diff options
Diffstat (limited to 'include/linux')
36 files changed, 495 insertions, 535 deletions
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 03a6653d329a..2ea0c282f3dc 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -22,7 +22,6 @@ struct ceph_osd_client; * completion callback for async writepages */ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *); -typedef void (*ceph_osdc_unsafe_callback_t)(struct ceph_osd_request *, bool); #define CEPH_HOMELESS_OSD -1 @@ -170,15 +169,12 @@ struct ceph_osd_request { unsigned int r_num_ops; int r_result; - bool r_got_reply; struct ceph_osd_client *r_osdc; struct kref r_kref; bool r_mempool; - struct completion r_completion; - struct completion r_done_completion; /* fsync waiter */ + struct completion r_completion; /* private to osd_client.c */ ceph_osdc_callback_t r_callback; - ceph_osdc_unsafe_callback_t r_unsafe_callback; struct list_head r_unsafe_item; struct inode *r_inode; /* for use by callbacks */ diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 9a9041784dcf..938656f70807 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -57,7 +57,7 @@ static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool) case CEPH_POOL_TYPE_EC: return false; default: - BUG_ON(1); + BUG(); } } @@ -82,13 +82,6 @@ void ceph_oloc_copy(struct ceph_object_locator *dest, void ceph_oloc_destroy(struct ceph_object_locator *oloc); /* - * Maximum supported by kernel client object name length - * - * (probably outdated: must be >= RBD_MAX_MD_NAME_LEN -- currently 100) - */ -#define CEPH_MAX_OID_NAME_LEN 100 - -/* * 51-char inline_name is long enough for all cephfs and all but one * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be * arbitrarily long (~PAGE_SIZE). It's done once during rbd map; all @@ -173,8 +166,8 @@ struct ceph_osdmap { * the list of osds that store+replicate them. */ struct crush_map *crush; - struct mutex crush_scratch_mutex; - int crush_scratch_ary[CEPH_PG_MAX_SIZE * 3]; + struct mutex crush_workspace_mutex; + void *crush_workspace; }; static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd) diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 5c0da61cb763..5d0018782d50 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -50,7 +50,7 @@ struct ceph_timespec { #define CEPH_PG_LAYOUT_LINEAR 2 #define CEPH_PG_LAYOUT_HYBRID 3 -#define CEPH_PG_MAX_SIZE 16 /* max # osds in a single pg */ +#define CEPH_PG_MAX_SIZE 32 /* max # osds in a single pg */ /* * placement group. diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 861b4677fc5b..3c02404cfce9 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -148,14 +148,18 @@ struct cgroup_subsys_state { * set for a task. */ struct css_set { - /* Reference count */ - atomic_t refcount; - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). */ - struct hlist_node hlist; + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* reference count */ + atomic_t refcount; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; /* * Lists running through all tasks using this cgroup group. @@ -167,21 +171,29 @@ struct css_set { struct list_head tasks; struct list_head mg_tasks; + /* all css_task_iters currently walking this cset */ + struct list_head task_iters; + /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. */ - struct list_head cgrp_links; + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct list_head cgrp_links; /* * List of csets participating in the on-going migration either as @@ -201,18 +213,6 @@ struct css_set { struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* all css_task_iters currently walking this cset */ - struct list_head task_iters; - /* dead and being drained, ignore for migration */ bool dead; @@ -388,6 +388,9 @@ struct cftype { struct list_head node; /* anchored at ss->cfts */ struct kernfs_ops *kf_ops; + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c83c23f0577b..f6b43fbb141c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -266,7 +266,7 @@ void css_task_iter_end(struct css_task_iter *it); * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css - * @tset: takset to iterate + * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h new file mode 100644 index 000000000000..e94290b29e99 --- /dev/null +++ b/include/linux/cgroup_rdma.h @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com> + * + * This file is subject to the terms and conditions of version 2 of the GNU + * General Public License. See the file COPYING in the main directory of the + * Linux distribution for more details. + */ + +#ifndef _CGROUP_RDMA_H +#define _CGROUP_RDMA_H + +#include <linux/cgroup.h> + +enum rdmacg_resource_type { + RDMACG_RESOURCE_HCA_HANDLE, + RDMACG_RESOURCE_HCA_OBJECT, + RDMACG_RESOURCE_MAX, +}; + +#ifdef CONFIG_CGROUP_RDMA + +struct rdma_cgroup { + struct cgroup_subsys_state css; + + /* + * head to keep track of all resource pools + * that belongs to this cgroup. + */ + struct list_head rpools; +}; + +struct rdmacg_device { + struct list_head dev_node; + struct list_head rpools; + char *name; +}; + +/* + * APIs for RDMA/IB stack to publish when a device wants to + * participate in resource accounting + */ +int rdmacg_register_device(struct rdmacg_device *device); +void rdmacg_unregister_device(struct rdmacg_device *device); + +/* APIs for RDMA/IB stack to charge/uncharge pool specific resources */ +int rdmacg_try_charge(struct rdma_cgroup **rdmacg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +void rdmacg_uncharge(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +#endif /* CONFIG_CGROUP_RDMA */ +#endif /* _CGROUP_RDMA_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 0df0336acee9..d0e597c44585 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -56,6 +56,10 @@ SUBSYS(hugetlb) SUBSYS(pids) #endif +#if IS_ENABLED(CONFIG_CGROUP_RDMA) +SUBSYS(rdma) +#endif + /* * The following subsystems are not supported on the default hierarchy. */ diff --git a/include/linux/compat.h b/include/linux/compat.h index 9e40be522793..aef47be2a5c1 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -711,8 +711,10 @@ int __compat_save_altstack(compat_stack_t __user *, unsigned long); compat_stack_t __user *__uss = uss; \ struct task_struct *t = current; \ put_user_ex(ptr_to_compat((void __user *)t->sas_ss_sp), &__uss->ss_sp); \ - put_user_ex(sas_ss_flags(sp), &__uss->ss_flags); \ + put_user_ex(t->sas_ss_flags, &__uss->ss_flags); \ put_user_ex(t->sas_ss_size, &__uss->ss_size); \ + if (t->sas_ss_flags & SS_AUTODISARM) \ + sas_ss_reset(t); \ } while (0); asmlinkage long compat_sys_sched_rr_get_interval(compat_pid_t pid, diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 811f7a915658..76e28c229805 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -197,6 +197,17 @@ #endif #endif +#ifdef CONFIG_STACK_VALIDATION +#define annotate_unreachable() ({ \ + asm("%c0:\t\n" \ + ".pushsection __unreachable, \"a\"\t\n" \ + ".long %c0b\t\n" \ + ".popsection\t\n" : : "i" (__LINE__)); \ +}) +#else +#define annotate_unreachable() +#endif + /* * Mark a position in code as unreachable. This can be used to * suppress control flow warnings after asm blocks that transfer @@ -206,7 +217,8 @@ * this in the preprocessor, but we can live with this because they're * unreleased. Really, we need to have autoconf for the kernel. */ -#define unreachable() __builtin_unreachable() +#define unreachable() \ + do { annotate_unreachable(); __builtin_unreachable(); } while (0) /* Mark a function definition as prohibited from being cloned. */ #define __noclone __attribute__((__noclone__, __optimize__("no-tracer"))) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 627e697e5d25..f8110051188f 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -577,12 +577,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s (_________p1); \ }) -/* Ignore/forbid kprobes attach on very low level functions marked by this attribute: */ -#ifdef CONFIG_KPROBES -# define __kprobes __attribute__((__section__(".kprobes.text"))) -# define nokprobe_inline __always_inline -#else -# define __kprobes -# define nokprobe_inline inline -#endif #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index be8f12b8f195..fbecbd089d75 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -135,13 +135,6 @@ struct crush_bucket { __u32 size; /* num items */ __s32 *items; - /* - * cached random permutation: used for uniform bucket and for - * the linear search fallback for the other bucket types. - */ - __u32 perm_x; /* @x for which *perm is defined */ - __u32 perm_n; /* num elements of *perm that are permuted/defined */ - __u32 *perm; }; struct crush_bucket_uniform { @@ -211,6 +204,21 @@ struct crush_map { * device fails. */ __u8 chooseleaf_stable; + /* + * This value is calculated after decode or construction by + * the builder. It is exposed here (rather than having a + * 'build CRUSH working space' function) so that callers can + * reserve a static buffer, allocate space on the stack, or + * otherwise avoid calling into the heap allocator if they + * want to. The size of the working space depends on the map, + * while the size of the scratch vector passed to the mapper + * depends on the size of the desired result set. + * + * Nothing stops the caller from allocating both in one swell + * foop and passing in two points, though. + */ + size_t working_size; + #ifndef __KERNEL__ /* * version 0 (original) of straw_calc has various flaws. version 1 @@ -248,4 +256,23 @@ static inline int crush_calc_tree_node(int i) return ((i+1) << 1)-1; } +/* + * These data structures are private to the CRUSH implementation. They + * are exposed in this header file because builder needs their + * definitions to calculate the total working size. + * + * Moving this out of the crush map allow us to treat the CRUSH map as + * immutable within the mapper and removes the requirement for a CRUSH + * map lock. + */ +struct crush_work_bucket { + __u32 perm_x; /* @x for which *perm is defined */ + __u32 perm_n; /* num elements of *perm that are permuted/defined */ + __u32 *perm; /* Permutation of the bucket's items */ +}; + +struct crush_work { + struct crush_work_bucket **work; /* Per-bucket working store */ +}; + #endif diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index 5dfd5b1125d2..c95e19e1ff11 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -15,6 +15,20 @@ extern int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, const __u32 *weights, int weight_max, - int *scratch); + void *cwin); + +/* + * Returns the exact amount of workspace that will need to be used + * for a given combination of crush_map and result_max. The caller can + * then allocate this much on its own, either on the stack, in a + * per-thread long-lived buffer, or however it likes. + */ +static inline size_t crush_work_size(const struct crush_map *map, + int result_max) +{ + return map->working_size + result_max * 3 * sizeof(__u32); +} + +void crush_init_workspace(const struct crush_map *map, void *v); #endif diff --git a/include/linux/dcache.h b/include/linux/dcache.h index c965e4469499..591b6c16f9c1 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -562,7 +562,7 @@ static inline struct dentry *d_backing_dentry(struct dentry *upper) * @inode: inode to select the dentry from multiple layers (can be NULL) * @flags: open flags to control copy-up behavior * - * If dentry is on an union/overlay, then return the underlying, real dentry. + * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.txt @@ -581,7 +581,7 @@ static inline struct dentry *d_real(struct dentry *dentry, * d_real_inode - Return the real inode * @dentry: The dentry to query * - * If dentry is on an union/overlay, then return the underlying, real inode. + * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) diff --git a/include/linux/fs.h b/include/linux/fs.h index c930cbc19342..c64f2cb7d364 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -655,6 +655,11 @@ struct inode { void *i_private; /* fs or device private pointer */ }; +static inline unsigned int i_blocksize(const struct inode *node) +{ + return (1 << node->i_blkbits); +} + static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); diff --git a/include/linux/idr.h b/include/linux/idr.h index 3c01b89aed67..bf70b3ef0a07 100644 --- a/include/linux/idr.h +++ b/include/linux/idr.h @@ -12,47 +12,29 @@ #ifndef __IDR_H__ #define __IDR_H__ -#include <linux/types.h> -#include <linux/bitops.h> -#include <linux/init.h> -#include <linux/rcupdate.h> +#include <linux/radix-tree.h> +#include <linux/gfp.h> +#include <linux/percpu.h> + +struct idr { + struct radix_tree_root idr_rt; + unsigned int idr_next; +}; /* - * Using 6 bits at each layer allows us to allocate 7 layers out of each page. - * 8 bits only gave us 3 layers out of every pair of pages, which is less - * efficient except for trees with a largest element between 192-255 inclusive. + * The IDR API does not expose the tagging functionality of the radix tree + * to users. Use tag 0 to track whether a node has free space below it. */ -#define IDR_BITS 6 -#define IDR_SIZE (1 << IDR_BITS) -#define IDR_MASK ((1 << IDR_BITS)-1) - -struct idr_layer { - int prefix; /* the ID prefix of this idr_layer */ - int layer; /* distance from leaf */ - struct idr_layer __rcu *ary[1<<IDR_BITS]; - int count; /* When zero, we can release it */ - union { - /* A zero bit means "space here" */ - DECLARE_BITMAP(bitmap, IDR_SIZE); - struct rcu_head rcu_head; - }; -}; +#define IDR_FREE 0 -struct idr { - struct idr_layer __rcu *hint; /* the last layer allocated from */ - struct idr_layer __rcu *top; - int layers; /* only valid w/o concurrent changes */ - int cur; /* current pos for cyclic allocation */ - spinlock_t lock; - int id_free_cnt; - struct idr_layer *id_free; -}; +/* Set the IDR flag and the IDR_FREE tag */ +#define IDR_RT_MARKER ((__force gfp_t)(3 << __GFP_BITS_SHIFT)) -#define IDR_INIT(name) \ +#define IDR_INIT \ { \ - .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ + .idr_rt = RADIX_TREE_INIT(IDR_RT_MARKER) \ } -#define DEFINE_IDR(name) struct idr name = IDR_INIT(name) +#define DEFINE_IDR(name) struct idr name = IDR_INIT /** * idr_get_cursor - Return the current position of the cyclic allocator @@ -62,9 +44,9 @@ struct idr { * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ -static inline unsigned int idr_get_cursor(struct idr *idr) +static inline unsigned int idr_get_cursor(const struct idr *idr) { - return READ_ONCE(idr->cur); + return READ_ONCE(idr->idr_next); } /** @@ -77,7 +59,7 @@ static inline unsigned int idr_get_cursor(struct idr *idr) */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { - WRITE_ONCE(idr->cur, val); + WRITE_ONCE(idr->idr_next, val); } /** @@ -97,22 +79,31 @@ static inline void idr_set_cursor(struct idr *idr, unsigned int val) * period). */ -/* - * This is what we export. - */ - -void *idr_find_slowpath(struct idr *idp, int id); void idr_preload(gfp_t gfp_mask); -int idr_alloc(struct idr *idp, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_alloc_cyclic(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask); -int idr_for_each(struct idr *idp, +int idr_alloc(struct idr *, void *entry, int start, int end, gfp_t); +int idr_alloc_cyclic(struct idr *, void *entry, int start, int end, gfp_t); +int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); -void *idr_get_next(struct idr *idp, int *nextid); -void *idr_replace(struct idr *idp, void *ptr, int id); -void idr_remove(struct idr *idp, int id); -void idr_destroy(struct idr *idp); -void idr_init(struct idr *idp); -bool idr_is_empty(struct idr *idp); +void *idr_get_next(struct idr *, int *nextid); +void *idr_replace(struct idr *, void *, int id); +void idr_destroy(struct idr *); + +static inline void *idr_remove(struct idr *idr, int id) +{ + return radix_tree_delete_item(&idr->idr_rt, id, NULL); +} + +static inline void idr_init(struct idr *idr) +{ + INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); + idr->idr_next = 0; +} + +static inline bool idr_is_empty(const struct idr *idr) +{ + return radix_tree_empty(&idr->idr_rt) && + radix_tree_tagged(&idr->idr_rt, IDR_FREE); +} /** * idr_preload_end - end preload section started with idr_preload() @@ -137,19 +128,14 @@ static inline void idr_preload_end(void) * This function can be called under rcu_read_lock(), given that the leaf * pointers lifetimes are correctly managed. */ -static inline void *idr_find(struct idr *idr, int id) +static inline void *idr_find(const struct idr *idr, int id) { - struct idr_layer *hint = rcu_dereference_raw(idr->hint); - - if (hint && (id & ~IDR_MASK) == hint->prefix) - return rcu_dereference_raw(hint->ary[id & IDR_MASK]); - - return idr_find_slowpath(idr, id); + return radix_tree_lookup(&idr->idr_rt, id); } /** * idr_for_each_entry - iterate over an idr's elements of a given type - * @idp: idr handle + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * @@ -157,57 +143,60 @@ static inline void *idr_find(struct idr *idr, int id) * after normal terminatinon @entry is left with the value NULL. This * is convenient for a "not found" value. */ -#define idr_for_each_entry(idp, entry, id) \ - for (id = 0; ((entry) = idr_get_next(idp, &(id))) != NULL; ++id) +#define idr_for_each_entry(idr, entry, id) \ + for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id) /** - * idr_for_each_entry - continue iteration over an idr's elements of a given type - * @idp: idr handle + * idr_for_each_entry_continue - continue iteration over an idr's elements of a given type + * @idr: idr handle * @entry: the type * to use as cursor * @id: id entry's key * * Continue to iterate over list of given type, continuing after * the current position. */ -#define idr_for_each_entry_continue(idp, entry, id) \ - for ((entry) = idr_get_next((idp), &(id)); \ +#define idr_for_each_entry_continue(idr, entry, id) \ + for ((entry) = idr_get_next((idr), &(id)); \ entry; \ - ++id, (entry) = idr_get_next((idp), &(id))) + ++id, (entry) = idr_get_next((idr), &(id))) /* * IDA - IDR based id allocator, use when translation from id to * pointer isn't necessary. - * - * IDA_BITMAP_LONGS is calculated to be one less to accommodate - * ida_bitmap->nr_busy so that the whole struct fits in 128 bytes. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ -#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long) - 1) +#define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { - long nr_busy; unsigned long bitmap[IDA_BITMAP_LONGS]; }; +DECLARE_PER_CPU(struct ida_bitmap *, ida_bitmap); + struct ida { - struct idr idr; - struct ida_bitmap *free_bitmap; + struct radix_tree_root ida_rt; }; -#define IDA_INIT(name) { .idr = IDR_INIT((name).idr), .free_bitmap = NULL, } -#define DEFINE_IDA(name) struct ida name = IDA_INIT(name) +#define IDA_INIT { \ + .ida_rt = RADIX_TREE_INIT(IDR_RT_MARKER | GFP_NOWAIT), \ +} +#define DEFINE_IDA(name) struct ida name = IDA_INIT 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); void ida_remove(struct ida *ida, int id); void ida_destroy(struct ida *ida); -void ida_init(struct ida *ida); int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end, gfp_t gfp_mask); void ida_simple_remove(struct ida *ida, unsigned int id); +static inline void ida_init(struct ida *ida) +{ + INIT_RADIX_TREE(&ida->ida_rt, IDR_RT_MARKER | GFP_NOWAIT); +} + /** * ida_get_new - allocate new ID * @ida: idr handle @@ -220,11 +209,8 @@ static inline int ida_get_new(struct ida *ida, int *p_id) return ida_get_new_above(ida, 0, p_id); } -static inline bool ida_is_empty(struct ida *ida) +static inline bool ida_is_empty(const struct ida *ida) { - return idr_is_empty(&ida->idr); + return radix_tree_empty(&ida->ida_rt); } - -void __init idr_init_cache(void); - #endif /* __IDR_H__ */ diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 78c5d5ae3857..f1045b2c6a00 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -100,7 +100,7 @@ struct ipmi_user_hndl { /* Create a new user of the IPMI layer on the given interface number. */ int ipmi_create_user(unsigned int if_num, - struct ipmi_user_hndl *handler, + const struct ipmi_user_hndl *handler, void *handler_data, ipmi_user_t *user); diff --git a/include/linux/kconfig.h b/include/linux/kconfig.h index 8f2e059e4d45..4d748603e818 100644 --- a/include/linux/kconfig.h +++ b/include/linux/kconfig.h @@ -8,7 +8,7 @@ /* * The use of "&&" / "||" is limited in certain expressions. - * The followings enable to calculate "and" / "or" with macro expansion only. + * The following enable to calculate "and" / "or" with macro expansion only. */ #define __and(x, y) ___and(x, y) #define ___and(x, y) ____and(__ARG_PLACEHOLDER_##x, y) diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 7056238fd9f5..a9b11b8d06f2 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -46,6 +46,7 @@ enum kernfs_node_flag { KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, + KERNFS_HAS_RELEASE = 0x2000, }; /* @flags for kernfs_create_root() */ @@ -175,6 +176,7 @@ struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; + struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ @@ -185,12 +187,20 @@ struct kernfs_open_file { char *prealloc_buf; size_t atomic_write_len; - bool mmapped; + bool mmapped:1; + bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* + * Optional open/release methods. Both are called with + * @of->seq_file populated. + */ + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + + /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 16ddfb8b304a..c328e4f7dcad 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -29,7 +29,7 @@ * <jkenisto@us.ibm.com> and Prasanna S Panchamukhi * <prasanna@in.ibm.com> added function-return probes. */ -#include <linux/compiler.h> /* for __kprobes */ +#include <linux/compiler.h> #include <linux/linkage.h> #include <linux/list.h> #include <linux/notifier.h> @@ -40,9 +40,9 @@ #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/ftrace.h> +#include <asm/kprobes.h> #ifdef CONFIG_KPROBES -#include <asm/kprobes.h> /* kprobe_status settings */ #define KPROBE_HIT_ACTIVE 0x00000001 @@ -51,6 +51,7 @@ #define KPROBE_HIT_SSDONE 0x00000008 #else /* CONFIG_KPROBES */ +#include <asm-generic/kprobes.h> typedef int kprobe_opcode_t; struct arch_specific_insn { int dummy; @@ -509,18 +510,4 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) } #endif -#ifdef CONFIG_KPROBES -/* - * Blacklist ganerating macro. Specify functions which is not probed - * by using this macro. - */ -#define __NOKPROBE_SYMBOL(fname) \ -static unsigned long __used \ - __attribute__((section("_kprobe_blacklist"))) \ - _kbl_addr_##fname = (unsigned long)fname; -#define NOKPROBE_SYMBOL(fname) __NOKPROBE_SYMBOL(fname) -#else -#define NOKPROBE_SYMBOL(fname) -#endif - #endif /* _LINUX_KPROBES_H */ diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h index 6483a6fdce59..ffb21e79204d 100644 --- a/include/linux/mfd/tps65910.h +++ b/include/linux/mfd/tps65910.h @@ -134,6 +134,7 @@ /* RTC_CTRL_REG bitfields */ #define TPS65910_RTC_CTRL_STOP_RTC 0x01 /*0=stop, 1=run */ +#define TPS65910_RTC_CTRL_AUTO_COMP 0x04 #define TPS65910_RTC_CTRL_GET_TIME 0x40 /* RTC_STATUS_REG bitfields */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 808751d7b737..4f6d440ad785 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -407,8 +407,27 @@ struct mm_struct { unsigned long task_size; /* size of task vm space */ unsigned long highest_vm_end; /* highest vma end address */ pgd_t * pgd; - atomic_t mm_users; /* How many users with user space? */ - atomic_t mm_count; /* How many references to "struct mm_struct" (users count as 1) */ + + /** + * @mm_users: The number of users including userspace. + * + * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops + * to 0 (i.e. when the task exits and there are no other temporary + * reference holders), we also release a reference on @mm_count + * (which may then free the &struct mm_struct if @mm_count also + * drops to 0). + */ + atomic_t mm_users; + + /** + * @mm_count: The number of references to &struct mm_struct + * (@mm_users count as 1). + * + * Use mmgrab()/mmdrop() to modify. When this drops to 0, the + * &struct mm_struct is freed. + */ + atomic_t mm_count; + atomic_long_t nr_ptes; /* PTE page table pages */ #if CONFIG_PGTABLE_LEVELS > 2 atomic_long_t nr_pmds; /* PMD page table pages */ diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h index 7b3d487d8b3f..b532ce524dae 100644 --- a/include/linux/mtd/qinfo.h +++ b/include/linux/mtd/qinfo.h @@ -14,7 +14,7 @@ * @DevId - Chip Device ID * @qinfo - pointer to qinfo records describing the chip * @numchips - number of chips including virual RWW partitions - * @chipshift - Chip/partiton size 2^chipshift + * @chipshift - Chip/partition size 2^chipshift * @chips - per-chip data structure */ struct lpddr_private { diff --git a/include/linux/pid.h b/include/linux/pid.h index 23705a53abba..298ead5512e5 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -191,10 +191,10 @@ pid_t pid_vnr(struct pid *pid); #define do_each_pid_thread(pid, type, task) \ do_each_pid_task(pid, type, task) { \ struct task_struct *tg___ = task; \ - do { + for_each_thread(tg___, task) { #define while_each_pid_thread(pid, type, task) \ - } while_each_thread(tg___, task); \ + } \ task = tg___; \ } while_each_pid_task(pid, type, task) #endif /* _LINUX_PID_H */ diff --git a/include/linux/platform_data/rtc-m48t86.h b/include/linux/platform_data/rtc-m48t86.h deleted file mode 100644 index 915d6b4f0f89..000000000000 --- a/include/linux/platform_data/rtc-m48t86.h +++ /dev/null @@ -1,16 +0,0 @@ -/* - * ST M48T86 / Dallas DS12887 RTC driver - * Copyright (c) 2006 Tower Technologies - * - * Author: Alessandro Zummo <a.zummo@towertech.it> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. -*/ - -struct m48t86_ops -{ - void (*writebyte)(unsigned char value, unsigned long addr); - unsigned char (*readbyte)(unsigned long addr); -}; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 52bda854593b..3e5735064b71 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -22,11 +22,13 @@ #define _LINUX_RADIX_TREE_H #include <linux/bitops.h> -#include <linux/preempt.h> -#include <linux/types.h> #include <linux/bug.h> #include <linux/kernel.h> +#include <linux/list.h> +#include <linux/preempt.h> #include <linux/rcupdate.h> +#include <linux/spinlock.h> +#include <linux/types.h> /* * The bottom two bits of the slot determine how the remaining bits in the @@ -94,7 +96,7 @@ struct radix_tree_node { unsigned char count; /* Total entry count */ unsigned char exceptional; /* Exceptional entry count */ struct radix_tree_node *parent; /* Used when ascending tree */ - void *private_data; /* For tree user */ + struct radix_tree_root *root; /* The tree we belong to */ union { struct list_head private_list; /* For tree user */ struct rcu_head rcu_head; /* Used when freeing node */ @@ -103,7 +105,10 @@ struct radix_tree_node { unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -/* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ +/* 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) + struct radix_tree_root { gfp_t gfp_mask; struct radix_tree_node __rcu *rnode; @@ -123,7 +128,7 @@ do { \ (root)->rnode = NULL; \ } while (0) -static inline bool radix_tree_empty(struct radix_tree_root *root) +static inline bool radix_tree_empty(const struct radix_tree_root *root) { return root->rnode == NULL; } @@ -216,10 +221,8 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) */ /** - * radix_tree_deref_slot - dereference a slot - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. + * radix_tree_deref_slot - dereference a slot + * @slot: slot pointer, returned by radix_tree_lookup_slot * * For use with radix_tree_lookup_slot(). Caller must hold tree at least read * locked across slot lookup and dereference. Not required if write lock is @@ -227,26 +230,27 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * * radix_tree_deref_retry must be used to confirm validity of the pointer if * only the read lock is held. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot(void **pslot) +static inline void *radix_tree_deref_slot(void __rcu **slot) { - return rcu_dereference(*pslot); + return rcu_dereference(*slot); } /** - * radix_tree_deref_slot_protected - dereference a slot without RCU lock but with tree lock held - * @pslot: pointer to slot, returned by radix_tree_lookup_slot - * Returns: item that was stored in that slot with any direct pointer flag - * removed. - * - * Similar to radix_tree_deref_slot but only used during migration when a pages - * mapping is being moved. The caller does not hold the RCU read lock but it - * must hold the tree lock to prevent parallel updates. + * radix_tree_deref_slot_protected - dereference a slot with tree lock held + * @slot: slot pointer, returned by radix_tree_lookup_slot + * + * Similar to radix_tree_deref_slot. The caller does not hold the RCU read + * lock but it must hold the tree lock to prevent parallel updates. + * + * Return: entry stored in that slot. */ -static inline void *radix_tree_deref_slot_protected(void **pslot, +static inline void *radix_tree_deref_slot_protected(void __rcu **slot, spinlock_t *treelock) { - return rcu_dereference_protected(*pslot, lockdep_is_held(treelock)); + return rcu_dereference_protected(*slot, lockdep_is_held(treelock)); } /** @@ -282,9 +286,9 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *root, unsigned long index, +int __radix_tree_create(struct radix_tree_root *, unsigned long index, unsigned order, struct radix_tree_node **nodep, - void ***slotp); + void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, @@ -292,55 +296,56 @@ static inline int radix_tree_insert(struct radix_tree_root *root, { return __radix_tree_insert(root, index, 0, entry); } -void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, - struct radix_tree_node **nodep, void ***slotp); -void *radix_tree_lookup(struct radix_tree_root *, unsigned long); -void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); +void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, + struct radix_tree_node **nodep, void __rcu ***slotp); +void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); +void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *, + unsigned long index); typedef void (*radix_tree_update_node_t)(struct radix_tree_node *, void *); -void __radix_tree_replace(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot, void *item, +void __radix_tree_replace(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot, void *entry, radix_tree_update_node_t update_node, void *private); void radix_tree_iter_replace(struct radix_tree_root *, - const struct radix_tree_iter *, void **slot, void *item); -void radix_tree_replace_slot(struct radix_tree_root *root, - void **slot, void *item); -void __radix_tree_delete_node(struct radix_tree_root *root, - struct radix_tree_node *node, + const struct radix_tree_iter *, void __rcu **slot, void *entry); +void radix_tree_replace_slot(struct radix_tree_root *, + void __rcu **slot, void *entry); +void __radix_tree_delete_node(struct radix_tree_root *, + struct radix_tree_node *, radix_tree_update_node_t update_node, void *private); +void radix_tree_iter_delete(struct radix_tree_root *, + struct radix_tree_iter *iter, void __rcu **slot); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); -void radix_tree_clear_tags(struct radix_tree_root *root, - struct radix_tree_node *node, - void **slot); -unsigned int radix_tree_gang_lookup(struct radix_tree_root *root, +void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, + void __rcu **slot); +unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root, - void ***results, unsigned long *indices, +unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); void radix_tree_init(void); -void *radix_tree_tag_set(struct radix_tree_root *root, +void *radix_tree_tag_set(struct radix_tree_root *, unsigned long index, unsigned int tag); -void *radix_tree_tag_clear(struct radix_tree_root *root, +void *radix_tree_tag_clear(struct radix_tree_root *, unsigned long index, unsigned int tag); -int radix_tree_tag_get(struct radix_tree_root *root, +int radix_tree_tag_get(const struct radix_tree_root *, unsigned long index, unsigned int tag); -void radix_tree_iter_tag_set(struct radix_tree_root *root, +void radix_tree_iter_tag_set(struct radix_tree_root *, + const struct radix_tree_iter *iter, unsigned int tag); +void radix_tree_iter_tag_clear(struct radix_tree_root *, const struct radix_tree_iter *iter, unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -unsigned int -radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results, - unsigned long first_index, unsigned int max_items, - unsigned int tag); -int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *, + void **results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *, + void __rcu ***results, unsigned long first_index, + unsigned int max_items, unsigned int tag); +int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); static inline void radix_tree_preload_end(void) { @@ -352,10 +357,14 @@ int radix_tree_split(struct radix_tree_root *, unsigned long index, unsigned new_order); int radix_tree_join(struct radix_tree_root *, unsigned long index, unsigned new_order, void *); +void __rcu **idr_get_free(struct radix_tree_root *, struct radix_tree_iter *, + gfp_t, int end); -#define RADIX_TREE_ITER_TAG_MASK 0x00FF /* tag index in lower byte */ -#define RADIX_TREE_ITER_TAGGED 0x0100 /* lookup tagged slots */ -#define RADIX_TREE_ITER_CONTIG 0x0200 /* stop at first hole */ +enum { + RADIX_TREE_ITER_TAG_MASK = 0x0f, /* tag index in lower nybble */ + RADIX_TREE_ITER_TAGGED = 0x10, /* lookup tagged slots */ + RADIX_TREE_ITER_CONTIG = 0x20, /* stop at first hole */ +}; /** * radix_tree_iter_init - initialize radix tree iterator @@ -364,7 +373,7 @@ int radix_tree_join(struct radix_tree_root *, unsigned long index, * @start: iteration starting index * Returns: NULL */ -static __always_inline void ** +static __always_inline void __rcu ** radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) { /* @@ -393,10 +402,46 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start) * Also it fills @iter with data about chunk: position in the tree (index), * its end (next_index), and constructs a bit mask for tagged iterating (tags). */ -void **radix_tree_next_chunk(struct radix_tree_root *root, +void __rcu **radix_tree_next_chunk(const struct radix_tree_root *, struct radix_tree_iter *iter, unsigned flags); /** + * radix_tree_iter_lookup - look up an index in the radix tree + * @root: radix tree root + * @iter: iterator state + * @index: key to look up + * + * If @index is present in the radix tree, this function returns the slot + * containing it and updates @iter to describe the entry. If @index is not + * present, it returns NULL. + */ +static inline void __rcu ** +radix_tree_iter_lookup(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, RADIX_TREE_ITER_CONTIG); +} + +/** + * radix_tree_iter_find - find a present entry + * @root: radix tree root + * @iter: iterator state + * @index: start location + * + * This function returns the slot containing the entry with the lowest index + * which is at least @index. If @index is larger than any present entry, this + * function returns NULL. The @iter is updated to describe the entry found. + */ +static inline void __rcu ** +radix_tree_iter_find(const struct radix_tree_root *root, + struct radix_tree_iter *iter, unsigned long index) +{ + radix_tree_iter_init(iter, index); + return radix_tree_next_chunk(root, iter, 0); +} + +/** * radix_tree_iter_retry - retry this chunk of the iteration * @iter: iterator state * @@ -406,7 +451,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, * and continue the iteration. */ static inline __must_check -void **radix_tree_iter_retry(struct radix_tree_iter *iter) +void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) { iter->next_index = iter->index; iter->tags = 0; @@ -429,7 +474,7 @@ __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) * have been invalidated by an insertion or deletion. Call this function * before releasing the lock to continue the iteration from the next index. */ -void **__must_check radix_tree_iter_resume(void **slot, +void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter); /** @@ -445,11 +490,11 @@ radix_tree_chunk_size(struct radix_tree_iter *iter) } #ifdef CONFIG_RADIX_TREE_MULTIORDER -void ** __radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, - unsigned flags); +void __rcu **__radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags); #else /* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void ** __radix_tree_next_slot(void **slot, +static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { return slot; @@ -475,8 +520,8 @@ static inline void ** __radix_tree_next_slot(void **slot, * b) we are doing non-tagged iteration, and iter->index and iter->next_index * have been set up so that radix_tree_chunk_size() returns 1 or 0. */ -static __always_inline void ** -radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) +static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, + struct radix_tree_iter *iter, unsigned flags) { if (flags & RADIX_TREE_ITER_TAGGED) { iter->tags >>= 1; @@ -514,7 +559,7 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags) return NULL; found: - if (unlikely(radix_tree_is_internal_node(*slot))) + if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) return __radix_tree_next_slot(slot, iter, flags); return slot; } diff --git a/include/linux/refcount.h b/include/linux/refcount.h index 600aadf9cca4..0023fee4bbbc 100644 --- a/include/linux/refcount.h +++ b/include/linux/refcount.h @@ -1,54 +1,10 @@ #ifndef _LINUX_REFCOUNT_H #define _LINUX_REFCOUNT_H -/* - * Variant of atomic_t specialized for reference counts. - * - * The interface matches the atomic_t interface (to aid in porting) but only - * provides the few functions one should use for reference counting. - * - * It differs in that the counter saturates at UINT_MAX and will not move once - * there. This avoids wrapping the counter and causing 'spurious' - * use-after-free issues. - * - * Memory ordering rules are slightly relaxed wrt regular atomic_t functions - * and provide only what is strictly required for refcounts. - * - * The increments are fully relaxed; these will not provide ordering. The - * rationale is that whatever is used to obtain the object we're increasing the - * reference count on will provide the ordering. For locked data structures, - * its the lock acquire, for RCU/lockless data structures its the dependent - * load. - * - * Do note that inc_not_zero() provides a control dependency which will order - * future stores against the inc, this ensures we'll never modify the object - * if we did not in fact acquire a reference. - * - * The decrements will provide release order, such that all the prior loads and - * stores will be issued before, it also provides a control dependency, which - * will order us against the subsequent free(). - * - * The control dependency is against the load of the cmpxchg (ll/sc) that - * succeeded. This means the stores aren't fully ordered, but this is fine - * because the 1->0 transition indicates no concurrency. - * - * Note that the allocator is responsible for ordering things between free() - * and alloc(). - * - */ - #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/mutex.h> #include <linux/spinlock.h> - -#ifdef CONFIG_DEBUG_REFCOUNT -#define REFCOUNT_WARN(cond, str) WARN_ON(cond) -#define __refcount_check __must_check -#else -#define REFCOUNT_WARN(cond, str) (void)(cond) -#define __refcount_check -#endif +#include <linux/kernel.h> typedef struct refcount_struct { atomic_t refs; @@ -66,229 +22,21 @@ static inline unsigned int refcount_read(const refcount_t *r) return atomic_read(&r->refs); } -static inline __refcount_check -bool refcount_add_not_zero(unsigned int i, refcount_t *r) -{ - unsigned int old, new, val = atomic_read(&r->refs); - - for (;;) { - if (!val) - return false; - - if (unlikely(val == UINT_MAX)) - return true; - - new = val + i; - if (new < val) - new = UINT_MAX; - old = atomic_cmpxchg_relaxed(&r->refs, val, new); - if (old == val) - break; - - val = old; - } - - REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); - - return true; -} - -static inline void refcount_add(unsigned int i, refcount_t *r) -{ - REFCOUNT_WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n"); -} - -/* - * Similar to atomic_inc_not_zero(), will saturate at UINT_MAX and WARN. - * - * Provides no memory ordering, it is assumed the caller has guaranteed the - * object memory to be stable (RCU, etc.). It does provide a control dependency - * and thereby orders future stores. See the comment on top. - */ -static inline __refcount_check -bool refcount_inc_not_zero(refcount_t *r) -{ - unsigned int old, new, val = atomic_read(&r->refs); - - for (;;) { - new = val + 1; - - if (!val) - return false; - - if (unlikely(!new)) - return true; - - old = atomic_cmpxchg_relaxed(&r->refs, val, new); - if (old == val) - break; - - val = old; - } - - REFCOUNT_WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n"); - - return true; -} - -/* - * Similar to atomic_inc(), will saturate at UINT_MAX and WARN. - * - * Provides no memory ordering, it is assumed the caller already has a - * reference on the object, will WARN when this is not so. - */ -static inline void refcount_inc(refcount_t *r) -{ - REFCOUNT_WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n"); -} - -/* - * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to - * decrement when saturated at UINT_MAX. - * - * Provides release memory ordering, such that prior loads and stores are done - * before, and provides a control dependency such that free() must come after. - * See the comment on top. - */ -static inline __refcount_check -bool refcount_sub_and_test(unsigned int i, refcount_t *r) -{ - unsigned int old, new, val = atomic_read(&r->refs); - - for (;;) { - if (unlikely(val == UINT_MAX)) - return false; - - new = val - i; - if (new > val) { - REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); - return false; - } - - old = atomic_cmpxchg_release(&r->refs, val, new); - if (old == val) - break; - - val = old; - } - - return !new; -} - -static inline __refcount_check -bool refcount_dec_and_test(refcount_t *r) -{ - return refcount_sub_and_test(1, r); -} +extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r); +extern void refcount_add(unsigned int i, refcount_t *r); -/* - * Similar to atomic_dec(), it will WARN on underflow and fail to decrement - * when saturated at UINT_MAX. - * - * Provides release memory ordering, such that prior loads and stores are done - * before. - */ -static inline -void refcount_dec(refcount_t *r) -{ - REFCOUNT_WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n"); -} - -/* - * No atomic_t counterpart, it attempts a 1 -> 0 transition and returns the - * success thereof. - * - * Like all decrement operations, it provides release memory order and provides - * a control dependency. - * - * It can be used like a try-delete operator; this explicit case is provided - * and not cmpxchg in generic, because that would allow implementing unsafe - * operations. - */ -static inline __refcount_check -bool refcount_dec_if_one(refcount_t *r) -{ - return atomic_cmpxchg_release(&r->refs, 1, 0) == 1; -} - -/* - * No atomic_t counterpart, it decrements unless the value is 1, in which case - * it will return false. - * - * Was often done like: atomic_add_unless(&var, -1, 1) - */ -static inline __refcount_check -bool refcount_dec_not_one(refcount_t *r) -{ - unsigned int old, new, val = atomic_read(&r->refs); +extern __must_check bool refcount_inc_not_zero(refcount_t *r); +extern void refcount_inc(refcount_t *r); - for (;;) { - if (unlikely(val == UINT_MAX)) - return true; +extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r); +extern void refcount_sub(unsigned int i, refcount_t *r); - if (val == 1) - return false; +extern __must_check bool refcount_dec_and_test(refcount_t *r); +extern void refcount_dec(refcount_t *r); - new = val - 1; - if (new > val) { - REFCOUNT_WARN(new > val, "refcount_t: underflow; use-after-free.\n"); - return true; - } - - old = atomic_cmpxchg_release(&r->refs, val, new); - if (old == val) - break; - - val = old; - } - - return true; -} - -/* - * Similar to atomic_dec_and_mutex_lock(), it will WARN on underflow and fail - * to decrement when saturated at UINT_MAX. - * - * Provides release memory ordering, such that prior loads and stores are done - * before, and provides a control dependency such that free() must come after. - * See the comment on top. - */ -static inline __refcount_check -bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock) -{ - if (refcount_dec_not_one(r)) - return false; - - mutex_lock(lock); - if (!refcount_dec_and_test(r)) { - mutex_unlock(lock); - return false; - } - - return true; -} - -/* - * Similar to atomic_dec_and_lock(), it will WARN on underflow and fail to - * decrement when saturated at UINT_MAX. - * - * Provides release memory ordering, such that prior loads and stores are done - * before, and provides a control dependency such that free() must come after. - * See the comment on top. - */ -static inline __refcount_check -bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock) -{ - if (refcount_dec_not_one(r)) - return false; - - spin_lock(lock); - if (!refcount_dec_and_test(r)) { - spin_unlock(lock); - return false; - } - - return true; -} +extern __must_check bool refcount_dec_if_one(refcount_t *r); +extern __must_check bool refcount_dec_not_one(refcount_t *r); +extern __must_check bool refcount_dec_and_mutex_lock(refcount_t *r, struct mutex *lock); +extern __must_check bool refcount_dec_and_lock(refcount_t *r, spinlock_t *lock); #endif /* _LINUX_REFCOUNT_H */ diff --git a/include/linux/rodata_test.h b/include/linux/rodata_test.h new file mode 100644 index 000000000000..ea05f6c51413 --- /dev/null +++ b/include/linux/rodata_test.h @@ -0,0 +1,23 @@ +/* + * rodata_test.h: functional test for mark_rodata_ro function + * + * (C) Copyright 2008 Intel Corporation + * Author: Arjan van de Ven <arjan@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#ifndef _RODATA_TEST_H +#define _RODATA_TEST_H + +#ifdef CONFIG_DEBUG_RODATA_TEST +extern const int rodata_test_data; +void rodata_test(void); +#else +static inline void rodata_test(void) {} +#endif + +#endif /* _RODATA_TEST_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 451e241f32c5..4a28deb5f210 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2904,6 +2904,28 @@ static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) */ extern struct mm_struct * mm_alloc(void); +/** + * mmgrab() - Pin a &struct mm_struct. + * @mm: The &struct mm_struct to pin. + * + * Make sure that @mm will not get freed even after the owning task + * exits. This doesn't guarantee that the associated address space + * will still exist later on and mmget_not_zero() has to be used before + * accessing it. + * + * This is a preferred way to to pin @mm for a longer/unbounded amount + * of time. + * + * Use mmdrop() to release the reference acquired by mmgrab(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmgrab(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_count); +} + /* mmdrop drops the mm and the page tables */ extern void __mmdrop(struct mm_struct *); static inline void mmdrop(struct mm_struct *mm) @@ -2926,6 +2948,27 @@ static inline void mmdrop_async(struct mm_struct *mm) } } +/** + * mmget() - Pin the address space associated with a &struct mm_struct. + * @mm: The address space to pin. + * + * Make sure that the address space of the given &struct mm_struct doesn't + * go away. This does not protect against parts of the address space being + * modified or freed, however. + * + * Never use this function to pin this address space for an + * unbounded/indefinite amount of time. + * + * Use mmput() to release the reference acquired by mmget(). + * + * See also <Documentation/vm/active_mm.txt> for an in-depth explanation + * of &mm_struct.mm_count vs &mm_struct.mm_users. + */ +static inline void mmget(struct mm_struct *mm) +{ + atomic_inc(&mm->mm_users); +} + static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); diff --git a/include/linux/sem.h b/include/linux/sem.h index d0efd6e6c20a..4fc222f8755d 100644 --- a/include/linux/sem.h +++ b/include/linux/sem.h @@ -21,7 +21,7 @@ struct sem_array { struct list_head list_id; /* undo requests on this array */ int sem_nsems; /* no. of semaphores in array */ int complex_count; /* pending complex operations */ - bool complex_mode; /* no parallel simple ops */ + unsigned int use_global_lock;/* >0: global lock required */ }; #ifdef CONFIG_SYSVIPC diff --git a/include/linux/spi/flash.h b/include/linux/spi/flash.h index 3f22932e67a4..f4199e758f97 100644 --- a/include/linux/spi/flash.h +++ b/include/linux/spi/flash.h @@ -7,7 +7,7 @@ struct mtd_partition; * struct flash_platform_data: board-specific flash data * @name: optional flash device name (eg, as used with mtdparts=) * @parts: optional array of mtd_partitions for static partitioning - * @nr_parts: number of mtd_partitions for static partitoning + * @nr_parts: number of mtd_partitions for static partitioning * @type: optional flash device type (e.g. m25p80 vs m25p64), for use * with chips that can't be queried for JEDEC or other IDs * diff --git a/include/linux/sunrpc/cache.h b/include/linux/sunrpc/cache.h index 8a511c0985aa..20d157a518a7 100644 --- a/include/linux/sunrpc/cache.h +++ b/include/linux/sunrpc/cache.h @@ -204,8 +204,11 @@ static inline void cache_put(struct cache_head *h, struct cache_detail *cd) kref_put(&h->ref, cd->cache_put); } -static inline int cache_is_expired(struct cache_detail *detail, struct cache_head *h) +static inline bool cache_is_expired(struct cache_detail *detail, struct cache_head *h) { + if (!test_bit(CACHE_VALID, &h->flags)) + return false; + return (h->expiry_time < seconds_since_boot()) || (detail->flush_time >= h->last_refresh); } @@ -227,6 +230,7 @@ extern void sunrpc_destroy_cache_detail(struct cache_detail *cd); extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *, umode_t, struct cache_detail *); extern void sunrpc_cache_unregister_pipefs(struct cache_detail *); +extern void sunrpc_cache_unhash(struct cache_detail *, struct cache_head *); /* Must store cache_detail in seq_file->private if using next three functions */ extern void *cache_seq_start(struct seq_file *file, loff_t *pos); diff --git a/include/linux/sunrpc/rpc_rdma.h b/include/linux/sunrpc/rpc_rdma.h index cfda6adcf33c..245fc59b7324 100644 --- a/include/linux/sunrpc/rpc_rdma.h +++ b/include/linux/sunrpc/rpc_rdma.h @@ -110,6 +110,15 @@ struct rpcrdma_msg { }; /* + * XDR sizes, in quads + */ +enum { + rpcrdma_fixed_maxsz = 4, + rpcrdma_segment_maxsz = 4, + rpcrdma_readchunk_maxsz = 2 + rpcrdma_segment_maxsz, +}; + +/* * Smallest RPC/RDMA header: rm_xid through rm_type, then rm_nochunks */ #define RPCRDMA_HDRLEN_MIN (sizeof(__be32) * 7) diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 7321ae933867..e770abeed32d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -400,10 +400,14 @@ struct svc_version { struct svc_procedure * vs_proc; /* per-procedure info */ u32 vs_xdrsize; /* xdrsize needed for this version */ - unsigned int vs_hidden : 1, /* Don't register with portmapper. - * Only used for nfsacl so far. */ - vs_rpcb_optnl:1;/* Don't care the result of register. - * Only used for nfsv4. */ + /* Don't register with rpcbind */ + bool vs_hidden; + + /* Don't care if the rpcbind registration fails */ + bool vs_rpcb_optnl; + + /* Need xprt with congestion control */ + bool vs_need_cong_ctrl; /* Override dispatch function (e.g. when caching replies). * A return value of 0 means drop the request. diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index 757fb963696c..b105f73e3ca2 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -70,7 +70,7 @@ extern atomic_t rdma_stat_sq_prod; * completes. */ struct svc_rdma_op_ctxt { - struct list_head free; + struct list_head list; struct svc_rdma_op_ctxt *read_hdr; struct svc_rdma_fastreg_mr *frmr; int hdr_count; @@ -78,7 +78,6 @@ struct svc_rdma_op_ctxt { struct ib_cqe cqe; struct ib_cqe reg_cqe; struct ib_cqe inv_cqe; - struct list_head dto_q; u32 byte_len; u32 position; struct svcxprt_rdma *xprt; @@ -141,7 +140,8 @@ struct svcxprt_rdma { atomic_t sc_sq_avail; /* SQEs ready to be consumed */ unsigned int sc_sq_depth; /* Depth of SQ */ unsigned int sc_rq_depth; /* Depth of RQ */ - u32 sc_max_requests; /* Forward credits */ + __be32 sc_fc_credits; /* Forward credits */ + u32 sc_max_requests; /* Max requests */ u32 sc_max_bc_requests;/* Backward credits */ int sc_max_req_size; /* Size of each RQ WR buf */ @@ -171,7 +171,6 @@ struct svcxprt_rdma { wait_queue_head_t sc_send_wait; /* SQ exhaustion waitlist */ unsigned long sc_flags; - struct list_head sc_dto_q; /* DTO tasklet I/O pending Q */ struct list_head sc_read_complete_q; struct work_struct sc_work; }; @@ -214,11 +213,7 @@ extern void svc_rdma_xdr_encode_write_list(struct rpcrdma_msg *, int); extern void svc_rdma_xdr_encode_reply_array(struct rpcrdma_write_array *, int); extern void svc_rdma_xdr_encode_array_chunk(struct rpcrdma_write_array *, int, __be32, __be64, u32); -extern void svc_rdma_xdr_encode_reply_header(struct svcxprt_rdma *, - struct rpcrdma_msg *, - struct rpcrdma_msg *, - enum rpcrdma_proc); -extern int svc_rdma_xdr_get_reply_hdr_len(struct rpcrdma_msg *); +extern unsigned int svc_rdma_xdr_get_reply_hdr_len(__be32 *rdma_resp); /* svc_rdma_recvfrom.c */ extern int svc_rdma_recvfrom(struct svc_rqst *); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 7440290f64ac..ddb7f94a9d06 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -67,6 +67,7 @@ struct svc_xprt { #define XPT_CACHE_AUTH 11 /* cache auth info */ #define XPT_LOCAL 12 /* connection from loopback interface */ #define XPT_KILL_TEMP 13 /* call xpo_kill_temp_xprt before closing */ +#define XPT_CONG_CTRL 14 /* has congestion control */ struct svc_serv *xpt_server; /* service for transport */ atomic_t xpt_reserved; /* space on outq that is rsvd */ diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index a26cc437293c..bde063cefd04 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -106,9 +106,9 @@ struct work_struct { #endif }; -#define WORK_DATA_INIT() ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL) +#define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ - ATOMIC_LONG_INIT(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC) + ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; |
