diff options
Diffstat (limited to 'include/linux')
93 files changed, 1642 insertions, 744 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/bitmap.h b/include/linux/bitmap.h index 90528f12bdfa..29fc933df3bf 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1, } /** - * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third + * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 + * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index cf074bce3eb3..c94a9ff9f082 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -4,6 +4,13 @@ #include <asm/types.h> #include <linux/bits.h> +/* Set bits in the first 'n' bytes when loaded from memory */ +#ifdef __LITTLE_ENDIAN +# define aligned_byte_mask(n) ((1UL << 8*(n))-1) +#else +# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n))) +#endif + #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) 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 5b9d22338606..3bf3835d0e86 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -656,11 +656,11 @@ 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); void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size); +int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); 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(size_t size, int numa_node); +void *bpf_map_area_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); diff --git a/include/linux/can/core.h b/include/linux/can/core.h index 8339071ab08b..e20a0cd09ba5 100644 --- a/include/linux/can/core.h +++ b/include/linux/can/core.h @@ -65,5 +65,6 @@ extern void can_rx_unregister(struct net *net, struct net_device *dev, void *data); extern int can_send(struct sk_buff *skb, int loop); +void can_sock_destruct(struct sock *sk); #endif /* !_CAN_CORE_H */ 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/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b318efd8a74..cdf016596659 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -40,6 +40,7 @@ # define __GCC4_has_attribute___noclone__ 1 # define __GCC4_has_attribute___nonstring__ 0 # define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) +# define __GCC4_has_attribute___fallthrough__ 0 #endif /* @@ -186,6 +187,22 @@ #endif /* + * Add the pseudo keyword 'fallthrough' so case statement blocks + * must end with any of these keywords: + * break; + * fallthrough; + * goto <label>; + * return [expression]; + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#Statement-Attributes + */ +#if __has_attribute(__fallthrough__) +# define fallthrough __attribute__((__fallthrough__)) +#else +# define fallthrough do {} while (0) /* fallthrough */ +#endif + +/* * Note the missing underscores. * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noinline-function-attribute diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d0633ebdaa9c..bc6c879bd110 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -59,6 +59,11 @@ extern ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_tsx_async_abort(struct device *dev, + struct device_attribute *attr, + char *buf); +extern ssize_t cpu_show_itlb_multihit(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, @@ -213,28 +218,7 @@ static inline int cpuhp_smt_enable(void) { return 0; } static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; } #endif -/* - * These are used for a global "mitigations=" cmdline option for toggling - * optional CPU mitigations. - */ -enum cpu_mitigations { - CPU_MITIGATIONS_OFF, - CPU_MITIGATIONS_AUTO, - CPU_MITIGATIONS_AUTO_NOSMT, -}; - -extern enum cpu_mitigations cpu_mitigations; - -/* mitigations=off */ -static inline bool cpu_mitigations_off(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_OFF; -} - -/* mitigations=auto,nosmt */ -static inline bool cpu_mitigations_auto_nosmt(void) -{ - return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; -} +extern bool cpu_mitigations_off(void); +extern bool cpu_mitigations_auto_nosmt(void); #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c57e88e85c41..92d5fdc8154e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -13,6 +13,7 @@ #include <linux/completion.h> #include <linux/kobject.h> #include <linux/notifier.h> +#include <linux/pm_qos.h> #include <linux/spinlock.h> #include <linux/sysfs.h> @@ -76,8 +77,10 @@ struct cpufreq_policy { struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ - struct dev_pm_qos_request *min_freq_req; - struct dev_pm_qos_request *max_freq_req; + struct freq_constraints constraints; + struct freq_qos_request *min_freq_req; + struct freq_qos_request *max_freq_req; + struct cpufreq_frequency_table *freq_table; enum cpufreq_table_sorting freq_table_sorted; 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/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/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/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 79435cfc20eb..897e799dbcb9 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -31,6 +31,8 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull +#define SJA1105_HWTS_RX_EN 0 + /* Global tagger data: each struct sja1105_port has a reference to * the structure defined in struct sja1105_private. */ @@ -42,7 +44,7 @@ struct sja1105_tagger_data { * from taggers running on multiple ports on SMP systems */ spinlock_t meta_lock; - bool hwts_rx_en; + unsigned long state; }; struct sja1105_skb_cb { diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h index 6c809440f319..4cf02ecd67de 100644 --- a/include/linux/dynamic_debug.h +++ b/include/linux/dynamic_debug.h @@ -204,6 +204,12 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val, do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0) #define dynamic_dev_dbg(dev, fmt, ...) \ do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0) +#define dynamic_hex_dump(prefix_str, prefix_type, rowsize, \ + groupsize, buf, len, ascii) \ + do { if (0) \ + print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, \ + rowsize, groupsize, buf, len, ascii); \ + } while (0) #endif #endif 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/efi.h b/include/linux/efi.h index bd3837022307..d87acf62958e 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1579,9 +1579,22 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg, efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg, struct efi_boot_memmap *map); +efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg, + unsigned long size, unsigned long align, + unsigned long *addr, unsigned long min); + +static inline efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, - unsigned long *addr); + unsigned long *addr) +{ + /* + * Don't allocate at 0x0. It will confuse code that + * checks pointers against NULL. Skip the first 8 + * bytes so we start at a nice even number. + */ + return efi_low_alloc_above(sys_table_arg, size, align, addr, 0x8); +} efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg, unsigned long size, unsigned long align, @@ -1592,7 +1605,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg, unsigned long image_size, unsigned long alloc_size, unsigned long preferred_addr, - unsigned long alignment); + unsigned long alignment, + unsigned long min_addr); efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg, efi_loaded_image_t *image, 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/export.h b/include/linux/export.h index 95f55b7f83a0..941d075f03d6 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -18,8 +18,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#define NS_SEPARATOR "." - #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to * generate a checksums for some symbols */ @@ -48,14 +46,14 @@ extern struct module __this_module; * absolute relocations that require runtime processing on relocatable * kernels. */ -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ __ADDRESSABLE(sym) \ asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ " .balign 4 \n" \ - "__ksymtab_" #sym NS_SEPARATOR #ns ": \n" \ + "__ksymtab_" #sym ": \n" \ " .long " #sym "- . \n" \ " .long __kstrtab_" #sym "- . \n" \ - " .long __kstrtab_ns_" #sym "- . \n" \ + " .long __kstrtabns_" #sym "- . \n" \ " .previous \n") #define __KSYMTAB_ENTRY(sym, sec) \ @@ -74,16 +72,14 @@ struct kernel_symbol { int namespace_offset; }; #else -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ - static const struct kernel_symbol __ksymtab_##sym##__##ns \ - asm("__ksymtab_" #sym NS_SEPARATOR #ns) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ + static const struct kernel_symbol __ksymtab_##sym \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ - = { (unsigned long)&sym, __kstrtab_##sym, __kstrtab_ns_##sym } + = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } #define __KSYMTAB_ENTRY(sym, sec) \ static const struct kernel_symbol __ksymtab_##sym \ - asm("__ksymtab_" #sym) \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ = { (unsigned long)&sym, __kstrtab_##sym, NULL } @@ -112,10 +108,10 @@ struct kernel_symbol { /* For every exported symbol, place a struct in the __ksymtab section */ #define ___EXPORT_SYMBOL_NS(sym, sec, ns) \ ___export_symbol_common(sym, sec); \ - static const char __kstrtab_ns_##sym[] \ + static const char __kstrtabns_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ = #ns; \ - __KSYMTAB_ENTRY_NS(sym, sec, ns) + __KSYMTAB_ENTRY_NS(sym, sec) #define ___EXPORT_SYMBOL(sym, sec) \ ___export_symbol_common(sym, sec); \ 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/filter.h b/include/linux/filter.h index 2ce57645f3cd..0367a75f873b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1099,7 +1099,6 @@ static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym) #endif /* CONFIG_BPF_JIT */ -void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) 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/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/gfp.h b/include/linux/gfp.h index fb07b503dc45..61f2f6ff9467 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -325,6 +325,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) return !!(gfp_flags & __GFP_DIRECT_RECLAIM); } +/** + * gfpflags_normal_context - is gfp_flags a normal sleepable context? + * @gfp_flags: gfp_flags to test + * + * Test whether @gfp_flags indicates that the allocation is from the + * %current context and allowed to sleep. + * + * An allocation being allowed to block doesn't mean it owns the %current + * context. When direct reclaim path tries to allocate memory, the + * allocation context is nested inside whatever %current was doing at the + * time of the original allocation. The nested allocation may be allowed + * to block but modifying anything %current owns can corrupt the outer + * context's expectations. + * + * %true result from this function indicates that the allocation context + * can sleep and use anything that's associated with %current. + */ +static inline bool gfpflags_normal_context(const gfp_t gfp_flags) +{ + return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) == + __GFP_DIRECT_RECLAIM; +} + #ifdef CONFIG_HIGHMEM #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM #else diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f8245d67f070..5dd9c982e2cb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -202,6 +202,14 @@ struct gpio_irq_chip { bool threaded; /** + * @init_hw: optional routine to initialize hardware before + * an IRQ chip will be added. This is quite useful when + * a particular driver wants to clear IRQ related registers + * in order to avoid undesired events. + */ + int (*init_hw)(struct gpio_chip *chip); + + /** * @init_valid_mask: optional routine to initialize @valid_mask, to be * used if not all GPIO lines are valid interrupts. Sometimes some * lines just cannot fire interrupts, and this routine, when defined, diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 04c36b7a61dd..72579168189d 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -235,7 +235,7 @@ enum hwmon_power_attributes { #define HWMON_P_LABEL BIT(hwmon_power_label) #define HWMON_P_ALARM BIT(hwmon_power_alarm) #define HWMON_P_CAP_ALARM BIT(hwmon_power_cap_alarm) -#define HWMON_P_MIN_ALARM BIT(hwmon_power_max_alarm) +#define HWMON_P_MIN_ALARM BIT(hwmon_power_min_alarm) #define HWMON_P_MAX_ALARM BIT(hwmon_power_max_alarm) #define HWMON_P_LCRIT_ALARM BIT(hwmon_power_lcrit_alarm) #define HWMON_P_CRIT_ALARM BIT(hwmon_power_crit_alarm) diff --git a/include/linux/idr.h b/include/linux/idr.h index 4ec8986e5dfb..ac6e946b6767 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -185,7 +185,7 @@ static inline void idr_preload_end(void) * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 2e55e4cdbd8a..a367ead4bf4b 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -29,7 +29,6 @@ struct macvlan_dev { netdev_features_t set_features; enum macvlan_mode mode; u16 flags; - int nest_level; unsigned int macaddr_count; #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index 06faa066496f..ec7e4bd07f82 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -223,6 +223,7 @@ struct team { atomic_t count_pending; struct delayed_work dw; } mcast_rejoin; + struct lock_class_key team_lock_key; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 244278d5c222..b05e855f1ddd 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -182,7 +182,6 @@ struct vlan_dev_priv { #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif - unsigned int nest_level; }; static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev) @@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev, extern bool vlan_uses_dev(const struct net_device *dev); -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG_ON(!is_vlan_dev(dev)); - return vlan_dev_priv(dev)->nest_level; -} #else static inline struct net_device * __vlan_find_dev_deep_rcu(struct net_device *real_dev, @@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev) { return false; } -static inline int vlan_get_encap_level(struct net_device *dev) -{ - BUG(); - return 0; -} #endif /** diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index ed11ef594378..6d8bf4bdf240 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -336,7 +336,8 @@ enum { #define QI_DEV_IOTLB_SID(sid) ((u64)((sid) & 0xffff) << 32) #define QI_DEV_IOTLB_QDEP(qdep) (((qdep) & 0x1f) << 16) #define QI_DEV_IOTLB_ADDR(addr) ((u64)(addr) & VTD_PAGE_MASK) -#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_IOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_IOTLB_SIZE 1 #define QI_DEV_IOTLB_MAX_INVS 32 @@ -360,7 +361,8 @@ enum { #define QI_DEV_EIOTLB_PASID(p) (((u64)p) << 32) #define QI_DEV_EIOTLB_SID(sid) ((u64)((sid) & 0xffff) << 16) #define QI_DEV_EIOTLB_QDEP(qd) ((u64)((qd) & 0x1f) << 4) -#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | ((u64)(pfsid & 0xfff) << 52)) +#define QI_DEV_EIOTLB_PFSID(pfsid) (((u64)(pfsid & 0xf) << 12) | \ + ((u64)((pfsid >> 4) & 0xfff) << 52)) #define QI_DEV_EIOTLB_MAX_INVS 32 /* Page group response descriptor QW0 */ 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 fcb46b3374c6..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); @@ -966,6 +985,7 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); +bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; @@ -1090,6 +1110,7 @@ enum kvm_stat_kind { struct kvm_stat_data { int offset; + int mode; struct kvm *kvm; }; @@ -1097,6 +1118,7 @@ struct kvm_stats_debugfs_item { const char *name; int offset; enum kvm_stat_kind kind; + int mode; }; extern struct kvm_stats_debugfs_item debugfs_entries[]; extern struct dentry *kvm_debugfs_dir; @@ -1238,7 +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; @@ -1291,7 +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; @@ -1380,4 +1402,10 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) } #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ +typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data); + +int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, + uintptr_t data, const char *name, + struct task_struct **thread_ptr); + #endif 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/leds.h b/include/linux/leds.h index b8df71193329..efb309dba914 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -247,7 +247,7 @@ extern void led_set_brightness(struct led_classdev *led_cdev, /** * led_set_brightness_sync - set LED brightness synchronously * @led_cdev: the LED to set - * @brightness: the brightness to set it to + * @value: the brightness to set it to * * Set an LED's brightness immediately. This function will block * the caller for the time required for accessing device registers, @@ -301,8 +301,7 @@ extern void led_sysfs_enable(struct led_classdev *led_cdev); /** * led_compose_name - compose LED class device name * @dev: LED controller device object - * @child: child fwnode_handle describing a LED or a group of synchronized LEDs; - * it must be provided only for fwnode based LEDs + * @init_data: the LED class device initialization data * @led_classdev_name: composed LED class device name * * Create LED class device name basing on the provided init_data argument. 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/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/memcontrol.h b/include/linux/memcontrol.h index 9b60863429cc..ae703ea3ef48 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -356,6 +356,19 @@ static inline bool mem_cgroup_disabled(void) return !cgroup_subsys_enabled(memory_cgrp_subsys); } +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, + bool in_low_reclaim) +{ + if (mem_cgroup_disabled()) + return 0; + + if (in_low_reclaim) + return READ_ONCE(memcg->memory.emin); + + return max(READ_ONCE(memcg->memory.emin), + READ_ONCE(memcg->memory.elow)); +} + enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); @@ -537,6 +550,8 @@ void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); +unsigned long mem_cgroup_size(struct mem_cgroup *memcg); + void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); @@ -829,6 +844,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm, { } +static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg, + bool in_low_reclaim) +{ + return 0; +} + static inline enum mem_cgroup_protection mem_cgroup_protected( struct mem_cgroup *root, struct mem_cgroup *memcg) { @@ -968,6 +989,11 @@ static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return 0; } +static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return 0; +} + static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { @@ -1264,6 +1290,9 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { + if (mem_cgroup_disabled()) + return; + if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } diff --git a/include/linux/memory.h b/include/linux/memory.h index 0ebb105eb261..4c75dae8dd29 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -119,6 +119,7 @@ extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); +extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); #define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION<<PAGE_SHIFT) #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad24554f11f9..75f880c25bb8 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,7 +31,7 @@ #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -#define PHY_ID_KSZ8795 0x00221550 +#define PHY_ID_KSZ87XX 0x00221550 #define PHY_ID_KSZ9477 0x00221631 diff --git a/include/linux/mii.h b/include/linux/mii.h index 5cd824c1c0ca..4ce8901a1af6 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -455,6 +455,15 @@ static inline void mii_lpa_mod_linkmode_lpa_t(unsigned long *lp_advertising, lp_advertising, lpa & LPA_LPACK); } +static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising, + u32 ctrl1000) +{ + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, advertising, + ctrl1000 & ADVERTISE_1000HALF); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, advertising, + ctrl1000 & ADVERTISE_1000FULL); +} + /** * linkmode_adv_to_lcl_adv_t * @advertising:pointer to linkmode advertising diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 138c50d5a353..0836fe232f97 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1545,9 +1545,8 @@ struct mlx5_ifc_extended_dest_format_bits { }; union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits { - struct mlx5_ifc_dest_format_struct_bits dest_format_struct; + struct mlx5_ifc_extended_dest_format_bits extended_dest_format; struct mlx5_ifc_flow_counter_list_bits flow_counter_list; - u8 reserved_at_0[0x40]; }; struct mlx5_ifc_fte_match_param_bits { diff --git a/include/linux/mm.h b/include/linux/mm.h index cc292273e6ba..a2adf95b3f9c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2222fa795284..270aa8fd2800 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -221,6 +221,11 @@ struct page { #endif } _struct_page_alignment; +static inline atomic_t *compound_mapcount_ptr(struct page *page) +{ + return &page[1].compound_mapcount; +} + /* * Used for sizing the vmemmap region on some architectures */ 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/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 9eda1c31d1f7..c20f190b4c18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -925,6 +925,7 @@ struct dev_ifalias { struct devlink; struct tlsdev_ops; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -1421,7 +1422,6 @@ struct net_device_ops { void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); - int (*ndo_get_lock_subclass)(struct net_device *dev); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); @@ -1649,6 +1649,8 @@ enum netdev_priv_flags { * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length + * @upper_level: Maximum depth level of upper devices. + * @lower_level: Maximum depth level of lower devices. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address @@ -1758,9 +1760,13 @@ enum netdev_priv_flags { * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. - * - * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock + spinlock + * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount + * @qdisc_xmit_lock_key: lockdep class annotating + * netdev_queue->_xmit_lock spinlock + * @addr_list_lock_key: lockdep class annotating + * net_device->addr_list_lock spinlock * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -1875,6 +1881,8 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; + unsigned char upper_level; + unsigned char lower_level; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; @@ -2045,8 +2053,10 @@ struct net_device { #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; - struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; + struct lock_class_key qdisc_tx_busylock_key; + struct lock_class_key qdisc_running_key; + struct lock_class_key qdisc_xmit_lock_key; + struct lock_class_key addr_list_lock_key; bool proto_down; unsigned wol_enabled:1; }; @@ -2124,23 +2134,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } -#define netdev_lockdep_set_classes(dev) \ -{ \ - static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ - static struct lock_class_key qdisc_xmit_lock_key; \ - static struct lock_class_key dev_addr_list_lock_key; \ - unsigned int i; \ - \ - (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ - lockdep_set_class(&(dev)->addr_list_lock, \ - &dev_addr_list_lock_key); \ - for (i = 0; i < (dev)->num_tx_queues; i++) \ - lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ - &qdisc_xmit_lock_key); \ -} - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, @@ -3139,6 +3132,7 @@ static inline void netif_stop_queue(struct net_device *dev) } void netif_tx_stop_all_queues(struct net_device *dev); +void netdev_update_lockdep_key(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { @@ -4056,16 +4050,6 @@ static inline void netif_addr_lock(struct net_device *dev) spin_lock(&dev->addr_list_lock); } -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - int subclass = SINGLE_DEPTH_NESTING; - - if (dev->netdev_ops->ndo_get_lock_subclass) - subclass = dev->netdev_ops->ndo_get_lock_subclass(dev); - - spin_lock_nested(&dev->addr_list_lock, subclass); -} - static inline void netif_addr_lock_bh(struct net_device *dev) { spin_lock_bh(&dev->addr_list_lock); @@ -4329,6 +4313,16 @@ int netdev_master_upper_dev_link(struct net_device *dev, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack); +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); @@ -4340,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, 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/page-flags.h b/include/linux/page-flags.h index f91cb8898ff0..1bf83c8fcaa7 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -622,12 +622,28 @@ static inline int PageTransCompound(struct page *page) * * Unlike PageTransCompound, this is safe to be called only while * split_huge_pmd() cannot run from under us, like if protected by the - * MMU notifier, otherwise it may result in page->_mapcount < 0 false + * MMU notifier, otherwise it may result in page->_mapcount check false * positives. + * + * We have to treat page cache THP differently since every subpage of it + * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE + * mapped in the current process so comparing subpage's _mapcount to + * compound_mapcount to filter out PTE mapped case. */ static inline int PageTransCompoundMap(struct page *page) { - return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0; + struct page *head; + + if (!PageTransCompound(page)) + return 0; + + if (PageAnon(page)) + return atomic_read(&page->_mapcount) < 0; + + head = compound_head(page); + /* File THP is PMD mapped and not PTE mapped */ + return atomic_read(&page->_mapcount) == + atomic_read(compound_mapcount_ptr(head)); } /* diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 682fd465df06..cfce186f0c4e 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -18,7 +18,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, - PAGE_EXT_OWNER_ACTIVE, + PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, @@ -36,6 +36,7 @@ struct page_ext { unsigned long flags; }; +extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); #ifdef CONFIG_SPARSEMEM @@ -52,6 +53,13 @@ static inline void page_ext_init(void) struct page_ext *lookup_page_ext(const struct page *page); +static inline struct page_ext *page_ext_next(struct page_ext *curr) +{ + void *next = curr; + next += page_ext_size; + return next; +} + #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 61448c19a132..a07bfdb7d8ea 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -292,7 +292,7 @@ struct pmu { * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported - * -EACCESS -- @event is for this PMU, @event is valid, but no privilidges + * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * @@ -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 a7ecbe0e55aa..9a0e981df502 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -678,6 +678,7 @@ static inline bool phy_is_started(struct phy_device *phydev) return phydev->state >= PHY_UP; } +void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** @@ -1076,6 +1077,7 @@ int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); +int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); 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/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h index 6eaa53cef0bd..30e676b36b24 100644 --- a/include/linux/platform_data/dma-imx-sdma.h +++ b/include/linux/platform_data/dma-imx-sdma.h @@ -51,7 +51,10 @@ struct sdma_script_start_addrs { /* End of v2 array */ s32 zcanfd_2_mcu_addr; s32 zqspi_2_mcu_addr; + s32 mcu_2_ecspi_addr; /* End of v3 array */ + s32 mcu_2_zqspi_addr; + /* End of v4 array */ }; /** 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_device.h b/include/linux/platform_device.h index 1b5cec067533..f2688404d1cd 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -64,6 +64,8 @@ extern struct resource *platform_get_resource_byname(struct platform_device *, unsigned int, const char *); extern int platform_get_irq_byname(struct platform_device *, const char *); +extern int platform_get_irq_byname_optional(struct platform_device *dev, + const char *name); extern int platform_add_devices(struct platform_device **, int); struct platform_device_info { diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 222c3e01397c..ebf5ef17cc2a 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,8 +34,6 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 -#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 -#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE (-1) #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -54,8 +52,6 @@ struct pm_qos_flags_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_MIN_FREQUENCY, - DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -97,14 +93,10 @@ struct pm_qos_flags { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; - struct pm_qos_constraints min_frequency; - struct pm_qos_constraints max_frequency; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; struct dev_pm_qos_request *flags_req; - struct dev_pm_qos_request *min_frequency_req; - struct dev_pm_qos_request *max_frequency_req; }; /* Action requested to pm_qos_update_target */ @@ -199,10 +191,6 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; - case DEV_PM_QOS_MIN_FREQUENCY: - return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - case DEV_PM_QOS_MAX_FREQUENCY: - return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; @@ -267,4 +255,48 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + +static inline int freq_qos_request_active(struct freq_qos_request *req) +{ + return !IS_ERR_OR_NULL(req->qos); +} + +void freq_constraints_init(struct freq_constraints *qos); + +s32 freq_qos_read_value(struct freq_constraints *qos, + enum freq_qos_req_type type); + +int freq_qos_add_request(struct freq_constraints *qos, + struct freq_qos_request *req, + enum freq_qos_req_type type, s32 value); +int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); +int freq_qos_remove_request(struct freq_qos_request *req); + +int freq_qos_add_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); +int freq_qos_remove_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); + #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/radix-tree.h b/include/linux/radix-tree.h index b5116013f27e..63e62372443a 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -316,24 +316,6 @@ radix_tree_iter_lookup(const struct radix_tree_root *root, } /** - * radix_tree_iter_find - find a present entry - * @root: radix tree root - * @iter: iterator state - * @index: start location - * - * This function returns the slot containing the entry with the lowest index - * which is at least @index. If @index is larger than any present entry, this - * function returns NULL. The @iter is updated to describe the entry found. - */ -static inline void __rcu ** -radix_tree_iter_find(const struct radix_tree_root *root, - struct radix_tree_iter *iter, unsigned long index) -{ - radix_tree_iter_init(iter, index); - return radix_tree_next_chunk(root, iter, 0); -} - -/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h index 9326d671b6e6..eaae6b4e9f24 100644 --- a/include/linux/reset-controller.h +++ b/include/linux/reset-controller.h @@ -7,7 +7,7 @@ struct reset_controller_dev; /** - * struct reset_control_ops + * struct reset_control_ops - reset controller driver callbacks * * @reset: for self-deasserting resets, does all necessary * things to reset the device @@ -33,7 +33,7 @@ struct of_phandle_args; * @provider: name of the reset controller device controlling this reset line * @index: ID of the reset controller in the reset controller device * @dev_id: name of the device associated with this reset line - * @con_id name of the reset line (can be NULL) + * @con_id: name of the reset line (can be NULL) */ struct reset_control_lookup { struct list_head list; diff --git a/include/linux/reset.h b/include/linux/reset.h index e7793fc0fa93..eb597e8aa430 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -143,7 +143,7 @@ static inline int device_reset_optional(struct device *dev) * If this function is called more than once for the same reset_control it will * return -EBUSY. * - * See reset_control_get_shared for details on shared references to + * See reset_control_get_shared() for details on shared references to * reset-controls. * * Use of id names is optional. 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 2c2e56bd8913..6666e25606b7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -223,6 +223,7 @@ extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +asmlinkage void preempt_schedule_irq(void); extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); @@ -1467,6 +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/security.h b/include/linux/security.h index a8d59d612d27..9df7547afc0c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -105,6 +105,7 @@ enum lockdown_reason { LOCKDOWN_NONE, LOCKDOWN_MODULE_SIGNATURE, LOCKDOWN_DEV_MEM, + LOCKDOWN_EFI_TEST, LOCKDOWN_KEXEC, LOCKDOWN_HIBERNATION, LOCKDOWN_PCI_ACCESS, 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/skbuff.h b/include/linux/skbuff.h index e7d3b1a513ef..8688f7adfda7 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1354,7 +1354,8 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6 return skb->hash; } -__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb); +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb); static inline __u32 skb_get_hash_raw(const struct sk_buff *skb) { @@ -1495,6 +1496,19 @@ static inline int skb_queue_empty(const struct sk_buff_head *list) } /** + * skb_queue_empty_lockless - check if a queue is empty + * @list: queue head + * + * Returns true if the queue is empty, false otherwise. + * This variant can be used in lockless contexts. + */ +static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list) +{ + return READ_ONCE(list->next) == (const struct sk_buff *) list; +} + + +/** * skb_queue_is_last - check if skb is the last entry in the queue * @list: queue head * @skb: buffer @@ -1847,9 +1861,11 @@ static inline void __skb_insert(struct sk_buff *newsk, struct sk_buff *prev, struct sk_buff *next, struct sk_buff_head *list) { - newsk->next = next; - newsk->prev = prev; - next->prev = prev->next = newsk; + /* see skb_queue_empty_lockless() for the opposite READ_ONCE() */ + WRITE_ONCE(newsk->next, next); + WRITE_ONCE(newsk->prev, prev); + WRITE_ONCE(next->prev, newsk); + WRITE_ONCE(prev->next, newsk); list->qlen++; } @@ -1860,11 +1876,11 @@ static inline void __skb_queue_splice(const struct sk_buff_head *list, struct sk_buff *first = list->next; struct sk_buff *last = list->prev; - first->prev = prev; - prev->next = first; + WRITE_ONCE(first->prev, prev); + WRITE_ONCE(prev->next, first); - last->next = next; - next->prev = last; + WRITE_ONCE(last->next, next); + WRITE_ONCE(next->prev, last); } /** @@ -2005,8 +2021,8 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; - next->prev = prev; - prev->next = next; + WRITE_ONCE(next->prev, prev); + WRITE_ONCE(prev->next, next); } /** @@ -3510,8 +3526,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, @@ -4152,23 +4169,26 @@ 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(struct sk_buff *skb) +static inline void nf_reset_ct(struct sk_buff *skb) { #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) nf_conntrack_put(skb_nfct(skb)); skb->_nfct = 0; #endif -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - skb_ext_del(skb, SKB_EXT_BRIDGE_NF); -#endif } static inline void nf_reset_trace(struct sk_buff *skb) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e4b3fb4bb77c..ce7055259877 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -139,6 +139,11 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes) } } +static inline u32 sk_msg_iter_dist(u32 start, u32 end) +{ + return end >= start ? end - start : end + (MAX_MSG_FRAGS - start); +} + #define sk_msg_iter_var_prev(var) \ do { \ if (var == 0) \ @@ -198,9 +203,7 @@ static inline u32 sk_msg_elem_used(const struct sk_msg *msg) if (sk_msg_full(msg)) return MAX_MSG_FRAGS; - return msg->sg.end >= msg->sg.start ? - msg->sg.end - msg->sg.start : - msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start); + return sk_msg_iter_dist(msg->sg.start, msg->sg.end); } static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which) diff --git a/include/linux/slab.h b/include/linux/slab.h index ab2b98ad76e1..4d2a2fa55ed5 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -493,6 +493,10 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * + * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN + * bytes. For @size of power of two bytes, the alignment is also guaranteed + * to be at least to the size. + * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` diff --git a/include/linux/socket.h b/include/linux/socket.h index fc0bed59fc84..09c32a21555b 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -263,7 +263,7 @@ struct ucred { #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ -#define SOMAXCONN 128 +#define SOMAXCONN 4096 /* Flags we can use with send/ and recv. Added those for 1003.1g not all are supported yet @@ -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/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/string.h b/include/linux/string.h index b2f9df7f0761..b6ccdc2c7f02 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -227,7 +227,26 @@ static inline bool strstarts(const char *str, const char *prefix) } size_t memweight(const void *ptr, size_t bytes); -void memzero_explicit(void *s, size_t count); + +/** + * memzero_explicit - Fill a region of memory (e.g. sensitive + * keying data) with 0s. + * @s: Pointer to the start of the area. + * @count: The size of the area. + * + * Note: usually using memset() is just fine (!), but in cases + * where clearing out _local_ data at the end of a scope is + * necessary, memzero_explicit() should be used instead in + * order to prevent the compiler from optimising away zeroing. + * + * memzero_explicit() doesn't need an arch-specific version as + * it just invokes the one of memset() implicitly. + */ +static inline void memzero_explicit(void *s, size_t count) +{ + memset(s, 0, count); + barrier_data(s); +} /** * kbasename - return the last part of a pathname. diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h index 87d27e13d885..d796058cdff2 100644 --- a/include/linux/sunrpc/bc_xprt.h +++ b/include/linux/sunrpc/bc_xprt.h @@ -64,6 +64,11 @@ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt, return 0; } +static inline void xprt_destroy_backchannel(struct rpc_xprt *xprt, + unsigned int max_reqs) +{ +} + static inline bool svc_is_backchannel(const struct svc_rqst *rqstp) { return false; diff --git a/include/linux/sunrpc/xprtsock.h b/include/linux/sunrpc/xprtsock.h index 7638dbe7bc50..a940de03808d 100644 --- a/include/linux/sunrpc/xprtsock.h +++ b/include/linux/sunrpc/xprtsock.h @@ -61,6 +61,7 @@ struct sock_xprt { struct mutex recv_mutex; struct sockaddr_storage srcaddr; unsigned short srcport; + int xprt_err; /* * UDP socket buffer size parameters diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 5420817ed317..fa7ee503fb76 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -196,9 +196,9 @@ struct bin_attribute { .size = _size, \ } -#define __BIN_ATTR_WO(_name) { \ +#define __BIN_ATTR_WO(_name, _size) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ - .store = _name##_store, \ + .write = _name##_write, \ .size = _size, \ } diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 99617e528ea2..668e25a76d69 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -393,7 +393,7 @@ struct tcp_sock { /* fastopen_rsk points to request_sock that resulted in this big * socket. Used to retransmit SYNACKs etc. */ - struct request_sock *fastopen_rsk; + struct request_sock __rcu *fastopen_rsk; u32 *saved_syn; }; @@ -447,8 +447,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) static inline bool tcp_passive_fastopen(const struct sock *sk) { - return (sk->sk_state == TCP_SYN_RECV && - tcp_sk(sk)->fastopen_rsk != NULL); + return sk->sk_state == TCP_SYN_RECV && + rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL; } static inline void fastopen_queue_tune(struct sock *sk, int backlog) 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/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 63238c84dc0b..131ea1bad458 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -152,7 +152,7 @@ struct tcg_algorithm_info { * total. Once we've done this we know the offset of the data length field, * and can calculate the total size of the event. * - * Return: size of the event on success, <0 on failure + * Return: size of the event on success, 0 on failure */ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, @@ -170,6 +170,7 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, u16 halg; int i; int j; + u32 count, event_type; marker = event; marker_start = marker; @@ -190,16 +191,22 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, } event = (struct tcg_pcr_event2_head *)mapping; + /* + * The loop below will unmap these fields if the log is larger than + * one page, so save them here for reference: + */ + count = READ_ONCE(event->count); + event_type = READ_ONCE(event->event_type); efispecid = (struct tcg_efi_specid_event_head *)event_header->event; /* Check if event is malformed. */ - if (event->count > efispecid->num_algs) { + if (count > efispecid->num_algs) { size = 0; goto out; } - for (i = 0; i < event->count; i++) { + for (i = 0; i < count; i++) { halg_size = sizeof(event->digests[i].alg_id); /* Map the digest's algorithm identifier */ @@ -256,8 +263,9 @@ static inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *event, + event_field->event_size; size = marker - marker_start; - if ((event->event_type == 0) && (event_field->event_size == 0)) + if (event_type == 0 && event_field->event_size == 0) size = 0; + out: if (do_mapping) TPM_MEMUNMAP(mapping, mapping_size); diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 70bbdc38dc37..d4ee6e942562 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,76 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from, #endif /* ARCH_HAS_NOCACHE_UACCESS */ +extern __must_check int check_zeroed_user(const void __user *from, size_t size); + +/** + * copy_struct_from_user: copy a struct from userspace + * @dst: Destination address, in kernel space. This buffer must be @ksize + * bytes long. + * @ksize: Size of @dst struct. + * @src: Source address, in userspace. + * @usize: (Alleged) size of @src struct. + * + * Copies a struct from userspace to kernel space, in a way that guarantees + * backwards-compatibility for struct syscall arguments (as long as future + * struct extensions are made such that all new fields are *appended* to the + * old struct, and zeroed-out new fields have the same meaning as the old + * struct). + * + * @ksize is just sizeof(*dst), and @usize should've been passed by userspace. + * The recommended usage is something like the following: + * + * SYSCALL_DEFINE2(foobar, const struct foo __user *, uarg, size_t, usize) + * { + * int err; + * struct foo karg = {}; + * + * if (usize > PAGE_SIZE) + * return -E2BIG; + * if (usize < FOO_SIZE_VER0) + * return -EINVAL; + * + * err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + * if (err) + * return err; + * + * // ... + * } + * + * There are three cases to consider: + * * If @usize == @ksize, then it's copied verbatim. + * * If @usize < @ksize, then the userspace has passed an old struct to a + * newer kernel. The rest of the trailing bytes in @dst (@ksize - @usize) + * are to be zero-filled. + * * If @usize > @ksize, then the userspace has passed a new struct to an + * older kernel. The trailing bytes unknown to the kernel (@usize - @ksize) + * are checked to ensure they are zeroed, otherwise -E2BIG is returned. + * + * Returns (in all cases, some data may have been copied): + * * -E2BIG: (@usize > @ksize) and there are non-zero trailing bytes in @src. + * * -EFAULT: access to userspace failed. + */ +static __always_inline __must_check int +copy_struct_from_user(void *dst, size_t ksize, const void __user *src, + size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + /* Deal with trailing bytes. */ + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + int ret = check_zeroed_user(src + size, rest); + if (ret <= 0) + return ret ?: -E2BIG; + } + /* Copy the interoperable parts of the struct. */ + if (copy_from_user(dst, src, size)) + return -EFAULT; + return 0; +} + /* * probe_kernel_read(): safely attempt to read from a location * @dst: pointer to the buffer that shall take the data @@ -285,8 +355,10 @@ extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) -#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) +#define unsafe_get_user(x,p,e) unsafe_op_wrap(__get_user(x,p),e) +#define unsafe_put_user(x,p,e) unsafe_op_wrap(__put_user(x,p),e) +#define unsafe_copy_to_user(d,s,l,e) unsafe_op_wrap(__copy_to_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } #endif diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 4c7781f4b29b..07875ccc7bb5 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,7 +48,6 @@ struct virtio_vsock_sock { struct virtio_vsock_pkt { struct virtio_vsock_hdr hdr; - struct work_struct work; struct list_head list; /* socket refcnt not held, only use for cancellation */ struct vsock_sock *vsk; diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5921599b6dc4..86eecbd98e84 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -230,8 +230,8 @@ static inline int xa_err(void *entry) * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: - * * xa_limit_32b - [0 - UINT_MAX] - * * xa_limit_31b - [0 - INT_MAX] + * * xa_limit_32b - [0 - UINT_MAX] + * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; |