diff options
Diffstat (limited to 'include/linux')
30 files changed, 630 insertions, 890 deletions
diff --git a/include/linux/ahci_platform.h b/include/linux/ahci_platform.h index 6dfd51a04d77..09a947e8bc87 100644 --- a/include/linux/ahci_platform.h +++ b/include/linux/ahci_platform.h @@ -43,10 +43,7 @@ struct ahci_host_priv *ahci_platform_get_resources( struct platform_device *pdev); int ahci_platform_init_host(struct platform_device *pdev, struct ahci_host_priv *hpriv, - const struct ata_port_info *pi_template, - unsigned long host_flags, - unsigned int force_port_map, - unsigned int mask_port_map); + const struct ata_port_info *pi_template); int ahci_platform_suspend_host(struct device *dev); int ahci_platform_resume_host(struct device *dev); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 8a111dd42d7a..b5223c570eba 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -203,7 +203,15 @@ struct cgroup { struct kernfs_node *kn; /* cgroup kernfs entry */ struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ - /* the bitmask of subsystems enabled on the child cgroups */ + /* + * The bitmask of subsystems enabled on the child cgroups. + * ->subtree_control is the one configured through + * "cgroup.subtree_control" while ->child_subsys_mask is the + * effective one which may have more subsystems enabled. + * Controller knobs are made available iff it's enabled in + * ->subtree_control. + */ + unsigned int subtree_control; unsigned int child_subsys_mask; /* Private pointers for each registered subsystem */ @@ -248,73 +256,9 @@ struct cgroup { /* cgroup_root->flags */ enum { - /* - * Unfortunately, cgroup core and various controllers are riddled - * with idiosyncrasies and pointless options. The following flag, - * when set, will force sane behavior - some options are forced on, - * others are disallowed, and some controllers will change their - * hierarchical or other behaviors. - * - * The set of behaviors affected by this flag are still being - * determined and developed and the mount option for this flag is - * prefixed with __DEVEL__. The prefix will be dropped once we - * reach the point where all behaviors are compatible with the - * planned unified hierarchy, which will automatically turn on this - * flag. - * - * The followings are the behaviors currently affected this flag. - * - * - Mount options "noprefix", "xattr", "clone_children", - * "release_agent" and "name" are disallowed. - * - * - When mounting an existing superblock, mount options should - * match. - * - * - Remount is disallowed. - * - * - rename(2) is disallowed. - * - * - "tasks" is removed. Everything should be at process - * granularity. Use "cgroup.procs" instead. - * - * - "cgroup.procs" is not sorted. pids will be unique unless they - * got recycled inbetween reads. - * - * - "release_agent" and "notify_on_release" are removed. - * Replacement notification mechanism will be implemented. - * - * - "cgroup.clone_children" is removed. - * - * - "cgroup.subtree_populated" is available. Its value is 0 if - * the cgroup and its descendants contain no task; otherwise, 1. - * The file also generates kernfs notification which can be - * monitored through poll and [di]notify when the value of the - * file changes. - * - * - If mount is requested with sane_behavior but without any - * subsystem, the default unified hierarchy is mounted. - * - * - cpuset: tasks will be kept in empty cpusets when hotplug happens - * and take masks of ancestors with non-empty cpus/mems, instead of - * being moved to an ancestor. - * - * - cpuset: a task can be moved into an empty cpuset, and again it - * takes masks of ancestors. - * - * - memcg: use_hierarchy is on by default and the cgroup file for - * the flag is not created. - * - * - blkcg: blk-throttle becomes properly hierarchical. - * - * - debug: disallowed on the default hierarchy. - */ - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), - + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ - - /* mount options live below bit 16 */ - CGRP_ROOT_OPTION_MASK = (1 << 16) - 1, }; /* @@ -440,9 +384,11 @@ struct css_set { enum { CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ - CFTYPE_INSANE = (1 << 2), /* don't create if sane_behavior */ CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ - CFTYPE_ONLY_ON_DFL = (1 << 4), /* only on default hierarchy */ + + /* internal flags, do not use outside cgroup core proper */ + __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ + __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ }; #define MAX_CFTYPE_NAME 64 @@ -526,20 +472,64 @@ struct cftype { extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; +/** + * cgroup_on_dfl - test whether a cgroup is on the default hierarchy + * @cgrp: the cgroup of interest + * + * The default hierarchy is the v2 interface of cgroup and this function + * can be used to test whether a cgroup is on the default hierarchy for + * cases where a subsystem should behave differnetly depending on the + * interface version. + * + * The set of behaviors which change on the default hierarchy are still + * being determined and the mount option is prefixed with __DEVEL__. + * + * List of changed behaviors: + * + * - Mount options "noprefix", "xattr", "clone_children", "release_agent" + * and "name" are disallowed. + * + * - When mounting an existing superblock, mount options should match. + * + * - Remount is disallowed. + * + * - rename(2) is disallowed. + * + * - "tasks" is removed. Everything should be at process granularity. Use + * "cgroup.procs" instead. + * + * - "cgroup.procs" is not sorted. pids will be unique unless they got + * recycled inbetween reads. + * + * - "release_agent" and "notify_on_release" are removed. Replacement + * notification mechanism will be implemented. + * + * - "cgroup.clone_children" is removed. + * + * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup + * and its descendants contain no task; otherwise, 1. The file also + * generates kernfs notification which can be monitored through poll and + * [di]notify when the value of the file changes. + * + * - cpuset: tasks will be kept in empty cpusets when hotplug happens and + * take masks of ancestors with non-empty cpus/mems, instead of being + * moved to an ancestor. + * + * - cpuset: a task can be moved into an empty cpuset, and again it takes + * masks of ancestors. + * + * - memcg: use_hierarchy is on by default and the cgroup file for the flag + * is not created. + * + * - blkcg: blk-throttle becomes properly hierarchical. + * + * - debug: disallowed on the default hierarchy. + */ static inline bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } -/* - * See the comment above CGRP_ROOT_SANE_BEHAVIOR for details. This - * function can be called as long as @cgrp is accessible. - */ -static inline bool cgroup_sane_behavior(const struct cgroup *cgrp) -{ - return cgrp->root->flags & CGRP_ROOT_SANE_BEHAVIOR; -} - /* no synchronization, the result can only be used as a hint */ static inline bool cgroup_has_tasks(struct cgroup *cgrp) { @@ -602,7 +592,8 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); -int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); @@ -634,6 +625,7 @@ struct cgroup_subsys { int (*css_online)(struct cgroup_subsys_state *css); void (*css_offline)(struct cgroup_subsys_state *css); void (*css_free)(struct cgroup_subsys_state *css); + void (*css_reset)(struct cgroup_subsys_state *css); int (*can_attach)(struct cgroup_subsys_state *css, struct cgroup_taskset *tset); @@ -682,8 +674,21 @@ struct cgroup_subsys { */ struct list_head cfts; - /* base cftypes, automatically registered with subsys itself */ - struct cftype *base_cftypes; + /* + * Base cftypes which are automatically registered. The two can + * point to the same array. + */ + struct cftype *dfl_cftypes; /* for the default hierarchy */ + struct cftype *legacy_cftypes; /* for the legacy hierarchies */ + + /* + * A subsystem may depend on other subsystems. When such subsystem + * is enabled on a cgroup, the depended-upon subsystems are enabled + * together if available. Subsystems enabled due to dependency are + * not visible to userland until explicitly enabled. The following + * specifies the mask of subsystems that this one depends on. + */ + unsigned int depends_on; }; #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 0c287dbbb144..411dd7eb2653 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -619,5 +619,10 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) #endif /* platform dependent I/O accessors */ +#ifdef CONFIG_DEBUG_FS +struct dentry *clk_debugfs_add_file(struct clk *clk, char *name, umode_t mode, + void *data, const struct file_operations *fops); +#endif + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ diff --git a/include/linux/clk/clk-conf.h b/include/linux/clk/clk-conf.h new file mode 100644 index 000000000000..f3050e15f833 --- /dev/null +++ b/include/linux/clk/clk-conf.h @@ -0,0 +1,20 @@ +/* + * Copyright (C) 2014 Samsung Electronics Co., Ltd. + * Sylwester Nawrocki <s.nawrocki@samsung.com> + * + * 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 device_node; + +#if defined(CONFIG_OF) && defined(CONFIG_COMMON_CLK) +int of_clk_set_defaults(struct device_node *node, bool clk_supplier); +#else +static inline int of_clk_set_defaults(struct device_node *node, + bool clk_supplier) +{ + return 0; +} +#endif diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ec4112d257bc..8f8ae95c6e27 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -482,8 +482,8 @@ extern struct cpufreq_governor cpufreq_gov_conservative; *********************************************************************/ /* Special Values of .frequency field */ -#define CPUFREQ_ENTRY_INVALID ~0 -#define CPUFREQ_TABLE_END ~1 +#define CPUFREQ_ENTRY_INVALID ~0u +#define CPUFREQ_TABLE_END ~1u /* Special Values of .flags field */ #define CPUFREQ_BOOST_FREQ (1 << 0) diff --git a/include/linux/crypto.h b/include/linux/crypto.h index b92eadf92d72..d45e949699ea 100644 --- a/include/linux/crypto.h +++ b/include/linux/crypto.h @@ -710,9 +710,9 @@ static inline void ablkcipher_request_free(struct ablkcipher_request *req) static inline void ablkcipher_request_set_callback( struct ablkcipher_request *req, - u32 flags, crypto_completion_t complete, void *data) + u32 flags, crypto_completion_t compl, void *data) { - req->base.complete = complete; + req->base.complete = compl; req->base.data = data; req->base.flags = flags; } @@ -841,10 +841,10 @@ static inline void aead_request_free(struct aead_request *req) static inline void aead_request_set_callback(struct aead_request *req, u32 flags, - crypto_completion_t complete, + crypto_completion_t compl, void *data) { - req->base.complete = complete; + req->base.complete = compl; req->base.data = data; req->base.flags = flags; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e11d60cc867b..2daccaf4b547 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -833,7 +833,7 @@ static inline struct file *get_file(struct file *f) * * Lockd stuffs a "host" pointer into this. */ -typedef struct files_struct *fl_owner_t; +typedef void *fl_owner_t; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 255cd5cc0754..a23c096b3080 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -80,6 +80,7 @@ int dequeue_hwpoisoned_huge_page(struct page *page); bool isolate_huge_page(struct page *page, struct list_head *list); void putback_active_hugepage(struct page *page); bool is_hugepage_active(struct page *page); +void free_huge_page(struct page *page); #ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 17aa1cce6f8e..30faf797c2c3 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -91,6 +91,7 @@ struct kernfs_elem_attr { const struct kernfs_ops *ops; struct kernfs_open_node *open; loff_t size; + struct kernfs_node *notify_next; /* for kernfs_notify() */ }; /* @@ -304,6 +305,7 @@ struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags, struct kernfs_root *root, unsigned long magic, bool *new_sb_created, const void *ns); void kernfs_kill_sb(struct super_block *sb); +struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns); void kernfs_init(void); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 7dcef3317689..13d55206ccf6 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -73,7 +73,6 @@ struct kthread_worker { struct kthread_work { struct list_head node; kthread_work_func_t func; - wait_queue_head_t done; struct kthread_worker *worker; }; @@ -85,7 +84,6 @@ struct kthread_work { #define KTHREAD_WORK_INIT(work, fn) { \ .node = LIST_HEAD_INIT((work).node), \ .func = (fn), \ - .done = __WAIT_QUEUE_HEAD_INITIALIZER((work).done), \ } #define DEFINE_KTHREAD_WORKER(worker) \ @@ -95,22 +93,16 @@ struct kthread_work { struct kthread_work work = KTHREAD_WORK_INIT(work, fn) /* - * kthread_worker.lock and kthread_work.done need their own lockdep class - * keys if they are defined on stack with lockdep enabled. Use the - * following macros when defining them on stack. + * kthread_worker.lock needs its own lockdep class key when defined on + * stack with lockdep enabled. Use the following macros in such cases. */ #ifdef CONFIG_LOCKDEP # define KTHREAD_WORKER_INIT_ONSTACK(worker) \ ({ init_kthread_worker(&worker); worker; }) # define DEFINE_KTHREAD_WORKER_ONSTACK(worker) \ struct kthread_worker worker = KTHREAD_WORKER_INIT_ONSTACK(worker) -# define KTHREAD_WORK_INIT_ONSTACK(work, fn) \ - ({ init_kthread_work((&work), fn); work; }) -# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) \ - struct kthread_work work = KTHREAD_WORK_INIT_ONSTACK(work, fn) #else # define DEFINE_KTHREAD_WORKER_ONSTACK(worker) DEFINE_KTHREAD_WORKER(worker) -# define DEFINE_KTHREAD_WORK_ONSTACK(work, fn) DEFINE_KTHREAD_WORK(work, fn) #endif extern void __init_kthread_worker(struct kthread_worker *worker, @@ -127,7 +119,6 @@ extern void __init_kthread_worker(struct kthread_worker *worker, memset((work), 0, sizeof(struct kthread_work)); \ INIT_LIST_HEAD(&(work)->node); \ (work)->func = (fn); \ - init_waitqueue_head(&(work)->done); \ } while (0) int kthread_worker_fn(void *worker_ptr); diff --git a/include/linux/libata.h b/include/linux/libata.h index 5ab4e3a76721..92abb497ab14 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -593,6 +593,7 @@ struct ata_host { struct device *dev; void __iomem * const *iomap; unsigned int n_ports; + unsigned int n_tags; /* nr of NCQ tags */ void *private_data; struct ata_port_operations *ops; unsigned long flags; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index b12f4bbd064c..35b51e7af886 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -578,8 +578,6 @@ struct mlx4_cq { u32 cons_index; u16 irq; - bool irq_affinity_change; - __be32 *set_ci_db; __be32 *arm_db; int arm_sn; @@ -1167,6 +1165,8 @@ int mlx4_assign_eq(struct mlx4_dev *dev, char *name, struct cpu_rmap *rmap, int *vector); void mlx4_release_eq(struct mlx4_dev *dev, int vec); +int mlx4_eq_get_irq(struct mlx4_dev *dev, int vec); + int mlx4_get_phys_port_id(struct mlx4_dev *dev); int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port); int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port); diff --git a/include/linux/msi.h b/include/linux/msi.h index 92a2f991262a..8103f32f6d87 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -25,7 +25,8 @@ void write_msi_msg(unsigned int irq, struct msi_msg *msg); struct msi_desc { struct { __u8 is_msix : 1; - __u8 multiple: 3; /* log2 number of messages */ + __u8 multiple: 3; /* log2 num of messages allocated */ + __u8 multi_cap : 3; /* log2 num of messages supported */ __u8 maskbit : 1; /* mask-pending bit supported ? */ __u8 is_64 : 1; /* Address size: 0=32bit 1=64bit */ __u8 pos; /* Location of the msi capability */ diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 11692dea18aa..42aa9b9ecd5f 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -17,6 +17,7 @@ #include <linux/lockdep.h> #include <linux/atomic.h> #include <asm/processor.h> +#include <linux/osq_lock.h> /* * Simple, straightforward mutexes with strict semantics: @@ -46,7 +47,6 @@ * - detects multi-task circular deadlocks and prints out all affected * locks and tasks (and only those tasks) */ -struct optimistic_spin_queue; struct mutex { /* 1: unlocked, 0: locked, negative: locked, possible waiters */ atomic_t count; @@ -56,7 +56,7 @@ struct mutex { struct task_struct *owner; #endif #ifdef CONFIG_MUTEX_SPIN_ON_OWNER - struct optimistic_spin_queue *osq; /* Spinner MCS lock */ + struct optimistic_spin_queue osq; /* Spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_MUTEXES const char *name; diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 05117899fcb4..0ff360d5b3b3 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -73,6 +73,8 @@ extern int early_init_dt_scan_root(unsigned long node, const char *uname, int depth, void *data); extern bool early_init_dt_scan(void *params); +extern bool early_init_dt_verify(void *params); +extern void early_init_dt_scan_nodes(void); extern const char *of_flat_dt_get_machine_name(void); extern const void *of_flat_dt_match_machine(const void *default_match, @@ -84,6 +86,7 @@ extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); extern void early_get_first_memblock_info(void *, phys_addr_t *); extern u64 fdt_translate_address(const void *blob, int node_offset); +extern void of_fdt_limit_memory(int limit); #else /* CONFIG_OF_FLATTREE */ static inline void early_init_fdt_scan_reserved_mem(void) {} static inline const char *of_flat_dt_get_machine_name(void) { return NULL; } diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index a70c9493d55a..d449018d0726 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -25,9 +25,6 @@ struct phy_device *of_phy_attach(struct net_device *dev, extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np); -extern void of_mdiobus_link_phydev(struct mii_bus *mdio, - struct phy_device *phydev); - #else /* CONFIG_OF */ static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) { @@ -63,11 +60,6 @@ static inline struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np) { return NULL; } - -static inline void of_mdiobus_link_phydev(struct mii_bus *mdio, - struct phy_device *phydev) -{ -} #endif /* CONFIG_OF */ #if defined(CONFIG_OF) && defined(CONFIG_FIXED_PHY) diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h new file mode 100644 index 000000000000..90230d5811c5 --- /dev/null +++ b/include/linux/osq_lock.h @@ -0,0 +1,27 @@ +#ifndef __LINUX_OSQ_LOCK_H +#define __LINUX_OSQ_LOCK_H + +/* + * An MCS like lock especially tailored for optimistic spinning for sleeping + * lock implementations (mutex, rwsem, etc). + */ + +#define OSQ_UNLOCKED_VAL (0) + +struct optimistic_spin_queue { + /* + * Stores an encoded value of the CPU # of the tail node in the queue. + * If the queue is empty, then it's set to OSQ_UNLOCKED_VAL. + */ + atomic_t tail; +}; + +/* Init macro and function. */ +#define OSQ_LOCK_UNLOCKED { ATOMIC_INIT(OSQ_UNLOCKED_VAL) } + +static inline void osq_lock_init(struct optimistic_spin_queue *lock) +{ + atomic_set(&lock->tail, OSQ_UNLOCKED_VAL); +} + +#endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0a97b583ee8d..e1474ae18c88 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -399,6 +399,18 @@ static inline struct page *read_mapping_page(struct address_space *mapping, } /* + * Get the offset in PAGE_SIZE. + * (TODO: hugepage should have ->index in PAGE_SIZE) + */ +static inline pgoff_t page_to_pgoff(struct page *page) +{ + if (unlikely(PageHeadHuge(page))) + return page->index << compound_order(page); + else + return page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); +} + +/* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) diff --git a/include/linux/pci.h b/include/linux/pci.h index 466bcd111d85..6ed3647b38df 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -978,6 +978,8 @@ int pci_try_reset_slot(struct pci_slot *slot); int pci_probe_reset_bus(struct pci_bus *bus); int pci_reset_bus(struct pci_bus *bus); int pci_try_reset_bus(struct pci_bus *bus); +void pci_reset_secondary_bus(struct pci_dev *dev); +void pcibios_reset_secondary_bus(struct pci_dev *dev); void pci_reset_bridge_secondary_bus(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); @@ -1186,7 +1188,6 @@ int pci_msix_vec_count(struct pci_dev *dev); int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec); void pci_msix_shutdown(struct pci_dev *dev); void pci_disable_msix(struct pci_dev *dev); -void msi_remove_pci_irq_vectors(struct pci_dev *dev); void pci_restore_msi_state(struct pci_dev *dev); int pci_msi_enabled(void); int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec); @@ -1217,7 +1218,6 @@ static inline int pci_enable_msix(struct pci_dev *dev, { return -ENOSYS; } static inline void pci_msix_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msix(struct pci_dev *dev) { } -static inline void msi_remove_pci_irq_vectors(struct pci_dev *dev) { } static inline void pci_restore_msi_state(struct pci_dev *dev) { } static inline int pci_msi_enabled(void) { return 0; } static inline int pci_enable_msi_range(struct pci_dev *dev, int minvec, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 7fa31731c854..6ed0bb73a864 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -6,6 +6,8 @@ * Do not add new entries to this file unless the definitions * are shared between multiple drivers. */ +#ifndef _LINUX_PCI_IDS_H +#define _LINUX_PCI_IDS_H /* Device classes and subclasses */ @@ -2968,3 +2970,5 @@ #define PCI_DEVICE_ID_XEN_PLATFORM 0x0001 #define PCI_VENDOR_ID_OCZ 0x1b85 + +#endif /* _LINUX_PCI_IDS_H */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index a5fc7d01aad6..cfd56046ecec 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -1,6 +1,40 @@ +/* + * linux/percpu-defs.h - basic definitions for percpu areas + * + * DO NOT INCLUDE DIRECTLY OUTSIDE PERCPU IMPLEMENTATION PROPER. + * + * This file is separate from linux/percpu.h to avoid cyclic inclusion + * dependency from arch header files. Only to be included from + * asm/percpu.h. + * + * This file includes macros necessary to declare percpu sections and + * variables, and definitions of percpu accessors and operations. It + * should provide enough percpu features to arch header files even when + * they can only include asm/percpu.h to avoid cyclic inclusion dependency. + */ + #ifndef _LINUX_PERCPU_DEFS_H #define _LINUX_PERCPU_DEFS_H +#ifdef CONFIG_SMP + +#ifdef MODULE +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_ALIGNED_SECTION "" +#else +#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned" +#define PER_CPU_ALIGNED_SECTION "..shared_aligned" +#endif +#define PER_CPU_FIRST_SECTION "..first" + +#else + +#define PER_CPU_SHARED_ALIGNED_SECTION "" +#define PER_CPU_ALIGNED_SECTION "..shared_aligned" +#define PER_CPU_FIRST_SECTION "" + +#endif + /* * Base implementations of per-CPU variable declarations and definitions, where * the section in which the variable is to be placed is provided by the @@ -19,19 +53,6 @@ __attribute__((section(".discard"), unused)) /* - * Macro which verifies @ptr is a percpu pointer without evaluating - * @ptr. This is to be used in percpu accessors to verify that the - * input parameter is a percpu pointer. - * - * + 0 is required in order to convert the pointer type from a - * potential array type to a pointer to a single item of the array. - */ -#define __verify_pcpu_ptr(ptr) do { \ - const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ - (void)__vpp_verify; \ -} while (0) - -/* * s390 and alpha modules require percpu variables to be defined as * weak to force the compiler to generate GOT based external * references for them. This is necessary because percpu sections @@ -146,10 +167,10 @@ * Declaration/definition used for per-CPU variables that must be read mostly. */ #define DECLARE_PER_CPU_READ_MOSTLY(type, name) \ - DECLARE_PER_CPU_SECTION(type, name, "..readmostly") + DECLARE_PER_CPU_SECTION(type, name, "..read_mostly") #define DEFINE_PER_CPU_READ_MOSTLY(type, name) \ - DEFINE_PER_CPU_SECTION(type, name, "..readmostly") + DEFINE_PER_CPU_SECTION(type, name, "..read_mostly") /* * Intermodule exports for per-CPU variables. sparse forgets about @@ -164,4 +185,337 @@ #define EXPORT_PER_CPU_SYMBOL_GPL(var) #endif +/* + * Accessors and operations. + */ +#ifndef __ASSEMBLY__ + +/* + * __verify_pcpu_ptr() verifies @ptr is a percpu pointer without evaluating + * @ptr and is invoked once before a percpu area is accessed by all + * accessors and operations. This is performed in the generic part of + * percpu and arch overrides don't need to worry about it; however, if an + * arch wants to implement an arch-specific percpu accessor or operation, + * it may use __verify_pcpu_ptr() to verify the parameters. + * + * + 0 is required in order to convert the pointer type from a + * potential array type to a pointer to a single item of the array. + */ +#define __verify_pcpu_ptr(ptr) \ +do { \ + const void __percpu *__vpp_verify = (typeof((ptr) + 0))NULL; \ + (void)__vpp_verify; \ +} while (0) + +#ifdef CONFIG_SMP + +/* + * Add an offset to a pointer but keep the pointer as-is. Use RELOC_HIDE() + * to prevent the compiler from making incorrect assumptions about the + * pointer value. The weird cast keeps both GCC and sparse happy. + */ +#define SHIFT_PERCPU_PTR(__p, __offset) \ + RELOC_HIDE((typeof(*(__p)) __kernel __force *)(__p), (__offset)) + +#define per_cpu_ptr(ptr, cpu) \ +({ \ + __verify_pcpu_ptr(ptr); \ + SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))); \ +}) + +#define raw_cpu_ptr(ptr) \ +({ \ + __verify_pcpu_ptr(ptr); \ + arch_raw_cpu_ptr(ptr); \ +}) + +#ifdef CONFIG_DEBUG_PREEMPT +#define this_cpu_ptr(ptr) \ +({ \ + __verify_pcpu_ptr(ptr); \ + SHIFT_PERCPU_PTR(ptr, my_cpu_offset); \ +}) +#else +#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) +#endif + +#else /* CONFIG_SMP */ + +#define VERIFY_PERCPU_PTR(__p) \ +({ \ + __verify_pcpu_ptr(__p); \ + (typeof(*(__p)) __kernel __force *)(__p); \ +}) + +#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR(ptr); }) +#define raw_cpu_ptr(ptr) per_cpu_ptr(ptr, 0) +#define this_cpu_ptr(ptr) raw_cpu_ptr(ptr) + +#endif /* CONFIG_SMP */ + +#define per_cpu(var, cpu) (*per_cpu_ptr(&(var), cpu)) +#define __raw_get_cpu_var(var) (*raw_cpu_ptr(&(var))) +#define __get_cpu_var(var) (*this_cpu_ptr(&(var))) + +/* keep until we have removed all uses of __this_cpu_ptr */ +#define __this_cpu_ptr(ptr) raw_cpu_ptr(ptr) + +/* + * Must be an lvalue. Since @var must be a simple identifier, + * we force a syntax error here if it isn't. + */ +#define get_cpu_var(var) \ +(*({ \ + preempt_disable(); \ + this_cpu_ptr(&var); \ +})) + +/* + * The weird & is necessary because sparse considers (void)(var) to be + * a direct dereference of percpu variable (var). + */ +#define put_cpu_var(var) \ +do { \ + (void)&(var); \ + preempt_enable(); \ +} while (0) + +#define get_cpu_ptr(var) \ +({ \ + preempt_disable(); \ + this_cpu_ptr(var); \ +}) + +#define put_cpu_ptr(var) \ +do { \ + (void)(var); \ + preempt_enable(); \ +} while (0) + +/* + * Branching function to split up a function into a set of functions that + * are called for different scalar sizes of the objects handled. + */ + +extern void __bad_size_call_parameter(void); + +#ifdef CONFIG_DEBUG_PREEMPT +extern void __this_cpu_preempt_check(const char *op); +#else +static inline void __this_cpu_preempt_check(const char *op) { } +#endif + +#define __pcpu_size_call_return(stem, variable) \ +({ \ + typeof(variable) pscr_ret__; \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: pscr_ret__ = stem##1(variable); break; \ + case 2: pscr_ret__ = stem##2(variable); break; \ + case 4: pscr_ret__ = stem##4(variable); break; \ + case 8: pscr_ret__ = stem##8(variable); break; \ + default: \ + __bad_size_call_parameter(); break; \ + } \ + pscr_ret__; \ +}) + +#define __pcpu_size_call_return2(stem, variable, ...) \ +({ \ + typeof(variable) pscr2_ret__; \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \ + case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \ + case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \ + case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \ + default: \ + __bad_size_call_parameter(); break; \ + } \ + pscr2_ret__; \ +}) + +/* + * Special handling for cmpxchg_double. cmpxchg_double is passed two + * percpu variables. The first has to be aligned to a double word + * boundary and the second has to follow directly thereafter. + * We enforce this on all architectures even if they don't support + * a double cmpxchg instruction, since it's a cheap requirement, and it + * avoids breaking the requirement for architectures with the instruction. + */ +#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...) \ +({ \ + bool pdcrb_ret__; \ + __verify_pcpu_ptr(&(pcp1)); \ + BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2)); \ + VM_BUG_ON((unsigned long)(&(pcp1)) % (2 * sizeof(pcp1))); \ + VM_BUG_ON((unsigned long)(&(pcp2)) != \ + (unsigned long)(&(pcp1)) + sizeof(pcp1)); \ + switch(sizeof(pcp1)) { \ + case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break; \ + case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break; \ + case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break; \ + case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break; \ + default: \ + __bad_size_call_parameter(); break; \ + } \ + pdcrb_ret__; \ +}) + +#define __pcpu_size_call(stem, variable, ...) \ +do { \ + __verify_pcpu_ptr(&(variable)); \ + switch(sizeof(variable)) { \ + case 1: stem##1(variable, __VA_ARGS__);break; \ + case 2: stem##2(variable, __VA_ARGS__);break; \ + case 4: stem##4(variable, __VA_ARGS__);break; \ + case 8: stem##8(variable, __VA_ARGS__);break; \ + default: \ + __bad_size_call_parameter();break; \ + } \ +} while (0) + +/* + * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com> + * + * Optimized manipulation for memory allocated through the per cpu + * allocator or for addresses of per cpu variables. + * + * These operation guarantee exclusivity of access for other operations + * on the *same* processor. The assumption is that per cpu data is only + * accessed by a single processor instance (the current one). + * + * The arch code can provide optimized implementation by defining macros + * for certain scalar sizes. F.e. provide this_cpu_add_2() to provide per + * cpu atomic operations for 2 byte sized RMW actions. If arch code does + * not provide operations for a scalar size then the fallback in the + * generic code will be used. + * + * cmpxchg_double replaces two adjacent scalars at once. The first two + * parameters are per cpu variables which have to be of the same size. A + * truth value is returned to indicate success or failure (since a double + * register result is difficult to handle). There is very limited hardware + * support for these operations, so only certain sizes may work. + */ + +/* + * Operations for contexts where we do not want to do any checks for + * preemptions. Unless strictly necessary, always use [__]this_cpu_*() + * instead. + * + * If there is no other protection through preempt disable and/or disabling + * interupts then one of these RMW operations can show unexpected behavior + * because the execution thread was rescheduled on another processor or an + * interrupt occurred and the same percpu variable was modified from the + * interrupt context. + */ +#define raw_cpu_read(pcp) __pcpu_size_call_return(raw_cpu_read_, pcp) +#define raw_cpu_write(pcp, val) __pcpu_size_call(raw_cpu_write_, pcp, val) +#define raw_cpu_add(pcp, val) __pcpu_size_call(raw_cpu_add_, pcp, val) +#define raw_cpu_and(pcp, val) __pcpu_size_call(raw_cpu_and_, pcp, val) +#define raw_cpu_or(pcp, val) __pcpu_size_call(raw_cpu_or_, pcp, val) +#define raw_cpu_add_return(pcp, val) __pcpu_size_call_return2(raw_cpu_add_return_, pcp, val) +#define raw_cpu_xchg(pcp, nval) __pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval) +#define raw_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval) +#define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + __pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2) + +#define raw_cpu_sub(pcp, val) raw_cpu_add(pcp, -(val)) +#define raw_cpu_inc(pcp) raw_cpu_add(pcp, 1) +#define raw_cpu_dec(pcp) raw_cpu_sub(pcp, 1) +#define raw_cpu_sub_return(pcp, val) raw_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define raw_cpu_inc_return(pcp) raw_cpu_add_return(pcp, 1) +#define raw_cpu_dec_return(pcp) raw_cpu_add_return(pcp, -1) + +/* + * Operations for contexts that are safe from preemption/interrupts. These + * operations verify that preemption is disabled. + */ +#define __this_cpu_read(pcp) \ +({ \ + __this_cpu_preempt_check("read"); \ + raw_cpu_read(pcp); \ +}) + +#define __this_cpu_write(pcp, val) \ +({ \ + __this_cpu_preempt_check("write"); \ + raw_cpu_write(pcp, val); \ +}) + +#define __this_cpu_add(pcp, val) \ +({ \ + __this_cpu_preempt_check("add"); \ + raw_cpu_add(pcp, val); \ +}) + +#define __this_cpu_and(pcp, val) \ +({ \ + __this_cpu_preempt_check("and"); \ + raw_cpu_and(pcp, val); \ +}) + +#define __this_cpu_or(pcp, val) \ +({ \ + __this_cpu_preempt_check("or"); \ + raw_cpu_or(pcp, val); \ +}) + +#define __this_cpu_add_return(pcp, val) \ +({ \ + __this_cpu_preempt_check("add_return"); \ + raw_cpu_add_return(pcp, val); \ +}) + +#define __this_cpu_xchg(pcp, nval) \ +({ \ + __this_cpu_preempt_check("xchg"); \ + raw_cpu_xchg(pcp, nval); \ +}) + +#define __this_cpu_cmpxchg(pcp, oval, nval) \ +({ \ + __this_cpu_preempt_check("cmpxchg"); \ + raw_cpu_cmpxchg(pcp, oval, nval); \ +}) + +#define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ +({ __this_cpu_preempt_check("cmpxchg_double"); \ + raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2); \ +}) + +#define __this_cpu_sub(pcp, val) __this_cpu_add(pcp, -(typeof(pcp))(val)) +#define __this_cpu_inc(pcp) __this_cpu_add(pcp, 1) +#define __this_cpu_dec(pcp) __this_cpu_sub(pcp, 1) +#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) +#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) + +/* + * Operations with implied preemption protection. These operations can be + * used without worrying about preemption. Note that interrupts may still + * occur while an operation is in progress and if the interrupt modifies + * the variable too then RMW actions may not be reliable. + */ +#define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, pcp) +#define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, pcp, val) +#define this_cpu_add(pcp, val) __pcpu_size_call(this_cpu_add_, pcp, val) +#define this_cpu_and(pcp, val) __pcpu_size_call(this_cpu_and_, pcp, val) +#define this_cpu_or(pcp, val) __pcpu_size_call(this_cpu_or_, pcp, val) +#define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) +#define this_cpu_xchg(pcp, nval) __pcpu_size_call_return2(this_cpu_xchg_, pcp, nval) +#define this_cpu_cmpxchg(pcp, oval, nval) \ + __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval) +#define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ + __pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2) + +#define this_cpu_sub(pcp, val) this_cpu_add(pcp, -(typeof(pcp))(val)) +#define this_cpu_inc(pcp) this_cpu_add(pcp, 1) +#define this_cpu_dec(pcp) this_cpu_sub(pcp, 1) +#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(typeof(pcp))(val)) +#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) +#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) + +#endif /* __ASSEMBLY__ */ #endif /* _LINUX_PERCPU_DEFS_H */ diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index 5d8920e23073..3dfbf237cd8f 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -57,11 +57,9 @@ struct percpu_ref { atomic_t count; /* * The low bit of the pointer indicates whether the ref is in percpu - * mode; if set, then get/put will manipulate the atomic_t (this is a - * hack because we need to keep the pointer around for - * percpu_ref_kill_rcu()) + * mode; if set, then get/put will manipulate the atomic_t. */ - unsigned __percpu *pcpu_count; + unsigned long pcpu_count_ptr; percpu_ref_func_t *release; percpu_ref_func_t *confirm_kill; struct rcu_head rcu; @@ -69,7 +67,8 @@ struct percpu_ref { int __must_check percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release); -void percpu_ref_cancel_init(struct percpu_ref *ref); +void percpu_ref_reinit(struct percpu_ref *ref); +void percpu_ref_exit(struct percpu_ref *ref); void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill); @@ -88,12 +87,28 @@ static inline void percpu_ref_kill(struct percpu_ref *ref) return percpu_ref_kill_and_confirm(ref, NULL); } -#define PCPU_STATUS_BITS 2 -#define PCPU_STATUS_MASK ((1 << PCPU_STATUS_BITS) - 1) -#define PCPU_REF_PTR 0 #define PCPU_REF_DEAD 1 -#define REF_STATUS(count) (((unsigned long) count) & PCPU_STATUS_MASK) +/* + * Internal helper. Don't use outside percpu-refcount proper. The + * function doesn't return the pointer and let the caller test it for NULL + * because doing so forces the compiler to generate two conditional + * branches as it can't assume that @ref->pcpu_count is not NULL. + */ +static inline bool __pcpu_ref_alive(struct percpu_ref *ref, + unsigned __percpu **pcpu_countp) +{ + unsigned long pcpu_ptr = ACCESS_ONCE(ref->pcpu_count_ptr); + + /* paired with smp_store_release() in percpu_ref_reinit() */ + smp_read_barrier_depends(); + + if (unlikely(pcpu_ptr & PCPU_REF_DEAD)) + return false; + + *pcpu_countp = (unsigned __percpu *)pcpu_ptr; + return true; +} /** * percpu_ref_get - increment a percpu refcount @@ -107,9 +122,7 @@ static inline void percpu_ref_get(struct percpu_ref *ref) rcu_read_lock_sched(); - pcpu_count = ACCESS_ONCE(ref->pcpu_count); - - if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) + if (__pcpu_ref_alive(ref, &pcpu_count)) this_cpu_inc(*pcpu_count); else atomic_inc(&ref->count); @@ -133,9 +146,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) rcu_read_lock_sched(); - pcpu_count = ACCESS_ONCE(ref->pcpu_count); - - if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) { + if (__pcpu_ref_alive(ref, &pcpu_count)) { this_cpu_inc(*pcpu_count); ret = true; } else { @@ -168,9 +179,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) rcu_read_lock_sched(); - pcpu_count = ACCESS_ONCE(ref->pcpu_count); - - if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) { + if (__pcpu_ref_alive(ref, &pcpu_count)) { this_cpu_inc(*pcpu_count); ret = true; } @@ -193,9 +202,7 @@ static inline void percpu_ref_put(struct percpu_ref *ref) rcu_read_lock_sched(); - pcpu_count = ACCESS_ONCE(ref->pcpu_count); - - if (likely(REF_STATUS(pcpu_count) == PCPU_REF_PTR)) + if (__pcpu_ref_alive(ref, &pcpu_count)) this_cpu_dec(*pcpu_count); else if (unlikely(atomic_dec_and_test(&ref->count))) ref->release(ref); @@ -203,4 +210,19 @@ static inline void percpu_ref_put(struct percpu_ref *ref) rcu_read_unlock_sched(); } +/** + * percpu_ref_is_zero - test whether a percpu refcount reached zero + * @ref: percpu_ref to test + * + * Returns %true if @ref reached zero. + */ +static inline bool percpu_ref_is_zero(struct percpu_ref *ref) +{ + unsigned __percpu *pcpu_count; + + if (__pcpu_ref_alive(ref, &pcpu_count)) + return false; + return !atomic_read(&ref->count); +} + #endif diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 8419053d0f2e..6f61b61b7996 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -23,32 +23,6 @@ PERCPU_MODULE_RESERVE) #endif -/* - * Must be an lvalue. Since @var must be a simple identifier, - * we force a syntax error here if it isn't. - */ -#define get_cpu_var(var) (*({ \ - preempt_disable(); \ - this_cpu_ptr(&var); })) - -/* - * The weird & is necessary because sparse considers (void)(var) to be - * a direct dereference of percpu variable (var). - */ -#define put_cpu_var(var) do { \ - (void)&(var); \ - preempt_enable(); \ -} while (0) - -#define get_cpu_ptr(var) ({ \ - preempt_disable(); \ - this_cpu_ptr(var); }) - -#define put_cpu_ptr(var) do { \ - (void)(var); \ - preempt_enable(); \ -} while (0) - /* minimum unit size, also is the maximum supported allocation size */ #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) @@ -140,17 +114,6 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif -/* - * Use this to get to a cpu's version of the per-cpu object - * dynamically allocated. Non-atomic access to the current CPU's - * version should probably be combined with get_cpu()/put_cpu(). - */ -#ifdef CONFIG_SMP -#define per_cpu_ptr(ptr, cpu) SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu))) -#else -#define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); VERIFY_PERCPU_PTR((ptr)); }) -#endif - extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); extern bool is_kernel_percpu_address(unsigned long addr); @@ -166,640 +129,4 @@ extern phys_addr_t per_cpu_ptr_to_phys(void *addr); #define alloc_percpu(type) \ (typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type)) -/* - * Branching function to split up a function into a set of functions that - * are called for different scalar sizes of the objects handled. - */ - -extern void __bad_size_call_parameter(void); - -#ifdef CONFIG_DEBUG_PREEMPT -extern void __this_cpu_preempt_check(const char *op); -#else -static inline void __this_cpu_preempt_check(const char *op) { } -#endif - -#define __pcpu_size_call_return(stem, variable) \ -({ typeof(variable) pscr_ret__; \ - __verify_pcpu_ptr(&(variable)); \ - switch(sizeof(variable)) { \ - case 1: pscr_ret__ = stem##1(variable);break; \ - case 2: pscr_ret__ = stem##2(variable);break; \ - case 4: pscr_ret__ = stem##4(variable);break; \ - case 8: pscr_ret__ = stem##8(variable);break; \ - default: \ - __bad_size_call_parameter();break; \ - } \ - pscr_ret__; \ -}) - -#define __pcpu_size_call_return2(stem, variable, ...) \ -({ \ - typeof(variable) pscr2_ret__; \ - __verify_pcpu_ptr(&(variable)); \ - switch(sizeof(variable)) { \ - case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \ - case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \ - case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \ - case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \ - default: \ - __bad_size_call_parameter(); break; \ - } \ - pscr2_ret__; \ -}) - -/* - * Special handling for cmpxchg_double. cmpxchg_double is passed two - * percpu variables. The first has to be aligned to a double word - * boundary and the second has to follow directly thereafter. - * We enforce this on all architectures even if they don't support - * a double cmpxchg instruction, since it's a cheap requirement, and it - * avoids breaking the requirement for architectures with the instruction. - */ -#define __pcpu_double_call_return_bool(stem, pcp1, pcp2, ...) \ -({ \ - bool pdcrb_ret__; \ - __verify_pcpu_ptr(&pcp1); \ - BUILD_BUG_ON(sizeof(pcp1) != sizeof(pcp2)); \ - VM_BUG_ON((unsigned long)(&pcp1) % (2 * sizeof(pcp1))); \ - VM_BUG_ON((unsigned long)(&pcp2) != \ - (unsigned long)(&pcp1) + sizeof(pcp1)); \ - switch(sizeof(pcp1)) { \ - case 1: pdcrb_ret__ = stem##1(pcp1, pcp2, __VA_ARGS__); break; \ - case 2: pdcrb_ret__ = stem##2(pcp1, pcp2, __VA_ARGS__); break; \ - case 4: pdcrb_ret__ = stem##4(pcp1, pcp2, __VA_ARGS__); break; \ - case 8: pdcrb_ret__ = stem##8(pcp1, pcp2, __VA_ARGS__); break; \ - default: \ - __bad_size_call_parameter(); break; \ - } \ - pdcrb_ret__; \ -}) - -#define __pcpu_size_call(stem, variable, ...) \ -do { \ - __verify_pcpu_ptr(&(variable)); \ - switch(sizeof(variable)) { \ - case 1: stem##1(variable, __VA_ARGS__);break; \ - case 2: stem##2(variable, __VA_ARGS__);break; \ - case 4: stem##4(variable, __VA_ARGS__);break; \ - case 8: stem##8(variable, __VA_ARGS__);break; \ - default: \ - __bad_size_call_parameter();break; \ - } \ -} while (0) - -/* - * this_cpu operations (C) 2008-2013 Christoph Lameter <cl@linux.com> - * - * Optimized manipulation for memory allocated through the per cpu - * allocator or for addresses of per cpu variables. - * - * These operation guarantee exclusivity of access for other operations - * on the *same* processor. The assumption is that per cpu data is only - * accessed by a single processor instance (the current one). - * - * The first group is used for accesses that must be done in a - * preemption safe way since we know that the context is not preempt - * safe. Interrupts may occur. If the interrupt modifies the variable - * too then RMW actions will not be reliable. - * - * The arch code can provide optimized functions in two ways: - * - * 1. Override the function completely. F.e. define this_cpu_add(). - * The arch must then ensure that the various scalar format passed - * are handled correctly. - * - * 2. Provide functions for certain scalar sizes. F.e. provide - * this_cpu_add_2() to provide per cpu atomic operations for 2 byte - * sized RMW actions. If arch code does not provide operations for - * a scalar size then the fallback in the generic code will be - * used. - */ - -#define _this_cpu_generic_read(pcp) \ -({ typeof(pcp) ret__; \ - preempt_disable(); \ - ret__ = *this_cpu_ptr(&(pcp)); \ - preempt_enable(); \ - ret__; \ -}) - -#ifndef this_cpu_read -# ifndef this_cpu_read_1 -# define this_cpu_read_1(pcp) _this_cpu_generic_read(pcp) -# endif -# ifndef this_cpu_read_2 -# define this_cpu_read_2(pcp) _this_cpu_generic_read(pcp) -# endif -# ifndef this_cpu_read_4 -# define this_cpu_read_4(pcp) _this_cpu_generic_read(pcp) -# endif -# ifndef this_cpu_read_8 -# define this_cpu_read_8(pcp) _this_cpu_generic_read(pcp) -# endif -# define this_cpu_read(pcp) __pcpu_size_call_return(this_cpu_read_, (pcp)) -#endif - -#define _this_cpu_generic_to_op(pcp, val, op) \ -do { \ - unsigned long flags; \ - raw_local_irq_save(flags); \ - *raw_cpu_ptr(&(pcp)) op val; \ - raw_local_irq_restore(flags); \ -} while (0) - -#ifndef this_cpu_write -# ifndef this_cpu_write_1 -# define this_cpu_write_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef this_cpu_write_2 -# define this_cpu_write_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef this_cpu_write_4 -# define this_cpu_write_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef this_cpu_write_8 -# define this_cpu_write_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), =) -# endif -# define this_cpu_write(pcp, val) __pcpu_size_call(this_cpu_write_, (pcp), (val)) -#endif - -#ifndef this_cpu_add -# ifndef this_cpu_add_1 -# define this_cpu_add_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef this_cpu_add_2 -# define this_cpu_add_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef this_cpu_add_4 -# define this_cpu_add_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef this_cpu_add_8 -# define this_cpu_add_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), +=) -# endif -# define this_cpu_add(pcp, val) __pcpu_size_call(this_cpu_add_, (pcp), (val)) -#endif - -#ifndef this_cpu_sub -# define this_cpu_sub(pcp, val) this_cpu_add((pcp), -(typeof(pcp))(val)) -#endif - -#ifndef this_cpu_inc -# define this_cpu_inc(pcp) this_cpu_add((pcp), 1) -#endif - -#ifndef this_cpu_dec -# define this_cpu_dec(pcp) this_cpu_sub((pcp), 1) -#endif - -#ifndef this_cpu_and -# ifndef this_cpu_and_1 -# define this_cpu_and_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef this_cpu_and_2 -# define this_cpu_and_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef this_cpu_and_4 -# define this_cpu_and_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef this_cpu_and_8 -# define this_cpu_and_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), &=) -# endif -# define this_cpu_and(pcp, val) __pcpu_size_call(this_cpu_and_, (pcp), (val)) -#endif - -#ifndef this_cpu_or -# ifndef this_cpu_or_1 -# define this_cpu_or_1(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef this_cpu_or_2 -# define this_cpu_or_2(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef this_cpu_or_4 -# define this_cpu_or_4(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef this_cpu_or_8 -# define this_cpu_or_8(pcp, val) _this_cpu_generic_to_op((pcp), (val), |=) -# endif -# define this_cpu_or(pcp, val) __pcpu_size_call(this_cpu_or_, (pcp), (val)) -#endif - -#define _this_cpu_generic_add_return(pcp, val) \ -({ \ - typeof(pcp) ret__; \ - unsigned long flags; \ - raw_local_irq_save(flags); \ - raw_cpu_add(pcp, val); \ - ret__ = raw_cpu_read(pcp); \ - raw_local_irq_restore(flags); \ - ret__; \ -}) - -#ifndef this_cpu_add_return -# ifndef this_cpu_add_return_1 -# define this_cpu_add_return_1(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_2 -# define this_cpu_add_return_2(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_4 -# define this_cpu_add_return_4(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# ifndef this_cpu_add_return_8 -# define this_cpu_add_return_8(pcp, val) _this_cpu_generic_add_return(pcp, val) -# endif -# define this_cpu_add_return(pcp, val) __pcpu_size_call_return2(this_cpu_add_return_, pcp, val) -#endif - -#define this_cpu_sub_return(pcp, val) this_cpu_add_return(pcp, -(typeof(pcp))(val)) -#define this_cpu_inc_return(pcp) this_cpu_add_return(pcp, 1) -#define this_cpu_dec_return(pcp) this_cpu_add_return(pcp, -1) - -#define _this_cpu_generic_xchg(pcp, nval) \ -({ typeof(pcp) ret__; \ - unsigned long flags; \ - raw_local_irq_save(flags); \ - ret__ = raw_cpu_read(pcp); \ - raw_cpu_write(pcp, nval); \ - raw_local_irq_restore(flags); \ - ret__; \ -}) - -#ifndef this_cpu_xchg -# ifndef this_cpu_xchg_1 -# define this_cpu_xchg_1(pcp, nval) _this_cpu_generic_xchg(pcp, nval) -# endif -# ifndef this_cpu_xchg_2 -# define this_cpu_xchg_2(pcp, nval) _this_cpu_generic_xchg(pcp, nval) -# endif -# ifndef this_cpu_xchg_4 -# define this_cpu_xchg_4(pcp, nval) _this_cpu_generic_xchg(pcp, nval) -# endif -# ifndef this_cpu_xchg_8 -# define this_cpu_xchg_8(pcp, nval) _this_cpu_generic_xchg(pcp, nval) -# endif -# define this_cpu_xchg(pcp, nval) \ - __pcpu_size_call_return2(this_cpu_xchg_, (pcp), nval) -#endif - -#define _this_cpu_generic_cmpxchg(pcp, oval, nval) \ -({ \ - typeof(pcp) ret__; \ - unsigned long flags; \ - raw_local_irq_save(flags); \ - ret__ = raw_cpu_read(pcp); \ - if (ret__ == (oval)) \ - raw_cpu_write(pcp, nval); \ - raw_local_irq_restore(flags); \ - ret__; \ -}) - -#ifndef this_cpu_cmpxchg -# ifndef this_cpu_cmpxchg_1 -# define this_cpu_cmpxchg_1(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef this_cpu_cmpxchg_2 -# define this_cpu_cmpxchg_2(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef this_cpu_cmpxchg_4 -# define this_cpu_cmpxchg_4(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef this_cpu_cmpxchg_8 -# define this_cpu_cmpxchg_8(pcp, oval, nval) _this_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# define this_cpu_cmpxchg(pcp, oval, nval) \ - __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval) -#endif - -/* - * cmpxchg_double replaces two adjacent scalars at once. The first - * two parameters are per cpu variables which have to be of the same - * size. A truth value is returned to indicate success or failure - * (since a double register result is difficult to handle). There is - * very limited hardware support for these operations, so only certain - * sizes may work. - */ -#define _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ -({ \ - int ret__; \ - unsigned long flags; \ - raw_local_irq_save(flags); \ - ret__ = raw_cpu_generic_cmpxchg_double(pcp1, pcp2, \ - oval1, oval2, nval1, nval2); \ - raw_local_irq_restore(flags); \ - ret__; \ -}) - -#ifndef this_cpu_cmpxchg_double -# ifndef this_cpu_cmpxchg_double_1 -# define this_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef this_cpu_cmpxchg_double_2 -# define this_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef this_cpu_cmpxchg_double_4 -# define this_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef this_cpu_cmpxchg_double_8 -# define this_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) -#endif - -/* - * Generic percpu operations for contexts where we do not want to do - * any checks for preemptiosn. - * - * If there is no other protection through preempt disable and/or - * disabling interupts then one of these RMW operations can show unexpected - * behavior because the execution thread was rescheduled on another processor - * or an interrupt occurred and the same percpu variable was modified from - * the interrupt context. - */ -#ifndef raw_cpu_read -# ifndef raw_cpu_read_1 -# define raw_cpu_read_1(pcp) (*raw_cpu_ptr(&(pcp))) -# endif -# ifndef raw_cpu_read_2 -# define raw_cpu_read_2(pcp) (*raw_cpu_ptr(&(pcp))) -# endif -# ifndef raw_cpu_read_4 -# define raw_cpu_read_4(pcp) (*raw_cpu_ptr(&(pcp))) -# endif -# ifndef raw_cpu_read_8 -# define raw_cpu_read_8(pcp) (*raw_cpu_ptr(&(pcp))) -# endif -# define raw_cpu_read(pcp) __pcpu_size_call_return(raw_cpu_read_, (pcp)) -#endif - -#define raw_cpu_generic_to_op(pcp, val, op) \ -do { \ - *raw_cpu_ptr(&(pcp)) op val; \ -} while (0) - - -#ifndef raw_cpu_write -# ifndef raw_cpu_write_1 -# define raw_cpu_write_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef raw_cpu_write_2 -# define raw_cpu_write_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef raw_cpu_write_4 -# define raw_cpu_write_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) -# endif -# ifndef raw_cpu_write_8 -# define raw_cpu_write_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), =) -# endif -# define raw_cpu_write(pcp, val) __pcpu_size_call(raw_cpu_write_, (pcp), (val)) -#endif - -#ifndef raw_cpu_add -# ifndef raw_cpu_add_1 -# define raw_cpu_add_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef raw_cpu_add_2 -# define raw_cpu_add_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef raw_cpu_add_4 -# define raw_cpu_add_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) -# endif -# ifndef raw_cpu_add_8 -# define raw_cpu_add_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), +=) -# endif -# define raw_cpu_add(pcp, val) __pcpu_size_call(raw_cpu_add_, (pcp), (val)) -#endif - -#ifndef raw_cpu_sub -# define raw_cpu_sub(pcp, val) raw_cpu_add((pcp), -(val)) -#endif - -#ifndef raw_cpu_inc -# define raw_cpu_inc(pcp) raw_cpu_add((pcp), 1) -#endif - -#ifndef raw_cpu_dec -# define raw_cpu_dec(pcp) raw_cpu_sub((pcp), 1) -#endif - -#ifndef raw_cpu_and -# ifndef raw_cpu_and_1 -# define raw_cpu_and_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef raw_cpu_and_2 -# define raw_cpu_and_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef raw_cpu_and_4 -# define raw_cpu_and_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) -# endif -# ifndef raw_cpu_and_8 -# define raw_cpu_and_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), &=) -# endif -# define raw_cpu_and(pcp, val) __pcpu_size_call(raw_cpu_and_, (pcp), (val)) -#endif - -#ifndef raw_cpu_or -# ifndef raw_cpu_or_1 -# define raw_cpu_or_1(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef raw_cpu_or_2 -# define raw_cpu_or_2(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef raw_cpu_or_4 -# define raw_cpu_or_4(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) -# endif -# ifndef raw_cpu_or_8 -# define raw_cpu_or_8(pcp, val) raw_cpu_generic_to_op((pcp), (val), |=) -# endif -# define raw_cpu_or(pcp, val) __pcpu_size_call(raw_cpu_or_, (pcp), (val)) -#endif - -#define raw_cpu_generic_add_return(pcp, val) \ -({ \ - raw_cpu_add(pcp, val); \ - raw_cpu_read(pcp); \ -}) - -#ifndef raw_cpu_add_return -# ifndef raw_cpu_add_return_1 -# define raw_cpu_add_return_1(pcp, val) raw_cpu_generic_add_return(pcp, val) -# endif -# ifndef raw_cpu_add_return_2 -# define raw_cpu_add_return_2(pcp, val) raw_cpu_generic_add_return(pcp, val) -# endif -# ifndef raw_cpu_add_return_4 -# define raw_cpu_add_return_4(pcp, val) raw_cpu_generic_add_return(pcp, val) -# endif -# ifndef raw_cpu_add_return_8 -# define raw_cpu_add_return_8(pcp, val) raw_cpu_generic_add_return(pcp, val) -# endif -# define raw_cpu_add_return(pcp, val) \ - __pcpu_size_call_return2(raw_cpu_add_return_, pcp, val) -#endif - -#define raw_cpu_sub_return(pcp, val) raw_cpu_add_return(pcp, -(typeof(pcp))(val)) -#define raw_cpu_inc_return(pcp) raw_cpu_add_return(pcp, 1) -#define raw_cpu_dec_return(pcp) raw_cpu_add_return(pcp, -1) - -#define raw_cpu_generic_xchg(pcp, nval) \ -({ typeof(pcp) ret__; \ - ret__ = raw_cpu_read(pcp); \ - raw_cpu_write(pcp, nval); \ - ret__; \ -}) - -#ifndef raw_cpu_xchg -# ifndef raw_cpu_xchg_1 -# define raw_cpu_xchg_1(pcp, nval) raw_cpu_generic_xchg(pcp, nval) -# endif -# ifndef raw_cpu_xchg_2 -# define raw_cpu_xchg_2(pcp, nval) raw_cpu_generic_xchg(pcp, nval) -# endif -# ifndef raw_cpu_xchg_4 -# define raw_cpu_xchg_4(pcp, nval) raw_cpu_generic_xchg(pcp, nval) -# endif -# ifndef raw_cpu_xchg_8 -# define raw_cpu_xchg_8(pcp, nval) raw_cpu_generic_xchg(pcp, nval) -# endif -# define raw_cpu_xchg(pcp, nval) \ - __pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval) -#endif - -#define raw_cpu_generic_cmpxchg(pcp, oval, nval) \ -({ \ - typeof(pcp) ret__; \ - ret__ = raw_cpu_read(pcp); \ - if (ret__ == (oval)) \ - raw_cpu_write(pcp, nval); \ - ret__; \ -}) - -#ifndef raw_cpu_cmpxchg -# ifndef raw_cpu_cmpxchg_1 -# define raw_cpu_cmpxchg_1(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef raw_cpu_cmpxchg_2 -# define raw_cpu_cmpxchg_2(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef raw_cpu_cmpxchg_4 -# define raw_cpu_cmpxchg_4(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# ifndef raw_cpu_cmpxchg_8 -# define raw_cpu_cmpxchg_8(pcp, oval, nval) raw_cpu_generic_cmpxchg(pcp, oval, nval) -# endif -# define raw_cpu_cmpxchg(pcp, oval, nval) \ - __pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval) -#endif - -#define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ -({ \ - int __ret = 0; \ - if (raw_cpu_read(pcp1) == (oval1) && \ - raw_cpu_read(pcp2) == (oval2)) { \ - raw_cpu_write(pcp1, (nval1)); \ - raw_cpu_write(pcp2, (nval2)); \ - __ret = 1; \ - } \ - (__ret); \ -}) - -#ifndef raw_cpu_cmpxchg_double -# ifndef raw_cpu_cmpxchg_double_1 -# define raw_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef raw_cpu_cmpxchg_double_2 -# define raw_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef raw_cpu_cmpxchg_double_4 -# define raw_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# ifndef raw_cpu_cmpxchg_double_8 -# define raw_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) -# endif -# define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - __pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2)) -#endif - -/* - * Generic percpu operations for context that are safe from preemption/interrupts. - */ -#ifndef __this_cpu_read -# define __this_cpu_read(pcp) \ - (__this_cpu_preempt_check("read"),__pcpu_size_call_return(raw_cpu_read_, (pcp))) -#endif - -#ifndef __this_cpu_write -# define __this_cpu_write(pcp, val) \ -do { __this_cpu_preempt_check("write"); \ - __pcpu_size_call(raw_cpu_write_, (pcp), (val)); \ -} while (0) -#endif - -#ifndef __this_cpu_add -# define __this_cpu_add(pcp, val) \ -do { __this_cpu_preempt_check("add"); \ - __pcpu_size_call(raw_cpu_add_, (pcp), (val)); \ -} while (0) -#endif - -#ifndef __this_cpu_sub -# define __this_cpu_sub(pcp, val) __this_cpu_add((pcp), -(typeof(pcp))(val)) -#endif - -#ifndef __this_cpu_inc -# define __this_cpu_inc(pcp) __this_cpu_add((pcp), 1) -#endif - -#ifndef __this_cpu_dec -# define __this_cpu_dec(pcp) __this_cpu_sub((pcp), 1) -#endif - -#ifndef __this_cpu_and -# define __this_cpu_and(pcp, val) \ -do { __this_cpu_preempt_check("and"); \ - __pcpu_size_call(raw_cpu_and_, (pcp), (val)); \ -} while (0) - -#endif - -#ifndef __this_cpu_or -# define __this_cpu_or(pcp, val) \ -do { __this_cpu_preempt_check("or"); \ - __pcpu_size_call(raw_cpu_or_, (pcp), (val)); \ -} while (0) -#endif - -#ifndef __this_cpu_add_return -# define __this_cpu_add_return(pcp, val) \ - (__this_cpu_preempt_check("add_return"),__pcpu_size_call_return2(raw_cpu_add_return_, pcp, val)) -#endif - -#define __this_cpu_sub_return(pcp, val) __this_cpu_add_return(pcp, -(typeof(pcp))(val)) -#define __this_cpu_inc_return(pcp) __this_cpu_add_return(pcp, 1) -#define __this_cpu_dec_return(pcp) __this_cpu_add_return(pcp, -1) - -#ifndef __this_cpu_xchg -# define __this_cpu_xchg(pcp, nval) \ - (__this_cpu_preempt_check("xchg"),__pcpu_size_call_return2(raw_cpu_xchg_, (pcp), nval)) -#endif - -#ifndef __this_cpu_cmpxchg -# define __this_cpu_cmpxchg(pcp, oval, nval) \ - (__this_cpu_preempt_check("cmpxchg"),__pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)) -#endif - -#ifndef __this_cpu_cmpxchg_double -# define __this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \ - (__this_cpu_preempt_check("cmpxchg_double"),__pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))) -#endif - #endif /* __LINUX_PERCPU_H */ diff --git a/include/linux/platform_data/ata-samsung_cf.h b/include/linux/platform_data/ata-samsung_cf.h index c2049e3d7444..748e71642c4a 100644 --- a/include/linux/platform_data/ata-samsung_cf.h +++ b/include/linux/platform_data/ata-samsung_cf.h @@ -29,7 +29,6 @@ extern void s3c_ide_set_platdata(struct s3c_ide_platdata *pdata); /* architecture-specific IDE configuration */ extern void s3c64xx_ide_setup_gpio(void); -extern void s5pc100_ide_setup_gpio(void); extern void s5pv210_ide_setup_gpio(void); #endif /*__ATA_SAMSUNG_CF_H */ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 077904c8b70d..cc79eff4a1ad 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -334,6 +334,9 @@ static inline void user_single_step_siginfo(struct task_struct *tsk, * calling arch_ptrace_stop() when it would be superfluous. For example, * if the thread has not been back to user mode since the last stop, the * thread state might indicate that nothing needs to be done. + * + * This is guaranteed to be invoked once before a task stops for ptrace and + * may include arch-specific operations necessary prior to a ptrace stop. */ #define arch_ptrace_stop_needed(code, info) (0) #endif diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5a75d19aa661..6a94cc8b1ca0 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -44,7 +44,6 @@ #include <linux/debugobjects.h> #include <linux/bug.h> #include <linux/compiler.h> -#include <linux/percpu.h> #include <asm/barrier.h> extern int rcu_expedited; /* for sysctl */ @@ -300,41 +299,6 @@ bool __rcu_is_watching(void); #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ /* - * Hooks for cond_resched() and friends to avoid RCU CPU stall warnings. - */ - -#define RCU_COND_RESCHED_LIM 256 /* ms vs. 100s of ms. */ -DECLARE_PER_CPU(int, rcu_cond_resched_count); -void rcu_resched(void); - -/* - * Is it time to report RCU quiescent states? - * - * Note unsynchronized access to rcu_cond_resched_count. Yes, we might - * increment some random CPU's count, and possibly also load the result from - * yet another CPU's count. We might even clobber some other CPU's attempt - * to zero its counter. This is all OK because the goal is not precision, - * but rather reasonable amortization of rcu_note_context_switch() overhead - * and extremely high probability of avoiding RCU CPU stall warnings. - * Note that this function has to be preempted in just the wrong place, - * many thousands of times in a row, for anything bad to happen. - */ -static inline bool rcu_should_resched(void) -{ - return raw_cpu_inc_return(rcu_cond_resched_count) >= - RCU_COND_RESCHED_LIM; -} - -/* - * Report quiscent states to RCU if it is time to do so. - */ -static inline void rcu_cond_resched(void) -{ - if (unlikely(rcu_should_resched())) - rcu_resched(); -} - -/* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ @@ -358,9 +322,19 @@ void wait_rcu_gp(call_rcu_func_t crf); * initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD +void init_rcu_head(struct rcu_head *head); +void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void init_rcu_head(struct rcu_head *head) +{ +} + +static inline void destroy_rcu_head(struct rcu_head *head) +{ +} + static inline void init_rcu_head_on_stack(struct rcu_head *head) { } diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h index d5b13bc07a0b..561e8615528d 100644 --- a/include/linux/rwsem-spinlock.h +++ b/include/linux/rwsem-spinlock.h @@ -15,13 +15,13 @@ #ifdef __KERNEL__ /* * the rw-semaphore definition - * - if activity is 0 then there are no active readers or writers - * - if activity is +ve then that is the number of active readers - * - if activity is -1 then there is one active writer + * - if count is 0 then there are no active readers or writers + * - if count is +ve then that is the number of active readers + * - if count is -1 then there is one active writer * - if wait_list is not empty, then there are processes waiting for the semaphore */ struct rw_semaphore { - __s32 activity; + __s32 count; raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 8d79708146aa..035d3c57fc8a 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -13,10 +13,11 @@ #include <linux/kernel.h> #include <linux/list.h> #include <linux/spinlock.h> - #include <linux/atomic.h> +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +#include <linux/osq_lock.h> +#endif -struct optimistic_spin_queue; struct rw_semaphore; #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK @@ -25,15 +26,15 @@ struct rw_semaphore; /* All arch specific implementations share the same struct */ struct rw_semaphore { long count; - raw_spinlock_t wait_lock; struct list_head wait_list; -#ifdef CONFIG_SMP + raw_spinlock_t wait_lock; +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER + struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; - struct optimistic_spin_queue *osq; /* spinner MCS lock */ #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; @@ -64,22 +65,19 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) # define __RWSEM_DEP_MAP_INIT(lockname) #endif -#if defined(CONFIG_SMP) && !defined(CONFIG_RWSEM_GENERIC_SPINLOCK) -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, \ - __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ - LIST_HEAD_INIT((name).wait_list), \ - NULL, /* owner */ \ - NULL /* mcs lock */ \ - __RWSEM_DEP_MAP_INIT(name) } +#ifdef CONFIG_RWSEM_SPIN_ON_OWNER +#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL #else -#define __RWSEM_INITIALIZER(name) \ - { RWSEM_UNLOCKED_VALUE, \ - __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ - LIST_HEAD_INIT((name).wait_list) \ - __RWSEM_DEP_MAP_INIT(name) } +#define __RWSEM_OPT_INIT(lockname) #endif +#define __RWSEM_INITIALIZER(name) \ + { .count = RWSEM_UNLOCKED_VALUE, \ + .wait_list = LIST_HEAD_INIT((name).wait_list), \ + .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock) \ + __RWSEM_OPT_INIT(name) \ + __RWSEM_DEP_MAP_INIT(name) } + #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) diff --git a/include/linux/sched.h b/include/linux/sched.h index 306f4f0c987a..0376b054a0d0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -872,21 +872,21 @@ enum cpu_idle_type { #define SD_NUMA 0x4000 /* cross-node balancing */ #ifdef CONFIG_SCHED_SMT -static inline const int cpu_smt_flags(void) +static inline int cpu_smt_flags(void) { return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES; } #endif #ifdef CONFIG_SCHED_MC -static inline const int cpu_core_flags(void) +static inline int cpu_core_flags(void) { return SD_SHARE_PKG_RESOURCES; } #endif #ifdef CONFIG_NUMA -static inline const int cpu_numa_flags(void) +static inline int cpu_numa_flags(void) { return SD_NUMA; } @@ -999,7 +999,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); -typedef const int (*sched_domain_flags_f)(void); +typedef int (*sched_domain_flags_f)(void); #define SDTL_OVERLAP 0x01 diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index 1a64b26046ed..9b7de1b46437 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -70,7 +70,9 @@ US_FLAG(NEEDS_CAP16, 0x00400000) \ /* cannot handle READ_CAPACITY_10 */ \ US_FLAG(IGNORE_UAS, 0x00800000) \ - /* Device advertises UAS but it is broken */ + /* Device advertises UAS but it is broken */ \ + US_FLAG(BROKEN_FUA, 0x01000000) \ + /* Cannot handle FUA in WRITE or READ CDBs */ \ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; |
