diff options
Diffstat (limited to 'include/linux')
134 files changed, 2886 insertions, 885 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fbf0052c1641..b338613fb536 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -711,6 +711,8 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_address(acpi_handle handle, u32 *addr); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -966,6 +968,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res) return NULL; } +static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + return -ENODEV; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC @@ -1005,6 +1012,7 @@ int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); +bool acpi_storage_d3(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1012,6 +1020,10 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } +static inline bool acpi_storage_d3(struct device *dev) +{ + return false; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) @@ -1097,6 +1109,8 @@ void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const c #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); +bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, @@ -1104,6 +1118,11 @@ static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, { return false; } +static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, + struct acpi_resource_gpio **agpio) +{ + return false; +} static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index) { diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h new file mode 100644 index 000000000000..0a24ab7cb66f --- /dev/null +++ b/include/linux/acpi_mdio.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ACPI helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_ACPI_MDIO_H +#define __LINUX_ACPI_MDIO_H + +#include <linux/phy.h> + +#if IS_ENABLED(CONFIG_ACPI_MDIO) +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +#else /* CONFIG_ACPI_MDIO */ +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} +#endif + +#endif /* __LINUX_ACPI_MDIO_H */ diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h index a889f28afb42..c637e0997f6d 100644 --- a/include/linux/adreno-smmu-priv.h +++ b/include/linux/adreno-smmu-priv.h @@ -9,6 +9,32 @@ #include <linux/io-pgtable.h> /** + * struct adreno_smmu_fault_info - container for key fault information + * + * @far: The faulting IOVA from ARM_SMMU_CB_FAR + * @ttbr0: The current TTBR0 pagetable from ARM_SMMU_CB_TTBR0 + * @contextidr: The value of ARM_SMMU_CB_CONTEXTIDR + * @fsr: The fault status from ARM_SMMU_CB_FSR + * @fsynr0: The value of FSYNR0 from ARM_SMMU_CB_FSYNR0 + * @fsynr1: The value of FSYNR1 from ARM_SMMU_CB_FSYNR0 + * @cbfrsynra: The value of CBFRSYNRA from ARM_SMMU_GR1_CBFRSYNRA(idx) + * + * This struct passes back key page fault information to the GPU driver + * through the get_fault_info function pointer. + * The GPU driver can use this information to print informative + * log messages and provide deeper GPU specific insight into the fault. + */ +struct adreno_smmu_fault_info { + u64 far; + u64 ttbr0; + u32 contextidr; + u32 fsr; + u32 fsynr0; + u32 fsynr1; + u32 cbfrsynra; +}; + +/** * struct adreno_smmu_priv - private interface between adreno-smmu and GPU * * @cookie: An opque token provided by adreno-smmu and passed @@ -17,6 +43,13 @@ * @set_ttbr0_cfg: Set the TTBR0 config for the GPUs context bank. A * NULL config disables TTBR0 translation, otherwise * TTBR0 translation is enabled with the specified cfg + * @get_fault_info: Called by the GPU fault handler to get information about + * the fault + * @set_stall: Configure whether stall on fault (CFCFG) is enabled. Call + * before set_ttbr0_cfg(). If stalling on fault is enabled, + * the GPU driver must call resume_translation() + * @resume_translation: Resume translation after a fault + * * * The GPU driver (drm/msm) and adreno-smmu work together for controlling * the GPU's SMMU instance. This is by necessity, as the GPU is directly @@ -31,6 +64,9 @@ struct adreno_smmu_priv { const void *cookie; const struct io_pgtable_cfg *(*get_ttbr1_cfg)(const void *cookie); int (*set_ttbr0_cfg)(const void *cookie, const struct io_pgtable_cfg *cfg); + void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info); + void (*set_stall)(const void *cookie, bool enabled); + void (*resume_translation)(const void *cookie, bool terminate); }; -#endif /* __ADRENO_SMMU_PRIV_H */
\ No newline at end of file +#endif /* __ADRENO_SMMU_PRIV_H */ diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h index 4cc40201273e..83ad775ad0aa 100644 --- a/include/linux/ascii85.h +++ b/include/linux/ascii85.h @@ -8,7 +8,8 @@ #ifndef _ASCII85_H_ #define _ASCII85_H_ -#include <linux/kernel.h> +#include <linux/math.h> +#include <linux/types.h> #define ASCII85_BUFSZ 6 diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 8612f8fc86c1..db0e099c2399 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select); * PF removes the filters and returns status. */ +/* VIRTCHNL_ETHER_ADDR_LEGACY + * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad + * bytes. Moving forward all VF drivers should not set type to + * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy + * behavior. The control plane function (i.e. PF) can use a best effort method + * of tracking the primary/device unicast in this case, but there is no + * guarantee and functionality depends on the implementation of the PF. + */ + +/* VIRTCHNL_ETHER_ADDR_PRIMARY + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the + * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and + * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane + * function (i.e. PF) to accurately track and use this MAC address for + * displaying on the host and for VM/function reset. + */ + +/* VIRTCHNL_ETHER_ADDR_EXTRA + * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra + * unicast and/or multicast filters that are being added/deleted via + * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively. + */ struct virtchnl_ether_addr { u8 addr[ETH_ALEN]; - u8 pad[2]; + u8 type; +#define VIRTCHNL_ETHER_ADDR_LEGACY 0 +#define VIRTCHNL_ETHER_ADDR_PRIMARY 1 +#define VIRTCHNL_ETHER_ADDR_EXTRA 2 +#define VIRTCHNL_ETHER_ADDR_TYPE_MASK 3 /* first two bits of type are valid */ + u8 pad; }; VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr); diff --git a/include/linux/bio.h b/include/linux/bio.h index a0b4cfdf62a4..2203b686e1f0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -44,9 +44,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) -#define bio_multiple_segments(bio) \ - ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) - #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) @@ -271,7 +268,7 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { - *bv = bio_iovec(bio); + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) @@ -279,10 +276,9 @@ static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) struct bvec_iter iter = bio->bi_iter; int idx; - if (unlikely(!bio_multiple_segments(bio))) { - *bv = bio_iovec(bio); - return; - } + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); @@ -822,4 +818,6 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); + #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 359486940fa0..fd2de2b422ed 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -426,19 +426,29 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define blk_mq_alloc_disk(set, queuedata) \ +({ \ + static struct lock_class_key __key; \ + struct gendisk *__disk = __blk_mq_alloc_disk(set, queuedata); \ + \ + if (!IS_ERR(__disk)) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, + void *queuedata); struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *); struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, void *queuedata); -struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, - struct request_queue *q, - bool elevator_init); -struct request_queue *blk_mq_init_sq_queue(struct blk_mq_tag_set *set, - const struct blk_mq_ops *ops, - unsigned int queue_depth, - unsigned int set_flags); +int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, + struct request_queue *q); void blk_mq_unregister_dev(struct device *, struct request_queue *); int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set); +int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, + const struct blk_mq_ops *ops, unsigned int queue_depth, + unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index db026b6ec15a..b05f2fd495fc 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -29,7 +29,6 @@ struct block_device { int bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ void * bd_claiming; struct device bd_device; void * bd_holder; @@ -40,9 +39,6 @@ struct block_device { #endif struct kobject *bd_holder_dir; u8 bd_partno; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; @@ -304,6 +300,7 @@ enum { BIO_CGROUP_ACCT, /* has been accounted to a cgroup */ BIO_TRACKED, /* set if bio goes through the rq_qos path */ BIO_REMAPPED, + BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ BIO_FLAG_LAST }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f69c75bd6d27..103acc5228e7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/pm.h> +#include <linux/sbitmap.h> struct module; struct scsi_ioctl_command; @@ -493,6 +494,9 @@ struct request_queue { atomic_t nr_active_requests_shared_sbitmap; + struct sbitmap_queue sched_bitmap_tags; + struct sbitmap_queue sched_breserved_tags; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); @@ -1008,6 +1012,18 @@ static inline unsigned int blk_rq_stats_sectors(const struct request *rq) /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond); +static inline unsigned int bio_zone_no(struct bio *bio) +{ + return blk_queue_zone_no(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + +static inline unsigned int bio_zone_is_seq(struct bio *bio) +{ + return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), + bio->bi_iter.bi_sector); +} + static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); @@ -1209,7 +1225,6 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h new file mode 100644 index 000000000000..2bc8b1f69c93 --- /dev/null +++ b/include/linux/bootmem_info.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_BOOTMEM_INFO_H +#define __LINUX_BOOTMEM_INFO_H + +#include <linux/mm.h> + +/* + * Types for free bootmem stored in page->lru.next. These have to be in + * some random range in unsigned long space for debugging purposes. + */ +enum { + MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, + SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, + MIX_SECTION_INFO, + NODE_INFO, + MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, +}; + +#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE +void __init register_page_bootmem_info_node(struct pglist_data *pgdat); + +void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type); +void put_page_bootmem(struct page *page); + +/* + * Any memory allocated via the memblock allocator and not via the + * buddy will be marked reserved already in the memmap. For those + * pages, we can call this function to free it to buddy allocator. + */ +static inline void free_bootmem_page(struct page *page) +{ + unsigned long magic = (unsigned long)page->freelist; + + /* + * The reserve_bootmem_region sets the reserved flag on bootmem + * pages. + */ + VM_BUG_ON_PAGE(page_ref_count(page) != 2, page); + + if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) + put_page_bootmem(page); + else + VM_BUG_ON_PAGE(1, page); +} +#else +static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) +{ +} + +static inline void put_page_bootmem(struct page *page) +{ +} + +static inline void get_page_bootmem(unsigned long info, struct page *page, + unsigned long type) +{ +} + +static inline void free_bootmem_page(struct page *page) +{ + free_reserved_page(page); +} +#endif + +#endif /* __LINUX_BOOTMEM_INFO_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 02b02cb29ce2..f309fc1509f2 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,7 @@ #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> +#include <linux/bpfptr.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -69,6 +70,8 @@ struct bpf_map_ops { void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); + int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, + void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); @@ -1428,7 +1431,7 @@ struct bpf_iter__bpf_map_elem { int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); -int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); @@ -1459,7 +1462,7 @@ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); -int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size, +int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and @@ -1479,8 +1482,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) } /* verify correctness of eBPF program */ -int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, - union bpf_attr __user *uattr); +int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); @@ -1499,8 +1501,13 @@ int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, struct net_device *dev_rx); +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress); bool dev_map_can_have_prog(struct bpf_map *map); void __cpu_map_flush(void); @@ -1668,6 +1675,13 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, return 0; } +static inline +int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + return 0; +} + struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, @@ -1677,6 +1691,14 @@ static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, return 0; } +static inline +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + struct bpf_prog *xdp_prog, struct bpf_map *map, + bool exclude_ingress) +{ + return 0; +} + static inline void __cpu_map_flush(void) { } @@ -1826,6 +1848,9 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) @@ -1851,6 +1876,13 @@ static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) static inline void bpf_map_offload_map_free(struct bpf_map *map) { } + +static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + return -ENOTSUPP; +} #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) @@ -1964,6 +1996,7 @@ extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; +extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); @@ -2015,6 +2048,7 @@ struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; + struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index b902c580c48d..24496bc28e7b 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -58,7 +58,7 @@ struct bpf_local_storage_data { * from the object's bpf_local_storage. * * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. + * the number of cachelines accessed during the cache hit case. */ struct bpf_local_storage_map __rcu *smap; u8 data[] __aligned(8); @@ -71,7 +71,7 @@ struct bpf_local_storage_elem { struct bpf_local_storage __rcu *local_storage; struct rcu_head rcu; /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize + /* The data is stored in another cacheline to minimize * the number of cachelines access during a cache hit. */ struct bpf_local_storage_data sdata ____cacheline_aligned; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index f883f01a5061..a9db1eae6796 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -77,6 +77,8 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_LSM, lsm, void *, void *) #endif /* CONFIG_BPF_LSM */ #endif +BPF_PROG_TYPE(BPF_PROG_TYPE_SYSCALL, bpf_syscall, + void *, void *) BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 06841517ab1e..e774ecc1cd1f 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -215,6 +215,13 @@ struct bpf_idx_pair { u32 idx; }; +struct bpf_id_pair { + u32 old; + u32 cur; +}; + +/* Maximum number of register states that can exist at once */ +#define BPF_ID_MAP_SIZE (MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) #define MAX_CALL_FRAMES 8 struct bpf_verifier_state { /* call stack tracking */ @@ -418,6 +425,7 @@ struct bpf_verifier_env { const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE]; struct { int *insn_state; int *insn_stack; @@ -442,6 +450,7 @@ struct bpf_verifier_env { u32 peak_states; /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; + bpfptr_t fd_array; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h new file mode 100644 index 000000000000..5cdeab497cb3 --- /dev/null +++ b/include/linux/bpfptr.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* A pointer that can point to either kernel or userspace memory. */ +#ifndef _LINUX_BPFPTR_H +#define _LINUX_BPFPTR_H + +#include <linux/sockptr.h> + +typedef sockptr_t bpfptr_t; + +static inline bool bpfptr_is_kernel(bpfptr_t bpfptr) +{ + return bpfptr.is_kernel; +} + +static inline bpfptr_t KERNEL_BPFPTR(void *p) +{ + return (bpfptr_t) { .kernel = p, .is_kernel = true }; +} + +static inline bpfptr_t USER_BPFPTR(void __user *p) +{ + return (bpfptr_t) { .user = p }; +} + +static inline bpfptr_t make_bpfptr(u64 addr, bool is_kernel) +{ + if (is_kernel) + return KERNEL_BPFPTR((void*) (uintptr_t) addr); + else + return USER_BPFPTR(u64_to_user_ptr(addr)); +} + +static inline bool bpfptr_is_null(bpfptr_t bpfptr) +{ + if (bpfptr_is_kernel(bpfptr)) + return !bpfptr.kernel; + return !bpfptr.user; +} + +static inline void bpfptr_add(bpfptr_t *bpfptr, size_t val) +{ + if (bpfptr_is_kernel(*bpfptr)) + bpfptr->kernel += val; + else + bpfptr->user += val; +} + +static inline int copy_from_bpfptr_offset(void *dst, bpfptr_t src, + size_t offset, size_t size) +{ + return copy_from_sockptr_offset(dst, (sockptr_t) src, offset, size); +} + +static inline int copy_from_bpfptr(void *dst, bpfptr_t src, size_t size) +{ + return copy_from_bpfptr_offset(dst, src, 0, size); +} + +static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset, + const void *src, size_t size) +{ + return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size); +} + +static inline void *memdup_bpfptr(bpfptr_t src, size_t len) +{ + return memdup_sockptr((sockptr_t) src, len); +} + +static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count) +{ + return strncpy_from_sockptr(dst, (sockptr_t) src, count); +} + +#endif /* _LINUX_BPFPTR_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 3bac66e0183a..94a0c976c90f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -21,7 +21,7 @@ extern const struct file_operations btf_fops; void btf_get(struct btf *btf); void btf_put(struct btf *btf); -int btf_new_fd(const union bpf_attr *attr); +int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr); struct btf *btf_get_by_fd(int fd); int btf_get_info_by_fd(const struct btf *btf, const union bpf_attr *attr, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index fb8f6d2cd104..e1c705fdfa7c 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -71,6 +71,9 @@ enum { /* Cgroup is frozen. */ CGRP_FROZEN, + + /* Control group has to be killed. */ + CGRP_KILL, }; /* cgroup_root->flags */ @@ -110,6 +113,7 @@ enum { CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ CFTYPE_WORLD_WRITABLE = (1 << 4), /* (DON'T USE FOR NEW FILES) S_IWUGO */ CFTYPE_DEBUG = (1 << 5), /* create when cgroup_debug */ + CFTYPE_PRESSURE = (1 << 6), /* only if pressure feature is enabled */ /* internal flags, do not use outside cgroup core proper */ __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 6bc9c76680b2..2cc237e3e8b3 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -676,6 +676,8 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) return &cgrp->psi; } +bool cgroup_psi_enabled(void); + static inline void cgroup_init_kthreadd(void) { /* @@ -735,6 +737,11 @@ static inline struct psi_group *cgroup_psi(struct cgroup *cgrp) return NULL; } +static inline bool cgroup_psi_enabled(void) +{ + return false; +} + static inline bool task_under_cgroup_hierarchy(struct task_struct *task, struct cgroup *ancestor) { @@ -906,20 +913,6 @@ void cgroup_freeze(struct cgroup *cgrp, bool freeze); void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src, struct cgroup *dst); -static inline bool cgroup_task_freeze(struct task_struct *task) -{ - bool ret; - - if (task->flags & PF_KTHREAD) - return false; - - rcu_read_lock(); - ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags); - rcu_read_unlock(); - - return ret; -} - static inline bool cgroup_task_frozen(struct task_struct *task) { return task->frozen; @@ -929,10 +922,6 @@ static inline bool cgroup_task_frozen(struct task_struct *task) static inline void cgroup_enter_frozen(void) { } static inline void cgroup_leave_frozen(bool always_leave) { } -static inline bool cgroup_task_freeze(struct task_struct *task) -{ - return false; -} static inline bool cgroup_task_frozen(struct task_struct *task) { return false; diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index f7ff722a03dd..d128ad1570aa 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -123,20 +123,6 @@ static inline void tegra_cpu_clock_resume(void) } #endif -extern int tegra210_plle_hw_sequence_start(void); -extern bool tegra210_plle_hw_sequence_is_enabled(void); -extern void tegra210_xusb_pll_hw_control_enable(void); -extern void tegra210_xusb_pll_hw_sequence_start(void); -extern void tegra210_sata_pll_hw_control_enable(void); -extern void tegra210_sata_pll_hw_sequence_start(void); -extern void tegra210_set_sata_pll_seq_sw(bool state); -extern void tegra210_put_utmipll_in_iddq(void); -extern void tegra210_put_utmipll_out_iddq(void); -extern int tegra210_clk_handle_mbist_war(unsigned int id); -extern void tegra210_clk_emc_dll_enable(bool flag); -extern void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); -extern void tegra210_clk_emc_update_setting(u32 emc_src_value); - struct clk; struct tegra_emc; @@ -144,17 +130,10 @@ typedef long (tegra20_clk_emc_round_cb)(unsigned long rate, unsigned long min_rate, unsigned long max_rate, void *arg); - -void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, - void *cb_arg); -int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); - typedef int (tegra124_emc_prepare_timing_change_cb)(struct tegra_emc *emc, unsigned long rate); typedef void (tegra124_emc_complete_timing_change_cb)(struct tegra_emc *emc, unsigned long rate); -void tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, - tegra124_emc_complete_timing_change_cb *complete_cb); struct tegra210_clk_emc_config { unsigned long rate; @@ -176,8 +155,87 @@ struct tegra210_clk_emc_provider { const struct tegra210_clk_emc_config *config); }; +#if defined(CONFIG_ARCH_TEGRA_2x_SOC) || defined(CONFIG_ARCH_TEGRA_3x_SOC) +void tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg); +int tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same); +#else +static inline void +tegra20_clk_set_emc_round_callback(tegra20_clk_emc_round_cb *round_cb, + void *cb_arg) +{ +} + +static inline int +tegra20_clk_prepare_emc_mc_same_freq(struct clk *emc_clk, bool same) +{ + return 0; +} +#endif + +#ifdef CONFIG_TEGRA124_CLK_EMC +void tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, + tegra124_emc_complete_timing_change_cb *complete_cb); +#else +static inline void +tegra124_clk_set_emc_callbacks(tegra124_emc_prepare_timing_change_cb *prep_cb, + tegra124_emc_complete_timing_change_cb *complete_cb) +{ +} +#endif + +#ifdef CONFIG_ARCH_TEGRA_210_SOC +int tegra210_plle_hw_sequence_start(void); +bool tegra210_plle_hw_sequence_is_enabled(void); +void tegra210_xusb_pll_hw_control_enable(void); +void tegra210_xusb_pll_hw_sequence_start(void); +void tegra210_sata_pll_hw_control_enable(void); +void tegra210_sata_pll_hw_sequence_start(void); +void tegra210_set_sata_pll_seq_sw(bool state); +void tegra210_put_utmipll_in_iddq(void); +void tegra210_put_utmipll_out_iddq(void); +int tegra210_clk_handle_mbist_war(unsigned int id); +void tegra210_clk_emc_dll_enable(bool flag); +void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value); +void tegra210_clk_emc_update_setting(u32 emc_src_value); + int tegra210_clk_emc_attach(struct clk *clk, struct tegra210_clk_emc_provider *provider); void tegra210_clk_emc_detach(struct clk *clk); +#else +static inline int tegra210_plle_hw_sequence_start(void) +{ + return 0; +} + +static inline bool tegra210_plle_hw_sequence_is_enabled(void) +{ + return false; +} + +static inline int tegra210_clk_handle_mbist_war(unsigned int id) +{ + return 0; +} + +static inline int +tegra210_clk_emc_attach(struct clk *clk, + struct tegra210_clk_emc_provider *provider) +{ + return 0; +} + +static inline void tegra210_xusb_pll_hw_control_enable(void) {} +static inline void tegra210_xusb_pll_hw_sequence_start(void) {} +static inline void tegra210_sata_pll_hw_control_enable(void) {} +static inline void tegra210_sata_pll_hw_sequence_start(void) {} +static inline void tegra210_set_sata_pll_seq_sw(bool state) {} +static inline void tegra210_put_utmipll_in_iddq(void) {} +static inline void tegra210_put_utmipll_out_iddq(void) {} +static inline void tegra210_clk_emc_dll_enable(bool flag) {} +static inline void tegra210_clk_emc_dll_update_setting(u32 emc_dll_src_value) {} +static inline void tegra210_clk_emc_update_setting(u32 emc_src_value) {} +static inline void tegra210_clk_emc_detach(struct clk *clk) {} +#endif #endif /* __LINUX_CLK_TEGRA_H_ */ diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index c62f6fa6763d..3486f20a3753 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -63,6 +63,17 @@ struct clk_omap_reg { * @auto_recal_bit: bitshift of the driftguard enable bit in @control_reg * @recal_en_bit: bitshift of the PRM_IRQENABLE_* bit for recalibration IRQs * @recal_st_bit: bitshift of the PRM_IRQSTATUS_* bit for recalibration IRQs + * @ssc_deltam_reg: register containing the DPLL SSC frequency spreading + * @ssc_modfreq_reg: register containing the DPLL SSC modulation frequency + * @ssc_modfreq_mant_mask: mask of the mantissa component in @ssc_modfreq_reg + * @ssc_modfreq_exp_mask: mask of the exponent component in @ssc_modfreq_reg + * @ssc_enable_mask: mask of the DPLL SSC enable bit in @control_reg + * @ssc_downspread_mask: mask of the DPLL SSC low frequency only bit in + * @control_reg + * @ssc_modfreq: the DPLL SSC frequency modulation in kHz + * @ssc_deltam: the DPLL SSC frequency spreading in permille (10th of percent) + * @ssc_downspread: require the only low frequency spread of the DPLL in SSC + * mode * @flags: DPLL type/features (see below) * * Possible values for @flags: @@ -110,6 +121,17 @@ struct dpll_data { u8 auto_recal_bit; u8 recal_en_bit; u8 recal_st_bit; + struct clk_omap_reg ssc_deltam_reg; + struct clk_omap_reg ssc_modfreq_reg; + u32 ssc_deltam_int_mask; + u32 ssc_deltam_frac_mask; + u32 ssc_modfreq_mant_mask; + u32 ssc_modfreq_exp_mask; + u32 ssc_enable_mask; + u32 ssc_downspread_mask; + u32 ssc_modfreq; + u32 ssc_deltam; + bool ssc_downspread; u8 flags; }; diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h index fd06b2780a22..8a8423eb8e9a 100644 --- a/include/linux/clkdev.h +++ b/include/linux/clkdev.h @@ -30,11 +30,6 @@ struct clk_lookup { .clk = c, \ } -struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id, - const char *dev_fmt, ...) __printf(3, 4); -struct clk_lookup *clkdev_hw_alloc(struct clk_hw *hw, const char *con_id, - const char *dev_fmt, ...) __printf(3, 4); - void clkdev_add(struct clk_lookup *cl); void clkdev_drop(struct clk_lookup *cl); diff --git a/include/linux/compat.h b/include/linux/compat.h index 8855b1b702b2..c270124e4402 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -532,8 +532,6 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); /* diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index adbe76b203e2..49b0ac8b6fd3 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -13,6 +13,12 @@ /* all clang versions usable with the kernel support KASAN ABI version 5 */ #define KASAN_ABI_VERSION 5 +/* + * Note: Checking __has_feature(*_sanitizer) is only true if the feature is + * enabled. Therefore it is not required to additionally check defined(CONFIG_*) + * to avoid adding redundant attributes in other configurations. + */ + #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) /* Emulate GCC's __SANITIZE_ADDRESS__ flag */ #define __SANITIZE_ADDRESS__ @@ -46,6 +52,17 @@ #endif /* + * Support for __has_feature(coverage_sanitizer) was added in Clang 13 together + * with no_sanitize("coverage"). Prior versions of Clang support coverage + * instrumentation, but cannot be queried for support by the preprocessor. + */ +#if __has_feature(coverage_sanitizer) +#define __no_sanitize_coverage __attribute__((no_sanitize("coverage"))) +#else +#define __no_sanitize_coverage +#endif + +/* * Not all versions of clang implement the type-generic versions * of the builtin overflow checkers. Fortunately, clang implements * __has_builtin allowing us to avoid awkward version diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 5d97ef738a57..cb9217fc60af 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -122,6 +122,12 @@ #define __no_sanitize_undefined #endif +#if defined(CONFIG_KCOV) && __has_attribute(__no_sanitize_coverage__) +#define __no_sanitize_coverage __attribute__((no_sanitize_coverage)) +#else +#define __no_sanitize_coverage +#endif + #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 77047904cf70..b67261a1e3e9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -219,6 +219,16 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) +/* + * With CONFIG_CFI_CLANG, the compiler replaces function addresses in + * instrumented C code with jump table addresses. Architectures that + * support CFI can define this macro to return the actual function address + * when needed. + */ +#ifndef function_nocfi +#define function_nocfi(x) (x) +#endif + #endif /* __KERNEL__ */ /* diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 183ddd5fd072..2487be0e7199 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -27,15 +27,16 @@ */ #ifndef __has_attribute # define __has_attribute(x) __GCC4_has_attribute_##x -# define __GCC4_has_attribute___assume_aligned__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___assume_aligned__ 1 # define __GCC4_has_attribute___copy__ 0 # define __GCC4_has_attribute___designated_init__ 0 # define __GCC4_has_attribute___externally_visible__ 1 # define __GCC4_has_attribute___no_caller_saved_registers__ 0 # define __GCC4_has_attribute___noclone__ 1 +# define __GCC4_has_attribute___no_profile_instrument_function__ 0 # define __GCC4_has_attribute___nonstring__ 0 -# define __GCC4_has_attribute___no_sanitize_address__ (__GNUC_MINOR__ >= 8) -# define __GCC4_has_attribute___no_sanitize_undefined__ (__GNUC_MINOR__ >= 9) +# define __GCC4_has_attribute___no_sanitize_address__ 1 +# define __GCC4_has_attribute___no_sanitize_undefined__ 1 # define __GCC4_has_attribute___fallthrough__ 0 #endif @@ -239,6 +240,18 @@ #endif /* + * Optional: only supported since GCC >= 7.1, clang >= 13.0. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fprofile_005finstrument_005ffunction-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#no-profile-instrument-function + */ +#if __has_attribute(__no_profile_instrument_function__) +# define __no_profile __attribute__((__no_profile_instrument_function__)) +#else +# define __no_profile +#endif + +/* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-noreturn-function-attribute * clang: https://clang.llvm.org/docs/AttributeReference.html#noreturn * clang: https://clang.llvm.org/docs/AttributeReference.html#id1 diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index d29bda7f6ebd..e4ea86fc584d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -210,7 +210,7 @@ struct ftrace_likely_data { /* Section for code which can't be instrumented at all */ #define noinstr \ noinline notrace __attribute((__section__(".noinstr.text"))) \ - __no_kcsan __no_sanitize_address + __no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage #endif /* __KERNEL__ */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index ff700fb6ce1d..7457d49acf9a 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -361,6 +361,12 @@ struct dm_target { * Set if we need to limit the number of in-flight bios when swapping. */ bool limit_swap_bios:1; + + /* + * Set if this target implements a a zoned device and needs emulation of + * zone append operations using regular writes. + */ + bool emulate_zone_append:1; }; void *dm_per_bio_data(struct bio *bio, size_t data_size); @@ -478,7 +484,8 @@ struct dm_report_zones_args { /* must be filled by ->report_zones before calling dm_report_zones_cb */ sector_t start; }; -int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx, void *data); +int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector, + struct dm_report_zones_args *args, unsigned int nr_zones); #endif /* CONFIG_BLK_DEV_ZONED */ /* diff --git a/include/linux/device.h b/include/linux/device.h index 959cb9d2c9ab..4cd200f8b47a 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -817,6 +817,7 @@ int device_online(struct device *dev); void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode); void device_set_of_node_from_dev(struct device *dev, const struct device *dev2); +void device_set_node(struct device *dev, struct fwnode_handle *fwnode); static inline int dev_num_vf(struct device *dev) { diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h index f40f77717a24..74891802200d 100644 --- a/include/linux/devm-helpers.h +++ b/include/linux/devm-helpers.h @@ -51,4 +51,29 @@ static inline int devm_delayed_work_autocancel(struct device *dev, return devm_add_action(dev, devm_delayed_work_drop, w); } +static inline void devm_work_drop(void *res) +{ + cancel_work_sync(res); +} + +/** + * devm_work_autocancel - Resource-managed work allocation + * @dev: Device which lifetime work is bound to + * @w: Work to be added (and automatically cancelled) + * @worker: Worker function + * + * Initialize work which is automatically cancelled when driver is detached. + * A few drivers need to queue work which must be cancelled before driver + * is detached to avoid accessing removed resources. + * devm_work_autocancel() can be used to omit the explicit + * cancelleation when driver is detached. + */ +static inline int devm_work_autocancel(struct device *dev, + struct work_struct *w, + work_func_t worker) +{ + INIT_WORK(w, worker); + return devm_add_action(dev, devm_work_drop, w); +} + #endif diff --git a/include/linux/dm-kcopyd.h b/include/linux/dm-kcopyd.h index e42de7750c88..c1707ee5b540 100644 --- a/include/linux/dm-kcopyd.h +++ b/include/linux/dm-kcopyd.h @@ -51,6 +51,7 @@ MODULE_PARM_DESC(name, description) struct dm_kcopyd_client; struct dm_kcopyd_client *dm_kcopyd_client_create(struct dm_kcopyd_throttle *throttle); void dm_kcopyd_client_destroy(struct dm_kcopyd_client *kc); +void dm_kcopyd_client_flush(struct dm_kcopyd_client *kc); /* * Submit a copy job to kcopyd. This is built on top of the diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index d44a77e8a7e3..562b885cf9c3 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -78,19 +78,11 @@ struct dma_resv { #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -/** - * dma_resv_get_list - get the reservation object's - * shared fence list, with update-side lock held - * @obj: the reservation object - * - * Returns the shared fence list. Does NOT take references to - * the fence. The obj->lock must be held. - */ -static inline struct dma_resv_list *dma_resv_get_list(struct dma_resv *obj) -{ - return rcu_dereference_protected(obj->fence, - dma_resv_held(obj)); -} +#ifdef CONFIG_DEBUG_MUTEXES +void dma_resv_reset_shared_max(struct dma_resv *obj); +#else +static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} +#endif /** * dma_resv_lock - lock the reservation object @@ -215,38 +207,29 @@ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) */ static inline void dma_resv_unlock(struct dma_resv *obj) { -#ifdef CONFIG_DEBUG_MUTEXES - /* Test shared fence slot reservation */ - if (rcu_access_pointer(obj->fence)) { - struct dma_resv_list *fence = dma_resv_get_list(obj); - - fence->shared_max = fence->shared_count; - } -#endif + dma_resv_reset_shared_max(obj); ww_mutex_unlock(&obj->lock); } /** - * dma_resv_get_excl - get the reservation object's - * exclusive fence, with update-side lock held + * dma_resv_exclusive - return the object's exclusive fence * @obj: the reservation object * - * Returns the exclusive fence (if any). Does NOT take a - * reference. Writers must hold obj->lock, readers may only - * hold a RCU read side lock. + * Returns the exclusive fence (if any). Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each * * RETURNS * The exclusive fence or NULL */ static inline struct dma_fence * -dma_resv_get_excl(struct dma_resv *obj) +dma_resv_excl_fence(struct dma_resv *obj) { - return rcu_dereference_protected(obj->fence_excl, - dma_resv_held(obj)); + return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); } /** - * dma_resv_get_excl_rcu - get the reservation object's + * dma_resv_get_excl_unlocked - get the reservation object's * exclusive fence, without lock held. * @obj: the reservation object * @@ -257,7 +240,7 @@ dma_resv_get_excl(struct dma_resv *obj) * The exclusive fence or NULL if none */ static inline struct dma_fence * -dma_resv_get_excl_rcu(struct dma_resv *obj) +dma_resv_get_excl_unlocked(struct dma_resv *obj) { struct dma_fence *fence; @@ -271,23 +254,29 @@ dma_resv_get_excl_rcu(struct dma_resv *obj) return fence; } +/** + * dma_resv_shared_list - get the reservation object's shared fence list + * @obj: the reservation object + * + * Returns the shared fence list. Caller must either hold the objects + * through dma_resv_lock() or the RCU read side lock through rcu_read_lock(), + * or one of the variants of each + */ +static inline struct dma_resv_list *dma_resv_shared_list(struct dma_resv *obj) +{ + return rcu_dereference_check(obj->fence, dma_resv_held(obj)); +} + void dma_resv_init(struct dma_resv *obj); void dma_resv_fini(struct dma_resv *obj); int dma_resv_reserve_shared(struct dma_resv *obj, unsigned int num_fences); void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence); - void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence); - -int dma_resv_get_fences_rcu(struct dma_resv *obj, - struct dma_fence **pfence_excl, - unsigned *pshared_count, - struct dma_fence ***pshared); - +int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **pfence_excl, + unsigned *pshared_count, struct dma_fence ***pshared); int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); - -long dma_resv_wait_timeout_rcu(struct dma_resv *obj, bool wait_all, bool intr, - unsigned long timeout); - -bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all); +long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, + unsigned long timeout); +bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); #endif /* _LINUX_RESERVATION_H */ diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b12b05f1c8b4..1587961f1a7b 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -37,8 +37,6 @@ struct dsa_8021q_context { #define DSA_8021Q_N_SUBVLAN 8 -#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -52,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); @@ -70,78 +71,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid); bool vid_is_dsa_8021q(u16 vid); -#else - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) -{ - return NULL; -} - -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return 0; -} - -int dsa_8021q_rx_switch_id(u16 vid) -{ - return 0; -} - -int dsa_8021q_rx_source_port(u16 vid) -{ - return 0; -} - -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - return 0; -} - -bool vid_is_dsa_8021q_rxvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q_txvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q(u16 vid) -{ - return false; -} - -#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ - #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1eb84562b311..b6089b88314c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -14,6 +14,7 @@ #define ETH_P_SJA1105 ETH_P_DSA_8021Q #define ETH_P_SJA1105_META 0x0008 +#define ETH_P_SJA1110 0xdadc /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull @@ -44,11 +45,14 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; + u8 ts_id; }; struct sja1105_skb_cb { struct sk_buff *clone; - u32 meta_tstamp; + u64 tstamp; + /* Only valid for packets cloned for 2-step TX timestamping */ + u8 ts_id; }; #define SJA1105_SKB_CB(skb) \ @@ -65,4 +69,24 @@ struct sja1105_port { u16 xmit_tpid; }; +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + +#else + +static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ + #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/elevator.h b/include/linux/elevator.h index dcb2f9022c1d..ef9ceead3db1 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -117,9 +117,11 @@ extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, + struct list_head *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); +void elevator_init_mq(struct request_queue *q); /* * io scheduler registration diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index e030f7510cd3..29dbb603bc91 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -401,12 +401,12 @@ struct ethtool_rmon_stats { * required information to the driver. */ struct ethtool_module_eeprom { - __u32 offset; - __u32 length; - __u8 page; - __u8 bank; - __u8 i2c_address; - __u8 *data; + u32 offset; + u32 length; + u8 page; + u8 bank; + u8 i2c_address; + u8 *data; }; /** diff --git a/include/linux/filter.h b/include/linux/filter.h index 9a09547bc7ba..472f97074da0 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -646,6 +646,7 @@ struct bpf_redirect_info { u32 flags; u32 tgt_index; void *tgt_value; + struct bpf_map *map; u32 map_id; enum bpf_map_type map_type; u32 kern_flags; @@ -762,11 +763,9 @@ DECLARE_BPF_DISPATCHER(xdp) static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, struct xdp_buff *xdp) { - /* Caller needs to hold rcu_read_lock() (!), otherwise program - * can be released while still running, or map elements could be - * freed early while still having concurrent users. XDP fastpath - * already takes rcu_read_lock() when fetching the program, so - * it's not necessary here anymore. + /* Driver XDP hooks are invoked within a single NAPI poll cycle and thus + * under local_bh_disable(), which provides the needed RCU protection + * for accessing map entries. */ return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp)); } @@ -995,11 +994,13 @@ void bpf_warn_invalid_xdp_action(u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, + struct sock *migrating_sk, u32 hash) { return NULL; @@ -1464,17 +1465,19 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, u64 flags, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, + u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ - if (unlikely(flags > XDP_TX)) + if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, ifindex); - if (unlikely(!ri->tgt_value)) { + if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes @@ -1482,13 +1485,21 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; - return flags; + return flags & action_mask; } ri->tgt_index = ifindex; ri->map_id = map->id; ri->map_type = map->map_type; + if (flags & BPF_F_BROADCAST) { + WRITE_ONCE(ri->map, map); + ri->flags = flags; + } else { + WRITE_ONCE(ri->map, NULL); + ri->flags = 0; + } + return XDP_REDIRECT; } diff --git a/include/linux/fs.h b/include/linux/fs.h index fad6663cd1b0..02bf57e6f6e2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2171,7 +2171,6 @@ struct super_operations { ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif - int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h new file mode 100644 index 000000000000..faf603c48c86 --- /dev/null +++ b/include/linux/fwnode_mdio.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * FWNODE helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_FWNODE_MDIO_H +#define __LINUX_FWNODE_MDIO_H + +#include <linux/phy.h> + +#if IS_ENABLED(CONFIG_FWNODE_MDIO) +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr); + +#else /* CONFIG_FWNODE_MDIO */ +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + return -EINVAL; +} + +static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, + u32 addr) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_FWNODE_MDIO_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 6fc26f7bdf71..13b34177cc85 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -153,6 +153,11 @@ struct gendisk { unsigned long state; #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 +#define GD_QUEUE_REF 2 + + struct mutex open_mutex; /* open/close mutex */ + unsigned open_partitions; /* number of open partitions */ + struct kobject *slave_dir; struct timer_rand_state *random; @@ -218,7 +223,6 @@ static inline void add_disk_no_queue_reg(struct gendisk *disk) } extern void del_gendisk(struct gendisk *gp); -extern struct block_device *bdget_disk(struct gendisk *disk, int partno); void set_disk_ro(struct gendisk *disk, bool read_only); @@ -252,8 +256,7 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } -int bdev_disk_changed(struct block_device *bdev, bool invalidate); -int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); +int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); extern struct gendisk *__alloc_disk_node(int minors, int node_id); @@ -277,6 +280,28 @@ extern void put_disk(struct gendisk *disk); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +/** + * blk_alloc_disk - allocate a gendisk structure + * @node_id: numa node to allocate on + * + * Allocate and pre-initialize a gendisk structure for use with BIO based + * drivers. + * + * Context: can sleep + */ +#define blk_alloc_disk(node_id) \ +({ \ + struct gendisk *__disk = __blk_alloc_disk(node_id); \ + static struct lock_class_key __key; \ + \ + if (__disk) \ + lockdep_init_map(&__disk->lockdep_map, \ + "(bio completion)", &__key, 0); \ + __disk; \ +}) +struct gendisk *__blk_alloc_disk(int node); +void blk_cleanup_disk(struct gendisk *disk); + int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)); #define register_blkdev(major, name) \ @@ -306,6 +331,7 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +dev_t part_devt(struct gendisk *disk, u8 partno); dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index c73b25bc9213..566feb56601f 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -692,6 +692,8 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); void devm_acpi_dev_remove_driver_gpios(struct device *dev); +struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); + #else /* CONFIG_GPIOLIB && CONFIG_ACPI */ struct acpi_device; diff --git a/include/linux/hid.h b/include/linux/hid.h index 10e922cee4eb..9e067f937dbc 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -102,6 +102,7 @@ struct hid_item { #define HID_COLLECTION_PHYSICAL 0 #define HID_COLLECTION_APPLICATION 1 #define HID_COLLECTION_LOGICAL 2 +#define HID_COLLECTION_NAMED_ARRAY 4 /* * HID report descriptor global item tags @@ -800,6 +801,7 @@ struct hid_driver { * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device + * @may_wakeup: return if device may act as a wakeup source during system-suspend */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -824,6 +826,7 @@ struct hid_ll_driver { int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); + bool (*may_wakeup)(struct hid_device *hdev); }; extern struct hid_ll_driver i2c_hid_ll_driver; @@ -1150,6 +1153,22 @@ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, } /** + * hid_may_wakeup - return if the hid device may act as a wakeup source during system-suspend + * + * @hdev: hid device + */ +static inline bool hid_hw_may_wakeup(struct hid_device *hdev) +{ + if (hdev->ll_driver->may_wakeup) + return hdev->ll_driver->may_wakeup(hdev); + + if (hdev->dev.parent) + return device_may_wakeup(hdev->dev.parent); + + return false; +} + +/** * hid_hw_wait - wait for buffered io to complete * * @hdev: hid device diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 2a8ebe6c222e..f123e15d966e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -10,8 +10,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, - struct vm_area_struct *vma); -void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); + struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma); +void huge_pmd_set_accessed(struct vm_fault *vmf); int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); @@ -24,7 +24,7 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) } #endif -vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); @@ -115,9 +115,34 @@ extern struct kobj_attribute shmem_enabled_attr; extern unsigned long transparent_hugepage_flags; +static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, + unsigned long haddr) +{ + /* Don't have to check pgoff for anonymous vma */ + if (!vma_is_anonymous(vma)) { + if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff, + HPAGE_PMD_NR)) + return false; + } + + if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) + return false; + return true; +} + +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + /* Explicitly disabled through madvise. */ + if ((vm_flags & VM_NOHUGEPAGE) || + test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) + return false; + return true; +} + /* * to be used on vmas which are known to support THP. - * Use transparent_hugepage_enabled otherwise + * Use transparent_hugepage_active otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -128,15 +153,12 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_NEVER_DAX)) return false; - if (vma->vm_flags & VM_NOHUGEPAGE) + if (!transhuge_vma_enabled(vma, vma->vm_flags)) return false; if (vma_is_temporary_stack(vma)) return false; - if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) - return false; - if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; @@ -150,24 +172,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -bool transparent_hugepage_enabled(struct vm_area_struct *vma); - -#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) - -static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, - unsigned long haddr) -{ - /* Don't have to check pgoff for anonymous vma */ - if (!vma_is_anonymous(vma)) { - if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != - (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) - return false; - } - - if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) - return false; - return true; -} +bool transparent_hugepage_active(struct vm_area_struct *vma); #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ @@ -283,7 +288,7 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); -vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); +vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; @@ -354,7 +359,7 @@ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) return false; } -static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) +static inline bool transparent_hugepage_active(struct vm_area_struct *vma) { return false; } @@ -365,6 +370,12 @@ static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, return false; } +static inline bool transhuge_vma_enabled(struct vm_area_struct *vma, + unsigned long vm_flags) +{ + return false; +} + static inline void prep_transhuge_page(struct page *page) {} static inline bool is_transparent_hugepage(struct page *page) @@ -430,8 +441,7 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, - pmd_t orig_pmd) +static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { return 0; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8ba79dc64ab8..8e0f32f935bd 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -29,6 +29,23 @@ typedef struct { unsigned long pd; } hugepd_t; #include <linux/shm.h> #include <asm/tlbflush.h> +/* + * For HugeTLB page, there are more metadata to save in the struct page. But + * the head struct page cannot meet our needs, so we have to abuse other tail + * struct page to store the metadata. In order to avoid conflicts caused by + * subsequent use of more tail struct pages, we gather these discrete indexes + * of tail struct page here. + */ +enum { + SUBPAGE_INDEX_SUBPOOL = 1, /* reuse page->private */ +#ifdef CONFIG_CGROUP_HUGETLB + SUBPAGE_INDEX_CGROUP, /* reuse page->private */ + SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */ + __MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD, +#endif + __NR_USED_SUBPAGE, +}; + struct hugepage_subpool { spinlock_t lock; long count; @@ -515,12 +532,14 @@ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. + * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, + HPG_vmemmap_optimized, __NR_HPAGEFLAGS, }; @@ -566,6 +585,7 @@ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) +HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) #ifdef CONFIG_HUGETLB_PAGE @@ -588,6 +608,9 @@ struct hstate { unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP + unsigned int nr_free_vmemmap_pages; +#endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ struct cftype cgroup_files_dfl[7]; @@ -635,13 +658,13 @@ extern unsigned int default_hstate_idx; */ static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) { - return (struct hugepage_subpool *)(hpage+1)->private; + return (void *)page_private(hpage + SUBPAGE_INDEX_SUBPOOL); } static inline void hugetlb_set_page_subpool(struct page *hpage, struct hugepage_subpool *subpool) { - set_page_private(hpage+1, (unsigned long)subpool); + set_page_private(hpage + SUBPAGE_INDEX_SUBPOOL, (unsigned long)subpool); } static inline struct hstate *hstate_file(struct file *f) @@ -718,8 +741,8 @@ static inline void arch_clear_hugepage_flags(struct page *page) { } #endif #ifndef arch_make_huge_pte -static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, - struct page *page, int writable) +static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, + vm_flags_t flags) { return entry; } @@ -875,6 +898,11 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; +static inline struct hugepage_subpool *hugetlb_page_subpool(struct page *hpage) +{ + return NULL; +} + static inline int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list) { @@ -1028,6 +1056,12 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr } #endif /* CONFIG_HUGETLB_PAGE */ +#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP +extern bool hugetlb_free_vmemmap_enabled; +#else +#define hugetlb_free_vmemmap_enabled false +#endif + static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 0bff345c4bc6..0b8d1fdda3a1 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -21,15 +21,16 @@ struct hugetlb_cgroup; struct resv_map; struct file_region; +#ifdef CONFIG_CGROUP_HUGETLB /* * Minimum page order trackable by hugetlb cgroup. * At least 4 pages are necessary for all the tracking information. - * The second tail page (hpage[2]) is the fault usage cgroup. - * The third tail page (hpage[3]) is the reservation usage cgroup. + * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault + * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD]) + * is the reservation usage cgroup. */ -#define HUGETLB_CGROUP_MIN_ORDER 2 +#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__MAX_CGROUP_SUBPAGE_INDEX + 1) -#ifdef CONFIG_CGROUP_HUGETLB enum hugetlb_memory_event { HUGETLB_MAX, HUGETLB_NR_MEMORY_EVENTS, @@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd) if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return NULL; if (rsvd) - return (struct hugetlb_cgroup *)page[3].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD); else - return (struct hugetlb_cgroup *)page[2].private; + return (void *)page_private(page + SUBPAGE_INDEX_CGROUP); } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page) @@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page, if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER) return -1; if (rsvd) - page[3].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD, + (unsigned long)h_cg); else - page[2].private = (unsigned long)h_cg; + set_page_private(page + SUBPAGE_INDEX_CGROUP, + (unsigned long)h_cg); return 0; } diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 2967437f1b11..a6730072d13a 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -9,7 +9,7 @@ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net> * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH * Copyright (c) 2016 - 2017 Intel Deutschland GmbH - * Copyright (c) 2018 - 2020 Intel Corporation + * Copyright (c) 2018 - 2021 Intel Corporation */ #ifndef LINUX_IEEE80211_H @@ -2179,6 +2179,8 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 #define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) #define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) @@ -2933,6 +2935,7 @@ enum ieee80211_category { WLAN_CATEGORY_BACK = 3, WLAN_CATEGORY_PUBLIC = 4, WLAN_CATEGORY_RADIO_MEASUREMENT = 5, + WLAN_CATEGORY_FAST_BBS_TRANSITION = 6, WLAN_CATEGORY_HT = 7, WLAN_CATEGORY_SA_QUERY = 8, WLAN_CATEGORY_PROTECTED_DUAL_OF_ACTION = 9, @@ -3110,6 +3113,11 @@ enum ieee80211_tdls_actioncode { */ #define WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT BIT(6) +/* Timing Measurement protocol for time sync is set in the 7th bit of 3rd byte + * of the @WLAN_EID_EXT_CAPABILITY information element + */ +#define WLAN_EXT_CAPA3_TIMING_MEASUREMENT_SUPPORT BIT(7) + /* TDLS capabilities in the 4th byte of @WLAN_EID_EXT_CAPABILITY */ #define WLAN_EXT_CAPA4_TDLS_BUFFER_STA BIT(4) #define WLAN_EXT_CAPA4_TDLS_PEER_PSM BIT(5) diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h index bf5c5f32c65e..b712217f7030 100644 --- a/include/linux/if_arp.h +++ b/include/linux/if_arp.h @@ -48,6 +48,7 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev) case ARPHRD_TUNNEL6: case ARPHRD_SIT: case ARPHRD_IPGRE: + case ARPHRD_IP6GRE: case ARPHRD_VOID: case ARPHRD_NONE: case ARPHRD_RAWIP: diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 2cc35038a8ca..b651c5e32a28 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -67,10 +67,12 @@ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list); bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto); bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto); +bool br_multicast_has_router_adjacent(struct net_device *dev, int proto); bool br_multicast_enabled(const struct net_device *dev); bool br_multicast_router(const struct net_device *dev); int br_mdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) @@ -87,6 +89,13 @@ static inline bool br_multicast_has_querier_adjacent(struct net_device *dev, { return false; } + +static inline bool br_multicast_has_router_adjacent(struct net_device *dev, + int proto) +{ + return true; +} + static inline bool br_multicast_enabled(const struct net_device *dev) { return false; @@ -95,9 +104,9 @@ static inline bool br_multicast_router(const struct net_device *dev) { return false; } -static inline int br_mdb_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb, +static inline int br_mdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -112,7 +121,8 @@ int br_vlan_get_proto(const struct net_device *dev, u16 *p_proto); int br_vlan_get_info(const struct net_device *dev, u16 vid, struct bridge_vlan_info *p_vinfo); int br_vlan_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb, struct netlink_ext_ack *extack); + const void *ctx, bool adding, struct notifier_block *nb, + struct netlink_ext_ack *extack); #else static inline bool br_vlan_enabled(const struct net_device *dev) { @@ -141,8 +151,8 @@ static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, } static inline int br_vlan_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb, + struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; @@ -156,9 +166,9 @@ struct net_device *br_fdb_find_port(const struct net_device *br_dev, void br_fdb_clear_offload(const struct net_device *dev, u16 vid); bool br_port_flag_is_set(const struct net_device *dev, unsigned long flag); u8 br_port_get_stp_state(const struct net_device *dev); -clock_t br_get_ageing_time(struct net_device *br_dev); -int br_fdb_replay(struct net_device *br_dev, struct net_device *dev, - struct notifier_block *nb); +clock_t br_get_ageing_time(const struct net_device *br_dev); +int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev, + const void *ctx, bool adding, struct notifier_block *nb); #else static inline struct net_device * br_fdb_find_port(const struct net_device *br_dev, @@ -183,14 +193,14 @@ static inline u8 br_port_get_stp_state(const struct net_device *dev) return BR_STATE_DISABLED; } -static inline clock_t br_get_ageing_time(struct net_device *br_dev) +static inline clock_t br_get_ageing_time(const struct net_device *br_dev) { return 0; } -static inline int br_fdb_replay(struct net_device *br_dev, - struct net_device *dev, - struct notifier_block *nb) +static inline int br_fdb_replay(const struct net_device *br_dev, + const struct net_device *dev, const void *ctx, + bool adding, struct notifier_block *nb) { return -EOPNOTSUPP; } diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h index 4efb537f57f3..10e7521ecb6c 100644 --- a/include/linux/if_rmnet.h +++ b/include/linux/if_rmnet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only - * Copyright (c) 2013-2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2013-2019, 2021 The Linux Foundation. All rights reserved. */ #ifndef _LINUX_IF_RMNET_H_ @@ -12,10 +12,12 @@ struct rmnet_map_header { } __aligned(1); /* rmnet_map_header flags field: - * PAD_LEN: number of pad bytes following packet data - * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * PAD_LEN: number of pad bytes following packet data + * CMD: 1 = packet contains a MAP command; 0 = packet contains data + * NEXT_HEADER: 1 = packet contains V5 CSUM header 0 = no V5 CSUM header */ #define MAP_PAD_LEN_MASK GENMASK(5, 0) +#define MAP_NEXT_HEADER_FLAG BIT(6) #define MAP_CMD_FLAG BIT(7) struct rmnet_map_dl_csum_trailer { @@ -23,7 +25,7 @@ struct rmnet_map_dl_csum_trailer { u8 flags; /* MAP_CSUM_DL_VALID_FLAG */ __be16 csum_start_offset; __be16 csum_length; - __be16 csum_value; + __sum16 csum_value; } __aligned(1); /* rmnet_map_dl_csum_trailer flags field: @@ -45,4 +47,26 @@ struct rmnet_map_ul_csum_header { #define MAP_CSUM_UL_UDP_FLAG BIT(14) #define MAP_CSUM_UL_ENABLED_FLAG BIT(15) +/* MAP CSUM headers */ +struct rmnet_map_v5_csum_header { + u8 header_info; + u8 csum_info; + __be16 reserved; +} __aligned(1); + +/* v5 header_info field + * NEXT_HEADER: represents whether there is any next header + * HEADER_TYPE: represents the type of this header + * + * csum_info field + * CSUM_VALID_OR_REQ: + * 1 = for UL, checksum computation is requested. + * 1 = for DL, validated the checksum and has found it valid + */ + +#define MAPV5_HDRINFO_NXT_HDR_FLAG BIT(0) +#define MAPV5_HDRINFO_HDR_TYPE_FMASK GENMASK(7, 1) +#define MAPV5_CSUMINFO_VALID_FLAG BIT(7) + +#define RMNET_MAP_HEADER_TYPE_CSUM_OFFLOAD 2 #endif /* !(_LINUX_IF_RMNET_H_) */ diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 0d6b4bc191c5..25e2b4e80502 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -8,11 +8,17 @@ #ifndef _INTEL_ISH_CLIENT_IF_H_ #define _INTEL_ISH_CLIENT_IF_H_ +#include <linux/device.h> +#include <linux/uuid.h> + struct ishtp_cl_device; struct ishtp_device; struct ishtp_cl; struct ishtp_fw_client; +typedef __printf(2, 3) void (*ishtp_print_log)(struct ishtp_device *dev, + const char *format, ...); + /* Client state */ enum cl_state { ISHTP_CL_INITIALIZING = 0, @@ -36,7 +42,7 @@ struct ishtp_cl_driver { const char *name; const guid_t *guid; int (*probe)(struct ishtp_cl_device *dev); - int (*remove)(struct ishtp_cl_device *dev); + void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); const struct dev_pm_ops *pm; }; @@ -76,7 +82,7 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device, /* Get the device * from ishtp device instance */ struct device *ishtp_device(struct ishtp_cl_device *cl_device); /* Trace interface for clients */ -void *ishtp_trace_callback(struct ishtp_cl_device *cl_device); +ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device); /* Get device pointer of PCI device for DMA acces */ struct device *ishtp_get_pci_device(struct ishtp_cl_device *cl_device); diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index db0e1920cb12..6cc035321562 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -780,6 +780,11 @@ struct journal_s unsigned long j_flags; /** + * @j_atomic_flags: Atomic journaling state flags. + */ + unsigned long j_atomic_flags; + + /** * @j_errno: * * Is there an outstanding uncleared error on the journal (from a prior @@ -905,6 +910,29 @@ struct journal_s struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; /** + * @j_shrinker: + * + * Journal head shrinker, reclaim buffer's journal head which + * has been written back. + */ + struct shrinker j_shrinker; + + /** + * @j_jh_shrink_count: + * + * Number of journal buffers on the checkpoint list. [j_list_lock] + */ + struct percpu_counter j_jh_shrink_count; + + /** + * @j_shrink_transaction: + * + * Record next transaction will shrink on the checkpoint list. + * [j_list_lock] + */ + transaction_t *j_shrink_transaction; + + /** * @j_head: * * Journal head: identifies the first unused block in the journal. @@ -1370,6 +1398,16 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) * mode */ #define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ #define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ +#define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 +#define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 +#define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ + JBD2_JOURNAL_FLUSH_ZEROOUT) + +/* + * Journal atomic flag definitions + */ +#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing + * buffer back to disk */ /* * Function declarations for the journaling transaction and buffer @@ -1407,6 +1445,7 @@ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy); +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); @@ -1500,7 +1539,7 @@ extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); -extern int jbd2_journal_flush (journal_t *); +extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); @@ -1517,6 +1556,8 @@ extern int jbd2_journal_set_features (journal_t *, unsigned long, unsigned long, unsigned long); extern void jbd2_journal_clear_features (journal_t *, unsigned long, unsigned long, unsigned long); +extern int jbd2_journal_register_shrinker(journal_t *journal); +extern void jbd2_journal_unregister_shrinker(journal_t *journal); extern int jbd2_journal_load (journal_t *journal); extern int jbd2_journal_destroy (journal_t *); extern int jbd2_journal_recover (journal_t *journal); diff --git a/include/linux/kcore.h b/include/linux/kcore.h index da676cdbd727..86c0f1d18998 100644 --- a/include/linux/kcore.h +++ b/include/linux/kcore.h @@ -11,14 +11,11 @@ enum kcore_type { KCORE_RAM, KCORE_VMEMMAP, KCORE_USER, - KCORE_OTHER, - KCORE_REMAP, }; struct kcore_list { struct list_head list; unsigned long addr; - unsigned long vaddr; size_t size; int type; }; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bf950621febf..1b2f0a7e00d6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -10,10 +10,12 @@ #include <linux/types.h> #include <linux/compiler.h> #include <linux/bitops.h> +#include <linux/kstrtox.h> #include <linux/log2.h> #include <linux/math.h> #include <linux/minmax.h> #include <linux/typecheck.h> +#include <linux/panic.h> #include <linux/printk.h> #include <linux/build_bug.h> #include <linux/static_call_types.h> @@ -71,8 +73,19 @@ */ #define lower_32_bits(n) ((u32)((n) & 0xffffffff)) +/** + * upper_16_bits - return bits 16-31 of a number + * @n: the number we're accessing + */ +#define upper_16_bits(n) ((u16)((n) >> 16)) + +/** + * lower_16_bits - return bits 0-15 of a number + * @n: the number we're accessing + */ +#define lower_16_bits(n) ((u16)((n) & 0xffff)) + struct completion; -struct pt_regs; struct user; #ifdef CONFIG_PREEMPT_VOLUNTARY @@ -177,159 +190,9 @@ void __might_fault(const char *file, int line); static inline void might_fault(void) { } #endif -extern struct atomic_notifier_head panic_notifier_list; -extern long (*panic_blink)(int state); -__printf(1, 2) -void panic(const char *fmt, ...) __noreturn __cold; -void nmi_panic(struct pt_regs *regs, const char *msg); -extern void oops_enter(void); -extern void oops_exit(void); -extern bool oops_may_print(void); void do_exit(long error_code) __noreturn; void complete_and_exit(struct completion *, long) __noreturn; -/* Internal, do not use. */ -int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); -int __must_check _kstrtol(const char *s, unsigned int base, long *res); - -int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); -int __must_check kstrtoll(const char *s, unsigned int base, long long *res); - -/** - * kstrtoul - convert a string to an unsigned long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign, but not a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtoul(). Return code must be checked. -*/ -static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. - */ - if (sizeof(unsigned long) == sizeof(unsigned long long) && - __alignof__(unsigned long) == __alignof__(unsigned long long)) - return kstrtoull(s, base, (unsigned long long *)res); - else - return _kstrtoul(s, base, res); -} - -/** - * kstrtol - convert a string to a long - * @s: The start of the string. The string must be null-terminated, and may also - * include a single newline before its terminating null. The first character - * may also be a plus sign or a minus sign. - * @base: The number base to use. The maximum supported base is 16. If base is - * given as 0, then the base of the string is automatically detected with the - * conventional semantics - If it begins with 0x the number will be parsed as a - * hexadecimal (case insensitive), if it otherwise begins with 0, it will be - * parsed as an octal number. Otherwise it will be parsed as a decimal. - * @res: Where to write the result of the conversion on success. - * - * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. - * Preferred over simple_strtol(). Return code must be checked. - */ -static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) -{ - /* - * We want to shortcut function call, but - * __builtin_types_compatible_p(long, long long) = 0. - */ - if (sizeof(long) == sizeof(long long) && - __alignof__(long) == __alignof__(long long)) - return kstrtoll(s, base, (long long *)res); - else - return _kstrtol(s, base, res); -} - -int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); -int __must_check kstrtoint(const char *s, unsigned int base, int *res); - -static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) -{ - return kstrtoull(s, base, res); -} - -static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) -{ - return kstrtoll(s, base, res); -} - -static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) -{ - return kstrtouint(s, base, res); -} - -static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) -{ - return kstrtoint(s, base, res); -} - -int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); -int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); -int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); -int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); -int __must_check kstrtobool(const char *s, bool *res); - -int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); -int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); -int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); -int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); -int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); -int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); -int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); -int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); -int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); -int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); -int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); - -static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) -{ - return kstrtoull_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) -{ - return kstrtoll_from_user(s, count, base, res); -} - -static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) -{ - return kstrtouint_from_user(s, count, base, res); -} - -static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) -{ - return kstrtoint_from_user(s, count, base, res); -} - -/* - * Use kstrto<foo> instead. - * - * NOTE: simple_strto<foo> does not check for the range overflow and, - * depending on the input, may give interesting results. - * - * Use these functions if and only if you cannot use kstrto<foo>, because - * the conversion ends on the first non-digit character, which may be far - * beyond the supported range. It might be useful to parse the strings like - * 10x50 or 12:21 without altering original string or temporary buffer in use. - * Keep in mind above caveat. - */ - -extern unsigned long simple_strtoul(const char *,char **,unsigned int); -extern long simple_strtol(const char *,char **,unsigned int); -extern unsigned long long simple_strtoull(const char *,char **,unsigned int); -extern long long simple_strtoll(const char *,char **,unsigned int); - extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); @@ -372,52 +235,8 @@ extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); -#ifdef CONFIG_SMP -extern unsigned int sysctl_oops_all_cpu_backtrace; -#else -#define sysctl_oops_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - extern void bust_spinlocks(int yes); -extern int panic_timeout; -extern unsigned long panic_print; -extern int panic_on_oops; -extern int panic_on_unrecovered_nmi; -extern int panic_on_io_nmi; -extern int panic_on_warn; -extern unsigned long panic_on_taint; -extern bool panic_on_taint_nousertaint; -extern int sysctl_panic_on_rcu_stall; -extern int sysctl_max_rcu_stall_to_panic; -extern int sysctl_panic_on_stackoverflow; - -extern bool crash_kexec_post_notifiers; - -/* - * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It - * holds a CPU number which is executing panic() currently. A value of - * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). - */ -extern atomic_t panic_cpu; -#define PANIC_CPU_INVALID -1 -/* - * Only to be used by arch init code. If the user over-wrote the default - * CONFIG_PANIC_TIMEOUT, honor it. - */ -static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) -{ - if (panic_timeout == arch_default_timeout) - panic_timeout = timeout; -} -extern const char *print_tainted(void); -enum lockdep_ok { - LOCKDEP_STILL_OK, - LOCKDEP_NOW_UNRELIABLE -}; -extern void add_taint(unsigned flag, enum lockdep_ok); -extern int test_taint(unsigned flag); -extern unsigned long get_taint(void); extern int root_mountflags; extern bool early_boot_irqs_disabled; @@ -436,36 +255,6 @@ extern enum system_states { SYSTEM_SUSPEND, } system_state; -/* This cannot be an enum because some may be used in assembly source. */ -#define TAINT_PROPRIETARY_MODULE 0 -#define TAINT_FORCED_MODULE 1 -#define TAINT_CPU_OUT_OF_SPEC 2 -#define TAINT_FORCED_RMMOD 3 -#define TAINT_MACHINE_CHECK 4 -#define TAINT_BAD_PAGE 5 -#define TAINT_USER 6 -#define TAINT_DIE 7 -#define TAINT_OVERRIDDEN_ACPI_TABLE 8 -#define TAINT_WARN 9 -#define TAINT_CRAP 10 -#define TAINT_FIRMWARE_WORKAROUND 11 -#define TAINT_OOT_MODULE 12 -#define TAINT_UNSIGNED_MODULE 13 -#define TAINT_SOFTLOCKUP 14 -#define TAINT_LIVEPATCH 15 -#define TAINT_AUX 16 -#define TAINT_RANDSTRUCT 17 -#define TAINT_FLAGS_COUNT 18 -#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) - -struct taint_flag { - char c_true; /* character printed when tainted */ - char c_false; /* character printed when not tainted */ - bool module; /* also show as a per-module taint flag */ -}; - -extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; - extern const char hex_asc[]; #define hex_asc_lo(x) hex_asc[((x) & 0x0f)] #define hex_asc_hi(x) hex_asc[((x) & 0xf0) >> 4] diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 523ffc7bc3a8..4d0c28c2ba12 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -399,7 +399,6 @@ int enable_kprobe(struct kprobe *kp); void dump_kprobe(struct kprobe *kp); void *alloc_insn_page(void); -void free_insn_page(void *page); int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h new file mode 100644 index 000000000000..529974e22ea7 --- /dev/null +++ b/include/linux/kstrtox.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KSTRTOX_H +#define _LINUX_KSTRTOX_H + +#include <linux/compiler.h> +#include <linux/types.h> + +/* Internal, do not use. */ +int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); +int __must_check _kstrtol(const char *s, unsigned int base, long *res); + +int __must_check kstrtoull(const char *s, unsigned int base, unsigned long long *res); +int __must_check kstrtoll(const char *s, unsigned int base, long long *res); + +/** + * kstrtoul - convert a string to an unsigned long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign, but not a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtoul(). Return code must be checked. +*/ +static inline int __must_check kstrtoul(const char *s, unsigned int base, unsigned long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(unsigned long, unsigned long long) = 0. + */ + if (sizeof(unsigned long) == sizeof(unsigned long long) && + __alignof__(unsigned long) == __alignof__(unsigned long long)) + return kstrtoull(s, base, (unsigned long long *)res); + else + return _kstrtoul(s, base, res); +} + +/** + * kstrtol - convert a string to a long + * @s: The start of the string. The string must be null-terminated, and may also + * include a single newline before its terminating null. The first character + * may also be a plus sign or a minus sign. + * @base: The number base to use. The maximum supported base is 16. If base is + * given as 0, then the base of the string is automatically detected with the + * conventional semantics - If it begins with 0x the number will be parsed as a + * hexadecimal (case insensitive), if it otherwise begins with 0, it will be + * parsed as an octal number. Otherwise it will be parsed as a decimal. + * @res: Where to write the result of the conversion on success. + * + * Returns 0 on success, -ERANGE on overflow and -EINVAL on parsing error. + * Preferred over simple_strtol(). Return code must be checked. + */ +static inline int __must_check kstrtol(const char *s, unsigned int base, long *res) +{ + /* + * We want to shortcut function call, but + * __builtin_types_compatible_p(long, long long) = 0. + */ + if (sizeof(long) == sizeof(long long) && + __alignof__(long) == __alignof__(long long)) + return kstrtoll(s, base, (long long *)res); + else + return _kstrtol(s, base, res); +} + +int __must_check kstrtouint(const char *s, unsigned int base, unsigned int *res); +int __must_check kstrtoint(const char *s, unsigned int base, int *res); + +static inline int __must_check kstrtou64(const char *s, unsigned int base, u64 *res) +{ + return kstrtoull(s, base, res); +} + +static inline int __must_check kstrtos64(const char *s, unsigned int base, s64 *res) +{ + return kstrtoll(s, base, res); +} + +static inline int __must_check kstrtou32(const char *s, unsigned int base, u32 *res) +{ + return kstrtouint(s, base, res); +} + +static inline int __must_check kstrtos32(const char *s, unsigned int base, s32 *res) +{ + return kstrtoint(s, base, res); +} + +int __must_check kstrtou16(const char *s, unsigned int base, u16 *res); +int __must_check kstrtos16(const char *s, unsigned int base, s16 *res); +int __must_check kstrtou8(const char *s, unsigned int base, u8 *res); +int __must_check kstrtos8(const char *s, unsigned int base, s8 *res); +int __must_check kstrtobool(const char *s, bool *res); + +int __must_check kstrtoull_from_user(const char __user *s, size_t count, unsigned int base, unsigned long long *res); +int __must_check kstrtoll_from_user(const char __user *s, size_t count, unsigned int base, long long *res); +int __must_check kstrtoul_from_user(const char __user *s, size_t count, unsigned int base, unsigned long *res); +int __must_check kstrtol_from_user(const char __user *s, size_t count, unsigned int base, long *res); +int __must_check kstrtouint_from_user(const char __user *s, size_t count, unsigned int base, unsigned int *res); +int __must_check kstrtoint_from_user(const char __user *s, size_t count, unsigned int base, int *res); +int __must_check kstrtou16_from_user(const char __user *s, size_t count, unsigned int base, u16 *res); +int __must_check kstrtos16_from_user(const char __user *s, size_t count, unsigned int base, s16 *res); +int __must_check kstrtou8_from_user(const char __user *s, size_t count, unsigned int base, u8 *res); +int __must_check kstrtos8_from_user(const char __user *s, size_t count, unsigned int base, s8 *res); +int __must_check kstrtobool_from_user(const char __user *s, size_t count, bool *res); + +static inline int __must_check kstrtou64_from_user(const char __user *s, size_t count, unsigned int base, u64 *res) +{ + return kstrtoull_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos64_from_user(const char __user *s, size_t count, unsigned int base, s64 *res) +{ + return kstrtoll_from_user(s, count, base, res); +} + +static inline int __must_check kstrtou32_from_user(const char __user *s, size_t count, unsigned int base, u32 *res) +{ + return kstrtouint_from_user(s, count, base, res); +} + +static inline int __must_check kstrtos32_from_user(const char __user *s, size_t count, unsigned int base, s32 *res) +{ + return kstrtoint_from_user(s, count, base, res); +} + +/* + * Use kstrto<foo> instead. + * + * NOTE: simple_strto<foo> does not check for the range overflow and, + * depending on the input, may give interesting results. + * + * Use these functions if and only if you cannot use kstrto<foo>, because + * the conversion ends on the first non-digit character, which may be far + * beyond the supported range. It might be useful to parse the strings like + * 10x50 or 12:21 without altering original string or temporary buffer in use. + * Keep in mind above caveat. + */ + +extern unsigned long simple_strtoul(const char *,char **,unsigned int); +extern long simple_strtol(const char *,char **,unsigned int); +extern unsigned long long simple_strtoull(const char *,char **,unsigned int); +extern long long simple_strtoll(const char *,char **,unsigned int); + +static inline int strtobool(const char *s, bool *res) +{ + return kstrtobool(s, res); +} + +#endif /* _LINUX_KSTRTOX_H */ diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h index cd23355d2271..17d02eda9538 100644 --- a/include/linux/lsm_audit.h +++ b/include/linux/lsm_audit.h @@ -48,13 +48,13 @@ struct lsm_ioctlop_audit { }; struct lsm_ibpkey_audit { - u64 subnet_prefix; - u16 pkey; + u64 subnet_prefix; + u16 pkey; }; struct lsm_ibendport_audit { - char dev_name[IB_DEVICE_NAME_MAX]; - u8 port; + const char *dev_name; + u8 port; }; /* Auxiliary data to use in generating the audit record. */ diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 04c01794de83..2adeea44c0d5 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -358,8 +358,7 @@ LSM_HOOK(int, 0, xfrm_state_alloc_acquire, struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid) LSM_HOOK(void, LSM_RET_VOID, xfrm_state_free_security, struct xfrm_state *x) LSM_HOOK(int, 0, xfrm_state_delete_security, struct xfrm_state *x) -LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid, - u8 dir) +LSM_HOOK(int, 0, xfrm_policy_lookup, struct xfrm_sec_ctx *ctx, u32 fl_secid) LSM_HOOK(int, 1, xfrm_state_pol_flow_match, struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic) LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid, diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index d5a983d65f05..44365aab043c 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -65,14 +65,10 @@ enum cmdq_code { CMDQ_CODE_LOGIC = 0xa0, }; -enum cmdq_cb_status { - CMDQ_CB_NORMAL = 0, - CMDQ_CB_ERROR -}; - struct cmdq_cb_data { - enum cmdq_cb_status sta; + int sta; void *data; + struct cmdq_pkt *pkt; }; typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 552309342c38..cbf46f56d105 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -30,7 +30,9 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NONE: no special request * @MEMBLOCK_HOTPLUG: hotpluggable region * @MEMBLOCK_MIRROR: mirrored region - * @MEMBLOCK_NOMAP: don't add to kernel direct mapping + * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as + * reserved in the memory map; refer to memblock_mark_nomap() description + * for further details */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 6d66037be646..bfe5c486f4ad 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1619,6 +1619,7 @@ static inline void set_shrinker_bit(struct mem_cgroup *memcg, #endif #ifdef CONFIG_MEMCG_KMEM +bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); @@ -1672,6 +1673,10 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) struct mem_cgroup *mem_cgroup_from_obj(void *p); #else +static inline bool mem_cgroup_kmem_disabled(void) +{ + return true; +} static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 28f32fd00fe9..a7fd2c3ccb77 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -18,18 +18,6 @@ struct vmem_altmap; #ifdef CONFIG_MEMORY_HOTPLUG struct page *pfn_to_online_page(unsigned long pfn); -/* - * Types for free bootmem stored in page->lru.next. These have to be in - * some random range in unsigned long space for debugging purposes. - */ -enum { - MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12, - SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE, - MIX_SECTION_INFO, - NODE_INFO, - MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, -}; - /* Types for control the zone type of onlined and offlined memory */ enum { /* Offline the memory. */ @@ -222,17 +210,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_NUMA */ #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ -#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat); -#else -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} -#endif -extern void put_page_bootmem(struct page *page); -extern void get_page_bootmem(unsigned long ingo, struct page *page, - unsigned long type); - void get_online_mems(void); void put_online_mems(void); @@ -260,10 +237,6 @@ static inline void zone_span_writelock(struct zone *zone) {} static inline void zone_span_writeunlock(struct zone *zone) {} static inline void zone_seqlock_init(struct zone *zone) {} -static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) -{ -} - static inline int try_online_node(int nid) { return 0; diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5f1c74df264d..0aaf91b496e2 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,11 +46,8 @@ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ - union { - short preferred_node; /* preferred */ - nodemask_t nodes; /* interleave/bind */ - /* undefined for default */ - } v; + nodemask_t nodes; /* interleave/bind/perfer */ + union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ @@ -150,7 +147,7 @@ extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); -extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, +extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy); diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 45a79da89c5f..c0e9d35889e8 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -26,7 +26,7 @@ struct vmem_altmap { }; /* - * Specialize ZONE_DEVICE memory into multiple types each having differents + * Specialize ZONE_DEVICE memory into multiple types each has a different * usage. * * MEMORY_DEVICE_PRIVATE: diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 416ee6dd2574..3d43c60b49fa 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -39,10 +39,26 @@ /* struct phy_device dev_flags definitions */ #define MICREL_PHY_50MHZ_CLK 0x00000001 #define MICREL_PHY_FXEN 0x00000002 +#define MICREL_KSZ8_P1_ERRATA 0x00000003 #define MICREL_KSZ9021_EXTREG_CTRL 0xB #define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC #define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104 #define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105 +/* Device specific MII_BMCR (Reg 0) bits */ +/* 1 = HP Auto MDI/MDI-X mode, 0 = Microchip Auto MDI/MDI-X mode */ +#define KSZ886X_BMCR_HP_MDIX BIT(5) +/* 1 = Force MDI (transmit on RXP/RXM pins), 0 = Normal operation + * (transmit on TXP/TXM pins) + */ +#define KSZ886X_BMCR_FORCE_MDI BIT(4) +/* 1 = Disable auto MDI-X */ +#define KSZ886X_BMCR_DISABLE_AUTO_MDIX BIT(3) +#define KSZ886X_BMCR_DISABLE_FAR_END_FAULT BIT(2) +#define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) +#define KSZ886X_BMCR_DISABLE_LED BIT(0) + +#define KSZ886X_CTRL_MDIX_STAT BIT(4) + #endif /* _MICREL_PHY_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4bb4e519e3f5..9b7b7cd3bae9 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -51,6 +51,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +extern void copy_huge_page(struct page *dst, struct page *src); #else static inline void putback_movable_pages(struct list_head *l) {} @@ -77,6 +78,9 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, return -ENOSYS; } +static inline void copy_huge_page(struct page *dst, struct page *src) +{ +} #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION @@ -95,14 +99,9 @@ static inline void __ClearPageMovable(struct page *page) #endif #ifdef CONFIG_NUMA_BALANCING -extern bool pmd_trans_migrating(pmd_t pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); #else -static inline bool pmd_trans_migrating(pmd_t pmd) -{ - return false; -} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { @@ -110,24 +109,6 @@ static inline int migrate_misplaced_page(struct page *page, } #endif /* CONFIG_NUMA_BALANCING */ -#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) -extern int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node); -#else -static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, - struct vm_area_struct *vma, - pmd_t *pmd, pmd_t entry, - unsigned long address, - struct page *page, int node) -{ - return -EAGAIN; -} -#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/ - - #ifdef CONFIG_MIGRATION /* diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 578c4ccae91c..0025913505ab 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1179,6 +1179,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_GENERAL_2 = 0x20, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1220,6 +1221,15 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_GEN_MAX(mdev, cap) \ MLX5_GET(cmd_hca_cap, mdev->caps.hca_max[MLX5_CAP_GENERAL], cap) +#define MLX5_CAP_GEN_2(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_64(mdev, cap) \ + MLX5_GET64(cmd_hca_cap_2, mdev->caps.hca_cur[MLX5_CAP_GENERAL_2], cap) + +#define MLX5_CAP_GEN_2_MAX(mdev, cap) \ + MLX5_GET(cmd_hca_cap_2, mdev->caps.hca_max[MLX5_CAP_GENERAL_2], cap) + #define MLX5_CAP_ETH(mdev, cap) \ MLX5_GET(per_protocol_networking_offload_caps,\ mdev->caps.hca_cur[MLX5_CAP_ETHERNET_OFFLOADS], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f8902bcd91e2..1efe37466969 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -554,6 +554,7 @@ struct mlx5_adev { int idx; }; +struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ struct mlx5_irq_table *irq_table; @@ -606,6 +607,7 @@ struct mlx5_priv { struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; struct mlx5_rl_table rl_table; + struct mlx5_ft_pool *ft_pool; struct mlx5_bfreg_data bfregs; struct mlx5_uars_page *uar; diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index e49d8c0d4f26..cea6ecb4b73e 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -16,6 +16,7 @@ struct mlx5_eq_param { u8 irq_index; int nent; u64 mask[4]; + cpumask_var_t affinity; }; struct mlx5_eq * diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 17109b65c1ac..bc7db2e059eb 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -98,10 +98,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, u16 vport_num); /* Reg C1 usage: - * Reg C1 = < ESW_TUN_ID(12) | ESW_TUN_OPTS(12) | ESW_ZONE_ID(8) > + * Reg C1 = < Reserved(1) | ESW_TUN_ID(12) | ESW_TUN_OPTS(11) | ESW_ZONE_ID(8) > * - * Highest 12 bits of reg c1 is the encapsulation tunnel id, next 12 bits is - * encapsulation tunnel options, and the lowest 8 bits are used for zone id. + * Highest bit is reserved for other offloads as marker bit, next 12 bits of reg c1 + * is the encapsulation tunnel id, next 11 bits is encapsulation tunnel options, + * and the lowest 8 bits are used for zone id. * * Zone id is used to restore CT flow when packet misses on chain. * @@ -109,16 +110,18 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, * on miss and to support inner header rewrite by means of implicit chain 0 * flows. */ +#define ESW_RESERVED_BITS 1 #define ESW_ZONE_ID_BITS 8 -#define ESW_TUN_OPTS_BITS 12 +#define ESW_TUN_OPTS_BITS 11 #define ESW_TUN_ID_BITS 12 #define ESW_TUN_OPTS_OFFSET ESW_ZONE_ID_BITS #define ESW_TUN_OFFSET ESW_TUN_OPTS_OFFSET #define ESW_ZONE_ID_MASK GENMASK(ESW_ZONE_ID_BITS - 1, 0) -#define ESW_TUN_OPTS_MASK GENMASK(32 - ESW_TUN_ID_BITS - 1, ESW_TUN_OPTS_OFFSET) -#define ESW_TUN_MASK GENMASK(31, ESW_TUN_OFFSET) +#define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET) +#define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET) #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ -#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT 0xFFF /* 0xFFF is a reserved mapping */ +/* 0x7FF is a reserved mapping */ +#define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1f51f4c3b1af..77746f7e35b8 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -87,6 +87,8 @@ enum { FDB_BYPASS_PATH, FDB_TC_OFFLOAD, FDB_FT_OFFLOAD, + FDB_TC_MISS, + FDB_BR_OFFLOAD, FDB_SLOW_PATH, FDB_PER_VPORT, }; @@ -254,10 +256,16 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_pkt_reformat_params { + int type; + u8 param_0; + u8 param_1; + size_t size; + void *data; +}; + struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, + struct mlx5_pkt_reformat_params *params, enum mlx5_flow_namespace_type ns_type); void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, struct mlx5_pkt_reformat *reformat); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index eb86e80e4643..b4546e29e561 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -435,7 +435,10 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_40[0x20]; - u8 reserved_at_60[0x18]; + u8 reserved_at_60[0x2]; + u8 reformat_insert[0x1]; + u8 reformat_remove[0x1]; + u8 reserver_at_64[0x14]; u8 log_max_ft_num[0x8]; u8 reserved_at_80[0x10]; @@ -953,9 +956,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { }; enum { - MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_QP_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, + MLX5_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, + MLX5_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, + MLX5_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, }; struct mlx5_ifc_roce_cap_bits { @@ -1296,23 +1299,12 @@ enum { MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, }; -enum { - MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_SQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_SQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, -}; - -enum { - MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING = 0x0, - MLX5_RQ_TIMESTAMP_FORMAT_CAP_REAL_TIME = 0x1, - MLX5_RQ_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME = 0x2, -}; - struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_0[0x1f]; u8 vhca_resource_manager[0x1]; - u8 reserved_at_20[0x3]; + u8 hca_cap_2[0x1]; + u8 reserved_at_21[0x2]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -1732,6 +1724,17 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_7c0[0x40]; }; +struct mlx5_ifc_cmd_hca_cap_2_bits { + u8 reserved_at_0[0xa0]; + + u8 max_reformat_insert_size[0x8]; + u8 max_reformat_insert_offset[0x8]; + u8 max_reformat_remove_size[0x8]; + u8 max_reformat_remove_offset[0x8]; + + u8 reserved_at_c0[0x740]; +}; + enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_VPORT = 0x0, MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, @@ -2944,9 +2947,9 @@ enum { }; enum { - MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_QPC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, + MLX5_TIMESTAMP_FORMAT_DEFAULT = 0x1, + MLX5_TIMESTAMP_FORMAT_REAL_TIME = 0x2, }; struct mlx5_ifc_qpc_bits { @@ -3105,6 +3108,7 @@ struct mlx5_ifc_roce_addr_layout_bits { union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; + struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; struct mlx5_ifc_odp_cap_bits odp_cap; struct mlx5_ifc_atomic_caps_bits atomic_caps; struct mlx5_ifc_roce_cap_bits roce_cap; @@ -3396,12 +3400,6 @@ enum { MLX5_SQC_STATE_ERR = 0x3, }; -enum { - MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_SQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, -}; - struct mlx5_ifc_sqc_bits { u8 rlky[0x1]; u8 cd_master[0x1]; @@ -3507,12 +3505,6 @@ enum { MLX5_RQC_STATE_ERR = 0x3, }; -enum { - MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING = 0x0, - MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT = 0x1, - MLX5_RQC_TIMESTAMP_FORMAT_REAL_TIME = 0x2, -}; - struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; u8 delay_drop_en[0x1]; @@ -3790,8 +3782,8 @@ struct mlx5_ifc_eqc_bits { u8 reserved_at_80[0x20]; - u8 reserved_at_a0[0x18]; - u8 intr[0x8]; + u8 reserved_at_a0[0x14]; + u8 intr[0xc]; u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; @@ -5785,12 +5777,14 @@ struct mlx5_ifc_query_eq_in_bits { }; struct mlx5_ifc_packet_reformat_context_in_bits { - u8 reserved_at_0[0x5]; - u8 reformat_type[0x3]; - u8 reserved_at_8[0xe]; + u8 reformat_type[0x8]; + u8 reserved_at_8[0x4]; + u8 reformat_param_0[0x4]; + u8 reserved_at_10[0x6]; u8 reformat_data_size[0xa]; - u8 reserved_at_20[0x10]; + u8 reformat_param_1[0x8]; + u8 reserved_at_28[0x8]; u8 reformat_data[2][0x8]; u8 more_reformat_data[][0x8]; @@ -5830,12 +5824,20 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1, + MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7, + MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9, +}; + enum mlx5_reformat_ctx_type { MLX5_REFORMAT_TYPE_L2_TO_VXLAN = 0x0, MLX5_REFORMAT_TYPE_L2_TO_NVGRE = 0x1, MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2, MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3, MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4, + MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf, + MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10, }; struct mlx5_ifc_alloc_packet_reformat_context_in_bits { @@ -5956,6 +5958,8 @@ enum { MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM = 0x59, MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM = 0x5B, MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME = 0x5D, + MLX5_ACTION_IN_FIELD_OUT_EMD_47_32 = 0x6F, + MLX5_ACTION_IN_FIELD_OUT_EMD_31_0 = 0x70, }; struct mlx5_ifc_alloc_modify_header_context_out_bits { @@ -11055,6 +11059,11 @@ struct mlx5_ifc_create_sampler_obj_in_bits { struct mlx5_ifc_sampler_obj_bits sampler_object; }; +struct mlx5_ifc_query_sampler_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_sampler_obj_bits sampler_object; +}; + enum { MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_128 = 0x0, MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_KEY_SIZE_256 = 0x1, diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index b7deb790f257..61e48d459b23 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -550,8 +550,8 @@ static inline const char *mlx5_qp_state_str(int state) static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) { return !MLX5_CAP_ROCE(dev, qp_ts_format) ? - MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : - MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; + MLX5_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_TIMESTAMP_FORMAT_DEFAULT; } #endif /* MLX5_QP_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 6d0f827ca4eb..788a0b1323d0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -125,16 +125,6 @@ extern int mmap_rnd_compat_bits __read_mostly; #endif /* - * With CONFIG_CFI_CLANG, the compiler replaces function addresses in - * instrumented C code with jump table addresses. Architectures that - * support CFI can define this macro to return the actual function address - * when needed. - */ -#ifndef function_nocfi -#define function_nocfi(x) (x) -#endif - -/* * To prevent common memory management code establishing * a zero page mapping on a read fault. * This macro should be defined within <asm/pgtable.h>. @@ -155,7 +145,7 @@ extern int mmap_rnd_compat_bits __read_mostly; /* This function must be updated when the size of struct page grows above 80 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can - * combine write statments if they are both assignments and can be reordered, + * combine write statements if they are both assignments and can be reordered, * this can result in several of the writes here being dropped. */ #define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) @@ -550,7 +540,12 @@ struct vm_fault { pud_t *pud; /* Pointer to pud entry matching * the 'address' */ - pte_t orig_pte; /* Value of PTE at the time of fault */ + union { + pte_t orig_pte; /* Value of PTE at the time of fault */ + pmd_t orig_pmd; /* Value of PMD at the time of fault, + * used by PMD fault only. + */ + }; struct page *cow_page; /* Page handler may use for COW fault */ struct page *page; /* ->fault handlers should return a @@ -1672,10 +1667,11 @@ struct address_space *page_mapping(struct page *page); static inline bool page_is_pfmemalloc(const struct page *page) { /* - * Page index cannot be this large so this must be - * a pfmemalloc page. + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. */ - return page->index == -1UL; + return (uintptr_t)page->lru.next & BIT(1); } /* @@ -1684,12 +1680,12 @@ static inline bool page_is_pfmemalloc(const struct page *page) */ static inline void set_page_pfmemalloc(struct page *page) { - page->index = -1UL; + page->lru.next = (void *)BIT(1); } static inline void clear_page_pfmemalloc(struct page *page) { - page->index = 0; + page->lru.next = NULL; } /* @@ -3076,6 +3072,11 @@ static inline void print_vma_addr(char *prefix, unsigned long rip) } #endif +int vmemmap_remap_free(unsigned long start, unsigned long end, + unsigned long reuse); +int vmemmap_remap_alloc(unsigned long start, unsigned long end, + unsigned long reuse, gfp_t gfp_mask); + void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index b66d0225414e..52bbd2b7cb46 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -97,6 +97,13 @@ struct page { }; struct { /* page_pool used by netstack */ /** + * @pp_magic: magic value to avoid recycling non + * page_pool allocated pages. + */ + unsigned long pp_magic; + struct page_pool *pp; + unsigned long _pp_mapping_pad; + /** * @dma_addr: might require a 64-bit value on * 32-bit architectures. */ @@ -397,7 +404,7 @@ struct mm_struct { unsigned long mmap_base; /* base of mmap area */ unsigned long mmap_legacy_base; /* base of mmap area in bottom-up allocations */ #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES - /* Base adresses for compatible mmap() */ + /* Base addresses for compatible mmap() */ unsigned long mmap_compat_base; unsigned long mmap_compat_legacy_base; #endif diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 1a6a9eb6d3fa..6692da8d121d 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -41,7 +41,12 @@ struct mmu_interval_notifier; * * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal * a device driver to possibly ignore the invalidation if the - * migrate_pgmap_owner field matches the driver's device private pgmap owner. + * owner field matches the driver's device private pgmap owner. + * + * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no + * longer have exclusive access to the page. When sent during creation of an + * exclusive range the owner will be initialised to the value provided by the + * caller of make_device_exclusive_range(), otherwise the owner will be NULL. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, @@ -51,6 +56,7 @@ enum mmu_notifier_event { MMU_NOTIFY_SOFT_DIRTY, MMU_NOTIFY_RELEASE, MMU_NOTIFY_MIGRATE, + MMU_NOTIFY_EXCLUSIVE, }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) @@ -269,7 +275,7 @@ struct mmu_notifier_range { unsigned long end; unsigned flags; enum mmu_notifier_event event; - void *migrate_pgmap_owner; + void *owner; }; static inline int mm_has_notifiers(struct mm_struct *mm) @@ -521,14 +527,14 @@ static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, range->flags = flags; } -static inline void mmu_notifier_range_init_migrate( - struct mmu_notifier_range *range, unsigned int flags, +static inline void mmu_notifier_range_init_owner( + struct mmu_notifier_range *range, + enum mmu_notifier_event event, unsigned int flags, struct vm_area_struct *vma, struct mm_struct *mm, - unsigned long start, unsigned long end, void *pgmap) + unsigned long start, unsigned long end, void *owner) { - mmu_notifier_range_init(range, MMU_NOTIFY_MIGRATE, flags, vma, mm, - start, end); - range->migrate_pgmap_owner = pgmap; + mmu_notifier_range_init(range, event, flags, vma, mm, start, end); + range->owner = owner; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ @@ -655,8 +661,8 @@ static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) -#define mmu_notifier_range_init_migrate(range, flags, vma, mm, start, end, \ - pgmap) \ +#define mmu_notifier_range_init_owner(range, event, flags, vma, mm, start, \ + end, owner) \ _mmu_notifier_range_init(range, start, end) static inline bool diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 265a32e1ff74..fcb535560028 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -114,7 +114,7 @@ static inline bool free_area_empty(struct free_area *area, int migratetype) struct pglist_data; /* - * Add a wild amount of padding here to ensure datas fall into separate + * Add a wild amount of padding here to ensure data fall into separate * cachelines. There are very few zone structures in the machine, so space * consumption is not a concern here. */ @@ -1064,7 +1064,10 @@ extern char numa_zonelist_order[]; #ifndef CONFIG_NUMA extern struct pglist_data contig_page_data; -#define NODE_DATA(nid) (&contig_page_data) +static inline struct pglist_data *NODE_DATA(int nid) +{ + return &contig_page_data; +} #define NODE_MEM_MAP(nid) mem_map #else /* CONFIG_NUMA */ @@ -1445,10 +1448,30 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) #endif #ifndef CONFIG_HAVE_ARCH_PFN_VALID +/** + * pfn_valid - check if there is a valid memory map entry for a PFN + * @pfn: the page frame number to check + * + * Check if there is a valid memory map entry aka struct page for the @pfn. + * Note, that availability of the memory map entry does not imply that + * there is actual usable memory at that @pfn. The struct page may + * represent a hole or an unusable page frame. + * + * Return: 1 for PFNs that have memory map entries and 0 otherwise + */ static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + /* + * Ensure the upper PAGE_SHIFT bits are clear in the + * pfn. Else it might lead to false positives when + * some of the upper bits are set, but the lower bits + * match a valid pfn. + */ + if (PHYS_PFN(PFN_PHYS(pfn)) != pfn) + return 0; + if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __nr_to_section(pfn_to_section_nr(pfn)); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 7d45b5f989b0..8e291cfdaf06 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -447,6 +447,7 @@ struct hv_vmbus_device_id { struct rpmsg_device_id { char name[RPMSG_NAME_SIZE]; + kernel_ulong_t driver_data; }; /* i2c */ diff --git a/include/linux/mpi.h b/include/linux/mpi.h index 3e5358f4de2f..eb0d1c1db208 100644 --- a/include/linux/mpi.h +++ b/include/linux/mpi.h @@ -200,7 +200,7 @@ struct mpi_ec_ctx { unsigned int nbits; /* Number of bits. */ /* Domain parameters. Note that they may not all be set and if set - * the MPIs may be flaged as constant. + * the MPIs may be flagged as constant. */ MPI p; /* Prime specifying the field GF(p). */ MPI a; /* First coefficient of the Weierstrass equation. */ @@ -267,7 +267,7 @@ int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx); /** * mpi_get_size() - returns max size required to store the number * - * @a: A multi precision integer for which we want to allocate a bufer + * @a: A multi precision integer for which we want to allocate a buffer * * Return: size required to store the number */ diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h index f41387a8969f..6b3267b49755 100644 --- a/include/linux/net/intel/i40e_client.h +++ b/include/linux/net/intel/i40e_client.h @@ -4,6 +4,8 @@ #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ +#include <linux/auxiliary_bus.h> + #define I40E_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the @@ -48,7 +50,7 @@ struct i40e_qv_info { struct i40e_qvlist_info { u32 num_vectors; - struct i40e_qv_info qv_info[1]; + struct i40e_qv_info qv_info[]; }; @@ -78,6 +80,7 @@ struct i40e_info { u8 lanmac[6]; struct net_device *netdev; struct pci_dev *pcidev; + struct auxiliary_device *aux_dev; u8 __iomem *hw_addr; u8 fid; /* function id, PF id or VF id */ #define I40E_CLIENT_FTYPE_PF 0 @@ -100,6 +103,11 @@ struct i40e_info { u32 fw_build; /* firmware build number */ }; +struct i40e_auxiliary_device { + struct auxiliary_device aux_dev; + struct i40e_info *ldev; +}; + #define I40E_CLIENT_RESET_LEVEL_PF 1 #define I40E_CLIENT_RESET_LEVEL_CORE 2 #define I40E_CLIENT_VSI_FLAG_TCP_ENABLE BIT(1) @@ -187,8 +195,7 @@ static inline bool i40e_client_is_registered(struct i40e_client *client) return test_bit(__I40E_CLIENT_REGISTERED, &client->state); } -/* used by clients */ -int i40e_register_client(struct i40e_client *client); -int i40e_unregister_client(struct i40e_client *client); +void i40e_client_device_register(struct i40e_info *ldev, struct i40e_client *client); +void i40e_client_device_unregister(struct i40e_info *ldev); #endif /* _I40E_CLIENT_H_ */ diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h new file mode 100644 index 000000000000..e32f6712aee0 --- /dev/null +++ b/include/linux/net/intel/iidc.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021, Intel Corporation. */ + +#ifndef _IIDC_H_ +#define _IIDC_H_ + +#include <linux/auxiliary_bus.h> +#include <linux/dcbnl.h> +#include <linux/device.h> +#include <linux/if_ether.h> +#include <linux/kernel.h> +#include <linux/netdevice.h> + +enum iidc_event_type { + IIDC_EVENT_BEFORE_MTU_CHANGE, + IIDC_EVENT_AFTER_MTU_CHANGE, + IIDC_EVENT_BEFORE_TC_CHANGE, + IIDC_EVENT_AFTER_TC_CHANGE, + IIDC_EVENT_CRIT_ERR, + IIDC_EVENT_NBITS /* must be last */ +}; + +enum iidc_reset_type { + IIDC_PFR, + IIDC_CORER, + IIDC_GLOBR, +}; + +#define IIDC_MAX_USER_PRIORITY 8 + +/* Struct to hold per RDMA Qset info */ +struct iidc_rdma_qset_params { + /* Qset TEID returned to the RDMA driver in + * ice_add_rdma_qset and used by RDMA driver + * for calls to ice_del_rdma_qset + */ + u32 teid; /* Qset TEID */ + u16 qs_handle; /* RDMA driver provides this */ + u16 vport_id; /* VSI index */ + u8 tc; /* TC branch the Qset should belong to */ +}; + +struct iidc_qos_info { + u64 tc_ctx; + u8 rel_bw; + u8 prio_type; + u8 egress_virt_up; + u8 ingress_virt_up; +}; + +/* Struct to pass QoS info */ +struct iidc_qos_params { + struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS]; + u8 up2tc[IIDC_MAX_USER_PRIORITY]; + u8 vport_relative_bw; + u8 vport_priority_type; + u8 num_tc; +}; + +struct iidc_event { + DECLARE_BITMAP(type, IIDC_EVENT_NBITS); + u32 reg; +}; + +struct ice_pf; + +int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset); +int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); +int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); +void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); + +#define IIDC_RDMA_ROCE_NAME "roce" + +/* Structure representing auxiliary driver tailored information about the core + * PCI dev, each auxiliary driver using the IIDC interface will have an + * instance of this struct dedicated to it. + */ + +struct iidc_auxiliary_dev { + struct auxiliary_device adev; + struct ice_pf *pf; +}; + +/* structure representing the auxiliary driver. This struct is to be + * allocated and populated by the auxiliary driver's owner. The core PCI + * driver will access these ops by performing a container_of on the + * auxiliary_device->dev.driver. + */ +struct iidc_auxiliary_drv { + struct auxiliary_driver adrv; + /* This event_handler is meant to be a blocking call. For instance, + * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not + * return until the auxiliary driver is ready for the MTU change to + * happen. + */ + void (*event_handler)(struct ice_pf *pf, struct iidc_event *event); +}; + +#endif /* _IIDC_H_*/ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 3de38d6a0aea..2c6b9e416225 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -93,7 +93,7 @@ enum { /* * Add your fresh new feature above and remember to update - * netdev_features_strings[] in net/core/ethtool.c and maybe + * netdev_features_strings[] in net/ethtool/common.c and maybe * some feature mask #defines below. Please also describe it * in Documentation/networking/netdev-features.rst. */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5cbc950b34df..eaf5bb008aa9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4114,7 +4114,7 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev, return NET_RX_DROP; } - skb_scrub_packet(skb, true); + skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } @@ -4187,8 +4187,8 @@ unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); - void netif_carrier_off(struct net_device *dev); +void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index f0f3a8354c3c..3fda1a508733 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -65,8 +65,8 @@ struct nf_hook_ops; struct sock; struct nf_hook_state { - unsigned int hook; - u_int8_t pf; + u8 hook; + u8 pf; struct net_device *in; struct net_device *out; struct sock *sk; @@ -77,12 +77,18 @@ struct nf_hook_state { typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); +enum nf_hook_ops_type { + NF_HOOK_OP_UNDEFINED, + NF_HOOK_OP_NF_TABLES, +}; + struct nf_hook_ops { /* User fills in from here down. */ nf_hookfn *hook; struct net_device *dev; void *priv; - u_int8_t pf; + u8 pf; + enum nf_hook_ops_type hook_ops_type:8; unsigned int hooknum; /* Hooks are ordered in ascending priority. */ int priority; diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h index 515ce53aa20d..241e005f290a 100644 --- a/include/linux/netfilter/nfnetlink.h +++ b/include/linux/netfilter/nfnetlink.h @@ -11,6 +11,7 @@ struct nfnl_info { struct net *net; struct sock *sk; const struct nlmsghdr *nlh; + const struct nfgenmsg *nfmsg; struct netlink_ext_ack *extack; }; diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 07c6ad8f2a02..28d7027cd460 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -36,8 +36,8 @@ struct xt_action_param { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; - int fragoff; unsigned int thoff; + u16 fragoff; bool hotdrop; }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index edcbd60b88b9..b7c4c4130b65 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -636,8 +636,8 @@ struct nvme_lba_range_type { __u8 type; __u8 attributes; __u8 rsvd2[14]; - __u64 slba; - __u64 nlb; + __le64 slba; + __le64 nlb; __u8 guid[16]; __u8 rsvd48[16]; }; @@ -944,6 +944,13 @@ struct nvme_zone_mgmt_recv_cmd { enum { NVME_ZRA_ZONE_REPORT = 0, NVME_ZRASF_ZONE_REPORT_ALL = 0, + NVME_ZRASF_ZONE_STATE_EMPTY = 0x01, + NVME_ZRASF_ZONE_STATE_IMP_OPEN = 0x02, + NVME_ZRASF_ZONE_STATE_EXP_OPEN = 0x03, + NVME_ZRASF_ZONE_STATE_CLOSED = 0x04, + NVME_ZRASF_ZONE_STATE_READONLY = 0x05, + NVME_ZRASF_ZONE_STATE_FULL = 0x06, + NVME_ZRASF_ZONE_STATE_OFFLINE = 0x07, NVME_REPORT_ZONE_PARTIAL = 1, }; @@ -1504,6 +1511,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, NVME_SC_CAP_EXCEEDED = 0x81, diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index 2b05e7f7c238..da633d34ab86 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -72,6 +72,13 @@ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node * return mdiobus_register(mdio); } +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return devm_mdiobus_register(dev, mdio); +} + static inline struct mdio_device *of_mdio_find_device(struct device_node *np) { return NULL; diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h new file mode 100644 index 000000000000..861e606b820f --- /dev/null +++ b/include/linux/once_lite.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ONCE_LITE_H +#define _LINUX_ONCE_LITE_H + +#include <linux/types.h> + +/* Call a function once. Similar to DO_ONCE(), but does not use jump label + * patching via static keys. + */ +#define DO_ONCE_LITE(func, ...) \ + DO_ONCE_LITE_IF(true, func, ##__VA_ARGS__) +#define DO_ONCE_LITE_IF(condition, func, ...) \ + ({ \ + static bool __section(".data.once") __already_done; \ + bool __ret_do_once = !!(condition); \ + \ + if (unlikely(__ret_do_once && !__already_done)) { \ + __already_done = true; \ + func(__VA_ARGS__); \ + } \ + unlikely(__ret_do_once); \ + }) + +#endif /* _LINUX_ONCE_LITE_H */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 458696550028..5922031ffab6 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -704,6 +704,18 @@ PAGEFLAG_FALSE(DoubleMap) #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 @@ -766,9 +778,19 @@ PAGE_TYPE_OPS(Buddy, buddy) * relies on this feature is aware that re-onlining the memory block will * require to re-set the pages PageOffline() and not giving them to the * buddy via online_page_callback_t. + * + * There are drivers that mark a page PageOffline() and expect there won't be + * any further access to page content. PFN walkers that read content of random + * pages should check PageOffline() and synchronize with such drivers using + * page_offline_freeze()/page_offline_thaw(). */ PAGE_TYPE_OPS(Offline, offline) +extern void page_offline_freeze(void); +extern void page_offline_thaw(void); +extern void page_offline_begin(void); +extern void page_offline_end(void); + /* * Marks pages in use as page tables. */ diff --git a/include/linux/panic.h b/include/linux/panic.h new file mode 100644 index 000000000000..f5844908a089 --- /dev/null +++ b/include/linux/panic.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_H +#define _LINUX_PANIC_H + +#include <linux/compiler_attributes.h> +#include <linux/types.h> + +struct pt_regs; + +extern long (*panic_blink)(int state); +__printf(1, 2) +void panic(const char *fmt, ...) __noreturn __cold; +void nmi_panic(struct pt_regs *regs, const char *msg); +extern void oops_enter(void); +extern void oops_exit(void); +extern bool oops_may_print(void); + +#ifdef CONFIG_SMP +extern unsigned int sysctl_oops_all_cpu_backtrace; +#else +#define sysctl_oops_all_cpu_backtrace 0 +#endif /* CONFIG_SMP */ + +extern int panic_timeout; +extern unsigned long panic_print; +extern int panic_on_oops; +extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; +extern int panic_on_warn; + +extern unsigned long panic_on_taint; +extern bool panic_on_taint_nousertaint; + +extern int sysctl_panic_on_rcu_stall; +extern int sysctl_max_rcu_stall_to_panic; +extern int sysctl_panic_on_stackoverflow; + +extern bool crash_kexec_post_notifiers; + +/* + * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It + * holds a CPU number which is executing panic() currently. A value of + * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec(). + */ +extern atomic_t panic_cpu; +#define PANIC_CPU_INVALID -1 + +/* + * Only to be used by arch init code. If the user over-wrote the default + * CONFIG_PANIC_TIMEOUT, honor it. + */ +static inline void set_arch_panic_timeout(int timeout, int arch_default_timeout) +{ + if (panic_timeout == arch_default_timeout) + panic_timeout = timeout; +} + +/* This cannot be an enum because some may be used in assembly source. */ +#define TAINT_PROPRIETARY_MODULE 0 +#define TAINT_FORCED_MODULE 1 +#define TAINT_CPU_OUT_OF_SPEC 2 +#define TAINT_FORCED_RMMOD 3 +#define TAINT_MACHINE_CHECK 4 +#define TAINT_BAD_PAGE 5 +#define TAINT_USER 6 +#define TAINT_DIE 7 +#define TAINT_OVERRIDDEN_ACPI_TABLE 8 +#define TAINT_WARN 9 +#define TAINT_CRAP 10 +#define TAINT_FIRMWARE_WORKAROUND 11 +#define TAINT_OOT_MODULE 12 +#define TAINT_UNSIGNED_MODULE 13 +#define TAINT_SOFTLOCKUP 14 +#define TAINT_LIVEPATCH 15 +#define TAINT_AUX 16 +#define TAINT_RANDSTRUCT 17 +#define TAINT_FLAGS_COUNT 18 +#define TAINT_FLAGS_MAX ((1UL << TAINT_FLAGS_COUNT) - 1) + +struct taint_flag { + char c_true; /* character printed when tainted */ + char c_false; /* character printed when not tainted */ + bool module; /* also show as a per-module taint flag */ +}; + +extern const struct taint_flag taint_flags[TAINT_FLAGS_COUNT]; + +enum lockdep_ok { + LOCKDEP_STILL_OK, + LOCKDEP_NOW_UNRELIABLE, +}; + +extern const char *print_tainted(void); +extern void add_taint(unsigned flag, enum lockdep_ok); +extern int test_taint(unsigned flag); +extern unsigned long get_taint(void); + +#endif /* _LINUX_PANIC_H */ diff --git a/include/linux/panic_notifier.h b/include/linux/panic_notifier.h new file mode 100644 index 000000000000..41e32483d7a7 --- /dev/null +++ b/include/linux/panic_notifier.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PANIC_NOTIFIERS_H +#define _LINUX_PANIC_NOTIFIERS_H + +#include <linux/notifier.h> +#include <linux/types.h> + +extern struct atomic_notifier_head panic_notifier_list; + +extern bool crash_kexec_post_notifiers; + +#endif /* _LINUX_PANIC_NOTIFIERS_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 24306504226a..d1f0916c6a37 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -862,6 +862,8 @@ struct module; * MSI-X vectors available for distribution to the VFs. * @err_handler: See Documentation/PCI/pci-error-recovery.rst * @groups: Sysfs attribute groups. + * @dev_groups: Attributes attached to the device that will be + * created once it is bound to the driver. * @driver: Driver model structure. * @dynids: List of dynamically added device IDs. */ @@ -879,6 +881,7 @@ struct pci_driver { u32 (*sriov_get_vf_total_msix)(struct pci_dev *pf); const struct pci_error_handlers *err_handler; const struct attribute_group **groups; + const struct attribute_group **dev_groups; struct device_driver driver; struct pci_dynids dynids; }; diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index 2cb5188a7ef1..add077a81b21 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -10,37 +10,33 @@ #include <linux/phy.h> #include <linux/phylink.h> +#define NXP_SJA1105_XPCS_ID 0x00000010 +#define NXP_SJA1110_XPCS_ID 0x00000020 + /* AN mode */ #define DW_AN_C73 1 #define DW_AN_C37_SGMII 2 +#define DW_2500BASEX 3 -struct mdio_xpcs_args { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); - struct mii_bus *bus; - int addr; - int an_mode; -}; +struct xpcs_id; -struct mdio_xpcs_ops { - int (*validate)(struct mdio_xpcs_args *xpcs, - unsigned long *supported, - struct phylink_link_state *state); - int (*config)(struct mdio_xpcs_args *xpcs, - const struct phylink_link_state *state); - int (*get_state)(struct mdio_xpcs_args *xpcs, - struct phylink_link_state *state); - int (*link_up)(struct mdio_xpcs_args *xpcs, int speed, - phy_interface_t interface); - int (*probe)(struct mdio_xpcs_args *xpcs, phy_interface_t interface); +struct dw_xpcs { + struct mdio_device *mdiodev; + const struct xpcs_id *id; + struct phylink_pcs pcs; }; -#if IS_ENABLED(CONFIG_PCS_XPCS) -struct mdio_xpcs_ops *mdio_xpcs_get_ops(void); -#else -static inline struct mdio_xpcs_ops *mdio_xpcs_get_ops(void) -{ - return NULL; -} -#endif +int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface); +void xpcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, int duplex); +int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface, + unsigned int mode); +void xpcs_validate(struct dw_xpcs *xpcs, unsigned long *supported, + struct phylink_link_state *state); +int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, + int enable); +struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev, + phy_interface_t interface); +void xpcs_destroy(struct dw_xpcs *xpcs); #endif /* __LINUX_PCS_XPCS_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index c32600c9e1ad..e82660f7b9e4 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -29,6 +29,24 @@ #endif /* + * This defines the first usable user address. Platforms + * can override its value with custom FIRST_USER_ADDRESS + * defined in their respective <asm/pgtable.h>. + */ +#ifndef FIRST_USER_ADDRESS +#define FIRST_USER_ADDRESS 0UL +#endif + +/* + * This defines the generic helper for accessing PMD page + * table page. Although platforms can still override this + * via their respective <asm/pgtable.h>. + */ +#ifndef pmd_pgtable +#define pmd_pgtable(pmd) pmd_page(pmd) +#endif + +/* * A page table page can be thought of an array like this: pXd_t[PTRS_PER_PxD] * * The pXx_index() functions return the index of the entry in the page @@ -1379,10 +1397,34 @@ static inline int p4d_clear_huge(p4d_t *p4d) } #endif /* !__PAGETABLE_P4D_FOLDED */ +#ifndef __PAGETABLE_PUD_FOLDED int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot); -int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pud_clear_huge(pud_t *pud); +#else +static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pud_clear_huge(pud_t *pud) +{ + return 0; +} +#endif /* !__PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_PMD_FOLDED +int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot); int pmd_clear_huge(pmd_t *pmd); +#else +static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} +static inline int pmd_clear_huge(pmd_t *pmd) +{ + return 0; +} +#endif /* !__PAGETABLE_PMD_FOLDED */ + int p4d_free_pud_page(p4d_t *p4d, unsigned long addr); int pud_free_pmd_page(pud_t *pud, unsigned long addr); int pmd_free_pte_page(pmd_t *pmd, unsigned long addr); diff --git a/include/linux/phy.h b/include/linux/phy.h index 852743f07e3e..3b80dc3ed68b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -93,6 +93,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface * @PHY_INTERFACE_MODE_RMII: Reduced Media Independent Interface + * @PHY_INTERFACE_MODE_REVRMII: Reduced Media Independent Interface in PHY role * @PHY_INTERFACE_MODE_RGMII: Reduced gigabit media-independent interface * @PHY_INTERFACE_MODE_RGMII_ID: RGMII with Internal RX+TX delay * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay @@ -111,6 +112,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RXAUI: Reduced XAUI * @PHY_INTERFACE_MODE_XAUI: 10 Gigabit Attachment Unit Interface * @PHY_INTERFACE_MODE_10GBASER: 10G BaseR + * @PHY_INTERFACE_MODE_25GBASER: 25G BaseR * @PHY_INTERFACE_MODE_USXGMII: Universal Serial 10GE MII * @PHY_INTERFACE_MODE_10GKR: 10GBASE-KR - with Clause 73 AN * @PHY_INTERFACE_MODE_MAX: Book keeping @@ -126,6 +128,7 @@ typedef enum { PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, + PHY_INTERFACE_MODE_REVRMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, @@ -145,6 +148,7 @@ typedef enum { PHY_INTERFACE_MODE_XAUI, /* 10GBASE-R, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GBASER, + PHY_INTERFACE_MODE_25GBASER, PHY_INTERFACE_MODE_USXGMII, /* 10GBASE-KR - with Clause 73 AN */ PHY_INTERFACE_MODE_10GKR, @@ -185,6 +189,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; + case PHY_INTERFACE_MODE_REVRMII: + return "rev-rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: @@ -219,6 +225,8 @@ static inline const char *phy_modes(phy_interface_t interface) return "xaui"; case PHY_INTERFACE_MODE_10GBASER: return "10gbase-r"; + case PHY_INTERFACE_MODE_25GBASER: + return "25gbase-r"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; case PHY_INTERFACE_MODE_10GKR: @@ -1373,10 +1381,42 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); +struct phy_device *device_phy_find_device(struct device *dev); +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + return 0; +} +static inline +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + return 0; +} + +static inline +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + return NULL; +} + +static inline struct phy_device *device_phy_find_device(struct device *dev) +{ + return NULL; +} + +static inline +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fd2acfd9b597..afb3ded0b691 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags); void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index 5a96602a3316..eee0e3948537 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -81,28 +81,28 @@ struct pinctrl_map; * passed in the argument on a custom form, else just use argument 1 * to indicate low power mode, argument 0 turns low power mode off. * @PIN_CONFIG_MODE_PWM: this will configure the pin for PWM + * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a + * value on the line. Use argument 1 to indicate high level, argument 0 to + * indicate low level. (Please see Documentation/driver-api/pin-control.rst, + * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_OUTPUT_ENABLE: this will enable the pin's output mode * without driving a value there. For most platforms this reduces to * enable the output buffers and then let the pin controller current * configuration (eg. the currently selected mux function) drive values on * the line. Use argument 1 to enable output mode, argument 0 to disable * it. - * @PIN_CONFIG_OUTPUT: this will configure the pin as an output and drive a - * value on the line. Use argument 1 to indicate high level, argument 0 to - * indicate low level. (Please see Documentation/driver-api/pin-control.rst, - * section "GPIO mode pitfalls" for a discussion around this parameter.) * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells * the driver which alternative power source to use. - * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. - * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to - * this parameter (on a custom format) tells the driver which alternative - * slew rate to use. * @PIN_CONFIG_SKEW_DELAY: if the pin has programmable skew rate (on inputs) * or latch delay (on outputs) this parameter (in a custom format) * specifies the clock skew or latch delay. It typically controls how * many double inverters are put in front of the line. + * @PIN_CONFIG_SLEEP_HARDWARE_STATE: indicate this is sleep related state. + * @PIN_CONFIG_SLEW_RATE: if the pin can select slew rate, the argument to + * this parameter (on a custom format) tells the driver which alternative + * slew rate to use. * @PIN_CONFIG_END: this is the last enumerator for pin configurations, if * you need to pass in custom configurations to the pin controller, use * PIN_CONFIG_END+1 as the base offset. @@ -127,13 +127,13 @@ enum pin_config_param { PIN_CONFIG_INPUT_SCHMITT_ENABLE, PIN_CONFIG_MODE_LOW_POWER, PIN_CONFIG_MODE_PWM, - PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_OUTPUT, + PIN_CONFIG_OUTPUT_ENABLE, PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, + PIN_CONFIG_SKEW_DELAY, PIN_CONFIG_SLEEP_HARDWARE_STATE, PIN_CONFIG_SLEW_RATE, - PIN_CONFIG_SKEW_DELAY, PIN_CONFIG_END = 0x7F, PIN_CONFIG_MAX = 0xFF, }; diff --git a/include/linux/poison.h b/include/linux/poison.h index aff1c9250c82..d62ef5a6b4e9 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -78,4 +78,7 @@ /********** security/ **********/ #define KEY_DESTROY 0xbd +/********** net/core/page_pool.c **********/ +#define PP_SIGNATURE (0x40 + POISON_POINTER_DELTA) + #endif diff --git a/include/linux/printk.h b/include/linux/printk.h index d796183f26c9..e834d78f0478 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -8,6 +8,7 @@ #include <linux/linkage.h> #include <linux/cache.h> #include <linux/ratelimit_types.h> +#include <linux/once_lite.h> extern const char linux_banner[]; extern const char linux_proc_banner[]; @@ -482,27 +483,9 @@ extern int kptr_restrict; #ifdef CONFIG_PRINTK #define printk_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk, fmt, ##__VA_ARGS__) #define printk_deferred_once(fmt, ...) \ -({ \ - static bool __section(".data.once") __print_once; \ - bool __ret_print_once = !__print_once; \ - \ - if (!__print_once) { \ - __print_once = true; \ - printk_deferred(fmt, ##__VA_ARGS__); \ - } \ - unlikely(__ret_print_once); \ -}) + DO_ONCE_LITE(printk_deferred, fmt, ##__VA_ARGS__) #else #define printk_once(fmt, ...) \ no_printk(fmt, ##__VA_ARGS__) diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 51d7f1b8b32a..aba237c0b3a2 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -186,6 +186,32 @@ struct ptp_clock_event { }; }; +/** + * scaled_ppm_to_ppb() - convert scaled ppm to ppb + * + * @ppm: Parts per million, but with a 16 bit binary fractional field + */ +static inline long scaled_ppm_to_ppb(long ppm) +{ + /* + * The 'freq' field in the 'struct timex' is in parts per + * million, but with a 16 bit binary fractional field. + * + * We want to calculate + * + * ppb = scaled_ppm * 1000 / 2^16 + * + * which simplifies to + * + * ppb = scaled_ppm * 125 / 2^13 + */ + s64 ppb = 1 + ppm; + + ppb *= 125; + ppb >>= 13; + return (long)ppb; +} + #if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) /** @@ -230,14 +256,6 @@ extern void ptp_clock_event(struct ptp_clock *ptp, extern int ptp_clock_index(struct ptp_clock *ptp); /** - * scaled_ppm_to_ppb() - convert scaled ppm to ppb - * - * @ppm: Parts per million, but with a 16 bit binary fractional field - */ - -extern long scaled_ppm_to_ppb(long ppm); - -/** * ptp_find_pin() - obtain the pin index of a given auxiliary function * * The caller must hold ptp_clock::pincfg_mux. Drivers do not have diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 977807e1be53..0a3807e927c5 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -702,7 +702,7 @@ enum mf_mode { /* Per-protocol connection types */ enum protocol_type { - PROTOCOLID_ISCSI, + PROTOCOLID_TCP_ULP, PROTOCOLID_FCOE, PROTOCOLID_ROCE, PROTOCOLID_CORE, diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h new file mode 100644 index 000000000000..5a2ab0606308 --- /dev/null +++ b/include/linux/qed/nvmetcp_common.h @@ -0,0 +1,531 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef __NVMETCP_COMMON__ +#define __NVMETCP_COMMON__ + +#include "tcp_common.h" +#include <linux/nvme-tcp.h> + +#define NVMETCP_SLOW_PATH_LAYER_CODE (6) +#define NVMETCP_WQE_NUM_SGES_SLOWIO (0xf) + +/* NVMeTCP firmware function init parameters */ +struct nvmetcp_spe_func_init { + __le16 half_way_close_timeout; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 ll2_rx_queue_id; + u8 flags; +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_COUNTERS_EN_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_SPE_FUNC_INIT_NVMETCP_MODE_SHIFT 1 +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_MASK 0x3F +#define NVMETCP_SPE_FUNC_INIT_RESERVED0_SHIFT 2 + u8 debug_flags; + __le16 reserved1; + u8 params; +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_MAX_SYN_RT_SHIFT 0 +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_MASK 0xF +#define NVMETCP_SPE_FUNC_INIT_RESERVED1_SHIFT 4 + u8 reserved2[5]; + struct scsi_init_func_params func_params; + struct scsi_init_func_queues q_params; +}; + +/* NVMeTCP init params passed by driver to FW in NVMeTCP init ramrod. */ +struct nvmetcp_init_ramrod_params { + struct nvmetcp_spe_func_init nvmetcp_init_spe; + struct tcp_init_params tcp_init; +}; + +/* NVMeTCP Ramrod Command IDs */ +enum nvmetcp_ramrod_cmd_id { + NVMETCP_RAMROD_CMD_ID_UNUSED = 0, + NVMETCP_RAMROD_CMD_ID_INIT_FUNC = 1, + NVMETCP_RAMROD_CMD_ID_DESTROY_FUNC = 2, + NVMETCP_RAMROD_CMD_ID_OFFLOAD_CONN = 3, + NVMETCP_RAMROD_CMD_ID_UPDATE_CONN = 4, + NVMETCP_RAMROD_CMD_ID_TERMINATION_CONN = 5, + NVMETCP_RAMROD_CMD_ID_CLEAR_SQ = 6, + MAX_NVMETCP_RAMROD_CMD_ID +}; + +struct nvmetcp_glbl_queue_entry { + struct regpair cq_pbl_addr; + struct regpair reserved; +}; + +/* NVMeTCP conn level EQEs */ +enum nvmetcp_eqe_opcode { + NVMETCP_EVENT_TYPE_INIT_FUNC = 0, /* Response after init Ramrod */ + NVMETCP_EVENT_TYPE_DESTROY_FUNC, /* Response after destroy Ramrod */ + NVMETCP_EVENT_TYPE_OFFLOAD_CONN,/* Response after option 2 offload Ramrod */ + NVMETCP_EVENT_TYPE_UPDATE_CONN, /* Response after update Ramrod */ + NVMETCP_EVENT_TYPE_CLEAR_SQ, /* Response after clear sq Ramrod */ + NVMETCP_EVENT_TYPE_TERMINATE_CONN, /* Response after termination Ramrod */ + NVMETCP_EVENT_TYPE_RESERVED0, + NVMETCP_EVENT_TYPE_RESERVED1, + NVMETCP_EVENT_TYPE_ASYN_CONNECT_COMPLETE, /* Connect completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_TERMINATE_DONE, /* Termination completed (A-syn EQE) */ + NVMETCP_EVENT_TYPE_START_OF_ERROR_TYPES = 10, /* Separate EQs from err EQs */ + NVMETCP_EVENT_TYPE_ASYN_ABORT_RCVD, /* TCP RST packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_CLOSE_RCVD, /* TCP FIN packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_SYN_RCVD, /* TCP SYN+ACK packet receive (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_TIME, /* TCP max retransmit time (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_RT_CNT, /* TCP max retransmit count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_MAX_KA_PROBES_CNT, /* TCP ka probes count (A-syn EQE) */ + NVMETCP_EVENT_TYPE_ASYN_FIN_WAIT2, /* TCP fin wait 2 (A-syn EQE) */ + NVMETCP_EVENT_TYPE_NVMETCP_CONN_ERROR, /* NVMeTCP error response (A-syn EQE) */ + NVMETCP_EVENT_TYPE_TCP_CONN_ERROR, /* NVMeTCP error - tcp error (A-syn EQE) */ + MAX_NVMETCP_EQE_OPCODE +}; + +struct nvmetcp_conn_offload_section { + struct regpair cccid_itid_table_addr; /* CCCID to iTID table address */ + __le16 cccid_max_range; /* CCCID max value - used for validation */ + __le16 reserved[3]; +}; + +/* NVMe TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod */ +struct nvmetcp_conn_offload_params { + struct regpair sq_pbl_addr; + struct regpair r2tq_pbl_addr; + struct regpair xhq_pbl_addr; + struct regpair uhq_pbl_addr; + __le16 physical_q0; + __le16 physical_q1; + u8 flags; +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TCP_ON_CHIP_1B_SHIFT 0 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_TARGET_MODE_SHIFT 1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESTRICTED_MODE_SHIFT 2 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_MASK 0x1 +#define NVMETCP_CONN_OFFLOAD_PARAMS_NVMETCP_MODE_SHIFT 3 +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_MASK 0xF +#define NVMETCP_CONN_OFFLOAD_PARAMS_RESERVED1_SHIFT 4 + u8 default_cq; + __le16 reserved0; + __le32 reserved1; + __le32 initial_ack; + + struct nvmetcp_conn_offload_section nvmetcp; /* NVMe/TCP section */ +}; + +/* NVMe TCP and TCP connection offload params passed by driver to FW in NVMeTCP offload ramrod. */ +struct nvmetcp_spe_conn_offload { + __le16 reserved; + __le16 conn_id; + __le32 fw_cid; + struct nvmetcp_conn_offload_params nvmetcp; + struct tcp_offload_params_opt2 tcp; +}; + +/* NVMeTCP connection update params passed by driver to FW in NVMETCP update ramrod. */ +struct nvmetcp_conn_update_ramrod_params { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 flags; +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_HD_EN_SHIFT 0 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_DD_EN_SHIFT 1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED0_SHIFT 2 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED1_DATA_SHIFT 3 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED2_SHIFT 4 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED3_SHIFT 5 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED4_SHIFT 6 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_MASK 0x1 +#define NVMETCP_CONN_UPDATE_RAMROD_PARAMS_RESERVED5_SHIFT 7 + u8 reserved3[3]; + __le32 max_seq_size; + __le32 max_send_pdu_length; + __le32 max_recv_pdu_length; + __le32 first_seq_length; + __le32 reserved4[5]; +}; + +/* NVMeTCP connection termination request */ +struct nvmetcp_spe_conn_termination { + __le16 reserved0; + __le16 conn_id; + __le32 reserved1; + u8 abortive; + u8 reserved2[7]; + struct regpair reserved3; + struct regpair reserved4; +}; + +struct nvmetcp_dif_flags { + u8 flags; +}; + +enum nvmetcp_wqe_type { + NVMETCP_WQE_TYPE_NORMAL, + NVMETCP_WQE_TYPE_TASK_CLEANUP, + NVMETCP_WQE_TYPE_MIDDLE_PATH, + NVMETCP_WQE_TYPE_IC, + MAX_NVMETCP_WQE_TYPE +}; + +struct nvmetcp_wqe { + __le16 task_id; + u8 flags; +#define NVMETCP_WQE_WQE_TYPE_MASK 0x7 /* [use nvmetcp_wqe_type] */ +#define NVMETCP_WQE_WQE_TYPE_SHIFT 0 +#define NVMETCP_WQE_NUM_SGES_MASK 0xF +#define NVMETCP_WQE_NUM_SGES_SHIFT 3 +#define NVMETCP_WQE_RESPONSE_MASK 0x1 +#define NVMETCP_WQE_RESPONSE_SHIFT 7 + struct nvmetcp_dif_flags prot_flags; + __le32 contlen_cdbsize; +#define NVMETCP_WQE_CONT_LEN_MASK 0xFFFFFF +#define NVMETCP_WQE_CONT_LEN_SHIFT 0 +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_MASK 0xFF +#define NVMETCP_WQE_CDB_SIZE_OR_NVMETCP_CMD_SHIFT 24 +}; + +struct nvmetcp_host_cccid_itid_entry { + __le16 itid; +}; + +struct nvmetcp_connect_done_results { + __le16 icid; + __le16 conn_id; + struct tcp_ulp_connect_done_params params; +}; + +struct nvmetcp_eqe_data { + __le16 icid; + __le16 conn_id; + __le16 reserved; + u8 error_code; + u8 error_pdu_opcode_reserved; +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_MASK 0x3F +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_SHIFT 0 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_MASK 0x1 +#define NVMETCP_EQE_DATA_ERROR_PDU_OPCODE_VALID_SHIFT 6 +#define NVMETCP_EQE_DATA_RESERVED0_MASK 0x1 +#define NVMETCP_EQE_DATA_RESERVED0_SHIFT 7 +}; + +enum nvmetcp_task_type { + NVMETCP_TASK_TYPE_HOST_WRITE, + NVMETCP_TASK_TYPE_HOST_READ, + NVMETCP_TASK_TYPE_INIT_CONN_REQUEST, + NVMETCP_TASK_TYPE_RESERVED0, + NVMETCP_TASK_TYPE_CLEANUP, + NVMETCP_TASK_TYPE_HOST_READ_NO_CQE, + MAX_NVMETCP_TASK_TYPE +}; + +struct nvmetcp_db_data { + u8 params; +#define NVMETCP_DB_DATA_DEST_MASK 0x3 /* destination of doorbell (use enum db_dest) */ +#define NVMETCP_DB_DATA_DEST_SHIFT 0 +#define NVMETCP_DB_DATA_AGG_CMD_MASK 0x3 /* aggregative command to CM (use enum db_agg_cmd_sel) */ +#define NVMETCP_DB_DATA_AGG_CMD_SHIFT 2 +#define NVMETCP_DB_DATA_BYPASS_EN_MASK 0x1 /* enable QM bypass */ +#define NVMETCP_DB_DATA_BYPASS_EN_SHIFT 4 +#define NVMETCP_DB_DATA_RESERVED_MASK 0x1 +#define NVMETCP_DB_DATA_RESERVED_SHIFT 5 +#define NVMETCP_DB_DATA_AGG_VAL_SEL_MASK 0x3 /* aggregative value selection */ +#define NVMETCP_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; /* bit for every DQ counter flags in CM context that DQ can increment */ + __le16 sq_prod; +}; + +struct nvmetcp_fw_nvmf_cqe { + __le32 reserved[4]; +}; + +struct nvmetcp_icresp_mdata { + u8 digest; + u8 cpda; + __le16 pfv; + __le32 maxdata; + __le16 rsvd[4]; +}; + +union nvmetcp_fw_cqe_data { + struct nvmetcp_fw_nvmf_cqe nvme_cqe; + struct nvmetcp_icresp_mdata icresp_mdata; +}; + +struct nvmetcp_fw_cqe { + __le16 conn_id; + u8 cqe_type; + u8 cqe_error_status_bits; +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_MASK 0x7 +#define CQE_ERROR_BITMAP_DIF_ERR_BITS_SHIFT 0 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_MASK 0x1 +#define CQE_ERROR_BITMAP_DATA_DIGEST_ERR_SHIFT 3 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_MASK 0x1 +#define CQE_ERROR_BITMAP_RCV_ON_INVALID_CONN_SHIFT 4 + __le16 itid; + u8 task_type; + u8 fw_dbg_field; + u8 caused_conn_err; + u8 reserved0[3]; + __le32 reserved1; + union nvmetcp_fw_cqe_data cqe_data; + struct regpair task_opaque; + __le32 reserved[6]; +}; + +enum nvmetcp_fw_cqes_type { + NVMETCP_FW_CQE_TYPE_NORMAL = 1, + NVMETCP_FW_CQE_TYPE_RESERVED0, + NVMETCP_FW_CQE_TYPE_RESERVED1, + NVMETCP_FW_CQE_TYPE_CLEANUP, + NVMETCP_FW_CQE_TYPE_DUMMY, + MAX_NVMETCP_FW_CQES_TYPE +}; + +struct ystorm_nvmetcp_task_state { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 resrved0; + __le32 buffer_offset; + __le16 cccid; + struct nvmetcp_dif_flags dif_flags; + u8 flags; +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_LOCAL_COMP_SHIFT 0 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SLOW_IO_SHIFT 1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SET_DIF_OFFSET_SHIFT 2 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_MASK 0x1 +#define YSTORM_NVMETCP_TASK_STATE_SEND_W_RSP_SHIFT 3 +}; + +struct ystorm_nvmetcp_task_rxmit_opt { + __le32 reserved[4]; +}; + +struct nvmetcp_task_hdr { + __le32 reg[18]; +}; + +struct nvmetcp_task_hdr_aligned { + struct nvmetcp_task_hdr task_hdr; + __le32 reserved[2]; /* HSI_COMMENT: Align to QREG */ +}; + +struct e5_tdif_task_context { + __le32 reserved[16]; +}; + +struct e5_rdif_task_context { + __le32 reserved[12]; +}; + +struct ystorm_nvmetcp_task_st_ctx { + struct ystorm_nvmetcp_task_state state; + struct ystorm_nvmetcp_task_rxmit_opt rxmit_opt; + struct nvmetcp_task_hdr_aligned pdu_hdr; +}; + +struct mstorm_nvmetcp_task_st_ctx { + struct scsi_cached_sges data_desc; + struct scsi_sgl_params sgl_params; + __le32 rem_task_size; + __le32 data_buffer_offset; + u8 task_type; + struct nvmetcp_dif_flags dif_flags; + __le16 dif_task_icid; + struct regpair reserved0; + __le32 expected_itt; + __le32 reserved1; +}; + +struct ustorm_nvmetcp_task_st_ctx { + __le32 rem_rcv_len; + __le32 exp_data_transfer_len; + __le32 exp_data_sn; + struct regpair reserved0; + __le32 reg1_map; +#define REG1_NUM_SGES_MASK 0xF +#define REG1_NUM_SGES_SHIFT 0 +#define REG1_RESERVED1_MASK 0xFFFFFFF +#define REG1_RESERVED1_SHIFT 4 + u8 flags2; +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_AHS_EXIST_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_MASK 0x7F +#define USTORM_NVMETCP_TASK_ST_CTX_RESERVED1_SHIFT 1 + struct nvmetcp_dif_flags dif_flags; + __le16 reserved3; + __le16 tqe_opaque[2]; + __le32 reserved5; + __le32 nvme_tcp_opaque_lo; + __le32 nvme_tcp_opaque_hi; + u8 task_type; + u8 error_flags; +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_DIGEST_ERROR_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_DATA_TRUNCATED_ERROR_SHIFT 1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_UNDER_RUN_ERROR_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_NVME_TCP_SHIFT 3 + u8 flags; +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_MASK 0x3 +#define USTORM_NVMETCP_TASK_ST_CTX_CQE_WRITE_SHIFT 0 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_LOCAL_COMP_SHIFT 2 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_Q0_R2TQE_WRITE_SHIFT 3 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_TOTAL_DATA_ACKED_DONE_SHIFT 4 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_HQ_SCANNED_DONE_SHIFT 5 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_MASK 0x1 +#define USTORM_NVMETCP_TASK_ST_CTX_R2T2RECV_DONE_SHIFT 6 + u8 cq_rss_number; +}; + +struct e5_ystorm_nvmetcp_task_ag_ctx { + u8 reserved /* cdu_validation */; + u8 byte1 /* state_and_core_id */; + __le16 word0 /* icid */; + u8 flags0; + u8 flags1; + u8 flags2; + u8 flags3; + __le32 TTT; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_mstorm_nvmetcp_task_ag_ctx { + u8 cdu_validation; + u8 byte1; + __le16 task_cid; + u8 flags0; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_VALID_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 + u8 flags1; +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1_SHIFT 2 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_MASK 0x3 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF2_SHIFT 4 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_MASK 0x1 +#define E5_MSTORM_NVMETCP_TASK_AG_CTX_CF1EN_SHIFT 7 + u8 flags2; + u8 flags3; + __le32 reg0; + u8 byte2; + u8 byte3; + u8 byte4; + u8 e4_reserved7; +}; + +struct e5_ustorm_nvmetcp_task_ag_ctx { + u8 reserved; + u8 state_and_core_id; + __le16 icid; + u8 flags0; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 + u8 flags1; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 + u8 flags2; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CF3EN_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 + u8 flags3; + u8 flags4; +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 + u8 byte2; + u8 byte3; + u8 e4_reserved8; + __le32 dif_err_intervals; + __le32 dif_error_1st_interval; + __le32 rcv_cont_len; + __le32 exp_cont_len; + __le32 total_data_acked; + __le32 exp_data_acked; + __le16 word1; + __le16 next_tid; + __le32 hdr_residual_count; + __le32 exp_r2t_sn; +}; + +struct e5_nvmetcp_task_context { + struct ystorm_nvmetcp_task_st_ctx ystorm_st_context; + struct e5_ystorm_nvmetcp_task_ag_ctx ystorm_ag_context; + struct regpair ystorm_ag_padding[2]; + struct e5_tdif_task_context tdif_context; + struct e5_mstorm_nvmetcp_task_ag_ctx mstorm_ag_context; + struct regpair mstorm_ag_padding[2]; + struct e5_ustorm_nvmetcp_task_ag_ctx ustorm_ag_context; + struct regpair ustorm_ag_padding[2]; + struct mstorm_nvmetcp_task_st_ctx mstorm_st_context; + struct regpair mstorm_st_padding[2]; + struct ustorm_nvmetcp_task_st_ctx ustorm_st_context; + struct regpair ustorm_st_padding[2]; + struct e5_rdif_task_context rdif_context; +}; + +#endif /* __NVMETCP_COMMON__*/ diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 68d17a4fbf20..850b98991670 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -542,6 +542,22 @@ struct qed_iscsi_pf_params { u8 bdq_pbl_num_entries[3]; }; +struct qed_nvmetcp_pf_params { + u64 glbl_q_params_addr; + u16 cq_num_entries; + u16 num_cons; + u16 num_tasks; + u8 num_sq_pages_in_ring; + u8 num_r2tq_pages_in_ring; + u8 num_uhq_pages_in_ring; + u8 num_queues; + u8 gl_rq_pi; + u8 gl_cmd_pi; + u8 debug_mode; + u8 ll2_ooo_queue_id; + u16 min_rto; +}; + struct qed_rdma_pf_params { /* Supplied to QED during resource allocation (may affect the ILT and * the doorbell BAR). @@ -560,6 +576,7 @@ struct qed_pf_params { struct qed_eth_pf_params eth_pf_params; struct qed_fcoe_pf_params fcoe_pf_params; struct qed_iscsi_pf_params iscsi_pf_params; + struct qed_nvmetcp_pf_params nvmetcp_pf_params; struct qed_rdma_pf_params rdma_pf_params; }; @@ -662,6 +679,7 @@ enum qed_sb_type { enum qed_protocol { QED_PROTOCOL_ETH, QED_PROTOCOL_ISCSI, + QED_PROTOCOL_NVMETCP = QED_PROTOCOL_ISCSI, QED_PROTOCOL_FCOE, }; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index ea273ba1c991..ff808d248883 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -18,7 +18,7 @@ enum qed_ll2_conn_type { QED_LL2_TYPE_FCOE, - QED_LL2_TYPE_ISCSI, + QED_LL2_TYPE_TCP_ULP, QED_LL2_TYPE_TEST, QED_LL2_TYPE_OOO, QED_LL2_TYPE_RESERVED2, diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h new file mode 100644 index 000000000000..14671bc19ed1 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -0,0 +1,240 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* Copyright 2021 Marvell. All rights reserved. */ + +#ifndef _QED_NVMETCP_IF_H +#define _QED_NVMETCP_IF_H +#include <linux/types.h> +#include <linux/qed/qed_if.h> +#include <linux/qed/storage_common.h> +#include <linux/qed/nvmetcp_common.h> + +#define QED_NVMETCP_MAX_IO_SIZE 0x800000 +#define QED_NVMETCP_CMN_HDR_SIZE (sizeof(struct nvme_tcp_hdr)) +#define QED_NVMETCP_CMD_HDR_SIZE (sizeof(struct nvme_tcp_cmd_pdu)) +#define QED_NVMETCP_NON_IO_HDR_SIZE ((QED_NVMETCP_CMN_HDR_SIZE + 16)) + +typedef int (*nvmetcp_event_cb_t) (void *context, + u8 fw_event_code, void *fw_handle); + +struct qed_dev_nvmetcp_info { + struct qed_dev_info common; + u8 port_id; /* Physical port */ + u8 num_cqs; +}; + +#define MAX_TID_BLOCKS_NVMETCP (512) +struct qed_nvmetcp_tid { + u32 size; /* In bytes per task */ + u32 num_tids_per_block; + u8 *blocks[MAX_TID_BLOCKS_NVMETCP]; +}; + +struct qed_nvmetcp_id_params { + u8 mac[ETH_ALEN]; + u32 ip[4]; + u16 port; +}; + +struct qed_nvmetcp_params_offload { + /* FW initializations */ + dma_addr_t sq_pbl_addr; + dma_addr_t nvmetcp_cccid_itid_table_addr; + u16 nvmetcp_cccid_max_range; + u8 default_cq; + + /* Networking and TCP stack initializations */ + struct qed_nvmetcp_id_params src; + struct qed_nvmetcp_id_params dst; + u32 ka_timeout; + u32 ka_interval; + u32 max_rt_time; + u32 cwnd; + u16 mss; + u16 vlan_id; + bool timestamp_en; + bool delayed_ack_en; + bool tcp_keep_alive_en; + bool ecn_en; + u8 ip_version; + u8 ka_max_probe_cnt; + u8 ttl; + u8 tos_or_tc; + u8 rcv_wnd_scale; +}; + +struct qed_nvmetcp_params_update { + u32 max_io_size; + u32 max_recv_pdu_length; + u32 max_send_pdu_length; + + /* Placeholder: pfv, cpda, hpda */ + + bool hdr_digest_en; + bool data_digest_en; +}; + +struct qed_nvmetcp_cb_ops { + struct qed_common_cb_ops common; +}; + +struct nvmetcp_sge { + struct regpair sge_addr; /* SGE address */ + __le32 sge_len; /* SGE length */ + __le32 reserved; +}; + +/* IO path HSI function SGL params */ +struct storage_sgl_task_params { + struct nvmetcp_sge *sgl; + struct regpair sgl_phys_addr; + u32 total_buffer_size; + u16 num_sges; + bool small_mid_sge; +}; + +/* IO path HSI function FW task context params */ +struct nvmetcp_task_params { + void *context; /* Output parameter - set/filled by the HSI function */ + struct nvmetcp_wqe *sqe; + u32 tx_io_size; /* in bytes (Without DIF, if exists) */ + u32 rx_io_size; /* in bytes (Without DIF, if exists) */ + u16 conn_icid; + u16 itid; + struct regpair opq; /* qedn_task_ctx address */ + u16 host_cccid; + u8 cq_rss_number; + bool send_write_incapsule; +}; + +/** + * struct qed_nvmetcp_ops - qed NVMeTCP operations. + * @common: common operations pointer + * @ll2: light L2 operations pointer + * @fill_dev_info: fills NVMeTCP specific information + * @param cdev + * @param info + * @return 0 on success, otherwise error value. + * @register_ops: register nvmetcp operations + * @param cdev + * @param ops - specified using qed_nvmetcp_cb_ops + * @param cookie - driver private + * @start: nvmetcp in FW + * @param cdev + * @param tasks - qed will fill information about tasks + * return 0 on success, otherwise error value. + * @stop: nvmetcp in FW + * @param cdev + * return 0 on success, otherwise error value. + * @acquire_conn: acquire a new nvmetcp connection + * @param cdev + * @param handle - qed will fill handle that should be + * used henceforth as identifier of the + * connection. + * @param p_doorbell - qed will fill the address of the + * doorbell. + * @return 0 on sucesss, otherwise error value. + * @release_conn: release a previously acquired nvmetcp connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @offload_conn: configures an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @update_conn: updates an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @param conn_info - the configuration to use for the + * offload. + * @return 0 on success, otherwise error value. + * @destroy_conn: stops an offloaded connection + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @clear_sq: clear all task in sq + * @param cdev + * @param handle - the connection handle. + * @return 0 on success, otherwise error value. + * @add_src_tcp_port_filter: Add source tcp port filter + * @param cdev + * @param src_port + * @remove_src_tcp_port_filter: Remove source tcp port filter + * @param cdev + * @param src_port + * @add_dst_tcp_port_filter: Add destination tcp port filter + * @param cdev + * @param dest_port + * @remove_dst_tcp_port_filter: Remove destination tcp port filter + * @param cdev + * @param dest_port + * @clear_all_filters: Clear all filters. + * @param cdev + */ +struct qed_nvmetcp_ops { + const struct qed_common_ops *common; + + const struct qed_ll2_ops *ll2; + + int (*fill_dev_info)(struct qed_dev *cdev, + struct qed_dev_nvmetcp_info *info); + + void (*register_ops)(struct qed_dev *cdev, + struct qed_nvmetcp_cb_ops *ops, void *cookie); + + int (*start)(struct qed_dev *cdev, + struct qed_nvmetcp_tid *tasks, + void *event_context, nvmetcp_event_cb_t async_event_cb); + + int (*stop)(struct qed_dev *cdev); + + int (*acquire_conn)(struct qed_dev *cdev, + u32 *handle, + u32 *fw_cid, void __iomem **p_doorbell); + + int (*release_conn)(struct qed_dev *cdev, u32 handle); + + int (*offload_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_offload *conn_info); + + int (*update_conn)(struct qed_dev *cdev, + u32 handle, + struct qed_nvmetcp_params_update *conn_info); + + int (*destroy_conn)(struct qed_dev *cdev, u32 handle, u8 abrt_conn); + + int (*clear_sq)(struct qed_dev *cdev, u32 handle); + + int (*add_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + void (*remove_src_tcp_port_filter)(struct qed_dev *cdev, u16 src_port); + + int (*add_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*remove_dst_tcp_port_filter)(struct qed_dev *cdev, u16 dest_port); + + void (*clear_all_filters)(struct qed_dev *cdev); + + void (*init_read_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_write_io)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_cmd_pdu *cmd_pdu_header, + struct nvme_command *nvme_cmd, + struct storage_sgl_task_params *sgl_task_params); + + void (*init_icreq_exchange)(struct nvmetcp_task_params *task_params, + struct nvme_tcp_icreq_pdu *init_conn_req_pdu_hdr, + struct storage_sgl_task_params *tx_sgl_task_params, + struct storage_sgl_task_params *rx_sgl_task_params); + + void (*init_task_cleanup)(struct nvmetcp_task_params *task_params); +}; + +const struct qed_nvmetcp_ops *qed_get_nvmetcp_ops(void); +void qed_put_nvmetcp_ops(void); +#endif diff --git a/include/linux/qed/qed_nvmetcp_ip_services_if.h b/include/linux/qed/qed_nvmetcp_ip_services_if.h new file mode 100644 index 000000000000..3604aee53796 --- /dev/null +++ b/include/linux/qed/qed_nvmetcp_ip_services_if.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ +/* + * Copyright 2021 Marvell. All rights reserved. + */ + +#ifndef _QED_IP_SERVICES_IF_H +#define _QED_IP_SERVICES_IF_H + +#include <linux/types.h> +#include <net/route.h> +#include <net/ip6_route.h> +#include <linux/inetdevice.h> + +int qed_route_ipv4(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +int qed_route_ipv6(struct sockaddr_storage *local_addr, + struct sockaddr_storage *remote_addr, + struct sockaddr *hardware_address, + struct net_device **ndev); +void qed_vlan_get_ndev(struct net_device **ndev, u16 *vlan_id); +struct pci_dev *qed_validate_ndev(struct net_device *ndev); +void qed_return_tcp_port(struct socket *sock); +int qed_fetch_tcp_port(struct sockaddr_storage local_ip_addr, + struct socket **sock, u16 *port); +__be16 qed_get_in_port(struct sockaddr_storage *sa); + +#endif /* _QED_IP_SERVICES_IF_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9455476c5ba2..d7895b81264e 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -363,6 +363,20 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) \ +({ \ + typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(_________p1)); \ +}) + #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 8d04e7deedc6..83fb86133fe1 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -86,9 +86,6 @@ struct anon_vma_chain { }; enum ttu_flags { - TTU_MIGRATION = 0x1, /* migration mode */ - TTU_MUNLOCK = 0x2, /* munlock mode */ - TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */ TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */ TTU_SYNC = 0x10, /* avoid racy checks with PVMW_SYNC */ @@ -98,7 +95,6 @@ enum ttu_flags { * do a final flush if necessary */ TTU_RMAP_LOCKED = 0x80, /* do not grab rmap lock: * caller holds it */ - TTU_SPLIT_FREEZE = 0x100, /* freeze pte under splitting thp */ }; #ifdef CONFIG_MMU @@ -195,7 +191,12 @@ static inline void page_dup_rmap(struct page *page, bool compound) int page_referenced(struct page *, int is_locked, struct mem_cgroup *memcg, unsigned long *vm_flags); -bool try_to_unmap(struct page *, enum ttu_flags flags); +void try_to_migrate(struct page *page, enum ttu_flags flags); +void try_to_unmap(struct page *, enum ttu_flags flags); + +int make_device_exclusive_range(struct mm_struct *mm, unsigned long start, + unsigned long end, struct page **pages, + void *arg); /* Avoid racy checks */ #define PVMW_SYNC (1 << 0) @@ -240,7 +241,7 @@ int page_mkclean(struct page *); * called in munlock()/munmap() path to check for other vmas holding * the page mlocked. */ -void try_to_munlock(struct page *); +void page_mlock(struct page *page); void remove_migration_ptes(struct page *old, struct page *new, bool locked); diff --git a/include/linux/sctp.h b/include/linux/sctp.h index bb1926589693..a86e852507b3 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -98,6 +98,7 @@ enum sctp_cid { SCTP_CID_I_FWD_TSN = 0xC2, SCTP_CID_ASCONF_ACK = 0x80, SCTP_CID_RECONF = 0x82, + SCTP_CID_PAD = 0x84, }; /* enum */ @@ -410,6 +411,12 @@ struct sctp_heartbeat_chunk { }; +/* PAD chunk could be bundled with heartbeat chunk to probe pmtu */ +struct sctp_pad_chunk { + struct sctp_chunkhdr uh; +}; + + /* For the abort and shutdown ACK we must carry the init tag in the * common header. Just the common header is all that is needed with a * chunk descriptor. diff --git a/include/linux/security.h b/include/linux/security.h index 06f7c50ce77f..24eda04221e9 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1681,7 +1681,7 @@ int security_xfrm_state_alloc_acquire(struct xfrm_state *x, struct xfrm_sec_ctx *polsec, u32 secid); int security_xfrm_state_delete(struct xfrm_state *x); void security_xfrm_state_free(struct xfrm_state *x); -int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); +int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid); int security_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, const struct flowi_common *flic); @@ -1732,7 +1732,7 @@ static inline int security_xfrm_state_delete(struct xfrm_state *x) return 0; } -static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) +static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid) { return 0; } diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 723b1fa1177e..dd99569595fd 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -126,8 +126,16 @@ void seq_put_decimal_ll(struct seq_file *m, const char *delimiter, long long num void seq_put_hex_ll(struct seq_file *m, const char *delimiter, unsigned long long v, unsigned int width); +void seq_escape_mem(struct seq_file *m, const char *src, size_t len, + unsigned int flags, const char *esc); + +static inline void seq_escape_str(struct seq_file *m, const char *src, + unsigned int flags, const char *esc) +{ + seq_escape_mem(m, src, strlen(src), flags, esc); +} + void seq_escape(struct seq_file *m, const char *s, const char *esc); -void seq_escape_mem_ascii(struct seq_file *m, const char *src, size_t isz); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index aa77dcd1646f..8e775ce517bb 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -122,21 +122,18 @@ static inline bool shmem_file(struct file *file) extern bool shmem_charge(struct inode *inode, long pages); extern void shmem_uncharge(struct inode *inode, long pages); +#ifdef CONFIG_USERFAULTFD #ifdef CONFIG_SHMEM -extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, +extern int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, + bool zeropage, struct page **pagep); -extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm, - pmd_t *dst_pmd, - struct vm_area_struct *dst_vma, - unsigned long dst_addr); -#else -#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \ - src_addr, pagep) ({ BUG(); 0; }) -#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \ - dst_addr) ({ BUG(); 0; }) -#endif +#else /* !CONFIG_SHMEM */ +#define shmem_mfill_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, \ + src_addr, zeropage, pagep) ({ BUG(); 0; }) +#endif /* CONFIG_SHMEM */ +#endif /* CONFIG_USERFAULTFD */ #endif diff --git a/include/linux/signal.h b/include/linux/signal.h index 5160fd45e5ca..3454c7ff0778 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -462,8 +462,6 @@ int __save_altstack(stack_t __user *, unsigned long); unsafe_put_user((void __user *)t->sas_ss_sp, &__uss->ss_sp, label); \ unsafe_put_user(t->sas_ss_flags, &__uss->ss_flags, label); \ unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ - if (t->sas_ss_flags & SS_AUTODISARM) \ - sas_ss_reset(t); \ } while (0); #ifdef CONFIG_PROC_FS diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbf820a50a39..b2db9cd9a73f 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -37,6 +37,7 @@ #include <linux/in6.h> #include <linux/if_packet.h> #include <net/flow.h> +#include <net/page_pool.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_common.h> #endif @@ -667,6 +668,8 @@ typedef unsigned char *sk_buff_data_t; * @head_frag: skb was allocated from page fragments, * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves + * @pp_recycle: mark the packet for recycling instead of freeing (implies + * page_pool support on driver) * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) * @ooo_okay: allow the mapping of a socket to a queue to be changed @@ -791,10 +794,12 @@ struct sk_buff { fclone:2, peeked:1, head_frag:1, - pfmemalloc:1; + pfmemalloc:1, + pp_recycle:1; /* page_pool recycle indicator */ #ifdef CONFIG_SKB_EXTENSIONS __u8 active_extensions; #endif + /* fields enclosed in headers_start/headers_end are copied * using a single memcpy() in __copy_skb_header() */ @@ -3081,12 +3086,20 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f) /** * __skb_frag_unref - release a reference on a paged fragment. * @frag: the paged fragment + * @recycle: recycle the page if allocated via page_pool * - * Releases a reference on the paged fragment @frag. + * Releases a reference on the paged fragment @frag + * or recycles the page via the page_pool API. */ -static inline void __skb_frag_unref(skb_frag_t *frag) +static inline void __skb_frag_unref(skb_frag_t *frag, bool recycle) { - put_page(skb_frag_page(frag)); + struct page *page = skb_frag_page(frag); + +#ifdef CONFIG_PAGE_POOL + if (recycle && page_pool_return_skb_page(page)) + return; +#endif + put_page(page); } /** @@ -3098,7 +3111,7 @@ static inline void __skb_frag_unref(skb_frag_t *frag) */ static inline void skb_frag_unref(struct sk_buff *skb, int f) { - __skb_frag_unref(&skb_shinfo(skb)->frags[f]); + __skb_frag_unref(&skb_shinfo(skb)->frags[f], skb->pp_recycle); } /** @@ -4697,5 +4710,21 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) #endif } +#ifdef CONFIG_PAGE_POOL +static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, + struct page_pool *pp) +{ + skb->pp_recycle = 1; + page_pool_store_mem_info(page, pp); +} +#endif + +static inline bool skb_pp_recycle(struct sk_buff *skb, void *data) +{ + if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle) + return false; + return page_pool_return_skb_page(virt_to_page(data)); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index aba0f0f429be..96f319099744 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -126,8 +126,6 @@ int sk_msg_zerocopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from, struct sk_msg *msg, u32 bytes); -int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags, - long timeo, int *err); int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, int len, int flags); @@ -348,7 +346,7 @@ static inline void sk_psock_report_error(struct sk_psock *psock, int err) struct sock *sk = psock->sk; sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); } struct sk_psock *sk_psock_init(struct sock *sk, int node); diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 0db36360ef21..d5ae621d66ba 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -172,6 +172,18 @@ struct stmmac_fpe_cfg { enum stmmac_fpe_state lo_fpe_state; /* Local station FPE state */ }; +struct stmmac_safety_feature_cfg { + u32 tsoee; + u32 mrxpee; + u32 mestee; + u32 mrxee; + u32 mtxee; + u32 epsi; + u32 edpp; + u32 prtyen; + u32 tmouten; +}; + struct plat_stmmacenet_data { int bus_id; int phy_addr; @@ -184,6 +196,7 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_est *est; struct stmmac_fpe_cfg *fpe_cfg; + struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; int has_gmac; int enh_desc; @@ -210,6 +223,7 @@ struct plat_stmmacenet_data { void (*fix_mac_speed)(void *priv, unsigned int speed); int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); + void (*speed_mode_2500)(struct net_device *ndev, void *priv); void (*ptp_clk_freq_config)(void *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); @@ -223,8 +237,10 @@ struct plat_stmmacenet_data { struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; unsigned int clk_ref_rate; + unsigned int mult_fact_100ns; s32 ptp_max_adj; struct reset_control *stmmac_rst; + struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; int has_gmac4; bool has_sun8i; @@ -249,5 +265,6 @@ struct plat_stmmacenet_data { int msi_sfty_ue_vec; int msi_rx_base_vec; int msi_tx_base_vec; + bool use_phy_wol; }; #endif diff --git a/include/linux/string.h b/include/linux/string.h index 9521d8cab18e..b48d2d28e0b1 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -2,7 +2,6 @@ #ifndef _LINUX_STRING_H_ #define _LINUX_STRING_H_ - #include <linux/compiler.h> /* for inline */ #include <linux/types.h> /* for size_t */ #include <linux/stddef.h> /* for NULL */ @@ -184,12 +183,6 @@ extern char **argv_split(gfp_t gfp, const char *str, int *argcp); extern void argv_free(char **argv); extern bool sysfs_streq(const char *s1, const char *s2); -extern int kstrtobool(const char *s, bool *res); -static inline int strtobool(const char *s, bool *res) -{ - return kstrtobool(s, res); -} - int match_string(const char * const *array, size_t n, const char *string); int __sysfs_match_string(const char * const *array, size_t n, const char *s); diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index fa06dcdc481e..68189c4a2eb1 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -2,6 +2,7 @@ #ifndef _LINUX_STRING_HELPERS_H_ #define _LINUX_STRING_HELPERS_H_ +#include <linux/bits.h> #include <linux/ctype.h> #include <linux/types.h> @@ -18,13 +19,15 @@ enum string_size_units { void string_get_size(u64 size, u64 blk_size, enum string_size_units units, char *buf, int len); -#define UNESCAPE_SPACE 0x01 -#define UNESCAPE_OCTAL 0x02 -#define UNESCAPE_HEX 0x04 -#define UNESCAPE_SPECIAL 0x08 +#define UNESCAPE_SPACE BIT(0) +#define UNESCAPE_OCTAL BIT(1) +#define UNESCAPE_HEX BIT(2) +#define UNESCAPE_SPECIAL BIT(3) #define UNESCAPE_ANY \ (UNESCAPE_SPACE | UNESCAPE_OCTAL | UNESCAPE_HEX | UNESCAPE_SPECIAL) +#define UNESCAPE_ALL_MASK GENMASK(3, 0) + int string_unescape(char *src, char *dst, size_t size, unsigned int flags); static inline int string_unescape_inplace(char *buf, unsigned int flags) @@ -42,22 +45,24 @@ static inline int string_unescape_any_inplace(char *buf) return string_unescape_any(buf, buf, 0); } -#define ESCAPE_SPACE 0x01 -#define ESCAPE_SPECIAL 0x02 -#define ESCAPE_NULL 0x04 -#define ESCAPE_OCTAL 0x08 +#define ESCAPE_SPACE BIT(0) +#define ESCAPE_SPECIAL BIT(1) +#define ESCAPE_NULL BIT(2) +#define ESCAPE_OCTAL BIT(3) #define ESCAPE_ANY \ (ESCAPE_SPACE | ESCAPE_OCTAL | ESCAPE_SPECIAL | ESCAPE_NULL) -#define ESCAPE_NP 0x10 +#define ESCAPE_NP BIT(4) #define ESCAPE_ANY_NP (ESCAPE_ANY | ESCAPE_NP) -#define ESCAPE_HEX 0x20 +#define ESCAPE_HEX BIT(5) +#define ESCAPE_NA BIT(6) +#define ESCAPE_NAP BIT(7) +#define ESCAPE_APPEND BIT(8) + +#define ESCAPE_ALL_MASK GENMASK(8, 0) int string_escape_mem(const char *src, size_t isz, char *dst, size_t osz, unsigned int flags, const char *only); -int string_escape_mem_ascii(const char *src, size_t isz, char *dst, - size_t osz); - static inline int string_escape_mem_any_np(const char *src, size_t isz, char *dst, size_t osz, const char *only) { diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index d0965e2997b0..b134b2b3371c 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -14,6 +14,7 @@ #include <linux/kref.h> #include <linux/slab.h> #include <linux/atomic.h> +#include <linux/kstrtox.h> #include <linux/proc_fs.h> /* diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 0806796eabcb..068e1982ad37 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -6,7 +6,7 @@ * managing access and communication to and from the SSAM EC, as well as main * communication structures and definitions. * - * Copyright (C) 2019-2020 Maximilian Luz <luzmaximilian@gmail.com> + * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ #ifndef _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H @@ -796,6 +796,20 @@ enum ssam_event_mask { SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) /** + * enum ssam_event_notifier_flags - Flags for event notifiers. + * @SSAM_EVENT_NOTIFIER_OBSERVER: + * The corresponding notifier acts as observer. Registering a notifier + * with this flag set will not attempt to enable any event. Equally, + * unregistering will not attempt to disable any event. Note that a + * notifier with this flag may not even correspond to a certain event at + * all, only to a specific event target category. Event matching will not + * be influenced by this flag. + */ +enum ssam_event_notifier_flags { + SSAM_EVENT_NOTIFIER_OBSERVER = BIT(0), +}; + +/** * struct ssam_event_notifier - Notifier block for SSAM events. * @base: The base notifier block with callback function and priority. * @event: The event for which this block will receive notifications. @@ -803,6 +817,7 @@ enum ssam_event_mask { * @event.id: ID specifying the event. * @event.mask: Flags determining how events are matched to the notifier. * @event.flags: Flags used for enabling the event. + * @flags: Notifier flags (see &enum ssam_event_notifier_flags). */ struct ssam_event_notifier { struct ssam_notifier_block base; @@ -813,6 +828,8 @@ struct ssam_event_notifier { enum ssam_event_mask mask; u8 flags; } event; + + unsigned long flags; }; int ssam_notifier_register(struct ssam_controller *ctrl, @@ -821,4 +838,12 @@ int ssam_notifier_register(struct ssam_controller *ctrl, int ssam_notifier_unregister(struct ssam_controller *ctrl, struct ssam_event_notifier *n); +int ssam_controller_event_enable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + +int ssam_controller_event_disable(struct ssam_controller *ctrl, + struct ssam_event_registry reg, + struct ssam_event_id id, u8 flags); + #endif /* _LINUX_SURFACE_AGGREGATOR_CONTROLLER_H */ diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index 6ff9c58b3e17..f636c5310321 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -7,7 +7,7 @@ * Provides support for non-platform/non-ACPI SSAM clients via dedicated * subsystem. * - * Copyright (C) 2019-2020 Maximilian Luz <luzmaximilian@gmail.com> + * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ #ifndef _LINUX_SURFACE_AGGREGATOR_DEVICE_H diff --git a/include/linux/surface_aggregator/serial_hub.h b/include/linux/surface_aggregator/serial_hub.h index 64276fbfa1d5..c3de43edcffa 100644 --- a/include/linux/surface_aggregator/serial_hub.h +++ b/include/linux/surface_aggregator/serial_hub.h @@ -6,7 +6,7 @@ * Surface System Aggregator Module (SSAM). Provides the interface for basic * packet- and request-based communication with the SSAM EC via SSH. * - * Copyright (C) 2019-2020 Maximilian Luz <luzmaximilian@gmail.com> + * Copyright (C) 2019-2021 Maximilian Luz <luzmaximilian@gmail.com> */ #ifndef _LINUX_SURFACE_AGGREGATOR_SERIAL_HUB_H diff --git a/include/linux/swap.h b/include/linux/swap.h index 49b1dd2c100b..6f5a43251593 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -62,12 +62,17 @@ static inline int current_is_kswapd(void) * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry - * to a special SWP_DEVICE_* entry. + * to a special SWP_DEVICE_{READ|WRITE} entry. + * + * When a page is mapped by the device for exclusive access we set the CPU page + * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE -#define SWP_DEVICE_NUM 2 +#define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) +#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) +#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif @@ -537,7 +542,11 @@ static inline void put_swap_device(struct swap_info_struct *si) { } -#define swap_address_space(entry) (NULL) +static inline struct address_space *swap_address_space(swp_entry_t entry) +{ + return NULL; +} + #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL @@ -560,8 +569,8 @@ static inline void show_swap_cache_info(void) { } -#define free_swap_and_cache(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) -#define swapcache_prepare(e) ({(is_migration_entry(e) || is_device_private_entry(e));}) +/* used to sanity check ptes in zap_pte_range when CONFIG_SWAP=0 */ +#define free_swap_and_cache(e) is_pfn_swap_entry(e) static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5907205c712c..d356ab4047f7 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -107,10 +107,14 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { - return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ, - page_to_pfn(page)); + return swp_entry(SWP_DEVICE_READ, offset); +} + +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) +{ + return swp_entry(SWP_DEVICE_WRITE, offset); } static inline bool is_device_private_entry(swp_entry_t entry) @@ -119,33 +123,40 @@ static inline bool is_device_private_entry(swp_entry_t entry) return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE; } -static inline void make_device_private_entry_read(swp_entry_t *entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { - *entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry)); + return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); } -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { - return unlikely(swp_type(entry) == SWP_DEVICE_WRITE); + return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset); } -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { - return swp_offset(entry); + return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset); +} + +static inline bool is_device_exclusive_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ || + swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE; } -static inline struct page *device_private_entry_to_page(swp_entry_t entry) +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) { - return pfn_to_page(swp_offset(entry)); + return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE); } #else /* CONFIG_DEVICE_PRIVATE */ -static inline swp_entry_t make_device_private_entry(struct page *page, bool write) +static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { return swp_entry(0, 0); } -static inline void make_device_private_entry_read(swp_entry_t *entry) +static inline swp_entry_t make_writable_device_private_entry(pgoff_t offset) { + return swp_entry(0, 0); } static inline bool is_device_private_entry(swp_entry_t entry) @@ -153,61 +164,52 @@ static inline bool is_device_private_entry(swp_entry_t entry) return false; } -static inline bool is_write_device_private_entry(swp_entry_t entry) +static inline bool is_writable_device_private_entry(swp_entry_t entry) { return false; } -static inline unsigned long device_private_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset) { - return 0; + return swp_entry(0, 0); } -static inline struct page *device_private_entry_to_page(swp_entry_t entry) +static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset) { - return NULL; + return swp_entry(0, 0); } -#endif /* CONFIG_DEVICE_PRIVATE */ -#ifdef CONFIG_MIGRATION -static inline swp_entry_t make_migration_entry(struct page *page, int write) +static inline bool is_device_exclusive_entry(swp_entry_t entry) { - BUG_ON(!PageLocked(compound_head(page))); + return false; +} - return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ, - page_to_pfn(page)); +static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) +{ + return false; } +#endif /* CONFIG_DEVICE_PRIVATE */ +#ifdef CONFIG_MIGRATION static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { - return swp_offset(entry); + return swp_entry(SWP_MIGRATION_READ, offset); } -static inline struct page *migration_entry_to_page(swp_entry_t entry) +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { - struct page *p = pfn_to_page(swp_offset(entry)); - /* - * Any use of migration entries may only occur while the - * corresponding page is locked - */ - BUG_ON(!PageLocked(compound_head(p))); - return p; -} - -static inline void make_migration_entry_read(swp_entry_t *entry) -{ - *entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry)); + return swp_entry(SWP_MIGRATION_WRITE, offset); } extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, @@ -217,37 +219,58 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, extern void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte); #else - -#define make_migration_entry(page, write) swp_entry(0, 0) -static inline int is_migration_entry(swp_entry_t swp) +static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { - return 0; + return swp_entry(0, 0); } -static inline unsigned long migration_entry_to_pfn(swp_entry_t entry) +static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { - return 0; + return swp_entry(0, 0); } -static inline struct page *migration_entry_to_page(swp_entry_t entry) +static inline int is_migration_entry(swp_entry_t swp) { - return NULL; + return 0; } -static inline void make_migration_entry_read(swp_entry_t *entryp) { } static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, struct mm_struct *mm, pte_t *pte) { } -static inline int is_write_migration_entry(swp_entry_t entry) +static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } #endif +static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) +{ + struct page *p = pfn_to_page(swp_offset(entry)); + + /* + * Any use of migration entries may only occur while the + * corresponding page is locked + */ + BUG_ON(is_migration_entry(entry) && !PageLocked(p)); + + return p; +} + +/* + * A pfn swap entry is a special type of swap entry that always has a pfn stored + * in the swap offset. They are used to represent unaddressable device memory + * and to restrict access to a page undergoing migration. + */ +static inline bool is_pfn_swap_entry(swp_entry_t entry) +{ + return is_migration_entry(entry) || is_device_private_entry(entry) || + is_device_exclusive_entry(entry); +} + struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION @@ -265,6 +288,8 @@ static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd) if (pmd_swp_soft_dirty(pmd)) pmd = pmd_swp_clear_soft_dirty(pmd); + if (pmd_swp_uffd_wp(pmd)) + pmd = pmd_swp_clear_uffd_wp(pmd); arch_entry = __pmd_to_swp_entry(pmd); return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry)); } diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 050511e8f1f8..586128d5c3b8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -485,8 +485,8 @@ asmlinkage long sys_pipe2(int __user *fildes, int flags); /* fs/quota.c */ asmlinkage long sys_quotactl(unsigned int cmd, const char __user *special, qid_t id, void __user *addr); -asmlinkage long sys_quotactl_path(unsigned int cmd, const char __user *mountpoint, - qid_t id, void __user *addr); +asmlinkage long sys_quotactl_fd(unsigned int fd, unsigned int cmd, qid_t id, + void __user *addr); /* fs/readdir.c */ asmlinkage long sys_getdents64(unsigned int fd, diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 157762db9d4b..0999f6317978 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -9,6 +9,7 @@ #define _LINUX_THREAD_INFO_H #include <linux/types.h> +#include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> diff --git a/include/linux/usb/cdc-wdm.h b/include/linux/usb/cdc-wdm.h index 9b895f93d8de..9f5a51f79ba5 100644 --- a/include/linux/usb/cdc-wdm.h +++ b/include/linux/usb/cdc-wdm.h @@ -12,11 +12,12 @@ #ifndef __LINUX_USB_CDC_WDM_H #define __LINUX_USB_CDC_WDM_H +#include <linux/wwan.h> #include <uapi/linux/usb/cdc-wdm.h> extern struct usb_driver *usb_cdc_wdm_register(struct usb_interface *intf, struct usb_endpoint_descriptor *ep, - int bufsize, + int bufsize, enum wwan_port_type type, int (*manage_power)(struct usb_interface *, int)); #endif /* __LINUX_USB_CDC_WDM_H */ diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h index 794d1538b8ba..331d2ccf0bcc 100644 --- a/include/linux/userfaultfd_k.h +++ b/include/linux/userfaultfd_k.h @@ -53,6 +53,11 @@ enum mcopy_atomic_mode { MCOPY_ATOMIC_CONTINUE, }; +extern int mfill_atomic_install_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd, + struct vm_area_struct *dst_vma, + unsigned long dst_addr, struct page *page, + bool newly_allocated, bool wp_copy); + extern ssize_t mcopy_atomic(struct mm_struct *dst_mm, unsigned long dst_start, unsigned long src_start, unsigned long len, bool *mmap_changing, __u64 mode); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index dc636b727179..35d7eedb5e8e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -36,6 +36,7 @@ struct virtio_vsock_sock { u32 rx_bytes; u32 buf_alloc; struct list_head rx_queue; + u32 msg_count; }; struct virtio_vsock_pkt { @@ -80,8 +81,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index bfaaf0b6fa76..1dabd6f22486 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -104,6 +104,21 @@ static inline bool arch_vmap_pmd_supported(pgprot_t prot) } #endif +#ifndef arch_vmap_pte_range_map_size +static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, + u64 pfn, unsigned int max_page_shift) +{ + return PAGE_SIZE; +} +#endif + +#ifndef arch_vmap_pte_supported_shift +static inline int arch_vmap_pte_supported_shift(unsigned long size) +{ + return PAGE_SHIFT; +} +#endif + /* * Highlevel APIs for driver use */ diff --git a/include/linux/wait.h b/include/linux/wait.h index fe10e8570a52..6598ae35e1b5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1136,7 +1136,7 @@ do { \ * Waitqueues which are removed from the waitqueue_head at wakeup time */ void prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); -void prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); +bool prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state); void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry); long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 95de51c10248..667e86cfbdcf 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -361,7 +361,6 @@ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int vm_highmem_is_dirtyable; -extern int block_dump; extern int laptop_mode; int dirty_background_ratio_handler(struct ctl_table *table, int write, diff --git a/include/linux/wwan.h b/include/linux/wwan.h index aa05a253dcf9..9fac819f92e3 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -6,7 +6,10 @@ #include <linux/device.h> #include <linux/kernel.h> +#include <linux/poll.h> #include <linux/skbuff.h> +#include <linux/netlink.h> +#include <linux/netdevice.h> /** * enum wwan_port_type - WWAN port types @@ -15,7 +18,10 @@ * @WWAN_PORT_QMI: Qcom modem/MSM interface for modem control * @WWAN_PORT_QCDM: Qcom Modem diagnostic interface * @WWAN_PORT_FIREHOSE: XML based command protocol - * @WWAN_PORT_MAX: Number of supported port types + * + * @WWAN_PORT_MAX: Highest supported port types + * @WWAN_PORT_UNKNOWN: Special value to indicate an unknown port type + * @__WWAN_PORT_MAX: Internal use */ enum wwan_port_type { WWAN_PORT_AT, @@ -23,7 +29,12 @@ enum wwan_port_type { WWAN_PORT_QMI, WWAN_PORT_QCDM, WWAN_PORT_FIREHOSE, - WWAN_PORT_MAX, + + /* Add new port types above this line */ + + __WWAN_PORT_MAX, + WWAN_PORT_MAX = __WWAN_PORT_MAX - 1, + WWAN_PORT_UNKNOWN, }; struct wwan_port; @@ -31,15 +42,23 @@ struct wwan_port; /** struct wwan_port_ops - The WWAN port operations * @start: The routine for starting the WWAN port device. * @stop: The routine for stopping the WWAN port device. - * @tx: The routine that sends WWAN port protocol data to the device. + * @tx: Non-blocking routine that sends WWAN port protocol data to the device. + * @tx_blocking: Optional blocking routine that sends WWAN port protocol data + * to the device. + * @tx_poll: Optional routine that sets additional TX poll flags. * * The wwan_port_ops structure contains a list of low-level operations - * that control a WWAN port device. All functions are mandatory. + * that control a WWAN port device. All functions are mandatory unless specified. */ struct wwan_port_ops { int (*start)(struct wwan_port *port); void (*stop)(struct wwan_port *port); int (*tx)(struct wwan_port *port, struct sk_buff *skb); + + /* Optional operations */ + int (*tx_blocking)(struct wwan_port *port, struct sk_buff *skb); + __poll_t (*tx_poll)(struct wwan_port *port, struct file *filp, + poll_table *wait); }; /** @@ -108,4 +127,48 @@ void wwan_port_txon(struct wwan_port *port); */ void *wwan_port_get_drvdata(struct wwan_port *port); +/** + * struct wwan_netdev_priv - WWAN core network device private data + * @link_id: WWAN device data link id + * @drv_priv: driver private data area, size is determined in &wwan_ops + */ +struct wwan_netdev_priv { + u32 link_id; + + /* must be last */ + u8 drv_priv[] __aligned(sizeof(void *)); +}; + +static inline void *wwan_netdev_drvpriv(struct net_device *dev) +{ + return ((struct wwan_netdev_priv *)netdev_priv(dev))->drv_priv; +} + +/* + * Used to indicate that the WWAN core should not create a default network + * link. + */ +#define WWAN_NO_DEFAULT_LINK U32_MAX + +/** + * struct wwan_ops - WWAN device ops + * @priv_size: size of private netdev data area + * @setup: set up a new netdev + * @newlink: register the new netdev + * @dellink: remove the given netdev + */ +struct wwan_ops { + unsigned int priv_size; + void (*setup)(struct net_device *dev); + int (*newlink)(void *ctxt, struct net_device *dev, + u32 if_id, struct netlink_ext_ack *extack); + void (*dellink)(void *ctxt, struct net_device *dev, + struct list_head *head); +}; + +int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, + void *ctxt, u32 def_link_id); + +void wwan_unregister_ops(struct device *parent); + #endif /* __WWAN_H */ diff --git a/include/linux/zbud.h b/include/linux/zbud.h deleted file mode 100644 index b1eaf6e31735..000000000000 --- a/include/linux/zbud.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ZBUD_H_ -#define _ZBUD_H_ - -#include <linux/types.h> - -struct zbud_pool; - -struct zbud_ops { - int (*evict)(struct zbud_pool *pool, unsigned long handle); -}; - -struct zbud_pool *zbud_create_pool(gfp_t gfp, const struct zbud_ops *ops); -void zbud_destroy_pool(struct zbud_pool *pool); -int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, - unsigned long *handle); -void zbud_free(struct zbud_pool *pool, unsigned long handle); -int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); -void *zbud_map(struct zbud_pool *pool, unsigned long handle); -void zbud_unmap(struct zbud_pool *pool, unsigned long handle); -u64 zbud_get_pool_size(struct zbud_pool *pool); - -#endif /* _ZBUD_H_ */ |