diff options
Diffstat (limited to 'include/linux')
68 files changed, 1714 insertions, 892 deletions
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 93a5f16d03f3..edef565c2a1a 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -9,12 +9,17 @@ #ifndef _LINUX_ANON_INODES_H #define _LINUX_ANON_INODES_H +#include <linux/types.h> + struct file_operations; struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_fmode(const char *name, + const struct file_operations *fops, + void *priv, int flags, fmode_t f_mode); struct file *anon_inode_create_getfile(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index a63d61ca55af..b721f360d759 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -60,14 +60,14 @@ void topology_scale_freq_tick(void); void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); -DECLARE_PER_CPU(unsigned long, thermal_pressure); +DECLARE_PER_CPU(unsigned long, hw_pressure); -static inline unsigned long topology_get_thermal_pressure(int cpu) +static inline unsigned long topology_get_hw_pressure(int cpu) { - return per_cpu(thermal_pressure, cpu); + return per_cpu(hw_pressure, cpu); } -void topology_update_thermal_pressure(const struct cpumask *cpus, +void topology_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_freq); struct cpu_topology { diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index c906f666ff5d..c82d56768101 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -126,6 +126,7 @@ /* FFA Bus/Device/Driver related */ struct ffa_device { u32 id; + u32 properties; int vm_id; bool mode_32bit; uuid_t uuid; @@ -221,12 +222,29 @@ struct ffa_partition_info { #define FFA_PARTITION_DIRECT_SEND BIT(1) /* partition can send and receive indirect messages. */ #define FFA_PARTITION_INDIRECT_MSG BIT(2) +/* partition can receive notifications */ +#define FFA_PARTITION_NOTIFICATION_RECV BIT(3) /* partition runs in the AArch64 execution state. */ #define FFA_PARTITION_AARCH64_EXEC BIT(8) u32 properties; u32 uuid[4]; }; +static inline +bool ffa_partition_check_property(struct ffa_device *dev, u32 property) +{ + return dev->properties & property; +} + +#define ffa_partition_supports_notify_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_NOTIFICATION_RECV) + +#define ffa_partition_supports_indirect_msg(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_INDIRECT_MSG) + +#define ffa_partition_supports_direct_recv(dev) \ + ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV) + /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */ struct ffa_send_direct_data { unsigned long data0; /* w3/x3 */ @@ -236,6 +254,14 @@ struct ffa_send_direct_data { unsigned long data4; /* w7/x7 */ }; +struct ffa_indirect_msg_hdr { + u32 flags; + u32 res0; + u32 offset; + u32 send_recv_id; + u32 size; +}; + struct ffa_mem_region_addr_range { /* The base IPA of the constituent memory region, aligned to 4 kiB */ u64 address; @@ -396,6 +422,7 @@ struct ffa_msg_ops { void (*mode_32bit_set)(struct ffa_device *dev); int (*sync_send_receive)(struct ffa_device *dev, struct ffa_send_direct_data *data); + int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz); }; struct ffa_mem_ops { diff --git a/include/linux/bio.h b/include/linux/bio.h index 875d792bffff..d5379548d684 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -615,6 +615,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) bl->tail = bl2->tail; } +static inline void bio_list_merge_init(struct bio_list *bl, + struct bio_list *bl2) +{ + bio_list_merge(bl, bl2); + bio_list_init(bl2); +} + static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { @@ -824,5 +831,9 @@ static inline void bio_clear_polled(struct bio *bio) struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, blk_opf_t opf, gfp_t gfp); +struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new); + +struct bio *blk_alloc_discard_bio(struct block_device *bdev, + sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask); #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d3d8fd8e229b..89ba6b16fe8b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -54,8 +54,8 @@ typedef __u32 __bitwise req_flags_t; /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) +/* The request completion needs to be signaled to zone write pluging. */ +#define RQF_ZONE_WRITE_PLUGGING ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) #define RQF_RESV ((__force req_flags_t)(1 << 23)) @@ -1150,85 +1150,4 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, } void blk_dump_rq_flags(struct request *, char *); -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return disk_zone_no(rq->q->disk, blk_rq_pos(rq)); -} - -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); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->disk->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - 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; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - #endif /* BLK_MQ_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index cb1526ec44b5..25dbf1097085 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -88,15 +88,9 @@ struct block_device { /* * Block error status values. See block/blk-core:blk_errors for the details. - * Alpha cannot write a byte atomically, so we need to use 32-bit value. */ -#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__) -typedef u32 __bitwise blk_status_t; -typedef u32 blk_short_t; -#else typedef u8 __bitwise blk_status_t; typedef u16 blk_short_t; -#endif #define BLK_STS_OK 0 #define BLK_STS_NOTSUPP ((__force blk_status_t)1) #define BLK_STS_TIMEOUT ((__force blk_status_t)2) @@ -137,25 +131,13 @@ typedef u16 blk_short_t; #define BLK_STS_DEV_RESOURCE ((__force blk_status_t)13) /* - * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone - * related resources are unavailable, but the driver can guarantee the queue - * will be rerun in the future once the resources become available again. - * - * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references - * a zone specific resource and IO to a different zone on the same device could - * still be served. Examples of that are zones that are write-locked, but a read - * to the same zone could be served. - */ -#define BLK_STS_ZONE_RESOURCE ((__force blk_status_t)14) - -/* * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion * path if the device returns a status indicating that too many zone resources * are currently open. The same command should be successful if resubmitted * after the number of open zones decreases below the device's limits, which is * reported in the request_queue's max_open_zones. */ -#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)15) +#define BLK_STS_ZONE_OPEN_RESOURCE ((__force blk_status_t)14) /* * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion @@ -164,20 +146,20 @@ typedef u16 blk_short_t; * after the number of active zones decreases below the device's limits, which * is reported in the request_queue's max_active_zones. */ -#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16) +#define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)15) /* * BLK_STS_OFFLINE is returned from the driver when the target device is offline * or is being taken offline. This could help differentiate the case where a * device is intentionally being shut down from a real I/O error. */ -#define BLK_STS_OFFLINE ((__force blk_status_t)17) +#define BLK_STS_OFFLINE ((__force blk_status_t)16) /* * BLK_STS_DURATION_LIMIT is returned from the driver when the target device * aborted the command because it exceeded one of its Command Duration Limits. */ -#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)18) +#define BLK_STS_DURATION_LIMIT ((__force blk_status_t)17) /** * blk_path_error - returns true if error may be path related @@ -234,7 +216,12 @@ struct bio { struct bvec_iter bi_iter; - blk_qc_t bi_cookie; + union { + /* for polled bios: */ + blk_qc_t bi_cookie; + /* for plugged zoned writes only: */ + unsigned int __bi_nr_segments; + }; bio_end_io_t *bi_end_io; void *bi_private; #ifdef CONFIG_BLK_CGROUP @@ -304,7 +291,8 @@ enum { BIO_QOS_THROTTLED, /* bio went through rq_qos throttle path */ BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, - BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ + BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */ + BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */ BIO_FLAG_LAST }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 69e7da33ca49..69c4f113db42 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -179,22 +179,21 @@ struct gendisk { #ifdef CONFIG_BLK_DEV_ZONED /* - * Zoned block device information for request dispatch control. - * nr_zones is the total number of zones of the device. This is always - * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones - * bits which indicates if a zone is conventional (bit set) or - * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones - * bits which indicates if a zone is write locked, that is, if a write - * request targeting the zone was dispatched. - * - * Reads of this information must be protected with blk_queue_enter() / - * blk_queue_exit(). Modifying this information is only allowed while - * no requests are being processed. See also blk_mq_freeze_queue() and - * blk_mq_unfreeze_queue(). + * Zoned block device information. Reads of this information must be + * protected with blk_queue_enter() / blk_queue_exit(). Modifying this + * information is only allowed while no requests are being processed. + * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue(). */ unsigned int nr_zones; + unsigned int zone_capacity; unsigned long *conv_zones_bitmap; - unsigned long *seq_zones_wlock; + unsigned int zone_wplugs_hash_bits; + spinlock_t zone_wplugs_lock; + struct mempool_s *zone_wplugs_pool; + struct hlist_head *zone_wplugs_hash; + struct list_head zone_wplugs_err_list; + struct work_struct zone_wplugs_work; + struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ #if IS_ENABLED(CONFIG_CDROM) @@ -233,6 +232,19 @@ static inline unsigned int disk_openers(struct gendisk *disk) return atomic_read(&disk->part0->bd_openers); } +/** + * disk_has_partscan - return %true if partition scanning is enabled on a disk + * @disk: disk to check + * + * Returns %true if partitions scanning is enabled for @disk, or %false if + * partition scanning is disabled either permanently or temporarily. + */ +static inline bool disk_has_partscan(struct gendisk *disk) +{ + return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) && + !test_bit(GD_SUPPRESS_PART_SCAN, &disk->state); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -331,8 +343,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, sector_t sectors, sector_t nr_sectors); -int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); +int blk_revalidate_disk_zones(struct gendisk *disk); /* * Independent access ranges: struct blk_independent_access_range describes @@ -449,8 +460,6 @@ struct request_queue { atomic_t nr_active_requests_shared_tags; - unsigned int required_elevator_features; - struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -633,15 +642,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - if (!blk_queue_is_zoned(disk->queue)) - return false; - if (!disk->conv_zones_bitmap) - return true; - return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap); -} - static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { @@ -664,6 +664,7 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return bdev->bd_disk->queue->limits.max_active_zones; } +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int bdev_nr_zones(struct block_device *bdev) { @@ -674,10 +675,6 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; } -static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) -{ - return false; -} static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { return 0; @@ -691,6 +688,10 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { return 0; } +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} #endif /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_depth(struct request_queue *q) @@ -855,9 +856,11 @@ static inline unsigned int bio_zone_no(struct bio *bio) return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); } -static inline unsigned int bio_zone_is_seq(struct bio *bio) +static inline bool bio_straddles_zones(struct bio *bio) { - return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector); + return bio_sectors(bio) && + bio_zone_no(bio) != + disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1); } /* @@ -942,14 +945,6 @@ disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); void disk_set_independent_access_ranges(struct gendisk *disk, struct blk_independent_access_ranges *iars); -/* - * Elevator features for blk_queue_required_elevator_features: - */ -/* Supports zoned block devices sequential write constraint */ -#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) - -extern void blk_queue_required_elevator_features(struct request_queue *q, - unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); @@ -1156,12 +1151,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q) +static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l) { + unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors); - const struct queue_limits *l = &q->limits; + return min_not_zero(l->max_zone_append_sectors, max_sectors); +} + +static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q) +{ + if (!blk_queue_is_zoned(q)) + return 0; + + return queue_limits_max_zone_append_sectors(&q->limits); +} + +static inline bool queue_emulates_zone_append(struct request_queue *q) +{ + return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors; +} - return min(l->max_zone_append_sectors, l->max_sectors); +static inline bool bdev_emulates_zone_append(struct block_device *bdev) +{ + return queue_emulates_zone_append(bdev_get_queue(bdev)); } static inline unsigned int @@ -1303,18 +1315,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec) return disk_zone_no(bdev->bd_disk, sec); } -/* Whether write serialization is required for @op on zoned devices. */ -static inline bool op_needs_zoned_write_locking(enum req_op op) -{ - 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); @@ -1330,6 +1330,12 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev, return sector & (bdev_zone_sectors(bdev) - 1); } +static inline sector_t bio_offset_from_zone_start(struct bio *bio) +{ + return bdev_offset_from_zone_start(bio->bi_bdev, + bio->bi_iter.bi_sector); +} + static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sector) { diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h new file mode 100644 index 000000000000..18e0a2fc3816 --- /dev/null +++ b/include/linux/bus/stm32_firewall_device.h @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023, STMicroelectronics - All Rights Reserved + */ + +#ifndef STM32_FIREWALL_DEVICE_H +#define STM32_FIREWALL_DEVICE_H + +#include <linux/of.h> +#include <linux/platform_device.h> +#include <linux/types.h> + +#define STM32_FIREWALL_MAX_EXTRA_ARGS 5 + +/* Opaque reference to stm32_firewall_controller */ +struct stm32_firewall_controller; + +/** + * struct stm32_firewall - Information on a device's firewall. Each device can have more than one + * firewall. + * + * @firewall_ctrl: Pointer referencing a firewall controller of the device. It is + * opaque so a device cannot manipulate the controller's ops or access + * the controller's data + * @extra_args: Extra arguments that are implementation dependent + * @entry: Name of the firewall entry + * @extra_args_size: Number of extra arguments + * @firewall_id: Firewall ID associated the device for this firewall controller + */ +struct stm32_firewall { + struct stm32_firewall_controller *firewall_ctrl; + u32 extra_args[STM32_FIREWALL_MAX_EXTRA_ARGS]; + const char *entry; + size_t extra_args_size; + u32 firewall_id; +}; + +#if IS_ENABLED(CONFIG_STM32_FIREWALL) +/** + * stm32_firewall_get_firewall - Get the firewall(s) associated to given device. + * The firewall controller reference is always the first argument + * of each of the access-controller property entries. + * The firewall ID is always the second argument of each of the + * access-controller property entries. + * If there's no argument linked to the phandle, then the firewall ID + * field is set to U32_MAX, which is an invalid ID. + * + * @np: Device node to parse + * @firewall: Array of firewall references + * @nb_firewall: Number of firewall references to get. Must be at least 1. + * + * Returns 0 on success, -ENODEV if there's no match with a firewall controller or appropriate errno + * code if error occurred. + */ +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); + +/** + * stm32_firewall_grant_access - Request firewall access rights and grant access. + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_release_access - Release access granted from a call to + * stm32_firewall_grant_access(). + * + * @firewall: Firewall reference containing the ID to check against its firewall + * controller + */ +void stm32_firewall_release_access(struct stm32_firewall *firewall); + +/** + * stm32_firewall_grant_access_by_id - Request firewall access rights of a given device + * based on a specific firewall ID + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + * + * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or + * appropriate errno code if error occurred + */ +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +/** + * stm32_firewall_release_access_by_id - Release access granted from a call to + * stm32_firewall_grant_access_by_id(). + * + * Warnings: + * There is no way to ensure that the given ID will correspond to the firewall referenced in the + * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this + * function must be used with caution. + * This function should be used for subsystem resources that do not have the same firewall ID + * as their parent. + * U32_MAX is an invalid ID. + * + * @firewall: Firewall reference containing the firewall controller + * @subsystem_id: Firewall ID of the subsystem resource + */ +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id); + +#else /* CONFIG_STM32_FIREWALL */ + +int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall, + unsigned int nb_firewall); +{ + return -ENODEV; +} + +int stm32_firewall_grant_access(struct stm32_firewall *firewall) +{ + return -ENODEV; +} + +void stm32_firewall_release_access(struct stm32_firewall *firewall) +{ +} + +int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ + return -ENODEV; +} + +void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id) +{ +} + +#endif /* CONFIG_STM32_FIREWALL */ +#endif /* STM32_FIREWALL_DEVICE_H */ diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h new file mode 100644 index 000000000000..998deec67740 --- /dev/null +++ b/include/linux/cmpxchg-emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Emulated 1-byte and 2-byte cmpxchg operations for architectures + * lacking direct support for these sizes. These are implemented in terms + * of 4-byte cmpxchg operations. + * + * Copyright (C) 2024 Paul E. McKenney. + */ + +#ifndef __LINUX_CMPXCHG_EMU_H +#define __LINUX_CMPXCHG_EMU_H + +uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new); + +#endif /* __LINUX_CMPXCHG_EMU_H */ diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 2abaa3a825a9..774c2570fe51 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -273,9 +273,27 @@ struct ftrace_likely_data { * disable all instrumentation. See Kconfig.kcsan where this is mandatory. */ # define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation +/* + * Type qualifier to mark variables where all data-racy accesses should be + * ignored by KCSAN. Note, the implementation simply marks these variables as + * volatile, since KCSAN will treat such accesses as "marked". + */ +# define __data_racy volatile # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused #else # define __no_kcsan +# define __data_racy +#endif + +#ifdef __SANITIZE_MEMORY__ +/* + * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined + * functions, therefore disabling KMSAN checks also requires disabling inlining. + * + * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors + * within the function and marks all its outputs as initialized. + */ +# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused #endif #ifndef __no_sanitize_or_inline diff --git a/include/linux/coredump.h b/include/linux/coredump.h index d3eba4360150..0904ba010341 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -30,6 +30,8 @@ struct coredump_params { struct core_vma_metadata *vma_meta; }; +extern unsigned int core_file_note_size_limit; + /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 272e4e79e15c..861c3bfc5f17 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -221,7 +221,18 @@ void cpuhp_report_idle_dead(void); static inline void cpuhp_report_idle_dead(void) { } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ +#ifdef CONFIG_CPU_MITIGATIONS extern bool cpu_mitigations_off(void); extern bool cpu_mitigations_auto_nosmt(void); +#else +static inline bool cpu_mitigations_off(void) +{ + return true; +} +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return false; +} +#endif #endif /* _LINUX_CPU_H_ */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 9956afb9acc2..20f7e98ee8af 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -241,6 +241,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); void cpufreq_disable_fast_switch(struct cpufreq_policy *policy); bool has_target_index(void); + +DECLARE_PER_CPU(unsigned long, cpufreq_pressure); +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return READ_ONCE(per_cpu(cpufreq_pressure, cpu)); +} #else static inline unsigned int cpufreq_get(unsigned int cpu) { @@ -264,6 +270,10 @@ static inline bool cpufreq_supports_freq_invariance(void) } static inline void disable_cpufreq(void) { } static inline void cpufreq_update_limits(unsigned int cpu) { } +static inline unsigned long cpufreq_get_pressure(int cpu) +{ + return 0; +} #endif #ifdef CONFIG_CPU_FREQ_STAT diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index c3f9bb6602ba..e06bad467f55 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -682,11 +682,4 @@ static inline bool dma_fence_is_container(struct dma_fence *fence) return dma_fence_is_array(fence) || dma_fence_is_chain(fence); } -#define DMA_FENCE_WARN(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ - ##args); \ - } while (0) - #endif /* __LINUX_DMA_FENCE_H */ diff --git a/include/linux/elf.h b/include/linux/elf.h index c9a46c4e183b..5c402788da19 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC []; struct file; struct coredump_params; -#ifndef ARCH_HAVE_EXTRA_ELF_NOTES +#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES static inline int elf_coredump_extra_notes_size(void) { return 0; } static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; } #else diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 224645f17c33..297231854ada 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -608,6 +608,31 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, } /** + * eth_skb_pkt_type - Assign packet type if destination address does not match + * @skb: Assigned a packet type if address does not match @dev address + * @dev: Network device used to compare packet address against + * + * If the destination MAC address of the packet does not match the network + * device address, assign an appropriate packet type. + */ +static inline void eth_skb_pkt_type(struct sk_buff *skb, + const struct net_device *dev) +{ + const struct ethhdr *eth = eth_hdr(skb); + + if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { + if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { + if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) + skb->pkt_type = PACKET_BROADCAST; + else + skb->pkt_type = PACKET_MULTICAST; + } else { + skb->pkt_type = PACKET_OTHERHOST; + } + } +} + +/** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * diff --git a/include/linux/file.h b/include/linux/file.h index 169692cb1906..45d0f4800abd 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -84,6 +84,7 @@ static inline void fdput_pos(struct fd f) } DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd) +DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd) extern int f_dupfd(unsigned int from, struct file *file, unsigned flags); extern int replace_fd(unsigned fd, struct file *file, unsigned flags); diff --git a/include/linux/filter.h b/include/linux/filter.h index c99bc3df2d28..219ee7a76874 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -963,6 +963,7 @@ bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); +u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h index 5c28298a98be..366243ee9609 100644 --- a/include/linux/firmware/qcom/qcom_qseecom.h +++ b/include/linux/firmware/qcom/qcom_qseecom.h @@ -10,6 +10,7 @@ #define __QCOM_QSEECOM_H #include <linux/auxiliary_bus.h> +#include <linux/dma-mapping.h> #include <linux/types.h> #include <linux/firmware/qcom/qcom_scm.h> @@ -25,11 +26,56 @@ struct qseecom_client { }; /** + * qseecom_scm_dev() - Get the SCM device associated with the QSEECOM client. + * @client: The QSEECOM client device. + * + * Returns the SCM device under which the provided QSEECOM client device + * operates. This function is intended to be used for DMA allocations. + */ +static inline struct device *qseecom_scm_dev(struct qseecom_client *client) +{ + return client->aux_dev.dev.parent->parent; +} + +/** + * qseecom_dma_alloc() - Allocate DMA memory for a QSEECOM client. + * @client: The QSEECOM client to allocate the memory for. + * @size: The number of bytes to allocate. + * @dma_handle: Pointer to where the DMA address should be stored. + * @gfp: Allocation flags. + * + * Wrapper function for dma_alloc_coherent(), allocating DMA memory usable for + * TZ/QSEECOM communication. Refer to dma_alloc_coherent() for details. + */ +static inline void *qseecom_dma_alloc(struct qseecom_client *client, size_t size, + dma_addr_t *dma_handle, gfp_t gfp) +{ + return dma_alloc_coherent(qseecom_scm_dev(client), size, dma_handle, gfp); +} + +/** + * dma_free_coherent() - Free QSEECOM DMA memory. + * @client: The QSEECOM client for which the memory has been allocated. + * @size: The number of bytes allocated. + * @cpu_addr: Virtual memory address to free. + * @dma_handle: DMA memory address to free. + * + * Wrapper function for dma_free_coherent(), freeing memory previously + * allocated with qseecom_dma_alloc(). Refer to dma_free_coherent() for + * details. + */ +static inline void qseecom_dma_free(struct qseecom_client *client, size_t size, + void *cpu_addr, dma_addr_t dma_handle) +{ + return dma_free_coherent(qseecom_scm_dev(client), size, cpu_addr, dma_handle); +} + +/** * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app. * @client: The QSEECOM client associated with the target app. - * @req: Request buffer sent to the app (must be DMA-mappable). + * @req: DMA address of the request buffer sent to the app. * @req_size: Size of the request buffer. - * @rsp: Response buffer, written to by the app (must be DMA-mappable). + * @rsp: DMA address of the response buffer, written to by the app. * @rsp_size: Size of the response buffer. * * Sends a request to the QSEE app associated with the given client and read @@ -43,8 +89,9 @@ struct qseecom_client { * * Return: Zero on success, nonzero on failure. */ -static inline int qcom_qseecom_app_send(struct qseecom_client *client, void *req, size_t req_size, - void *rsp, size_t rsp_size) +static inline int qcom_qseecom_app_send(struct qseecom_client *client, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size); } diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h index ccaf28846054..aaa19f93ac43 100644 --- a/include/linux/firmware/qcom/qcom_scm.h +++ b/include/linux/firmware/qcom/qcom_scm.h @@ -118,8 +118,8 @@ bool qcom_scm_lmh_dcvsh_available(void); #ifdef CONFIG_QCOM_QSEECOM int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id); -int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size, void *rsp, - size_t rsp_size); +int qcom_scm_qseecom_app_send(u32 app_id, dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size); #else /* CONFIG_QCOM_QSEECOM */ @@ -128,9 +128,9 @@ static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id) return -EINVAL; } -static inline int qcom_scm_qseecom_app_send(u32 app_id, void *req, - size_t req_size, void *rsp, - size_t rsp_size) +static inline int qcom_scm_qseecom_app_send(u32 app_id, + dma_addr_t req, size_t req_size, + dma_addr_t rsp, size_t rsp_size) { return -EINVAL; } diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 6aeebe0a6777..85fc0e6f0f7f 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -15,10 +15,14 @@ #define FORTIFY_REASON(func, write) (FIELD_PREP(BIT(0), write) | \ FIELD_PREP(GENMASK(7, 1), func)) +/* Overridden by KUnit tests. */ #ifndef fortify_panic # define fortify_panic(func, write, avail, size, retfail) \ __fortify_panic(FORTIFY_REASON(func, write), avail, size) #endif +#ifndef fortify_warn_once +# define fortify_warn_once(x...) WARN_ONCE(x) +#endif #define FORTIFY_READ 0 #define FORTIFY_WRITE 1 @@ -609,7 +613,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, const size_t __q_size = (q_size); \ const size_t __p_size_field = (p_size_field); \ const size_t __q_size_field = (q_size_field); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size, \ __q_size, __p_size_field, \ __q_size_field, FORTIFY_FUNC_ ##op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ @@ -734,7 +738,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp if (__compiletime_lessthan(p_size, size)) __read_overflow(); if (p_size < size) - fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, NULL); + fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size, + __real_kmemdup(p, 0, gfp)); return __real_kmemdup(p, size, gfp); } diff --git a/include/linux/fs.h b/include/linux/fs.h index 8dfd53b52744..de946a1fd845 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -110,23 +110,26 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, */ /* file is open for reading */ -#define FMODE_READ ((__force fmode_t)0x1) +#define FMODE_READ ((__force fmode_t)(1 << 0)) /* file is open for writing */ -#define FMODE_WRITE ((__force fmode_t)0x2) +#define FMODE_WRITE ((__force fmode_t)(1 << 1)) /* file is seekable */ -#define FMODE_LSEEK ((__force fmode_t)0x4) +#define FMODE_LSEEK ((__force fmode_t)(1 << 2)) /* file can be accessed using pread */ -#define FMODE_PREAD ((__force fmode_t)0x8) +#define FMODE_PREAD ((__force fmode_t)(1 << 3)) /* file can be accessed using pwrite */ -#define FMODE_PWRITE ((__force fmode_t)0x10) +#define FMODE_PWRITE ((__force fmode_t)(1 << 4)) /* File is opened for execution with sys_execve / sys_uselib */ -#define FMODE_EXEC ((__force fmode_t)0x20) +#define FMODE_EXEC ((__force fmode_t)(1 << 5)) /* File writes are restricted (block device specific) */ -#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40) +#define FMODE_WRITE_RESTRICTED ((__force fmode_t)(1 << 6)) + +/* FMODE_* bits 7 to 8 */ + /* 32bit hashes as llseek() offset (for directories) */ -#define FMODE_32BITHASH ((__force fmode_t)0x200) +#define FMODE_32BITHASH ((__force fmode_t)(1 << 9)) /* 64bit hashes as llseek() offset (for directories) */ -#define FMODE_64BITHASH ((__force fmode_t)0x400) +#define FMODE_64BITHASH ((__force fmode_t)(1 << 10)) /* * Don't update ctime and mtime. @@ -134,60 +137,53 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ -#define FMODE_NOCMTIME ((__force fmode_t)0x800) +#define FMODE_NOCMTIME ((__force fmode_t)(1 << 11)) /* Expect random access pattern */ -#define FMODE_RANDOM ((__force fmode_t)0x1000) +#define FMODE_RANDOM ((__force fmode_t)(1 << 12)) /* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) +#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ -#define FMODE_PATH ((__force fmode_t)0x4000) +#define FMODE_PATH ((__force fmode_t)(1 << 14)) /* File needs atomic accesses to f_pos */ -#define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) +#define FMODE_ATOMIC_POS ((__force fmode_t)(1 << 15)) /* Write access to underlying fs */ -#define FMODE_WRITER ((__force fmode_t)0x10000) +#define FMODE_WRITER ((__force fmode_t)(1 << 16)) /* Has read method(s) */ -#define FMODE_CAN_READ ((__force fmode_t)0x20000) +#define FMODE_CAN_READ ((__force fmode_t)(1 << 17)) /* Has write method(s) */ -#define FMODE_CAN_WRITE ((__force fmode_t)0x40000) +#define FMODE_CAN_WRITE ((__force fmode_t)(1 << 18)) -#define FMODE_OPENED ((__force fmode_t)0x80000) -#define FMODE_CREATED ((__force fmode_t)0x100000) +#define FMODE_OPENED ((__force fmode_t)(1 << 19)) +#define FMODE_CREATED ((__force fmode_t)(1 << 20)) /* File is stream-like */ -#define FMODE_STREAM ((__force fmode_t)0x200000) +#define FMODE_STREAM ((__force fmode_t)(1 << 21)) /* File supports DIRECT IO */ -#define FMODE_CAN_ODIRECT ((__force fmode_t)0x400000) +#define FMODE_CAN_ODIRECT ((__force fmode_t)(1 << 22)) -#define FMODE_NOREUSE ((__force fmode_t)0x800000) +#define FMODE_NOREUSE ((__force fmode_t)(1 << 23)) -/* File supports non-exclusive O_DIRECT writes from multiple threads */ -#define FMODE_DIO_PARALLEL_WRITE ((__force fmode_t)0x1000000) +/* FMODE_* bit 24 */ /* File is embedded in backing_file object */ -#define FMODE_BACKING ((__force fmode_t)0x2000000) +#define FMODE_BACKING ((__force fmode_t)(1 << 25)) /* File was opened by fanotify and shouldn't generate fanotify events */ -#define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +#define FMODE_NONOTIFY ((__force fmode_t)(1 << 26)) /* File is capable of returning -EAGAIN if I/O will block */ -#define FMODE_NOWAIT ((__force fmode_t)0x8000000) +#define FMODE_NOWAIT ((__force fmode_t)(1 << 27)) /* File represents mount that needs unmounting */ -#define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) +#define FMODE_NEED_UNMOUNT ((__force fmode_t)(1 << 28)) /* File does not contribute to nr_files count */ -#define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) - -/* File supports async buffered reads */ -#define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000) - -/* File supports async nowait buffered writes */ -#define FMODE_BUF_WASYNC ((__force fmode_t)0x80000000) +#define FMODE_NOACCOUNT ((__force fmode_t)(1 << 29)) /* * Attribute flags. These should be or-ed together to figure out what @@ -1035,12 +1031,13 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[]; + unsigned char f_handle[] __counted_by(handle_bytes); }; static inline struct file *get_file(struct file *f) { - atomic_long_inc(&f->f_count); + long prior = atomic_long_fetch_inc_relaxed(&f->f_count); + WARN_ONCE(!prior, "struct file::f_count incremented from zero; use-after-free condition present!\n"); return f; } @@ -2003,8 +2000,11 @@ struct iov_iter; struct io_uring_cmd; struct offset_ctx; +typedef unsigned int __bitwise fop_flags_t; + struct file_operations { struct module *owner; + fop_flags_t fop_flags; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); @@ -2017,7 +2017,6 @@ struct file_operations { long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -2048,6 +2047,17 @@ struct file_operations { unsigned int poll_flags); } __randomize_layout; +/* Supports async buffered reads */ +#define FOP_BUFFER_RASYNC ((__force fop_flags_t)(1 << 0)) +/* Supports async buffered writes */ +#define FOP_BUFFER_WASYNC ((__force fop_flags_t)(1 << 1)) +/* Supports synchronous page faults for mappings */ +#define FOP_MMAP_SYNC ((__force fop_flags_t)(1 << 2)) +/* Supports non-exclusive O_DIRECT writes from multiple threads */ +#define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) +/* Contains huge pages */ +#define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) + /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, int (*) (struct file *, struct dir_context *)); @@ -2253,7 +2263,13 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) + +#ifdef CONFIG_SWAP #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) +#else +#define IS_SWAPFILE(inode) ((void)(inode), 0U) +#endif + #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) @@ -3340,6 +3356,8 @@ void simple_offset_init(struct offset_ctx *octx); int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry); void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry); int simple_offset_empty(struct dentry *dentry); +int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); int simple_offset_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 01542c4b87a2..d3350979115f 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -132,4 +132,8 @@ static inline bool fs_validate_description(const char *name, #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL) #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL) +/* String parameter that allows empty argument */ +#define fsparam_string_empty(NAME, OPT) \ + __fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL) + #endif /* _LINUX_FS_PARSER_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 6e8562cbcc43..9de27643607f 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -172,9 +172,12 @@ extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); -extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, - loff_t, size_t, loff_t, netfs_io_terminated_t, void *, - bool); +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool using_pgpriv2, bool cond); extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); /** @@ -597,7 +600,8 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * @i_size: The new size of the inode * @term_func: The function to call upon completion * @term_func_priv: The private data for @term_func - * @caching: If PG_fscache has been set + * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write + * @caching: If we actually want to do the caching * * Helper function for a netfs to write dirty data from an inode into the cache * object that's backing it. @@ -608,19 +612,21 @@ static inline void fscache_clear_page_bits(struct address_space *mapping, * marked with PG_fscache. * * If given, @term_func will be called upon completion and supplied with - * @term_func_priv. Note that the PG_fscache flags will have been cleared by - * this point, so the netfs must retain its own pin on the mapping. + * @term_func_priv. Note that if @using_pgpriv2 is set, the PG_private_2 flags + * will have been cleared by this point, so the netfs must retain its own pin + * on the mapping. */ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, - bool caching) + bool using_pgpriv2, bool caching) { if (caching) __fscache_write_to_cache(cookie, mapping, start, len, i_size, - term_func, term_func_priv, caching); + term_func, term_func_priv, + using_pgpriv2, caching); else if (term_func) term_func(term_func_priv, -ENOBUFS, false); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 77b30a8c6076..b06f7c426d38 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -554,17 +554,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } -extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, int creat_flags, int page_size_log); -static inline bool is_file_hugepages(struct file *file) +static inline bool is_file_hugepages(const struct file *file) { - if (file->f_op == &hugetlbfs_file_operations) - return true; - - return is_file_shm_hugepages(file); + return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 68ed6697fece..e123d5e17b52 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -11,7 +11,6 @@ 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); -int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); bool io_is_uring_fops(struct file *file); static inline void io_uring_files_cancel(void) @@ -45,11 +44,6 @@ static inline const char *io_uring_get_opcode(u8 opcode) { return ""; } -static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, - unsigned int issue_flags) -{ - return -EOPNOTSUPP; -} static inline bool io_is_uring_fops(struct file *file) { return false; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index e453a997c060..447fbfd32215 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -26,12 +26,25 @@ static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); + +/* + * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd + * and the corresponding io_uring request. + * + * Note: the caller should never hard code @issue_flags and is only allowed + * to pass the mask provided by the core io_uring code. + */ void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, unsigned issue_flags); + void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned), unsigned flags); +/* + * Note: the caller should never hard code @issue_flags and only use the + * mask provided by the core io_uring code. + */ void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, unsigned int issue_flags); @@ -56,6 +69,17 @@ static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd, } #endif +/* + * Polled completions must ensure they are coming from a poll queue, and + * hence are completed inside the usual poll handling loops. + */ +static inline void io_uring_cmd_iopoll_done(struct io_uring_cmd *ioucmd, + ssize_t ret, ssize_t res2) +{ + lockdep_assert(in_task()); + io_uring_cmd_done(ioucmd, ret, res2, 0); +} + /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */ static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd, void (*task_work_cb)(struct io_uring_cmd *, unsigned)) diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h new file mode 100644 index 000000000000..b58f39fed4d5 --- /dev/null +++ b/include/linux/io_uring/net.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _LINUX_IO_URING_NET_H +#define _LINUX_IO_URING_NET_H + +struct io_uring_cmd; + +#if defined(CONFIG_IO_URING) +int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags); + +#else +static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + return -EOPNOTSUPP; +} +#endif + +#endif diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index ac333ea81d31..7a6b190c7da7 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -205,6 +205,7 @@ struct io_submit_state { bool plug_started; bool need_plug; + bool cq_flush; unsigned short submit_nr; unsigned int cqes_count; struct blk_plug plug; @@ -219,7 +220,7 @@ struct io_ev_fd { }; struct io_alloc_cache { - struct io_wq_work_node list; + void **entries; unsigned int nr_cached; unsigned int max_cached; size_t elem_size; @@ -299,6 +300,8 @@ struct io_ring_ctx { struct io_hash_table cancel_table_locked; struct io_alloc_cache apoll_cache; struct io_alloc_cache netmsg_cache; + struct io_alloc_cache rw_cache; + struct io_alloc_cache uring_cache; /* * Any cancelable uring_cmd is added to this list in @@ -341,14 +344,8 @@ struct io_ring_ctx { unsigned cq_last_tm_flush; } ____cacheline_aligned_in_smp; - struct io_uring_cqe completion_cqes[16]; - spinlock_t completion_lock; - /* IRQ completion list, under ->completion_lock */ - unsigned int locked_free_nr; - struct io_wq_work_list locked_free_list; - struct list_head io_buffers_comp; struct list_head cq_overflow_list; struct io_hash_table cancel_table; @@ -371,9 +368,6 @@ struct io_ring_ctx { struct list_head io_buffers_cache; - /* deferred free list, protected by ->uring_lock */ - struct hlist_head io_buf_list; - /* Keep this last, we don't need it for the fast path */ struct wait_queue_head poll_wq; struct io_restriction restrictions; @@ -438,8 +432,6 @@ struct io_ring_ctx { }; struct io_tw_state { - /* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */ - bool locked; }; enum { @@ -480,6 +472,7 @@ enum { REQ_F_CAN_POLL_BIT, REQ_F_BL_EMPTY_BIT, REQ_F_BL_NO_RECYCLE_BIT, + REQ_F_BUFFERS_COMMIT_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -558,6 +551,8 @@ enum { REQ_F_BL_EMPTY = IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT), /* don't recycle provided buffers for this request */ REQ_F_BL_NO_RECYCLE = IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT), + /* buffer ring head needs incrementing on put */ + REQ_F_BUFFERS_COMMIT = IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT), }; typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts); diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index f0a949b7c973..f5a2727ca4a9 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -216,6 +216,7 @@ extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); +extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, @@ -265,6 +266,8 @@ static __always_inline void jump_label_init(void) static_key_initialized = true; } +static __always_inline void jump_label_init_ro(void) { } + static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) diff --git a/include/linux/math64.h b/include/linux/math64.h index bf74478926d4..d34def7f9a8c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -4,8 +4,8 @@ #include <linux/types.h> #include <linux/math.h> -#include <vdso/math64.h> #include <asm/div64.h> +#include <vdso/math64.h> #if BITS_PER_LONG == 64 @@ -179,16 +179,12 @@ static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift) #ifndef mul_u64_u32_shr static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) { - u32 ah, al; + u32 ah = a >> 32, al = a; u64 ret; - al = a; - ah = a >> 32; - ret = mul_u32_u32(al, mul) >> shift; if (ah) ret += mul_u32_u32(ah, mul) << (32 - shift); - return ret; } #endif /* mul_u64_u32_shr */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 7b0ee64225de..b6bdaa18b9e9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1223,14 +1223,16 @@ static inline void page_mapcount_reset(struct page *page) * a large folio, it includes the number of times this page is mapped * as part of that folio. * - * The result is undefined for pages which cannot be mapped into userspace. - * For example SLAB or special types of pages. See function page_has_type(). - * They use this field in struct page differently. + * Will report 0 for pages which cannot be mapped into userspace, eg + * slab, page tables and similar. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; + /* Handle page_has_type() pages */ + if (mapcount < 0) + mapcount = 0; if (unlikely(PageCompound(page))) mapcount += folio_entire_mapcount(page_folio(page)); diff --git a/include/linux/namei.h b/include/linux/namei.h index 74e0cc14ebf8..967aa9ea9f96 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -44,6 +44,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ +#define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 100cbb261269..f45d06284f2f 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -20,95 +20,24 @@ #include <linux/uio.h> enum netfs_sreq_ref_trace; - -/* - * Overload PG_private_2 to give us PG_fscache - this is used to indicate that - * a page is currently backed by a local disk cache - */ -#define folio_test_fscache(folio) folio_test_private_2(folio) -#define PageFsCache(page) PagePrivate2((page)) -#define SetPageFsCache(page) SetPagePrivate2((page)) -#define ClearPageFsCache(page) ClearPagePrivate2((page)) -#define TestSetPageFsCache(page) TestSetPagePrivate2((page)) -#define TestClearPageFsCache(page) TestClearPagePrivate2((page)) +typedef struct mempool_s mempool_t; /** - * folio_start_fscache - Start an fscache write on a folio. + * folio_start_private_2 - Start an fscache write on a folio. [DEPRECATED] * @folio: The folio. * * Call this function before writing a folio to a local cache. Starting a * second write before the first one finishes is not allowed. + * + * Note that this should no longer be used. */ -static inline void folio_start_fscache(struct folio *folio) +static inline void folio_start_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); folio_get(folio); folio_set_private_2(folio); } -/** - * folio_end_fscache - End an fscache write on a folio. - * @folio: The folio. - * - * Call this function after the folio has been written to the local cache. - * This will wake any sleepers waiting on this folio. - */ -static inline void folio_end_fscache(struct folio *folio) -{ - folio_end_private_2(folio); -} - -/** - * folio_wait_fscache - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait for - * the write to finish. Another write may start after this one finishes, - * unless the caller holds the folio lock. - */ -static inline void folio_wait_fscache(struct folio *folio) -{ - folio_wait_private_2(folio); -} - -/** - * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. - * @folio: The folio. - * - * If this folio is currently being written to a local cache, wait - * for the write to finish or for a fatal signal to be received. - * Another write may start after this one finishes, unless the caller - * holds the folio lock. - * - * Return: - * - 0 if successful. - * - -EINTR if a fatal signal was encountered. - */ -static inline int folio_wait_fscache_killable(struct folio *folio) -{ - return folio_wait_private_2_killable(folio); -} - -static inline void set_page_fscache(struct page *page) -{ - folio_start_fscache(page_folio(page)); -} - -static inline void end_page_fscache(struct page *page) -{ - folio_end_private_2(page_folio(page)); -} - -static inline void wait_on_page_fscache(struct page *page) -{ - folio_wait_private_2(page_folio(page)); -} - -static inline int wait_on_page_fscache_killable(struct page *page) -{ - return folio_wait_private_2_killable(page_folio(page)); -} - /* Marks used on xarray-based buffers */ #define NETFS_BUF_PUT_MARK XA_MARK_0 /* - Page needs putting */ #define NETFS_BUF_PAGECACHE_MARK XA_MARK_1 /* - Page needs wb/dirty flag wrangling */ @@ -135,6 +64,7 @@ struct netfs_inode { #if IS_ENABLED(CONFIG_FSCACHE) struct fscache_cookie *cache; #endif + struct mutex wb_lock; /* Writeback serialisation */ loff_t remote_i_size; /* Size of the remote file */ loff_t zero_point; /* Size after which we assume there's no data * on the server */ @@ -142,7 +72,8 @@ struct netfs_inode { #define NETFS_ICTX_ODIRECT 0 /* The file has DIO in progress */ #define NETFS_ICTX_UNBUFFERED 1 /* I/O should not use the pagecache */ #define NETFS_ICTX_WRITETHROUGH 2 /* Write-through caching */ -#define NETFS_ICTX_NO_WRITE_STREAMING 3 /* Don't engage in write-streaming */ +#define NETFS_ICTX_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ }; /* @@ -165,16 +96,25 @@ struct netfs_folio { unsigned int dirty_len; /* Write-streaming dirty data length */ }; #define NETFS_FOLIO_INFO 0x1UL /* OR'd with folio->private. */ +#define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */ -static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +static inline bool netfs_is_folio_info(const void *priv) { - void *priv = folio_get_private(folio); + return (unsigned long)priv & NETFS_FOLIO_INFO; +} - if ((unsigned long)priv & NETFS_FOLIO_INFO) +static inline struct netfs_folio *__netfs_folio_info(const void *priv) +{ + if (netfs_is_folio_info(priv)) return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO); return NULL; } +static inline struct netfs_folio *netfs_folio_info(struct folio *folio) +{ + return __netfs_folio_info(folio_get_private(folio)); +} + static inline struct netfs_group *netfs_folio_group(struct folio *folio) { struct netfs_folio *finfo; @@ -187,6 +127,33 @@ static inline struct netfs_group *netfs_folio_group(struct folio *folio) } /* + * Stream of I/O subrequests going to a particular destination, such as the + * server or the local cache. This is mainly intended for writing where we may + * have to write to multiple destinations concurrently. + */ +struct netfs_io_stream { + /* Submission tracking */ + struct netfs_io_subrequest *construct; /* Op being constructed */ + unsigned int submit_off; /* Folio offset we're submitting from */ + unsigned int submit_len; /* Amount of data left to submit */ + unsigned int submit_max_len; /* Amount I/O can be rounded up to */ + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Collection tracking */ + struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_subrequest *front; /* Op being collected */ + unsigned long long collected_to; /* Position we've collected results to */ + size_t transferred; /* The amount transferred from this stream */ + enum netfs_io_source source; /* Where to read from/write to */ + unsigned short error; /* Aggregate error for the stream */ + unsigned char stream_nr; /* Index of stream in parent table */ + bool avail; /* T if stream is available */ + bool active; /* T if stream is active */ + bool need_retry; /* T if this stream needs retrying */ + bool failed; /* T if this stream failed */ +}; + +/* * Resources required to do operations on a cache. */ struct netfs_cache_resources { @@ -209,14 +176,17 @@ struct netfs_io_subrequest { struct work_struct work; struct list_head rreq_link; /* Link in rreq->subrequests */ struct iov_iter io_iter; /* Iterator for this subrequest */ - loff_t start; /* Where to start the I/O */ + unsigned long long start; /* Where to start the I/O */ + size_t max_len; /* Maximum size of the I/O */ size_t len; /* Size of the I/O */ size_t transferred; /* Amount of data transferred */ refcount_t ref; short error; /* 0 or error that occurred */ unsigned short debug_index; /* Index in list (for debugging output) */ + unsigned int nr_segs; /* Number of segs in io_iter */ unsigned int max_nr_segs; /* 0 or max number of segments in an iterator */ enum netfs_io_source source; /* Where to read from/write to */ + unsigned char stream_nr; /* I/O stream this belongs to */ unsigned long flags; #define NETFS_SREQ_COPY_TO_CACHE 0 /* Set if should copy the data to the cache */ #define NETFS_SREQ_CLEAR_TAIL 1 /* Set if the rest of the read should be cleared */ @@ -224,15 +194,20 @@ struct netfs_io_subrequest { #define NETFS_SREQ_SEEK_DATA_READ 3 /* Set if ->read() should SEEK_DATA first */ #define NETFS_SREQ_NO_PROGRESS 4 /* Set if we didn't manage to read any data */ #define NETFS_SREQ_ONDEMAND 5 /* Set if it's from on-demand read mode */ +#define NETFS_SREQ_BOUNDARY 6 /* Set if ends on hard boundary (eg. ceph object) */ +#define NETFS_SREQ_IN_PROGRESS 8 /* Unlocked when the subrequest completes */ +#define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */ +#define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */ +#define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */ }; enum netfs_io_origin { NETFS_READAHEAD, /* This read was triggered by readahead */ NETFS_READPAGE, /* This read is a synchronous read */ NETFS_READ_FOR_WRITE, /* This read is to prepare a write */ + NETFS_COPY_TO_CACHE, /* This write is to copy a read to the cache */ NETFS_WRITEBACK, /* This write was triggered by writepages */ NETFS_WRITETHROUGH, /* This write was made by netfs_perform_write() */ - NETFS_LAUNDER_WRITE, /* This is triggered by ->launder_folio() */ NETFS_UNBUFFERED_WRITE, /* This is an unbuffered write */ NETFS_DIO_READ, /* This is a direct I/O read */ NETFS_DIO_WRITE, /* This is a direct I/O write */ @@ -254,26 +229,36 @@ struct netfs_io_request { struct netfs_cache_resources cache_resources; struct list_head proc_link; /* Link in netfs_iorequests */ struct list_head subrequests; /* Contributory I/O operations */ + struct netfs_io_stream io_streams[2]; /* Streams of parallel I/O operations */ +#define NR_IO_STREAMS 2 //wreq->nr_io_streams + struct netfs_group *group; /* Writeback group being written back */ struct iov_iter iter; /* Unencrypted-side iterator */ struct iov_iter io_iter; /* I/O (Encrypted-side) iterator */ void *netfs_priv; /* Private data for the netfs */ + void *netfs_priv2; /* Private data for the netfs */ struct bio_vec *direct_bv; /* DIO buffer list (when handling iovec-iter) */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ unsigned int wsize; /* Maximum write size (0 for none) */ - unsigned int subreq_counter; /* Next subreq->debug_index */ + atomic_t subreq_counter; /* Next subreq->debug_index */ + unsigned int nr_group_rel; /* Number of refs to release on ->group */ + spinlock_t lock; /* Lock for queuing subreqs */ atomic_t nr_outstanding; /* Number of ops in progress */ atomic_t nr_copy_ops; /* Number of copy-to-cache ops in progress */ - size_t submitted; /* Amount submitted for I/O so far */ - size_t len; /* Length of the request */ size_t upper_len; /* Length can be extended to here */ + unsigned long long submitted; /* Amount submitted for I/O so far */ + unsigned long long len; /* Length of the request */ size_t transferred; /* Amount to be indicated as transferred */ short error; /* 0 or error that occurred */ enum netfs_io_origin origin; /* Origin of the request */ bool direct_bv_unpin; /* T if direct_bv[] must be unpinned */ - loff_t i_size; /* Size of the file */ - loff_t start; /* Start position */ + unsigned long long i_size; /* Size of the file */ + unsigned long long start; /* Start position */ + atomic64_t issued_to; /* Write issuer folio cursor */ + unsigned long long contiguity; /* Tracking for gaps in the writeback sequence */ + unsigned long long collected_to; /* Point we've collected to */ + unsigned long long cleaned_to; /* Position we've cleaned folios to */ pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t ref; unsigned long flags; @@ -287,6 +272,11 @@ struct netfs_io_request { #define NETFS_RREQ_UPLOAD_TO_SERVER 8 /* Need to write to the server */ #define NETFS_RREQ_NONBLOCK 9 /* Don't block if possible (O_NONBLOCK) */ #define NETFS_RREQ_BLOCKED 10 /* We blocked */ +#define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ +#define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ +#define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ +#define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark + * write to cache on read */ const struct netfs_request_ops *netfs_ops; void (*cleanup)(struct netfs_io_request *req); }; @@ -295,8 +285,8 @@ struct netfs_io_request { * Operations the network filesystem can/must provide to the helpers. */ struct netfs_request_ops { - unsigned int io_request_size; /* Alloc size for netfs_io_request struct */ - unsigned int io_subrequest_size; /* Alloc size for netfs_io_subrequest struct */ + mempool_t *request_pool; + mempool_t *subrequest_pool; int (*init_request)(struct netfs_io_request *rreq, struct file *file); void (*free_request)(struct netfs_io_request *rreq); void (*free_subrequest)(struct netfs_io_subrequest *rreq); @@ -312,10 +302,13 @@ struct netfs_request_ops { /* Modification handling */ void (*update_i_size)(struct inode *inode, loff_t i_size); + void (*post_modify)(struct inode *inode); /* Write request handling */ - void (*create_write_requests)(struct netfs_io_request *wreq, - loff_t start, size_t len); + void (*begin_writeback)(struct netfs_io_request *wreq); + void (*prepare_write)(struct netfs_io_subrequest *subreq); + void (*issue_write)(struct netfs_io_subrequest *subreq); + void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream); void (*invalidate_cache)(struct netfs_io_request *wreq); }; @@ -350,15 +343,27 @@ struct netfs_cache_ops { netfs_io_terminated_t term_func, void *term_func_priv); + /* Write data to the cache from a netfs subrequest. */ + void (*issue_write)(struct netfs_io_subrequest *subreq); + /* Expand readahead request */ void (*expand_readahead)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + unsigned long long *_start, + unsigned long long *_len, + unsigned long long i_size); /* Prepare a read operation, shortening it to a cached/uncached * boundary as appropriate. */ enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq, - loff_t i_size); + unsigned long long i_size); + + /* Prepare a write subrequest, working out if we're allowed to do it + * and finding out the maximum amount of data to gather before + * attempting to submit. If we're not permitted to do it, the + * subrequest should be marked failed. + */ + void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq); /* Prepare a write operation, working out what part of the write we can * actually do. @@ -410,7 +415,6 @@ int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc); void netfs_clear_inode_writeback(struct inode *inode, const void *aux); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length); bool netfs_release_folio(struct folio *folio, gfp_t gfp); -int netfs_launder_folio(struct folio *folio); /* VMA operations API. */ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group); @@ -426,9 +430,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, iov_iter_extraction_t extraction_flags); size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset, size_t max_size, size_t max_segs); -struct netfs_io_subrequest *netfs_create_write_request( - struct netfs_io_request *wreq, enum netfs_io_source dest, - loff_t start, size_t len, work_func_t worker); +void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq); void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error, bool was_async); void netfs_queue_write_request(struct netfs_io_subrequest *subreq); @@ -472,6 +474,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, #if IS_ENABLED(CONFIG_FSCACHE) ctx->cache = NULL; #endif + mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { ctx->zero_point = ctx->remote_i_size; diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 51421fdbb0ba..6f9242259edc 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -69,6 +69,7 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ OID_id_ansip384r1, /* 1.3.132.0.34 */ + OID_id_ansip521r1, /* 1.3.132.0.35 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 652d77805e99..4bf1c25fd1dc 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -190,7 +190,6 @@ enum pageflags { /* At least one page in this folio has the hwpoison flag set */ PG_has_hwpoisoned = PG_error, - PG_hugetlb = PG_active, PG_large_rmappable = PG_workingset, /* anon or file-backed */ }; @@ -458,30 +457,51 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) +#define FOLIO_TEST_FLAG_FALSE(name) \ +static inline bool folio_test_##name(const struct folio *folio) \ +{ return false; } +#define FOLIO_SET_FLAG_NOOP(name) \ +static inline void folio_set_##name(struct folio *folio) { } +#define FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void folio_clear_##name(struct folio *folio) { } +#define __FOLIO_SET_FLAG_NOOP(name) \ +static inline void __folio_set_##name(struct folio *folio) { } +#define __FOLIO_CLEAR_FLAG_NOOP(name) \ +static inline void __folio_clear_##name(struct folio *folio) { } +#define FOLIO_TEST_SET_FLAG_FALSE(name) \ +static inline bool folio_test_set_##name(struct folio *folio) \ +{ return false; } +#define FOLIO_TEST_CLEAR_FLAG_FALSE(name) \ +static inline bool folio_test_clear_##name(struct folio *folio) \ +{ return false; } + +#define FOLIO_FLAG_FALSE(name) \ +FOLIO_TEST_FLAG_FALSE(name) \ +FOLIO_SET_FLAG_NOOP(name) \ +FOLIO_CLEAR_FLAG_NOOP(name) + #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ +FOLIO_TEST_FLAG_FALSE(lname) \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_set_##lname(struct folio *folio) { } \ +FOLIO_SET_FLAG_NOOP(lname) \ static inline void SetPage##uname(struct page *page) { } #define CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void folio_clear_##lname(struct folio *folio) { } \ +FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname, lname) \ -static inline void __folio_clear_##lname(struct folio *folio) { } \ +__FOLIO_CLEAR_FLAG_NOOP(lname) \ static inline void __ClearPage##uname(struct page *page) { } #define TESTSETFLAG_FALSE(uname, lname) \ -static inline bool folio_test_set_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_SET_FLAG_FALSE(lname) \ static inline int TestSetPage##uname(struct page *page) { return 0; } #define TESTCLEARFLAG_FALSE(uname, lname) \ -static inline bool folio_test_clear_##lname(struct folio *folio) \ -{ return 0; } \ +FOLIO_TEST_CLEAR_FLAG_FALSE(lname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ @@ -855,29 +875,6 @@ TESTPAGEFLAG_FALSE(LargeRmappable, large_rmappable) #define PG_head_mask ((1UL << PG_head)) -#ifdef CONFIG_HUGETLB_PAGE -int PageHuge(const struct page *page); -SETPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) -CLEARPAGEFLAG(HugeTLB, hugetlb, PF_SECOND) - -/** - * folio_test_hugetlb - Determine if the folio belongs to hugetlbfs - * @folio: The folio to test. - * - * Context: Any context. Caller should have a reference on the folio to - * prevent it from being turned into a tail page. - * Return: True for hugetlbfs folios, false for anon folios or folios - * belonging to other filesystems. - */ -static inline bool folio_test_hugetlb(const struct folio *folio) -{ - return folio_test_large(folio) && - test_bit(PG_hugetlb, const_folio_flags(folio, 1)); -} -#else -TESTPAGEFLAG_FALSE(Huge, hugetlb) -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -934,33 +931,22 @@ PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* - * Check if a page is currently marked HWPoisoned. Note that this check is - * best effort only and inherently racy: there is no way to synchronize with - * failing hardware. - */ -static inline bool is_page_hwpoison(struct page *page) -{ - if (PageHWPoison(page)) - return true; - return PageHuge(page) && PageHWPoison(compound_head(page)); -} - -/* * For pages that are never mapped to userspace (and aren't PageSlab), * page_type may be used. Because it is initialised to -1, we invert the * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and * __ClearPageFoo *sets* the bit used for PageFoo. We reserve a few high and - * low bits so that an underflow or overflow of page_mapcount() won't be + * low bits so that an underflow or overflow of _mapcount won't be * mistaken for a page type value. */ #define PAGE_TYPE_BASE 0xf0000000 -/* Reserve 0x0000007f to catch underflows of page_mapcount */ +/* Reserve 0x0000007f to catch underflows of _mapcount */ #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 #define PG_table 0x00000200 #define PG_guard 0x00000400 +#define PG_hugetlb 0x00000800 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -977,35 +963,38 @@ static inline int page_has_type(const struct page *page) return page_type_has_type(page->page_type); } +#define FOLIO_TYPE_OPS(lname, fname) \ +static __always_inline bool folio_test_##fname(const struct folio *folio)\ +{ \ + return folio_test_type(folio, PG_##lname); \ +} \ +static __always_inline void __folio_set_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ + folio->page.page_type &= ~PG_##lname; \ +} \ +static __always_inline void __folio_clear_##fname(struct folio *folio) \ +{ \ + VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ + folio->page.page_type |= PG_##lname; \ +} + #define PAGE_TYPE_OPS(uname, lname, fname) \ +FOLIO_TYPE_OPS(lname, fname) \ static __always_inline int Page##uname(const struct page *page) \ { \ return PageType(page, PG_##lname); \ } \ -static __always_inline int folio_test_##fname(const struct folio *folio)\ -{ \ - return folio_test_type(folio, PG_##lname); \ -} \ static __always_inline void __SetPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!PageType(page, 0), page); \ page->page_type &= ~PG_##lname; \ } \ -static __always_inline void __folio_set_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_type(folio, 0), folio); \ - folio->page.page_type &= ~PG_##lname; \ -} \ static __always_inline void __ClearPage##uname(struct page *page) \ { \ VM_BUG_ON_PAGE(!Page##uname(page), page); \ page->page_type |= PG_##lname; \ -} \ -static __always_inline void __folio_clear_##fname(struct folio *folio) \ -{ \ - VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio); \ - folio->page.page_type |= PG_##lname; \ -} \ +} /* * PageBuddy() indicates that the page is free and in the buddy system @@ -1052,6 +1041,37 @@ PAGE_TYPE_OPS(Table, table, pgtable) */ PAGE_TYPE_OPS(Guard, guard, guard) +#ifdef CONFIG_HUGETLB_PAGE +FOLIO_TYPE_OPS(hugetlb, hugetlb) +#else +FOLIO_TEST_FLAG_FALSE(hugetlb) +#endif + +/** + * PageHuge - Determine if the page belongs to hugetlbfs + * @page: The page to test. + * + * Context: Any context. + * Return: True for hugetlbfs pages, false for anon pages or pages + * belonging to other filesystems. + */ +static inline bool PageHuge(const struct page *page) +{ + return folio_test_hugetlb(page_folio(page)); +} + +/* + * Check if a page is currently marked HWPoisoned. Note that this check is + * best effort only and inherently racy: there is no way to synchronize with + * failing hardware. + */ +static inline bool is_page_hwpoison(struct page *page) +{ + if (PageHWPoison(page)) + return true; + return PageHuge(page) && PageHWPoison(compound_head(page)); +} + extern bool is_free_buddy_page(struct page *page); PAGEFLAG(Isolated, isolated, PF_ANY); @@ -1118,7 +1138,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page) */ #define PAGE_FLAGS_SECOND \ (0xffUL /* order */ | 1UL << PG_has_hwpoisoned | \ - 1UL << PG_hugetlb | 1UL << PG_large_rmappable) + 1UL << PG_large_rmappable) #define PAGE_FLAGS_PRIVATE \ (1UL << PG_private | 1UL << PG_private_2) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2df35e65557d..c5e33e2ca48a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -40,6 +40,8 @@ int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); +int filemap_invalidate_inode(struct inode *inode, bool flush, + loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index a0c75e467df3..4beb29907c2b 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -580,6 +580,7 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F3 0x12fb #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3 0x12c3 #define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3 0x16fb +#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3 0x12bb #define PCI_DEVICE_ID_AMD_MI200_DF_F3 0x14d3 #define PCI_DEVICE_ID_AMD_MI300_DF_F3 0x152b #define PCI_DEVICE_ID_AMD_VANGOGH_USB 0x163a @@ -2686,8 +2687,10 @@ #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_HDA_HSW_0 0x0a0c +#define PCI_DEVICE_ID_INTEL_DSA_SPR0 0x0b25 #define PCI_DEVICE_ID_INTEL_HDA_HSW_2 0x0c0c #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 +#define PCI_DEVICE_ID_INTEL_IAX_SPR0 0x0cfe #define PCI_DEVICE_ID_INTEL_HDA_HSW_3 0x0d0c #define PCI_DEVICE_ID_INTEL_HDA_BYT 0x0f04 #define PCI_DEVICE_ID_INTEL_SST_BYT 0x0f28 diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d2a15c0c6f8a..a5304ae8c654 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -809,11 +809,8 @@ struct perf_event { u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; -#ifdef CONFIG_BPF_SYSCALL - perf_overflow_handler_t orig_overflow_handler; struct bpf_prog *prog; u64 bpf_cookie; -#endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; @@ -883,6 +880,7 @@ struct perf_event_pmu_context { unsigned int nr_events; unsigned int nr_cgroups; + unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; @@ -897,6 +895,11 @@ struct perf_event_pmu_context { int rotate_necessary; }; +static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) +{ + return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); +} + struct perf_event_groups { struct rb_root tree; u64 index; @@ -1342,8 +1345,10 @@ extern int perf_event_output(struct perf_event *event, struct pt_regs *regs); static inline bool -__is_default_overflow_handler(perf_overflow_handler_t overflow_handler) +is_default_overflow_handler(struct perf_event *event) { + perf_overflow_handler_t overflow_handler = event->overflow_handler; + if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) @@ -1351,22 +1356,6 @@ __is_default_overflow_handler(perf_overflow_handler_t overflow_handler) return false; } -#define is_default_overflow_handler(event) \ - __is_default_overflow_handler((event)->overflow_handler) - -#ifdef CONFIG_BPF_SYSCALL -static inline bool uses_default_overflow_handler(struct perf_event *event) -{ - if (likely(is_default_overflow_handler(event))) - return true; - - return __is_default_overflow_handler(event->orig_overflow_handler); -} -#else -#define uses_default_overflow_handler(event) \ - is_default_overflow_handler(event) -#endif - extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, @@ -1697,6 +1686,14 @@ perf_event_addr_filters(struct perf_event *event) return ifh; } +static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) +{ + /* Only the parent has fasync state */ + if (event->parent) + event = event->parent; + return &event->fasync; +} + extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index eb556f988d57..d8f15770a522 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -71,7 +71,6 @@ struct sysc_regbits { #define SYSC_QUIRK_SWSUP_SIDLE_ACT BIT(12) #define SYSC_QUIRK_SWSUP_SIDLE BIT(11) #define SYSC_QUIRK_EXT_OPT_CLOCK BIT(10) -#define SYSC_QUIRK_LEGACY_IDLE BIT(9) #define SYSC_QUIRK_RESET_STATUS BIT(8) #define SYSC_QUIRK_NO_IDLE BIT(7) #define SYSC_QUIRK_NO_IDLE_ON_INIT BIT(6) diff --git a/include/linux/profile.h b/include/linux/profile.h index 11db1ec516e2..04ae5ebcb637 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -18,13 +18,8 @@ struct proc_dir_entry; struct notifier_block; #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS) -void create_prof_cpu_mask(void); int create_proc_profile(void); #else -static inline void create_prof_cpu_mask(void) -{ -} - static inline int create_proc_profile(void) { return 0; diff --git a/include/linux/qat/qat_mig_dev.h b/include/linux/qat/qat_mig_dev.h new file mode 100644 index 000000000000..dbbb6a063dd2 --- /dev/null +++ b/include/linux/qat/qat_mig_dev.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright(c) 2024 Intel Corporation */ +#ifndef QAT_MIG_DEV_H_ +#define QAT_MIG_DEV_H_ + +struct pci_dev; + +struct qat_mig_dev { + void *parent_accel_dev; + u8 *state; + u32 setup_size; + u32 remote_setup_size; + u32 state_size; + s32 vf_id; +}; + +struct qat_mig_dev *qat_vfmig_create(struct pci_dev *pdev, int vf_id); +int qat_vfmig_init(struct qat_mig_dev *mdev); +void qat_vfmig_cleanup(struct qat_mig_dev *mdev); +void qat_vfmig_reset(struct qat_mig_dev *mdev); +int qat_vfmig_open(struct qat_mig_dev *mdev); +void qat_vfmig_close(struct qat_mig_dev *mdev); +int qat_vfmig_suspend(struct qat_mig_dev *mdev); +int qat_vfmig_resume(struct qat_mig_dev *mdev); +int qat_vfmig_save_state(struct qat_mig_dev *mdev); +int qat_vfmig_save_setup(struct qat_mig_dev *mdev); +int qat_vfmig_load_state(struct qat_mig_dev *mdev); +int qat_vfmig_load_setup(struct qat_mig_dev *mdev, int size); +void qat_vfmig_destroy(struct qat_mig_dev *mdev); + +#endif /*QAT_MIG_DEV_H_*/ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 17d7ed5f3ae6..dfd2399f2cde 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -401,15 +401,15 @@ static inline int debug_lockdep_rcu_enabled(void) } \ } while (0) -#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +#ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ @@ -809,9 +809,9 @@ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); + rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); - rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** @@ -1090,6 +1090,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; -DEFINE_LOCK_GUARD_0(rcu, rcu_read_lock(), rcu_read_unlock()) +DEFINE_LOCK_GUARD_0(rcu, + do { + rcu_read_lock(); + /* + * sparse doesn't call the cleanup function, + * so just release immediately and don't track + * the context. We don't need to anyway, since + * the whole point of the guard is to not need + * the explicit unlock. + */ + __release(RCU); + } while (0), + rcu_read_unlock()) #endif /* __LINUX_RCUPDATE_H */ diff --git a/include/linux/rcupdate_wait.h b/include/linux/rcupdate_wait.h index d07f0848802e..303ab9bee155 100644 --- a/include/linux/rcupdate_wait.h +++ b/include/linux/rcupdate_wait.h @@ -19,18 +19,18 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); -void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, +void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array); -#define _wait_rcu_gp(checktiny, ...) \ -do { \ - call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ - struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ - __wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array), \ - __crcu_array, __rs_array); \ +#define _wait_rcu_gp(checktiny, state, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)]; \ + __wait_rcu_gp(checktiny, state, ARRAY_SIZE(__crcu_array), __crcu_array, __rs_array); \ } while (0) -#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) +#define wait_rcu_gp(...) _wait_rcu_gp(false, TASK_UNINTERRUPTIBLE, __VA_ARGS__) +#define wait_rcu_gp_state(state, ...) _wait_rcu_gp(false, state, __VA_ARGS__) /** * synchronize_rcu_mult - Wait concurrently for multiple grace periods @@ -54,7 +54,7 @@ do { \ * grace period. */ #define synchronize_rcu_mult(...) \ - _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), TASK_UNINTERRUPTIBLE, __VA_ARGS__) static inline void cond_resched_rcu(void) { diff --git a/include/linux/regmap.h b/include/linux/regmap.h index b743241cfb7c..d470303b1bbb 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1230,6 +1230,7 @@ int regmap_multi_reg_write_bypassed(struct regmap *map, int regmap_raw_write_async(struct regmap *map, unsigned int reg, const void *val, size_t val_len); int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val); +int regmap_read_bypassed(struct regmap *map, unsigned int reg, unsigned int *val); int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len); int regmap_noinc_read(struct regmap *map, unsigned int reg, @@ -1739,6 +1740,13 @@ static inline int regmap_read(struct regmap *map, unsigned int reg, return -EINVAL; } +static inline int regmap_read_bypassed(struct regmap *map, unsigned int reg, + unsigned int *val) +{ + WARN_ONCE(1, "regmap API is disabled"); + return -EINVAL; +} + static inline int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, size_t val_len) { diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index 4660582a3302..ed180ca419da 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -320,13 +320,13 @@ devm_regulator_get_exclusive(struct device *dev, const char *id) static inline int devm_regulator_get_enable(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline int devm_regulator_get_enable_optional(struct device *dev, const char *id) { - return -ENODEV; + return 0; } static inline struct regulator *__must_check diff --git a/include/linux/sched.h b/include/linux/sched.h index 3c2abbc587b4..c75fd46506df 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -301,7 +301,7 @@ enum { TASK_COMM_LEN = 16, }; -extern void scheduler_tick(void); +extern void sched_tick(void); #define MAX_SCHEDULE_TIMEOUT LONG_MAX @@ -835,6 +835,7 @@ struct task_struct { #endif unsigned int policy; + unsigned long max_allowed_capacity; int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t *user_cpus_ptr; diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 478084f9105e..e670ac282333 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -5,8 +5,8 @@ #include <linux/sched.h> enum cpu_idle_type { + __CPU_NOT_IDLE = 0, CPU_IDLE, - CPU_NOT_IDLE, CPU_NEWLY_IDLE, CPU_MAX_IDLE_TYPES }; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 18572c9ea724..4237daa5ac7a 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -110,7 +110,7 @@ struct sched_domain { unsigned long last_decay_max_lb_cost; #ifdef CONFIG_SCHEDSTATS - /* load_balance() stats */ + /* sched_balance_rq() stats */ unsigned int lb_count[CPU_MAX_IDLE_TYPES]; unsigned int lb_failed[CPU_MAX_IDLE_TYPES]; unsigned int lb_balanced[CPU_MAX_IDLE_TYPES]; @@ -270,17 +270,17 @@ unsigned long arch_scale_cpu_capacity(int cpu) } #endif -#ifndef arch_scale_thermal_pressure +#ifndef arch_scale_hw_pressure static __always_inline -unsigned long arch_scale_thermal_pressure(int cpu) +unsigned long arch_scale_hw_pressure(int cpu) { return 0; } #endif -#ifndef arch_update_thermal_pressure +#ifndef arch_update_hw_pressure static __always_inline -void arch_update_thermal_pressure(const struct cpumask *cpus, +void arch_update_hw_pressure(const struct cpumask *cpus, unsigned long capped_frequency) { } #endif diff --git a/include/linux/scmi_protocol.h b/include/linux/scmi_protocol.h index b807141acc14..3a9bb5b9a9e8 100644 --- a/include/linux/scmi_protocol.h +++ b/include/linux/scmi_protocol.h @@ -737,6 +737,89 @@ struct scmi_powercap_proto_ops { u32 *power_thresh_high); }; +enum scmi_pinctrl_selector_type { + PIN_TYPE = 0, + GROUP_TYPE, + FUNCTION_TYPE, +}; + +enum scmi_pinctrl_conf_type { + SCMI_PIN_DEFAULT = 0, + SCMI_PIN_BIAS_BUS_HOLD = 1, + SCMI_PIN_BIAS_DISABLE = 2, + SCMI_PIN_BIAS_HIGH_IMPEDANCE = 3, + SCMI_PIN_BIAS_PULL_UP = 4, + SCMI_PIN_BIAS_PULL_DEFAULT = 5, + SCMI_PIN_BIAS_PULL_DOWN = 6, + SCMI_PIN_DRIVE_OPEN_DRAIN = 7, + SCMI_PIN_DRIVE_OPEN_SOURCE = 8, + SCMI_PIN_DRIVE_PUSH_PULL = 9, + SCMI_PIN_DRIVE_STRENGTH = 10, + SCMI_PIN_INPUT_DEBOUNCE = 11, + SCMI_PIN_INPUT_MODE = 12, + SCMI_PIN_PULL_MODE = 13, + SCMI_PIN_INPUT_VALUE = 14, + SCMI_PIN_INPUT_SCHMITT = 15, + SCMI_PIN_LOW_POWER_MODE = 16, + SCMI_PIN_OUTPUT_MODE = 17, + SCMI_PIN_OUTPUT_VALUE = 18, + SCMI_PIN_POWER_SOURCE = 19, + SCMI_PIN_SLEW_RATE = 20, + SCMI_PIN_OEM_START = 192, + SCMI_PIN_OEM_END = 255, +}; + +/** + * struct scmi_pinctrl_proto_ops - represents the various operations provided + * by SCMI Pinctrl Protocol + * + * @count_get: returns count of the registered elements in given type + * @name_get: returns name by index of given type + * @group_pins_get: returns the set of pins, assigned to the specified group + * @function_groups_get: returns the set of groups, assigned to the specified + * function + * @mux_set: set muxing function for groups of pins + * @settings_get_one: returns one configuration parameter for pin or group + * specified by config_type + * @settings_get_all: returns all configuration parameters for pin or group + * @settings_conf: sets the configuration parameter for pin or group + * @pin_request: aquire pin before selecting mux setting + * @pin_free: frees pin, acquired by request_pin call + */ +struct scmi_pinctrl_proto_ops { + int (*count_get)(const struct scmi_protocol_handle *ph, + enum scmi_pinctrl_selector_type type); + int (*name_get)(const struct scmi_protocol_handle *ph, u32 selector, + enum scmi_pinctrl_selector_type type, + const char **name); + int (*group_pins_get)(const struct scmi_protocol_handle *ph, + u32 selector, const unsigned int **pins, + unsigned int *nr_pins); + int (*function_groups_get)(const struct scmi_protocol_handle *ph, + u32 selector, unsigned int *nr_groups, + const unsigned int **groups); + int (*mux_set)(const struct scmi_protocol_handle *ph, u32 selector, + u32 group); + int (*settings_get_one)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + enum scmi_pinctrl_conf_type config_type, + u32 *config_value); + int (*settings_get_all)(const struct scmi_protocol_handle *ph, + u32 selector, + enum scmi_pinctrl_selector_type type, + unsigned int *nr_configs, + enum scmi_pinctrl_conf_type *config_types, + u32 *config_values); + int (*settings_conf)(const struct scmi_protocol_handle *ph, + u32 selector, enum scmi_pinctrl_selector_type type, + unsigned int nr_configs, + enum scmi_pinctrl_conf_type *config_type, + u32 *config_value); + int (*pin_request)(const struct scmi_protocol_handle *ph, u32 pin); + int (*pin_free)(const struct scmi_protocol_handle *ph, u32 pin); +}; + /** * struct scmi_notify_ops - represents notifications' operations provided by * SCMI core @@ -783,8 +866,6 @@ struct scmi_notify_ops { const u32 *src_id, struct notifier_block *nb); int (*devm_event_notifier_unregister)(struct scmi_device *sdev, - u8 proto_id, u8 evt_id, - const u32 *src_id, struct notifier_block *nb); int (*event_notifier_register)(const struct scmi_handle *handle, u8 proto_id, u8 evt_id, @@ -844,6 +925,7 @@ enum scmi_std_protocol { SCMI_PROTOCOL_RESET = 0x16, SCMI_PROTOCOL_VOLTAGE = 0x17, SCMI_PROTOCOL_POWERCAP = 0x18, + SCMI_PROTOCOL_PINCTRL = 0x19, }; enum scmi_system_events { diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 234bcdb1fba4..8bd4fda6e027 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,7 +118,18 @@ void seq_vprintf(struct seq_file *m, const char *fmt, va_list args); __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); -void seq_puts(struct seq_file *m, const char *s); +void __seq_puts(struct seq_file *m, const char *s); + +static __always_inline void seq_puts(struct seq_file *m, const char *s) +{ + if (!__builtin_constant_p(*s)) + __seq_puts(m, s); + else if (s[0] && !s[1]) + seq_putc(m, s[0]); + else + seq_write(m, s, __builtin_strlen(s)); +} + void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, diff --git a/include/linux/shm.h b/include/linux/shm.h index c55bef0538e5..1d3d3ae958fb 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -16,7 +16,6 @@ struct sysv_shm { long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr, unsigned long shmlba); -bool is_file_shm_hugepages(struct file *file); void exit_shm(struct task_struct *task); #define shm_init_task(task) INIT_LIST_HEAD(&(task)->sysvshm.shm_clist) #else @@ -30,10 +29,6 @@ static inline long do_shmat(int shmid, char __user *shmaddr, { return -ENOSYS; } -static inline bool is_file_shm_hugepages(struct file *file) -{ - return false; -} static inline void exit_shm(struct task_struct *task) { } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9d24aec064e8..1cc72c370190 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -527,6 +527,13 @@ enum { #define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY | \ SKBFL_DONT_ORPHAN | SKBFL_MANAGED_FRAG_REFS) +struct ubuf_info_ops { + void (*complete)(struct sk_buff *, struct ubuf_info *, + bool zerocopy_success); + /* has to be compatible with skb_zcopy_set() */ + int (*link_skb)(struct sk_buff *skb, struct ubuf_info *uarg); +}; + /* * The callback notifies userspace to release buffers when skb DMA is done in * lower device, the skb last reference should be 0 when calling this. @@ -536,8 +543,7 @@ enum { * The desc field is used to track userspace buffer index. */ struct ubuf_info { - void (*callback)(struct sk_buff *, struct ubuf_info *, - bool zerocopy_success); + const struct ubuf_info_ops *ops; refcount_t refcnt; u8 flags; }; @@ -1662,14 +1668,13 @@ static inline void skb_set_end_offset(struct sk_buff *skb, unsigned int offset) } #endif +extern const struct ubuf_info_ops msg_zerocopy_ubuf_ops; + struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, struct ubuf_info *uarg); void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref); -void msg_zerocopy_callback(struct sk_buff *skb, struct ubuf_info *uarg, - bool success); - int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, struct sk_buff *skb, struct iov_iter *from, size_t length); @@ -1757,13 +1762,13 @@ static inline void *skb_zcopy_get_nouarg(struct sk_buff *skb) static inline void net_zcopy_put(struct ubuf_info *uarg) { if (uarg) - uarg->callback(NULL, uarg, true); + uarg->ops->complete(NULL, uarg, true); } static inline void net_zcopy_put_abort(struct ubuf_info *uarg, bool have_uref) { if (uarg) { - if (uarg->callback == msg_zerocopy_callback) + if (uarg->ops == &msg_zerocopy_ubuf_ops) msg_zerocopy_put_abort(uarg, have_uref); else if (have_uref) net_zcopy_put(uarg); @@ -1777,7 +1782,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (uarg) { if (!skb_zcopy_is_nouarg(skb)) - uarg->callback(skb, uarg, zerocopy_success); + uarg->ops->complete(skb, uarg, zerocopy_success); skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } @@ -3031,6 +3036,21 @@ static inline void skb_mac_header_rebuild(struct sk_buff *skb) } } +/* Move the full mac header up to current network_header. + * Leaves skb->data pointing at offset skb->mac_len into the mac_header. + * Must be provided the complete mac header length. + */ +static inline void skb_mac_header_rebuild_full(struct sk_buff *skb, u32 full_mac_len) +{ + if (skb_mac_header_was_set(skb)) { + const unsigned char *old_mac = skb_mac_header(skb); + + skb_set_mac_header(skb, -full_mac_len); + memmove(skb_mac_header(skb), old_mac, full_mac_len); + __skb_push(skb, full_mac_len - skb->mac_len); + } +} + static inline int skb_checksum_start_offset(const struct sk_buff *skb) { return skb->csum_start - skb_headroom(skb); diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index e65ec3fd2799..a509caf823d6 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -461,10 +461,12 @@ static inline void sk_psock_put(struct sock *sk, struct sk_psock *psock) static inline void sk_psock_data_ready(struct sock *sk, struct sk_psock *psock) { + read_lock_bh(&sk->sk_callback_lock); if (psock->saved_data_ready) psock->saved_data_ready(sk); else sk->sk_data_ready(sk); + read_unlock_bh(&sk->sk_callback_lock); } static inline void psock_set_prog(struct bpf_prog **pprog, diff --git a/include/linux/slab.h b/include/linux/slab.h index e53cbfa18325..739b21262507 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -266,7 +266,7 @@ void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); -DEFINE_FREE(kfree, void *, if (_T) kfree(_T)) +DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) /** * ksize - Report actual allocation size of associated object @@ -792,7 +792,7 @@ static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t fla extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) __realloc_size(3); extern void kvfree(const void *addr); -DEFINE_FREE(kvfree, void *, if (_T) kvfree(_T)) +DEFINE_FREE(kvfree, void *, if (!IS_ERR_OR_NULL(_T)) kvfree(_T)) extern void kvfree_sensitive(const void *addr, size_t len); diff --git a/include/linux/soc/mediatek/mtk-cmdq.h b/include/linux/soc/mediatek/mtk-cmdq.h index 649955d2cf5c..d4a8e34505e6 100644 --- a/include/linux/soc/mediatek/mtk-cmdq.h +++ b/include/linux/soc/mediatek/mtk-cmdq.h @@ -14,6 +14,15 @@ #define CMDQ_ADDR_HIGH(addr) ((u32)(((addr) >> 16) & GENMASK(31, 0))) #define CMDQ_ADDR_LOW(addr) ((u16)(addr) | BIT(1)) +/* + * Every cmdq thread has its own SPRs (Specific Purpose Registers), + * so there are 4 * N (threads) SPRs in GCE that shares the same indexes below. + */ +#define CMDQ_THR_SPR_IDX0 (0) +#define CMDQ_THR_SPR_IDX1 (1) +#define CMDQ_THR_SPR_IDX2 (2) +#define CMDQ_THR_SPR_IDX3 (3) + struct cmdq_pkt; struct cmdq_client_reg { @@ -62,17 +71,19 @@ void cmdq_mbox_destroy(struct cmdq_client *client); /** * cmdq_pkt_create() - create a CMDQ packet * @client: the CMDQ mailbox client + * @pkt: the CMDQ packet * @size: required CMDQ buffer size * - * Return: CMDQ packet pointer + * Return: 0 for success; else the error code is returned */ -struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size); +int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size); /** * cmdq_pkt_destroy() - destroy the CMDQ packet + * @client: the CMDQ mailbox client * @pkt: the CMDQ packet */ -void cmdq_pkt_destroy(struct cmdq_pkt *pkt); +void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt); /** * cmdq_pkt_write() - append write command to the CMDQ packet @@ -174,6 +185,18 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, u16 addr_low, u32 value, u32 mask); /** + * cmdq_pkt_mem_move() - append memory move command to the CMDQ packet + * @pkt: the CMDQ packet + * @src_addr: source address + * @dst_addr: destination address + * + * Appends a CMDQ command to copy the value found in `src_addr` to `dst_addr`. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_mem_move(struct cmdq_pkt *pkt, dma_addr_t src_addr, dma_addr_t dst_addr); + +/** * cmdq_pkt_wfe() - append wait for event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event type to wait @@ -184,6 +207,21 @@ int cmdq_pkt_write_s_mask_value(struct cmdq_pkt *pkt, u8 high_addr_reg_idx, int cmdq_pkt_wfe(struct cmdq_pkt *pkt, u16 event, bool clear); /** + * cmdq_pkt_acquire_event() - append acquire event command to the CMDQ packet + * @pkt: the CMDQ packet + * @event: the desired event to be acquired + * + * User can use cmdq_pkt_acquire_event() as `mutex_lock` and cmdq_pkt_clear_event() + * as `mutex_unlock` to protect some `critical section` instructions between them. + * cmdq_pkt_acquire_event() would wait for event to be cleared. + * After event is cleared by cmdq_pkt_clear_event in other GCE threads, + * cmdq_pkt_acquire_event() would set event and keep executing next instruction. + * + * Return: 0 for success; else the error code is returned + */ +int cmdq_pkt_acquire_event(struct cmdq_pkt *pkt, u16 event); + +/** * cmdq_pkt_clear_event() - append clear event command to the CMDQ packet * @pkt: the CMDQ packet * @event: the desired event to be cleared @@ -248,36 +286,76 @@ int cmdq_pkt_poll_mask(struct cmdq_pkt *pkt, u8 subsys, int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value); /** - * cmdq_pkt_jump() - Append jump command to the CMDQ packet, ask GCE - * to execute an instruction that change current thread PC to - * a physical address which should contains more instruction. + * cmdq_pkt_poll_addr() - Append blocking POLL command to CMDQ packet + * @pkt: the CMDQ packet + * @addr: the hardware register address + * @value: the specified target register value + * @mask: the specified target register mask + * + * Appends a polling (POLL) command to the CMDQ packet and asks the GCE + * to execute an instruction that checks for the specified `value` (with + * or without `mask`) to appear in the specified hardware register `addr`. + * All GCE threads will be blocked by this instruction. + * + * Return: 0 for success or negative error code + */ +int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask); + +/** + * cmdq_pkt_jump_abs() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a absolute physical address which should + * contains more instruction. * @pkt: the CMDQ packet - * @addr: physical address of target instruction buffer + * @addr: absolute physical address of target instruction buffer + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr); +int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa); + +/* This wrapper has to be removed after all users migrated to jump_abs */ +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return cmdq_pkt_jump_abs(pkt, addr, shift_pa); +} /** - * cmdq_pkt_finalize() - Append EOC and jump command to pkt. + * cmdq_pkt_jump_rel() - Append jump command to the CMDQ packet, ask GCE + * to execute an instruction that change current thread + * PC to a physical address with relative offset. The + * target address should contains more instruction. * @pkt: the CMDQ packet + * @offset: relative offset of target instruction buffer from current PC. + * @shift_pa: shift bits of physical address in CMDQ instruction. This value + * is got by cmdq_get_shift_pa(). * * Return: 0 for success; else the error code is returned */ -int cmdq_pkt_finalize(struct cmdq_pkt *pkt); +int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa); + +/** + * cmdq_pkt_eoc() - Append EOC and ask GCE to generate an IRQ at end of execution + * @pkt: The CMDQ packet + * + * Appends an End Of Code (EOC) command to the CMDQ packet and asks the GCE + * to generate an interrupt at the end of the execution of all commands in + * the pipeline. + * The EOC command is usually appended to the end of the pipeline to notify + * that all commands are done. + * + * Return: 0 for success or negative error number + */ +int cmdq_pkt_eoc(struct cmdq_pkt *pkt); /** - * cmdq_pkt_flush_async() - trigger CMDQ to asynchronously execute the CMDQ - * packet and call back at the end of done packet + * cmdq_pkt_finalize() - Append EOC and jump command to pkt. * @pkt: the CMDQ packet * * Return: 0 for success; else the error code is returned - * - * Trigger CMDQ to asynchronously execute the CMDQ packet and call back - * at the end of done packet. Note that this is an ASYNC function. When the - * function returned, it may or may not be finished. */ -int cmdq_pkt_flush_async(struct cmdq_pkt *pkt); +int cmdq_pkt_finalize(struct cmdq_pkt *pkt); #else /* IS_ENABLED(CONFIG_MTK_CMDQ) */ @@ -294,12 +372,12 @@ static inline struct cmdq_client *cmdq_mbox_create(struct device *dev, int index static inline void cmdq_mbox_destroy(struct cmdq_client *client) { } -static inline struct cmdq_pkt *cmdq_pkt_create(struct cmdq_client *client, size_t size) +static inline int cmdq_pkt_create(struct cmdq_client *client, struct cmdq_pkt *pkt, size_t size) { - return ERR_PTR(-EINVAL); + return -EINVAL; } -static inline void cmdq_pkt_destroy(struct cmdq_pkt *pkt) { } +static inline void cmdq_pkt_destroy(struct cmdq_client *client, struct cmdq_pkt *pkt) { } static inline int cmdq_pkt_write(struct cmdq_pkt *pkt, u8 subsys, u16 offset, u32 value) { @@ -374,17 +452,32 @@ static inline int cmdq_pkt_assign(struct cmdq_pkt *pkt, u16 reg_idx, u32 value) return -EINVAL; } -static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr) +static inline int cmdq_pkt_poll_addr(struct cmdq_pkt *pkt, dma_addr_t addr, u32 value, u32 mask) { return -EINVAL; } -static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_jump_abs(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump(struct cmdq_pkt *pkt, dma_addr_t addr, u8 shift_pa) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_jump_rel(struct cmdq_pkt *pkt, s32 offset, u8 shift_pa) { return -EINVAL; } -static inline int cmdq_pkt_flush_async(struct cmdq_pkt *pkt) +static inline int cmdq_pkt_eoc(struct cmdq_pkt *pkt) +{ + return -EINVAL; +} + +static inline int cmdq_pkt_finalize(struct cmdq_pkt *pkt) { return -EINVAL; } diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h index 447133171d95..4d96bbdb45f0 100644 --- a/include/linux/srcutiny.h +++ b/include/linux/srcutiny.h @@ -64,8 +64,10 @@ static inline int __srcu_read_lock(struct srcu_struct *ssp) { int idx; + preempt_disable(); // Needed for PREEMPT_AUTO idx = ((READ_ONCE(ssp->srcu_idx) + 1) & 0x2) >> 1; WRITE_ONCE(ssp->srcu_lock_nesting[idx], READ_ONCE(ssp->srcu_lock_nesting[idx]) + 1); + preempt_enable(); return idx; } diff --git a/include/linux/stat.h b/include/linux/stat.h index 52150570d37a..bf92441dbad2 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -53,6 +53,7 @@ struct kstat { u32 dio_mem_align; u32 dio_offset_align; u64 change_cookie; + u64 subvol; }; /* These definitions are internal to the kernel for now. Mainly used by nfsd. */ diff --git a/include/linux/string.h b/include/linux/string.h index 9ba8b4597009..10e5177bb49c 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -14,8 +14,8 @@ #include <uapi/linux/string.h> extern char *strndup_user(const char __user *, long); -extern void *memdup_user(const void __user *, size_t); -extern void *vmemdup_user(const void __user *, size_t); +extern void *memdup_user(const void __user *, size_t) __realloc_size(2); +extern void *vmemdup_user(const void __user *, size_t) __realloc_size(2); extern void *memdup_user_nul(const void __user *, size_t); /** @@ -27,7 +27,8 @@ extern void *memdup_user_nul(const void __user *, size_t); * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ -static inline void *memdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *memdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -46,7 +47,8 @@ static inline void *memdup_array_user(const void __user *src, size_t n, size_t s * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ -static inline void *vmemdup_array_user(const void __user *src, size_t n, size_t size) +static inline __realloc_size(2, 3) +void *vmemdup_array_user(const void __user *src, size_t n, size_t size) { size_t nbytes; @@ -285,7 +287,8 @@ extern char *kstrndup(const char *s, size_t len, gfp_t gfp); extern void *kmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern void *kvmemdup(const void *src, size_t len, gfp_t gfp) __realloc_size(2); extern char *kmemdup_nul(const char *s, size_t len, gfp_t gfp); -extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp); +extern void *kmemdup_array(const void *src, size_t element_size, size_t count, gfp_t gfp) + __realloc_size(2, 3); /* lib/argv_split.c */ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); @@ -423,6 +426,55 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, } while (0) /** + * memtostr - Copy a possibly non-NUL-term string to a NUL-term string + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + dest[_copy_len] = '\0'; \ +} while (0) + +/** + * memtostr_pad - Copy a possibly non-NUL-term string to a NUL-term string + * with NUL padding in the destination + * @dest: Pointer to destination NUL-terminates string + * @src: Pointer to character array (likely marked as __nonstring) + * + * This is a replacement for strncpy() uses where the source is not + * a NUL-terminated string. + * + * Note that sizes of @dest and @src must be known at compile-time. + */ +#define memtostr_pad(dest, src) do { \ + const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _src_len = __builtin_object_size(src, 1); \ + const size_t _src_chars = strnlen(src, _src_len); \ + const size_t _copy_len = min(_dest_len - 1, _src_chars); \ + \ + BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ + !__builtin_constant_p(_src_len) || \ + _dest_len == 0 || _dest_len == (size_t)-1 || \ + _src_len == 0 || _src_len == (size_t)-1); \ + memcpy(dest, src, _copy_len); \ + memset(&dest[_copy_len], 0, _dest_len - _copy_len); \ +} while (0) + +/** * memset_after - Set a value after a struct member to the end of a struct * * @obj: Address of target struct instance diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 24cd199dd6f3..d33bab33099a 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -210,7 +210,6 @@ struct svc_rdma_recv_ctxt { */ struct svc_rdma_write_info { struct svcxprt_rdma *wi_rdma; - struct list_head wi_list; const struct svc_rdma_chunk *wi_chunk; @@ -239,10 +238,7 @@ struct svc_rdma_send_ctxt { struct ib_cqe sc_cqe; struct xdr_buf sc_hdrbuf; struct xdr_stream sc_stream; - - struct list_head sc_write_info_list; struct svc_rdma_write_info sc_reply_info; - void *sc_xprt_buf; int sc_page_count; int sc_cur_sge_no; @@ -274,14 +270,11 @@ extern void svc_rdma_cc_init(struct svcxprt_rdma *rdma, extern void svc_rdma_cc_release(struct svcxprt_rdma *rdma, struct svc_rdma_chunk_ctxt *cc, enum dma_data_direction dir); -extern void svc_rdma_write_chunk_release(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt); extern void svc_rdma_reply_chunk_release(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt); -extern int svc_rdma_prepare_write_list(struct svcxprt_rdma *rdma, - const struct svc_rdma_pcl *write_pcl, - struct svc_rdma_send_ctxt *sctxt, - const struct xdr_buf *xdr); +extern int svc_rdma_send_write_list(struct svcxprt_rdma *rdma, + const struct svc_rdma_recv_ctxt *rctxt, + const struct xdr_buf *xdr); extern int svc_rdma_prepare_reply_chunk(struct svcxprt_rdma *rdma, const struct svc_rdma_pcl *write_pcl, const struct svc_rdma_pcl *reply_pcl, diff --git a/include/linux/tee_core.h b/include/linux/tee_core.h new file mode 100644 index 000000000000..efd16ed52315 --- /dev/null +++ b/include/linux/tee_core.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Linaro Limited + */ + +#ifndef __TEE_CORE_H +#define __TEE_CORE_H + +#include <linux/cdev.h> +#include <linux/device.h> +#include <linux/idr.h> +#include <linux/kref.h> +#include <linux/list.h> +#include <linux/tee.h> +#include <linux/tee_drv.h> +#include <linux/types.h> +#include <linux/uuid.h> + +/* + * The file describes the API provided by the generic TEE driver to the + * specific TEE driver. + */ + +#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ + /* in secure world */ +#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ +#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ +#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ + +#define TEE_DEVICE_FLAG_REGISTERED 0x1 +#define TEE_MAX_DEV_NAME_LEN 32 + +/** + * struct tee_device - TEE Device representation + * @name: name of device + * @desc: description of device + * @id: unique id of device + * @flags: represented by TEE_DEVICE_FLAG_REGISTERED above + * @dev: embedded basic device structure + * @cdev: embedded cdev + * @num_users: number of active users of this device + * @c_no_user: completion used when unregistering the device + * @mutex: mutex protecting @num_users and @idr + * @idr: register of user space shared memory objects allocated or + * registered on this device + * @pool: shared memory pool + */ +struct tee_device { + char name[TEE_MAX_DEV_NAME_LEN]; + const struct tee_desc *desc; + int id; + unsigned int flags; + + struct device dev; + struct cdev cdev; + + size_t num_users; + struct completion c_no_users; + struct mutex mutex; /* protects num_users and idr */ + + struct idr idr; + struct tee_shm_pool *pool; +}; + +/** + * struct tee_driver_ops - driver operations vtable + * @get_version: returns version of driver + * @open: called when the device file is opened + * @release: release this open file + * @open_session: open a new session + * @close_session: close a session + * @system_session: declare session as a system session + * @invoke_func: invoke a trusted function + * @cancel_req: request cancel of an ongoing invoke or open + * @supp_recv: called for supplicant to get a command + * @supp_send: called for supplicant to send a response + * @shm_register: register shared memory buffer in TEE + * @shm_unregister: unregister shared memory buffer in TEE + */ +struct tee_driver_ops { + void (*get_version)(struct tee_device *teedev, + struct tee_ioctl_version_data *vers); + int (*open)(struct tee_context *ctx); + void (*release)(struct tee_context *ctx); + int (*open_session)(struct tee_context *ctx, + struct tee_ioctl_open_session_arg *arg, + struct tee_param *param); + int (*close_session)(struct tee_context *ctx, u32 session); + int (*system_session)(struct tee_context *ctx, u32 session); + int (*invoke_func)(struct tee_context *ctx, + struct tee_ioctl_invoke_arg *arg, + struct tee_param *param); + int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); + int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, + struct tee_param *param); + int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, + struct tee_param *param); + int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, + struct page **pages, size_t num_pages, + unsigned long start); + int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); +}; + +/** + * struct tee_desc - Describes the TEE driver to the subsystem + * @name: name of driver + * @ops: driver operations vtable + * @owner: module providing the driver + * @flags: Extra properties of driver, defined by TEE_DESC_* below + */ +#define TEE_DESC_PRIVILEGED 0x1 +struct tee_desc { + const char *name; + const struct tee_driver_ops *ops; + struct module *owner; + u32 flags; +}; + +/** + * tee_device_alloc() - Allocate a new struct tee_device instance + * @teedesc: Descriptor for this driver + * @dev: Parent device for this device + * @pool: Shared memory pool, NULL if not used + * @driver_data: Private driver data for this device + * + * Allocates a new struct tee_device instance. The device is + * removed by tee_device_unregister(). + * + * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure + */ +struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, + struct device *dev, + struct tee_shm_pool *pool, + void *driver_data); + +/** + * tee_device_register() - Registers a TEE device + * @teedev: Device to register + * + * tee_device_unregister() need to be called to remove the @teedev if + * this function fails. + * + * @returns < 0 on failure + */ +int tee_device_register(struct tee_device *teedev); + +/** + * tee_device_unregister() - Removes a TEE device + * @teedev: Device to unregister + * + * This function should be called to remove the @teedev even if + * tee_device_register() hasn't been called yet. Does nothing if + * @teedev is NULL. + */ +void tee_device_unregister(struct tee_device *teedev); + +/** + * tee_session_calc_client_uuid() - Calculates client UUID for session + * @uuid: Resulting UUID + * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) + * @connectuon_data: Connection data for opening session + * + * Based on connection method calculates UUIDv5 based client UUID. + * + * For group based logins verifies that calling process has specified + * credentials. + * + * @return < 0 on failure + */ +int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, + const u8 connection_data[TEE_IOCTL_UUID_LEN]); + +/** + * struct tee_shm_pool - shared memory pool + * @ops: operations + * @private_data: private data for the shared memory manager + */ +struct tee_shm_pool { + const struct tee_shm_pool_ops *ops; + void *private_data; +}; + +/** + * struct tee_shm_pool_ops - shared memory pool operations + * @alloc: called when allocating shared memory + * @free: called when freeing shared memory + * @destroy_pool: called when destroying the pool + */ +struct tee_shm_pool_ops { + int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, + size_t size, size_t align); + void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); + void (*destroy_pool)(struct tee_shm_pool *pool); +}; + +/* + * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory + * @vaddr: Virtual address of start of pool + * @paddr: Physical address of start of pool + * @size: Size in bytes of the pool + * + * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. + */ +struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, + phys_addr_t paddr, size_t size, + int min_alloc_order); + +/** + * tee_shm_pool_free() - Free a shared memory pool + * @pool: The shared memory pool to free + * + * The must be no remaining shared memory allocated from this pool when + * this function is called. + */ +static inline void tee_shm_pool_free(struct tee_shm_pool *pool) +{ + pool->ops->destroy_pool(pool); +} + +/** + * tee_get_drvdata() - Return driver_data pointer + * @returns the driver_data pointer supplied to tee_register(). + */ +void *tee_get_drvdata(struct tee_device *teedev); + +/** + * tee_shm_alloc_priv_buf() - Allocate shared memory for private use by specific + * TEE driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); + +int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, + int (*shm_register)(struct tee_context *ctx, + struct tee_shm *shm, + struct page **pages, + size_t num_pages, + unsigned long start)); +void tee_dyn_shm_free_helper(struct tee_shm *shm, + int (*shm_unregister)(struct tee_context *ctx, + struct tee_shm *shm)); + +/** + * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind + * @shm: Shared memory handle + * @returns true if object is dynamic shared memory + */ +static inline bool tee_shm_is_dynamic(struct tee_shm *shm) +{ + return shm && (shm->flags & TEE_SHM_DYNAMIC); +} + +/** + * tee_shm_put() - Decrease reference count on a shared memory handle + * @shm: Shared memory handle + */ +void tee_shm_put(struct tee_shm *shm); + +/** + * tee_shm_get_id() - Get id of a shared memory object + * @shm: Shared memory handle + * @returns id + */ +static inline int tee_shm_get_id(struct tee_shm *shm) +{ + return shm->id; +} + +/** + * tee_shm_get_from_id() - Find shared memory object and increase reference + * count + * @ctx: Context owning the shared memory + * @id: Id of shared memory object + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure + */ +struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); + +static inline bool tee_param_is_memref(struct tee_param *param) +{ + switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: + case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: + return true; + default: + return false; + } +} + +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + +#endif /*__TEE_CORE_H*/ diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 71632e3c5f18..786b9ae6cf4d 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -1,40 +1,28 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015-2022 Linaro Limited + * Copyright (c) 2015-2024 Linaro Limited */ #ifndef __TEE_DRV_H #define __TEE_DRV_H #include <linux/device.h> -#include <linux/idr.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/mod_devicetable.h> #include <linux/tee.h> #include <linux/types.h> -#include <linux/uuid.h> /* - * The file describes the API provided by the generic TEE driver to the - * specific TEE driver. + * The file describes the API provided by the TEE subsystem to the + * TEE client drivers. */ -#define TEE_SHM_DYNAMIC BIT(0) /* Dynamic shared memory registered */ - /* in secure world */ -#define TEE_SHM_USER_MAPPED BIT(1) /* Memory mapped in user space */ -#define TEE_SHM_POOL BIT(2) /* Memory allocated from pool */ -#define TEE_SHM_PRIV BIT(3) /* Memory private to TEE driver */ - -struct device; struct tee_device; -struct tee_shm; -struct tee_shm_pool; /** * struct tee_context - driver specific context on file pointer data * @teedev: pointer to this drivers struct tee_device - * @list_shm: List of shared memory object owned by this context * @data: driver specific context data, managed by the driver * @refcount: reference counter for this structure * @releasing: flag that indicates if context is being released right now. @@ -57,134 +45,6 @@ struct tee_context { bool cap_memref_null; }; -struct tee_param_memref { - size_t shm_offs; - size_t size; - struct tee_shm *shm; -}; - -struct tee_param_value { - u64 a; - u64 b; - u64 c; -}; - -struct tee_param { - u64 attr; - union { - struct tee_param_memref memref; - struct tee_param_value value; - } u; -}; - -/** - * struct tee_driver_ops - driver operations vtable - * @get_version: returns version of driver - * @open: called when the device file is opened - * @release: release this open file - * @open_session: open a new session - * @close_session: close a session - * @system_session: declare session as a system session - * @invoke_func: invoke a trusted function - * @cancel_req: request cancel of an ongoing invoke or open - * @supp_recv: called for supplicant to get a command - * @supp_send: called for supplicant to send a response - * @shm_register: register shared memory buffer in TEE - * @shm_unregister: unregister shared memory buffer in TEE - */ -struct tee_driver_ops { - void (*get_version)(struct tee_device *teedev, - struct tee_ioctl_version_data *vers); - int (*open)(struct tee_context *ctx); - void (*release)(struct tee_context *ctx); - int (*open_session)(struct tee_context *ctx, - struct tee_ioctl_open_session_arg *arg, - struct tee_param *param); - int (*close_session)(struct tee_context *ctx, u32 session); - int (*system_session)(struct tee_context *ctx, u32 session); - int (*invoke_func)(struct tee_context *ctx, - struct tee_ioctl_invoke_arg *arg, - struct tee_param *param); - int (*cancel_req)(struct tee_context *ctx, u32 cancel_id, u32 session); - int (*supp_recv)(struct tee_context *ctx, u32 *func, u32 *num_params, - struct tee_param *param); - int (*supp_send)(struct tee_context *ctx, u32 ret, u32 num_params, - struct tee_param *param); - int (*shm_register)(struct tee_context *ctx, struct tee_shm *shm, - struct page **pages, size_t num_pages, - unsigned long start); - int (*shm_unregister)(struct tee_context *ctx, struct tee_shm *shm); -}; - -/** - * struct tee_desc - Describes the TEE driver to the subsystem - * @name: name of driver - * @ops: driver operations vtable - * @owner: module providing the driver - * @flags: Extra properties of driver, defined by TEE_DESC_* below - */ -#define TEE_DESC_PRIVILEGED 0x1 -struct tee_desc { - const char *name; - const struct tee_driver_ops *ops; - struct module *owner; - u32 flags; -}; - -/** - * tee_device_alloc() - Allocate a new struct tee_device instance - * @teedesc: Descriptor for this driver - * @dev: Parent device for this device - * @pool: Shared memory pool, NULL if not used - * @driver_data: Private driver data for this device - * - * Allocates a new struct tee_device instance. The device is - * removed by tee_device_unregister(). - * - * @returns a pointer to a 'struct tee_device' or an ERR_PTR on failure - */ -struct tee_device *tee_device_alloc(const struct tee_desc *teedesc, - struct device *dev, - struct tee_shm_pool *pool, - void *driver_data); - -/** - * tee_device_register() - Registers a TEE device - * @teedev: Device to register - * - * tee_device_unregister() need to be called to remove the @teedev if - * this function fails. - * - * @returns < 0 on failure - */ -int tee_device_register(struct tee_device *teedev); - -/** - * tee_device_unregister() - Removes a TEE device - * @teedev: Device to unregister - * - * This function should be called to remove the @teedev even if - * tee_device_register() hasn't been called yet. Does nothing if - * @teedev is NULL. - */ -void tee_device_unregister(struct tee_device *teedev); - -/** - * tee_session_calc_client_uuid() - Calculates client UUID for session - * @uuid: Resulting UUID - * @connection_method: Connection method for session (TEE_IOCTL_LOGIN_*) - * @connectuon_data: Connection data for opening session - * - * Based on connection method calculates UUIDv5 based client UUID. - * - * For group based logins verifies that calling process has specified - * credentials. - * - * @return < 0 on failure - */ -int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, - const u8 connection_data[TEE_IOCTL_UUID_LEN]); - /** * struct tee_shm - shared memory object * @ctx: context using the object @@ -195,15 +55,12 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @pages: locked pages from userspace * @num_pages: number of locked pages * @refcount: reference counter - * @flags: defined by TEE_SHM_* in tee_drv.h + * @flags: defined by TEE_SHM_* in tee_core.h * @id: unique id of a shared memory object on this device, shared * with user space * @sec_world_id: * secure world assigned id of this shared memory object, not * used by all drivers - * - * This pool is only supposed to be accessed directly from the TEE - * subsystem and from drivers that implements their own shm pool manager. */ struct tee_shm { struct tee_context *ctx; @@ -219,88 +76,53 @@ struct tee_shm { u64 sec_world_id; }; -/** - * struct tee_shm_pool - shared memory pool - * @ops: operations - * @private_data: private data for the shared memory manager - */ -struct tee_shm_pool { - const struct tee_shm_pool_ops *ops; - void *private_data; +struct tee_param_memref { + size_t shm_offs; + size_t size; + struct tee_shm *shm; }; -/** - * struct tee_shm_pool_ops - shared memory pool operations - * @alloc: called when allocating shared memory - * @free: called when freeing shared memory - * @destroy_pool: called when destroying the pool - */ -struct tee_shm_pool_ops { - int (*alloc)(struct tee_shm_pool *pool, struct tee_shm *shm, - size_t size, size_t align); - void (*free)(struct tee_shm_pool *pool, struct tee_shm *shm); - void (*destroy_pool)(struct tee_shm_pool *pool); +struct tee_param_value { + u64 a; + u64 b; + u64 c; }; -/* - * tee_shm_pool_alloc_res_mem() - Create a shm manager for reserved memory - * @vaddr: Virtual address of start of pool - * @paddr: Physical address of start of pool - * @size: Size in bytes of the pool - * - * @returns pointer to a 'struct tee_shm_pool' or an ERR_PTR on failure. - */ -struct tee_shm_pool *tee_shm_pool_alloc_res_mem(unsigned long vaddr, - phys_addr_t paddr, size_t size, - int min_alloc_order); +struct tee_param { + u64 attr; + union { + struct tee_param_memref memref; + struct tee_param_value value; + } u; +}; /** - * tee_shm_pool_free() - Free a shared memory pool - * @pool: The shared memory pool to free - * - * The must be no remaining shared memory allocated from this pool when - * this function is called. + * tee_shm_alloc_kernel_buf() - Allocate kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory allocation + * @size: Shared memory allocation size + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -static inline void tee_shm_pool_free(struct tee_shm_pool *pool) -{ - pool->ops->destroy_pool(pool); -} +struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); /** - * tee_get_drvdata() - Return driver_data pointer - * @returns the driver_data pointer supplied to tee_register(). + * tee_shm_register_kernel_buf() - Register kernel shared memory for a + * particular TEE client driver + * @ctx: The TEE context for shared memory registration + * @addr: Kernel buffer address + * @length: Kernel buffer length + * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure */ -void *tee_get_drvdata(struct tee_device *teedev); - -struct tee_shm *tee_shm_alloc_priv_buf(struct tee_context *ctx, size_t size); -struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size); - struct tee_shm *tee_shm_register_kernel_buf(struct tee_context *ctx, void *addr, size_t length); /** - * tee_shm_is_dynamic() - Check if shared memory object is of the dynamic kind - * @shm: Shared memory handle - * @returns true if object is dynamic shared memory - */ -static inline bool tee_shm_is_dynamic(struct tee_shm *shm) -{ - return shm && (shm->flags & TEE_SHM_DYNAMIC); -} - -/** * tee_shm_free() - Free shared memory * @shm: Handle to shared memory to free */ void tee_shm_free(struct tee_shm *shm); /** - * tee_shm_put() - Decrease reference count on a shared memory handle - * @shm: Shared memory handle - */ -void tee_shm_put(struct tee_shm *shm); - -/** * tee_shm_get_va() - Get virtual address of a shared memory plus an offset * @shm: Shared memory handle * @offs: Offset from start of this shared memory @@ -353,25 +175,6 @@ static inline size_t tee_shm_get_page_offset(struct tee_shm *shm) } /** - * tee_shm_get_id() - Get id of a shared memory object - * @shm: Shared memory handle - * @returns id - */ -static inline int tee_shm_get_id(struct tee_shm *shm) -{ - return shm->id; -} - -/** - * tee_shm_get_from_id() - Find shared memory object and increase reference - * count - * @ctx: Context owning the shared memory - * @id: Id of shared memory object - * @returns a pointer to 'struct tee_shm' on success or an ERR_PTR on failure - */ -struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id); - -/** * tee_client_open_context() - Open a TEE context * @start: if not NULL, continue search after this context * @match: function to check TEE device @@ -470,18 +273,6 @@ int tee_client_invoke_func(struct tee_context *ctx, int tee_client_cancel_req(struct tee_context *ctx, struct tee_ioctl_cancel_arg *arg); -static inline bool tee_param_is_memref(struct tee_param *param) -{ - switch (param->attr & TEE_IOCTL_PARAM_ATTR_TYPE_MASK) { - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT: - case TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INOUT: - return true; - default: - return false; - } -} - extern const struct bus_type tee_bus_type; /** @@ -509,18 +300,4 @@ struct tee_client_driver { #define to_tee_client_driver(d) \ container_of(d, struct tee_client_driver, driver) -/** - * teedev_open() - Open a struct tee_device - * @teedev: Device to open - * - * @return a pointer to struct tee_context on success or an ERR_PTR on failure. - */ -struct tee_context *teedev_open(struct tee_device *teedev); - -/** - * teedev_close_context() - closes a struct tee_context - * @ctx: The struct tee_context to close - */ -void teedev_close_context(struct tee_context *ctx); - #endif /*__TEE_DRV_H*/ diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h index 62973f7d4610..d306d9dd2207 100644 --- a/include/linux/timerqueue.h +++ b/include/linux/timerqueue.h @@ -37,11 +37,6 @@ static inline bool timerqueue_node_queued(struct timerqueue_node *node) return !RB_EMPTY_NODE(&node->node); } -static inline bool timerqueue_node_expires(struct timerqueue_node *node) -{ - return node->expires; -} - static inline void timerqueue_init_head(struct timerqueue_head *head) { head->rb_root = RB_ROOT_CACHED; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 4ee9d13749ad..c17e4efbb2e5 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -23,6 +23,7 @@ #include <linux/fs.h> #include <linux/highmem.h> #include <crypto/hash_info.h> +#include <crypto/aes.h> #define TPM_DIGEST_SIZE 20 /* Max TPM v1.2 PCR size */ #define TPM_MAX_DIGEST_SIZE SHA512_DIGEST_SIZE @@ -30,17 +31,28 @@ struct tpm_chip; struct trusted_key_payload; struct trusted_key_options; +/* opaque structure, holds auth session parameters like the session key */ +struct tpm2_auth; + +enum tpm2_session_types { + TPM2_SE_HMAC = 0x00, + TPM2_SE_POLICY = 0x01, + TPM2_SE_TRIAL = 0x02, +}; /* if you add a new hash to this, increment TPM_MAX_HASHES below */ enum tpm_algorithms { TPM_ALG_ERROR = 0x0000, TPM_ALG_SHA1 = 0x0004, + TPM_ALG_AES = 0x0006, TPM_ALG_KEYEDHASH = 0x0008, TPM_ALG_SHA256 = 0x000B, TPM_ALG_SHA384 = 0x000C, TPM_ALG_SHA512 = 0x000D, TPM_ALG_NULL = 0x0010, TPM_ALG_SM3_256 = 0x0012, + TPM_ALG_ECC = 0x0023, + TPM_ALG_CFB = 0x0043, }; /* @@ -49,6 +61,11 @@ enum tpm_algorithms { */ #define TPM_MAX_HASHES 5 +enum tpm2_curves { + TPM2_ECC_NONE = 0x0000, + TPM2_ECC_NIST_P256 = 0x0003, +}; + struct tpm_digest { u16 alg_id; u8 digest[TPM_MAX_DIGEST_SIZE]; @@ -116,6 +133,20 @@ struct tpm_chip_seqops { const struct seq_operations *seqops; }; +/* fixed define for the curve we use which is NIST_P256 */ +#define EC_PT_SZ 32 + +/* + * fixed define for the size of a name. This is actually HASHALG size + * plus 2, so 32 for SHA256 + */ +#define TPM2_NAME_SIZE 34 + +/* + * The maximum size for an object context + */ +#define TPM2_MAX_CONTEXT_SIZE 4096 + struct tpm_chip { struct device dev; struct device devs; @@ -170,6 +201,18 @@ struct tpm_chip { /* active locality */ int locality; + +#ifdef CONFIG_TCG_TPM2_HMAC + /* details for communication security via sessions */ + + /* saved context for NULL seed */ + u8 null_key_context[TPM2_MAX_CONTEXT_SIZE]; + /* name of NULL seed */ + u8 null_key_name[TPM2_NAME_SIZE]; + u8 null_ec_key_x[EC_PT_SZ]; + u8 null_ec_key_y[EC_PT_SZ]; + struct tpm2_auth *auth; +#endif }; #define TPM_HEADER_SIZE 10 @@ -194,6 +237,7 @@ enum tpm2_timeouts { enum tpm2_structures { TPM2_ST_NO_SESSIONS = 0x8001, TPM2_ST_SESSIONS = 0x8002, + TPM2_ST_CREATION = 0x8021, }; /* Indicates from what layer of the software stack the error comes from */ @@ -204,6 +248,7 @@ enum tpm2_return_codes { TPM2_RC_SUCCESS = 0x0000, TPM2_RC_HASH = 0x0083, /* RC_FMT1 */ TPM2_RC_HANDLE = 0x008B, + TPM2_RC_INTEGRITY = 0x009F, TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, @@ -231,6 +276,8 @@ enum tpm2_command_codes { TPM2_CC_CONTEXT_LOAD = 0x0161, TPM2_CC_CONTEXT_SAVE = 0x0162, TPM2_CC_FLUSH_CONTEXT = 0x0165, + TPM2_CC_READ_PUBLIC = 0x0173, + TPM2_CC_START_AUTH_SESS = 0x0176, TPM2_CC_VERIFY_SIGNATURE = 0x0177, TPM2_CC_GET_CAPABILITY = 0x017A, TPM2_CC_GET_RANDOM = 0x017B, @@ -243,9 +290,25 @@ enum tpm2_command_codes { }; enum tpm2_permanent_handles { + TPM2_RH_NULL = 0x40000007, TPM2_RS_PW = 0x40000009, }; +/* Most Significant Octet for key types */ +enum tpm2_mso_type { + TPM2_MSO_NVRAM = 0x01, + TPM2_MSO_SESSION = 0x02, + TPM2_MSO_POLICY = 0x03, + TPM2_MSO_PERMANENT = 0x40, + TPM2_MSO_VOLATILE = 0x80, + TPM2_MSO_PERSISTENT = 0x81, +}; + +static inline enum tpm2_mso_type tpm2_handle_mso(u32 handle) +{ + return handle >> 24; +} + enum tpm2_capabilities { TPM2_CAP_HANDLES = 1, TPM2_CAP_COMMANDS = 2, @@ -284,6 +347,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), TPM_CHIP_FLAG_SUSPENDED = BIT(8), TPM_CHIP_FLAG_HWRNG_DISABLED = BIT(9), + TPM_CHIP_FLAG_DISABLE = BIT(10), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -297,28 +361,61 @@ struct tpm_header { }; } __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 { + /* the capacity exceeded: */ TPM_BUF_OVERFLOW = BIT(0), + /* TPM2B format: */ + TPM_BUF_TPM2B = BIT(1), + /* read out of boundary: */ + TPM_BUF_BOUNDARY_ERROR = BIT(2), }; +/* + * A string buffer type for constructing TPM commands. + */ struct tpm_buf { - unsigned int flags; + u32 flags; + u32 length; u8 *data; + u8 handles; }; enum tpm2_object_attributes { TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_ST_CLEAR = BIT(2), TPM2_OA_FIXED_PARENT = BIT(4), + TPM2_OA_SENSITIVE_DATA_ORIGIN = BIT(5), TPM2_OA_USER_WITH_AUTH = BIT(6), + TPM2_OA_ADMIN_WITH_POLICY = BIT(7), + TPM2_OA_NO_DA = BIT(10), + TPM2_OA_ENCRYPTED_DUPLICATION = BIT(11), + TPM2_OA_RESTRICTED = BIT(16), + TPM2_OA_DECRYPT = BIT(17), + TPM2_OA_SIGN = BIT(18), }; +/* + * definitions for the canonical template. These are mandated + * by the TCG key template documents + */ + +#define AES_KEY_BYTES AES_KEYSIZE_128 +#define AES_KEY_BITS (AES_KEY_BYTES*8) +#define TPM2_OA_TMPL (TPM2_OA_NO_DA | \ + TPM2_OA_FIXED_TPM | \ + TPM2_OA_FIXED_PARENT | \ + TPM2_OA_SENSITIVE_DATA_ORIGIN | \ + TPM2_OA_USER_WITH_AUTH | \ + TPM2_OA_DECRYPT | \ + TPM2_OA_RESTRICTED) + enum tpm2_session_attributes { TPM2_SA_CONTINUE_SESSION = BIT(0), + TPM2_SA_AUDIT_EXCLUSIVE = BIT(1), + TPM2_SA_AUDIT_RESET = BIT(3), + TPM2_SA_DECRYPT = BIT(5), + TPM2_SA_ENCRYPT = BIT(6), + TPM2_SA_AUDIT = BIT(7), }; struct tpm2_hash { @@ -326,84 +423,21 @@ struct tpm2_hash { 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); -} +int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal); +void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal); +int tpm_buf_init_sized(struct tpm_buf *buf); +void tpm_buf_reset_sized(struct tpm_buf *buf); +void tpm_buf_destroy(struct tpm_buf *buf); +u32 tpm_buf_length(struct tpm_buf *buf); +void tpm_buf_append(struct tpm_buf *buf, const u8 *new_data, u16 new_length); +void tpm_buf_append_u8(struct tpm_buf *buf, const u8 value); +void tpm_buf_append_u16(struct tpm_buf *buf, const u16 value); +void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value); +u8 tpm_buf_read_u8(struct tpm_buf *buf, off_t *offset); +u16 tpm_buf_read_u16(struct tpm_buf *buf, off_t *offset); +u32 tpm_buf_read_u32(struct tpm_buf *buf, off_t *offset); + +u8 *tpm_buf_parameters(struct tpm_buf *buf); /* * Check if TPM device is in the firmware upgrade mode. @@ -415,7 +449,7 @@ static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) static inline u32 tpm2_rc_value(u32 rc) { - return (rc & BIT(7)) ? rc & 0xff : rc; + return (rc & BIT(7)) ? rc & 0xbf : rc; } #if defined(CONFIG_TCG_TPM) || defined(CONFIG_TCG_TPM_MODULE) @@ -429,10 +463,19 @@ extern int tpm_pcr_read(struct tpm_chip *chip, u32 pcr_idx, struct tpm_digest *digest); 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 struct tpm_chip *tpm_default_chip(void); void tpm2_flush_context(struct tpm_chip *chip, u32 handle); + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ + /* simple authorization for empty auth */ + tpm_buf_append_u32(buf, 9); /* total length of auth */ + tpm_buf_append_u32(buf, handle); + tpm_buf_append_u16(buf, 0); /* nonce len */ + tpm_buf_append_u8(buf, 0); /* attributes */ + tpm_buf_append_u16(buf, 0); /* hmac len */ +} #else static inline int tpm_is_tpm2(struct tpm_chip *chip) { @@ -450,10 +493,6 @@ static inline int tpm_pcr_extend(struct tpm_chip *chip, u32 pcr_idx, return -ENODEV; } -static inline int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen) -{ - return -ENODEV; -} static inline int tpm_get_random(struct tpm_chip *chip, u8 *data, size_t max) { return -ENODEV; @@ -463,5 +502,102 @@ static inline struct tpm_chip *tpm_default_chip(void) { return NULL; } + +static inline void tpm_buf_append_empty_auth(struct tpm_buf *buf, u32 handle) +{ +} #endif +#ifdef CONFIG_TCG_TPM2_HMAC + +int tpm2_start_auth_session(struct tpm_chip *chip); +void tpm_buf_append_name(struct tpm_chip *chip, struct tpm_buf *buf, + u32 handle, u8 *name); +void tpm_buf_append_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen); +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + tpm_buf_append_hmac_session(chip, buf, attributes, passphrase, + passphraselen); +} +void tpm_buf_fill_hmac_session(struct tpm_chip *chip, struct tpm_buf *buf); +int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf, + int rc); +void tpm2_end_auth_session(struct tpm_chip *chip); +#else +#include <asm/unaligned.h> + +static inline int tpm2_start_auth_session(struct tpm_chip *chip) +{ + return 0; +} +static inline void tpm2_end_auth_session(struct tpm_chip *chip) +{ +} +static inline void tpm_buf_append_name(struct tpm_chip *chip, + struct tpm_buf *buf, + u32 handle, u8 *name) +{ + tpm_buf_append_u32(buf, handle); + /* count the number of handles in the upper bits of flags */ + buf->handles++; +} +static inline void tpm_buf_append_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, u8 *passphrase, + int passphraselen) +{ + /* offset tells us where the sessions area begins */ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + u32 len = 9 + passphraselen; + + if (tpm_buf_length(buf) != offset) { + /* not the first session so update the existing length */ + len += get_unaligned_be32(&buf->data[offset]); + put_unaligned_be32(len, &buf->data[offset]); + } else { + tpm_buf_append_u32(buf, len); + } + /* auth handle */ + tpm_buf_append_u32(buf, TPM2_RS_PW); + /* nonce */ + tpm_buf_append_u16(buf, 0); + /* attributes */ + tpm_buf_append_u8(buf, 0); + /* passphrase */ + tpm_buf_append_u16(buf, passphraselen); + tpm_buf_append(buf, passphrase, passphraselen); +} +static inline void tpm_buf_append_hmac_session_opt(struct tpm_chip *chip, + struct tpm_buf *buf, + u8 attributes, + u8 *passphrase, + int passphraselen) +{ + int offset = buf->handles * 4 + TPM_HEADER_SIZE; + struct tpm_header *head = (struct tpm_header *) buf->data; + + /* + * if the only sessions are optional, the command tag + * must change to TPM2_ST_NO_SESSIONS + */ + if (tpm_buf_length(buf) == offset) + head->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS); +} +static inline void tpm_buf_fill_hmac_session(struct tpm_chip *chip, + struct tpm_buf *buf) +{ +} +static inline int tpm_buf_check_hmac_response(struct tpm_chip *chip, + struct tpm_buf *buf, + int rc) +{ + return rc; +} +#endif /* CONFIG_TCG_TPM2_HMAC */ + #endif diff --git a/include/linux/tracefs.h b/include/linux/tracefs.h index 7a5fe17b6bf9..d03f74658716 100644 --- a/include/linux/tracefs.h +++ b/include/linux/tracefs.h @@ -62,6 +62,8 @@ struct eventfs_file; typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, const struct file_operations **fops); +typedef void (*eventfs_release)(const char *name, void *data); + /** * struct eventfs_entry - dynamically created eventfs file call back handler * @name: Then name of the dynamic file in an eventfs directory @@ -72,6 +74,7 @@ typedef int (*eventfs_callback)(const char *name, umode_t *mode, void **data, struct eventfs_entry { const char *name; eventfs_callback callback; + eventfs_release release; }; struct eventfs_inode; diff --git a/include/linux/tty.h b/include/linux/tty.h index 2b2e6f0a54d6..2372f9357240 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -145,15 +145,12 @@ struct tty_operations; * @count: count of open processes, reaching zero cancels all the work for * this tty and drops a @kref too (but does not free this tty) * @winsize: size of the terminal "window" (cf. @winsize_mutex) - * @flow: flow settings grouped together, see also @flow.unused + * @flow: flow settings grouped together * @flow.lock: lock for @flow members * @flow.stopped: tty stopped/started by stop_tty()/start_tty() * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has * precedence over @flow.stopped) - * @flow.unused: alignment for Alpha, so that no members other than @flow.* are - * modified by the same 64b word store. The @flow's __aligned is - * there for the very same reason. - * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl: control settings grouped together * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both @@ -161,7 +158,6 @@ struct tty_operations; * them. * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled - * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS * handling * @receive_room: bytes permitted to feed to @ldisc without any being lost @@ -216,8 +212,7 @@ struct tty_struct { spinlock_t lock; bool stopped; bool tco_stopped; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) flow; + } flow; struct { struct pid *pgrp; @@ -225,8 +220,7 @@ struct tty_struct { spinlock_t lock; unsigned char pktstatus; bool packet; - unsigned long unused[0]; - } __aligned(sizeof(unsigned long)) ctrl; + } ctrl; bool hw_stopped; bool closing; diff --git a/include/linux/uio.h b/include/linux/uio.h index 00cebe2b70de..7020adedfa08 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -206,6 +206,16 @@ size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) } static __always_inline __must_check +bool copy_to_iter_full(const void *addr, size_t bytes, struct iov_iter *i) +{ + size_t copied = copy_to_iter(addr, bytes, i); + if (likely(copied == bytes)) + return true; + iov_iter_revert(i, copied); + return false; +} + +static __always_inline __must_check bool copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { size_t copied = copy_from_iter(addr, bytes, i); diff --git a/include/linux/vtime.h b/include/linux/vtime.h index 3684487d01e1..29dd5b91dd7d 100644 --- a/include/linux/vtime.h +++ b/include/linux/vtime.h @@ -5,10 +5,6 @@ #include <linux/context_tracking_state.h> #include <linux/sched.h> -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE -#include <asm/vtime.h> -#endif - /* * Common vtime APIs */ @@ -18,7 +14,6 @@ extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void arch_vtime_task_switch(struct task_struct *tsk); extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); |