diff options
Diffstat (limited to 'include')
91 files changed, 1339 insertions, 588 deletions
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..d4cd4cc4389c 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -33,8 +33,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** - * queued_read_trylock - try to acquire read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_trylock - try to acquire read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) @@ -52,8 +52,8 @@ static inline int queued_read_trylock(struct qrwlock *lock) } /** - * queued_write_trylock - try to acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_trylock - try to acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) @@ -68,8 +68,8 @@ static inline int queued_write_trylock(struct qrwlock *lock) _QW_LOCKED)); } /** - * queued_read_lock - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { @@ -84,8 +84,8 @@ static inline void queued_read_lock(struct qrwlock *lock) } /** - * queued_write_lock - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { @@ -98,8 +98,8 @@ static inline void queued_write_lock(struct qrwlock *lock) } /** - * queued_read_unlock - release read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_unlock - release read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { @@ -110,8 +110,8 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** - * queued_write_unlock - release write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_unlock - release write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { @@ -120,7 +120,7 @@ static inline void queued_write_unlock(struct qrwlock *lock) /** * queued_rwlock_is_contended - check if the lock is contended - * @lock : Pointer to queue rwlock structure + * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) @@ -130,7 +130,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock) /* * Remapping rwlock architecture specific functions to the corresponding - * queue rwlock functions. + * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index c36f1d5a2572..12392c14c4d0 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -7,7 +7,7 @@ #include <asm/spinlock_types.h> /* - * The queue read/write lock data structure + * The queued read/write lock data structure */ typedef struct qrwlock { diff --git a/include/clocksource/timer-goldfish.h b/include/clocksource/timer-goldfish.h new file mode 100644 index 000000000000..05a3a4f610d6 --- /dev/null +++ b/include/clocksource/timer-goldfish.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * goldfish-timer clocksource + * Registers definition for the goldfish-timer device + */ + +#ifndef _CLOCKSOURCE_TIMER_GOLDFISH_H +#define _CLOCKSOURCE_TIMER_GOLDFISH_H + +/* + * TIMER_TIME_LOW get low bits of current time and update TIMER_TIME_HIGH + * TIMER_TIME_HIGH get high bits of time at last TIMER_TIME_LOW read + * TIMER_ALARM_LOW set low bits of alarm and activate it + * TIMER_ALARM_HIGH set high bits of next alarm + * TIMER_IRQ_ENABLED enable alarm interrupt + * TIMER_CLEAR_ALARM disarm an existing alarm + * TIMER_ALARM_STATUS alarm status (running or not) + * TIMER_CLEAR_INTERRUPT clear interrupt + */ +#define TIMER_TIME_LOW 0x00 +#define TIMER_TIME_HIGH 0x04 +#define TIMER_ALARM_LOW 0x08 +#define TIMER_ALARM_HIGH 0x0c +#define TIMER_IRQ_ENABLED 0x10 +#define TIMER_CLEAR_ALARM 0x14 +#define TIMER_ALARM_STATUS 0x18 +#define TIMER_CLEAR_INTERRUPT 0x1c + +extern int goldfish_timer_init(int irq, void __iomem *base); + +#endif /* _CLOCKSOURCE_TIMER_GOLDFISH_H */ diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h index 6db58d180866..77bc5522e61c 100644 --- a/include/linux/atomic/atomic-arch-fallback.h +++ b/include/linux/atomic/atomic-arch-fallback.h @@ -147,6 +147,76 @@ #endif /* arch_try_cmpxchg_relaxed */ +#ifndef arch_try_cmpxchg64_relaxed +#ifdef arch_try_cmpxchg64 +#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64 +#define arch_try_cmpxchg64_release arch_try_cmpxchg64 +#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64 +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64 */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_acquire */ + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_release */ + +#ifndef arch_try_cmpxchg64_relaxed +#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \ +({ \ + typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \ + ___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \ + if (unlikely(___r != ___o)) \ + *___op = ___r; \ + likely(___r == ___o); \ +}) +#endif /* arch_try_cmpxchg64_relaxed */ + +#else /* arch_try_cmpxchg64_relaxed */ + +#ifndef arch_try_cmpxchg64_acquire +#define arch_try_cmpxchg64_acquire(...) \ + __atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64_release +#define arch_try_cmpxchg64_release(...) \ + __atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#ifndef arch_try_cmpxchg64 +#define arch_try_cmpxchg64(...) \ + __atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__) +#endif + +#endif /* arch_try_cmpxchg64_relaxed */ + #ifndef arch_atomic_read_acquire static __always_inline int arch_atomic_read_acquire(const atomic_t *v) @@ -2386,4 +2456,4 @@ arch_atomic64_dec_if_positive(atomic64_t *v) #endif #endif /* _LINUX_ATOMIC_FALLBACK_H */ -// 8e2cc06bc0d2c0967d2f8424762bd48555ee40ae +// b5e87bdd5ede61470c29f7a7e4de781af3770f09 diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 5d69b143c28e..7a139ec030b0 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -2006,6 +2006,44 @@ atomic_long_dec_if_positive(atomic_long_t *v) arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ }) +#define try_cmpxchg64(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_acquire(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_release(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + +#define try_cmpxchg64_relaxed(ptr, oldp, ...) \ +({ \ + typeof(ptr) __ai_ptr = (ptr); \ + typeof(oldp) __ai_oldp = (oldp); \ + instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ + instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ + arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \ +}) + #define cmpxchg_local(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ @@ -2045,4 +2083,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 87c974b93032afd42143613434d1a7788fa598f9 +// 764f741eb77a7ad565dc8d99ce2837d5542e8aee diff --git a/include/linux/audit.h b/include/linux/audit.h index d06134ac6245..cece70231138 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -339,7 +339,7 @@ static inline void audit_uring_entry(u8 op) } static inline void audit_uring_exit(int success, long code) { - if (unlikely(!audit_dummy_context())) + if (unlikely(audit_context())) __audit_uring_exit(success, code); } static inline void audit_syscall_entry(int major, unsigned long a0, diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 87ce24d238f3..2bd073fa6bb5 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -17,8 +17,6 @@ #include <linux/backing-dev-defs.h> #include <linux/slab.h> -struct blkcg; - static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); @@ -154,7 +152,7 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); -void wb_blkcg_offline(struct blkcg *blkcg); +void wb_blkcg_offline(struct cgroup_subsys_state *css); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode @@ -378,7 +376,7 @@ static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } -static inline void wb_blkcg_offline(struct blkcg *blkcg) +static inline void wb_blkcg_offline(struct cgroup_subsys_state *css) { } diff --git a/include/linux/bio.h b/include/linux/bio.h index 278cc81cc1e7..1cf3738ef1ea 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -269,6 +269,7 @@ struct folio_iter { size_t offset; size_t length; /* private: for use by the iterator */ + struct folio *_next; size_t _seg_count; int _i; }; @@ -283,6 +284,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, PAGE_SIZE * (bvec->bv_page - &fi->folio->page); fi->_seg_count = bvec->bv_len; fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_next = folio_next(fi->folio); fi->_i = i; } @@ -290,9 +292,10 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) { fi->_seg_count -= fi->length; if (fi->_seg_count) { - fi->folio = folio_next(fi->folio); + fi->folio = fi->_next; fi->offset = 0; fi->length = min(folio_size(fi->folio), fi->_seg_count); + fi->_next = folio_next(fi->folio); } else if (fi->_i + 1 < bio->bi_vcnt) { bio_first_folio(fi, bio, fi->_i + 1); } else { @@ -405,9 +408,7 @@ extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, unsigned int opf, gfp_t gfp_mask, struct bio_set *bs); -struct bio *bio_alloc_kiocb(struct kiocb *kiocb, struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, struct bio_set *bs); -struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned short nr_iovecs); +struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask); extern void bio_put(struct bio *); struct bio *bio_alloc_clone(struct block_device *bdev, struct bio *bio_src, @@ -782,6 +783,12 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } +static inline void bio_clear_polled(struct bio *bio) +{ + /* can't support alloc cache if we turn off polling */ + bio->bi_opf &= ~(REQ_POLLED | REQ_ALLOC_CACHE); +} + struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, unsigned int nr_pages, unsigned int opf, gfp_t gfp); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 652cd05b0924..9f40dbc65f82 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -14,265 +14,39 @@ * Nauman Rafique <nauman@google.com> */ -#include <linux/cgroup.h> -#include <linux/percpu.h> -#include <linux/percpu_counter.h> -#include <linux/u64_stats_sync.h> -#include <linux/seq_file.h> -#include <linux/radix-tree.h> -#include <linux/blkdev.h> -#include <linux/atomic.h> -#include <linux/kthread.h> -#include <linux/fs.h> +#include <linux/types.h> + +struct bio; +struct cgroup_subsys_state; +struct request_queue; #define FC_APPID_LEN 129 #ifdef CONFIG_BLK_CGROUP - -enum blkg_iostat_type { - BLKG_IOSTAT_READ, - BLKG_IOSTAT_WRITE, - BLKG_IOSTAT_DISCARD, - - BLKG_IOSTAT_NR, -}; - -struct blkcg_gq; -struct blkg_policy_data; - -struct blkcg { - struct cgroup_subsys_state css; - spinlock_t lock; - refcount_t online_pin; - - struct radix_tree_root blkg_tree; - struct blkcg_gq __rcu *blkg_hint; - struct hlist_head blkg_list; - - struct blkcg_policy_data *cpd[BLKCG_MAX_POLS]; - - struct list_head all_blkcgs_node; -#ifdef CONFIG_BLK_CGROUP_FC_APPID - char fc_app_id[FC_APPID_LEN]; -#endif -#ifdef CONFIG_CGROUP_WRITEBACK - struct list_head cgwb_list; -#endif -}; - -struct blkg_iostat { - u64 bytes[BLKG_IOSTAT_NR]; - u64 ios[BLKG_IOSTAT_NR]; -}; - -struct blkg_iostat_set { - struct u64_stats_sync sync; - struct blkg_iostat cur; - struct blkg_iostat last; -}; - -/* association between a blk cgroup and a request queue */ -struct blkcg_gq { - /* Pointer to the associated request_queue */ - struct request_queue *q; - struct list_head q_node; - struct hlist_node blkcg_node; - struct blkcg *blkcg; - - /* all non-root blkcg_gq's are guaranteed to have access to parent */ - struct blkcg_gq *parent; - - /* reference count */ - struct percpu_ref refcnt; - - /* is this blkg online? protected by both blkcg and q locks */ - bool online; - - struct blkg_iostat_set __percpu *iostat_cpu; - struct blkg_iostat_set iostat; - - struct blkg_policy_data *pd[BLKCG_MAX_POLS]; - - spinlock_t async_bio_lock; - struct bio_list async_bios; - union { - struct work_struct async_bio_work; - struct work_struct free_work; - }; - - atomic_t use_delay; - atomic64_t delay_nsec; - atomic64_t delay_start; - u64 last_delay; - int last_use; - - struct rcu_head rcu_head; -}; - extern struct cgroup_subsys_state * const blkcg_root_css; -void blkcg_destroy_blkgs(struct blkcg *blkcg); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); - -static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct blkcg, css) : NULL; -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, %NULL if not associated. - * Callers are expected to either handle %NULL or know association has been - * done prior to calling this. - */ -static inline struct blkcg *bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; -} - -static inline bool blk_cgroup_congested(void) -{ - struct cgroup_subsys_state *css; - bool ret = false; - - rcu_read_lock(); - css = kthread_blkcg(); - if (!css) - css = task_css(current, io_cgrp_id); - while (css) { - if (atomic_read(&css->cgroup->congestion_count)) { - ret = true; - break; - } - css = css->parent; - } - rcu_read_unlock(); - return ret; -} - -/** - * blkcg_parent - get the parent of a blkcg - * @blkcg: blkcg of interest - * - * Return the parent blkcg of @blkcg. Can be called anytime. - */ -static inline struct blkcg *blkcg_parent(struct blkcg *blkcg) -{ - return css_to_blkcg(blkcg->css.parent); -} - -/** - * blkcg_pin_online - pin online state - * @blkcg: blkcg of interest - * - * While pinned, a blkcg is kept online. This is primarily used to - * impedance-match blkg and cgwb lifetimes so that blkg doesn't go offline - * while an associated cgwb is still active. - */ -static inline void blkcg_pin_online(struct blkcg *blkcg) -{ - refcount_inc(&blkcg->online_pin); -} - -/** - * blkcg_unpin_online - unpin online state - * @blkcg: blkcg of interest - * - * This is primarily used to impedance-match blkg and cgwb lifetimes so - * that blkg doesn't go offline while an associated cgwb is still active. - * When this count goes to zero, all active cgwbs have finished so the - * blkcg can continue destruction by calling blkcg_destroy_blkgs(). - */ -static inline void blkcg_unpin_online(struct blkcg *blkcg) -{ - do { - if (!refcount_dec_and_test(&blkcg->online_pin)) - break; - blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); - } while (blkcg); -} +bool blk_cgroup_congested(void); +void blkcg_pin_online(struct cgroup_subsys_state *blkcg_css); +void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css); +struct list_head *blkcg_get_cgwb_list(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio); #else /* CONFIG_BLK_CGROUP */ -struct blkcg { -}; - -struct blkcg_gq { -}; - #define blkcg_root_css ((struct cgroup_subsys_state *)ERR_PTR(-EINVAL)) static inline void blkcg_maybe_throttle_current(void) { } static inline bool blk_cgroup_congested(void) { return false; } - -#ifdef CONFIG_BLOCK static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { } -static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } -#endif /* CONFIG_BLOCK */ - -#endif /* CONFIG_BLK_CGROUP */ - -#ifdef CONFIG_BLK_CGROUP_FC_APPID -/* - * Sets the fc_app_id field associted to blkcg - * @app_id: application identifier - * @cgrp_id: cgroup id - * @app_id_len: size of application identifier - */ -static inline int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len) -{ - struct cgroup *cgrp; - struct cgroup_subsys_state *css; - struct blkcg *blkcg; - int ret = 0; - - if (app_id_len > FC_APPID_LEN) - return -EINVAL; - - cgrp = cgroup_get_from_id(cgrp_id); - if (!cgrp) - return -ENOENT; - css = cgroup_get_e_css(cgrp, &io_cgrp_subsys); - if (!css) { - ret = -ENOENT; - goto out_cgrp_put; - } - blkcg = css_to_blkcg(css); - /* - * There is a slight race condition on setting the appid. - * Worst case an I/O may not find the right id. - * This is no different from the I/O we let pass while obtaining - * the vmid from the fabric. - * Adding the overhead of a lock is not necessary. - */ - strlcpy(blkcg->fc_app_id, app_id, app_id_len); - css_put(css); -out_cgrp_put: - cgroup_put(cgrp); - return ret; -} - -/** - * blkcg_get_fc_appid - get the fc app identifier associated with a bio - * @bio: target bio - * - * On success return the fc_app_id, on failure return NULL - */ -static inline char *blkcg_get_fc_appid(struct bio *bio) +static inline struct cgroup_subsys_state *bio_blkcg_css(struct bio *bio) { - if (bio && bio->bi_blkg && - (bio->bi_blkg->blkcg->fc_app_id[0] != '\0')) - return bio->bi_blkg->blkcg->fc_app_id; return NULL; } -#else -static inline int blkcg_set_fc_appid(char *buf, u64 id, size_t len) { return -EINVAL; } -static inline char *blkcg_get_fc_appid(struct bio *bio) { return NULL; } -#endif /*CONFIG_BLK_CGROUP_FC_APPID*/ +#endif /* CONFIG_BLK_CGROUP */ + +int blkcg_set_fc_appid(char *app_id, u64 cgrp_id, size_t app_id_len); +char *blkcg_get_fc_appid(struct bio *bio); + #endif /* _BLK_CGROUP_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 7aa5c54901a9..9f07061418db 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -163,7 +163,6 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; - int error_count; /* for legacy drivers, don't use */ }; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1973ef9bd40f..c007d58d2703 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -44,7 +44,7 @@ struct block_device { unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ dev_t bd_dev; - int bd_openers; + atomic_t bd_openers; struct inode * bd_inode; /* will die */ struct super_block * bd_super; void * bd_claiming; @@ -246,9 +246,8 @@ typedef unsigned int blk_qc_t; struct bio { struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; - unsigned int bi_opf; /* bottom bits req flags, - * top bits REQ_OP. Use - * accessors. + unsigned int bi_opf; /* bottom bits REQ_OP, top bits + * req_flags. */ unsigned short bi_flags; /* BIO_* below */ unsigned short bi_ioprio; @@ -329,7 +328,6 @@ enum { BIO_QOS_MERGED, /* but went through rq_qos merge path */ BIO_REMAPPED, BIO_ZONE_WRITE_LOCKED, /* Owns a zoned device zone write lock */ - BIO_PERCPU_CACHE, /* can participate in per-cpu alloc cache */ BIO_FLAG_LAST }; @@ -409,15 +407,17 @@ enum req_flag_bits { * work item to avoid such priority inversions. */ __REQ_CGROUP_PUNT, + __REQ_POLLED, /* caller polls for completion using bio_poll */ + __REQ_ALLOC_CACHE, /* allocate IO from cache if available */ + __REQ_SWAP, /* swap I/O */ + __REQ_DRV, /* for driver use */ - /* command specific flags for REQ_OP_WRITE_ZEROES: */ + /* + * Command specific flags, keep last: + */ + /* for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using bio_poll */ - - /* for driver use */ - __REQ_DRV, - __REQ_SWAP, /* swapping request. */ __REQ_NR_BITS, /* stops here */ }; @@ -439,6 +439,7 @@ enum req_flag_bits { #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) #define REQ_POLLED (1ULL << __REQ_POLLED) +#define REQ_ALLOC_CACHE (1ULL << __REQ_ALLOC_CACHE) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d016138997..5bdf2ac9142c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -176,6 +176,21 @@ static inline bool disk_live(struct gendisk *disk) return !inode_unhashed(disk->part0->bd_inode); } +/** + * disk_openers - returns how many openers are there for a disk + * @disk: disk to check + * + * This returns the number of openers for a disk. Note that this value is only + * stable if disk->open_mutex is held. + * + * Note: Due to a quirk in the block layer open code, each open partition is + * only counted once even if there are multiple openers. + */ +static inline unsigned int disk_openers(struct gendisk *disk) +{ + return atomic_read(&disk->part0->bd_openers); +} + /* * The gendisk is refcounted by the part0 block_device, and the bd_device * therein is also used for device model presentation in sysfs. @@ -248,6 +263,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; unsigned int discard_granularity; @@ -540,10 +556,8 @@ struct request_queue { #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ @@ -582,11 +596,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) -#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) -#define blk_queue_secure_erase(q) \ - (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) @@ -602,7 +613,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) -#define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) #define blk_queue_nowait(q) test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags) @@ -950,6 +960,8 @@ extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); +void blk_queue_max_secure_erase_sectors(struct request_queue *q, + unsigned int max_sectors); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); @@ -1090,13 +1102,12 @@ static inline long nr_blockdev_pages(void) extern void blk_io_schedule(void); -#define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ - -extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); -extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, int flags, - struct bio **biop); +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask); +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct bio **biop); +int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ @@ -1115,7 +1126,7 @@ static inline int sb_issue_discard(struct super_block *sb, sector_t block, SECTOR_SHIFT), nr_blocks << (sb->s_blocksize_bits - SECTOR_SHIFT), - gfp_mask, flags); + gfp_mask); } static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask) @@ -1189,6 +1200,12 @@ static inline unsigned int queue_max_zone_append_sectors(const struct request_qu return min(l->max_zone_append_sectors, l->max_sectors); } +static inline unsigned int +bdev_max_zone_append_sectors(struct block_device *bdev) +{ + return queue_max_zone_append_sectors(bdev_get_queue(bdev)); +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1246,84 +1263,54 @@ bdev_zone_write_granularity(struct block_device *bdev) return queue_zone_write_granularity(bdev_get_queue(bdev)); } -static inline int queue_alignment_offset(const struct request_queue *q) -{ - if (q->limits.misaligned) - return -1; +int bdev_alignment_offset(struct block_device *bdev); +unsigned int bdev_discard_alignment(struct block_device *bdev); - return q->limits.alignment_offset; +static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_discard_sectors; } -static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +static inline unsigned int bdev_discard_granularity(struct block_device *bdev) { - unsigned int granularity = max(lim->physical_block_size, lim->io_min); - unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) - << SECTOR_SHIFT; + return bdev_get_queue(bdev)->limits.discard_granularity; +} - return (granularity + lim->alignment_offset - alignment) % granularity; +static inline unsigned int +bdev_max_secure_erase_sectors(struct block_device *bdev) +{ + return bdev_get_queue(bdev)->limits.max_secure_erase_sectors; } -static inline int bdev_alignment_offset(struct block_device *bdev) +static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); - if (q->limits.misaligned) - return -1; - if (bdev_is_partition(bdev)) - return queue_limit_alignment_offset(&q->limits, - bdev->bd_start_sect); - return q->limits.alignment_offset; + if (q) + return q->limits.max_write_zeroes_sectors; + + return 0; } -static inline int queue_discard_alignment(const struct request_queue *q) +static inline bool bdev_nonrot(struct block_device *bdev) { - if (q->limits.discard_misaligned) - return -1; - - return q->limits.discard_alignment; + return blk_queue_nonrot(bdev_get_queue(bdev)); } -static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +static inline bool bdev_stable_writes(struct block_device *bdev) { - unsigned int alignment, granularity, offset; - - if (!lim->max_discard_sectors) - return 0; - - /* Why are these in bytes, not sectors? */ - alignment = lim->discard_alignment >> SECTOR_SHIFT; - granularity = lim->discard_granularity >> SECTOR_SHIFT; - if (!granularity) - return 0; - - /* Offset of the partition start in 'granularity' sectors */ - offset = sector_div(sector, granularity); - - /* And why do we do this modulus *again* in blkdev_issue_discard()? */ - offset = (granularity + alignment - offset) % granularity; - - /* Turn it back into bytes, gaah */ - return offset << SECTOR_SHIFT; + return test_bit(QUEUE_FLAG_STABLE_WRITES, + &bdev_get_queue(bdev)->queue_flags); } -static inline int bdev_discard_alignment(struct block_device *bdev) +static inline bool bdev_write_cache(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (bdev_is_partition(bdev)) - return queue_limit_discard_alignment(&q->limits, - bdev->bd_start_sect); - return q->limits.discard_alignment; + return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags); } -static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) +static inline bool bdev_fua(struct block_device *bdev) { - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return q->limits.max_write_zeroes_sectors; - - return 0; + return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags); } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) @@ -1491,9 +1478,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, - unsigned int op); -void disk_end_io_acct(struct gendisk *disk, unsigned int op, +unsigned long bdev_start_io_acct(struct block_device *bdev, + unsigned int sectors, unsigned int op, + unsigned long start_time); +void bdev_end_io_acct(struct block_device *bdev, unsigned int op, unsigned long start_time); void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 22501a293fa5..623e22492afa 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -27,12 +27,10 @@ struct blk_trace { atomic_t dropped; }; -struct blkcg; - extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *); extern void blk_trace_shutdown(struct request_queue *); -extern __printf(3, 4) -void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...); +__printf(3, 4) void __blk_trace_note_message(struct blk_trace *bt, + struct cgroup_subsys_state *css, const char *fmt, ...); /** * blk_add_trace_msg - Add a (simple) message to the blktrace stream @@ -47,14 +45,14 @@ void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *f * NOTE: Can not use 'static inline' due to presence of var args... * **/ -#define blk_add_cgroup_trace_msg(q, cg, fmt, ...) \ +#define blk_add_cgroup_trace_msg(q, css, fmt, ...) \ do { \ struct blk_trace *bt; \ \ rcu_read_lock(); \ bt = rcu_dereference((q)->blk_trace); \ if (unlikely(bt)) \ - __trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\ + __blk_trace_note_message(bt, css, fmt, ##__VA_ARGS__);\ rcu_read_unlock(); \ } while (0) #define blk_add_trace_msg(q, fmt, ...) \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bdb5298735ce..ecc3d3ec41cf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2085,6 +2085,8 @@ void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); +void unpriv_ebpf_notify(int new_state); + #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index efd8205282da..cb0d6cd1c12f 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -72,6 +72,24 @@ enum cc_attr { * Examples include TDX guest & SEV. */ CC_ATTR_GUEST_UNROLL_STRING_IO, + + /** + * @CC_ATTR_SEV_SNP: Guest SNP is active. + * + * The platform/OS is running as a guest/virtual machine and actively + * using AMD SEV-SNP features. + */ + CC_ATTR_GUEST_SEV_SNP, + + /** + * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled. + * + * The platform/OS is running as a guest/virtual machine does not + * support CPU hotplug feature. + * + * Examples include TDX Guest. + */ + CC_ATTR_HOTPLUG_DISABLED, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 0a89f111e00e..67caa909e3e6 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -77,7 +77,6 @@ struct cdrom_device_ops { int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); - int (*select_disc) (struct cdrom_device_info *, int); int (*get_last_session) (struct cdrom_device_info *, struct cdrom_multisession *); int (*get_mcn) (struct cdrom_device_info *, diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3431011f364d..cba8a6ffc329 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -287,6 +287,9 @@ struct ceph_osd_linger_request { rados_watcherrcb_t errcb; void *data; + struct ceph_pagelist *request_pl; + struct page **notify_id_pages; + struct page ***preply_pages; size_t *preply_len; }; diff --git a/include/linux/compat.h b/include/linux/compat.h index 1c758b0e0359..01fddf72a81f 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -235,6 +235,7 @@ typedef struct compat_siginfo { struct { compat_ulong_t _data; u32 _type; + u32 _flags; } _perf; }; } _sigfault; diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 219aa5ddbc73..01ce94b58b42 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -109,7 +109,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #endif /* Unreachable code */ -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros @@ -128,10 +128,10 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") -#else +#else /* !CONFIG_OBJTOOL */ #define annotate_unreachable() #define __annotate_jump_table -#endif +#endif /* CONFIG_OBJTOOL */ #ifndef unreachable # define unreachable() do { \ diff --git a/include/linux/cper.h b/include/linux/cper.h index 6a511a1078ca..eacb7dd7b3af 100644 --- a/include/linux/cper.h +++ b/include/linux/cper.h @@ -558,6 +558,7 @@ extern const char *const cper_proc_error_type_strs[4]; u64 cper_next_record_id(void); const char *cper_severity_str(unsigned int); const char *cper_mem_err_type_str(unsigned int); +const char *cper_mem_err_status_str(u64 status); void cper_print_bits(const char *prefix, unsigned int bits, const char * const strs[], unsigned int strs_size); void cper_mem_err_pack(const struct cper_sec_mem_err *, @@ -568,5 +569,7 @@ void cper_print_proc_arm(const char *pfx, const struct cper_sec_proc_arm *proc); void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc); +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg); +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg); #endif diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35c7d6db4139..d5595d57f4e5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1199,7 +1199,6 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy, struct cpufreq_governor *old_gov) { } #endif -extern void arch_freq_prepare_all(void); extern unsigned int arch_freq_get_on_cpu(int cpu); #ifndef arch_set_freq_scale diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 82e33137f917..b66c5f389159 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -222,6 +222,7 @@ enum cpuhp_state { CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, CPUHP_AP_PERF_ARM_CCN_ONLINE, + CPUHP_AP_PERF_ARM_HISI_CPA_ONLINE, CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE, CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE, CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, diff --git a/include/linux/efi.h b/include/linux/efi.h index ccd4d3f91c98..db424f3dc3f2 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -213,6 +213,8 @@ struct capsule_info { size_t page_bytes_remain; }; +int efi_capsule_setup_info(struct capsule_info *cap_info, void *kbuff, + size_t hdr_bytes); int __efi_capsule_setup_info(struct capsule_info *cap_info); /* @@ -383,6 +385,7 @@ void efi_native_runtime_setup(void); #define EFI_LOAD_FILE_PROTOCOL_GUID EFI_GUID(0x56ec3091, 0x954c, 0x11d2, 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b) #define EFI_LOAD_FILE2_PROTOCOL_GUID EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e, 0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d) #define EFI_RT_PROPERTIES_TABLE_GUID EFI_GUID(0xeb66918a, 0x7eef, 0x402a, 0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9) +#define EFI_DXE_SERVICES_TABLE_GUID EFI_GUID(0x05ad34ba, 0x6f02, 0x4214, 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9) #define EFI_IMAGE_SECURITY_DATABASE_GUID EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596, 0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f) #define EFI_SHIM_LOCK_GUID EFI_GUID(0x605dab50, 0xe046, 0x4300, 0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23) @@ -390,6 +393,7 @@ void efi_native_runtime_setup(void); #define EFI_CERT_SHA256_GUID EFI_GUID(0xc1c41626, 0x504c, 0x4092, 0xac, 0xa9, 0x41, 0xf9, 0x36, 0x93, 0x43, 0x28) #define EFI_CERT_X509_GUID EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72) #define EFI_CERT_X509_SHA256_GUID EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed) +#define EFI_CC_BLOB_GUID EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42) /* * This GUID is used to pass to the kernel proper the struct screen_info @@ -405,6 +409,20 @@ void efi_native_runtime_setup(void); #define LINUX_EFI_MEMRESERVE_TABLE_GUID EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5, 0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2) #define LINUX_EFI_INITRD_MEDIA_GUID EFI_GUID(0x5568e427, 0x68fc, 0x4f3d, 0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68) #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID EFI_GUID(0xc451ed2b, 0x9694, 0x45d3, 0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89) +#define LINUX_EFI_COCO_SECRET_AREA_GUID EFI_GUID(0xadf956ad, 0xe98c, 0x484c, 0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47) + +#define RISCV_EFI_BOOT_PROTOCOL_GUID EFI_GUID(0xccd15fec, 0x6f73, 0x4eec, 0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf) + +/* + * This GUID may be installed onto the kernel image's handle as a NULL protocol + * to signal to the stub that the placement of the image should be respected, + * and moving the image in physical memory is undesirable. To ensure + * compatibility with 64k pages kernels with virtually mapped stacks, and to + * avoid defeating physical randomization, this protocol should only be + * installed if the image was placed at a randomized 128k aligned address in + * memory. + */ +#define LINUX_EFI_LOADED_IMAGE_FIXED_GUID EFI_GUID(0xf5a37b6d, 0x3344, 0x42a5, 0xb6, 0xbb, 0x97, 0x86, 0x48, 0xc1, 0x89, 0x0a) /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) @@ -435,6 +453,7 @@ typedef struct { } efi_config_table_type_t; #define EFI_SYSTEM_TABLE_SIGNATURE ((u64)0x5453595320494249ULL) +#define EFI_DXE_SERVICES_TABLE_SIGNATURE ((u64)0x565245535f455844ULL) #define EFI_2_30_SYSTEM_TABLE_REVISION ((2 << 16) | (30)) #define EFI_2_20_SYSTEM_TABLE_REVISION ((2 << 16) | (20)) @@ -596,6 +615,7 @@ extern struct efi { unsigned long tpm_log; /* TPM2 Event Log table */ unsigned long tpm_final_log; /* TPM2 Final Events Log table */ unsigned long mokvar_table; /* MOK variable config table */ + unsigned long coco_secret; /* Confidential computing secret table */ efi_get_time_t *get_time; efi_set_time_t *set_time; @@ -1335,4 +1355,12 @@ extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } #endif +struct linux_efi_coco_secret_area { + u64 base_pa; + u64 size; +}; + +/* Header of a populated EFI secret area */ +#define EFI_SECRET_TABLE_HEADER_GUID EFI_GUID(0x1e74f542, 0x71dd, 0x4d66, 0x96, 0x3e, 0xef, 0x42, 0x87, 0xff, 0x17, 0x3b) + #endif /* _LINUX_EFI_H */ diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index f8e206e82476..346a8b56cdc8 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -84,15 +84,6 @@ static inline void elf_core_copy_regs(elf_gregset_t *elfregs, struct pt_regs *re #endif } -static inline void elf_core_copy_kernel_regs(elf_gregset_t *elfregs, struct pt_regs *regs) -{ -#ifdef ELF_CORE_COPY_KERNEL_REGS - ELF_CORE_COPY_KERNEL_REGS((*elfregs), regs); -#else - elf_core_copy_regs(elfregs, regs); -#endif -} - static inline int elf_core_copy_task_regs(struct task_struct *t, elf_gregset_t* elfregs) { #if defined (ELF_CORE_COPY_TASK_REGS) diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index ab78bd4c2eb0..c92ac75d6556 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -63,7 +63,7 @@ ARCH_EXIT_TO_USER_MODE_WORK) /** - * arch_check_user_regs - Architecture specific sanity check for user mode regs + * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs * @regs: Pointer to currents pt_regs * * Defaults to an empty implementation. Can be replaced by architecture @@ -73,10 +73,10 @@ * section. Use __always_inline so the compiler cannot push it out of line * and make it instrumentable. */ -static __always_inline void arch_check_user_regs(struct pt_regs *regs); +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs); -#ifndef arch_check_user_regs -static __always_inline void arch_check_user_regs(struct pt_regs *regs) {} +#ifndef arch_enter_from_user_mode +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {} #endif /** diff --git a/include/linux/fs.h b/include/linux/fs.h index bbde95387a23..87b5af1d9fbe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1953,6 +1953,7 @@ struct dir_context { #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; +struct io_uring_cmd; struct file_operations { struct module *owner; @@ -1995,6 +1996,7 @@ struct file_operations { struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); + int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags); } __randomize_layout; struct inode_operations { diff --git a/include/linux/goldfish.h b/include/linux/goldfish.h index 12be1601fd84..bcc17f95b906 100644 --- a/include/linux/goldfish.h +++ b/include/linux/goldfish.h @@ -8,14 +8,21 @@ /* Helpers for Goldfish virtual platform */ +#ifndef gf_ioread32 +#define gf_ioread32 ioread32 +#endif +#ifndef gf_iowrite32 +#define gf_iowrite32 iowrite32 +#endif + static inline void gf_write_ptr(const void *ptr, void __iomem *portl, void __iomem *porth) { const unsigned long addr = (unsigned long)ptr; - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } @@ -23,9 +30,9 @@ static inline void gf_write_dma_addr(const dma_addr_t addr, void __iomem *portl, void __iomem *porth) { - __raw_writel(lower_32_bits(addr), portl); + gf_iowrite32(lower_32_bits(addr), portl); #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - __raw_writel(upper_32_bits(addr), porth); + gf_iowrite32(upper_32_bits(addr), porth); #endif } diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 874aabd270c9..cb689264f3e9 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -588,6 +588,22 @@ void gpiochip_relres_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_disable_irq(struct gpio_chip *gc, unsigned int offset); void gpiochip_enable_irq(struct gpio_chip *gc, unsigned int offset); +/* irq_data versions of the above */ +int gpiochip_irq_reqres(struct irq_data *data); +void gpiochip_irq_relres(struct irq_data *data); + +/* Paste this in your irq_chip structure */ +#define GPIOCHIP_IRQ_RESOURCE_HELPERS \ + .irq_request_resources = gpiochip_irq_reqres, \ + .irq_release_resources = gpiochip_irq_relres + +static inline void gpio_irq_chip_set_chip(struct gpio_irq_chip *girq, + const struct irq_chip *chip) +{ + /* Yes, dropping const is ugly, but it isn't like we have a choice */ + girq->chip = (struct irq_chip *)chip; +} + /* Line status inquiry for drivers */ bool gpiochip_line_is_open_drain(struct gpio_chip *gc, unsigned int offset); bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset); diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index 24359b4a9605..bc7babe91b2e 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -2,7 +2,7 @@ #ifndef __LINUX_INSTRUMENTATION_H #define __LINUX_INSTRUMENTATION_H -#if defined(CONFIG_DEBUG_ENTRY) && defined(CONFIG_STACK_VALIDATION) +#ifdef CONFIG_NOINSTR_VALIDATION #include <linux/stringify.h> @@ -53,9 +53,9 @@ ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) -#else +#else /* !CONFIG_NOINSTR_VALIDATION */ # define instrumentation_begin() do { } while(0) # define instrumentation_end() do { } while(0) -#endif +#endif /* CONFIG_NOINSTR_VALIDATION */ #endif /* __LINUX_INSTRUMENTATION_H */ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index a49fe8d88676..a92bce40b04b 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -222,24 +222,6 @@ devm_request_any_context_irq(struct device *dev, unsigned int irq, extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id); -/* - * On lockdep we dont want to enable hardirqs in hardirq - * context. Use local_irq_enable_in_hardirq() to annotate - * kernel code that has to do this nevertheless (pretty much - * the only valid case is for old/broken hardware that is - * insanely slow). - * - * NOTE: in theory this might break fragile code that relies - * on hardirq delivery - in practice we dont seem to have such - * places left. So the only effect should be slightly increased - * irqs-off latencies. - */ -#ifdef CONFIG_LOCKDEP -# define local_irq_enable_in_hardirq() do { } while (0) -#else -# define local_irq_enable_in_hardirq() local_irq_enable() -#endif - bool irq_has_action(unsigned int irq); extern void disable_irq_nosync(unsigned int irq); extern bool disable_hardirq(unsigned int irq); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 1814e698d861..4a2f6cc5a492 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -5,11 +5,37 @@ #include <linux/sched.h> #include <linux/xarray.h> +enum io_uring_cmd_flags { + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, + + /* ctx state flags, for URING_CMD */ + IO_URING_F_SQE128 = 4, + IO_URING_F_CQE32 = 8, + IO_URING_F_IOPOLL = 16, +}; + +struct io_uring_cmd { + struct file *file; + const void *cmd; + /* callback to defer completions to task context */ + void (*task_work_cb)(struct io_uring_cmd *cmd); + u32 cmd_op; + u32 pad; + u8 pdu[32]; /* available inline for free use */ +}; + #if defined(CONFIG_IO_URING) +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); void io_uring_unreg_ringfd(void); +const char *io_uring_get_opcode(u8 opcode); static inline void io_uring_files_cancel(void) { @@ -29,6 +55,14 @@ static inline void io_uring_free(struct task_struct *tsk) __io_uring_free(tsk); } #else +static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, + ssize_t ret2) +{ +} +static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, + void (*task_work_cb)(struct io_uring_cmd *)) +{ +} static inline struct sock *io_uring_get_socket(struct file *file) { return NULL; @@ -42,6 +76,10 @@ static inline void io_uring_files_cancel(void) static inline void io_uring_free(struct task_struct *tsk) { } +static inline const char *io_uring_get_opcode(u8 opcode) +{ + return ""; +} #endif #endif diff --git a/include/linux/irq.h b/include/linux/irq.h index f92788ccdba2..505308253d23 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup + * IRQCHIP_IMMUTABLE: Don't ever change anything in this chip */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -582,6 +583,7 @@ enum { IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), + IRQCHIP_IMMUTABLE = (1 << 11), }; #include <linux/irqdesc.h> diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 12d91f0dedf9..728691365464 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -127,6 +127,8 @@ #define GICR_PIDR2 GICD_PIDR2 #define GICR_CTLR_ENABLE_LPIS (1UL << 0) +#define GICR_CTLR_CES (1UL << 1) +#define GICR_CTLR_IR (1UL << 2) #define GICR_CTLR_RWP (1UL << 3) #define GICR_TYPER_CPU_NUMBER(r) (((r) >> 8) & 0xffff) diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 4b140938b03e..5ec0fa71399e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -20,13 +20,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void lockdep_softirqs_on(unsigned long ip); extern void lockdep_softirqs_off(unsigned long ip); - extern void lockdep_hardirqs_on_prepare(unsigned long ip); + extern void lockdep_hardirqs_on_prepare(void); extern void lockdep_hardirqs_on(unsigned long ip); extern void lockdep_hardirqs_off(unsigned long ip); #else static inline void lockdep_softirqs_on(unsigned long ip) { } static inline void lockdep_softirqs_off(unsigned long ip) { } - static inline void lockdep_hardirqs_on_prepare(unsigned long ip) { } + static inline void lockdep_hardirqs_on_prepare(void) { } static inline void lockdep_hardirqs_on(unsigned long ip) { } static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif diff --git a/include/linux/kthread.h b/include/linux/kthread.h index de5d75bafd66..30e5bec81d2b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -222,9 +222,5 @@ void kthread_associate_blkcg(struct cgroup_subsys_state *css); struct cgroup_subsys_state *kthread_blkcg(void); #else static inline void kthread_associate_blkcg(struct cgroup_subsys_state *css) { } -static inline struct cgroup_subsys_state *kthread_blkcg(void) -{ - return NULL; -} #endif #endif /* _LINUX_KTHREAD_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 34eed5f85ed6..4640393f20ab 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -453,7 +453,7 @@ static __always_inline void guest_state_enter_irqoff(void) { instrumentation_begin(); trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); + lockdep_hardirqs_on_prepare(); instrumentation_end(); guest_context_enter_irqoff(); diff --git a/include/linux/libata.h b/include/linux/libata.h index 9b1d3d8b1252..732de9014626 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -820,7 +820,6 @@ struct ata_port { unsigned int cbl; /* cable type; ATA_CBL_xxx */ struct ata_queued_cmd qcmd[ATA_MAX_QUEUE + 1]; - unsigned long sas_tag_allocated; /* for sas tag allocation only */ u64 qc_active; int nr_active_links; /* #links with active qcs */ unsigned int sas_last_tag; /* track next tag hw expects */ @@ -1111,7 +1110,7 @@ extern void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *udma_mask); extern u8 ata_xfer_mask2mode(unsigned long xfer_mask); extern unsigned long ata_xfer_mode2mask(u8 xfer_mode); -extern int ata_xfer_mode2shift(unsigned long xfer_mode); +extern int ata_xfer_mode2shift(u8 xfer_mode); extern const char *ata_mode_string(unsigned long xfer_mask); extern unsigned long ata_id_xfermask(const u16 *id); extern int ata_std_qc_defer(struct ata_queued_cmd *qc); diff --git a/include/linux/linkage.h b/include/linux/linkage.h index acb1ad2356f1..1feab6136b5b 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -171,12 +171,9 @@ /* SYM_ALIAS -- use only if you have to */ #ifndef SYM_ALIAS -#define SYM_ALIAS(alias, name, sym_type, linkage) \ - linkage(alias) ASM_NL \ - .set alias, name ASM_NL \ - .type alias sym_type ASM_NL \ - .set .L__sym_size_##alias, .L__sym_size_##name ASM_NL \ - .size alias, .L__sym_size_##alias +#define SYM_ALIAS(alias, name, linkage) \ + linkage(alias) ASM_NL \ + .set alias, name ASM_NL #endif /* === code annotations === */ @@ -261,7 +258,7 @@ */ #ifndef SYM_FUNC_ALIAS #define SYM_FUNC_ALIAS(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_GLOBAL) + SYM_ALIAS(alias, name, SYM_L_GLOBAL) #endif /* @@ -269,7 +266,7 @@ */ #ifndef SYM_FUNC_ALIAS_LOCAL #define SYM_FUNC_ALIAS_LOCAL(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_LOCAL) + SYM_ALIAS(alias, name, SYM_L_LOCAL) #endif /* @@ -277,7 +274,7 @@ */ #ifndef SYM_FUNC_ALIAS_WEAK #define SYM_FUNC_ALIAS_WEAK(alias, name) \ - SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK) + SYM_ALIAS(alias, name, SYM_L_WEAK) #endif /* SYM_CODE_START -- use for non-C (special) functions */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2c6b9e416225..7c2d77d75a88 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -169,7 +169,7 @@ enum { #define NETIF_F_HW_HSR_FWD __NETIF_F(HW_HSR_FWD) #define NETIF_F_HW_HSR_DUP __NETIF_F(HW_HSR_DUP) -/* Finds the next feature with the highest number of the range of start till 0. +/* Finds the next feature with the highest number of the range of start-1 till 0. */ static inline int find_next_netdev_feature(u64 feature, unsigned long start) { @@ -188,7 +188,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) for ((bit) = find_next_netdev_feature((mask_addr), \ NETDEV_FEATURE_COUNT); \ (bit) >= 0; \ - (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) + (bit) = find_next_netdev_feature((mask_addr), (bit))) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b1fbe21650bb..f736c020cde2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -900,7 +900,7 @@ struct net_device_path_stack { struct net_device_path_ctx { const struct net_device *dev; - const u8 *daddr; + u8 daddr[ETH_ALEN]; int num_vlans; struct { diff --git a/include/linux/nvme.h b/include/linux/nvme.h index f626a445d1a8..29ec3e3481ff 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -137,6 +137,7 @@ enum { NVME_REG_CMBMSC = 0x0050, /* Controller Memory Buffer Memory * Space Control */ + NVME_REG_CRTO = 0x0068, /* Controller Ready Timeouts */ NVME_REG_PMRCAP = 0x0e00, /* Persistent Memory Capabilities */ NVME_REG_PMRCTL = 0x0e04, /* Persistent Memory Region Control */ NVME_REG_PMRSTS = 0x0e08, /* Persistent Memory Region Status */ @@ -161,6 +162,9 @@ enum { #define NVME_CMB_BIR(cmbloc) ((cmbloc) & 0x7) #define NVME_CMB_OFST(cmbloc) (((cmbloc) >> 12) & 0xfffff) +#define NVME_CRTO_CRIMT(crto) ((crto) >> 16) +#define NVME_CRTO_CRWMT(crto) ((crto) & 0xffff) + enum { NVME_CMBSZ_SQS = 1 << 0, NVME_CMBSZ_CQS = 1 << 1, @@ -204,8 +208,10 @@ enum { NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, - NVME_CAP_CSS_NVM = 1 << 0, - NVME_CAP_CSS_CSI = 1 << 6, + NVME_CC_CRIME = 1 << 24, +}; + +enum { NVME_CSTS_RDY = 1 << 0, NVME_CSTS_CFS = 1 << 1, NVME_CSTS_NSSRO = 1 << 4, @@ -214,10 +220,23 @@ enum { NVME_CSTS_SHST_OCCUR = 1 << 2, NVME_CSTS_SHST_CMPLT = 2 << 2, NVME_CSTS_SHST_MASK = 3 << 2, +}; + +enum { NVME_CMBMSC_CRE = 1 << 0, NVME_CMBMSC_CMSE = 1 << 1, }; +enum { + NVME_CAP_CSS_NVM = 1 << 0, + NVME_CAP_CSS_CSI = 1 << 6, +}; + +enum { + NVME_CAP_CRMS_CRIMS = 1ULL << 59, + NVME_CAP_CRMS_CRWMS = 1ULL << 60, +}; + struct nvme_id_power_state { __le16 max_power; /* centiwatts */ __u8 rsvd2; @@ -405,6 +424,21 @@ struct nvme_id_ns { __u8 vs[3712]; }; +/* I/O Command Set Independent Identify Namespace Data Structure */ +struct nvme_id_ns_cs_indep { + __u8 nsfeat; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __le32 anagrpid; + __u8 nsattr; + __u8 rsvd9; + __le16 nvmsetid; + __le16 endgid; + __u8 nstat; + __u8 rsvd15[4081]; +}; + struct nvme_zns_lbafe { __le64 zsze; __u8 zdes; @@ -469,6 +503,7 @@ enum { NVME_ID_CNS_NS_DESC_LIST = 0x03, NVME_ID_CNS_CS_NS = 0x05, NVME_ID_CNS_CS_CTRL = 0x06, + NVME_ID_CNS_NS_CS_INDEP = 0x08, NVME_ID_CNS_NS_PRESENT_LIST = 0x10, NVME_ID_CNS_NS_PRESENT = 0x11, NVME_ID_CNS_CTRL_NS_LIST = 0x12, @@ -523,6 +558,10 @@ enum { }; enum { + NVME_NSTAT_NRDY = 1 << 0, +}; + +enum { NVME_NVM_NS_16B_GUARD = 0, NVME_NVM_NS_32B_GUARD = 1, NVME_NVM_NS_64B_GUARD = 2, @@ -1583,6 +1622,7 @@ enum { NVME_SC_NS_WRITE_PROTECTED = 0x20, NVME_SC_CMD_INTERRUPTED = 0x21, NVME_SC_TRANSIENT_TR_ERR = 0x22, + NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY = 0x24, NVME_SC_INVALID_IO_CMD_SET = 0x2C, NVME_SC_LBA_RANGE = 0x80, @@ -1679,9 +1719,11 @@ enum { /* * Path-related Errors: */ + NVME_SC_INTERNAL_PATH_ERROR = 0x300, NVME_SC_ANA_PERSISTENT_LOSS = 0x301, NVME_SC_ANA_INACCESSIBLE = 0x302, NVME_SC_ANA_TRANSITION = 0x303, + NVME_SC_CTRL_PATH_ERROR = 0x360, NVME_SC_HOST_PATH_ERROR = 0x370, NVME_SC_HOST_ABORTED_CMD = 0x371, diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 586d35720f13..6491fa8fba6d 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -38,7 +38,9 @@ struct unwind_hint { #define UNWIND_HINT_TYPE_REGS_PARTIAL 2 #define UNWIND_HINT_TYPE_FUNC 3 -#ifdef CONFIG_STACK_VALIDATION +#ifdef CONFIG_OBJTOOL + +#include <asm/asm.h> #ifndef __ASSEMBLY__ @@ -137,7 +139,7 @@ struct unwind_hint { .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + _ASM_PTR \func .popsection .endm @@ -157,7 +159,7 @@ struct unwind_hint { #endif /* __ASSEMBLY__ */ -#else /* !CONFIG_STACK_VALIDATION */ +#else /* !CONFIG_OBJTOOL */ #ifndef __ASSEMBLY__ @@ -179,6 +181,6 @@ struct unwind_hint { .endm #endif -#endif /* CONFIG_STACK_VALIDATION */ +#endif /* CONFIG_OBJTOOL */ #endif /* _LINUX_OBJTOOL_H */ diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 993994cd943a..6165283bdb6f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1046,6 +1046,7 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index af97dd427501..da759560eec5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1063,6 +1063,22 @@ static inline void perf_sample_data_init(struct perf_sample_data *data, data->txn = 0; } +/* + * Clear all bitfields in the perf_branch_entry. + * The to and from fields are not cleared because they are + * systematically modified by caller. + */ +static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) +{ + br->mispred = 0; + br->predicted = 0; + br->in_tx = 0; + br->abort = 0; + br->cycles = 0; + br->type = 0; + br->reserved = 0; +} + extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, @@ -1660,4 +1676,10 @@ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); +#ifndef PERF_NEEDS_LOPWR_CB +static inline void perf_lopwr_cb(bool mode) +{ +} +#endif + #endif /* _LINUX_PERF_EVENT_H */ diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 40185f9d7c14..a6bd74e29b6b 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -216,6 +216,8 @@ struct mlxreg_core_platform_data { * @mask_low: low aggregation interrupt common mask; * @deferred_nr: I2C adapter number must be exist prior probing execution; * @shift_nr: I2C adapter numbers must be incremented by this value; + * @handle: handle to be passed by callback; + * @completion_notify: callback to notify when platform driver probing is done; */ struct mlxreg_core_hotplug_platform_data { struct mlxreg_core_item *items; @@ -228,6 +230,8 @@ struct mlxreg_core_hotplug_platform_data { u32 mask_low; int deferred_nr; int shift_nr; + void *handle; + int (*completion_notify)(void *handle, int id); }; #endif /* __LINUX_PLATFORM_DATA_MLXREG_H */ diff --git a/include/linux/platform_data/x86/pmc_atom.h b/include/linux/platform_data/x86/pmc_atom.h index 022bcea9edec..6807839c718b 100644 --- a/include/linux/platform_data/x86/pmc_atom.h +++ b/include/linux/platform_data/x86/pmc_atom.h @@ -144,6 +144,5 @@ #define SLEEP_ENABLE 0x2000 extern int pmc_atom_read(int offset, u32 *value); -extern int pmc_atom_write(int offset, u32 value); #endif /* PMC_ATOM_H */ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e7c39c200e2b..1a32036c918c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -196,6 +196,7 @@ void synchronize_rcu_tasks_rude(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu diff --git a/include/linux/sched.h b/include/linux/sched.h index e06cfdaa3c6f..b89c8571187b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -941,6 +941,9 @@ struct task_struct { #ifdef CONFIG_IOMMU_SVA unsigned pasid_activated:1; #endif +#ifdef CONFIG_CPU_SUP_INTEL + unsigned reported_split_lock:1; +#endif unsigned long atomic_flags; /* Flags requiring atomic access. */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 3c8b34876744..20ed5ba2bde4 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -320,7 +320,7 @@ int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); -int force_sig_perf(void __user *addr, u32 type, u64 sig_data); +int send_sig_perf(void __user *addr, u32 type, u64 sig_data); int force_sig_ptrace_errno_trap(int errno, void __user *addr); int force_sig_fault_trapno(int sig, int code, void __user *addr, int trapno); @@ -356,13 +356,22 @@ static inline void clear_notify_signal(void) } /* + * Returns 'true' if kick_process() is needed to force a transition from + * user -> kernel to guarantee expedient run of TWA_SIGNAL based task_work. + */ +static inline bool __set_notify_signal(struct task_struct *task) +{ + return !test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && + !wake_up_state(task, TASK_INTERRUPTIBLE); +} + +/* * Called to break out of interruptible wait loops, and enter the * exit_to_user_mode_loop(). */ static inline void set_notify_signal(struct task_struct *task) { - if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_SIGNAL) && - !wake_up_state(task, TASK_INTERRUPTIBLE)) + if (__set_notify_signal(task)) kick_process(task); } diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 892562ebbd3a..5e799a47431e 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -16,7 +16,7 @@ * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ -static inline void *task_stack_page(const struct task_struct *task) +static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } diff --git a/include/linux/socket.h b/include/linux/socket.h index 6f85f5d957ef..17311ad9f9af 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -50,6 +50,9 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ + + int msg_inq; /* output, data left in socket */ + struct iov_iter msg_iter; /* data */ /* @@ -62,8 +65,9 @@ struct msghdr { void __user *msg_control_user; }; bool msg_control_is_user : 1; - __kernel_size_t msg_controllen; /* ancillary data buffer length */ + bool msg_get_inq : 1;/* return INQ after receive */ unsigned int msg_flags; /* flags on received message */ + __kernel_size_t msg_controllen; /* ancillary data buffer length */ struct kiocb *msg_iocb; /* ptr to iocb for async requests */ }; @@ -434,6 +438,7 @@ extern struct file *do_accept(struct file *file, unsigned file_flags, extern int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags); extern int __sys_socket(int family, int type, int protocol); +extern struct file *__sys_socket_file(int family, int type, int protocol); extern int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen); extern int __sys_connect_file(struct file *file, struct sockaddr_storage *addr, int addrlen, int file_flags); diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h index cb1f4351e8ba..e3014319d1ad 100644 --- a/include/linux/srcutree.h +++ b/include/linux/srcutree.h @@ -47,11 +47,9 @@ struct srcu_data { */ struct srcu_node { spinlock_t __private lock; - unsigned long srcu_have_cbs[4]; /* GP seq for children */ - /* having CBs, but only */ - /* is > ->srcu_gq_seq. */ - unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs */ - /* have CBs for given GP? */ + unsigned long srcu_have_cbs[4]; /* GP seq for children having CBs, but only */ + /* if greater than ->srcu_gq_seq. */ + unsigned long srcu_data_have_cbs[4]; /* Which srcu_data structs have CBs for given GP? */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ struct srcu_node *srcu_parent; /* Next up in tree. */ int grplo; /* Least CPU for node. */ @@ -62,18 +60,24 @@ struct srcu_node { * Per-SRCU-domain structure, similar in function to rcu_state. */ struct srcu_struct { - struct srcu_node node[NUM_RCU_NODES]; /* Combining tree. */ + struct srcu_node *node; /* Combining tree. */ struct srcu_node *level[RCU_NUM_LVLS + 1]; /* First node at each level. */ + int srcu_size_state; /* Small-to-big transition state. */ struct mutex srcu_cb_mutex; /* Serialize CB preparation. */ - spinlock_t __private lock; /* Protect counters */ + spinlock_t __private lock; /* Protect counters and size state. */ struct mutex srcu_gp_mutex; /* Serialize GP work. */ unsigned int srcu_idx; /* Current rdr array element. */ unsigned long srcu_gp_seq; /* Grace-period seq #. */ unsigned long srcu_gp_seq_needed; /* Latest gp_seq needed. */ unsigned long srcu_gp_seq_needed_exp; /* Furthest future exp GP. */ + unsigned long srcu_gp_start; /* Last GP start timestamp (jiffies) */ unsigned long srcu_last_gp_end; /* Last GP end timestamp (ns) */ + unsigned long srcu_size_jiffies; /* Current contention-measurement interval. */ + unsigned long srcu_n_lock_retries; /* Contention events in current interval. */ + unsigned long srcu_n_exp_nodelay; /* # expedited no-delays in current GP phase. */ struct srcu_data __percpu *sda; /* Per-CPU srcu_data array. */ + bool sda_is_static; /* May ->sda be passed to free_percpu()? */ unsigned long srcu_barrier_seq; /* srcu_barrier seq #. */ struct mutex srcu_barrier_mutex; /* Serialize barrier ops. */ struct completion srcu_barrier_completion; @@ -81,10 +85,23 @@ struct srcu_struct { atomic_t srcu_barrier_cpu_cnt; /* # CPUs not yet posting a */ /* callback for the barrier */ /* operation. */ + unsigned long reschedule_jiffies; + unsigned long reschedule_count; struct delayed_work work; struct lockdep_map dep_map; }; +/* Values for size state variable (->srcu_size_state). */ +#define SRCU_SIZE_SMALL 0 +#define SRCU_SIZE_ALLOC 1 +#define SRCU_SIZE_WAIT_BARRIER 2 +#define SRCU_SIZE_WAIT_CALL 3 +#define SRCU_SIZE_WAIT_CBS1 4 +#define SRCU_SIZE_WAIT_CBS2 5 +#define SRCU_SIZE_WAIT_CBS3 6 +#define SRCU_SIZE_WAIT_CBS4 7 +#define SRCU_SIZE_BIG 8 + /* Values for state variable (bottom bits of ->srcu_gp_seq). */ #define SRCU_STATE_IDLE 0 #define SRCU_STATE_SCAN1 1 @@ -121,6 +138,7 @@ struct srcu_struct { #ifdef MODULE # define __DEFINE_SRCU(name, is_static) \ is_static struct srcu_struct name; \ + extern struct srcu_struct * const __srcu_struct_##name; \ struct srcu_struct * const __srcu_struct_##name \ __section("___srcu_struct_ptrs") = &name #else diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 24eea1b05ca2..29917850f079 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -270,5 +270,6 @@ struct plat_stmmacenet_data { int msi_rx_base_vec; int msi_tx_base_vec; bool use_phy_wol; + bool sph_disable; }; #endif diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 46fb3ebdd16e..ea7a74ea7389 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -124,6 +124,22 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); */ int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); +/** + * stop_core_cpuslocked: - stop all threads on just one core + * @cpu: any cpu in the targeted core + * @fn: the function to run + * @data: the data ptr for @fn() + * + * Same as above, but instead of every CPU, only the logical CPUs of a + * single core are affected. + * + * Context: Must be called from within a cpus_read_lock() protected region. + * + * Return: 0 if all executions of @fn returned 0, any non zero return + * value if any returned non zero. + */ +int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data); + int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); #else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index 267b7aeaf1a6..90501404fa49 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -160,6 +160,7 @@ struct rpc_add_xprt_test { #define RPC_CLNT_CREATE_NO_RETRANS_TIMEOUT (1UL << 9) #define RPC_CLNT_CREATE_SOFTERR (1UL << 10) #define RPC_CLNT_CREATE_REUSEPORT (1UL << 11) +#define RPC_CLNT_CREATE_CONNECTED (1UL << 12) struct rpc_clnt *rpc_create(struct rpc_create_args *args); struct rpc_clnt *rpc_bind_new_program(struct rpc_clnt *, diff --git a/include/linux/task_work.h b/include/linux/task_work.h index 897494b597ba..795ef5a68429 100644 --- a/include/linux/task_work.h +++ b/include/linux/task_work.h @@ -17,6 +17,7 @@ enum task_work_notify_mode { TWA_NONE, TWA_RESUME, TWA_SIGNAL, + TWA_SIGNAL_NO_IPI, }; static inline bool task_work_pending(struct task_struct *task) diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 78a98bdff76d..fe1e467ba046 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -177,6 +177,7 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); extern u64 ktime_get_boot_fast_ns(void); +extern u64 ktime_get_tai_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..648f00105f58 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,14 +196,6 @@ extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) -struct ctl_table; - -extern unsigned int sysctl_timer_migration; -int timer_migration_handler(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - unsigned long __round_jiffies(unsigned long j, int cpu); unsigned long __round_jiffies_relative(unsigned long j, int cpu); unsigned long round_jiffies(unsigned long j); diff --git a/include/linux/torture.h b/include/linux/torture.h index 63fa4196e51c..7038104463e4 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -118,7 +118,7 @@ void _torture_stop_kthread(char *m, struct task_struct **tp); _torture_stop_kthread("Stopping " #n " task", &(tp)) #ifdef CONFIG_PREEMPTION -#define torture_preempt_schedule() preempt_schedule() +#define torture_preempt_schedule() __preempt_schedule() #else #define torture_preempt_schedule() do { } while (0) #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 546179418ffa..5a328cf02b75 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -231,6 +231,28 @@ static inline bool pagefault_disabled(void) */ #define faulthandler_disabled() (pagefault_disabled() || in_atomic()) +#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS + +/** + * probe_subpage_writeable: probe the user range for write faults at sub-page + * granularity (e.g. arm64 MTE) + * @uaddr: start of address range + * @size: size of address range + * + * Returns 0 on success, the number of bytes not probed on fault. + * + * It is expected that the caller checked for the write permission of each + * page in the range either by put_user() or GUP. The architecture port can + * implement a more efficient get_user() probing if the same sub-page faults + * are triggered by either a read or a write. + */ +static inline size_t probe_subpage_writeable(char __user *uaddr, size_t size) +{ + return 0; +} + +#endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */ + #ifndef ARCH_HAS_NOCACHE_UACCESS static inline __must_check unsigned long diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 8abd08245326..62d7b81b1cb7 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -36,6 +36,9 @@ /* HCI priority */ #define HCI_PRIO_MAX 7 +/* HCI maximum id value */ +#define HCI_MAX_ID 10000 + /* HCI Core structures */ struct inquiry_data { bdaddr_t bdaddr; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index f72ec113ae56..98e1ec1a14f0 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -425,7 +425,7 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) } int __inet_hash_connect(struct inet_timewait_death_row *death_row, - struct sock *sk, u32 port_offset, + struct sock *sk, u64 port_offset, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, struct inet_timewait_sock **)); diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 463ae5d33eb0..5b47545f22d3 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -71,7 +71,6 @@ struct inet_timewait_sock { tw_tos : 8; u32 tw_txhash; u32 tw_priority; - u32 tw_bslot; /* bind bucket slot */ struct timer_list tw_timer; struct inet_bind_bucket *tw_tb; }; @@ -110,6 +109,8 @@ static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo void inet_twsk_deschedule_put(struct inet_timewait_sock *tw); +void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family); + static inline struct net *twsk_net(const struct inet_timewait_sock *twsk) { diff --git a/include/net/ip.h b/include/net/ip.h index 3984f2c39c4b..0161137914cf 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -56,6 +56,7 @@ struct inet_skb_parm { #define IPSKB_DOREDIRECT BIT(5) #define IPSKB_FRAG_PMTU BIT(6) #define IPSKB_L3SLAVE BIT(7) +#define IPSKB_NOPOLICY BIT(8) u16 frag_max_size; }; diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index d7d2495f83c2..dac91aa38c5a 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -4,8 +4,8 @@ #include <linux/types.h> -u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); -u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, +u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); +u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); u32 secure_tcp_seq(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport); diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index 748cf87a4d7e..3e02709a1df6 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -14,6 +14,7 @@ struct tcf_pedit { struct tc_action common; unsigned char tcfp_nkeys; unsigned char tcfp_flags; + u32 tcfp_off_max_hint; struct tc_pedit_key *tcfp_keys; struct tcf_pedit_key_ex *tcfp_keys_ex; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6fb899ff5afc..d2efddce65d4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1093,6 +1093,18 @@ static inline bool __xfrm_check_nopolicy(struct net *net, struct sk_buff *skb, return false; } +static inline bool __xfrm_check_dev_nopolicy(struct sk_buff *skb, + int dir, unsigned short family) +{ + if (dir != XFRM_POLICY_OUT && family == AF_INET) { + /* same dst may be used for traffic originating from + * devices with different policy settings. + */ + return IPCB(skb)->flags & IPSKB_NOPOLICY; + } + return skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY); +} + static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) @@ -1104,7 +1116,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return __xfrm_check_nopolicy(net, skb, dir) || - (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || + __xfrm_check_dev_nopolicy(skb, dir, family) || __xfrm_policy_check(sk, ndir, skb, family); } diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 7b2bf9b1fe69..de26c992f821 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -681,7 +681,6 @@ struct ocelot_vcap_id { struct ocelot_vcap_filter { struct list_head list; - struct list_head trap_list; enum ocelot_vcap_filter_type type; int block_id; @@ -695,6 +694,7 @@ struct ocelot_vcap_filter { struct ocelot_vcap_stats stats; /* For VCAP IS1 and IS2 */ bool take_ts; + bool is_trap; unsigned long ingress_port_mask; /* For VCAP ES0 */ struct ocelot_vcap_port ingress_port; diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h index 675f3a1fe613..773963a1e0b5 100644 --- a/include/target/target_core_backend.h +++ b/include/target/target_core_backend.h @@ -14,7 +14,7 @@ #define TRANSPORT_FLAG_PASSTHROUGH_ALUA 0x2 #define TRANSPORT_FLAG_PASSTHROUGH_PGR 0x4 -struct request_queue; +struct block_device; struct scatterlist; struct target_backend_ops { @@ -117,7 +117,7 @@ sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd, bool target_sense_desc_format(struct se_device *dev); sector_t target_to_linux_sector(struct se_device *dev, sector_t lb); bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib, - struct request_queue *q); + struct block_device *bdev); static inline bool target_dev_configured(struct se_device *se_dev) { diff --git a/include/trace/events/intel_ifs.h b/include/trace/events/intel_ifs.h new file mode 100644 index 000000000000..d7353024016c --- /dev/null +++ b/include/trace/events/intel_ifs.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM intel_ifs + +#if !defined(_TRACE_IFS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IFS_H + +#include <linux/ktime.h> +#include <linux/tracepoint.h> + +TRACE_EVENT(ifs_status, + + TP_PROTO(int cpu, union ifs_scan activate, union ifs_status status), + + TP_ARGS(cpu, activate, status), + + TP_STRUCT__entry( + __field( u64, status ) + __field( int, cpu ) + __field( u8, start ) + __field( u8, stop ) + ), + + TP_fast_assign( + __entry->cpu = cpu; + __entry->start = activate.start; + __entry->stop = activate.stop; + __entry->status = status.data; + ), + + TP_printk("cpu: %d, start: %.2x, stop: %.2x, status: %llx", + __entry->cpu, + __entry->start, + __entry->stop, + __entry->status) +); + +#endif /* _TRACE_IFS_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index cddf5b6fbeb4..66fcc5a1a5b1 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -7,6 +7,7 @@ #include <linux/tracepoint.h> #include <uapi/linux/io_uring.h> +#include <linux/io_uring.h> struct io_wq_work; @@ -147,7 +148,7 @@ TRACE_EVENT(io_uring_queue_async_work, TP_PROTO(void *ctx, void * req, unsigned long long user_data, u8 opcode, unsigned int flags, struct io_wq_work *work, int rw), - TP_ARGS(ctx, req, user_data, flags, opcode, work, rw), + TP_ARGS(ctx, req, user_data, opcode, flags, work, rw), TP_STRUCT__entry ( __field( void *, ctx ) @@ -169,8 +170,9 @@ TRACE_EVENT(io_uring_queue_async_work, __entry->rw = rw; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, flags 0x%x, %s queue, work %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, flags 0x%x, %s queue, work %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->rw ? "hashed" : "normal", __entry->work) ); @@ -205,8 +207,9 @@ TRACE_EVENT(io_uring_defer, __entry->opcode = opcode; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d", - __entry->ctx, __entry->req, __entry->data, __entry->opcode) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s", + __entry->ctx, __entry->req, __entry->data, + io_uring_get_opcode(__entry->opcode)) ); /** @@ -305,9 +308,9 @@ TRACE_EVENT(io_uring_fail_link, __entry->link = link; ), - TP_printk("ring %p, request %p, user_data 0x%llx, opcode %d, link %p", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, - __entry->link) + TP_printk("ring %p, request %p, user_data 0x%llx, opcode %s, link %p", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->link) ); /** @@ -318,13 +321,16 @@ TRACE_EVENT(io_uring_fail_link, * @user_data: user data associated with the request * @res: result of the request * @cflags: completion flags + * @extra1: extra 64-bit data for CQE32 + * @extra2: extra 64-bit data for CQE32 * */ TRACE_EVENT(io_uring_complete, - TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags), + TP_PROTO(void *ctx, void *req, u64 user_data, int res, unsigned cflags, + u64 extra1, u64 extra2), - TP_ARGS(ctx, req, user_data, res, cflags), + TP_ARGS(ctx, req, user_data, res, cflags, extra1, extra2), TP_STRUCT__entry ( __field( void *, ctx ) @@ -332,6 +338,8 @@ TRACE_EVENT(io_uring_complete, __field( u64, user_data ) __field( int, res ) __field( unsigned, cflags ) + __field( u64, extra1 ) + __field( u64, extra2 ) ), TP_fast_assign( @@ -340,12 +348,17 @@ TRACE_EVENT(io_uring_complete, __entry->user_data = user_data; __entry->res = res; __entry->cflags = cflags; + __entry->extra1 = extra1; + __entry->extra2 = extra2; ), - TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x", + TP_printk("ring %p, req %p, user_data 0x%llx, result %d, cflags 0x%x " + "extra1 %llu extra2 %llu ", __entry->ctx, __entry->req, __entry->user_data, - __entry->res, __entry->cflags) + __entry->res, __entry->cflags, + (unsigned long long) __entry->extra1, + (unsigned long long) __entry->extra2) ); /** @@ -389,9 +402,9 @@ TRACE_EVENT(io_uring_submit_sqe, __entry->sq_thread = sq_thread; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, flags 0x%x, " + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, flags 0x%x, " "non block %d, sq_thread %d", __entry->ctx, __entry->req, - __entry->user_data, __entry->opcode, + __entry->user_data, io_uring_get_opcode(__entry->opcode), __entry->flags, __entry->force_nonblock, __entry->sq_thread) ); @@ -433,8 +446,9 @@ TRACE_EVENT(io_uring_poll_arm, __entry->events = events; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask 0x%x, events 0x%x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask 0x%x, events 0x%x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask, __entry->events) ); @@ -470,8 +484,9 @@ TRACE_EVENT(io_uring_task_add, __entry->mask = mask; ), - TP_printk("ring %p, req %p, user_data 0x%llx, opcode %d, mask %x", - __entry->ctx, __entry->req, __entry->user_data, __entry->opcode, + TP_printk("ring %p, req %p, user_data 0x%llx, opcode %s, mask %x", + __entry->ctx, __entry->req, __entry->user_data, + io_uring_get_opcode(__entry->opcode), __entry->mask) ); @@ -506,7 +521,7 @@ TRACE_EVENT(io_uring_req_failed, __field( u16, personality ) __field( u32, file_index ) __field( u64, pad1 ) - __field( u64, pad2 ) + __field( u64, addr3 ) __field( int, error ) ), @@ -520,27 +535,69 @@ TRACE_EVENT(io_uring_req_failed, __entry->off = sqe->off; __entry->addr = sqe->addr; __entry->len = sqe->len; - __entry->op_flags = sqe->rw_flags; + __entry->op_flags = sqe->poll32_events; __entry->buf_index = sqe->buf_index; __entry->personality = sqe->personality; __entry->file_index = sqe->file_index; __entry->pad1 = sqe->__pad2[0]; - __entry->pad2 = sqe->__pad2[1]; + __entry->addr3 = sqe->addr3; __entry->error = error; ), TP_printk("ring %p, req %p, user_data 0x%llx, " - "op %d, flags 0x%x, prio=%d, off=%llu, addr=%llu, " + "opcode %s, flags 0x%x, prio=%d, off=%llu, addr=%llu, " "len=%u, rw_flags=0x%x, buf_index=%d, " - "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + "personality=%d, file_index=%d, pad=0x%llx, addr3=%llx, " + "error=%d", __entry->ctx, __entry->req, __entry->user_data, - __entry->opcode, __entry->flags, __entry->ioprio, + io_uring_get_opcode(__entry->opcode), + __entry->flags, __entry->ioprio, (unsigned long long)__entry->off, (unsigned long long) __entry->addr, __entry->len, __entry->op_flags, __entry->buf_index, __entry->personality, __entry->file_index, (unsigned long long) __entry->pad1, - (unsigned long long) __entry->pad2, __entry->error) + (unsigned long long) __entry->addr3, __entry->error) +); + + +/* + * io_uring_cqe_overflow - a CQE overflowed + * + * @ctx: pointer to a ring context structure + * @user_data: user data associated with the request + * @res: CQE result + * @cflags: CQE flags + * @ocqe: pointer to the overflow cqe (if available) + * + */ +TRACE_EVENT(io_uring_cqe_overflow, + + TP_PROTO(void *ctx, unsigned long long user_data, s32 res, u32 cflags, + void *ocqe), + + TP_ARGS(ctx, user_data, res, cflags, ocqe), + + TP_STRUCT__entry ( + __field( void *, ctx ) + __field( unsigned long long, user_data ) + __field( s32, res ) + __field( u32, cflags ) + __field( void *, ocqe ) + ), + + TP_fast_assign( + __entry->ctx = ctx; + __entry->user_data = user_data; + __entry->res = res; + __entry->cflags = cflags; + __entry->ocqe = ocqe; + ), + + TP_printk("ring %p, user_data 0x%llx, res %d, flags %x, " + "overflow_cqe %p", + __entry->ctx, __entry->user_data, __entry->res, + __entry->cflags, __entry->ocqe) ); #endif /* _TRACE_IO_URING_H */ diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h index d7512129a324..9ebd081e057e 100644 --- a/include/trace/events/lock.h +++ b/include/trace/events/lock.h @@ -5,11 +5,22 @@ #if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_LOCK_H -#include <linux/lockdep.h> +#include <linux/sched.h> #include <linux/tracepoint.h> +/* flags for lock:contention_begin */ +#define LCB_F_SPIN (1U << 0) +#define LCB_F_READ (1U << 1) +#define LCB_F_WRITE (1U << 2) +#define LCB_F_RT (1U << 3) +#define LCB_F_PERCPU (1U << 4) +#define LCB_F_MUTEX (1U << 5) + + #ifdef CONFIG_LOCKDEP +#include <linux/lockdep.h> + TRACE_EVENT(lock_acquire, TP_PROTO(struct lockdep_map *lock, unsigned int subclass, @@ -78,8 +89,54 @@ DEFINE_EVENT(lock, lock_acquired, TP_ARGS(lock, ip) ); -#endif -#endif +#endif /* CONFIG_LOCK_STAT */ +#endif /* CONFIG_LOCKDEP */ + +TRACE_EVENT(contention_begin, + + TP_PROTO(void *lock, unsigned int flags), + + TP_ARGS(lock, flags), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(unsigned int, flags) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->flags = flags; + ), + + TP_printk("%p (flags=%s)", __entry->lock_addr, + __print_flags(__entry->flags, "|", + { LCB_F_SPIN, "SPIN" }, + { LCB_F_READ, "READ" }, + { LCB_F_WRITE, "WRITE" }, + { LCB_F_RT, "RT" }, + { LCB_F_PERCPU, "PERCPU" }, + { LCB_F_MUTEX, "MUTEX" } + )) +); + +TRACE_EVENT(contention_end, + + TP_PROTO(void *lock, int ret), + + TP_ARGS(lock, ret), + + TP_STRUCT__entry( + __field(void *, lock_addr) + __field(int, ret) + ), + + TP_fast_assign( + __entry->lock_addr = lock; + __entry->ret = ret; + ), + + TP_printk("%p (ret=%d)", __entry->lock_addr, __entry->ret) +); #endif /* _TRACE_LOCK_H */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 65e786756321..fbb99a61f714 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -222,11 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, TRACE_EVENT(sched_switch, TP_PROTO(bool preempt, - unsigned int prev_state, struct task_struct *prev, - struct task_struct *next), + struct task_struct *next, + unsigned int prev_state), - TP_ARGS(preempt, prev_state, prev, next), + TP_ARGS(preempt, prev, next, prev_state), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 6ad031c71be7..2e713a7d9aa3 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -48,6 +48,7 @@ DEFINE_EVENT(timer_class, timer_init, * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time + * @flags: the timers flags */ TRACE_EVENT(timer_start, @@ -84,6 +85,7 @@ TRACE_EVENT(timer_start, /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list + * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ @@ -190,7 +192,8 @@ TRACE_EVENT(hrtimer_init, /** * hrtimer_start - called when the hrtimer is started - * @hrtimer: pointer to struct hrtimer + * @hrtimer: pointer to struct hrtimer + * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, diff --git a/include/uapi/asm-generic/siginfo.h b/include/uapi/asm-generic/siginfo.h index 3ba180f550d7..ffbe4cec9f32 100644 --- a/include/uapi/asm-generic/siginfo.h +++ b/include/uapi/asm-generic/siginfo.h @@ -99,6 +99,7 @@ union __sifields { struct { unsigned long _data; __u32 _type; + __u32 _flags; } _perf; }; } _sigfault; @@ -164,6 +165,7 @@ typedef struct siginfo { #define si_pkey _sifields._sigfault._addr_pkey._pkey #define si_perf_data _sifields._sigfault._perf._data #define si_perf_type _sifields._sigfault._perf._type +#define si_perf_flags _sifields._sigfault._perf._flags #define si_band _sifields._sigpoll._band #define si_fd _sifields._sigpoll._fd #define si_call_addr _sifields._sigsys._call_addr @@ -271,6 +273,11 @@ typedef struct siginfo { */ /* + * Flags for si_perf_flags if SIGTRAP si_code is TRAP_PERF. + */ +#define TRAP_PERF_FLAG_ASYNC (1u << 0) + +/* * SIGCHLD si_codes */ #define CLD_EXITED 1 /* child has exited */ diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 804ff8d98f71..011e594e4a0d 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -103,7 +103,7 @@ #define CDROMREADALL 0x5318 /* read all 2646 bytes */ /* - * These ioctls are (now) only in ide-cd.c for controlling + * These ioctls were only in (now removed) ide-cd.c for controlling * drive spindown time. They should be implemented in the * Uniform driver, via generic packet commands, GPCMD_MODE_SELECT_10, * GPCMD_MODE_SENSE_10 and the GPMODE_POWER_PAGE... diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index 8e4a2ca0bcbf..b1523cb8ab30 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -92,7 +92,7 @@ struct dma_buf_sync { * between them in actual uapi, they're just different numbers. */ #define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) -#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, u32) -#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, u64) +#define DMA_BUF_SET_NAME_A _IOW(DMA_BUF_BASE, 1, __u32) +#define DMA_BUF_SET_NAME_B _IOW(DMA_BUF_BASE, 1, __u64) #endif diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 7ce993e6786c..429bec8dd70a 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -431,6 +431,8 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 1845cf7c80ba..53e7dae92e42 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -22,6 +22,7 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + __u32 cmd_op; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -45,6 +46,7 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -60,9 +62,28 @@ struct io_uring_sqe { __s32 splice_fd_in; __u32 file_index; }; - __u64 __pad2[2]; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; + }; }; +/* + * If sqe->file_index is set to this for opcodes that instantiate a new + * direct descriptor (like openat/openat2/accept), then io_uring will allocate + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, @@ -102,8 +123,25 @@ enum { #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ #define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) -enum { +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ + +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, @@ -145,6 +183,12 @@ enum { IORING_OP_SYMLINKAT, IORING_OP_LINKAT, IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, + IORING_OP_SOCKET, + IORING_OP_URING_CMD, /* this goes last, obviously */ IORING_OP_LAST, @@ -188,12 +232,45 @@ enum { #define IORING_POLL_UPDATE_USER_DATA (1U << 2) /* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) + +/* + * send/sendmsg and recv/recvmsg flags (sqe->addr2) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) + +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* @@ -201,9 +278,11 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) +#define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -236,6 +315,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; @@ -333,6 +413,10 @@ enum { IORING_REGISTER_RING_FDS = 20, IORING_UNREGISTER_RING_FDS = 21, + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + /* this goes last */ IORING_REGISTER_LAST }; @@ -350,9 +434,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; @@ -404,6 +494,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 98e60801195e..6f63527dd2ed 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -1,11 +1,6 @@ /* SPDX-License-Identifier: GPL-1.0+ WITH Linux-syscall-note */ /* - * include/linux/loop.h - * - * Written by Theodore Ts'o, 3/29/93. - * - * Copyright 1993 by Theodore Ts'o. Redistribution of this file is - * permitted under the GNU General Public License. + * Copyright 1993 by Theodore Ts'o. */ #ifndef _UAPI_LINUX_LOOP_H #define _UAPI_LINUX_LOOP_H diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h index b2e43185e3b5..2f76cba67166 100644 --- a/include/uapi/linux/nvme_ioctl.h +++ b/include/uapi/linux/nvme_ioctl.h @@ -70,6 +70,28 @@ struct nvme_passthru_cmd64 { __u64 result; }; +/* same as struct nvme_passthru_cmd64, minus the 8b result field */ +struct nvme_uring_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 rsvd2; +}; + #define nvme_admin_cmd nvme_passthru_cmd #define NVME_IOCTL_ID _IO('N', 0x40) @@ -83,4 +105,10 @@ struct nvme_passthru_cmd64 { #define NVME_IOCTL_IO64_CMD _IOWR('N', 0x48, struct nvme_passthru_cmd64) #define NVME_IOCTL_IO64_CMD_VEC _IOWR('N', 0x49, struct nvme_passthru_cmd64) +/* io_uring async commands: */ +#define NVME_URING_CMD_IO _IOWR('N', 0x80, struct nvme_uring_cmd) +#define NVME_URING_CMD_IO_VEC _IOWR('N', 0x81, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN _IOWR('N', 0x82, struct nvme_uring_cmd) +#define NVME_URING_CMD_ADMIN_VEC _IOWR('N', 0x83, struct nvme_uring_cmd) + #endif /* _UAPI_LINUX_NVME_IOCTL_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index e998764f0262..a5e06dcbba13 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,6 +272,15 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +/* arm64 Scalable Matrix Extension controls */ +/* Flag values must be in sync with SVE versions */ +#define PR_SME_SET_VL 63 /* set task vector length */ +# define PR_SME_SET_VL_ONEXEC (1 << 18) /* defer effect until exec */ +#define PR_SME_GET_VL 64 /* get task vector length */ +/* Bits common to PR_SME_SET_VL and PR_SME_GET_VL */ +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) /* inherit across exec */ + #define PR_SET_VMA 0x53564d41 # define PR_SET_VMA_ANON_NAME 0 diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 283c5a7b3f2c..db6c8588c1d0 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -184,7 +184,7 @@ struct rfkill_event_ext { #define RFKILL_IOC_NOINPUT 1 #define RFKILL_IOCTL_NOINPUT _IO(RFKILL_IOC_MAGIC, RFKILL_IOC_NOINPUT) #define RFKILL_IOC_MAX_SIZE 2 -#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_EXT_SIZE, __u32) +#define RFKILL_IOCTL_MAX_SIZE _IOW(RFKILL_IOC_MAGIC, RFKILL_IOC_MAX_SIZE, __u32) /* and that's all userspace gets */ diff --git a/include/uapi/linux/sev-guest.h b/include/uapi/linux/sev-guest.h new file mode 100644 index 000000000000..256aaeff7e65 --- /dev/null +++ b/include/uapi/linux/sev-guest.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Userspace interface for AMD SEV and SNP guest driver. + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Brijesh Singh <brijesh.singh@amd.com> + * + * SEV API specification is available at: https://developer.amd.com/sev/ + */ + +#ifndef __UAPI_LINUX_SEV_GUEST_H_ +#define __UAPI_LINUX_SEV_GUEST_H_ + +#include <linux/types.h> + +struct snp_report_req { + /* user data that should be included in the report */ + __u8 user_data[64]; + + /* The vmpl level to be included in the report */ + __u32 vmpl; + + /* Must be zero filled */ + __u8 rsvd[28]; +}; + +struct snp_report_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[4000]; +}; + +struct snp_derived_key_req { + __u32 root_key_select; + __u32 rsvd; + __u64 guest_field_select; + __u32 vmpl; + __u32 guest_svn; + __u64 tcb_version; +}; + +struct snp_derived_key_resp { + /* response data, see SEV-SNP spec for the format */ + __u8 data[64]; +}; + +struct snp_guest_request_ioctl { + /* message version number (must be non-zero) */ + __u8 msg_version; + + /* Request and response structure address */ + __u64 req_data; + __u64 resp_data; + + /* firmware error code on failure (see psp-sev.h) */ + __u64 fw_err; +}; + +struct snp_ext_report_req { + struct snp_report_req data; + + /* where to copy the certificate blob */ + __u64 certs_address; + + /* length of the certificate blob */ + __u32 certs_len; +}; + +#define SNP_GUEST_REQ_IOC_TYPE 'S' + +/* Get SNP attestation report */ +#define SNP_GET_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x0, struct snp_guest_request_ioctl) + +/* Get a derived key from the root */ +#define SNP_GET_DERIVED_KEY _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x1, struct snp_guest_request_ioctl) + +/* Get SNP extended report as defined in the GHCB specification version 2. */ +#define SNP_GET_EXT_REPORT _IOWR(SNP_GUEST_REQ_IOC_TYPE, 0x2, struct snp_guest_request_ioctl) + +#endif /* __UAPI_LINUX_SEV_GUEST_H_ */ diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 80d76b75bccd..7aa2eb766205 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index dfd5bf31cfb9..7d0f2f0037b8 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -57,8 +57,6 @@ #define INVALID_GRANT_REF ((grant_ref_t)-1) #define INVALID_GRANT_HANDLE ((grant_handle_t)-1) -#define GNTTAB_RESERVED_XENSTORE 1 - /* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */ #define NR_GRANT_FRAMES 4 diff --git a/include/xen/interface/grant_table.h b/include/xen/interface/grant_table.h index 3eeabbc7ee09..cebbd99f1f84 100644 --- a/include/xen/interface/grant_table.h +++ b/include/xen/interface/grant_table.h @@ -19,7 +19,8 @@ /* Some rough guidelines on accessing and updating grant-table entries * in a concurrency-safe manner. For more information, Linux contains a - * reference implementation for guest OSes (arch/xen/kernel/grant_table.c). + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD * * NB. WMB is a no-op on current-generation x86 processors. However, a * compiler barrier will still be required. @@ -80,8 +81,9 @@ typedef uint32_t grant_ref_t; */ /* - * Version 1 of the grant table entry structure is maintained purely - * for backwards compatibility. New guests should use version 2. + * Version 1 of the grant table entry structure is maintained largely for + * backwards compatibility. New guests are recommended to support using + * version 2 to overcome version 1 limitations, but to default to version 1. */ struct grant_entry_v1 { /* GTF_xxx: various type and flag information. [XEN,GST] */ @@ -89,12 +91,21 @@ struct grant_entry_v1 { /* The domain being granted foreign privileges. [GST] */ domid_t domid; /* - * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] - * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + * GTF_permit_access: GFN that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST] + * GTF_transfer_completed: MFN whose ownership transferred by @domid + * (non-translated guests only). [XEN] */ uint32_t frame; }; +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + /* * Type of grant entry. * GTF_invalid: This grant entry grants no privileges. @@ -111,10 +122,13 @@ struct grant_entry_v1 { #define GTF_type_mask (3U<<0) /* - * Subflags for GTF_permit_access. + * Subflags for GTF_permit_access and GTF_transitive. * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * Further subflags for GTF_permit_access only. + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for + * mappings of the grant [GST] * GTF_sub_page: Grant access to only a subrange of the page. @domid * will only be allowed to copy from the grant, and not * map it. [GST] @@ -125,6 +139,12 @@ struct grant_entry_v1 { #define GTF_reading (1U<<_GTF_reading) #define _GTF_writing (4) #define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) #define _GTF_sub_page (8) #define GTF_sub_page (1U<<_GTF_sub_page) @@ -164,8 +184,7 @@ struct grant_entry_header { }; /* - * Version 2 of the grant entry structure, here is a union because three - * different types are suppotted: full_page, sub_page and transitive. + * Version 2 of the grant entry structure. */ union grant_entry_v2 { struct grant_entry_header hdr; @@ -180,9 +199,9 @@ union grant_entry_v2 { * field of the same name in the V1 entry structure. */ struct { - struct grant_entry_header hdr; - uint32_t pad0; - uint64_t frame; + struct grant_entry_header hdr; + uint32_t pad0; + uint64_t frame; } full_page; /* @@ -191,10 +210,10 @@ union grant_entry_v2 { * in frame @frame. */ struct { - struct grant_entry_header hdr; - uint16_t page_off; - uint16_t length; - uint64_t frame; + struct grant_entry_header hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; } sub_page; /* @@ -202,12 +221,15 @@ union grant_entry_v2 { * grant @gref in domain @trans_domid, as if it was the local * domain. Obviously, the transitive access must be compatible * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. */ struct { - struct grant_entry_header hdr; - domid_t trans_domid; - uint16_t pad0; - grant_ref_t gref; + struct grant_entry_header hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; } transitive; uint32_t __spacer[4]; /* Pad to a power of two */ @@ -219,6 +241,21 @@ typedef uint16_t grant_status_t; * GRANT TABLE QUERIES AND USES */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#define GNTTABOP_cache_flush 12 +/* ` } */ + /* * Handle to track a mapping created via a grant reference. */ @@ -227,7 +264,7 @@ typedef uint32_t grant_handle_t; /* * GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access * by devices and/or host CPUs. If successful, <handle> is a tracking number - * that must be presented later to destroy the mapping(s). On error, <handle> + * that must be presented later to destroy the mapping(s). On error, <status> * is a negative status code. * NOTES: * 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address @@ -241,7 +278,6 @@ typedef uint32_t grant_handle_t; * host mapping is destroyed by other means then it is *NOT* guaranteed * to be accounted to the correct grant reference! */ -#define GNTTABOP_map_grant_ref 0 struct gnttab_map_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -266,7 +302,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_map_grant_ref); * 3. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_grant_ref 1 struct gnttab_unmap_grant_ref { /* IN parameters. */ uint64_t host_addr; @@ -286,7 +321,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_grant_ref); * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. * 3. Xen may not support more than a single grant-table page per domain. */ -#define GNTTABOP_setup_table 2 struct gnttab_setup_table { /* IN parameters. */ domid_t dom; @@ -301,7 +335,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_setup_table); * GNTTABOP_dump_table: Dump the contents of the grant table to the * xen console. Debugging use only. */ -#define GNTTABOP_dump_table 3 struct gnttab_dump_table { /* IN parameters. */ domid_t dom; @@ -311,17 +344,17 @@ struct gnttab_dump_table { DEFINE_GUEST_HANDLE_STRUCT(gnttab_dump_table); /* - * GNTTABOP_transfer_grant_ref: Transfer <frame> to a foreign domain. The - * foreign domain has previously registered its interest in the transfer via - * <domid, ref>. + * GNTTABOP_transfer: Transfer <frame> to a foreign domain. The foreign domain + * has previously registered its interest in the transfer via <domid, ref>. * * Note that, even if the transfer fails, the specified page no longer belongs * to the calling domain *unless* the error is GNTST_bad_page. + * + * Note further that only PV guests can use this operation. */ -#define GNTTABOP_transfer 4 struct gnttab_transfer { /* IN parameters. */ - xen_pfn_t mfn; + xen_pfn_t mfn; domid_t domid; grant_ref_t ref; /* OUT parameters. */ @@ -352,21 +385,20 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_transfer); #define _GNTCOPY_dest_gref (1) #define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) -#define GNTTABOP_copy 5 struct gnttab_copy { - /* IN parameters. */ - struct { - union { - grant_ref_t ref; - xen_pfn_t gmfn; - } u; - domid_t domid; - uint16_t offset; - } source, dest; - uint16_t len; - uint16_t flags; /* GNTCOPY_* */ - /* OUT parameters. */ - int16_t status; + /* IN parameters. */ + struct gnttab_copy_ptr { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); @@ -377,7 +409,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_copy); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_query_size 6 struct gnttab_query_size { /* IN parameters. */ domid_t dom; @@ -399,7 +430,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_query_size); * 2. After executing a batch of unmaps, it is guaranteed that no stale * mappings will remain in the device or host TLBs. */ -#define GNTTABOP_unmap_and_replace 7 struct gnttab_unmap_and_replace { /* IN parameters. */ uint64_t host_addr; @@ -412,14 +442,12 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_unmap_and_replace); /* * GNTTABOP_set_version: Request a particular version of the grant - * table shared table structure. This operation can only be performed - * once in any given domain. It must be performed before any grants - * are activated; otherwise, the domain will be stuck with version 1. - * The only defined versions are 1 and 2. + * table shared table structure. This operation may be used to toggle + * between different versions, but must be performed while no grants + * are active. The only defined versions are 1 and 2. */ -#define GNTTABOP_set_version 8 struct gnttab_set_version { - /* IN parameters */ + /* IN/OUT parameters */ uint32_t version; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); @@ -436,7 +464,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_set_version); * 1. <dom> may be specified as DOMID_SELF. * 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF. */ -#define GNTTABOP_get_status_frames 9 struct gnttab_get_status_frames { /* IN parameters. */ uint32_t nr_frames; @@ -451,7 +478,6 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_status_frames); * GNTTABOP_get_version: Get the grant table version which is in * effect for domain <dom>. */ -#define GNTTABOP_get_version 10 struct gnttab_get_version { /* IN parameters */ domid_t dom; @@ -462,26 +488,37 @@ struct gnttab_get_version { DEFINE_GUEST_HANDLE_STRUCT(gnttab_get_version); /* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* GNTST_* */ +}; +DEFINE_GUEST_HANDLE_STRUCT(gnttab_swap_grant_ref); + +/* * Issue one or more cache maintenance operations on a portion of a * page granted to the calling domain by a foreign domain. */ -#define GNTTABOP_cache_flush 12 struct gnttab_cache_flush { union { uint64_t dev_bus_addr; grant_ref_t ref; } a; - uint16_t offset; /* offset from start of grant */ - uint16_t length; /* size within the grant */ -#define GNTTAB_CACHE_CLEAN (1<<0) -#define GNTTAB_CACHE_INVAL (1<<1) -#define GNTTAB_CACHE_SOURCE_GREF (1<<31) + uint16_t offset; /* offset from start of grant */ + uint16_t length; /* size within the grant */ +#define GNTTAB_CACHE_CLEAN (1u<<0) +#define GNTTAB_CACHE_INVAL (1u<<1) +#define GNTTAB_CACHE_SOURCE_GREF (1u<<31) uint32_t op; }; DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); /* - * Bitfield values for update_pin_status.flags. + * Bitfield values for gnttab_map_grant_ref.flags. */ /* Map the grant entry for access by I/O devices. */ #define _GNTMAP_device_map (0) @@ -531,6 +568,7 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); #define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */ #define GNTST_address_too_big (-11) /* transfer page address too large. */ #define GNTST_eagain (-12) /* Operation not done; try again. */ +#define GNTST_no_space (-13) /* Out of space (handles etc). */ #define GNTTABOP_error_msgs { \ "okay", \ @@ -545,7 +583,8 @@ DEFINE_GUEST_HANDLE_STRUCT(gnttab_cache_flush); "bad page", \ "copy arguments cross page boundary", \ "page address size too large", \ - "operation not done; try again" \ + "operation not done; try again", \ + "out of space", \ } #endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 2470ec45ebb2..ba4c4274b714 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -72,9 +72,8 @@ typedef unsigned int RING_IDX; * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * mytag_front_ring_t front_ring; - * SHARED_RING_INIT((mytag_sring_t *)shared_page); - * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * mytag_front_ring_t ring; + * XEN_FRONT_RING_INIT(&ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): @@ -146,6 +145,11 @@ struct __name##_back_ring { \ #define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) +#define XEN_FRONT_RING_INIT(r, s, size) do { \ + SHARED_RING_INIT(s); \ + FRONT_RING_INIT(r, s, size); \ +} while (0) + #define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ (_r)->rsp_prod_pvt = (_i); \ (_r)->req_cons = (_i); \ @@ -170,16 +174,21 @@ struct __name##_back_ring { \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define XEN_RING_NR_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ +#define XEN_RING_NR_UNCONSUMED_REQUESTS(_r) ({ \ unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ unsigned int rsp = RING_SIZE(_r) - \ ((_r)->req_cons - (_r)->rsp_prod_pvt); \ req < rsp ? req : rsp; \ }) +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + (!!XEN_RING_NR_UNCONSUMED_RESPONSES(_r)) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + (!!XEN_RING_NR_UNCONSUMED_REQUESTS(_r)) + /* Direct access to individual ring elements, by index. */ #define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) diff --git a/include/xen/interface/io/vscsiif.h b/include/xen/interface/io/vscsiif.h index 1f6047d3de44..7ea4dc9611c4 100644 --- a/include/xen/interface/io/vscsiif.h +++ b/include/xen/interface/io/vscsiif.h @@ -43,7 +43,7 @@ * * A string specifying the backend device: either a 4-tuple "h:c:t:l" * (host, controller, target, lun, all integers), or a WWN (e.g. - * "naa.60014054ac780582"). + * "naa.60014054ac780582:0"). * * v-dev * Values: string @@ -87,6 +87,75 @@ * response structures. */ +/* + * Xenstore format in practice + * =========================== + * + * The backend driver uses a single_host:many_devices notation to manage domU + * devices. Everything is stored in /local/domain/<backend_domid>/backend/vscsi/. + * The xenstore layout looks like this (dom0 is assumed to be the backend_domid): + * + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" or "naa.wwn:lun" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "4" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * + * The frontend driver maintains its state in + * /local/domain/<domid>/device/vscsi/. + * + * <vhost>/backend = "/local/domain/0/backend/vscsi/<domid>/<vhost>" + * <vhost>/backend-id = "0" + * <vhost>/event-channel = "20" + * <vhost>/ring-ref = "43" + * <vhost>/state = "4" + * <vhost>/vscsi-devs/dev-0/state = "4" + * <vhost>/vscsi-devs/dev-1/state = "4" + * + * In addition to the entries for backend and frontend these flags are stored + * for the toolstack: + * + * <domid>/<vhost>/vscsi-devs/dev-1/p-devname = "/dev/$device" + * <domid>/<vhost>/libxl_ctrl_index = "0" + * + * + * Backend/frontend protocol + * ========================= + * + * To create a vhost along with a device: + * <domid>/<vhost>/feature-host = "0" + * <domid>/<vhost>/frontend = "/local/domain/<domid>/device/vscsi/0" + * <domid>/<vhost>/frontend-id = "<domid>" + * <domid>/<vhost>/online = "1" + * <domid>/<vhost>/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/p-dev = "8:0:2:1" + * <domid>/<vhost>/vscsi-devs/dev-0/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-0/v-dev = "0:0:0:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-0/state become 4 + * + * To add another device to a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/p-dev = "8:0:2:2" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "1" + * <domid>/<vhost>/vscsi-devs/dev-1/v-dev = "0:0:1:0" + * Wait for <domid>/<vhost>/state + <domid>/<vhost>/vscsi-devs/dev-1/state become 4 + * + * To remove a device from a vhost: + * <domid>/<vhost>/state = "7" + * <domid>/<vhost>/vscsi-devs/dev-1/state = "5" + * Wait for <domid>/<vhost>/state to become 4 + * Wait for <domid>/<vhost>/vscsi-devs/dev-1/state become 6 + * Remove <domid>/<vhost>/vscsi-devs/dev-1/{state,p-dev,v-dev,p-devname} + * Remove <domid>/<vhost>/vscsi-devs/dev-1/ + * + */ + /* Requests from the frontend to the backend */ /* @@ -117,7 +186,8 @@ * (plus the set VSCSIIF_SG_GRANT bit), the number of scsiif_request_segment * elements referencing the target data buffers is calculated from the lengths * of the seg[] elements (the sum of all valid seg[].length divided by the - * size of one scsiif_request_segment structure). + * size of one scsiif_request_segment structure). The frontend may use a mix of + * direct and indirect requests. */ #define VSCSIIF_ACT_SCSI_CDB 1 @@ -154,12 +224,14 @@ /* * based on Linux kernel 2.6.18, still valid + * * Changing these values requires support of multiple protocols via the rings * as "old clients" will blindly use these values and the resulting structure * sizes. */ #define VSCSIIF_MAX_COMMAND_SIZE 16 #define VSCSIIF_SENSE_BUFFERSIZE 96 +#define VSCSIIF_PAGE_SIZE 4096 struct scsiif_request_segment { grant_ref_t gref; @@ -167,7 +239,8 @@ struct scsiif_request_segment { uint16_t length; }; -#define VSCSIIF_SG_PER_PAGE (PAGE_SIZE / sizeof(struct scsiif_request_segment)) +#define VSCSIIF_SG_PER_PAGE (VSCSIIF_PAGE_SIZE / \ + sizeof(struct scsiif_request_segment)) /* Size of one request is 252 bytes */ struct vscsiif_request { @@ -207,6 +280,58 @@ struct vscsiif_response { uint32_t reserved[36]; }; +/* SCSI I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_STATUS(x) ((x) & 0x00ff) + +/* Host I/O status from vscsiif_response->rslt */ +#define XEN_VSCSIIF_RSLT_HOST(x) (((x) & 0x00ff0000) >> 16) +#define XEN_VSCSIIF_RSLT_HOST_OK 0 +/* Couldn't connect before timeout */ +#define XEN_VSCSIIF_RSLT_HOST_NO_CONNECT 1 +/* Bus busy through timeout */ +#define XEN_VSCSIIF_RSLT_HOST_BUS_BUSY 2 +/* Timed out for other reason */ +#define XEN_VSCSIIF_RSLT_HOST_TIME_OUT 3 +/* Bad target */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_TARGET 4 +/* Abort for some other reason */ +#define XEN_VSCSIIF_RSLT_HOST_ABORT 5 +/* Parity error */ +#define XEN_VSCSIIF_RSLT_HOST_PARITY 6 +/* Internal error */ +#define XEN_VSCSIIF_RSLT_HOST_ERROR 7 +/* Reset by somebody */ +#define XEN_VSCSIIF_RSLT_HOST_RESET 8 +/* Unexpected interrupt */ +#define XEN_VSCSIIF_RSLT_HOST_BAD_INTR 9 +/* Force command past mid-layer */ +#define XEN_VSCSIIF_RSLT_HOST_PASSTHROUGH 10 +/* Retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_SOFT_ERROR 11 +/* Hidden retry requested */ +#define XEN_VSCSIIF_RSLT_HOST_IMM_RETRY 12 +/* Requeue command requested */ +#define XEN_VSCSIIF_RSLT_HOST_REQUEUE 13 +/* Transport error disrupted I/O */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_DISRUPTED 14 +/* Transport class fastfailed */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_FAILFAST 15 +/* Permanent target failure */ +#define XEN_VSCSIIF_RSLT_HOST_TARGET_FAILURE 16 +/* Permanent nexus failure on path */ +#define XEN_VSCSIIF_RSLT_HOST_NEXUS_FAILURE 17 +/* Space allocation on device failed */ +#define XEN_VSCSIIF_RSLT_HOST_ALLOC_FAILURE 18 +/* Medium error */ +#define XEN_VSCSIIF_RSLT_HOST_MEDIUM_ERROR 19 +/* Transport marginal errors */ +#define XEN_VSCSIIF_RSLT_HOST_TRANSPORT_MARGINAL 20 + +/* Result values of reset operations */ +#define XEN_VSCSIIF_RSLT_RESET_SUCCESS 0x2002 +#define XEN_VSCSIIF_RSLT_RESET_FAILED 0x2003 + DEFINE_RING_TYPES(vscsiif, struct vscsiif_request, struct vscsiif_response); -#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ + +#endif /*__XEN__PUBLIC_IO_SCSI_H__*/ diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index d40a44f09b16..b62365478ac0 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -10,7 +10,8 @@ enum xsd_sockmsg_type { - XS_DEBUG, + XS_CONTROL, +#define XS_DEBUG XS_CONTROL XS_DIRECTORY, XS_READ, XS_GET_PERMS, @@ -30,8 +31,13 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES, + /* XS_RESTRICT has been removed */ + XS_RESET_WATCHES = XS_SET_TARGET + 2, + XS_DIRECTORY_PART, + + XS_TYPE_COUNT, /* Number of valid types. */ + + XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */ }; #define XS_WRITE_NONE "NONE" @@ -59,7 +65,8 @@ static struct xsd_errors xsd_errors[] __attribute__((unused)) = { XSD_ERROR(EROFS), XSD_ERROR(EBUSY), XSD_ERROR(EAGAIN), - XSD_ERROR(EISCONN) + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) }; struct xsd_sockmsg @@ -87,9 +94,31 @@ struct xenstore_domain_interface { char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ XENSTORE_RING_IDX req_cons, req_prod; XENSTORE_RING_IDX rsp_cons, rsp_prod; + uint32_t server_features; /* Bitmap of features supported by the server */ + uint32_t connection; + uint32_t error; }; /* Violating this is very bad. See docs/misc/xenstore.txt. */ #define XENSTORE_PAYLOAD_MAX 4096 +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +/* The ability to reconnect a ring */ +#define XENSTORE_SERVER_FEATURE_RECONNECTION 1 +/* The presence of the "error" field in the ring page */ +#define XENSTORE_SERVER_FEATURE_ERROR 2 + +/* Valid values for the connection field */ +#define XENSTORE_CONNECTED 0 /* the steady-state */ +#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */ + +/* Valid values for the error field */ +#define XENSTORE_ERROR_NONE 0 /* No error */ +#define XENSTORE_ERROR_COMM 1 /* Communication problem */ +#define XENSTORE_ERROR_RINGIDX 2 /* Invalid ring index */ +#define XENSTORE_ERROR_PROTO 3 /* Protocol violation (payload too long) */ + #endif /* _XS_WIRE_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index b13eb86395e0..eaa932b99d8a 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -224,8 +224,10 @@ int xenbus_watch_pathfmt(struct xenbus_device *dev, struct xenbus_watch *watch, const char *pathfmt, ...); int xenbus_switch_state(struct xenbus_device *dev, enum xenbus_state new_state); -int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, +int xenbus_setup_ring(struct xenbus_device *dev, gfp_t gfp, void **vaddr, unsigned int nr_pages, grant_ref_t *grefs); +void xenbus_teardown_ring(void **vaddr, unsigned int nr_pages, + grant_ref_t *grefs); int xenbus_map_ring_valloc(struct xenbus_device *dev, grant_ref_t *gnt_refs, unsigned int nr_grefs, void **vaddr); |