diff options
Diffstat (limited to 'include')
75 files changed, 739 insertions, 371 deletions
diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h deleted file mode 100644 index 69021830f078..000000000000 --- a/include/asm-generic/bugs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_BUGS_H -#define __ASM_GENERIC_BUGS_H -/* - * This file is included by 'init/main.c' to check for - * architecture-dependent bugs. - */ - -static inline void check_bugs(void) { } - -#endif /* __ASM_GENERIC_BUGS_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index cebdf1ca415d..da9e5629ea43 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -839,6 +839,9 @@ #ifdef CONFIG_UNWINDER_ORC #define ORC_UNWIND_TABLE \ + .orc_header : AT(ADDR(.orc_header) - LOAD_OFFSET) { \ + BOUNDED_SECTION_BY(.orc_header, _orc_header) \ + } \ . = ALIGN(4); \ .orc_unwind_ip : AT(ADDR(.orc_unwind_ip) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.orc_unwind_ip, _orc_unwind_ip) \ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7b71dd74baeb..5ef126a0a50f 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1507,6 +1507,12 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) } #endif +#ifdef CONFIG_ARM64 +void acpi_arm_init(void); +#else +static inline void acpi_arm_init(void) { } +#endif + #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else diff --git a/include/linux/acpi_agdi.h b/include/linux/acpi_agdi.h deleted file mode 100644 index f477f0b452fa..000000000000 --- a/include/linux/acpi_agdi.h +++ /dev/null @@ -1,13 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ - -#ifndef __ACPI_AGDI_H__ -#define __ACPI_AGDI_H__ - -#include <linux/acpi.h> - -#ifdef CONFIG_ACPI_AGDI -void __init acpi_agdi_init(void); -#else -static inline void acpi_agdi_init(void) {} -#endif -#endif /* __ACPI_AGDI_H__ */ diff --git a/include/linux/acpi_apmt.h b/include/linux/acpi_apmt.h deleted file mode 100644 index 40bd634d082f..000000000000 --- a/include/linux/acpi_apmt.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 - * - * ARM CoreSight PMU driver. - * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. - * - */ - -#ifndef __ACPI_APMT_H__ -#define __ACPI_APMT_H__ - -#include <linux/acpi.h> - -#ifdef CONFIG_ACPI_APMT -void acpi_apmt_init(void); -#else -static inline void acpi_apmt_init(void) { } -#endif /* CONFIG_ACPI_APMT */ - -#endif /* __ACPI_APMT_H__ */ diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index b43be0987b19..ee7cb6aaff71 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,13 +26,13 @@ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); +int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); + #ifdef CONFIG_ACPI_IORT -void acpi_iort_init(void); u32 iort_msi_map_id(struct device *dev, u32 id); struct irq_domain *iort_get_device_domain(struct device *dev, u32 id, enum irq_domain_bus_token bus_token); void acpi_configure_pmsi_domain(struct device *dev); -int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head); void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, @@ -43,7 +43,6 @@ int iort_iommu_configure_id(struct device *dev, const u32 *id_in); void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head); phys_addr_t acpi_iort_dma_get_max_cpu_address(void); #else -static inline void acpi_iort_init(void) { } static inline u32 iort_msi_map_id(struct device *dev, u32 id) { return id; } static inline struct irq_domain *iort_get_device_domain( diff --git a/include/linux/bio.h b/include/linux/bio.h index b3e7529ff55e..c4f5b5228105 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -229,7 +229,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count) static inline bool bio_flagged(struct bio *bio, unsigned int bit) { - return (bio->bi_flags & (1U << bit)) != 0; + return bio->bi_flags & (1U << bit); } static inline void bio_set_flag(struct bio *bio, unsigned int bit) @@ -465,14 +465,18 @@ extern void bio_uninit(struct bio *); void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf); void bio_chain(struct bio *, struct bio *); -int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); -bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); +int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len, + unsigned off); +bool __must_check bio_add_folio(struct bio *bio, struct folio *folio, + size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); +void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len, + size_t off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); @@ -488,7 +492,7 @@ void zero_fill_bio(struct bio *bio); static inline void bio_release_pages(struct bio *bio, bool mark_dirty) { - if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + if (bio_flagged(bio, BIO_PAGE_PINNED)) __bio_release_pages(bio, mark_dirty); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 06caacd77ed6..f401067ac03a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -28,8 +28,6 @@ typedef __u32 __bitwise req_flags_t; /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* may not be passed by ioscheduler */ -#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ @@ -38,12 +36,14 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* use hctx->sched_tags */ +#define RQF_SCHED_TAGS ((__force req_flags_t)(1 << 8)) +/* use an I/O scheduler for this request */ +#define RQF_USE_SCHED ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* elevator private data attached */ -#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* runtime pm request */ @@ -59,13 +59,11 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) -/* queue has elevator attached */ -#define RQF_ELV ((__force req_flags_t)(1 << 22)) -#define RQF_RESV ((__force req_flags_t)(1 << 23)) +#define RQF_RESV ((__force req_flags_t)(1 << 23)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + (RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) enum mq_rq_state { MQ_RQ_IDLE = 0, @@ -169,25 +167,20 @@ struct request { void *completion_data; }; - /* * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. + * more they have to dynamically allocate it. */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; union { struct __call_single_data csd; @@ -208,7 +201,7 @@ static inline enum req_op req_op(const struct request *req) static inline bool blk_rq_is_passthrough(struct request *rq) { - return blk_op_is_passthrough(req_op(rq)); + return blk_op_is_passthrough(rq->cmd_flags); } static inline unsigned short req_get_ioprio(struct request *req) @@ -746,8 +739,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, struct blk_mq_tags { unsigned int nr_tags; unsigned int nr_reserved_tags; - - atomic_t active_queues; + unsigned int active_queues; struct sbitmap_queue bitmap_tags; struct sbitmap_queue breserved_tags; @@ -844,7 +836,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib); */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED)); } static inline bool blk_mq_is_reserved_rq(struct request *rq) @@ -860,7 +852,7 @@ static inline bool blk_mq_add_to_batch(struct request *req, struct io_comp_batch *iob, int ioerror, void (*complete)(struct io_comp_batch *)) { - if (!iob || (req->rq_flags & RQF_ELV) || ioerror || + if (!iob || (req->rq_flags & RQF_USE_SCHED) || ioerror || (req->end_io && !blk_rq_is_passthrough(req))) return false; @@ -1164,6 +1156,18 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq)); } +/** + * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization. + * @rq: Request to examine. + * + * Note: REQ_OP_ZONE_APPEND requests do not require serialization. + */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return op_needs_zoned_write_locking(req_op(rq)) && + blk_rq_zone_is_seq(rq); +} + bool blk_req_needs_zone_write_lock(struct request *rq); bool blk_req_zone_write_trylock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); @@ -1194,6 +1198,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) return !blk_req_zone_is_write_locked(rq); } #else /* CONFIG_BLK_DEV_ZONED */ +static inline bool blk_rq_is_seq_zoned_write(struct request *rq) +{ + return false; +} + static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 740afe80f297..752a54e3284b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -55,6 +55,8 @@ struct block_device { struct super_block * bd_super; void * bd_claiming; void * bd_holder; + const struct blk_holder_ops *bd_holder_ops; + struct mutex bd_holder_lock; /* The counter of freeze processes */ int bd_fsfreeze_count; int bd_holders; @@ -323,7 +325,7 @@ struct bio { * bio flags */ enum { - BIO_NO_PAGE_REF, /* don't put release vec pages */ + BIO_PAGE_PINNED, /* Unpin pages in bio_release_pages() */ BIO_CLONED, /* doesn't own data */ BIO_BOUNCED, /* bio is a bounce bio */ BIO_QUIET, /* Make BIO Quiet */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0ffe203a602..ed44a997f629 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -41,7 +41,7 @@ struct blk_stat_callback; struct blk_crypto_profile; extern const struct device_type disk_type; -extern struct device_type part_type; +extern const struct device_type part_type; extern struct class block_class; /* @@ -112,6 +112,19 @@ struct blk_integrity { unsigned char tag_size; }; +typedef unsigned int __bitwise blk_mode_t; + +/* open for reading */ +#define BLK_OPEN_READ ((__force blk_mode_t)(1 << 0)) +/* open for writing */ +#define BLK_OPEN_WRITE ((__force blk_mode_t)(1 << 1)) +/* open exclusively (vs other exclusive openers */ +#define BLK_OPEN_EXCL ((__force blk_mode_t)(1 << 2)) +/* opened with O_NDELAY */ +#define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) +/* open for "writes" only for ioctls (specialy hack for floppy.c) */ +#define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) + struct gendisk { /* * major/first_minor/minors should not be set by any new driver, the @@ -187,6 +200,7 @@ struct gendisk { struct badblocks *bb; struct lockdep_map lockdep_map; u64 diskseq; + blk_mode_t open_mode; /* * Independent sector access ranges. This is always NULL for @@ -318,7 +332,6 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); #ifdef CONFIG_BLK_DEV_ZONED - #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); @@ -328,33 +341,11 @@ extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, gfp_t gfp_mask); int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(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_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg); - #else /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int bdev_nr_zones(struct block_device *bdev) { return 0; } - -static inline int blkdev_report_zones_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - -static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, - fmode_t mode, unsigned int cmd, - unsigned long arg) -{ - return -ENOTTY; -} - #endif /* CONFIG_BLK_DEV_ZONED */ /* @@ -392,6 +383,7 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; + struct mutex rq_qos_mutex; const struct blk_mq_ops *mq_ops; @@ -487,6 +479,7 @@ struct request_queue { * for flush operations */ struct blk_flush_queue *fq; + struct list_head flush_list; struct list_head requeue_list; spinlock_t requeue_lock; @@ -815,7 +808,7 @@ int __register_blkdev(unsigned int major, const char *name, __register_blkdev(major, name, NULL) void unregister_blkdev(unsigned int major, const char *name); -bool bdev_check_media_change(struct block_device *bdev); +bool disk_check_media_change(struct gendisk *disk); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); @@ -836,7 +829,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, dev_t part_devt(struct gendisk *disk, u8 partno); void inc_diskseq(struct gendisk *disk); -dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); extern int blk_register_queue(struct gendisk *disk); @@ -1281,15 +1273,18 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -static inline bool bdev_op_is_zoned_write(struct block_device *bdev, - blk_opf_t op) +/* Whether write serialization is required for @op on zoned devices. */ +static inline bool op_needs_zoned_write_locking(enum req_op op) { - if (!bdev_is_zoned(bdev)) - return false; - return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES; } +static inline bool bdev_op_is_zoned_write(struct block_device *bdev, + enum req_op op) +{ + return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op); +} + static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); @@ -1380,10 +1375,12 @@ struct block_device_operations { void (*submit_bio)(struct bio *bio); int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); - int (*open) (struct block_device *, fmode_t); - void (*release) (struct gendisk *, fmode_t); - int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); - int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); + int (*open)(struct gendisk *disk, blk_mode_t mode); + void (*release)(struct gendisk *disk); + int (*ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); + int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode, + unsigned cmd, unsigned long arg); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); void (*unlock_native_capacity) (struct gendisk *); @@ -1410,7 +1407,7 @@ struct block_device_operations { }; #ifdef CONFIG_COMPAT -extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t, +extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t, unsigned int, unsigned long); #else #define blkdev_compat_ptr_ioctl NULL @@ -1463,22 +1460,31 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #define BLKDEV_MAJOR_MAX 0 #endif -struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -int bd_prepare_to_claim(struct block_device *bdev, void *holder); +struct blk_holder_ops { + void (*mark_dead)(struct block_device *bdev); +}; + +/* + * Return the correct open flags for blkdev_get_by_* for super block flags + * as stored in sb->s_flags. + */ +#define sb_open_mode(flags) \ + (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) + +struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops); +struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, + void *holder, const struct blk_holder_ops *hops); +int bd_prepare_to_claim(struct block_device *bdev, void *holder, + const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void blkdev_put(struct block_device *bdev, fmode_t mode); +void blkdev_put(struct block_device *bdev, void *holder); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); -struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); -void bdev_add(struct block_device *bdev, dev_t dev); struct block_device *I_BDEV(struct inode *inode); -int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, - loff_t lend); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1488,6 +1494,7 @@ int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); void bdev_statx_dioalign(struct inode *inode, struct kstat *stat); void printk_all_partitions(void); +int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1509,6 +1516,10 @@ static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat) static inline void printk_all_partitions(void) { } +static inline int early_lookup_bdev(const char *pathname, dev_t *dev) +{ + return -EINVAL; +} #endif /* CONFIG_BLOCK */ int fsync_bdev(struct block_device *bdev); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index cfbda114348c..122c62e561fc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -85,10 +85,14 @@ extern int blk_trace_remove(struct request_queue *q); # define blk_add_driver_data(rq, data, len) do {} while (0) # define blk_trace_setup(q, name, dev, bdev, arg) (-ENOTTY) # define blk_trace_startstop(q, start) (-ENOTTY) -# define blk_trace_remove(q) (-ENOTTY) # define blk_add_trace_msg(q, fmt, ...) do { } while (0) # define blk_add_cgroup_trace_msg(q, cg, fmt, ...) do { } while (0) # define blk_trace_note_message_enabled(q) (false) + +static inline int blk_trace_remove(struct request_queue *q) +{ + return -ENOTTY; +} #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_COMPAT diff --git a/include/linux/bsg.h b/include/linux/bsg.h index 1ac81c809da9..ee2df73edf83 100644 --- a/include/linux/bsg.h +++ b/include/linux/bsg.h @@ -9,7 +9,7 @@ struct device; struct request_queue; typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr, - fmode_t mode, unsigned int timeout); + bool open_for_write, unsigned int timeout); struct bsg_device *bsg_register_queue(struct request_queue *q, struct device *parent, const char *name, diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 67caa909e3e6..98c6fd0b39b6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -13,6 +13,7 @@ #include <linux/fs.h> /* not really needed, later.. */ #include <linux/list.h> +#include <linux/blkdev.h> #include <scsi/scsi_common.h> #include <uapi/linux/cdrom.h> @@ -61,9 +62,9 @@ struct cdrom_device_info { __u8 last_sense; __u8 media_written; /* dirty flag, DVD+RW bookkeeping */ unsigned short mmc3_profile; /* current MMC3 profile */ - int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + bool opened_for_data; __s64 last_media_change_ms; }; @@ -101,11 +102,10 @@ int cdrom_read_tocentry(struct cdrom_device_info *cdi, struct cdrom_tocentry *entry); /* the general block_device operations structure: */ -extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode); -extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode); -extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, - fmode_t mode, unsigned int cmd, unsigned long arg); +int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode); +void cdrom_release(struct cdrom_device_info *cdi); +int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, + unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 8582a7142623..6e6e57ec69e8 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -184,8 +184,12 @@ void arch_cpu_idle_enter(void); void arch_cpu_idle_exit(void); void __noreturn arch_cpu_idle_dead(void); -int cpu_report_state(int cpu); -int cpu_check_up_prepare(int cpu); +#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT +void arch_cpu_finalize_init(void); +#else +static inline void arch_cpu_finalize_init(void) { } +#endif + void cpu_set_state_online(int cpu); void play_idle_precise(u64 duration_ns, u64 latency_ns); @@ -195,8 +199,6 @@ static inline void play_idle(unsigned long duration_us) } #ifdef CONFIG_HOTPLUG_CPU -bool cpu_wait_death(unsigned int cpu, int seconds); -bool cpu_report_death(void); void cpuhp_report_idle_dead(void); #else static inline void cpuhp_report_idle_dead(void) { } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 3ceb9dfa0993..25b6e6e6ba6b 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -133,6 +133,7 @@ enum cpuhp_state { CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, + CPUHP_BP_KICK_AP, CPUHP_BRINGUP_CPU, /* @@ -518,4 +519,20 @@ void cpuhp_online_idle(enum cpuhp_state state); static inline void cpuhp_online_idle(enum cpuhp_state state) { } #endif +struct task_struct; + +void cpuhp_ap_sync_alive(void); +void arch_cpuhp_sync_state_poll(void); +void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu); +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle); +bool arch_cpuhp_init_parallel_bringup(void); + +#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD +void cpuhp_ap_report_dead(void); +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu); +#else +static inline void cpuhp_ap_report_dead(void) { } +static inline void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } +#endif + #endif diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a52d2b9a6846..69d0435c7ebb 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -166,17 +166,15 @@ void dm_error(const char *message); struct dm_dev { struct block_device *bdev; struct dax_device *dax_dev; - fmode_t mode; + blk_mode_t mode; char name[16]; }; -dev_t dm_get_dev_t(const char *path); - /* * Constructors should call these functions to ensure destination devices * are opened/closed correctly. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, +int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, struct dm_dev **result); void dm_put_device(struct dm_target *ti, struct dm_dev *d); @@ -545,7 +543,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo); /* * First create an empty table. */ -int dm_table_create(struct dm_table **result, fmode_t mode, +int dm_table_create(struct dm_table **result, blk_mode_t mode, unsigned int num_targets, struct mapped_device *md); /* @@ -588,7 +586,7 @@ void dm_sync_table(struct mapped_device *md); * Queries */ sector_t dm_table_get_size(struct dm_table *t); -fmode_t dm_table_get_mode(struct dm_table *t); +blk_mode_t dm_table_get_mode(struct dm_table *t); struct mapped_device *dm_table_get_md(struct dm_table *t); const char *dm_table_device_name(struct dm_table *t); diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index c244267a6744..7738f458995f 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -126,7 +126,7 @@ int __must_check driver_register(struct device_driver *drv); void driver_unregister(struct device_driver *drv); struct device_driver *driver_find(const char *name, const struct bus_type *bus); -int driver_probe_done(void); +bool __init driver_probe_done(void); void wait_for_device_probe(void); void __init wait_for_init_devices_probe(void); diff --git a/include/linux/efi.h b/include/linux/efi.h index 571d1a6e1b74..18d83a613635 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -108,7 +108,8 @@ typedef struct { #define EFI_MEMORY_MAPPED_IO_PORT_SPACE 12 #define EFI_PAL_CODE 13 #define EFI_PERSISTENT_MEMORY 14 -#define EFI_MAX_MEMORY_TYPE 15 +#define EFI_UNACCEPTED_MEMORY 15 +#define EFI_MAX_MEMORY_TYPE 16 /* Attribute values: */ #define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ @@ -417,6 +418,7 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) #define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) #define LINUX_EFI_BOOT_MEMMAP_GUID EFI_GUID(0x800f683f, 0xd08b, 0x423a, 0xa2, 0x93, 0x96, 0x5c, 0x3c, 0x6f, 0xe2, 0xb4) +#define LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID EFI_GUID(0xd5d1de3c, 0x105c, 0x44f9, 0x9e, 0xa9, 0xbc, 0xef, 0x98, 0x12, 0x00, 0x31) #define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) @@ -435,6 +437,9 @@ void efi_native_runtime_setup(void); #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) #define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) +/* OVMF protocol GUIDs */ +#define OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID EFI_GUID(0xc5a010fe, 0x38a7, 0x4531, 0x8a, 0x4a, 0x05, 0x00, 0xd2, 0xfd, 0x16, 0x49) + typedef struct { efi_guid_t guid; u64 table; @@ -534,6 +539,14 @@ struct efi_boot_memmap { efi_memory_desc_t map[]; }; +struct efi_unaccepted_memory { + u32 version; + u32 unit_size; + u64 phys_base; + u64 size; + unsigned long bitmap[]; +}; + /* * Architecture independent structure for describing a memory map for the * benefit of efi_memmap_init_early(), and for passing context between @@ -636,6 +649,7 @@ extern struct efi { unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ unsigned long coco_secret; /* Confidential computing secret table */ + unsigned long unaccepted; /* Unaccepted memory table */ efi_get_time_t *get_time; efi_set_time_t *set_time; diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h index 36a486505b08..b9d83652c097 100644 --- a/include/linux/eventfd.h +++ b/include/linux/eventfd.h @@ -9,12 +9,12 @@ #ifndef _LINUX_EVENTFD_H #define _LINUX_EVENTFD_H -#include <linux/fcntl.h> #include <linux/wait.h> #include <linux/err.h> #include <linux/percpu-defs.h> #include <linux/percpu.h> #include <linux/sched.h> +#include <uapi/linux/eventfd.h> /* * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining @@ -23,10 +23,6 @@ * from eventfd, in order to leave a free define-space for * shared O_* flags. */ -#define EFD_SEMAPHORE (1 << 0) -#define EFD_CLOEXEC O_CLOEXEC -#define EFD_NONBLOCK O_NONBLOCK - #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK) #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE) @@ -40,7 +36,7 @@ struct file *eventfd_fget(int fd); struct eventfd_ctx *eventfd_ctx_fdget(int fd); struct eventfd_ctx *eventfd_ctx_fileget(struct file *file); __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n); -__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask); +__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, __poll_t mask); int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait, __u64 *cnt); void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt); diff --git a/include/linux/fs.h b/include/linux/fs.h index 133f0640fb24..ed5b32dc2625 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -119,13 +119,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) -/* File is opened with O_NDELAY (only set for block devices) */ -#define FMODE_NDELAY ((__force fmode_t)0x40) -/* File is opened with O_EXCL (only set for block devices) */ -#define FMODE_EXCL ((__force fmode_t)0x80) -/* File is opened using open(.., 3, ..) and is writeable only for ioctls - (specialy hack for floppy.c) */ -#define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ @@ -171,6 +164,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports non-exclusive O_DIRECT writes from multiple threads */ #define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* File is embedded in backing_file object */ +#define FMODE_BACKING ((__force fmode_t)0x2000000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -956,29 +952,35 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } +/* + * f_{lock,count,pos_lock} members can be highly contended and share + * the same cacheline. f_{lock,mode} are very frequently used together + * and so share the same cacheline as well. The read-mostly + * f_{path,inode,op} are kept on a separate cacheline. + */ struct file { union { struct llist_node f_llist; struct rcu_head f_rcuhead; unsigned int f_iocb_flags; }; - struct path f_path; - struct inode *f_inode; /* cached value */ - const struct file_operations *f_op; /* * Protects f_ep, f_flags. * Must not be taken from IRQ context. */ spinlock_t f_lock; - atomic_long_t f_count; - unsigned int f_flags; fmode_t f_mode; + atomic_long_t f_count; struct mutex f_pos_lock; loff_t f_pos; + unsigned int f_flags; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; + struct path f_path; + struct inode *f_inode; /* cached value */ + const struct file_operations *f_op; u64 f_version; #ifdef CONFIG_SECURITY @@ -1215,7 +1217,6 @@ struct super_block { uuid_t s_uuid; /* UUID */ unsigned int s_max_links; - fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business @@ -1242,7 +1243,7 @@ struct super_block { */ atomic_long_t s_fsnotify_connectors; - /* Being remounted read-only */ + /* Read-only state of the superblock is being changed */ int s_readonly_remount; /* per-sb errseq_t for reporting writeback errors via syncfs */ @@ -1672,9 +1673,12 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap, WHITEOUT_DEV); } -struct file *vfs_tmpfile_open(struct mnt_idmap *idmap, - const struct path *parentpath, - umode_t mode, int open_flag, const struct cred *cred); +struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, + const struct path *parentpath, + umode_t mode, int open_flag, + const struct cred *cred); +struct file *kernel_file_open(const struct path *path, int flags, + struct inode *inode, const struct cred *cred); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), @@ -1932,6 +1936,7 @@ struct super_operations { struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); + void (*shutdown)(struct super_block *sb); }; /* @@ -2349,11 +2354,31 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt, return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root}, name, flags, mode); } -extern struct file * dentry_open(const struct path *, int, const struct cred *); -extern struct file *dentry_create(const struct path *path, int flags, - umode_t mode, const struct cred *cred); -extern struct file * open_with_fake_path(const struct path *, int, - struct inode*, const struct cred *); +struct file *dentry_open(const struct path *path, int flags, + const struct cred *creds); +struct file *dentry_create(const struct path *path, int flags, umode_t mode, + const struct cred *cred); +struct file *backing_file_open(const struct path *path, int flags, + const struct path *real_path, + const struct cred *cred); +struct path *backing_file_real_path(struct file *f); + +/* + * file_real_path - get the path corresponding to f_inode + * + * When opening a backing file for a stackable filesystem (e.g., + * overlayfs) f_path may be on the stackable filesystem and f_inode on + * the underlying filesystem. When the path associated with f_inode is + * needed, this helper should be used instead of accessing f_path + * directly. +*/ +static inline const struct path *file_real_path(struct file *f) +{ + if (unlikely(f->f_mode & FMODE_BACKING)) + return backing_file_real_path(f); + return &f->f_path; +} + static inline struct file *file_clone_open(struct file *file) { return dentry_open(&file->f_path, file->f_flags, file->f_cred); @@ -2669,7 +2694,7 @@ extern void evict_inodes(struct super_block *sb); void dump_mapping(const struct address_space *); /* - * Userspace may rely on the the inode number being non-zero. For example, glibc + * Userspace may rely on the inode number being non-zero. For example, glibc * simply ignores files with zero i_ino in unlink() and other places. * * As an additional complication, if userspace was compiled with @@ -2752,11 +2777,9 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -ssize_t direct_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags); -extern ssize_t generic_file_splice_read(struct file *, loff_t *, - struct pipe_inode_info *, size_t, unsigned int); +ssize_t copy_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, + size_t len, unsigned int flags); extern ssize_t iter_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe, diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index bb8467cd11ae..ed48e4f1e755 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -91,11 +91,13 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) static inline int fsnotify_file(struct file *file, __u32 mask) { - const struct path *path = &file->f_path; + const struct path *path; if (file->f_mode & FMODE_NONOTIFY) return 0; + /* Overlayfs internal files have fake f_path */ + path = file_real_path(file); return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); } diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h index e76605d5b36e..1eb7eae580be 100644 --- a/include/linux/fsverity.h +++ b/include/linux/fsverity.h @@ -143,8 +143,8 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg); int fsverity_ioctl_measure(struct file *filp, void __user *arg); int fsverity_get_digest(struct inode *inode, - u8 digest[FS_VERITY_MAX_DIGEST_SIZE], - enum hash_algo *alg); + u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE], + u8 *alg, enum hash_algo *halg); /* open.c */ @@ -197,10 +197,14 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg) } static inline int fsverity_get_digest(struct inode *inode, - u8 digest[FS_VERITY_MAX_DIGEST_SIZE], - enum hash_algo *alg) + u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE], + u8 *alg, enum hash_algo *halg) { - return -EOPNOTSUPP; + /* + * fsverity is not enabled in the kernel configuration, so always report + * that the file doesn't have fsverity enabled (digest size 0). + */ + return 0; } /* open.c */ diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 5c6db5533be6..67b8774eed8f 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -252,6 +252,14 @@ struct gpio_irq_chip { bool initialized; /** + * @domain_is_allocated_externally: + * + * True it the irq_domain was allocated outside of gpiolib, in which + * case gpiolib won't free the irq_domain itself. + */ + bool domain_is_allocated_externally; + + /** * @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 diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 4de1dbcd3ef6..68da30625a6c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -507,7 +507,7 @@ static inline void folio_zero_range(struct folio *folio, zero_user_segments(&folio->page, start, start + length, 0, 0); } -static inline void put_and_unmap_page(struct page *page, void *addr) +static inline void unmap_and_put_page(struct page *page, void *addr) { kunmap_local(addr); put_page(page); diff --git a/include/linux/io.h b/include/linux/io.h index 308f4f0cfb93..7304f2a69960 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -68,6 +68,11 @@ void *devm_memremap(struct device *dev, resource_size_t offset, size_t size, unsigned long flags); void devm_memunmap(struct device *dev, void *addr); +/* architectures can override this */ +pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, + unsigned long size, pgprot_t prot); + + #ifdef CONFIG_PCI /* * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 7fe31b2cd02f..bb9c666bd584 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -46,13 +46,23 @@ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); -void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *, unsigned)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); const char *io_uring_get_opcode(u8 opcode); +void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned), + unsigned flags); +/* users should follow semantics of IOU_F_TWQ_LAZY_WAKE */ +void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)); + +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ + __io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0); +} static inline void io_uring_files_cancel(void) { @@ -85,6 +95,10 @@ static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } +static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 1b2a20a42413..f04ce513fadb 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -211,6 +211,16 @@ struct io_ring_ctx { unsigned int compat: 1; enum task_work_notify_mode notify_method; + + /* + * If IORING_SETUP_NO_MMAP is used, then the below holds + * the gup'ed pages for the two rings, and the sqes. + */ + unsigned short n_ring_pages; + unsigned short n_sqe_pages; + struct page **ring_pages; + struct page **sqe_pages; + struct io_rings *rings; struct task_struct *submitter_task; struct percpu_ref refs; diff --git a/include/linux/irq.h b/include/linux/irq.h index b1b28affb32a..d8a6fdce9373 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -223,32 +223,35 @@ struct irq_data { * irq_chip::irq_set_affinity() when deactivated. * IRQD_IRQ_ENABLED_ON_SUSPEND - Interrupt is enabled on suspend by irq pm if * irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set. + * IRQD_RESEND_WHEN_IN_PROGRESS - Interrupt may fire when already in progress in which + * case it must be resent at the next available opportunity. */ enum { IRQD_TRIGGER_MASK = 0xf, - IRQD_SETAFFINITY_PENDING = (1 << 8), - IRQD_ACTIVATED = (1 << 9), - IRQD_NO_BALANCING = (1 << 10), - IRQD_PER_CPU = (1 << 11), - IRQD_AFFINITY_SET = (1 << 12), - IRQD_LEVEL = (1 << 13), - IRQD_WAKEUP_STATE = (1 << 14), - IRQD_MOVE_PCNTXT = (1 << 15), - IRQD_IRQ_DISABLED = (1 << 16), - IRQD_IRQ_MASKED = (1 << 17), - IRQD_IRQ_INPROGRESS = (1 << 18), - IRQD_WAKEUP_ARMED = (1 << 19), - IRQD_FORWARDED_TO_VCPU = (1 << 20), - IRQD_AFFINITY_MANAGED = (1 << 21), - IRQD_IRQ_STARTED = (1 << 22), - IRQD_MANAGED_SHUTDOWN = (1 << 23), - IRQD_SINGLE_TARGET = (1 << 24), - IRQD_DEFAULT_TRIGGER_SET = (1 << 25), - IRQD_CAN_RESERVE = (1 << 26), - IRQD_MSI_NOMASK_QUIRK = (1 << 27), - IRQD_HANDLE_ENFORCE_IRQCTX = (1 << 28), - IRQD_AFFINITY_ON_ACTIVATE = (1 << 29), - IRQD_IRQ_ENABLED_ON_SUSPEND = (1 << 30), + IRQD_SETAFFINITY_PENDING = BIT(8), + IRQD_ACTIVATED = BIT(9), + IRQD_NO_BALANCING = BIT(10), + IRQD_PER_CPU = BIT(11), + IRQD_AFFINITY_SET = BIT(12), + IRQD_LEVEL = BIT(13), + IRQD_WAKEUP_STATE = BIT(14), + IRQD_MOVE_PCNTXT = BIT(15), + IRQD_IRQ_DISABLED = BIT(16), + IRQD_IRQ_MASKED = BIT(17), + IRQD_IRQ_INPROGRESS = BIT(18), + IRQD_WAKEUP_ARMED = BIT(19), + IRQD_FORWARDED_TO_VCPU = BIT(20), + IRQD_AFFINITY_MANAGED = BIT(21), + IRQD_IRQ_STARTED = BIT(22), + IRQD_MANAGED_SHUTDOWN = BIT(23), + IRQD_SINGLE_TARGET = BIT(24), + IRQD_DEFAULT_TRIGGER_SET = BIT(25), + IRQD_CAN_RESERVE = BIT(26), + IRQD_MSI_NOMASK_QUIRK = BIT(27), + IRQD_HANDLE_ENFORCE_IRQCTX = BIT(28), + IRQD_AFFINITY_ON_ACTIVATE = BIT(29), + IRQD_IRQ_ENABLED_ON_SUSPEND = BIT(30), + IRQD_RESEND_WHEN_IN_PROGRESS = BIT(31), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -448,6 +451,16 @@ static inline bool irqd_affinity_on_activate(struct irq_data *d) return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE; } +static inline void irqd_set_resend_when_in_progress(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_RESEND_WHEN_IN_PROGRESS; +} + +static inline bool irqd_needs_resend_when_in_progress(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_RESEND_WHEN_IN_PROGRESS; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/irqchip/mmp.h b/include/linux/irqchip/mmp.h deleted file mode 100644 index aa1813749a4f..000000000000 --- a/include/linux/irqchip/mmp.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __IRQCHIP_MMP_H -#define __IRQCHIP_MMP_H - -extern struct irq_chip icu_irq_chip; - -extern void icu_init_irq(void); -extern void mmp2_init_icu(void); - -#endif /* __IRQCHIP_MMP_H */ diff --git a/include/linux/irqchip/mxs.h b/include/linux/irqchip/mxs.h deleted file mode 100644 index 4f447e3f0f3a..000000000000 --- a/include/linux/irqchip/mxs.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2013 Freescale Semiconductor, Inc. - */ - -#ifndef __LINUX_IRQCHIP_MXS_H -#define __LINUX_IRQCHIP_MXS_H - -extern void icoll_handle_irq(struct pt_regs *); - -#endif diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 844a8e30e6de..d9451d456a73 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -102,6 +102,9 @@ struct irq_desc { int parent_irq; struct module *owner; const char *name; +#ifdef CONFIG_HARDIRQS_SW_RESEND + struct hlist_node resend_node; +#endif } ____cacheline_internodealigned_in_smp; #ifdef CONFIG_SPARSE_IRQ diff --git a/include/linux/mm.h b/include/linux/mm.h index 27ce77080c79..fec149585985 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1910,6 +1910,28 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, return page_maybe_dma_pinned(page); } +/** + * is_zero_page - Query if a page is a zero page + * @page: The page to query + * + * This returns true if @page is one of the permanent zero pages. + */ +static inline bool is_zero_page(const struct page *page) +{ + return is_zero_pfn(page_to_pfn(page)); +} + +/** + * is_zero_folio - Query if a folio is a zero page + * @folio: The folio to query + * + * This returns true if @folio is one of the permanent zero pages. + */ +static inline bool is_zero_folio(const struct folio *folio) +{ + return is_zero_page(&folio->page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_longterm_pinnable_page(struct page *page) @@ -1920,8 +1942,8 @@ static inline bool is_longterm_pinnable_page(struct page *page) if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) return false; #endif - /* The zero page may always be pinned */ - if (is_zero_pfn(page_to_pfn(page))) + /* The zero page can be "pinned" but gets special handling. */ + if (is_zero_page(page)) return true; /* Coherent device memory must always allow eviction. */ @@ -2383,6 +2405,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +void folio_add_pin(struct folio *folio); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -3816,4 +3839,23 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start, } #endif +#ifdef CONFIG_UNACCEPTED_MEMORY + +bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end); +void accept_memory(phys_addr_t start, phys_addr_t end); + +#else + +static inline bool range_contains_unaccepted_memory(phys_addr_t start, + phys_addr_t end) +{ + return false; +} + +static inline void accept_memory(phys_addr_t start, phys_addr_t end) +{ +} + +#endif + #endif /* _LINUX_MM_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index a4889c9d4055..6c1c2fc13017 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -143,6 +143,9 @@ enum zone_stat_item { NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, +#ifdef CONFIG_UNACCEPTED_MEMORY + NR_UNACCEPTED, +#endif NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { @@ -910,6 +913,11 @@ struct zone { /* free areas of different sizes */ struct free_area free_area[MAX_ORDER + 1]; +#ifdef CONFIG_UNACCEPTED_MEMORY + /* Pages to be accepted. All pages on the list are MAX_ORDER */ + struct list_head unaccepted_pages; +#endif + /* zone flags, see below */ unsigned long flags; diff --git a/include/linux/mount.h b/include/linux/mount.h index 1ea326c368f7..4b81ea90440e 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -107,7 +107,6 @@ extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); -extern dev_t name_to_dev_t(const char *name); extern bool path_is_mountpoint(const struct path *path); extern bool our_mnt(struct vfsmount *mnt); diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h index 15cc9b95e32b..6e471436bba5 100644 --- a/include/linux/mtd/blktrans.h +++ b/include/linux/mtd/blktrans.h @@ -34,7 +34,7 @@ struct mtd_blktrans_dev { struct blk_mq_tag_set *tag_set; spinlock_t queue_lock; void *priv; - fmode_t file_mode; + bool writable; }; struct mtd_blktrans_ops { diff --git a/include/linux/nubus.h b/include/linux/nubus.h index 392fc6c53e96..bdcd85e622d8 100644 --- a/include/linux/nubus.h +++ b/include/linux/nubus.h @@ -93,6 +93,7 @@ extern struct bus_type nubus_bus_type; /* Generic NuBus interface functions, modelled after the PCI interface */ #ifdef CONFIG_PROC_FS +extern bool nubus_populate_procfs; void nubus_proc_init(void); struct proc_dir_entry *nubus_proc_add_board(struct nubus_board *board); struct proc_dir_entry *nubus_proc_add_rsrc_dir(struct proc_dir_entry *procdir, diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index fa092b9be2fd..4109f1bd6128 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir { * @first_sgl: memory for 1st scatter/gather list segment for payload data * @sg_cnt: number of elements in the scatter/gather list * @io_dir: direction of the FCP request (see NVMEFC_FCP_xxx) - * @sqid: The nvme SQID the command is being issued on * @done: The callback routine the LLDD is to invoke upon completion of * the FCP operation. req argument is the pointer to the original * FCP IO operation. @@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir { * while processing the operation. The length of the buffer * corresponds to the fcprqst_priv_sz value specified in the * nvme_fc_port_template supplied by the LLDD. + * @sqid: The nvme SQID the command is being issued on * * Values set by the LLDD indicating completion status of the FCP operation. * Must be set prior to calling the done() callback. + * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @transferred_length: amount of payload data, in bytes, that were * transferred. Should equal payload_length on success. - * @rcv_rsplen: length, in bytes, of the FCP RSP IU received. * @status: Completion status of the FCP operation. must be 0 upon success, * negative errno value upon failure (ex: -EIO). Note: this is * NOT a reflection of the NVME CQE completion status. Only the @@ -219,14 +219,14 @@ struct nvmefc_fcp_req { int sg_cnt; enum nvmefc_fcp_datadir io_dir; - __le16 sqid; - void (*done)(struct nvmefc_fcp_req *req); void *private; - u32 transferred_length; + __le16 sqid; + u16 rcv_rsplen; + u32 transferred_length; u32 status; } __aligned(sizeof(u64)); /* alignment for other things alloc'd with */ diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h index c4602364e909..3c2891d85c41 100644 --- a/include/linux/olpc-ec.h +++ b/include/linux/olpc-ec.h @@ -56,6 +56,8 @@ extern int olpc_ec_sci_query(u16 *sci_value); extern bool olpc_ec_wakeup_available(void); +asmlinkage int xo1_do_sleep(u8 sleep_state); + #else static inline int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 95f33dadb2be..a99b1fcfc617 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -568,6 +568,7 @@ #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F3 0x14e3 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F3 0x14f3 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb +#define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 #define PCI_DEVICE_ID_AMD_LANCE 0x2000 #define PCI_DEVICE_ID_AMD_LANCE_HOME 0x2001 diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 525b5d64e394..c0e4baf940dc 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -26,9 +26,11 @@ */ #define ARMPMU_EVT_64BIT 0x00001 /* Event uses a 64bit counter */ #define ARMPMU_EVT_47BIT 0x00002 /* Event uses a 47bit counter */ +#define ARMPMU_EVT_63BIT 0x00004 /* Event uses a 63bit counter */ static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_64BIT) == ARMPMU_EVT_64BIT); static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_47BIT) == ARMPMU_EVT_47BIT); +static_assert((PERF_EVENT_FLAG_ARCH & ARMPMU_EVT_63BIT) == ARMPMU_EVT_63BIT); #define HW_OP_UNSUPPORTED 0xFFFF #define C(_x) PERF_COUNT_HW_CACHE_##_x diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d5628a7b5eaa..c8dcfdbda1f4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1845,9 +1845,9 @@ int perf_event_exit_cpu(unsigned int cpu); #define perf_event_exit_cpu NULL #endif -extern void __weak arch_perf_update_userpage(struct perf_event *event, - struct perf_event_mmap_page *userpg, - u64 now); +extern void arch_perf_update_userpage(struct perf_event *event, + struct perf_event_mmap_page *userpg, + u64 now); #ifdef CONFIG_MMU extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index d2c3f16cf6b1..02e0086b10f6 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -261,18 +261,14 @@ void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); extern const struct pipe_buf_operations nosteal_pipe_buf_ops; -#ifdef CONFIG_WATCH_QUEUE unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new); bool too_many_pipe_buffers_soft(unsigned long user_bufs); bool too_many_pipe_buffers_hard(unsigned long user_bufs); bool pipe_is_unprivileged_user(void); -#endif /* for F_SETPIPE_SZ and F_GETPIPE_SZ */ -#ifdef CONFIG_WATCH_QUEUE int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots); -#endif long pipe_fcntl(struct file *, unsigned int, unsigned long arg); struct pipe_inode_info *get_pipe_info(struct file *file, bool for_splice); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index f9c5ac80d59b..80cb00db42a4 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -156,7 +156,6 @@ struct pktcdvd_device { struct block_device *bdev; /* dev attached */ dev_t pkt_dev; /* our dev */ - char name[20]; struct packet_settings settings; struct packet_stats stats; int refcnt; /* Open count */ diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0260f5ea98fe..253f2676d93a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -158,6 +158,8 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); #endif /* CONFIG_PROC_PID_ARCH_STATUS */ +void arch_report_meminfo(struct seq_file *m); + #else /* CONFIG_PROC_FS */ static inline void proc_root_init(void) diff --git a/include/linux/regulator/pca9450.h b/include/linux/regulator/pca9450.h index 3c01c2bf84f5..505c908dbb81 100644 --- a/include/linux/regulator/pca9450.h +++ b/include/linux/regulator/pca9450.h @@ -196,11 +196,11 @@ enum { /* PCA9450_REG_LDO3_VOLT bits */ #define LDO3_EN_MASK 0xC0 -#define LDO3OUT_MASK 0x0F +#define LDO3OUT_MASK 0x1F /* PCA9450_REG_LDO4_VOLT bits */ #define LDO4_EN_MASK 0xC0 -#define LDO4OUT_MASK 0x0F +#define LDO4OUT_MASK 0x1F /* PCA9450_REG_LDO5_VOLT bits */ #define LDO5L_EN_MASK 0xC0 diff --git a/include/linux/root_dev.h b/include/linux/root_dev.h index 4e78651371ba..847c9a06101b 100644 --- a/include/linux/root_dev.h +++ b/include/linux/root_dev.h @@ -9,15 +9,8 @@ enum { Root_NFS = MKDEV(UNNAMED_MAJOR, 255), Root_CIFS = MKDEV(UNNAMED_MAJOR, 254), + Root_Generic = MKDEV(UNNAMED_MAJOR, 253), Root_RAM0 = MKDEV(RAMDISK_MAJOR, 0), - Root_RAM1 = MKDEV(RAMDISK_MAJOR, 1), - Root_FD0 = MKDEV(FLOPPY_MAJOR, 0), - Root_HDA1 = MKDEV(IDE0_MAJOR, 1), - Root_HDA2 = MKDEV(IDE0_MAJOR, 2), - Root_SDA1 = MKDEV(SCSI_DISK0_MAJOR, 1), - Root_SDA2 = MKDEV(SCSI_DISK0_MAJOR, 2), - Root_HDC1 = MKDEV(IDE1_MAJOR, 1), - Root_SR0 = MKDEV(SCSI_CDROM_MAJOR, 0), }; extern dev_t ROOT_DEV; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 20099268fa25..669e8cff40c7 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -135,7 +135,7 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - int posix_timer_id; + unsigned int next_posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ diff --git a/include/linux/splice.h b/include/linux/splice.h index a55179fd60fc..8f052c3dae95 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -76,6 +76,9 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *, struct splice_pipe_desc *); extern ssize_t add_to_pipe(struct pipe_inode_info *, struct pipe_buffer *); +long vfs_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags); extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, splice_direct_actor *); extern long do_splice(struct file *in, loff_t *off_in, diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 762d7231e574..3b10636c51a9 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -509,6 +509,27 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp) } /** + * svcxdr_encode_opaque_pages - Insert pages into an xdr_stream + * @xdr: xdr_stream to be updated + * @pages: array of pages to insert + * @base: starting offset of first data byte in @pages + * @len: number of data bytes in @pages to insert + * + * After the @pages are added, the tail iovec is instantiated pointing + * to end of the head buffer, and the stream is set up to encode + * subsequent items into the tail. + */ +static inline void svcxdr_encode_opaque_pages(struct svc_rqst *rqstp, + struct xdr_stream *xdr, + struct page **pages, + unsigned int base, + unsigned int len) +{ + xdr_write_pages(xdr, pages, base, len); + xdr->page_ptr = rqstp->rq_next_page - 1; +} + +/** * svcxdr_set_auth_slack - * @rqstp: RPC transaction * @slack: buffer space to reserve for the transaction's security flavor diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index fbc4bd423b35..a5ee0af2a310 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -135,7 +135,6 @@ struct svc_rdma_recv_ctxt { struct ib_sge rc_recv_sge; void *rc_recv_buf; struct xdr_stream rc_stream; - bool rc_temp; u32 rc_byte_len; unsigned int rc_page_count; u32 rc_inv_rkey; @@ -155,12 +154,12 @@ struct svc_rdma_send_ctxt { struct ib_send_wr sc_send_wr; struct ib_cqe sc_cqe; - struct completion sc_done; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; void *sc_xprt_buf; + int sc_page_count; int sc_cur_sge_no; - + struct page *sc_pages[RPCSVC_MAXPAGES]; struct ib_sge sc_sges[]; }; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 72014c9216fc..f89ec4b5ea16 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -242,8 +242,7 @@ extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf, struct page **pages, struct rpc_rqst *rqst); extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes); -extern int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, - size_t nbytes); +extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes); extern void __xdr_commit_encode(struct xdr_stream *xdr); extern void xdr_truncate_encode(struct xdr_stream *xdr, size_t len); extern void xdr_truncate_decode(struct xdr_stream *xdr, size_t len); diff --git a/include/linux/suspend.h b/include/linux/suspend.h index d0d4598a7b3f..f16653f7be32 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -452,6 +452,10 @@ extern struct pbe *restore_pblist; int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); +int hibernate_resume_nonboot_cpu_disable(void); +int arch_hibernation_header_save(void *addr, unsigned int max_size); +int arch_hibernation_header_restore(void *addr); + #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 33a0ee3bcb2e..24871f8ec8bb 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1280,6 +1280,7 @@ asmlinkage long sys_ni_syscall(void); #endif /* CONFIG_ARCH_HAS_SYSCALL_WRAPPER */ +asmlinkage long sys_ni_posix_timers(void); /* * Kernel code should not call syscalls (i.e., sys_xyzyyz()) directly. diff --git a/include/linux/time_namespace.h b/include/linux/time_namespace.h index bb9d3f5542f8..03d9c5ac01d1 100644 --- a/include/linux/time_namespace.h +++ b/include/linux/time_namespace.h @@ -44,7 +44,6 @@ struct time_namespace *copy_time_ns(unsigned long flags, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); -struct vdso_data *arch_get_vdso_data(void *vvar_page); struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) @@ -163,4 +162,6 @@ static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) } #endif +struct vdso_data *arch_get_vdso_data(void *vvar_page); + #endif /* _LINUX_TIMENS_H */ diff --git a/include/linux/uio.h b/include/linux/uio.h index 044c1d8c230c..8e7d2c425340 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -11,7 +11,6 @@ #include <uapi/linux/uio.h> struct page; -struct pipe_inode_info; typedef unsigned int __bitwise iov_iter_extraction_t; @@ -25,7 +24,6 @@ enum iter_type { ITER_IOVEC, ITER_KVEC, ITER_BVEC, - ITER_PIPE, ITER_XARRAY, ITER_DISCARD, ITER_UBUF, @@ -74,7 +72,6 @@ struct iov_iter { const struct kvec *kvec; const struct bio_vec *bvec; struct xarray *xarray; - struct pipe_inode_info *pipe; void __user *ubuf; }; size_t count; @@ -82,10 +79,6 @@ struct iov_iter { }; union { unsigned long nr_segs; - struct { - unsigned int head; - unsigned int start_head; - }; loff_t xarray_start; }; }; @@ -133,11 +126,6 @@ static inline bool iov_iter_is_bvec(const struct iov_iter *i) return iov_iter_type(i) == ITER_BVEC; } -static inline bool iov_iter_is_pipe(const struct iov_iter *i) -{ - return iov_iter_type(i) == ITER_PIPE; -} - static inline bool iov_iter_is_discard(const struct iov_iter *i) { return iov_iter_type(i) == ITER_DISCARD; @@ -286,19 +274,11 @@ void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec unsigned long nr_segs, size_t count); void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, - size_t count); void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count); void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray, loff_t start, size_t count); -ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, - size_t maxsize, unsigned maxpages, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); -ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, - struct page ***pages, size_t maxsize, size_t *start, - iov_iter_extraction_t extraction_flags); ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); diff --git a/include/linux/watch_queue.h b/include/linux/watch_queue.h index fc6bba20273b..45cd42f55d49 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -38,7 +38,7 @@ struct watch_filter { struct watch_queue { struct rcu_head rcu; struct watch_filter __rcu *filter; - struct pipe_inode_info *pipe; /* The pipe we're using as a buffer */ + struct pipe_inode_info *pipe; /* Pipe we use as a buffer, NULL if queue closed */ struct hlist_head watches; /* Contributory watches */ struct page **notes; /* Preallocated notifications */ unsigned long *notes_bitmap; /* Allocation bitmap for notes */ @@ -46,7 +46,6 @@ struct watch_queue { spinlock_t lock; unsigned int nr_notes; /* Number of notes */ unsigned int nr_pages; /* Number of pages in notes[] */ - bool defunct; /* T when queues closed */ }; /* diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 3992c994787f..683efe29fa69 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -68,7 +68,6 @@ enum { WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, - WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last @@ -79,12 +78,6 @@ enum { WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, - WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, - - /* convenience constants */ - WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, - WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, - WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, @@ -94,6 +87,14 @@ enum { WORKER_DESC_LEN = 24, }; +/* Convenience constants - of type 'unsigned long', not 'enum'! */ +#define WORK_OFFQ_CANCELING (1ul << __WORK_OFFQ_CANCELING) +#define WORK_OFFQ_POOL_NONE ((1ul << WORK_OFFQ_POOL_BITS) - 1) +#define WORK_STRUCT_NO_POOL (WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT) + +#define WORK_STRUCT_FLAG_MASK ((1ul << WORK_STRUCT_FLAG_BITS) - 1) +#define WORK_STRUCT_WQ_DATA_MASK (~WORK_STRUCT_FLAG_MASK) + struct work_struct { atomic_long_t data; struct list_head entry; diff --git a/include/net/dsa.h b/include/net/dsa.h index 8903053fa5aa..ab0f0a5b0860 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -959,6 +959,14 @@ struct dsa_switch_ops { void (*port_disable)(struct dsa_switch *ds, int port); /* + * Compatibility between device trees defining multiple CPU ports and + * drivers which are not OK to use by default the numerically smallest + * CPU port of a switch for its local ports. This can return NULL, + * meaning "don't know/don't care". + */ + struct dsa_port *(*preferred_default_local_cpu_port)(struct dsa_switch *ds); + + /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 83db182decc8..ee47d7143d99 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -472,7 +472,8 @@ struct nft_set_ops { int (*init)(const struct nft_set *set, const struct nft_set_desc *desc, const struct nlattr * const nla[]); - void (*destroy)(const struct nft_set *set); + void (*destroy)(const struct nft_ctx *ctx, + const struct nft_set *set); void (*gc_init)(const struct nft_set *set); unsigned int elemsize; @@ -809,6 +810,8 @@ int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); void nft_set_elem_destroy(const struct nft_set *set, void *elem, bool destroy_expr); +void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, + const struct nft_set *set, void *elem); /** * struct nft_set_gc_batch_head - nf_tables set garbage collection batch @@ -901,6 +904,7 @@ struct nft_expr_type { enum nft_trans_phase { NFT_TRANS_PREPARE, + NFT_TRANS_PREPARE_ERROR, NFT_TRANS_ABORT, NFT_TRANS_COMMIT, NFT_TRANS_RELEASE @@ -1009,7 +1013,10 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule) return (void *)&rule->data[rule->dlen]; } -void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule); +void nft_rule_expr_deactivate(const struct nft_ctx *ctx, struct nft_rule *rule, + enum nft_trans_phase phase); +void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule); static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, struct nft_regs *regs, @@ -1104,6 +1111,8 @@ int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, struct nft_set_elem *elem); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); +int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); +void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); enum nft_chain_types { NFT_CHAIN_T_DEFAULT = 0, @@ -1140,11 +1149,17 @@ int nft_chain_validate_dependency(const struct nft_chain *chain, int nft_chain_validate_hooks(const struct nft_chain *chain, unsigned int hook_flags); +static inline bool nft_chain_binding(const struct nft_chain *chain) +{ + return chain->flags & NFT_CHAIN_BINDING; +} + static inline bool nft_chain_is_bound(struct nft_chain *chain) { return (chain->flags & NFT_CHAIN_BINDING) && chain->bound; } +int nft_chain_add(struct nft_table *table, struct nft_chain *chain); void nft_chain_del(struct nft_chain *chain); void nf_tables_chain_destroy(struct nft_ctx *ctx); @@ -1558,6 +1573,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) * struct nft_trans - nf_tables object update in transaction * * @list: used internally + * @binding_list: list of objects with possible bindings * @msg_type: message type * @put_net: ctx->net needs to be put * @ctx: transaction context @@ -1565,6 +1581,7 @@ static inline void nft_set_elem_clear_busy(struct nft_set_ext *ext) */ struct nft_trans { struct list_head list; + struct list_head binding_list; int msg_type; bool put_net; struct nft_ctx ctx; @@ -1575,6 +1592,7 @@ struct nft_trans_rule { struct nft_rule *rule; struct nft_flow_rule *flow; u32 rule_id; + bool bound; }; #define nft_trans_rule(trans) \ @@ -1583,6 +1601,8 @@ struct nft_trans_rule { (((struct nft_trans_rule *)trans->data)->flow) #define nft_trans_rule_id(trans) \ (((struct nft_trans_rule *)trans->data)->rule_id) +#define nft_trans_rule_bound(trans) \ + (((struct nft_trans_rule *)trans->data)->bound) struct nft_trans_set { struct nft_set *set; @@ -1607,15 +1627,19 @@ struct nft_trans_set { (((struct nft_trans_set *)trans->data)->gc_int) struct nft_trans_chain { + struct nft_chain *chain; bool update; char *name; struct nft_stats __percpu *stats; u8 policy; + bool bound; u32 chain_id; struct nft_base_chain *basechain; struct list_head hook_list; }; +#define nft_trans_chain(trans) \ + (((struct nft_trans_chain *)trans->data)->chain) #define nft_trans_chain_update(trans) \ (((struct nft_trans_chain *)trans->data)->update) #define nft_trans_chain_name(trans) \ @@ -1624,6 +1648,8 @@ struct nft_trans_chain { (((struct nft_trans_chain *)trans->data)->stats) #define nft_trans_chain_policy(trans) \ (((struct nft_trans_chain *)trans->data)->policy) +#define nft_trans_chain_bound(trans) \ + (((struct nft_trans_chain *)trans->data)->bound) #define nft_trans_chain_id(trans) \ (((struct nft_trans_chain *)trans->data)->chain_id) #define nft_trans_basechain(trans) \ @@ -1700,6 +1726,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head binding_list; struct list_head module_list; struct list_head notify_list; struct mutex commit_mutex; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 33ee3f5936e6..151ca95dd08d 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1054,6 +1054,7 @@ struct xfrm_offload { struct sec_path { int len; int olen; + int verified_cnt; struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h index beac64e38b87..a207c07da9d2 100644 --- a/include/scsi/scsi_ioctl.h +++ b/include/scsi/scsi_ioctl.h @@ -45,11 +45,11 @@ typedef struct scsi_fctargaddress { int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev, int cmd, bool ndelay); -int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd, +int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd, void __user *arg); int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp); int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp); -bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode); +bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write); #endif /* __KERNEL__ */ #endif /* _SCSI_IOCTL_H */ diff --git a/include/soc/imx/timer.h b/include/soc/imx/timer.h deleted file mode 100644 index 25f29c6bbd0b..000000000000 --- a/include/soc/imx/timer.h +++ /dev/null @@ -1,16 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2015 Linaro Ltd. - */ - -#ifndef __SOC_IMX_TIMER_H__ -#define __SOC_IMX_TIMER_H__ - -enum imx_gpt_type { - GPT_TYPE_IMX1, /* i.MX1 */ - GPT_TYPE_IMX21, /* i.MX21/27 */ - GPT_TYPE_IMX31, /* i.MX31/35/25/37/51/6Q */ - GPT_TYPE_IMX6DL, /* i.MX6DL/SX/SL */ -}; - -#endif /* __SOC_IMX_TIMER_H__ */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 7f4dfbdf12a6..40e60c33cc6f 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -246,6 +246,32 @@ DEFINE_EVENT(block_rq, block_rq_merge, ); /** + * block_io_start - insert a request for execution + * @rq: block IO operation request + * + * Called when block operation request @rq is queued for execution + */ +DEFINE_EVENT(block_rq, block_io_start, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** + * block_io_done - block IO operation request completed + * @rq: block IO operation request + * + * Called when block operation request @rq is completed + */ +DEFINE_EVENT(block_rq, block_io_done, + + TP_PROTO(struct request *rq), + + TP_ARGS(rq) +); + +/** * block_bio_complete - completed all work on the block operation * @q: queue holding the block operation * @bio: block operation completed diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 8ea9cea9bfeb..a8206f5332e9 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -661,6 +661,35 @@ DEFINE_EVENT(btrfs__ordered_extent, btrfs_ordered_extent_mark_finished, TP_ARGS(inode, ordered) ); +TRACE_EVENT(btrfs_finish_ordered_extent, + + TP_PROTO(const struct btrfs_inode *inode, u64 start, u64 len, + bool uptodate), + + TP_ARGS(inode, start, len, uptodate), + + TP_STRUCT__entry_btrfs( + __field( u64, ino ) + __field( u64, start ) + __field( u64, len ) + __field( bool, uptodate ) + __field( u64, root_objectid ) + ), + + TP_fast_assign_btrfs(inode->root->fs_info, + __entry->ino = btrfs_ino(inode); + __entry->start = start; + __entry->len = len; + __entry->uptodate = uptodate; + __entry->root_objectid = inode->root->root_key.objectid; + ), + + TP_printk_btrfs("root=%llu(%s) ino=%llu start=%llu len=%llu uptodate=%d", + show_root_type(__entry->root_objectid), + __entry->ino, __entry->start, + __entry->len, !!__entry->uptodate) +); + DECLARE_EVENT_CLASS(btrfs__writepage, TP_PROTO(const struct page *page, const struct inode *inode, @@ -1982,25 +2011,27 @@ DEFINE_EVENT(btrfs__prelim_ref, btrfs_prelim_ref_insert, ); TRACE_EVENT(btrfs_inode_mod_outstanding_extents, - TP_PROTO(const struct btrfs_root *root, u64 ino, int mod), + TP_PROTO(const struct btrfs_root *root, u64 ino, int mod, unsigned outstanding), - TP_ARGS(root, ino, mod), + TP_ARGS(root, ino, mod, outstanding), TP_STRUCT__entry_btrfs( __field( u64, root_objectid ) __field( u64, ino ) __field( int, mod ) + __field( unsigned, outstanding ) ), TP_fast_assign_btrfs(root->fs_info, __entry->root_objectid = root->root_key.objectid; __entry->ino = ino; __entry->mod = mod; + __entry->outstanding = outstanding; ), - TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d", + TP_printk_btrfs("root=%llu(%s) ino=%llu mod=%d outstanding=%u", show_root_type(__entry->root_objectid), - __entry->ino, __entry->mod) + __entry->ino, __entry->mod, __entry->outstanding) ); DECLARE_EVENT_CLASS(btrfs__block_group, diff --git a/include/trace/events/csd.h b/include/trace/events/csd.h new file mode 100644 index 000000000000..67e9d01f80c2 --- /dev/null +++ b/include/trace/events/csd.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM csd + +#if !defined(_TRACE_CSD_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_CSD_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(csd_queue_cpu, + + TP_PROTO(const unsigned int cpu, + unsigned long callsite, + smp_call_func_t func, + struct __call_single_data *csd), + + TP_ARGS(cpu, callsite, func, csd), + + TP_STRUCT__entry( + __field(unsigned int, cpu) + __field(void *, callsite) + __field(void *, func) + __field(void *, csd) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->callsite = (void *)callsite; + __entry->func = func; + __entry->csd = csd; + ), + + TP_printk("cpu=%u callsite=%pS func=%ps csd=%p", + __entry->cpu, __entry->callsite, __entry->func, __entry->csd) + ); + +/* + * Tracepoints for a function which is called as an effect of smp_call_function.* + */ +DECLARE_EVENT_CLASS(csd_function, + + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + + TP_ARGS(func, csd), + + TP_STRUCT__entry( + __field(void *, func) + __field(void *, csd) + ), + + TP_fast_assign( + __entry->func = func; + __entry->csd = csd; + ), + + TP_printk("func=%ps, csd=%p", __entry->func, __entry->csd) +); + +DEFINE_EVENT(csd_function, csd_function_entry, + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + TP_ARGS(func, csd) +); + +DEFINE_EVENT(csd_function, csd_function_exit, + TP_PROTO(smp_call_func_t func, struct __call_single_data *csd), + TP_ARGS(func, csd) +); + +#endif /* _TRACE_CSD_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 8f461e04e5f0..f8069ef2ee0f 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -2112,6 +2112,14 @@ DEFINE_POST_CHUNK_EVENT(read); DEFINE_POST_CHUNK_EVENT(write); DEFINE_POST_CHUNK_EVENT(reply); +DEFINE_EVENT(svcrdma_post_chunk_class, svcrdma_cc_release, + TP_PROTO( + const struct rpc_rdma_cid *cid, + int sqecount + ), + TP_ARGS(cid, sqecount) +); + TRACE_EVENT(svcrdma_wc_read, TP_PROTO( const struct ib_wc *wc, diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 31bc7025cb44..69e42ef30979 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -2104,31 +2104,46 @@ DEFINE_SVC_DEFERRED_EVENT(drop); DEFINE_SVC_DEFERRED_EVENT(queue); DEFINE_SVC_DEFERRED_EVENT(recv); -TRACE_EVENT(svcsock_new_socket, +DECLARE_EVENT_CLASS(svcsock_lifetime_class, TP_PROTO( + const void *svsk, const struct socket *socket ), - - TP_ARGS(socket), - + TP_ARGS(svsk, socket), TP_STRUCT__entry( + __field(unsigned int, netns_ino) + __field(const void *, svsk) + __field(const void *, sk) __field(unsigned long, type) __field(unsigned long, family) - __field(bool, listener) + __field(unsigned long, state) ), - TP_fast_assign( + struct sock *sk = socket->sk; + + __entry->netns_ino = sock_net(sk)->ns.inum; + __entry->svsk = svsk; + __entry->sk = sk; __entry->type = socket->type; - __entry->family = socket->sk->sk_family; - __entry->listener = (socket->sk->sk_state == TCP_LISTEN); + __entry->family = sk->sk_family; + __entry->state = sk->sk_state; ), - - TP_printk("type=%s family=%s%s", - show_socket_type(__entry->type), + TP_printk("svsk=%p type=%s family=%s%s", + __entry->svsk, show_socket_type(__entry->type), rpc_show_address_family(__entry->family), - __entry->listener ? " (listener)" : "" + __entry->state == TCP_LISTEN ? " (listener)" : "" ) ); +#define DEFINE_SVCSOCK_LIFETIME_EVENT(name) \ + DEFINE_EVENT(svcsock_lifetime_class, name, \ + TP_PROTO( \ + const void *svsk, \ + const struct socket *socket \ + ), \ + TP_ARGS(svsk, socket)) + +DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_new); +DEFINE_SVCSOCK_LIFETIME_EVENT(svcsock_free); TRACE_EVENT(svcsock_marker, TP_PROTO( diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 3e8619c72f77..b4bc2828fa09 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -158,7 +158,11 @@ DEFINE_EVENT(timer_class, timer_cancel, { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ - { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }) + { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ + { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ + { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ + { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ + { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_init - called when the hrtimer is initialized diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 86b2a82da546..54e353c9f919 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(writeback_folio_template, strscpy_pad(__entry->name, bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : NULL), 32); - __entry->ino = mapping ? mapping->host->i_ino : 0; + __entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0; __entry->index = folio->index; ), diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h index 5e2fb8481252..a5aff2eb5f70 100644 --- a/include/uapi/linux/affs_hardblocks.h +++ b/include/uapi/linux/affs_hardblocks.h @@ -7,42 +7,42 @@ /* Just the needed definitions for the RDB of an Amiga HD. */ struct RigidDiskBlock { - __u32 rdb_ID; + __be32 rdb_ID; __be32 rdb_SummedLongs; - __s32 rdb_ChkSum; - __u32 rdb_HostID; + __be32 rdb_ChkSum; + __be32 rdb_HostID; __be32 rdb_BlockBytes; - __u32 rdb_Flags; - __u32 rdb_BadBlockList; + __be32 rdb_Flags; + __be32 rdb_BadBlockList; __be32 rdb_PartitionList; - __u32 rdb_FileSysHeaderList; - __u32 rdb_DriveInit; - __u32 rdb_Reserved1[6]; - __u32 rdb_Cylinders; - __u32 rdb_Sectors; - __u32 rdb_Heads; - __u32 rdb_Interleave; - __u32 rdb_Park; - __u32 rdb_Reserved2[3]; - __u32 rdb_WritePreComp; - __u32 rdb_ReducedWrite; - __u32 rdb_StepRate; - __u32 rdb_Reserved3[5]; - __u32 rdb_RDBBlocksLo; - __u32 rdb_RDBBlocksHi; - __u32 rdb_LoCylinder; - __u32 rdb_HiCylinder; - __u32 rdb_CylBlocks; - __u32 rdb_AutoParkSeconds; - __u32 rdb_HighRDSKBlock; - __u32 rdb_Reserved4; + __be32 rdb_FileSysHeaderList; + __be32 rdb_DriveInit; + __be32 rdb_Reserved1[6]; + __be32 rdb_Cylinders; + __be32 rdb_Sectors; + __be32 rdb_Heads; + __be32 rdb_Interleave; + __be32 rdb_Park; + __be32 rdb_Reserved2[3]; + __be32 rdb_WritePreComp; + __be32 rdb_ReducedWrite; + __be32 rdb_StepRate; + __be32 rdb_Reserved3[5]; + __be32 rdb_RDBBlocksLo; + __be32 rdb_RDBBlocksHi; + __be32 rdb_LoCylinder; + __be32 rdb_HiCylinder; + __be32 rdb_CylBlocks; + __be32 rdb_AutoParkSeconds; + __be32 rdb_HighRDSKBlock; + __be32 rdb_Reserved4; char rdb_DiskVendor[8]; char rdb_DiskProduct[16]; char rdb_DiskRevision[4]; char rdb_ControllerVendor[8]; char rdb_ControllerProduct[16]; char rdb_ControllerRevision[4]; - __u32 rdb_Reserved5[10]; + __be32 rdb_Reserved5[10]; }; #define IDNAME_RIGIDDISK 0x5244534B /* "RDSK" */ @@ -50,16 +50,16 @@ struct RigidDiskBlock { struct PartitionBlock { __be32 pb_ID; __be32 pb_SummedLongs; - __s32 pb_ChkSum; - __u32 pb_HostID; + __be32 pb_ChkSum; + __be32 pb_HostID; __be32 pb_Next; - __u32 pb_Flags; - __u32 pb_Reserved1[2]; - __u32 pb_DevFlags; + __be32 pb_Flags; + __be32 pb_Reserved1[2]; + __be32 pb_DevFlags; __u8 pb_DriveName[32]; - __u32 pb_Reserved2[15]; + __be32 pb_Reserved2[15]; __be32 pb_Environment[17]; - __u32 pb_EReserved[15]; + __be32 pb_EReserved[15]; }; #define IDNAME_PARTITION 0x50415254 /* "PART" */ diff --git a/include/uapi/linux/eventfd.h b/include/uapi/linux/eventfd.h new file mode 100644 index 000000000000..2eb9ab6c32f3 --- /dev/null +++ b/include/uapi/linux/eventfd.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_EVENTFD_H +#define _UAPI_LINUX_EVENTFD_H + +#include <linux/fcntl.h> + +#define EFD_SEMAPHORE (1 << 0) +#define EFD_CLOEXEC O_CLOEXEC +#define EFD_NONBLOCK O_NONBLOCK + +#endif /* _UAPI_LINUX_EVENTFD_H */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 0716cb17e436..f222d263bc55 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -173,6 +173,18 @@ enum { */ #define IORING_SETUP_DEFER_TASKRUN (1U << 13) +/* + * Application provides the memory for the rings + */ +#define IORING_SETUP_NO_MMAP (1U << 14) + +/* + * Register the ring fd in itself for use with + * IORING_REGISTER_USE_REGISTERED_RING; return a registered fd index rather + * than an fd. + */ +#define IORING_SETUP_REGISTERED_FD_ONLY (1U << 15) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -406,7 +418,7 @@ struct io_sqring_offsets { __u32 dropped; __u32 array; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* @@ -425,7 +437,7 @@ struct io_cqring_offsets { __u32 cqes; __u32 flags; __u32 resv1; - __u64 resv2; + __u64 user_addr; }; /* diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 4d93967f8aea..8eb0d7b758d2 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -74,7 +74,8 @@ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ #define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ -#define MOVE_MOUNT__MASK 0x00000177 +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 /* * fsopen() flags. diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h index 6a5552dfd6af..987a3022dc5f 100644 --- a/include/uapi/linux/pktcdvd.h +++ b/include/uapi/linux/pktcdvd.h @@ -16,6 +16,7 @@ #include <linux/types.h> /* + * UNUSED: * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. */ #define PACKET_DEBUG 1 diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 640bf687b94a..4b8558db90e1 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -47,6 +47,14 @@ _IOWR('u', UBLK_CMD_END_USER_RECOVERY, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_GET_DEV_INFO2 \ _IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_GET_FEATURES \ + _IOR('u', 0x13, struct ublksrv_ctrl_cmd) + +/* + * 64bits are enough now, and it should be easy to extend in case of + * running out of feature flags + */ +#define UBLK_FEATURES_LEN 8 /* * IO commands, issued by ublk server, and handled by ublk driver. @@ -93,9 +101,29 @@ #define UBLKSRV_CMD_BUF_OFFSET 0 #define UBLKSRV_IO_BUF_OFFSET 0x80000000 -/* tag bit is 12bit, so at most 4096 IOs for each queue */ +/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */ #define UBLK_MAX_QUEUE_DEPTH 4096 +/* single IO buffer max size is 32MB */ +#define UBLK_IO_BUF_OFF 0 +#define UBLK_IO_BUF_BITS 25 +#define UBLK_IO_BUF_BITS_MASK ((1ULL << UBLK_IO_BUF_BITS) - 1) + +/* so at most 64K IOs for each queue */ +#define UBLK_TAG_OFF UBLK_IO_BUF_BITS +#define UBLK_TAG_BITS 16 +#define UBLK_TAG_BITS_MASK ((1ULL << UBLK_TAG_BITS) - 1) + +/* max 4096 queues */ +#define UBLK_QID_OFF (UBLK_TAG_OFF + UBLK_TAG_BITS) +#define UBLK_QID_BITS 12 +#define UBLK_QID_BITS_MASK ((1ULL << UBLK_QID_BITS) - 1) + +#define UBLK_MAX_NR_QUEUES (1U << UBLK_QID_BITS) + +#define UBLKSRV_IO_BUF_TOTAL_BITS (UBLK_QID_OFF + UBLK_QID_BITS) +#define UBLKSRV_IO_BUF_TOTAL_SIZE (1ULL << UBLKSRV_IO_BUF_TOTAL_BITS) + /* * zero copy requires 4k block size, and can remap ublk driver's io * request into ublksrv's vm space @@ -145,6 +173,9 @@ /* use ioctl encoding for uring command */ #define UBLK_F_CMD_IOCTL_ENCODE (1UL << 6) +/* Copy between request and user buffer by pread()/pwrite() */ +#define UBLK_F_USER_COPY (1UL << 7) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 |