diff options
Diffstat (limited to 'include/linux')
56 files changed, 786 insertions, 266 deletions
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 2f7a29242b87..38cd77b39a64 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,7 +26,8 @@ #define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL) #define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL) -int iort_register_domain_token(int trans_id, struct fwnode_handle *fw_node); +int iort_register_domain_token(int trans_id, phys_addr_t base, + struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); struct fwnode_handle *iort_find_domain_token(int trans_id); #ifdef CONFIG_ACPI_IORT @@ -38,6 +39,7 @@ int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id); /* IOMMU interface */ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size); const struct iommu_ops *iort_iommu_configure(struct device *dev); +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head); #else static inline void acpi_iort_init(void) { } static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id) @@ -52,6 +54,9 @@ static inline void iort_dma_setup(struct device *dev, u64 *dma_addr, static inline const struct iommu_ops *iort_iommu_configure( struct device *dev) { return NULL; } +static inline +int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head) +{ return 0; } #endif #endif /* __ACPI_IORT_H__ */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3e4ce54d84ab..09da0f124699 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -175,7 +175,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); +long wait_iff_congested(int sync, long timeout); static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi) { @@ -329,7 +329,7 @@ static inline bool inode_to_wb_is_valid(struct inode *inode) * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be - * holding either @inode->i_lock, @inode->i_mapping->tree_lock, or the + * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) @@ -337,7 +337,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && - !lockdep_is_held(&inode->i_mapping->tree_lock) && + !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; @@ -349,7 +349,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) * @lockedp: temp bool output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't - * holding inode->i_lock, mapping->tree_lock or wb->list_lock. This + * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). @@ -370,11 +370,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) *lockedp = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(*lockedp)) - spin_lock_irq(&inode->i_mapping->tree_lock); + xa_lock_irq(&inode->i_mapping->i_pages); /* - * Protected by either !I_WB_SWITCH + rcu_read_lock() or tree_lock. - * inode_to_wb() will bark. Deref directly. + * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages + * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } @@ -387,7 +387,7 @@ unlocked_inode_to_wb_begin(struct inode *inode, bool *lockedp) static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked) { if (unlikely(locked)) - spin_unlock_irq(&inode->i_mapping->tree_lock); + xa_unlock_irq(&inode->i_mapping->i_pages); rcu_read_unlock(); } diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index b0abe21d6cc9..4955e0863b83 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -61,6 +61,8 @@ struct linux_binprm { unsigned interp_flags; unsigned interp_data; unsigned long loader, exec; + + struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */ } __randomize_layout; #define BINPRM_FLAGS_ENFORCE_NONDUMP_BIT 0 @@ -118,6 +120,7 @@ extern int __must_check remove_arg_zero(struct linux_binprm *); extern int search_binary_handler(struct linux_binprm *); extern int flush_old_exec(struct linux_binprm * bprm); extern void setup_new_exec(struct linux_binprm * bprm); +extern void finalize_exec(struct linux_binprm *bprm); extern void would_dump(struct linux_binprm *, struct file *); extern int suid_dumpable; diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 59042d5ac520..3901927cf6a0 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -204,6 +204,7 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_OSD_PRIMARY_AFFINITY | \ CEPH_FEATURE_MSGR_KEEPALIVE2 | \ CEPH_FEATURE_OSD_POOLRESEND | \ + CEPH_FEATURE_MDS_QUOTA | \ CEPH_FEATURE_CRUSH_V4 | \ CEPH_FEATURE_NEW_OSDOP_ENCODING | \ CEPH_FEATURE_SERVER_JEWEL | \ diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 88dd51381aaf..7ecfc88314d8 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -134,6 +134,7 @@ struct ceph_dir_layout { #define CEPH_MSG_CLIENT_LEASE 0x311 #define CEPH_MSG_CLIENT_SNAP 0x312 #define CEPH_MSG_CLIENT_CAPRELEASE 0x313 +#define CEPH_MSG_CLIENT_QUOTA 0x314 /* pool ops */ #define CEPH_MSG_POOLOP_REPLY 48 @@ -807,4 +808,20 @@ struct ceph_mds_snap_realm { } __attribute__ ((packed)); /* followed by my snap list, then prior parent snap list */ +/* + * quotas + */ +struct ceph_mds_quota { + __le64 ino; /* ino */ + struct ceph_timespec rctime; + __le64 rbytes; /* dir stats */ + __le64 rfiles; + __le64 rsubdirs; + __u8 struct_v; /* compat */ + __u8 struct_compat; + __le32 struct_len; + __le64 max_bytes; /* quota max. bytes */ + __le64 max_files; /* quota max. files */ +} __attribute__ ((packed)); + #endif diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index c2ec44cf5098..49c93b9308d7 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -262,6 +262,7 @@ extern struct kmem_cache *ceph_cap_cachep; extern struct kmem_cache *ceph_cap_flush_cachep; extern struct kmem_cache *ceph_dentry_cachep; extern struct kmem_cache *ceph_file_cachep; +extern struct kmem_cache *ceph_dir_file_cachep; /* ceph_common.c */ extern bool libceph_compatible(void *data); diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index ead9d85f1c11..c7dfcb8a1fb2 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -76,6 +76,7 @@ enum ceph_msg_data_type { #ifdef CONFIG_BLOCK CEPH_MSG_DATA_BIO, /* data source/destination is a bio list */ #endif /* CONFIG_BLOCK */ + CEPH_MSG_DATA_BVECS, /* data source/destination is a bio_vec array */ }; static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) @@ -87,22 +88,106 @@ static __inline__ bool ceph_msg_data_type_valid(enum ceph_msg_data_type type) #ifdef CONFIG_BLOCK case CEPH_MSG_DATA_BIO: #endif /* CONFIG_BLOCK */ + case CEPH_MSG_DATA_BVECS: return true; default: return false; } } +#ifdef CONFIG_BLOCK + +struct ceph_bio_iter { + struct bio *bio; + struct bvec_iter iter; +}; + +#define __ceph_bio_iter_advance_step(it, n, STEP) do { \ + unsigned int __n = (n), __cur_n; \ + \ + while (__n) { \ + BUG_ON(!(it)->iter.bi_size); \ + __cur_n = min((it)->iter.bi_size, __n); \ + (void)(STEP); \ + bio_advance_iter((it)->bio, &(it)->iter, __cur_n); \ + if (!(it)->iter.bi_size && (it)->bio->bi_next) { \ + dout("__ceph_bio_iter_advance_step next bio\n"); \ + (it)->bio = (it)->bio->bi_next; \ + (it)->iter = (it)->bio->bi_iter; \ + } \ + __n -= __cur_n; \ + } \ +} while (0) + +/* + * Advance @it by @n bytes. + */ +#define ceph_bio_iter_advance(it, n) \ + __ceph_bio_iter_advance_step(it, n, 0) + +/* + * Advance @it by @n bytes, executing BVEC_STEP for each bio_vec. + */ +#define ceph_bio_iter_advance_step(it, n, BVEC_STEP) \ + __ceph_bio_iter_advance_step(it, n, ({ \ + struct bio_vec bv; \ + struct bvec_iter __cur_iter; \ + \ + __cur_iter = (it)->iter; \ + __cur_iter.bi_size = __cur_n; \ + __bio_for_each_segment(bv, (it)->bio, __cur_iter, __cur_iter) \ + (void)(BVEC_STEP); \ + })) + +#endif /* CONFIG_BLOCK */ + +struct ceph_bvec_iter { + struct bio_vec *bvecs; + struct bvec_iter iter; +}; + +#define __ceph_bvec_iter_advance_step(it, n, STEP) do { \ + BUG_ON((n) > (it)->iter.bi_size); \ + (void)(STEP); \ + bvec_iter_advance((it)->bvecs, &(it)->iter, (n)); \ +} while (0) + +/* + * Advance @it by @n bytes. + */ +#define ceph_bvec_iter_advance(it, n) \ + __ceph_bvec_iter_advance_step(it, n, 0) + +/* + * Advance @it by @n bytes, executing BVEC_STEP for each bio_vec. + */ +#define ceph_bvec_iter_advance_step(it, n, BVEC_STEP) \ + __ceph_bvec_iter_advance_step(it, n, ({ \ + struct bio_vec bv; \ + struct bvec_iter __cur_iter; \ + \ + __cur_iter = (it)->iter; \ + __cur_iter.bi_size = (n); \ + for_each_bvec(bv, (it)->bvecs, __cur_iter, __cur_iter) \ + (void)(BVEC_STEP); \ + })) + +#define ceph_bvec_iter_shorten(it, n) do { \ + BUG_ON((n) > (it)->iter.bi_size); \ + (it)->iter.bi_size = (n); \ +} while (0) + struct ceph_msg_data { struct list_head links; /* ceph_msg->data */ enum ceph_msg_data_type type; union { #ifdef CONFIG_BLOCK struct { - struct bio *bio; - size_t bio_length; + struct ceph_bio_iter bio_pos; + u32 bio_length; }; #endif /* CONFIG_BLOCK */ + struct ceph_bvec_iter bvec_pos; struct { struct page **pages; /* NOT OWNER. */ size_t length; /* total # bytes */ @@ -122,11 +207,9 @@ struct ceph_msg_data_cursor { bool need_crc; /* crc update needed */ union { #ifdef CONFIG_BLOCK - struct { /* bio */ - struct bio *bio; /* bio from list */ - struct bvec_iter bvec_iter; - }; + struct ceph_bio_iter bio_iter; #endif /* CONFIG_BLOCK */ + struct bvec_iter bvec_iter; struct { /* pages */ unsigned int page_offset; /* offset in page */ unsigned short page_index; /* index in array */ @@ -290,9 +373,11 @@ extern void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, extern void ceph_msg_data_add_pagelist(struct ceph_msg *msg, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK -extern void ceph_msg_data_add_bio(struct ceph_msg *msg, struct bio *bio, - size_t length); +void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos, + u32 length); #endif /* CONFIG_BLOCK */ +void ceph_msg_data_add_bvecs(struct ceph_msg *msg, + struct ceph_bvec_iter *bvec_pos); extern struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags, bool can_fail); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 52fb37d1c2a5..528ccc943cee 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -57,6 +57,7 @@ enum ceph_osd_data_type { #ifdef CONFIG_BLOCK CEPH_OSD_DATA_TYPE_BIO, #endif /* CONFIG_BLOCK */ + CEPH_OSD_DATA_TYPE_BVECS, }; struct ceph_osd_data { @@ -72,10 +73,11 @@ struct ceph_osd_data { struct ceph_pagelist *pagelist; #ifdef CONFIG_BLOCK struct { - struct bio *bio; /* list of bios */ - size_t bio_length; /* total in list */ + struct ceph_bio_iter bio_pos; + u32 bio_length; }; #endif /* CONFIG_BLOCK */ + struct ceph_bvec_iter bvec_pos; }; }; @@ -405,10 +407,14 @@ extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *, unsigned int which, struct ceph_pagelist *pagelist); #ifdef CONFIG_BLOCK -extern void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *, - unsigned int which, - struct bio *bio, size_t bio_length); +void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, + unsigned int which, + struct ceph_bio_iter *bio_pos, + u32 bio_length); #endif /* CONFIG_BLOCK */ +void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, + unsigned int which, + struct ceph_bvec_iter *bvec_pos); extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *, unsigned int which, @@ -418,6 +424,9 @@ extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *, struct page **pages, u64 length, u32 alignment, bool pages_from_pool, bool own_pages); +void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, + unsigned int which, + struct bio_vec *bvecs, u32 bytes); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index d41fad99c0fa..e71fb222c7c3 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -5,7 +5,6 @@ #include <linux/rbtree.h> #include <linux/ceph/types.h> #include <linux/ceph/decode.h> -#include <linux/ceph/ceph_fs.h> #include <linux/crush/crush.h> /* @@ -280,11 +279,6 @@ bool ceph_osds_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, bool any_change); -/* calculate mapping of a file extent to an object */ -extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, - u64 off, u64 len, - u64 *bno, u64 *oxoff, u64 *oxlen); - int __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi, const struct ceph_object_id *oid, const struct ceph_object_locator *oloc, diff --git a/include/linux/ceph/striper.h b/include/linux/ceph/striper.h new file mode 100644 index 000000000000..cbd0d24b7148 --- /dev/null +++ b/include/linux/ceph/striper.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CEPH_STRIPER_H +#define _LINUX_CEPH_STRIPER_H + +#include <linux/list.h> +#include <linux/types.h> + +struct ceph_file_layout; + +void ceph_calc_file_object_mapping(struct ceph_file_layout *l, + u64 off, u64 len, + u64 *objno, u64 *objoff, u32 *xlen); + +struct ceph_object_extent { + struct list_head oe_item; + u64 oe_objno; + u64 oe_off; + u64 oe_len; +}; + +static inline void ceph_object_extent_init(struct ceph_object_extent *ex) +{ + INIT_LIST_HEAD(&ex->oe_item); +} + +/* + * Called for each mapped stripe unit. + * + * @bytes: number of bytes mapped, i.e. the minimum of the full length + * requested (file extent length) or the remainder of the stripe + * unit within an object + */ +typedef void (*ceph_object_extent_fn_t)(struct ceph_object_extent *ex, + u32 bytes, void *arg); + +int ceph_file_to_extents(struct ceph_file_layout *l, u64 off, u64 len, + struct list_head *object_extents, + struct ceph_object_extent *alloc_fn(void *arg), + void *alloc_arg, + ceph_object_extent_fn_t action_fn, + void *action_arg); +int ceph_iterate_extents(struct ceph_file_layout *l, u64 off, u64 len, + struct list_head *object_extents, + ceph_object_extent_fn_t action_fn, + void *action_arg); + +struct ceph_file_extent { + u64 fe_off; + u64 fe_len; +}; + +static inline u64 ceph_file_extents_bytes(struct ceph_file_extent *file_extents, + u32 num_file_extents) +{ + u64 bytes = 0; + u32 i; + + for (i = 0; i < num_file_extents; i++) + bytes += file_extents[i].fe_len; + + return bytes; +} + +int ceph_extent_to_file(struct ceph_file_layout *l, + u64 objno, u64 objoff, u64 objlen, + struct ceph_file_extent **file_extents, + u32 *num_file_extents); + +#endif diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index d3f264a5b04d..ceb96ecab96e 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -17,9 +17,6 @@ */ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end }; - /* all clang versions usable with the kernel support KASAN ABI version 5 */ #define KASAN_ABI_VERSION 5 diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e2c7f4369eff..b4bf73f5e38f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,6 +242,9 @@ #if defined(RANDSTRUCT_PLUGIN) && !defined(__CHECKER__) #define __randomize_layout __attribute__((randomize_layout)) #define __no_randomize_layout __attribute__((no_randomize_layout)) +/* This anon struct can add padding, so only enable it under randstruct. */ +#define randomized_struct_fields_start struct { +#define randomized_struct_fields_end } __randomize_layout; #endif #endif /* GCC_VERSION >= 40500 */ @@ -256,15 +259,6 @@ */ #define __visible __attribute__((externally_visible)) -/* - * RANDSTRUCT_PLUGIN wants to use an anonymous struct, but it is only - * possible since GCC 4.6. To provide as much build testing coverage - * as possible, this is used for all GCC 4.6+ builds, and not just on - * RANDSTRUCT_PLUGIN builds. - */ -#define randomized_struct_fields_start struct { -#define randomized_struct_fields_end } __randomize_layout; - #endif /* GCC_VERSION >= 40600 */ diff --git a/include/linux/const.h b/include/linux/const.h new file mode 100644 index 000000000000..7b55a55f5911 --- /dev/null +++ b/include/linux/const.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_CONST_H +#define _LINUX_CONST_H + +#include <uapi/linux/const.h> + +#define UL(x) (_UL(x)) +#define ULL(x) (_ULL(x)) + +#endif /* _LINUX_CONST_H */ diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 1fe49724da9e..87f48dd932eb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -960,8 +960,6 @@ extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq, extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs; extern struct freq_attr *cpufreq_generic_attr[]; -int cpufreq_table_validate_and_show(struct cpufreq_policy *policy, - struct cpufreq_frequency_table *table); int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy); unsigned int cpufreq_generic_get(unsigned int cpu); diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index a806e94c482f..1eefabf1621f 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -135,7 +135,8 @@ extern bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev); extern int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); extern int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index); extern void cpuidle_reflect(struct cpuidle_device *dev, int index); @@ -167,7 +168,7 @@ static inline bool cpuidle_not_available(struct cpuidle_driver *drv, struct cpuidle_device *dev) {return true; } static inline int cpuidle_select(struct cpuidle_driver *drv, - struct cpuidle_device *dev) + struct cpuidle_device *dev, bool *stop_tick) {return -ENODEV; } static inline int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) @@ -250,7 +251,8 @@ struct cpuidle_governor { struct cpuidle_device *dev); int (*select) (struct cpuidle_driver *drv, - struct cpuidle_device *dev); + struct cpuidle_device *dev, + bool *stop_tick); void (*reflect) (struct cpuidle_device *dev, int index); }; diff --git a/include/linux/dax.h b/include/linux/dax.h index 0185ecdae135..f9eb22ad341e 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -26,18 +26,42 @@ extern struct attribute_group dax_attribute_group; #if IS_ENABLED(CONFIG_DAX) struct dax_device *dax_get_by_host(const char *host); +struct dax_device *alloc_dax(void *private, const char *host, + const struct dax_operations *ops); void put_dax(struct dax_device *dax_dev); +void kill_dax(struct dax_device *dax_dev); +void dax_write_cache(struct dax_device *dax_dev, bool wc); +bool dax_write_cache_enabled(struct dax_device *dax_dev); #else static inline struct dax_device *dax_get_by_host(const char *host) { return NULL; } - +static inline struct dax_device *alloc_dax(void *private, const char *host, + const struct dax_operations *ops) +{ + /* + * Callers should check IS_ENABLED(CONFIG_DAX) to know if this + * NULL is an error or expected. + */ + return NULL; +} static inline void put_dax(struct dax_device *dax_dev) { } +static inline void kill_dax(struct dax_device *dax_dev) +{ +} +static inline void dax_write_cache(struct dax_device *dax_dev, bool wc) +{ +} +static inline bool dax_write_cache_enabled(struct dax_device *dax_dev) +{ + return false; +} #endif +struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int __bdev_dax_supported(struct super_block *sb, int blocksize); @@ -57,6 +81,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) } struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc); #else static inline int bdev_dax_supported(struct super_block *sb, int blocksize) { @@ -76,22 +102,23 @@ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { return NULL; } + +static inline int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc) +{ + return -EOPNOTSUPP; +} #endif int dax_read_lock(void); void dax_read_unlock(int id); -struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops); bool dax_alive(struct dax_device *dax_dev); -void kill_dax(struct dax_device *dax_dev); void *dax_get_private(struct dax_device *dax_dev); long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i); void dax_flush(struct dax_device *dax_dev, void *addr, size_t size); -void dax_write_cache(struct dax_device *dax_dev, bool wc); -bool dax_write_cache_enabled(struct dax_device *dax_dev); ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops); @@ -121,7 +148,4 @@ static inline bool dax_mapping(struct address_space *mapping) return mapping->host && IS_DAX(mapping->host); } -struct writeback_control; -int dax_writeback_mapping_range(struct address_space *mapping, - struct block_device *bdev, struct writeback_control *wbc); #endif diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index f838764993eb..861be5cab1df 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -470,7 +470,11 @@ typedef void (*dma_async_tx_callback_result)(void *dma_async_param, const struct dmaengine_result *result); struct dmaengine_unmap_data { +#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID) + u16 map_cnt; +#else u8 map_cnt; +#endif u8 to_cnt; u8 from_cnt; u8 bidi_cnt; diff --git a/include/linux/fs.h b/include/linux/fs.h index 1ee7f592e239..760d8da1b6c7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -13,6 +13,7 @@ #include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> +#include <linux/xarray.h> #include <linux/rbtree.h> #include <linux/init.h> #include <linux/pid.h> @@ -390,12 +391,11 @@ int pagecache_write_end(struct file *, struct address_space *mapping, struct address_space { struct inode *host; /* owner: inode, block_device */ - struct radix_tree_root page_tree; /* radix tree of all pages */ - spinlock_t tree_lock; /* and lock protecting it */ + struct radix_tree_root i_pages; /* cached pages */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ - /* Protected by tree_lock together with the radix tree */ + /* Protected by the i_pages lock */ unsigned long nrpages; /* number of total pages */ /* number of shadow or DAX exceptional entries */ unsigned long nrexceptional; @@ -1667,7 +1667,7 @@ typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { - const filldir_t actor; + filldir_t actor; loff_t pos; }; @@ -1989,7 +1989,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell - * wb stat updates to grab mapping->tree_lock. See + * wb stat updates to grab the i_pages lock. See * inode_switch_wb_work_fn() for details. * * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper @@ -2445,6 +2445,7 @@ extern int sync_blockdev(struct block_device *bdev); extern void kill_bdev(struct block_device *); extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); +extern void emergency_thaw_bdev(struct super_block *sb); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); @@ -2470,6 +2471,11 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) return 0; } +static inline int emergency_thaw_bdev(struct super_block *sb) +{ + return 0; +} + static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } @@ -3127,6 +3133,10 @@ extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); extern int noop_fsync(struct file *, loff_t, loff_t, int); +extern int noop_set_page_dirty(struct page *page); +extern void noop_invalidatepage(struct page *page, unsigned int offset, + unsigned int length); +extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 325017ad9311..39988924de3a 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -80,76 +80,145 @@ struct hmm; /* - * hmm_pfn_t - HMM uses its own pfn type to keep several flags per page + * hmm_pfn_flag_e - HMM flag enums * * Flags: - * HMM_PFN_VALID: pfn is valid - * HMM_PFN_READ: CPU page table has read permission set + * HMM_PFN_VALID: pfn is valid. It has, at least, read permission. * HMM_PFN_WRITE: CPU page table has write permission set + * HMM_PFN_DEVICE_PRIVATE: private device memory (ZONE_DEVICE) + * + * The driver provide a flags array, if driver valid bit for an entry is bit + * 3 ie (entry & (1 << 3)) is true if entry is valid then driver must provide + * an array in hmm_range.flags with hmm_range.flags[HMM_PFN_VALID] == 1 << 3. + * Same logic apply to all flags. This is same idea as vm_page_prot in vma + * except that this is per device driver rather than per architecture. + */ +enum hmm_pfn_flag_e { + HMM_PFN_VALID = 0, + HMM_PFN_WRITE, + HMM_PFN_DEVICE_PRIVATE, + HMM_PFN_FLAG_MAX +}; + +/* + * hmm_pfn_value_e - HMM pfn special value + * + * Flags: * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory - * HMM_PFN_EMPTY: corresponding CPU page table entry is pte_none() + * HMM_PFN_NONE: corresponding CPU page table entry is pte_none() * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the * result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not * be mirrored by a device, because the entry will never have HMM_PFN_VALID * set and the pfn value is undefined. - * HMM_PFN_DEVICE_UNADDRESSABLE: unaddressable device memory (ZONE_DEVICE) + * + * Driver provide entry value for none entry, error entry and special entry, + * driver can alias (ie use same value for error and special for instance). It + * should not alias none and error or special. + * + * HMM pfn value returned by hmm_vma_get_pfns() or hmm_vma_fault() will be: + * hmm_range.values[HMM_PFN_ERROR] if CPU page table entry is poisonous, + * hmm_range.values[HMM_PFN_NONE] if there is no CPU page table + * hmm_range.values[HMM_PFN_SPECIAL] if CPU page table entry is a special one */ -typedef unsigned long hmm_pfn_t; +enum hmm_pfn_value_e { + HMM_PFN_ERROR, + HMM_PFN_NONE, + HMM_PFN_SPECIAL, + HMM_PFN_VALUE_MAX +}; -#define HMM_PFN_VALID (1 << 0) -#define HMM_PFN_READ (1 << 1) -#define HMM_PFN_WRITE (1 << 2) -#define HMM_PFN_ERROR (1 << 3) -#define HMM_PFN_EMPTY (1 << 4) -#define HMM_PFN_SPECIAL (1 << 5) -#define HMM_PFN_DEVICE_UNADDRESSABLE (1 << 6) -#define HMM_PFN_SHIFT 7 +/* + * struct hmm_range - track invalidation lock on virtual address range + * + * @vma: the vm area struct for the range + * @list: all range lock are on a list + * @start: range virtual start address (inclusive) + * @end: range virtual end address (exclusive) + * @pfns: array of pfns (big enough for the range) + * @flags: pfn flags to match device driver page table + * @values: pfn value for some special case (none, special, error, ...) + * @pfn_shifts: pfn shift value (should be <= PAGE_SHIFT) + * @valid: pfns array did not change since it has been fill by an HMM function + */ +struct hmm_range { + struct vm_area_struct *vma; + struct list_head list; + unsigned long start; + unsigned long end; + uint64_t *pfns; + const uint64_t *flags; + const uint64_t *values; + uint8_t pfn_shift; + bool valid; +}; /* - * hmm_pfn_t_to_page() - return struct page pointed to by a valid hmm_pfn_t - * @pfn: hmm_pfn_t to convert to struct page - * Returns: struct page pointer if pfn is a valid hmm_pfn_t, NULL otherwise + * hmm_pfn_to_page() - return struct page pointed to by a valid HMM pfn + * @range: range use to decode HMM pfn value + * @pfn: HMM pfn value to get corresponding struct page from + * Returns: struct page pointer if pfn is a valid HMM pfn, NULL otherwise * - * If the hmm_pfn_t is valid (ie valid flag set) then return the struct page - * matching the pfn value stored in the hmm_pfn_t. Otherwise return NULL. + * If the HMM pfn is valid (ie valid flag set) then return the struct page + * matching the pfn value stored in the HMM pfn. Otherwise return NULL. */ -static inline struct page *hmm_pfn_t_to_page(hmm_pfn_t pfn) +static inline struct page *hmm_pfn_to_page(const struct hmm_range *range, + uint64_t pfn) { - if (!(pfn & HMM_PFN_VALID)) + if (pfn == range->values[HMM_PFN_NONE]) + return NULL; + if (pfn == range->values[HMM_PFN_ERROR]) return NULL; - return pfn_to_page(pfn >> HMM_PFN_SHIFT); + if (pfn == range->values[HMM_PFN_SPECIAL]) + return NULL; + if (!(pfn & range->flags[HMM_PFN_VALID])) + return NULL; + return pfn_to_page(pfn >> range->pfn_shift); } /* - * hmm_pfn_t_to_pfn() - return pfn value store in a hmm_pfn_t - * @pfn: hmm_pfn_t to extract pfn from - * Returns: pfn value if hmm_pfn_t is valid, -1UL otherwise + * hmm_pfn_to_pfn() - return pfn value store in a HMM pfn + * @range: range use to decode HMM pfn value + * @pfn: HMM pfn value to extract pfn from + * Returns: pfn value if HMM pfn is valid, -1UL otherwise */ -static inline unsigned long hmm_pfn_t_to_pfn(hmm_pfn_t pfn) +static inline unsigned long hmm_pfn_to_pfn(const struct hmm_range *range, + uint64_t pfn) { - if (!(pfn & HMM_PFN_VALID)) + if (pfn == range->values[HMM_PFN_NONE]) + return -1UL; + if (pfn == range->values[HMM_PFN_ERROR]) + return -1UL; + if (pfn == range->values[HMM_PFN_SPECIAL]) + return -1UL; + if (!(pfn & range->flags[HMM_PFN_VALID])) return -1UL; - return (pfn >> HMM_PFN_SHIFT); + return (pfn >> range->pfn_shift); } /* - * hmm_pfn_t_from_page() - create a valid hmm_pfn_t value from struct page - * @page: struct page pointer for which to create the hmm_pfn_t - * Returns: valid hmm_pfn_t for the page + * hmm_pfn_from_page() - create a valid HMM pfn value from struct page + * @range: range use to encode HMM pfn value + * @page: struct page pointer for which to create the HMM pfn + * Returns: valid HMM pfn for the page */ -static inline hmm_pfn_t hmm_pfn_t_from_page(struct page *page) +static inline uint64_t hmm_pfn_from_page(const struct hmm_range *range, + struct page *page) { - return (page_to_pfn(page) << HMM_PFN_SHIFT) | HMM_PFN_VALID; + return (page_to_pfn(page) << range->pfn_shift) | + range->flags[HMM_PFN_VALID]; } /* - * hmm_pfn_t_from_pfn() - create a valid hmm_pfn_t value from pfn - * @pfn: pfn value for which to create the hmm_pfn_t - * Returns: valid hmm_pfn_t for the pfn + * hmm_pfn_from_pfn() - create a valid HMM pfn value from pfn + * @range: range use to encode HMM pfn value + * @pfn: pfn value for which to create the HMM pfn + * Returns: valid HMM pfn for the pfn */ -static inline hmm_pfn_t hmm_pfn_t_from_pfn(unsigned long pfn) +static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, + unsigned long pfn) { - return (pfn << HMM_PFN_SHIFT) | HMM_PFN_VALID; + return (pfn << range->pfn_shift) | + range->flags[HMM_PFN_VALID]; } @@ -218,6 +287,16 @@ enum hmm_update_type { * @update: callback to update range on a device */ struct hmm_mirror_ops { + /* release() - release hmm_mirror + * + * @mirror: pointer to struct hmm_mirror + * + * This is called when the mm_struct is being released. + * The callback should make sure no references to the mirror occur + * after the callback returns. + */ + void (*release)(struct hmm_mirror *mirror); + /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror @@ -262,23 +341,6 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror); /* - * struct hmm_range - track invalidation lock on virtual address range - * - * @list: all range lock are on a list - * @start: range virtual start address (inclusive) - * @end: range virtual end address (exclusive) - * @pfns: array of pfns (big enough for the range) - * @valid: pfns array did not change since it has been fill by an HMM function - */ -struct hmm_range { - struct list_head list; - unsigned long start; - unsigned long end; - hmm_pfn_t *pfns; - bool valid; -}; - -/* * To snapshot the CPU page table, call hmm_vma_get_pfns(), then take a device * driver lock that serializes device page table updates, then call * hmm_vma_range_done(), to check if the snapshot is still valid. The same @@ -291,17 +353,13 @@ struct hmm_range { * * IF YOU DO NOT FOLLOW THE ABOVE RULE THE SNAPSHOT CONTENT MIGHT BE INVALID ! */ -int hmm_vma_get_pfns(struct vm_area_struct *vma, - struct hmm_range *range, - unsigned long start, - unsigned long end, - hmm_pfn_t *pfns); -bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range); +int hmm_vma_get_pfns(struct hmm_range *range); +bool hmm_vma_range_done(struct hmm_range *range); /* * Fault memory on behalf of device driver. Unlike handle_mm_fault(), this will - * not migrate any device memory back to system memory. The hmm_pfn_t array will + * not migrate any device memory back to system memory. The HMM pfn array will * be updated with the fault result and current snapshot of the CPU page table * for the range. * @@ -310,22 +368,26 @@ bool hmm_vma_range_done(struct vm_area_struct *vma, struct hmm_range *range); * function returns -EAGAIN. * * Return value does not reflect if the fault was successful for every single - * address or not. Therefore, the caller must to inspect the hmm_pfn_t array to + * address or not. Therefore, the caller must to inspect the HMM pfn array to * determine fault status for each address. * * Trying to fault inside an invalid vma will result in -EINVAL. * * See the function description in mm/hmm.c for further documentation. */ -int hmm_vma_fault(struct vm_area_struct *vma, - struct hmm_range *range, - unsigned long start, - unsigned long end, - hmm_pfn_t *pfns, - bool write, - bool block); -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +int hmm_vma_fault(struct hmm_range *range, bool block); +/* Below are for HMM internal use only! Not to be used by device driver! */ +void hmm_mm_destroy(struct mm_struct *mm); + +static inline void hmm_mm_init(struct mm_struct *mm) +{ + mm->hmm = NULL; +} +#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) || IS_ENABLED(CONFIG_DEVICE_PUBLIC) struct hmm_devmem; @@ -498,23 +560,9 @@ struct hmm_device { struct hmm_device *hmm_device_new(void *drvdata); void hmm_device_put(struct hmm_device *hmm_device); #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ -#endif /* IS_ENABLED(CONFIG_HMM) */ - -/* Below are for HMM internal use only! Not to be used by device driver! */ -#if IS_ENABLED(CONFIG_HMM_MIRROR) -void hmm_mm_destroy(struct mm_struct *mm); - -static inline void hmm_mm_init(struct mm_struct *mm) -{ - mm->hmm = NULL; -} -#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ -static inline void hmm_mm_destroy(struct mm_struct *mm) {} -static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ - - #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* IS_ENABLED(CONFIG_HMM) */ + #endif /* LINUX_HMM_H */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 78f456fcd242..a2656c3ebe81 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -424,6 +424,7 @@ static inline ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } extern u64 hrtimer_get_next_event(void); +extern u64 hrtimer_next_event_without(const struct hrtimer *exclude); extern bool hrtimer_active(const struct hrtimer *timer); diff --git a/include/linux/idr.h b/include/linux/idr.h index 7d6a6313f0ab..e856f4e0ab35 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -29,29 +29,31 @@ struct idr { #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ -#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) +#define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ + (1 << (ROOT_TAG_SHIFT + IDR_FREE))) -#define IDR_INIT_BASE(base) { \ - .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER), \ +#define IDR_INIT_BASE(name, base) { \ + .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. + * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ -#define IDR_INIT IDR_INIT_BASE(0) +#define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** - * DEFINE_IDR() - Define a statically-allocated IDR - * @name: Name of IDR + * DEFINE_IDR() - Define a statically-allocated IDR. + * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ -#define DEFINE_IDR(name) struct idr name = IDR_INIT +#define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator @@ -218,10 +220,10 @@ struct ida { struct radix_tree_root ida_rt; }; -#define IDA_INIT { \ - .ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT), \ +#define IDA_INIT(name) { \ + .ida_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER | GFP_NOWAIT), \ } -#define DEFINE_IDA(name) struct ida name = IDA_INIT +#define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_pre_get(struct ida *ida, gfp_t gfp_mask); int ida_get_new_above(struct ida *ida, int starting_id, int *p_id); diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 8dad3dd26eae..ef169d67df92 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -209,12 +209,12 @@ #define DMA_FECTL_IM (((u32)1) << 31) /* FSTS_REG */ -#define DMA_FSTS_PPF ((u32)2) -#define DMA_FSTS_PFO ((u32)1) -#define DMA_FSTS_IQE (1 << 4) -#define DMA_FSTS_ICE (1 << 5) -#define DMA_FSTS_ITE (1 << 6) -#define DMA_FSTS_PRO (1 << 7) +#define DMA_FSTS_PFO (1 << 0) /* Primary Fault Overflow */ +#define DMA_FSTS_PPF (1 << 1) /* Primary Pending Fault */ +#define DMA_FSTS_IQE (1 << 4) /* Invalidation Queue Error */ +#define DMA_FSTS_ICE (1 << 5) /* Invalidation Completion Error */ +#define DMA_FSTS_ITE (1 << 6) /* Invalidation Time-out Error */ +#define DMA_FSTS_PRO (1 << 7) /* Page Request Overflow */ #define dma_fsts_fault_record_index(s) (((s) >> 8) & 0xff) /* FRCD_REG, 32 bits access */ diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 41b8c5757859..19938ee6eb31 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -465,23 +465,23 @@ static inline int iommu_map(struct iommu_domain *domain, unsigned long iova, return -ENODEV; } -static inline int iommu_unmap(struct iommu_domain *domain, unsigned long iova, - size_t size) +static inline size_t iommu_unmap(struct iommu_domain *domain, + unsigned long iova, size_t size) { - return -ENODEV; + return 0; } -static inline int iommu_unmap_fast(struct iommu_domain *domain, unsigned long iova, - int gfp_order) +static inline size_t iommu_unmap_fast(struct iommu_domain *domain, + unsigned long iova, int gfp_order) { - return -ENODEV; + return 0; } static inline size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova, struct scatterlist *sg, unsigned int nents, int prot) { - return -ENODEV; + return 0; } static inline void iommu_flush_tlb_all(struct iommu_domain *domain) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 9385aa57497b..a27cf6652327 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -62,8 +62,11 @@ extern int register_refined_jiffies(long clock_tick_rate); /* TICK_NSEC is the time between ticks in nsec assuming SHIFTED_HZ */ #define TICK_NSEC ((NSEC_PER_SEC+HZ/2)/HZ) -/* TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ -#define TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) +/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */ +#define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ) + +/* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */ +#define USER_TICK_USEC ((1000000UL + USER_HZ/2) / USER_HZ) #ifndef __jiffy_arch_data #define __jiffy_arch_data diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 52b70894eaa5..6a1eb0b0aad9 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -439,7 +439,8 @@ 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); +extern int num_to_str(char *buf, int size, + unsigned long long num, unsigned int width); /* lib/printf utilities */ @@ -543,6 +544,7 @@ extern enum system_states { SYSTEM_RESTART, } 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 @@ -560,7 +562,8 @@ extern enum system_states { #define TAINT_SOFTLOCKUP 14 #define TAINT_LIVEPATCH 15 #define TAINT_AUX 16 -#define TAINT_FLAGS_COUNT 17 +#define TAINT_RANDSTRUCT 17 +#define TAINT_FLAGS_COUNT 18 struct taint_flag { char c_true; /* character printed when tainted */ diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h index e251533a5939..89fc8dc7bf38 100644 --- a/include/linux/kfifo.h +++ b/include/linux/kfifo.h @@ -41,11 +41,11 @@ */ /* - * Note about locking : There is no locking required until only * one reader - * and one writer is using the fifo and no kfifo_reset() will be * called - * kfifo_reset_out() can be safely used, until it will be only called + * Note about locking: There is no locking required until only one reader + * and one writer is using the fifo and no kfifo_reset() will be called. + * kfifo_reset_out() can be safely used, until it will be only called * in the reader thread. - * For multiple writer and one reader there is only a need to lock the writer. + * For multiple writer and one reader there is only a need to lock the writer. * And vice versa for only one writer and multiple reader there is only a need * to lock the reader. */ diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index ff855ed965fb..097072c5a852 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -76,12 +76,14 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm, unsigned int cmd, void *buf, unsigned int buf_len, int *cmd_rc); +struct device_node; struct nvdimm_bus_descriptor { const struct attribute_group **attr_groups; unsigned long bus_dsm_mask; unsigned long cmd_mask; struct module *module; char *provider_name; + struct device_node *of_node; ndctl_fn ndctl; int (*flush_probe)(struct nvdimm_bus_descriptor *nd_desc); int (*clear_to_send)(struct nvdimm_bus_descriptor *nd_desc, @@ -123,6 +125,7 @@ struct nd_region_desc { int num_lanes; int numa_node; unsigned long flags; + struct device_node *of_node; }; struct device; @@ -164,6 +167,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus); struct nvdimm_bus *to_nvdimm_bus(struct device *dev); struct nvdimm *to_nvdimm(struct device *dev); struct nd_region *to_nd_region(struct device *dev); +struct device *nd_region_dev(struct nd_region *nd_region); struct nd_blk_region *to_nd_blk_region(struct device *dev); struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus); struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus); diff --git a/include/linux/lockref.h b/include/linux/lockref.h index 2eac32095113..99f17cc8e163 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -37,6 +37,7 @@ struct lockref { extern void lockref_get(struct lockref *); extern int lockref_put_return(struct lockref *); extern int lockref_get_not_zero(struct lockref *); +extern int lockref_put_not_zero(struct lockref *); extern int lockref_get_or_lock(struct lockref *); extern int lockref_put_or_lock(struct lockref *); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index c46016bb25eb..d99b71bc2c66 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -48,13 +48,12 @@ enum memcg_stat_item { MEMCG_NR_STAT, }; -/* Cgroup-specific events, on top of universal VM events */ -enum memcg_event_item { - MEMCG_LOW = NR_VM_EVENT_ITEMS, +enum memcg_memory_event { + MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, - MEMCG_NR_EVENTS, + MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { @@ -88,7 +87,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEMCG_NR_STAT]; - unsigned long events[MEMCG_NR_EVENTS]; + unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -120,6 +119,9 @@ struct mem_cgroup_per_node { unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; + bool congested; /* memcg has many dirty pages */ + /* backed by a congested BDI */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -202,7 +204,8 @@ struct mem_cgroup { /* OOM-Killer disable */ int oom_kill_disable; - /* handle for "memory.events" */ + /* memory.events */ + atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; struct cgroup_file events_file; /* protect arrays of thresholds */ @@ -231,9 +234,10 @@ struct mem_cgroup { struct task_struct *move_lock_task; unsigned long move_lock_flags; + /* memory.stat */ struct mem_cgroup_stat_cpu __percpu *stat_cpu; atomic_long_t stat[MEMCG_NR_STAT]; - atomic_long_t events[MEMCG_NR_EVENTS]; + atomic_long_t events[NR_VM_EVENT_ITEMS]; unsigned long socket_pressure; @@ -645,9 +649,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void __count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long x; @@ -663,7 +667,8 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg, } static inline void count_memcg_events(struct mem_cgroup *memcg, - int idx, unsigned long count) + enum vm_event_item idx, + unsigned long count) { unsigned long flags; @@ -672,9 +677,8 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, local_irq_restore(flags); } -/* idx can be of type enum memcg_event_item or vm_event_item */ static inline void count_memcg_page_event(struct page *page, - int idx) + enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); @@ -698,10 +702,10 @@ static inline void count_memcg_event_mm(struct mm_struct *mm, rcu_read_unlock(); } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { - count_memcg_events(memcg, event, 1); + atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); } @@ -721,8 +725,8 @@ static inline bool mem_cgroup_disabled(void) return true; } -static inline void mem_cgroup_event(struct mem_cgroup *memcg, - enum memcg_event_item event) +static inline void memcg_memory_event(struct mem_cgroup *memcg, + enum memcg_memory_event event) { } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 2b0265265c28..e0e49b5b1ee1 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -216,9 +216,6 @@ void put_online_mems(void); void mem_hotplug_begin(void); void mem_hotplug_done(void); -extern void set_zone_contiguous(struct zone *zone); -extern void clear_zone_contiguous(struct zone *zone); - #else /* ! CONFIG_MEMORY_HOTPLUG */ #define pfn_to_online_page(pfn) \ ({ \ diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h index 48c3c5be7eb1..9ed2871ea335 100644 --- a/include/linux/mfd/samsung/rtc.h +++ b/include/linux/mfd/samsung/rtc.h @@ -141,15 +141,4 @@ enum s2mps_rtc_reg { #define WTSR_ENABLE_SHIFT 6 #define WTSR_ENABLE_MASK (1 << WTSR_ENABLE_SHIFT) -enum { - RTC_SEC = 0, - RTC_MIN, - RTC_HOUR, - RTC_WEEKDAY, - RTC_DATE, - RTC_MONTH, - RTC_YEAR1, - RTC_YEAR2, -}; - #endif /* __LINUX_MFD_SEC_RTC_H */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index ab45f8a0d288..f2b4abbca55e 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -7,8 +7,7 @@ #include <linux/migrate_mode.h> #include <linux/hugetlb.h> -typedef struct page *new_page_t(struct page *page, unsigned long private, - int **reason); +typedef struct page *new_page_t(struct page *page, unsigned long private); typedef void free_page_t(struct page *page, unsigned long private); /* @@ -43,9 +42,9 @@ static inline struct page *new_page_nodemask(struct page *page, return alloc_huge_page_nodemask(page_hstate(compound_head(page)), preferred_nid, nodemask); - if (thp_migration_supported() && PageTransHuge(page)) { - order = HPAGE_PMD_ORDER; + if (PageTransHuge(page)) { gfp_mask |= GFP_TRANSHUGE; + order = HPAGE_PMD_ORDER; } if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) diff --git a/include/linux/mm.h b/include/linux/mm.h index 3ad632366973..1ac1f06a4be6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -747,7 +747,7 @@ int finish_mkwrite_fault(struct vm_fault *vmf); * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is - * rooted at mapping->page_tree, and indexed by offset. + * rooted at mapping->i_pages, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * @@ -1466,6 +1466,7 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); +void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); int redirty_page_for_writepage(struct writeback_control *wbc, @@ -2108,6 +2109,7 @@ extern void setup_per_cpu_pageset(void); extern void zone_pcp_update(struct zone *zone); extern void zone_pcp_reset(struct zone *zone); +extern void setup_zone_pageset(struct zone *zone); /* page_alloc.c */ extern int min_free_kbytes; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f11ae29005f1..32699b2dc52a 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,6 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ NR_VM_NODE_STAT_ITEMS }; @@ -884,7 +885,7 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); -extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1]; +extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES]; int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *); int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, diff --git a/include/linux/nd.h b/include/linux/nd.h index 5dc6b695437d..43c181a6add5 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -180,6 +180,12 @@ struct nd_region; void nvdimm_region_notify(struct nd_region *nd_region, enum nvdimm_event event); int __must_check __nd_driver_register(struct nd_device_driver *nd_drv, struct module *module, const char *mod_name); +static inline void nd_driver_unregister(struct nd_device_driver *drv) +{ + driver_unregister(&drv->drv); +} #define nd_driver_register(driver) \ __nd_driver_register(driver, THIS_MODULE, KBUILD_MODNAME) +#define module_nd_driver(driver) \ + module_driver(driver, nd_driver_register, nd_driver_unregister) #endif /* __LINUX_ND_H__ */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 38187c68063d..2f129bbfaae8 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -198,14 +198,24 @@ struct nfs_inode { /* * Cache validity bit flags */ -#define NFS_INO_INVALID_ATTR 0x0001 /* cached attrs are invalid */ -#define NFS_INO_INVALID_DATA 0x0002 /* cached data is invalid */ -#define NFS_INO_INVALID_ATIME 0x0004 /* cached atime is invalid */ -#define NFS_INO_INVALID_ACCESS 0x0008 /* cached access cred invalid */ -#define NFS_INO_INVALID_ACL 0x0010 /* cached acls are invalid */ -#define NFS_INO_REVAL_PAGECACHE 0x0020 /* must revalidate pagecache */ -#define NFS_INO_REVAL_FORCED 0x0040 /* force revalidation ignoring a delegation */ -#define NFS_INO_INVALID_LABEL 0x0080 /* cached label is invalid */ +#define NFS_INO_INVALID_DATA BIT(1) /* cached data is invalid */ +#define NFS_INO_INVALID_ATIME BIT(2) /* cached atime is invalid */ +#define NFS_INO_INVALID_ACCESS BIT(3) /* cached access cred invalid */ +#define NFS_INO_INVALID_ACL BIT(4) /* cached acls are invalid */ +#define NFS_INO_REVAL_PAGECACHE BIT(5) /* must revalidate pagecache */ +#define NFS_INO_REVAL_FORCED BIT(6) /* force revalidation ignoring a delegation */ +#define NFS_INO_INVALID_LABEL BIT(7) /* cached label is invalid */ +#define NFS_INO_INVALID_CHANGE BIT(8) /* cached change is invalid */ +#define NFS_INO_INVALID_CTIME BIT(9) /* cached ctime is invalid */ +#define NFS_INO_INVALID_MTIME BIT(10) /* cached mtime is invalid */ +#define NFS_INO_INVALID_SIZE BIT(11) /* cached size is invalid */ +#define NFS_INO_INVALID_OTHER BIT(12) /* other attrs are invalid */ + +#define NFS_INO_INVALID_ATTR (NFS_INO_INVALID_CHANGE \ + | NFS_INO_INVALID_CTIME \ + | NFS_INO_INVALID_MTIME \ + | NFS_INO_INVALID_SIZE \ + | NFS_INO_INVALID_OTHER) /* inode metadata is invalid */ /* * Bit offsets in flags field @@ -292,10 +302,11 @@ static inline void nfs_mark_for_revalidate(struct inode *inode) struct nfs_inode *nfsi = NFS_I(inode); spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR | - NFS_INO_REVAL_PAGECACHE | - NFS_INO_INVALID_ACCESS | - NFS_INO_INVALID_ACL; + nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE + | NFS_INO_INVALID_ACCESS + | NFS_INO_INVALID_ACL + | NFS_INO_INVALID_CHANGE + | NFS_INO_INVALID_CTIME; if (S_ISDIR(inode->i_mode)) nfsi->cache_validity |= NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 6959968dc36a..34d28564ecf3 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1590,11 +1590,13 @@ struct nfs_rpc_ops { unsigned int); int (*create) (struct inode *, struct dentry *, struct iattr *, int); - int (*remove) (struct inode *, const struct qstr *); - void (*unlink_setup) (struct rpc_message *, struct inode *dir); + int (*remove) (struct inode *, struct dentry *); + void (*unlink_setup) (struct rpc_message *, struct dentry *); void (*unlink_rpc_prepare) (struct rpc_task *, struct nfs_unlinkdata *); int (*unlink_done) (struct rpc_task *, struct inode *); - void (*rename_setup) (struct rpc_message *msg, struct inode *dir); + void (*rename_setup) (struct rpc_message *msg, + struct dentry *old_dentry, + struct dentry *new_dentry); void (*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *); int (*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir); int (*link) (struct inode *, struct inode *, const struct qstr *); @@ -1633,7 +1635,6 @@ struct nfs_rpc_ops { struct iattr *iattr, int *); int (*have_delegation)(struct inode *, fmode_t); - int (*return_delegation)(struct inode *); struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *); struct nfs_client *(*init_client) (struct nfs_client *, const struct nfs_client_initdata *); diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index cdad58bbfd8b..4ae347cbc36d 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -63,7 +63,6 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn, bool skip_hwpoisoned_pages); -struct page *alloc_migrate_target(struct page *page, unsigned long private, - int **resultp); +struct page *alloc_migrate_target(struct page *page, unsigned long private); #endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 34ce3ebf97d5..b1bd2186e6d2 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -144,7 +144,7 @@ void release_pages(struct page **pages, int nr); * 3. check the page is still in pagecache (if no, goto 1) * * Remove-side that cares about stability of _refcount (eg. reclaim) has the - * following (with tree_lock held for write): + * following (with the i_pages lock held): * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) * B. remove page from pagecache * C. free the page @@ -157,7 +157,7 @@ void release_pages(struct page **pages, int nr); * * It is possible that between 1 and 2, the page is removed then the exact same * page is inserted into the same position in pagecache. That's OK: the - * old find_get_page using tree_lock could equally have run before or after + * old find_get_page using a lock could equally have run before or after * such a re-insertion, depending on order that locks are granted. * * Lookups racing against pagecache insertion isn't a big problem: either 1 diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index fcdc707eab99..2744cff1b297 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -129,6 +129,8 @@ struct mlxreg_core_platform_data { * @mask: top aggregation interrupt common mask; * @cell_low: location of low aggregation interrupt register; * @mask_low: low aggregation interrupt common mask; + * @deferred_nr: I2C adapter number must be exist prior probing execution; + * @shift_nr: I2C adapter numbers must be incremented by this value; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -139,6 +141,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask; u32 cell_low; u32 mask_low; + int deferred_nr; + int shift_nr; }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index fc55ff31eca7..34149e8b5f73 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -104,25 +104,29 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* The top bits of gfp_mask are used to store the root tags and the IDR flag */ -#define ROOT_IS_IDR ((__force gfp_t)(1 << __GFP_BITS_SHIFT)) -#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT + 1) +/* The IDR tag is stored in the low bits of the GFP flags */ +#define ROOT_IS_IDR ((__force gfp_t)4) +/* The top bits of gfp_mask are used to store the root tags */ +#define ROOT_TAG_SHIFT (__GFP_BITS_SHIFT) struct radix_tree_root { + spinlock_t xa_lock; gfp_t gfp_mask; struct radix_tree_node __rcu *rnode; }; -#define RADIX_TREE_INIT(mask) { \ +#define RADIX_TREE_INIT(name, mask) { \ + .xa_lock = __SPIN_LOCK_UNLOCKED(name.xa_lock), \ .gfp_mask = (mask), \ .rnode = NULL, \ } #define RADIX_TREE(name, mask) \ - struct radix_tree_root name = RADIX_TREE_INIT(mask) + struct radix_tree_root name = RADIX_TREE_INIT(name, mask) #define INIT_RADIX_TREE(root, mask) \ do { \ + spin_lock_init(&(root)->xa_lock); \ (root)->gfp_mask = (mask); \ (root)->rnode = NULL; \ } while (0) diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 728d421fffe9..d09a9c7af109 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -344,7 +344,7 @@ struct rproc_ops { int (*stop)(struct rproc *rproc); void (*kick)(struct rproc *rproc, int vqid); void * (*da_to_va)(struct rproc *rproc, u64 da, int len); - int (*load_rsc_table)(struct rproc *rproc, const struct firmware *fw); + int (*parse_fw)(struct rproc *rproc, const struct firmware *fw); struct resource_table *(*find_loaded_rsc_table)( struct rproc *rproc, const struct firmware *fw); int (*load)(struct rproc *rproc, const struct firmware *fw); @@ -395,6 +395,21 @@ enum rproc_crash_type { }; /** + * struct rproc_dump_segment - segment info from ELF header + * @node: list node related to the rproc segment list + * @da: device address of the segment + * @size: size of the segment + */ +struct rproc_dump_segment { + struct list_head node; + + dma_addr_t da; + size_t size; + + loff_t offset; +}; + +/** * struct rproc - represents a physical remote processor device * @node: list node of this rproc object * @domain: iommu domain @@ -424,6 +439,7 @@ enum rproc_crash_type { * @cached_table: copy of the resource table * @table_sz: size of @cached_table * @has_iommu: flag to indicate if remote processor is behind an MMU + * @dump_segments: list of segments in the firmware */ struct rproc { struct list_head node; @@ -455,19 +471,21 @@ struct rproc { size_t table_sz; bool has_iommu; bool auto_boot; + struct list_head dump_segments; }; /** * struct rproc_subdev - subdevice tied to a remoteproc * @node: list node related to the rproc subdevs list * @probe: probe function, called as the rproc is started - * @remove: remove function, called as the rproc is stopped + * @remove: remove function, called as the rproc is being stopped, the @crashed + * parameter indicates if this originates from the a recovery */ struct rproc_subdev { struct list_head node; int (*probe)(struct rproc_subdev *subdev); - void (*remove)(struct rproc_subdev *subdev); + void (*remove)(struct rproc_subdev *subdev, bool crashed); }; /* we currently support only two vrings per rvdev */ @@ -534,6 +552,7 @@ void rproc_free(struct rproc *rproc); int rproc_boot(struct rproc *rproc); void rproc_shutdown(struct rproc *rproc); void rproc_report_crash(struct rproc *rproc, enum rproc_crash_type type); +int rproc_coredump_add_segment(struct rproc *rproc, dma_addr_t da, size_t size); static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) { @@ -550,7 +569,7 @@ static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev, int (*probe)(struct rproc_subdev *subdev), - void (*remove)(struct rproc_subdev *subdev)); + void (*remove)(struct rproc_subdev *subdev, bool graceful)); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 7d9eb39fa76a..a0233edc0718 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -34,10 +34,12 @@ struct ring_buffer_event { * array[0] = time delta (28 .. 59) * size = 8 bytes * - * @RINGBUF_TYPE_TIME_STAMP: Sync time stamp with external clock - * array[0] = tv_nsec - * array[1..2] = tv_sec - * size = 16 bytes + * @RINGBUF_TYPE_TIME_STAMP: Absolute timestamp + * Same format as TIME_EXTEND except that the + * value is an absolute timestamp, not a delta + * event.time_delta contains bottom 27 bits + * array[0] = top (28 .. 59) bits + * size = 8 bytes * * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX: * Data record @@ -54,12 +56,12 @@ enum ring_buffer_type { RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28, RINGBUF_TYPE_PADDING, RINGBUF_TYPE_TIME_EXTEND, - /* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */ RINGBUF_TYPE_TIME_STAMP, }; unsigned ring_buffer_event_length(struct ring_buffer_event *event); void *ring_buffer_event_data(struct ring_buffer_event *event); +u64 ring_buffer_event_time_stamp(struct ring_buffer_event *event); /* * ring_buffer_discard_commit will remove an event that has not @@ -115,6 +117,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer, int ring_buffer_write(struct ring_buffer *buffer, unsigned long length, void *data); +void ring_buffer_nest_start(struct ring_buffer *buffer); +void ring_buffer_nest_end(struct ring_buffer *buffer); + struct ring_buffer_event * ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts, unsigned long *lost_events); @@ -178,6 +183,8 @@ void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer, int cpu, u64 *ts); void ring_buffer_set_clock(struct ring_buffer *buffer, u64 (*clock)(void)); +void ring_buffer_set_time_stamp_abs(struct ring_buffer *buffer, bool abs); +bool ring_buffer_time_stamp_abs(struct ring_buffer *buffer); size_t ring_buffer_page_len(void *page); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index fc6c90b57be0..4c007f69082f 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -145,12 +145,17 @@ struct rtc_device { bool registered; - struct nvmem_config *nvmem_config; struct nvmem_device *nvmem; /* Old ABI support */ bool nvram_old_abi; struct bin_attribute *nvram; + time64_t range_min; + timeu64_t range_max; + time64_t start_secs; + time64_t offset_secs; + bool set_start_time; + #ifdef CONFIG_RTC_INTF_DEV_UIE_EMUL struct work_struct uie_task; struct timer_list uie_timer; @@ -164,6 +169,11 @@ struct rtc_device { }; #define to_rtc_device(d) container_of(d, struct rtc_device, dev) +/* useful timestamps */ +#define RTC_TIMESTAMP_BEGIN_1900 -2208989361LL /* 1900-01-01 00:00:00 */ +#define RTC_TIMESTAMP_BEGIN_2000 946684800LL /* 2000-01-01 00:00:00 */ +#define RTC_TIMESTAMP_END_2099 4102444799LL /* 2099-12-31 23:59:59 */ + extern struct rtc_device *rtc_device_register(const char *name, struct device *dev, const struct rtc_class_ops *ops, @@ -212,10 +222,6 @@ void rtc_aie_update_irq(void *private); void rtc_uie_update_irq(void *private); enum hrtimer_restart rtc_pie_update_irq(struct hrtimer *timer); -int rtc_register(rtc_task_t *task); -int rtc_unregister(rtc_task_t *task); -int rtc_control(rtc_task_t *t, unsigned int cmd, unsigned long arg); - void rtc_timer_init(struct rtc_timer *timer, void (*f)(void *p), void *data); int rtc_timer_start(struct rtc_device *rtc, struct rtc_timer *timer, ktime_t expires, ktime_t period); @@ -271,4 +277,17 @@ extern int rtc_hctosys_ret; #define rtc_hctosys_ret -ENODEV #endif +#ifdef CONFIG_RTC_NVMEM +int rtc_nvmem_register(struct rtc_device *rtc, + struct nvmem_config *nvmem_config); +void rtc_nvmem_unregister(struct rtc_device *rtc); +#else +static inline int rtc_nvmem_register(struct rtc_device *rtc, + struct nvmem_config *nvmem_config) +{ + return -ENODEV; +} +static inline void rtc_nvmem_unregister(struct rtc_device *rtc) {} +#endif + #endif /* _LINUX_RTC_H_ */ diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 9806184bb3d5..2c570cd934af 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -104,7 +104,8 @@ static inline void mm_update_next_owner(struct mm_struct *mm) #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU -extern void arch_pick_mmap_layout(struct mm_struct *mm); +extern void arch_pick_mmap_layout(struct mm_struct *mm, + struct rlimit *rlim_stack); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); @@ -113,7 +114,8 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #else -static inline void arch_pick_mmap_layout(struct mm_struct *mm) {} +static inline void arch_pick_mmap_layout(struct mm_struct *mm, + struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index ab437dd2e3b9..a121982af0f5 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -118,9 +118,14 @@ __printf(2, 3) void seq_printf(struct seq_file *m, const char *fmt, ...); void seq_putc(struct seq_file *m, char c); void seq_puts(struct seq_file *m, const char *s); +void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, + unsigned long long num, unsigned int width); void seq_put_decimal_ull(struct seq_file *m, const char *delimiter, unsigned long long num); 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(struct seq_file *m, const char *s, const char *esc); void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, @@ -235,4 +240,5 @@ extern struct hlist_node *seq_hlist_start_percpu(struct hlist_head __percpu *hea extern struct hlist_node *seq_hlist_next_percpu(void *v, struct hlist_head __percpu *head, int *cpu, loff_t *pos); +void seq_file_init(void); #endif diff --git a/include/linux/soc/qcom/mdt_loader.h b/include/linux/soc/qcom/mdt_loader.h index bd8e0864b059..5b98bbdabc25 100644 --- a/include/linux/soc/qcom/mdt_loader.h +++ b/include/linux/soc/qcom/mdt_loader.h @@ -14,6 +14,7 @@ struct firmware; ssize_t qcom_mdt_get_size(const struct firmware *fw); int qcom_mdt_load(struct device *dev, const struct firmware *fw, const char *fw_name, int pas_id, void *mem_region, - phys_addr_t mem_phys, size_t mem_size); + phys_addr_t mem_phys, size_t mem_size, + phys_addr_t *reloc_base); #endif diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index ed761f751ecb..9b11b6a0978c 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -217,5 +217,12 @@ void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *, struct rpc_xprt *); bool rpc_clnt_xprt_switch_has_addr(struct rpc_clnt *clnt, const struct sockaddr *sap); void rpc_cleanup_clids(void); + +static inline int rpc_reply_expected(struct rpc_task *task) +{ + return (task->tk_msg.rpc_proc != NULL) && + (task->tk_msg.rpc_proc->p_decode != NULL); +} + #endif /* __KERNEL__ */ #endif /* _LINUX_SUNRPC_CLNT_H */ diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index d950223c64b1..2bd68177a442 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -253,6 +253,12 @@ xdr_stream_remaining(const struct xdr_stream *xdr) return xdr->nwords << 2; } +ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, + size_t size); +ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr, + size_t maxlen, gfp_t gfp_flags); +ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, + size_t size); ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str, size_t maxlen, gfp_t gfp_flags); /** @@ -313,6 +319,31 @@ xdr_stream_encode_u64(struct xdr_stream *xdr, __u64 n) } /** + * xdr_stream_encode_opaque_inline - Encode opaque xdr data + * @xdr: pointer to xdr_stream + * @ptr: pointer to void pointer + * @len: size of object + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t len) +{ + size_t count = sizeof(__u32) + xdr_align_size(len); + __be32 *p = xdr_reserve_space(xdr, count); + + if (unlikely(!p)) { + *ptr = NULL; + return -EMSGSIZE; + } + xdr_encode_opaque(p, NULL, len); + *ptr = ++p; + return count; +} + +/** * xdr_stream_encode_opaque_fixed - Encode fixed length opaque xdr data * @xdr: pointer to xdr_stream * @ptr: pointer to opaque data object @@ -356,6 +387,31 @@ xdr_stream_encode_opaque(struct xdr_stream *xdr, const void *ptr, size_t len) } /** + * xdr_stream_encode_uint32_array - Encode variable length array of integers + * @xdr: pointer to xdr_stream + * @array: array of integers + * @array_size: number of elements in @array + * + * Return values: + * On success, returns length in bytes of XDR buffer consumed + * %-EMSGSIZE on XDR buffer overflow + */ +static inline ssize_t +xdr_stream_encode_uint32_array(struct xdr_stream *xdr, + const __u32 *array, size_t array_size) +{ + ssize_t ret = (array_size+1) * sizeof(__u32); + __be32 *p = xdr_reserve_space(xdr, ret); + + if (unlikely(!p)) + return -EMSGSIZE; + *p++ = cpu_to_be32(array_size); + for (; array_size > 0; p++, array++, array_size--) + *p = cpu_to_be32p(array); + return ret; +} + +/** * xdr_stream_decode_u32 - Decode a 32-bit integer * @xdr: pointer to xdr_stream * @ptr: location to store integer @@ -432,6 +488,44 @@ xdr_stream_decode_opaque_inline(struct xdr_stream *xdr, void **ptr, size_t maxle } return len; } + +/** + * xdr_stream_decode_uint32_array - Decode variable length array of integers + * @xdr: pointer to xdr_stream + * @array: location to store the integer array or NULL + * @array_size: number of elements to store + * + * Return values: + * On success, returns number of elements stored in @array + * %-EBADMSG on XDR buffer overflow + * %-EMSGSIZE if the size of the array exceeds @array_size + */ +static inline ssize_t +xdr_stream_decode_uint32_array(struct xdr_stream *xdr, + __u32 *array, size_t array_size) +{ + __be32 *p; + __u32 len; + ssize_t retval; + + if (unlikely(xdr_stream_decode_u32(xdr, &len) < 0)) + return -EBADMSG; + p = xdr_inline_decode(xdr, len * sizeof(*p)); + if (unlikely(!p)) + return -EBADMSG; + if (array == NULL) + return len; + if (len <= array_size) { + if (len < array_size) + memset(array+len, 0, (array_size-len)*sizeof(*array)); + array_size = len; + retval = len; + } else + retval = -EMSGSIZE; + for (; array_size > 0; p++, array++, array_size--) + *array = be32_to_cpup(p); + return retval; +} #endif /* __KERNEL__ */ #endif /* _SUNRPC_XDR_H_ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 7fad83881ce1..5fea0fb420df 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -197,7 +197,7 @@ struct rpc_xprt { struct list_head free; /* free slots */ unsigned int max_reqs; /* max number of slots */ unsigned int min_reqs; /* min number of slots */ - atomic_t num_reqs; /* total slots */ + unsigned int num_reqs; /* total slots */ unsigned long state; /* transport state */ unsigned char resvport : 1; /* use a reserved port */ atomic_t swapper; /* we're swapping over this @@ -373,6 +373,7 @@ void xprt_wait_for_buffer_space(struct rpc_task *task, rpc_action action); void xprt_write_space(struct rpc_xprt *xprt); void xprt_adjust_cwnd(struct rpc_xprt *xprt, struct rpc_task *task, int result); struct rpc_rqst * xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid); +void xprt_update_rtt(struct rpc_task *task); void xprt_complete_rqst(struct rpc_task *task, int copied); void xprt_pin_rqst(struct rpc_rqst *req); void xprt_unpin_rqst(struct rpc_rqst *req); diff --git a/include/linux/tick.h b/include/linux/tick.h index 7f8c9a127f5a..55388ab45fd4 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -115,27 +115,46 @@ enum tick_dep_bits { extern bool tick_nohz_enabled; extern bool tick_nohz_tick_stopped(void); extern bool tick_nohz_tick_stopped_cpu(int cpu); +extern void tick_nohz_idle_stop_tick(void); +extern void tick_nohz_idle_retain_tick(void); +extern void tick_nohz_idle_restart_tick(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); -extern ktime_t tick_nohz_get_sleep_length(void); +extern bool tick_nohz_idle_got_tick(void); +extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); + +static inline void tick_nohz_idle_stop_tick_protected(void) +{ + local_irq_disable(); + tick_nohz_idle_stop_tick(); + local_irq_enable(); +} + #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline int tick_nohz_tick_stopped(void) { return 0; } static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; } +static inline void tick_nohz_idle_stop_tick(void) { } +static inline void tick_nohz_idle_retain_tick(void) { } +static inline void tick_nohz_idle_restart_tick(void) { } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } +static inline bool tick_nohz_idle_got_tick(void) { return false; } -static inline ktime_t tick_nohz_get_sleep_length(void) +static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { - return NSEC_PER_SEC / HZ; + *delta_next = TICK_NSEC; + return *delta_next; } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } + +static inline void tick_nohz_idle_stop_tick_protected(void) { } #endif /* !CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 82c219dfd3bb..9737fbec7019 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -31,6 +31,7 @@ struct timespec64 get_monotonic_coarse64(void); extern void getrawmonotonic64(struct timespec64 *ts); extern void ktime_get_ts64(struct timespec64 *ts); extern time64_t ktime_get_seconds(void); +extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); extern void ktime_get_active_ts64(struct timespec64 *ts); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index e0e98000b665..2bde3eff564c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -430,11 +430,13 @@ enum event_trigger_type { extern int filter_match_preds(struct event_filter *filter, void *rec); -extern enum event_trigger_type event_triggers_call(struct trace_event_file *file, - void *rec); -extern void event_triggers_post_call(struct trace_event_file *file, - enum event_trigger_type tt, - void *rec); +extern enum event_trigger_type +event_triggers_call(struct trace_event_file *file, void *rec, + struct ring_buffer_event *event); +extern void +event_triggers_post_call(struct trace_event_file *file, + enum event_trigger_type tt, + void *rec, struct ring_buffer_event *event); bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); @@ -454,7 +456,7 @@ trace_trigger_soft_disabled(struct trace_event_file *file) if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL); + event_triggers_call(file, NULL, NULL); if (eflags & EVENT_FILE_FL_SOFT_DISABLED) return true; if (eflags & EVENT_FILE_FL_PID_FILTER) diff --git a/include/linux/utsname.h b/include/linux/utsname.h index c8060c2ecd04..44429d9142ca 100644 --- a/include/linux/utsname.h +++ b/include/linux/utsname.h @@ -44,6 +44,8 @@ static inline void put_uts_ns(struct uts_namespace *ns) { kref_put(&ns->kref, free_uts_ns); } + +void uts_ns_init(void); #else static inline void get_uts_ns(struct uts_namespace *ns) { @@ -61,6 +63,10 @@ static inline struct uts_namespace *copy_utsname(unsigned long flags, return old_ns; } + +static inline void uts_ns_init(void) +{ +} #endif #ifdef CONFIG_PROC_SYSCTL diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index a4c2317d8b9f..f25cef84b41d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -20,6 +20,17 @@ extern int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif +struct reclaim_stat { + unsigned nr_dirty; + unsigned nr_unqueued_dirty; + unsigned nr_congested; + unsigned nr_writeback; + unsigned nr_immediate; + unsigned nr_activate; + unsigned nr_ref_keep; + unsigned nr_unmap_fail; +}; + #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. diff --git a/include/linux/xarray.h b/include/linux/xarray.h new file mode 100644 index 000000000000..2dfc8006fe64 --- /dev/null +++ b/include/linux/xarray.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _LINUX_XARRAY_H +#define _LINUX_XARRAY_H +/* + * eXtensible Arrays + * Copyright (c) 2017 Microsoft Corporation + * Author: Matthew Wilcox <mawilcox@microsoft.com> + */ + +#include <linux/spinlock.h> + +#define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) +#define xa_lock(xa) spin_lock(&(xa)->xa_lock) +#define xa_unlock(xa) spin_unlock(&(xa)->xa_lock) +#define xa_lock_bh(xa) spin_lock_bh(&(xa)->xa_lock) +#define xa_unlock_bh(xa) spin_unlock_bh(&(xa)->xa_lock) +#define xa_lock_irq(xa) spin_lock_irq(&(xa)->xa_lock) +#define xa_unlock_irq(xa) spin_unlock_irq(&(xa)->xa_lock) +#define xa_lock_irqsave(xa, flags) \ + spin_lock_irqsave(&(xa)->xa_lock, flags) +#define xa_unlock_irqrestore(xa, flags) \ + spin_unlock_irqrestore(&(xa)->xa_lock, flags) + +#endif /* _LINUX_XARRAY_H */ |
