offs; if + * not provided by the driver, spi-nor will send the erase + * opcode via write_reg(). + */ +struct spi_nor_controller_ops { + int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); + void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); + int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, size_t len); + int (*write_reg)(struct spi_nor *nor, u8 opcode, const u8 *buf, + size_t len); + + ssize_t (*read)(struct spi_nor *nor, loff_t from, size_t len, u8 *buf); + ssize_t (*write)(struct spi_nor *nor, loff_t to, size_t len, + const u8 *buf); + int (*erase)(struct spi_nor *nor, loff_t offs); +}; + +/** * struct spi_nor_locking_ops - SPI NOR locking methods * @lock: lock a region of the SPI NOR. * @unlock: unlock a region of the SPI NOR. @@ -549,19 +579,7 @@ struct flash_info; * @read_proto: the SPI protocol for read operations * @write_proto: the SPI protocol for write operations * @reg_proto the SPI protocol for read_reg/write_reg/erase operations - * @prepare: [OPTIONAL] do some preparations for the - * read/write/erase/lock/unlock operations - * @unprepare: [OPTIONAL] do some post work after the - * read/write/erase/lock/unlock operations - * @read_reg: [DRIVER-SPECIFIC] read out the register - * @write_reg: [DRIVER-SPECIFIC] write data to the register - * @read: [DRIVER-SPECIFIC] read data from the SPI NOR - * @write: [DRIVER-SPECIFIC] write data to the SPI NOR - * @erase: [DRIVER-SPECIFIC] erase a sector of the SPI NOR - * at the offset @offs; if not provided by the driver, - * spi-nor will send the erase opcode via write_reg() - * @clear_sr_bp: [FLASH-SPECIFIC] clears the Block Protection Bits from - * the SPI NOR Status Register. + * @controller_ops: SPI NOR controller driver specific operations. * @params: [FLASH-SPECIFIC] SPI-NOR flash parameters and settings. * The structure includes legacy flash parameters and * settings that can be overwritten by the spi_nor_fixups @@ -588,18 +606,8 @@ struct spi_nor { bool sst_write_second; u32 flags; - int (*prepare)(struct spi_nor *nor, enum spi_nor_ops ops); - void (*unprepare)(struct spi_nor *nor, enum spi_nor_ops ops); - int (*read_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - int (*write_reg)(struct spi_nor *nor, u8 opcode, u8 *buf, int len); - - ssize_t (*read)(struct spi_nor *nor, loff_t from, - size_t len, u_char *read_buf); - ssize_t (*write)(struct spi_nor *nor, loff_t to, - size_t len, const u_char *write_buf); - int (*erase)(struct spi_nor *nor, loff_t offs); + const struct spi_nor_controller_ops *controller_ops; - int (*clear_sr_bp)(struct spi_nor *nor); struct spi_nor_flash_parameter params; void *priv; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c20f190b4c18..9e6fb8524d91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -848,6 +848,7 @@ enum tc_setup_type { TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, + TC_SETUP_FT, }; /* These structures hold the attributes of bpf state that are being passed @@ -925,6 +926,15 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; +struct netdev_name_node { + struct hlist_node hlist; + struct list_head list; + struct net_device *dev; + const char *name; +}; + +int netdev_name_node_alt_create(struct net_device *dev, const char *name); +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); /* * This structure defines the management hooks for network devices. @@ -1564,7 +1574,7 @@ enum netdev_priv_flags { * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * - * @name_hlist: Device name hash chain, please keep it close to name[] + * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start @@ -1780,7 +1790,7 @@ enum netdev_priv_flags { struct net_device { char name[IFNAMSIZ]; - struct hlist_node name_hlist; + struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields @@ -2387,11 +2397,23 @@ struct pcpu_sw_netstats { } __aligned(4 * sizeof(u64)); struct pcpu_lstats { - u64 packets; - u64 bytes; + u64_stats_t packets; + u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); +void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); + +static inline void dev_lstats_add(struct net_device *dev, unsigned int len) +{ + struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); + + u64_stats_update_begin(&lstats->syncp); + u64_stats_add(&lstats->bytes, len); + u64_stats_inc(&lstats->packets); + u64_stats_update_end(&lstats->syncp); +} + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ @@ -2487,6 +2509,9 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb); struct netdev_notifier_info { struct net_device *dev; @@ -2557,6 +2582,9 @@ extern rwlock_t dev_base_lock; /* Device list lock */ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) +#define for_each_netdev_continue_reverse(net, d) \ + list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ + dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ @@ -4081,9 +4109,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); -int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name); - #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 77ebb61faf48..eb312e7ca36e 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -199,6 +199,8 @@ extern struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int i); +void nf_hook_slow_list(struct list_head *head, struct nf_hook_state *state, + const struct nf_hook_entries *e); /** * nf_hook - call a netfilter hook * @@ -311,17 +313,36 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct list_head *head, struct net_device *in, struct net_device *out, int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - struct sk_buff *skb, *next; - struct list_head sublist; - - INIT_LIST_HEAD(&sublist); - list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1) - list_add_tail(&skb->list, &sublist); + struct nf_hook_entries *hook_head = NULL; + +#ifdef CONFIG_JUMP_LABEL + if (__builtin_constant_p(pf) && + __builtin_constant_p(hook) && + !static_key_false(&nf_hooks_needed[pf][hook])) + return; +#endif + + rcu_read_lock(); + switch (pf) { + case NFPROTO_IPV4: + hook_head = rcu_dereference(net->nf.hooks_ipv4[hook]); + break; + case NFPROTO_IPV6: + hook_head = rcu_dereference(net->nf.hooks_ipv6[hook]); + break; + default: + WARN_ON_ONCE(1); + break; } - /* Put passed packets back on main list */ - list_splice(&sublist, head); + + if (hook_head) { + struct nf_hook_state state; + + nf_hook_state_init(&state, hook, pf, in, out, sk, net, okfn); + + nf_hook_slow_list(head, &state, hook_head); + } + rcu_read_unlock(); } /* Call setsockopt() */ diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 9bc255a8461b..4d8b1eaf7708 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -269,34 +269,15 @@ ip_set_ext_destroy(struct ip_set *set, void *data) /* Check that the extension is enabled for the set and * call it's destroy function for its extension part in data. */ - if (SET_WITH_COMMENT(set)) - ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy( - set, ext_comment(data, set)); -} + if (SET_WITH_COMMENT(set)) { + struct ip_set_comment *c = ext_comment(data, set); -static inline int -ip_set_put_flags(struct sk_buff *skb, struct ip_set *set) -{ - u32 cadt_flags = 0; - - if (SET_WITH_TIMEOUT(set)) - if (unlikely(nla_put_net32(skb, IPSET_ATTR_TIMEOUT, - htonl(set->timeout)))) - return -EMSGSIZE; - if (SET_WITH_COUNTER(set)) - cadt_flags |= IPSET_FLAG_WITH_COUNTERS; - if (SET_WITH_COMMENT(set)) - cadt_flags |= IPSET_FLAG_WITH_COMMENT; - if (SET_WITH_SKBINFO(set)) - cadt_flags |= IPSET_FLAG_WITH_SKBINFO; - if (SET_WITH_FORCEADD(set)) - cadt_flags |= IPSET_FLAG_WITH_FORCEADD; - - if (!cadt_flags) - return 0; - return nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(cadt_flags)); + ip_set_extensions[IPSET_EXT_ID_COMMENT].destroy(set, c); + } } +int ip_set_put_flags(struct sk_buff *skb, struct ip_set *set); + /* Netlink CB args */ enum { IPSET_CB_NET = 0, /* net namespace */ @@ -506,144 +487,8 @@ ip_set_timeout_set(unsigned long *timeout, u32 value) *timeout = t; } -static inline u32 -ip_set_timeout_get(const unsigned long *timeout) -{ - u32 t; - - if (*timeout == IPSET_ELEM_PERMANENT) - return 0; - - t = jiffies_to_msecs(*timeout - jiffies)/MSEC_PER_SEC; - /* Zero value in userspace means no timeout */ - return t == 0 ? 1 : t; -} - -static inline char* -ip_set_comment_uget(struct nlattr *tb) -{ - return nla_data(tb); -} - -/* Called from uadd only, protected by the set spinlock. - * The kadt functions don't use the comment extensions in any way. - */ -static inline void -ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, - const struct ip_set_ext *ext) -{ - struct ip_set_comment_rcu *c = rcu_dereference_protected(comment->c, 1); - size_t len = ext->comment ? strlen(ext->comment) : 0; - - if (unlikely(c)) { - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); - } - if (!len) - return; - if (unlikely(len > IPSET_MAX_COMMENT_SIZE)) - len = IPSET_MAX_COMMENT_SIZE; - c = kmalloc(sizeof(*c) + len + 1, GFP_ATOMIC); - if (unlikely(!c)) - return; - strlcpy(c->str, ext->comment, len + 1); - set->ext_size += sizeof(*c) + strlen(c->str) + 1; - rcu_assign_pointer(comment->c, c); -} - -/* Used only when dumping a set, protected by rcu_read_lock() */ -static inline int -ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c = rcu_dereference(comment->c); - - if (!c) - return 0; - return nla_put_string(skb, IPSET_ATTR_COMMENT, c->str); -} - -/* Called from uadd/udel, flush or the garbage collectors protected - * by the set spinlock. - * Called when the set is destroyed and when there can't be any user - * of the set data anymore. - */ -static inline void -ip_set_comment_free(struct ip_set *set, struct ip_set_comment *comment) -{ - struct ip_set_comment_rcu *c; - - c = rcu_dereference_protected(comment->c, 1); - if (unlikely(!c)) - return; - set->ext_size -= sizeof(*c) + strlen(c->str) + 1; - kfree_rcu(c, rcu); - rcu_assign_pointer(comment->c, NULL); -} - -static inline void -ip_set_add_bytes(u64 bytes, struct ip_set_counter *counter) -{ - atomic64_add((long long)bytes, &(counter)->bytes); -} - -static inline void -ip_set_add_packets(u64 packets, struct ip_set_counter *counter) -{ - atomic64_add((long long)packets, &(counter)->packets); -} - -static inline u64 -ip_set_get_bytes(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->bytes); -} - -static inline u64 -ip_set_get_packets(const struct ip_set_counter *counter) -{ - return (u64)atomic64_read(&(counter)->packets); -} - -static inline bool -ip_set_match_counter(u64 counter, u64 match, u8 op) -{ - switch (op) { - case IPSET_COUNTER_NONE: - return true; - case IPSET_COUNTER_EQ: - return counter == match; - case IPSET_COUNTER_NE: - return counter != match; - case IPSET_COUNTER_LT: - return counter < match; - case IPSET_COUNTER_GT: - return counter > match; - } - return false; -} - -static inline void -ip_set_update_counter(struct ip_set_counter *counter, - const struct ip_set_ext *ext, u32 flags) -{ - if (ext->packets != ULLONG_MAX && - !(flags & IPSET_FLAG_SKIP_COUNTER_UPDATE)) { - ip_set_add_bytes(ext->bytes, counter); - ip_set_add_packets(ext->packets, counter); - } -} - -static inline bool -ip_set_put_counter(struct sk_buff *skb, const struct ip_set_counter *counter) -{ - return nla_put_net64(skb, IPSET_ATTR_BYTES, - cpu_to_be64(ip_set_get_bytes(counter)), - IPSET_ATTR_PAD) || - nla_put_net64(skb, IPSET_ATTR_PACKETS, - cpu_to_be64(ip_set_get_packets(counter)), - IPSET_ATTR_PAD); -} +void ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, + const struct ip_set_ext *ext); static inline void ip_set_init_counter(struct ip_set_counter *counter, @@ -656,31 +501,6 @@ ip_set_init_counter(struct ip_set_counter *counter, } static inline void -ip_set_get_skbinfo(struct ip_set_skbinfo *skbinfo, - const struct ip_set_ext *ext, - struct ip_set_ext *mext, u32 flags) -{ - mext->skbinfo = *skbinfo; -} - -static inline bool -ip_set_put_skbinfo(struct sk_buff *skb, const struct ip_set_skbinfo *skbinfo) -{ - /* Send nonzero parameters only */ - return ((skbinfo->skbmark || skbinfo->skbmarkmask) && - nla_put_net64(skb, IPSET_ATTR_SKBMARK, - cpu_to_be64((u64)skbinfo->skbmark << 32 | - skbinfo->skbmarkmask), - IPSET_ATTR_PAD)) || - (skbinfo->skbprio && - nla_put_net32(skb, IPSET_ATTR_SKBPRIO, - cpu_to_be32(skbinfo->skbprio))) || - (skbinfo->skbqueue && - nla_put_net16(skb, IPSET_ATTR_SKBQUEUE, - cpu_to_be16(skbinfo->skbqueue))); -} - -static inline void ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, const struct ip_set_ext *ext) { diff --git a/include/linux/netfilter/ipset/ip_set_bitmap.h b/include/linux/netfilter/ipset/ip_set_bitmap.h index 2dddbc6dcac7..fcc4d214a788 100644 --- a/include/linux/netfilter/ipset/ip_set_bitmap.h +++ b/include/linux/netfilter/ipset/ip_set_bitmap.h @@ -12,18 +12,4 @@ enum { IPSET_ADD_START_STORED_TIMEOUT, }; -/* Common functions */ - -static inline u32 -range_to_mask(u32 from, u32 to, u8 *bits) -{ - u32 mask = 0xFFFFFFFE; - - *bits = 32; - while (--(*bits) > 0 && mask && (to & mask) != from) - mask <<= 1; - - return mask; -} - #endif /* __IP_SET_BITMAP_H */ diff --git a/include/linux/netfilter/ipset/ip_set_getport.h b/include/linux/netfilter/ipset/ip_set_getport.h index d74cd112b88a..1ecaabd9a048 100644 --- a/include/linux/netfilter/ipset/ip_set_getport.h +++ b/include/linux/netfilter/ipset/ip_set_getport.h @@ -20,9 +20,6 @@ static inline bool ip_set_get_ip6_port(const struct sk_buff *skb, bool src, } #endif -extern bool ip_set_get_ip_port(const struct sk_buff *skb, u8 pf, bool src, - __be16 *port); - static inline bool ip_set_proto_with_ports(u8 proto) { switch (proto) { diff --git a/include/linux/nvme-fc.h b/include/linux/nvme-fc.h index 067c9fea64fe..e8c30b39bb27 100644 --- a/include/linux/nvme-fc.h +++ b/include/linux/nvme-fc.h @@ -4,33 +4,60 @@ */ /* - * This file contains definitions relative to FC-NVME r1.14 (16-020vB). - * The fcnvme_lsdesc_cr_assoc_cmd struct reflects expected r1.16 content. + * This file contains definitions relative to FC-NVME-2 r1.06 + * (T11-2019-00210-v001). */ #ifndef _NVME_FC_H #define _NVME_FC_H 1 +#include <uapi/scsi/fc/fc_fs.h> -#define NVME_CMD_SCSI_ID 0xFD +#define NVME_CMD_FORMAT_ID 0xFD #define NVME_CMD_FC_ID FC_TYPE_NVME /* FC-NVME Cmd IU Flags */ -#define FCNVME_CMD_FLAGS_DIRMASK 0x03 -#define FCNVME_CMD_FLAGS_WRITE 0x01 -#define FCNVME_CMD_FLAGS_READ 0x02 +enum { + FCNVME_CMD_FLAGS_DIRMASK = 0x03, + FCNVME_CMD_FLAGS_WRITE = (1 << 0), + FCNVME_CMD_FLAGS_READ = (1 << 1), + + FCNVME_CMD_FLAGS_PICWP = (1 << 2), +}; + +enum { + FCNVME_CMD_CAT_MASK = 0x0F, + FCNVME_CMD_CAT_ADMINQ = 0x01, + FCNVME_CMD_CAT_CSSMASK = 0x07, + FCNVME_CMD_CAT_CSSFLAG = 0x08, +}; + +static inline __u8 fccmnd_set_cat_admin(__u8 rsv_cat) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_ADMINQ; +} + +static inline __u8 fccmnd_set_cat_css(__u8 rsv_cat, __u8 css) +{ + return (rsv_cat & ~FCNVME_CMD_CAT_MASK) | FCNVME_CMD_CAT_CSSFLAG | + (css & FCNVME_CMD_CAT_CSSMASK); +} struct nvme_fc_cmd_iu { - __u8 scsi_id; + __u8 format_id; __u8 fc_id; __be16 iu_len; - __u8 rsvd4[3]; + __u8 rsvd4[2]; + __u8 rsv_cat; __u8 flags; __be64 connection_id; __be32 csn; __be32 data_len; struct nvme_command sqe; - __be32 rsvd88[2]; + __u8 dps; + __u8 lbads; + __be16 ms; + __be32 rsvd92; }; #define NVME_FC_SIZEOF_ZEROS_RSP 12 @@ -38,11 +65,12 @@ struct nvme_fc_cmd_iu { enum { FCNVME_SC_SUCCESS = 0, FCNVME_SC_INVALID_FIELD = 1, - FCNVME_SC_INVALID_CONNID = 2, + /* reserved 2 */ + FCNVME_SC_ILL_CONN_PARAMS = 3, }; struct nvme_fc_ersp_iu { - __u8 status_code; + __u8 ersp_result; __u8 rsvd1; __be16 iu_len; __be32 rsn; @@ -53,14 +81,44 @@ struct nvme_fc_ersp_iu { }; -/* FC-NVME Link Services */ +#define FCNVME_NVME_SR_OPCODE 0x01 + +struct nvme_fc_nvme_sr_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 retry_rctl; + __be32 rsvd4; +}; + + +enum { + FCNVME_SRSTAT_ACC = 0x0, + FCNVME_SRSTAT_INV_FCID = 0x1, + /* reserved 0x2 */ + FCNVME_SRSTAT_LOGICAL_ERR = 0x3, + FCNVME_SRSTAT_INV_QUALIF = 0x4, + FCNVME_SRSTAT_UNABL2PERFORM = 0x9, +}; + +struct nvme_fc_nvme_sr_rsp_iu { + __u8 fc_id; + __u8 opcode; + __u8 rsvd2; + __u8 status; + __be32 rsvd4; +}; + + +/* FC-NVME Link Services - LS cmd values (w0 bits 31:24) */ enum { FCNVME_LS_RSVD = 0, FCNVME_LS_RJT = 1, FCNVME_LS_ACC = 2, - FCNVME_LS_CREATE_ASSOCIATION = 3, - FCNVME_LS_CREATE_CONNECTION = 4, - FCNVME_LS_DISCONNECT = 5, + FCNVME_LS_CREATE_ASSOCIATION = 3, /* Create Association */ + FCNVME_LS_CREATE_CONNECTION = 4, /* Create I/O Connection */ + FCNVME_LS_DISCONNECT_ASSOC = 5, /* Disconnect Association */ + FCNVME_LS_DISCONNECT_CONN = 6, /* Disconnect Connection */ }; /* FC-NVME Link Service Descriptors */ @@ -117,14 +175,17 @@ enum fcnvme_ls_rjt_reason { FCNVME_RJT_RC_UNSUP = 0x0b, /* command not supported */ - FCNVME_RJT_RC_INPROG = 0x0e, - /* command already in progress */ - FCNVME_RJT_RC_INV_ASSOC = 0x40, - /* Invalid Association ID*/ + /* Invalid Association ID */ FCNVME_RJT_RC_INV_CONN = 0x41, - /* Invalid Connection ID*/ + /* Invalid Connection ID */ + + FCNVME_RJT_RC_INV_PARAM = 0x42, + /* Invalid Parameters */ + + FCNVME_RJT_RC_INSUF_RES = 0x43, + /* Insufficient Resources */ FCNVME_RJT_RC_VENDOR = 0xff, /* vendor specific error */ @@ -138,14 +199,32 @@ enum fcnvme_ls_rjt_explan { FCNVME_RJT_EXP_OXID_RXID = 0x17, /* invalid OX_ID-RX_ID combination */ - FCNVME_RJT_EXP_INSUF_RES = 0x29, - /* insufficient resources */ - FCNVME_RJT_EXP_UNAB_DATA = 0x2a, /* unable to supply requested data */ FCNVME_RJT_EXP_INV_LEN = 0x2d, /* Invalid payload length */ + + FCNVME_RJT_EXP_INV_ERSP_RAT = 0x40, + /* Invalid NVMe_ERSP Ratio */ + + FCNVME_RJT_EXP_INV_CTLR_ID = 0x41, + /* Invalid Controller ID */ + + FCNVME_RJT_EXP_INV_QUEUE_ID = 0x42, + /* Invalid Queue ID */ + + FCNVME_RJT_EXP_INV_SQSIZE = 0x43, + /* Invalid Submission Queue Size */ + + FCNVME_RJT_EXP_INV_HOSTID = 0x44, + /* Invalid HOST ID */ + + FCNVME_RJT_EXP_INV_HOSTNQN = 0x45, + /* Invalid HOSTNQN */ + + FCNVME_RJT_EXP_INV_SUBNQN = 0x46, + /* Invalid SUBNQN */ }; /* FCNVME_LSDESC_RJT */ @@ -209,21 +288,11 @@ struct fcnvme_lsdesc_cr_conn_cmd { __be32 rsvd52; }; -/* Disconnect Scope Values */ -enum { - FCNVME_DISCONN_ASSOCIATION = 0, - FCNVME_DISCONN_CONNECTION = 1, -}; - /* FCNVME_LSDESC_DISCONN_CMD */ struct fcnvme_lsdesc_disconn_cmd { __be32 desc_tag; /* FCNVME_LSDESC_xxx */ __be32 desc_len; - u8 rsvd8[3]; - /* note: scope is really a 1 bit field */ - u8 scope; /* FCNVME_DISCONN_xxx */ - __be32 rsvd12; - __be64 id; + __be32 rsvd8[4]; }; /* FCNVME_LSDESC_CONN_ID */ @@ -242,9 +311,14 @@ struct fcnvme_lsdesc_assoc_id { /* r_ctl values */ enum { - FCNVME_RS_RCTL_DATA = 1, - FCNVME_RS_RCTL_XFER_RDY = 5, - FCNVME_RS_RCTL_RSP = 8, + FCNVME_RS_RCTL_CMND = 0x6, + FCNVME_RS_RCTL_DATA = 0x1, + FCNVME_RS_RCTL_CONF = 0x3, + FCNVME_RS_RCTL_SR = 0x9, + FCNVME_RS_RCTL_XFER_RDY = 0x5, + FCNVME_RS_RCTL_RSP = 0x7, + FCNVME_RS_RCTL_ERSP = 0x8, + FCNVME_RS_RCTL_SR_RSP = 0xA, }; @@ -264,7 +338,10 @@ struct fcnvme_ls_acc_hdr { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_rqst rqst; - /* Followed by cmd-specific ACC descriptors, see next definitions */ + /* + * Followed by cmd-specific ACCEPT descriptors, see xxx_acc + * definitions below + */ }; /* FCNVME_LS_CREATE_ASSOCIATION */ @@ -302,25 +379,39 @@ struct fcnvme_ls_cr_conn_acc { struct fcnvme_lsdesc_conn_id connectid; }; -/* FCNVME_LS_DISCONNECT */ -struct fcnvme_ls_disconnect_rqst { +/* FCNVME_LS_DISCONNECT_ASSOC */ +struct fcnvme_ls_disconnect_assoc_rqst { struct fcnvme_ls_rqst_w0 w0; __be32 desc_list_len; struct fcnvme_lsdesc_assoc_id associd; struct fcnvme_lsdesc_disconn_cmd discon_cmd; }; -struct fcnvme_ls_disconnect_acc { +struct fcnvme_ls_disconnect_assoc_acc { + struct fcnvme_ls_acc_hdr hdr; +}; + + +/* FCNVME_LS_DISCONNECT_CONN */ +struct fcnvme_ls_disconnect_conn_rqst { + struct fcnvme_ls_rqst_w0 w0; + __be32 desc_list_len; + struct fcnvme_lsdesc_assoc_id associd; + struct fcnvme_lsdesc_disconn_cmd connectid; +}; + +struct fcnvme_ls_disconnect_conn_acc { struct fcnvme_ls_acc_hdr hdr; }; /* - * Yet to be defined in FC-NVME: + * Default R_A_TOV is pulled in from fc_fs.h but needs conversion + * from ms to seconds for our use. */ -#define NVME_FC_CONNECT_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_LS_TIMEOUT_SEC 2 /* 2 seconds */ -#define NVME_FC_TGTOP_TIMEOUT_SEC 2 /* 2 seconds */ +#define FC_TWO_TIMES_R_A_TOV (2 * (FC_DEF_R_A_TOV / 1000)) +#define NVME_FC_LS_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV +#define NVME_FC_TGTOP_TIMEOUT_SEC FC_TWO_TIMES_R_A_TOV /* * TRADDR string must be of form "nn-<16hexdigits>:pn-<16hexdigits>" @@ -328,6 +419,7 @@ struct fcnvme_ls_disconnect_acc { * infront of the <16hexdigits>. Without is considered the "min" string * and with is considered the "max" string. The hexdigits may be upper * or lower case. + * Note: FC-NVME-2 standard requires a "0x" prefix. */ #define NVME_FC_TRADDR_NNLEN 3 /* "?n-" */ #define NVME_FC_TRADDR_OXNNLEN 5 /* "?n-0x" */ diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f61d6906e59d..3d5189f46cb1 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -107,8 +107,22 @@ enum { NVME_REG_AQA = 0x0024, /* Admin Queue Attributes */ NVME_REG_ASQ = 0x0028, /* Admin SQ Base Address */ NVME_REG_ACQ = 0x0030, /* Admin CQ Base Address */ - NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ + NVME_REG_CMBLOC = 0x0038, /* Controller Memory Buffer Location */ NVME_REG_CMBSZ = 0x003c, /* Controller Memory Buffer Size */ + NVME_REG_BPINFO = 0x0040, /* Boot Partition Information */ + NVME_REG_BPRSEL = 0x0044, /* Boot Partition Read Select */ + NVME_REG_BPMBL = 0x0048, /* Boot Partition Memory Buffer + * Location + */ + NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ + NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ + NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ + NVME_REG_PMREBS = 0x0e0c, /* Persistent Memory Region Elasticity + * Buffer Size + */ + NVME_REG_PMRSWTP = 0x0e10, /* Persistent Memory Region Sustained + * Write Throughput + */ NVME_REG_DBS = 0x1000, /* SQ 0 Tail Doorbell */ }; @@ -295,6 +309,14 @@ enum { NVME_CTRL_OACS_DIRECTIVES = 1 << 5, NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, NVME_CTRL_LPA_CMD_EFFECTS_LOG = 1 << 1, + NVME_CTRL_CTRATT_128_ID = 1 << 0, + NVME_CTRL_CTRATT_NON_OP_PSP = 1 << 1, + NVME_CTRL_CTRATT_NVM_SETS = 1 << 2, + NVME_CTRL_CTRATT_READ_RECV_LVLS = 1 << 3, + NVME_CTRL_CTRATT_ENDURANCE_GROUPS = 1 << 4, + NVME_CTRL_CTRATT_PREDICTABLE_LAT = 1 << 5, + NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY = 1 << 7, + NVME_CTRL_CTRATT_UUID_LIST = 1 << 9, }; struct nvme_lbaf { @@ -352,6 +374,9 @@ enum { NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, NVME_ID_CNS_CTRL_LIST = 0x13, + NVME_ID_CNS_SCNDRY_CTRL_LIST = 0x15, + NVME_ID_CNS_NS_GRANULARITY = 0x16, + NVME_ID_CNS_UUID_LIST = 0x17, }; enum { @@ -409,7 +434,8 @@ struct nvme_smart_log { __u8 avail_spare; __u8 spare_thresh; __u8 percent_used; - __u8 rsvd6[26]; + __u8 endu_grp_crit_warn_sumry; + __u8 rsvd7[25]; __u8 data_units_read[16]; __u8 data_units_written[16]; __u8 host_reads[16]; @@ -423,7 +449,11 @@ struct nvme_smart_log { __le32 warning_temp_time; __le32 critical_comp_time; __le16 temp_sensor[8]; - __u8 rsvd216[296]; + __le32 thm_temp1_trans_count; + __le32 thm_temp2_trans_count; + __le32 thm_temp1_total_time; + __le32 thm_temp2_total_time; + __u8 rsvd232[280]; }; struct nvme_fw_slot_info_log { @@ -440,6 +470,7 @@ enum { NVME_CMD_EFFECTS_NIC = 1 << 3, NVME_CMD_EFFECTS_CCC = 1 << 4, NVME_CMD_EFFECTS_CSE_MASK = 3 << 16, + NVME_CMD_EFFECTS_UUID_SEL = 1 << 19, }; struct nvme_effects_log { @@ -563,6 +594,7 @@ enum nvme_opcode { nvme_cmd_compare = 0x05, nvme_cmd_write_zeroes = 0x08, nvme_cmd_dsm = 0x09, + nvme_cmd_verify = 0x0c, nvme_cmd_resv_register = 0x0d, nvme_cmd_resv_report = 0x0e, nvme_cmd_resv_acquire = 0x11, @@ -772,6 +804,12 @@ struct nvme_write_zeroes_cmd { /* Features */ +enum { + NVME_TEMP_THRESH_MASK = 0xffff, + NVME_TEMP_THRESH_SELECT_SHIFT = 16, + NVME_TEMP_THRESH_TYPE_UNDER = 0x100000, +}; + struct nvme_feat_auto_pst { __le64 entries[32]; }; @@ -806,10 +844,14 @@ enum nvme_admin_opcode { nvme_admin_ns_mgmt = 0x0d, nvme_admin_activate_fw = 0x10, nvme_admin_download_fw = 0x11, + nvme_admin_dev_self_test = 0x14, nvme_admin_ns_attach = 0x15, nvme_admin_keep_alive = 0x18, nvme_admin_directive_send = 0x19, nvme_admin_directive_recv = 0x1a, + nvme_admin_virtual_mgmt = 0x1c, + nvme_admin_nvme_mi_send = 0x1d, + nvme_admin_nvme_mi_recv = 0x1e, nvme_admin_dbbuf = 0x7C, nvme_admin_format_nvm = 0x80, nvme_admin_security_send = 0x81, @@ -873,6 +915,7 @@ enum { NVME_FEAT_PLM_CONFIG = 0x13, NVME_FEAT_PLM_WINDOW = 0x14, NVME_FEAT_HOST_BEHAVIOR = 0x16, + NVME_FEAT_SANITIZE = 0x17, NVME_FEAT_SW_PROGRESS = 0x80, NVME_FEAT_HOST_ID = 0x81, NVME_FEAT_RESV_MASK = 0x82, @@ -883,6 +926,10 @@ enum { NVME_LOG_FW_SLOT = 0x03, NVME_LOG_CHANGED_NS = 0x04, NVME_LOG_CMD_EFFECTS = 0x05, + NVME_LOG_DEVICE_SELF_TEST = 0x06, + NVME_LOG_TELEMETRY_HOST = 0x07, + NVME_LOG_TELEMETRY_CTRL = 0x08, + NVME_LOG_ENDURANCE_GROUP = 0x09, NVME_LOG_ANA = 0x0c, NVME_LOG_DISC = 0x70, NVME_LOG_RESERVATION = 0x80, @@ -1290,7 +1337,11 @@ enum { NVME_SC_SGL_INVALID_OFFSET = 0x16, NVME_SC_SGL_INVALID_SUBTYPE = 0x17, + NVME_SC_SANITIZE_FAILED = 0x1C, + NVME_SC_SANITIZE_IN_PROGRESS = 0x1D, + NVME_SC_NS_WRITE_PROTECTED = 0x20, + NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, @@ -1328,6 +1379,8 @@ enum { NVME_SC_NS_NOT_ATTACHED = 0x11a, NVME_SC_THIN_PROV_NOT_SUPP = 0x11b, NVME_SC_CTRL_LIST_INVALID = 0x11c, + NVME_SC_BP_WRITE_PROHIBITED = 0x11e, + NVME_SC_PMR_SAN_PROHIBITED = 0x123, /* * I/O Command Set Specific - NVM commands: @@ -1368,6 +1421,7 @@ enum { NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, NVME_SC_HOST_PATH_ERROR = 0x370, + NVME_SC_HOST_ABORTED_CMD = 0x371, NVME_SC_CRD = 0x1800, NVME_SC_DNR = 0x4000, diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 8f8be5b00060..02dc4aa992b2 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -89,6 +89,9 @@ void nvmem_del_cell_lookups(struct nvmem_cell_lookup *entries, int nvmem_register_notifier(struct notifier_block *nb); int nvmem_unregister_notifier(struct notifier_block *nb); +struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)); + #else static inline struct nvmem_cell *nvmem_cell_get(struct device *dev, @@ -204,6 +207,12 @@ static inline int nvmem_unregister_notifier(struct notifier_block *nb) return -EOPNOTSUPP; } +static inline struct nvmem_device *nvmem_device_find(void *data, + int (*match)(struct device *dev, const void *data)) +{ + return NULL; +} + #endif /* CONFIG_NVMEM */ #if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF) diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 6aeaea1775e6..71bbfcf3adcd 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -6,15 +6,18 @@ #ifndef __LINUX_OF_NET_H #define __LINUX_OF_NET_H +#include <linux/phy.h> + #ifdef CONFIG_OF_NET #include <linux/of.h> struct net_device; -extern int of_get_phy_mode(struct device_node *np); +extern int of_get_phy_mode(struct device_node *np, phy_interface_t *interface); extern const void *of_get_mac_address(struct device_node *np); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else -static inline int of_get_phy_mode(struct device_node *np) +static inline int of_get_phy_mode(struct device_node *np, + phy_interface_t *interface) { return -ENODEV; } diff --git a/include/linux/pci.h b/include/linux/pci.h index f9088c89a534..1a6cf19eac2d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1686,6 +1686,7 @@ static inline struct pci_dev *pci_get_class(unsigned int class, static inline void pci_set_master(struct pci_dev *dev) { } static inline int pci_enable_device(struct pci_dev *dev) { return -EIO; } static inline void pci_disable_device(struct pci_dev *dev) { } +static inline int pcim_enable_device(struct pci_dev *pdev) { return -EIO; } static inline int pci_assign_resource(struct pci_dev *dev, int i) { return -EBUSY; } static inline int __pci_register_driver(struct pci_driver *drv, diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 68ccc5b1913b..a07bfdb7d8ea 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1336,6 +1336,8 @@ extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); +extern int perf_event_period(struct perf_event *event, u64 value); +extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, @@ -1415,6 +1417,14 @@ static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } +static inline int perf_event_period(struct perf_event *event, u64 value) +{ + return -EINVAL; +} +static inline u64 perf_event_pause(struct perf_event *event, bool reset) +{ + return 0; +} #endif #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) diff --git a/include/linux/phy.h b/include/linux/phy.h index 9a0e981df502..5032d453ac66 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -203,6 +203,8 @@ static inline const char *phy_modes(phy_interface_t interface) struct device; struct phylink; +struct sfp_bus; +struct sfp_upstream_ops; struct sk_buff; /* @@ -342,6 +344,8 @@ struct phy_c45_device_ids { * dev_flags: Device-specific flags used by the PHY driver. * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine + * sfp_bus_attached: flag indicating whether the SFP bus has been attached + * sfp_bus: SFP bus attached to this PHY's fiber port * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. @@ -432,6 +436,9 @@ struct phy_device { struct mutex lock; + /* This may be modified under the rtnl lock */ + bool sfp_bus_attached; + struct sfp_bus *sfp_bus; struct phylink *phylink; struct net_device *attached_dev; @@ -1020,6 +1027,10 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); +void phy_sfp_attach(void *upstream, struct sfp_bus *bus); +void phy_sfp_detach(void *upstream, struct sfp_bus *bus); +int phy_sfp_probe(struct phy_device *phydev, + const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); @@ -1065,6 +1076,16 @@ static inline const char *phydev_name(const struct phy_device *phydev) return dev_name(&phydev->mdio.dev); } +static inline void phy_lock_mdio_bus(struct phy_device *phydev) +{ + mutex_lock(&phydev->mdio.bus->mdio_lock); +} + +static inline void phy_unlock_mdio_bus(struct phy_device *phydev) +{ + mutex_unlock(&phydev->mdio.bus->mdio_lock); +} + void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); void phy_attached_info(struct phy_device *phydev); @@ -1106,6 +1127,10 @@ int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); +/* Clause 37 */ +int genphy_c37_config_aneg(struct phy_device *phydev); +int genphy_c37_read_status(struct phy_device *phydev); + /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); @@ -1145,7 +1170,6 @@ void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); -int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 300ecdb6790a..fed5488e3c75 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -72,7 +72,7 @@ struct phylink_config { /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. - * @mac_link_state: Read the current link state from the hardware. + * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_config: configure the MAC for the selected mode and state. * @mac_an_restart: restart 802.3z BaseX autonegotiation. * @mac_link_down: take the link down. @@ -84,8 +84,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); - int (*mac_link_state)(struct phylink_config *config, - struct phylink_link_state *state); + void (*mac_pcs_get_state)(struct phylink_config *config, + struct phylink_link_state *state); void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); void (*mac_an_restart)(struct phylink_config *config); @@ -127,18 +127,19 @@ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); /** - * mac_link_state() - Read the current link state from the hardware + * mac_pcs_get_state() - Read the current inband link state from the hardware * @config: a pointer to a &struct phylink_config. * @state: a pointer to a &struct phylink_link_state. * - * Read the current link state from the MAC, reporting the current - * speed in @state->speed, duplex mode in @state->duplex, pause mode - * in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, - * negotiation completion state in @state->an_complete, and link - * up state in @state->link. + * Read the current inband link state from the MAC PCS, reporting the + * current speed in @state->speed, duplex mode in @state->duplex, pause + * mode in @state->pause using the %MLO_PAUSE_RX and %MLO_PAUSE_TX bits, + * negotiation completion state in @state->an_complete, and link up state + * in @state->link. If possible, @state->lp_advertising should also be + * populated. */ -int mac_link_state(struct phylink_config *config, - struct phylink_link_state *state); +void mac_pcs_get_state(struct phylink_config *config, + struct phylink_link_state *state); /** * mac_config() - configure the MAC for the selected mode and state @@ -166,7 +167,7 @@ int mac_link_state(struct phylink_config *config, * 1000base-X or Cisco SGMII mode depending on the @state->interface * mode). In both cases, link state management (whether the link * is up or not) is performed by the MAC, and reported via the - * mac_link_state() callback. Changes in link state must be made + * mac_pcs_get_state() callback. Changes in link state must be made * by calling phylink_mac_change(). * * If in 802.3z mode, the link speed is fixed, dependent on the diff --git a/include/linux/pid.h b/include/linux/pid.h index 9645b1194c98..998ae7d24450 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -85,6 +85,10 @@ static inline struct pid *get_pid(struct pid *pid) extern void put_pid(struct pid *pid); extern struct task_struct *pid_task(struct pid *pid, enum pid_type); +static inline bool pid_has_task(struct pid *pid, enum pid_type type) +{ + return !hlist_empty(&pid->tasks[type]); +} extern struct task_struct *get_pid_task(struct pid *pid, enum pid_type); extern struct pid *get_task_pid(struct task_struct *task, enum pid_type type); @@ -120,7 +124,8 @@ extern struct pid *find_vpid(int nr); extern struct pid *find_get_pid(int nr); extern struct pid *find_ge_pid(int nr, struct pid_namespace *); -extern struct pid *alloc_pid(struct pid_namespace *ns); +extern struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, + size_t set_tid_size); extern void free_pid(struct pid *pid); extern void disable_pid_allocation(struct pid_namespace *ns); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 49538b172483..2ed6af88794b 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -12,6 +12,8 @@ #include <linux/ns_common.h> #include <linux/idr.h> +/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ +#define MAX_PID_NS_LEVEL 32 struct fs_pin; diff --git a/include/linux/platform_data/intel-spi.h b/include/linux/platform_data/intel-spi.h index ebb4f332588b..7f53a5c6f35e 100644 --- a/include/linux/platform_data/intel-spi.h +++ b/include/linux/platform_data/intel-spi.h @@ -13,6 +13,7 @@ enum intel_spi_type { INTEL_SPI_BYT = 1, INTEL_SPI_LPT, INTEL_SPI_BXT, + INTEL_SPI_CNL, }; /** diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h index f0e6d6483e62..65fd5ffd257c 100644 --- a/include/linux/platform_data/spi-mt65xx.h +++ b/include/linux/platform_data/spi-mt65xx.h @@ -11,7 +11,6 @@ /* Board specific platform_data */ struct mtk_chip_config { - u32 cs_pol; u32 sample_sel; }; #endif diff --git a/include/linux/psci.h b/include/linux/psci.h index e2bacc6fd2f2..ebe0a881d13d 100644 --- a/include/linux/psci.h +++ b/include/linux/psci.h @@ -7,6 +7,7 @@ #ifndef __LINUX_PSCI_H #define __LINUX_PSCI_H +#include <linux/arm-smccc.h> #include <linux/init.h> #include <linux/types.h> @@ -18,12 +19,6 @@ bool psci_tos_resident_on(int cpu); int psci_cpu_suspend_enter(u32 state); bool psci_power_state_is_valid(u32 state); -enum psci_conduit { - PSCI_CONDUIT_NONE, - PSCI_CONDUIT_SMC, - PSCI_CONDUIT_HVC, -}; - enum smccc_version { SMCCC_VERSION_1_0, SMCCC_VERSION_1_1, @@ -38,7 +33,7 @@ struct psci_operations { int (*affinity_info)(unsigned long target_affinity, unsigned long lowest_affinity_level); int (*migrate_info_type)(void); - enum psci_conduit conduit; + enum arm_smccc_conduit conduit; enum smccc_version smccc_version; }; diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h index a5d1837e4f35..6facf27865f9 100644 --- a/include/linux/pxa2xx_ssp.h +++ b/include/linux/pxa2xx_ssp.h @@ -206,7 +206,7 @@ enum pxa_ssp_type { }; struct ssp_device { - struct platform_device *pdev; + struct device *dev; struct list_head node; struct clk *clk; diff --git a/include/linux/regulator/ab8500.h b/include/linux/regulator/ab8500.h index 7cf8f797e13a..3ab1ddf151a2 100644 --- a/include/linux/regulator/ab8500.h +++ b/include/linux/regulator/ab8500.h @@ -37,14 +37,11 @@ enum ab8505_regulator_id { AB8505_LDO_AUX6, AB8505_LDO_INTCORE, AB8505_LDO_ADC, - AB8505_LDO_USB, AB8505_LDO_AUDIO, AB8505_LDO_ANAMIC1, AB8505_LDO_ANAMIC2, AB8505_LDO_AUX8, AB8505_LDO_ANA, - AB8505_SYSCLKREQ_2, - AB8505_SYSCLKREQ_4, AB8505_NUM_REGULATORS, }; diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h index d44ce5f18a56..55319943fcc5 100644 --- a/include/linux/regulator/fixed.h +++ b/include/linux/regulator/fixed.h @@ -36,6 +36,7 @@ struct fixed_voltage_config { const char *input_supply; int microvolts; unsigned startup_delay; + unsigned int off_on_delay; unsigned enabled_at_boot:1; struct regulator_init_data *init_data; }; diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index a986ac12a848..e40d019c3d9d 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -216,15 +216,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, */ bool sbitmap_any_bit_set(const struct sbitmap *sb); -/** - * sbitmap_any_bit_clear() - Check for an unset bit in a &struct - * sbitmap. - * @sb: Bitmap to check. - * - * Return: true if any bit in the bitmap is clear, false otherwise. - */ -bool sbitmap_any_bit_clear(const struct sbitmap *sb); - #define SB_NR_TO_INDEX(sb, bitnr) ((bitnr) >> (sb)->shift) #define SB_NR_TO_BIT(sb, bitnr) ((bitnr) & ((1U << (sb)->shift) - 1U)) diff --git a/include/linux/sched.h b/include/linux/sched.h index 67a1d86981a9..6666e25606b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ +#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 4b1c3b664f51..f1879884238e 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -26,6 +26,9 @@ struct kernel_clone_args { unsigned long stack; unsigned long stack_size; unsigned long tls; + pid_t *set_tid; + /* Number of elements in *set_tid */ + size_t set_tid_size; }; /* diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h index 53c28d750a45..1ac0d712a9c3 100644 --- a/include/linux/sed-opal.h +++ b/include/linux/sed-opal.h @@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd) case IOC_OPAL_PSID_REVERT_TPR: case IOC_OPAL_MBR_DONE: case IOC_OPAL_WRITE_SHADOW_MBR: + case IOC_OPAL_GENERIC_TABLE_RW: return true; } return false; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 1c35428e98bc..487fd9412d10 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -428,6 +428,10 @@ enum { SFP_TEC_CUR = 0x6c, SFP_STATUS = 0x6e, + SFP_STATUS_TX_DISABLE = BIT(7), + SFP_STATUS_TX_DISABLE_FORCE = BIT(6), + SFP_STATUS_TX_FAULT = BIT(2), + SFP_STATUS_RX_LOS = BIT(1), SFP_ALARM0 = 0x70, SFP_ALARM0_TEMP_HIGH = BIT(7), SFP_ALARM0_TEMP_LOW = BIT(6), @@ -508,10 +512,11 @@ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, u8 *data); void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); -struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, - void *upstream, - const struct sfp_upstream_ops *ops); -void sfp_unregister_upstream(struct sfp_bus *bus); +void sfp_bus_put(struct sfp_bus *bus); +struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops); +void sfp_bus_del_upstream(struct sfp_bus *bus); #else static inline int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, @@ -553,14 +558,22 @@ static inline void sfp_upstream_stop(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_register_upstream( - struct fwnode_handle *fwnode, void *upstream, - const struct sfp_upstream_ops *ops) +static inline void sfp_bus_put(struct sfp_bus *bus) { - return (struct sfp_bus *)-1; } -static inline void sfp_unregister_upstream(struct sfp_bus *bus) +static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +{ + return NULL; +} + +static inline int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, + const struct sfp_upstream_ops *ops) +{ + return 0; +} + +static inline void sfp_bus_del_upstream(struct sfp_bus *bus) { } #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 64a395c7f689..eceb3607864b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1795,7 +1795,7 @@ static inline struct sk_buff *skb_peek_next(struct sk_buff *skb, */ static inline struct sk_buff *skb_peek_tail(const struct sk_buff_head *list_) { - struct sk_buff *skb = list_->prev; + struct sk_buff *skb = READ_ONCE(list_->prev); if (skb == (struct sk_buff *)list_) skb = NULL; @@ -1861,7 +1861,9 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + /* See skb_queue_empty_lockless() and skb_peek_tail() + * for the opposite READ_ONCE() + */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); WRITE_ONCE(next->prev, newsk); @@ -2277,12 +2279,12 @@ static inline void *pskb_pull(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __pskb_pull(skb, len); } -static inline int pskb_may_pull(struct sk_buff *skb, unsigned int len) +static inline bool pskb_may_pull(struct sk_buff *skb, unsigned int len) { if (likely(len <= skb_headlen(skb))) - return 1; + return true; if (unlikely(len > skb->len)) - return 0; + return false; return __pskb_pull_tail(skb, len - skb_headlen(skb)) != NULL; } @@ -4169,12 +4171,18 @@ static inline void skb_ext_reset(struct sk_buff *skb) skb->active_extensions = 0; } } + +static inline bool skb_has_extensions(struct sk_buff *skb) +{ + return unlikely(skb->active_extensions); +} #else static inline void skb_ext_put(struct sk_buff *skb) {} static inline void skb_ext_reset(struct sk_buff *skb) {} static inline void skb_ext_del(struct sk_buff *skb, int unused) {} static inline void __skb_ext_copy(struct sk_buff *d, const struct sk_buff *s) {} static inline void skb_ext_copy(struct sk_buff *dst, const struct sk_buff *s) {} +static inline bool skb_has_extensions(struct sk_buff *skb) { return false; } #endif /* CONFIG_SKB_EXTENSIONS */ static inline void nf_reset_ct(struct sk_buff *skb) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ce7055259877..6cb077b646a5 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -28,13 +28,14 @@ struct sk_msg_sg { u32 end; u32 size; u32 copybreak; - bool copy[MAX_MSG_FRAGS]; + unsigned long copy; /* The extra element is used for chaining the front and sections when * the list becomes partitioned (e.g. end < start). The crypto APIs * require the chaining. */ struct scatterlist data[MAX_MSG_FRAGS + 1]; }; +static_assert(BITS_PER_LONG >= MAX_MSG_FRAGS); /* UAPI in filter.c depends on struct sk_msg_sg being first element. */ struct sk_msg { @@ -230,7 +231,7 @@ static inline void sk_msg_compute_data_pointers(struct sk_msg *msg) { struct scatterlist *sge = sk_msg_elem(msg, msg->sg.start); - if (msg->sg.copy[msg->sg.start]) { + if (test_bit(msg->sg.start, &msg->sg.copy)) { msg->data = NULL; msg->data_end = NULL; } else { @@ -249,7 +250,7 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, sg_set_page(sge, page, len, offset); sg_unmark_end(sge); - msg->sg.copy[msg->sg.end] = true; + __set_bit(msg->sg.end, &msg->sg.copy); msg->sg.size += len; sk_msg_iter_next(msg, end); } @@ -257,7 +258,10 @@ static inline void sk_msg_page_add(struct sk_msg *msg, struct page *page, static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state) { do { - msg->sg.copy[i] = copy_state; + if (copy_state) + __set_bit(i, &msg->sg.copy); + else + __clear_bit(i, &msg->sg.copy); sk_msg_iter_var_next(i); if (i == msg->sg.end) break; diff --git a/include/linux/socket.h b/include/linux/socket.h index 4049d9755cf1..09c32a21555b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -392,6 +392,9 @@ extern int __sys_recvfrom(int fd, void __user *ubuf, size_t size, extern int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len); +extern int __sys_accept4_file(struct file *file, unsigned file_flags, + struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags); extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index af4f265d0f67..98fe8663033a 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -13,6 +13,7 @@ #include <linux/completion.h> #include <linux/scatterlist.h> #include <linux/gpio/consumer.h> +#include <linux/ptp_clock_kernel.h> struct dma_chan; struct property_entry; @@ -90,6 +91,22 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, SPI_STATISTICS_ADD_TO_FIELD(stats, field, 1) /** + * struct spi_delay - SPI delay information + * @value: Value for the delay + * @unit: Unit for the delay + */ +struct spi_delay { +#define SPI_DELAY_UNIT_USECS 0 +#define SPI_DELAY_UNIT_NSECS 1 +#define SPI_DELAY_UNIT_SCK 2 + u16 value; + u8 unit; +}; + +extern int spi_delay_to_ns(struct spi_delay *_delay, struct spi_transfer *xfer); +extern int spi_delay_exec(struct spi_delay *_delay, struct spi_transfer *xfer); + +/** * struct spi_device - Controller side proxy for an SPI slave device * @dev: Driver model representation of the device. * @controller: SPI controller used with the device. @@ -123,7 +140,7 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, * the spi_master. * @cs_gpiod: gpio descriptor of the chipselect line (optional, NULL when * not using a GPIO line) - * @word_delay_usecs: microsecond delay to be inserted between consecutive + * @word_delay: delay to be inserted between consecutive * words of a transfer * * @statistics: statistics for the spi_device @@ -173,7 +190,7 @@ struct spi_device { const char *driver_override; int cs_gpio; /* LEGACY: chip select gpio */ struct gpio_desc *cs_gpiod; /* chip select gpio desc */ - uint8_t word_delay_usecs; /* inter-word delay */ + struct spi_delay word_delay; /* inter-word delay */ /* the statistics */ struct spi_statistics statistics; @@ -390,6 +407,11 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * controller has native support for memory like operations. * @unprepare_message: undo any work done by prepare_message(). * @slave_abort: abort the ongoing transfer request on an SPI slave controller + * @cs_setup: delay to be introduced by the controller after CS is asserted + * @cs_hold: delay to be introduced by the controller before CS is deasserted + * @cs_inactive: delay to be introduced by the controller after CS is + * deasserted. If @cs_change_delay is used from @spi_transfer, then the + * two delays will be added up. * @cs_gpios: LEGACY: array of GPIO descs to use as chip select lines; one per * CS number. Any individual value may be -ENOENT for CS lines that * are not GPIOs (driven by the SPI controller itself). Use the cs_gpiods @@ -409,6 +431,12 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv) * @fw_translate_cs: If the boot firmware uses different numbering scheme * what Linux expects, this optional hook can be used to translate * between the two. + * @ptp_sts_supported: If the driver sets this to true, it must provide a + * time snapshot in @spi_transfer->ptp_sts as close as possible to the + * moment in time when @spi_transfer->ptp_sts_word_pre and + * @spi_transfer->ptp_sts_word_post were transmitted. + * If the driver does not set this, the SPI core takes the snapshot as + * close to the driver hand-over as possible. * * Each SPI controller can communicate with one or more @spi_device * children. These make a small bus, sharing MOSI, MISO and SCK signals @@ -502,8 +530,8 @@ struct spi_controller { * to configure specific CS timing through spi_set_cs_timing() after * spi_setup(). */ - void (*set_cs_timing)(struct spi_device *spi, u8 setup_clk_cycles, - u8 hold_clk_cycles, u8 inactive_clk_cycles); + int (*set_cs_timing)(struct spi_device *spi, struct spi_delay *setup, + struct spi_delay *hold, struct spi_delay *inactive); /* bidirectional bulk transfers * @@ -587,6 +615,11 @@ struct spi_controller { /* Optimized handlers for SPI memory-like operations. */ const struct spi_controller_mem_ops *mem_ops; + /* CS delays */ + struct spi_delay cs_setup; + struct spi_delay cs_hold; + struct spi_delay cs_inactive; + /* gpio chip select */ int *cs_gpios; struct gpio_desc **cs_gpiods; @@ -604,6 +637,15 @@ struct spi_controller { void *dummy_tx; int (*fw_translate_cs)(struct spi_controller *ctlr, unsigned cs); + + /* + * Driver sets this field to indicate it is able to snapshot SPI + * transfers (needed e.g. for reading the time of POSIX clocks) + */ + bool ptp_sts_supported; + + /* Interrupt enable state during PTP system timestamping */ + unsigned long irq_flags; }; static inline void *spi_controller_get_devdata(struct spi_controller *ctlr) @@ -644,6 +686,14 @@ extern struct spi_message *spi_get_next_queued_message(struct spi_controller *ct extern void spi_finalize_current_message(struct spi_controller *ctlr); extern void spi_finalize_current_transfer(struct spi_controller *ctlr); +/* Helper calls for driver to timestamp transfer */ +void spi_take_timestamp_pre(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); +void spi_take_timestamp_post(struct spi_controller *ctlr, + struct spi_transfer *xfer, + const void *tx, bool irqs_off); + /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, unsigned int size, bool slave); @@ -739,13 +789,13 @@ extern void spi_res_release(struct spi_controller *ctlr, * @cs_change: affects chipselect after this transfer completes * @cs_change_delay: delay between cs deassert and assert when * @cs_change is set and @spi_transfer is not the last in @spi_message - * @cs_change_delay_unit: unit of cs_change_delay + * @delay: delay to be introduced after this transfer before + * (optionally) changing the chipselect status, then starting + * the next transfer or completing this @spi_message. * @delay_usecs: microseconds to delay after this transfer before * (optionally) changing the chipselect status, then starting * the next transfer or completing this @spi_message. - * @word_delay_usecs: microseconds to inter word delay after each word size - * (set by bits_per_word) transmission. - * @word_delay: clock cycles to inter word delay after each word size + * @word_delay: inter word delay to be introduced after each word size * (set by bits_per_word) transmission. * @effective_speed_hz: the effective SCK-speed that was used to * transfer this transfer. Set to 0 if the spi bus driver does @@ -753,6 +803,35 @@ extern void spi_res_release(struct spi_controller *ctlr, * @transfer_list: transfers are sequenced through @spi_message.transfers * @tx_sg: Scatterlist for transmit, currently not for client use * @rx_sg: Scatterlist for receive, currently not for client use + * @ptp_sts_word_pre: The word (subject to bits_per_word semantics) offset + * within @tx_buf for which the SPI device is requesting that the time + * snapshot for this transfer begins. Upon completing the SPI transfer, + * this value may have changed compared to what was requested, depending + * on the available snapshotting resolution (DMA transfer, + * @ptp_sts_supported is false, etc). + * @ptp_sts_word_post: See @ptp_sts_word_post. The two can be equal (meaning + * that a single byte should be snapshotted). + * If the core takes care of the timestamp (if @ptp_sts_supported is false + * for this controller), it will set @ptp_sts_word_pre to 0, and + * @ptp_sts_word_post to the length of the transfer. This is done + * purposefully (instead of setting to spi_transfer->len - 1) to denote + * that a transfer-level snapshot taken from within the driver may still + * be of higher quality. + * @ptp_sts: Pointer to a memory location held by the SPI slave device where a + * PTP system timestamp structure may lie. If drivers use PIO or their + * hardware has some sort of assist for retrieving exact transfer timing, + * they can (and should) assert @ptp_sts_supported and populate this + * structure using the ptp_read_system_*ts helper functions. + * The timestamp must represent the time at which the SPI slave device has + * processed the word, i.e. the "pre" timestamp should be taken before + * transmitting the "pre" word, and the "post" timestamp after receiving + * transmit confirmation from the controller for the "post" word. + * @timestamped_pre: Set by the SPI controller driver to denote it has acted + * upon the @ptp_sts request. Not set when the SPI core has taken care of + * the task. SPI device drivers are free to print a warning if this comes + * back unset and they need the better resolution. + * @timestamped_post: See above. The reason why both exist is that these + * booleans are also used to keep state in the core SPI logic. * * SPI transfers always write the same number of bytes as they read. * Protocol drivers should always provide @rx_buf and/or @tx_buf. @@ -830,18 +909,22 @@ struct spi_transfer { #define SPI_NBITS_DUAL 0x02 /* 2bits transfer */ #define SPI_NBITS_QUAD 0x04 /* 4bits transfer */ u8 bits_per_word; - u8 word_delay_usecs; u16 delay_usecs; - u16 cs_change_delay; - u8 cs_change_delay_unit; -#define SPI_DELAY_UNIT_USECS 0 -#define SPI_DELAY_UNIT_NSECS 1 -#define SPI_DELAY_UNIT_SCK 2 + struct spi_delay delay; + struct spi_delay cs_change_delay; + struct spi_delay word_delay; u32 speed_hz; - u16 word_delay; u32 effective_speed_hz; + unsigned int ptp_sts_word_pre; + unsigned int ptp_sts_word_post; + + struct ptp_system_timestamp *ptp_sts; + + bool timestamped_pre; + bool timestamped_post; + struct list_head transfer_list; }; @@ -935,6 +1018,20 @@ spi_transfer_del(struct spi_transfer *t) list_del(&t->transfer_list); } +static inline int +spi_transfer_delay_exec(struct spi_transfer *t) +{ + struct spi_delay d; + + if (t->delay_usecs) { + d.value = t->delay_usecs; + d.unit = SPI_DELAY_UNIT_USECS; + return spi_delay_exec(&d, NULL); + } + + return spi_delay_exec(&t->delay, t); +} + /** * spi_message_init_with_transfers - Initialize spi_message and append transfers * @m: spi_message to be initialized @@ -982,7 +1079,10 @@ static inline void spi_message_free(struct spi_message *m) kfree(m); } -extern void spi_set_cs_timing(struct spi_device *spi, u8 setup, u8 hold, u8 inactive_dly); +extern int spi_set_cs_timing(struct spi_device *spi, + struct spi_delay *setup, + struct spi_delay *hold, + struct spi_delay *inactive); extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); diff --git a/include/linux/stat.h b/include/linux/stat.h index 765573dc17d6..528c4baad091 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -33,7 +33,8 @@ struct kstat { STATX_ATTR_IMMUTABLE | \ STATX_ATTR_APPEND | \ STATX_ATTR_NODUMP | \ - STATX_ATTR_ENCRYPTED \ + STATX_ATTR_ENCRYPTED | \ + STATX_ATTR_VERITY \ )/* Attrs corresponding to FS_*_FL flags */ u64 ino; dev_t dev; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index dc60d03c4b60..d4bcd9387136 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -13,6 +13,7 @@ #define __STMMAC_PLATFORM_DATA #include <linux/platform_device.h> +#include <linux/phy.h> #define MTL_MAX_RX_QUEUES 8 #define MTL_MAX_TX_QUEUES 8 @@ -92,6 +93,7 @@ struct stmmac_dma_cfg { int fixed_burst; int mixed_burst; bool aal; + bool eame; }; #define AXI_BLEN 7 @@ -131,7 +133,7 @@ struct plat_stmmacenet_data { int bus_id; int phy_addr; int interface; - int phy_interface; + phy_interface_t phy_interface; struct stmmac_mdio_bus_data *mdio_bus_data; struct device_node *phy_node; struct device_node *phylink_node; diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 267369110584..85ec745767bd 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -10,6 +10,8 @@ #ifndef __SXGBE_PLATFORM_H__ #define __SXGBE_PLATFORM_H__ +#include <linux/phy.h> + /* MDC Clock Selection define*/ #define SXGBE_CSR_100_150M 0x0 /* MDC = clk_scr_i/62 */ #define SXGBE_CSR_150_250M 0x1 /* MDC = clk_scr_i/102 */ @@ -38,7 +40,7 @@ struct sxgbe_plat_data { char *phy_bus_name; int bus_id; int phy_addr; - int interface; + phy_interface_t interface; struct sxgbe_mdio_bus_data *mdio_bus_data; struct sxgbe_dma_cfg *dma_cfg; int clk_csr; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 668e25a76d69..ca6f01531e64 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -223,7 +223,7 @@ struct tcp_sock { fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */ fastopen_no_cookie:1, /* Allow send/recv SYN+data without a cookie */ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */ - unused:2; + fastopen_client_fail:2; /* reason why fastopen failed */ u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 53c0ea9ec9df..0d6e949ba315 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -21,6 +21,7 @@ #include <linux/acpi.h> #include <linux/cdev.h> #include <linux/fs.h> +#include <linux/highmem.h> #include <crypto/hash_info.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ @@ -67,6 +68,8 @@ struct tpm_class_ops { u8 (*status) (struct tpm_chip *chip); void (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); + void (*update_durations)(struct tpm_chip *chip, + unsigned long *duration_cap); int (*go_idle)(struct tpm_chip *chip); int (*cmd_ready)(struct tpm_chip *chip); int (*request_locality)(struct tpm_chip *chip, int loc); @@ -161,6 +164,235 @@ struct tpm_chip { int locality; }; +#define TPM_HEADER_SIZE 10 + +enum tpm2_const { + TPM2_PLATFORM_PCR = 24, + TPM2_PCR_SELECT_MIN = ((TPM2_PLATFORM_PCR + 7) / 8), +}; + +enum tpm2_timeouts { + TPM2_TIMEOUT_A = 750, + TPM2_TIMEOUT_B = 2000, + TPM2_TIMEOUT_C = 200, + TPM2_TIMEOUT_D = 30, + TPM2_DURATION_SHORT = 20, + TPM2_DURATION_MEDIUM = 750, + TPM2_DURATION_LONG = 2000, + TPM2_DURATION_LONG_LONG = 300000, + TPM2_DURATION_DEFAULT = 120000, +}; + +enum tpm2_structures { + TPM2_ST_NO_SESSIONS = 0x8001, + TPM2_ST_SESSIONS = 0x8002, +}; + +/* Indicates from what layer of the software stack the error comes from */ +#define TSS2_RC_LAYER_SHIFT 16 +#define TSS2_RESMGR_TPM_RC_LAYER (11 << TSS2_RC_LAYER_SHIFT) + +enum tpm2_return_codes { + TPM2_RC_SUCCESS = 0x0000, + TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ + TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ + TPM2_RC_FAILURE = 0x0101, + TPM2_RC_DISABLED = 0x0120, + TPM2_RC_COMMAND_CODE = 0x0143, + TPM2_RC_TESTING = 0x090A, /* RC_WARN */ + TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, +}; + +enum tpm2_command_codes { + TPM2_CC_FIRST = 0x011F, + TPM2_CC_HIERARCHY_CONTROL = 0x0121, + TPM2_CC_HIERARCHY_CHANGE_AUTH = 0x0129, + TPM2_CC_CREATE_PRIMARY = 0x0131, + TPM2_CC_SEQUENCE_COMPLETE = 0x013E, + TPM2_CC_SELF_TEST = 0x0143, + TPM2_CC_STARTUP = 0x0144, + TPM2_CC_SHUTDOWN = 0x0145, + TPM2_CC_NV_READ = 0x014E, + TPM2_CC_CREATE = 0x0153, + TPM2_CC_LOAD = 0x0157, + TPM2_CC_SEQUENCE_UPDATE = 0x015C, + TPM2_CC_UNSEAL = 0x015E, + TPM2_CC_CONTEXT_LOAD = 0x0161, + TPM2_CC_CONTEXT_SAVE = 0x0162, + TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_VERIFY_SIGNATURE = 0x0177, + TPM2_CC_GET_CAPABILITY = 0x017A, + TPM2_CC_GET_RANDOM = 0x017B, + TPM2_CC_PCR_READ = 0x017E, + TPM2_CC_PCR_EXTEND = 0x0182, + TPM2_CC_EVENT_SEQUENCE_COMPLETE = 0x0185, + TPM2_CC_HASH_SEQUENCE_START = 0x0186, + TPM2_CC_CREATE_LOADED = 0x0191, + TPM2_CC_LAST = 0x0193, /* Spec 1.36 */ +}; + +enum tpm2_permanent_handles { + TPM2_RS_PW = 0x40000009, +}; + +enum tpm2_capabilities { + TPM2_CAP_HANDLES = 1, + TPM2_CAP_COMMANDS = 2, + TPM2_CAP_PCRS = 5, + TPM2_CAP_TPM_PROPERTIES = 6, +}; + +enum tpm2_properties { + TPM_PT_TOTAL_COMMANDS = 0x0129, +}; + +enum tpm2_startup_types { + TPM2_SU_CLEAR = 0x0000, + TPM2_SU_STATE = 0x0001, +}; + +enum tpm2_cc_attrs { + TPM2_CC_ATTR_CHANDLES = 25, + TPM2_CC_ATTR_RHANDLE = 28, +}; + +#define TPM_VID_INTEL 0x8086 +#define TPM_VID_WINBOND 0x1050 +#define TPM_VID_STM 0x104A + +enum tpm_chip_flags { + TPM_CHIP_FLAG_TPM2 = BIT(1), + TPM_CHIP_FLAG_IRQ = BIT(2), + TPM_CHIP_FLAG_VIRTUAL = BIT(3), + TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), + TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), + TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), +}; + +#define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) + +struct tpm_header { + __be16 tag; + __be32 length; + union { + __be32 ordinal; + __be32 return_code; + }; +} __packed; + +/* A string buffer type for constructing TPM commands. This is based on the + * ideas of string buffer code in security/keys/trusted.h but is heap based + * in order to keep the stack usage minimal. + */ + +enum tpm_buf_flags { + TPM_BUF_OVERFLOW = BIT(0), +}; + +struct tpm_buf { + unsigned int flags; + u8 *data; +}; + +enum tpm2_object_attributes { + TPM2_OA_USER_WITH_AUTH = BIT(6), +}; + +enum tpm2_session_attributes { + TPM2_SA_CONTINUE_SESSION = BIT(0), +}; + +struct tpm2_hash { + unsigned int crypto_id; + unsigned int tpm_id; +}; + +static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + head->tag = cpu_to_be16(tag); + head->length = cpu_to_be32(sizeof(*head)); + head->ordinal = cpu_to_be32(ordinal); +} + +static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal) +{ + buf->data = (u8 *)__get_free_page(GFP_KERNEL); + if (!buf->data) + return -ENOMEM; + + buf->flags = 0; + tpm_buf_reset(buf, tag, ordinal); + return 0; +} + +static inline void tpm_buf_destroy(struct tpm_buf *buf) +{ + free_page((unsigned long)buf->data); +} + +static inline u32 tpm_buf_length(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be32_to_cpu(head->length); +} + +static inline u16 tpm_buf_tag(struct tpm_buf *buf) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + + return be16_to_cpu(head->tag); +} + +static inline void tpm_buf_append(struct tpm_buf *buf, + const unsigned char *new_data, + unsigned int new_len) +{ + struct tpm_header *head = (struct tpm_header *)buf->data; + u32 len = tpm_buf_length(buf); + + /* Return silently if overflow has already happened. */ + if (buf->flags & TPM_BUF_OVERFLOW) + return; + + if ((len + new_len) > PAGE_SIZE) { + WARN(1, "tpm_buf: overflow\n"); + buf->flags |= TPM_BUF_OVERFLOW; + return; + } + + memcpy(&buf->data[len], new_data, new_len); + head->length = cpu_to_be32(len + new_len); +} + +static inline void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value) +{ + tpm_buf_append(buf, &value, 1); +} + +static inline void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value) +{ + __be16 value2 = cpu_to_be16(value); + + tpm_buf_append(buf, (u8 *) &value2, 2); +} + +static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) +{ + __be32 value2 = cpu_to_be32(value); + + tpm_buf_append(buf, (u8 *) &value2, 4); +} + +static inline u32 tpm2_rc_value(u32 rc) +{ + return (rc & BIT(7)) ? rc & 0xff : rc; +} + #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) extern int tpm_is_tpm2(struct tpm_chip *chip); @@ -170,12 +402,6 @@ extern int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digests); extern int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen); extern int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max); -extern int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); -extern int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options); extern struct tpm_chip *tpm_default_chip(void); #else static inline int tpm_is_tpm2(struct tpm_chip *chip) @@ -204,18 +430,6 @@ static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) return -ENODEV; } -static inline int tpm_seal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} -static inline int tpm_unseal_trusted(struct tpm_chip *chip, - struct trusted_key_payload *payload, - struct trusted_key_options *options) -{ - return -ENODEV; -} static inline struct tpm_chip *tpm_default_chip(void) { return NULL; diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index a27604f99ed0..9de5c10293f5 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -40,8 +40,8 @@ * spin_lock_bh(...) or other synchronization to get exclusive access * ... * u64_stats_update_begin(&stats->syncp); - * stats->bytes64 += len; // non atomic operation - * stats->packets64++; // non atomic operation + * u64_stats_add(&stats->bytes64, len); // non atomic operation + * u64_stats_inc(&stats->packets64); // non atomic operation * u64_stats_update_end(&stats->syncp); * * While a consumer (reader) should use following template to get consistent @@ -52,8 +52,8 @@ * * do { * start = u64_stats_fetch_begin(&stats->syncp); - * tbytes = stats->bytes64; // non atomic operation - * tpackets = stats->packets64; // non atomic operation + * tbytes = u64_stats_read(&stats->bytes64); // non atomic operation + * tpackets = u64_stats_read(&stats->packets64); // non atomic operation * } while (u64_stats_fetch_retry(&stats->syncp, start)); * * @@ -68,6 +68,49 @@ struct u64_stats_sync { #endif }; +#if BITS_PER_LONG == 64 +#include <asm/local64.h> + +typedef struct { + local64_t v; +} u64_stats_t ; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return local64_read(&p->v); +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + local64_add(val, &p->v); +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + local64_inc(&p->v); +} + +#else + +typedef struct { + u64 v; +} u64_stats_t; + +static inline u64 u64_stats_read(const u64_stats_t *p) +{ + return p->v; +} + +static inline void u64_stats_add(u64_stats_t *p, unsigned long val) +{ + p->v += val; +} + +static inline void u64_stats_inc(u64_stats_t *p) +{ + p->v++; +} +#endif static inline void u64_stats_init(struct u64_stats_sync *syncp) { diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index d4ee6e942562..67f016010aad 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -311,6 +311,7 @@ copy_struct_from_user(void *dst, size_t ksize, const void __user *src, * happens, handle that and return -EFAULT. */ extern long probe_kernel_read(void *dst, const void *src, size_t size); +extern long probe_kernel_read_strict(void *dst, const void *src, size_t size); extern long __probe_kernel_read(void *dst, const void *src, size_t size); /* @@ -337,7 +338,22 @@ extern long __probe_user_read(void *dst, const void __user *src, size_t size); extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); +/* + * probe_user_write(): safely attempt to write to a location in user space + * @dst: address to write to + * @src: pointer to the data that shall be written + * @size: size of the data chunk + * + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ +extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); +extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); + extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); +extern long strncpy_from_unsafe_strict(char *dst, const void *unsafe_addr, + long count); +extern long __strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, long count); extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 07875ccc7bb5..71c81e0dc8f2 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -7,9 +7,6 @@ #include <net/sock.h> #include <net/af_vsock.h> -#define VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE 128 -#define VIRTIO_VSOCK_DEFAULT_BUF_SIZE (1024 * 256) -#define VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE (1024 * 256) #define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE (1024 * 4) #define VIRTIO_VSOCK_MAX_BUF_SIZE 0xFFFFFFFFUL #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64) @@ -25,11 +22,6 @@ enum { struct virtio_vsock_sock { struct vsock_sock *vsk; - /* Protected by lock_sock(sk_vsock(trans->vsk)) */ - u32 buf_size; - u32 buf_size_min; - u32 buf_size_max; - spinlock_t tx_lock; spinlock_t rx_lock; @@ -92,12 +84,6 @@ s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); -u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk); -u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk); -void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val); -void virtio_transport_set_max_buffer_size(struct vsock_sock *vs, u64 val); int virtio_transport_notify_poll_in(struct vsock_sock *vsk, size_t target, @@ -124,6 +110,7 @@ int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk, struct vsock_transport_send_notify_data *data); int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written, struct vsock_transport_send_notify_data *data); +void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val); u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk); bool virtio_transport_stream_is_active(struct vsock_sock *vsk); @@ -150,7 +137,8 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk, void virtio_transport_destruct(struct vsock_sock *vsk); -void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt); +void virtio_transport_recv_pkt(struct virtio_transport *t, + struct virtio_vsock_pkt *pkt); void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt); void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt); u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 wanted); diff --git a/include/linux/vm_sockets.h b/include/linux/vm_sockets.h deleted file mode 100644 index 33f1a2ecd905..000000000000 --- a/include/linux/vm_sockets.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * VMware vSockets Driver - * - * Copyright (C) 2007-2013 VMware, Inc. All rights reserved. - */ - -#ifndef _VM_SOCKETS_H -#define _VM_SOCKETS_H - -#include <uapi/linux/vm_sockets.h> - -int vm_sockets_get_local_cid(void); - -#endif /* _VM_SOCKETS_H */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 4e7809408073..b4c58a191eb1 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -93,6 +93,7 @@ extern void *vzalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); extern void *vzalloc_node(unsigned long size, int node); +extern void *vmalloc_user_node_flags(unsigned long size, int node, gfp_t flags); extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index acd9fafe4fc6..f28907345c80 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -19,6 +19,7 @@ struct msghdr; typedef void (vmci_device_shutdown_fn) (void *device_registration, void *user_data); +typedef void (*vmci_vsock_cb) (bool is_host); int vmci_datagram_create_handle(u32 resource_id, u32 flags, vmci_datagram_recv_cb recv_cb, @@ -37,6 +38,7 @@ int vmci_doorbell_destroy(struct vmci_handle handle); int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags); u32 vmci_get_context_id(void); bool vmci_is_context_owner(u32 context_id, kuid_t uid); +int vmci_register_vsock_callback(vmci_vsock_cb callback); int vmci_event_subscribe(u32 event, vmci_event_cb callback, void *callback_data, |