From d3091298570006fa538ec9beacbfb1098964962e Mon Sep 17 00:00:00 2001 From: Sam Ravnborg Date: Fri, 16 May 2014 23:26:05 +0200 Subject: sparc: fix sparse warnings in smp_32.c + smp_64.c Fix following warnings: smp_32.c:177:5: warning: symbol 'setup_profiling_timer' was not declared. Should it be static? smp_64.c:1202:5: warning: symbol 'setup_profiling_timer' was not declared. Should it be static? smp_64.c:989:6: warning: symbol 'kgdb_roundup_cpus' was not declared. Should it be static? Add prototype to include/linux/profile.h of setup_profiling_timer Add missing include to smp_64.c Signed-off-by: Sam Ravnborg Signed-off-by: David S. Miller --- include/linux/profile.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index aaad3861beb8..b537a25ffa17 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -44,6 +44,7 @@ extern int prof_on __read_mostly; int profile_init(void); int profile_setup(char *str); void profile_tick(int type); +int setup_profiling_timer(unsigned int multiplier); /* * Add multiple profiler hits to a given address: -- cgit v1.2.3 From b14903e10a06347234b387f7364f86aa07252d9f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 4 Jun 2014 16:46:00 +0200 Subject: regulator: add regulator_can_change_voltage stub When CONFIG_REGULATOR is not set, we cannot call regulator_can_change_voltage() from a device driver, which results in a build error like video/fbdev/omap2/dss/hdmi5.c: In function 'hdmi_init_regulator': video/fbdev/omap2/dss/hdmi5.c:149:2: error: implicit declaration of function 'regulator_can_change_voltage' [-Werror=implicit-function-declaration] even for drivers that don't require the regulator API normally. Such a use was recently added in the omap2+ hdmi driver. This avoids the problem by adding a static inline function stub in the API header, as we have for most of the other regulator functions as well. Signed-off-by: Arnd Bergmann Cc: Mark Brown Cc: Tomi Valkeinen Signed-off-by: Mark Brown --- include/linux/regulator/consumer.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h index e530681bea70..d60b92a7fc25 100644 --- a/include/linux/regulator/consumer.h +++ b/include/linux/regulator/consumer.h @@ -391,6 +391,11 @@ static inline void regulator_bulk_free(int num_consumers, { } +static inline int regulator_can_change_voltage(struct regulator *regulator) +{ + return 0; +} + static inline int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV) { -- cgit v1.2.3 From 962bd40bc30e412828e091bfda041b7547e779c8 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 10 Jun 2014 12:24:40 -0400 Subject: locks: add missing memory barrier in break_deleg break_deleg is subject to the same potential race as break_lease. Add a memory barrier to prevent it. Signed-off-by: Jeff Layton --- include/linux/fs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index c3f46e499dd0..22ae79650b82 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1914,6 +1914,12 @@ static inline int break_lease(struct inode *inode, unsigned int mode) static inline int break_deleg(struct inode *inode, unsigned int mode) { + /* + * Since this check is lockless, we must ensure that any refcounts + * taken are done before checking inode->i_flock. Otherwise, we could + * end up racing with tasks trying to set a new lease on this file. + */ + smp_mb(); if (inode->i_flock) return __break_lease(inode, mode, FL_DELEG); return 0; -- cgit v1.2.3 From 2940474af79744411da0cb63b041ad52c57bc443 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 11 Jun 2014 13:49:23 +0200 Subject: block: remove elv_abort_queue and blk_abort_flushes elv_abort_queue has no callers, and blk_abort_flushes is only called by elv_abort_queue. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-flush.c | 38 -------------------------------------- block/blk.h | 1 - block/elevator.c | 20 -------------------- include/linux/elevator.h | 1 - 4 files changed, 60 deletions(-) (limited to 'include/linux') diff --git a/block/blk-flush.c b/block/blk-flush.c index 8ffee4b5f93d..3cb5e9e7108a 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -421,44 +421,6 @@ void blk_insert_flush(struct request *rq) blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0); } -/** - * blk_abort_flushes - @q is being aborted, abort flush requests - * @q: request_queue being aborted - * - * To be called from elv_abort_queue(). @q is being aborted. Prepare all - * FLUSH/FUA requests for abortion. - * - * CONTEXT: - * spin_lock_irq(q->queue_lock) - */ -void blk_abort_flushes(struct request_queue *q) -{ - struct request *rq, *n; - int i; - - /* - * Requests in flight for data are already owned by the dispatch - * queue or the device driver. Just restore for normal completion. - */ - list_for_each_entry_safe(rq, n, &q->flush_data_in_flight, flush.list) { - list_del_init(&rq->flush.list); - blk_flush_restore_request(rq); - } - - /* - * We need to give away requests on flush queues. Restore for - * normal completion and put them on the dispatch queue. - */ - for (i = 0; i < ARRAY_SIZE(q->flush_queue); i++) { - list_for_each_entry_safe(rq, n, &q->flush_queue[i], - flush.list) { - list_del_init(&rq->flush.list); - blk_flush_restore_request(rq); - list_add_tail(&rq->queuelist, &q->queue_head); - } - } -} - /** * blkdev_issue_flush - queue a flush * @bdev: blockdev to issue flush for diff --git a/block/blk.h b/block/blk.h index 45385e9abf6f..6748c4f8d7a1 100644 --- a/block/blk.h +++ b/block/blk.h @@ -84,7 +84,6 @@ static inline void blk_clear_rq_complete(struct request *rq) #define ELV_ON_HASH(rq) ((rq)->cmd_flags & REQ_HASHED) void blk_insert_flush(struct request *rq); -void blk_abort_flushes(struct request_queue *q); static inline struct request *__elv_next_request(struct request_queue *q) { diff --git a/block/elevator.c b/block/elevator.c index f35edddfe9b5..34bded18910e 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -729,26 +729,6 @@ int elv_may_queue(struct request_queue *q, int rw) return ELV_MQUEUE_MAY; } -void elv_abort_queue(struct request_queue *q) -{ - struct request *rq; - - blk_abort_flushes(q); - - while (!list_empty(&q->queue_head)) { - rq = list_entry_rq(q->queue_head.next); - rq->cmd_flags |= REQ_QUIET; - trace_block_rq_abort(q, rq); - /* - * Mark this request as started so we don't trigger - * any debug logic in the end I/O path. - */ - blk_start_request(rq); - __blk_end_request_all(rq, -EIO); - } -} -EXPORT_SYMBOL(elv_abort_queue); - void elv_completed_request(struct request_queue *q, struct request *rq) { struct elevator_queue *e = q->elevator; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 4ff262e2bf37..e2a6bd7fb133 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -133,7 +133,6 @@ extern struct request *elv_latter_request(struct request_queue *, struct request extern int elv_register_queue(struct request_queue *q); extern void elv_unregister_queue(struct request_queue *q); extern int elv_may_queue(struct request_queue *, int); -extern void elv_abort_queue(struct request_queue *); extern void elv_completed_request(struct request_queue *, struct request *); extern int elv_set_request(struct request_queue *q, struct request *rq, struct bio *bio, gfp_t gfp_mask); -- cgit v1.2.3 From a6e15a39048ec3229b9a53425f4384f55f6cc1b3 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 13 Jun 2014 13:30:35 -0700 Subject: PM / hibernate: introduce "nohibernate" boot parameter To support using kernel features that are not compatible with hibernation, this creates the "nohibernate" kernel boot parameter to disable both hibernation and resume. This allows hibernation support to be a boot-time choice instead of only a compile-time choice. Signed-off-by: Kees Cook Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- Documentation/kernel-parameters.txt | 3 +++ include/linux/suspend.h | 2 ++ kernel/power/hibernate.c | 31 ++++++++++++++++++++++++++++++- kernel/power/main.c | 6 ++---- kernel/power/user.c | 3 +++ 5 files changed, 40 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6eaa9cdb7094..f8f0466b8b1d 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2184,6 +2184,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. in certain environments such as networked servers or real-time systems. + nohibernate [HIBERNATION] Disable hibernation and resume. + nohz= [KNL] Boottime enable/disable dynamic ticks Valid arguments: on, off Default: on @@ -2980,6 +2982,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted. noresume Don't check if there's a hibernation image present during boot. nocompress Don't compress/decompress hibernation images. + no Disable hibernation and resume. retain_initrd [RAM] Keep initrd memory after extraction diff --git a/include/linux/suspend.h b/include/linux/suspend.h index f76994b9396c..519064e0c943 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -327,6 +327,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); +extern bool hibernation_available(void); asmlinkage int swsusp_save(void); extern struct pbe *restore_pblist; #else /* CONFIG_HIBERNATION */ @@ -339,6 +340,7 @@ static inline void swsusp_unset_page_free(struct page *p) {} static inline void hibernation_set_ops(const struct platform_hibernation_ops *ops) {} static inline int hibernate(void) { return -ENOSYS; } static inline bool system_entering_hibernation(void) { return false; } +static inline bool hibernation_available(void) { return false; } #endif /* CONFIG_HIBERNATION */ /* Hibernation and suspend events */ diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 49e0a20fd010..258f492f0347 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -35,6 +35,7 @@ static int nocompress; static int noresume; +static int nohibernate; static int resume_wait; static unsigned int resume_delay; static char resume_file[256] = CONFIG_PM_STD_PARTITION; @@ -62,6 +63,11 @@ bool freezer_test_done; static const struct platform_hibernation_ops *hibernation_ops; +bool hibernation_available(void) +{ + return (nohibernate == 0); +} + /** * hibernation_set_ops - Set the global hibernate operations. * @ops: Hibernation operations to use in subsequent hibernation transitions. @@ -642,6 +648,11 @@ int hibernate(void) { int error; + if (!hibernation_available()) { + pr_debug("PM: Hibernation not available.\n"); + return -EPERM; + } + lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { @@ -734,7 +745,7 @@ static int software_resume(void) /* * If the user said "noresume".. bail out early. */ - if (noresume) + if (noresume || !hibernation_available()) return 0; /* @@ -900,6 +911,9 @@ static ssize_t disk_show(struct kobject *kobj, struct kobj_attribute *attr, int i; char *start = buf; + if (!hibernation_available()) + return sprintf(buf, "[disabled]\n"); + for (i = HIBERNATION_FIRST; i <= HIBERNATION_MAX; i++) { if (!hibernation_modes[i]) continue; @@ -934,6 +948,9 @@ static ssize_t disk_store(struct kobject *kobj, struct kobj_attribute *attr, char *p; int mode = HIBERNATION_INVALID; + if (!hibernation_available()) + return -EPERM; + p = memchr(buf, '\n', n); len = p ? p - buf : n; @@ -1101,6 +1118,10 @@ static int __init hibernate_setup(char *str) noresume = 1; else if (!strncmp(str, "nocompress", 10)) nocompress = 1; + else if (!strncmp(str, "no", 2)) { + noresume = 1; + nohibernate = 1; + } return 1; } @@ -1125,9 +1146,17 @@ static int __init resumedelay_setup(char *str) return 1; } +static int __init nohibernate_setup(char *str) +{ + noresume = 1; + nohibernate = 1; + return 1; +} + __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); __setup("hibernate=", hibernate_setup); __setup("resumewait", resumewait_setup); __setup("resumedelay=", resumedelay_setup); +__setup("nohibernate", nohibernate_setup); diff --git a/kernel/power/main.c b/kernel/power/main.c index 573410d6647e..8e90f330f139 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -300,13 +300,11 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, s += sprintf(s,"%s ", pm_states[i].label); #endif -#ifdef CONFIG_HIBERNATION - s += sprintf(s, "%s\n", "disk"); -#else + if (hibernation_available()) + s += sprintf(s, "disk "); if (s != buf) /* convert the last space to a newline */ *(s-1) = '\n'; -#endif return (s - buf); } diff --git a/kernel/power/user.c b/kernel/power/user.c index 98d357584cd6..526e8911460a 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -49,6 +49,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) struct snapshot_data *data; int error; + if (!hibernation_available()) + return -EPERM; + lock_system_sleep(); if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { -- cgit v1.2.3 From 736ed4de766d4f0e8e6142dd4f9d73ef61835ed9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 17 Jun 2014 22:09:29 -0700 Subject: block: blk_max_size_offset() should check ->max_sectors Commit 762380ad9322 inadvertently changed a check for max_sectors to max_hw_sectors. Revert that part, so we still compare against max_sectors. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 31e11051f1ba..713f8b62b435 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -920,7 +920,7 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset) { if (!q->limits.chunk_sectors) - return q->limits.max_hw_sectors; + return q->limits.max_sectors; return q->limits.chunk_sectors - (offset & (q->limits.chunk_sectors - 1)); -- cgit v1.2.3 From 8537b12034cf1fd3fab3da2c859d71f76846fae9 Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Tue, 17 Jun 2014 22:12:35 -0700 Subject: blk-mq: bitmap tag: fix races on shared ::wake_index fields Fix racy updates of shared blk_mq_bitmap_tags::wake_index and blk_mq_hw_ctx::wake_index fields. Cc: Ming Lei Signed-off-by: Alexander Gordeev Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 32 +++++++++++++++++++++----------- block/blk-mq-tag.h | 2 +- include/linux/blk-mq.h | 2 +- 3 files changed, 23 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 1aab39f71d95..6deb13055490 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -43,9 +43,16 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags) return bt_has_free_tags(&tags->bitmap_tags); } -static inline void bt_index_inc(unsigned int *index) +static inline int bt_index_inc(int index) { - *index = (*index + 1) & (BT_WAIT_QUEUES - 1); + return (index + 1) & (BT_WAIT_QUEUES - 1); +} + +static inline void bt_index_atomic_inc(atomic_t *index) +{ + int old = atomic_read(index); + int new = bt_index_inc(old); + atomic_cmpxchg(index, old, new); } /* @@ -69,14 +76,14 @@ static void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags) int i, wake_index; bt = &tags->bitmap_tags; - wake_index = bt->wake_index; + wake_index = atomic_read(&bt->wake_index); for (i = 0; i < BT_WAIT_QUEUES; i++) { struct bt_wait_state *bs = &bt->bs[wake_index]; if (waitqueue_active(&bs->wait)) wake_up(&bs->wait); - bt_index_inc(&wake_index); + wake_index = bt_index_inc(wake_index); } } @@ -212,12 +219,14 @@ static struct bt_wait_state *bt_wait_ptr(struct blk_mq_bitmap_tags *bt, struct blk_mq_hw_ctx *hctx) { struct bt_wait_state *bs; + int wait_index; if (!hctx) return &bt->bs[0]; - bs = &bt->bs[hctx->wait_index]; - bt_index_inc(&hctx->wait_index); + wait_index = atomic_read(&hctx->wait_index); + bs = &bt->bs[wait_index]; + bt_index_atomic_inc(&hctx->wait_index); return bs; } @@ -313,18 +322,19 @@ static struct bt_wait_state *bt_wake_ptr(struct blk_mq_bitmap_tags *bt) { int i, wake_index; - wake_index = bt->wake_index; + wake_index = atomic_read(&bt->wake_index); for (i = 0; i < BT_WAIT_QUEUES; i++) { struct bt_wait_state *bs = &bt->bs[wake_index]; if (waitqueue_active(&bs->wait)) { - if (wake_index != bt->wake_index) - bt->wake_index = wake_index; + int o = atomic_read(&bt->wake_index); + if (wake_index != o) + atomic_cmpxchg(&bt->wake_index, o, wake_index); return bs; } - bt_index_inc(&wake_index); + wake_index = bt_index_inc(wake_index); } return NULL; @@ -344,7 +354,7 @@ static void bt_clear_tag(struct blk_mq_bitmap_tags *bt, unsigned int tag) bs = bt_wake_ptr(bt); if (bs && atomic_dec_and_test(&bs->wait_cnt)) { atomic_set(&bs->wait_cnt, bt->wake_cnt); - bt_index_inc(&bt->wake_index); + bt_index_atomic_inc(&bt->wake_index); wake_up(&bs->wait); } } diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 98696a65d4d4..6206ed17ef76 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -24,7 +24,7 @@ struct blk_mq_bitmap_tags { unsigned int map_nr; struct blk_align_bitmap *map; - unsigned int wake_index; + atomic_t wake_index; struct bt_wait_state *bs; }; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a002cf191427..eb726b9c5762 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -42,7 +42,7 @@ struct blk_mq_hw_ctx { unsigned int nr_ctx; struct blk_mq_ctx **ctxs; - unsigned int wait_index; + atomic_t wait_index; struct blk_mq_tags *tags; -- cgit v1.2.3 From 2b8f2a28eac1d35a432705d269f02bdaeba9be8f Mon Sep 17 00:00:00 2001 From: Daniel Mack Date: Wed, 18 Jun 2014 11:01:41 +0200 Subject: net: phylib: add link_change_notify callback to phy device Add a notify callback to inform phy drivers when the core is about to do its link adjustment. No change for drivers that do not implement this callback. Signed-off-by: Daniel Mack Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 3 +++ include/linux/phy.h | 9 +++++++++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 3bc079a67a3d..f7c61812ea4a 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -720,6 +720,9 @@ void phy_state_machine(struct work_struct *work) mutex_lock(&phydev->lock); + if (phydev->drv->link_change_notify) + phydev->drv->link_change_notify(phydev); + switch (phydev->state) { case PHY_DOWN: case PHY_STARTING: diff --git a/include/linux/phy.h b/include/linux/phy.h index 864ddafad8cc..68041446c450 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -536,6 +536,15 @@ struct phy_driver { /* See set_wol, but for checking whether Wake on LAN is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); + /* + * Called to inform a PHY device driver when the core is about to + * change the link state. This callback is supposed to be used as + * fixup hook for drivers that need to take action when the link + * state changes. Drivers are by no means allowed to mess with the + * PHY device structure in their implementations. + */ + void (*link_change_notify)(struct phy_device *dev); + struct device_driver driver; }; #define to_phy_driver(d) container_of(d, struct phy_driver, driver) -- cgit v1.2.3 From e567bf7112518824830978d644dfb5a991e67d54 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 22 Jun 2014 16:32:48 -0600 Subject: Revert "block: add __init to elv_register" This reverts commit b5097e956a4d2919ee248d6481e4204c5568ed5c. The original commit is buggy, we do use the registration functions at runtime, for instance when loading IO schedulers through sysfs. Reported-by: Damien Wyart --- block/elevator.c | 2 +- include/linux/elevator.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/elevator.c b/block/elevator.c index 34bded18910e..24c28b659bb3 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -825,7 +825,7 @@ void elv_unregister_queue(struct request_queue *q) } EXPORT_SYMBOL(elv_unregister_queue); -int __init elv_register(struct elevator_type *e) +int elv_register(struct elevator_type *e) { char *def = ""; diff --git a/include/linux/elevator.h b/include/linux/elevator.h index e2a6bd7fb133..45a91474487d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -143,7 +143,7 @@ extern void elv_drain_elevator(struct request_queue *); * io scheduler registration */ extern void __init load_default_elevator_module(void); -extern int __init elv_register(struct elevator_type *); +extern int elv_register(struct elevator_type *); extern void elv_unregister(struct elevator_type *); /* -- cgit v1.2.3 From b3acc56bfe1287c6b666e80edc70b89eea2a1a80 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Mon, 23 Jun 2014 13:22:03 -0700 Subject: kexec: save PG_head_mask in VMCOREINFO To allow filtering of huge pages, makedumpfile must be able to identify them in the dump. This can be done by checking the appropriate page flag, so communicate its value to makedumpfile through the VMCOREINFO interface. There's only one small catch. Depending on how many page flags are available on a given architecture, this bit can be called PG_head or PG_compound. I sent a similar patch back in 2012, but Eric Biederman did not like using an #ifdef. So, this time I'm adding a common symbol (PG_head_mask) instead. See https://lkml.org/lkml/2012/11/28/91 for the previous version. Signed-off-by: Petr Tesarik Acked-by: Vivek Goyal Cc: Eric Biederman Cc: Paul Mackerras Cc: Fengguang Wu Cc: Benjamin Herrenschmidt Cc: Shaohua Li Cc: Alexey Kardashevskiy Cc: Sasha Levin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 3 +++ kernel/kexec.c | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3c545b48aeab..8304959ad336 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -360,6 +360,9 @@ static inline void ClearPageCompound(struct page *page) ClearPageHead(page); } #endif + +#define PG_head_mask ((1L << PG_head)) + #else /* * Reduce page flag use as much as possible by overlapping diff --git a/kernel/kexec.c b/kernel/kexec.c index 6748688813d0..369f41a94124 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1617,6 +1617,7 @@ static int __init crash_save_vmcoreinfo_init(void) #ifdef CONFIG_MEMORY_FAILURE VMCOREINFO_NUMBER(PG_hwpoison); #endif + VMCOREINFO_NUMBER(PG_head_mask); VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); arch_crash_save_vmcoreinfo(); -- cgit v1.2.3 From f3aca3d09525f87731ba6b892c9b010570bc54b4 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 23 Jun 2014 13:22:05 -0700 Subject: nmi: provide the option to issue an NMI back trace to every cpu but current Sometimes it is preferred not to use the trigger_all_cpu_backtrace() routine when one wants to avoid capturing a back trace for current. For instance if one was previously captured recently. This patch provides a new routine namely trigger_allbutself_cpu_backtrace() which offers the flexibility to issue an NMI to every cpu but current and capture a back trace accordingly. Patch x86 and sparc to support new routine. [dzickus@redhat.com: add stub in #else clause] [dzickus@redhat.com: don't print message in single processor case, wrap with get/put_cpu based on Oleg's suggestion] [sfr@canb.auug.org.au: undo C99ism] Signed-off-by: Aaron Tomlin Signed-off-by: Don Zickus Acked-by: David S. Miller Cc: Mateusz Guzik Cc: Oleg Nesterov Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/include/asm/irq_64.h | 2 +- arch/sparc/kernel/process_64.c | 18 ++++++++++++------ arch/x86/include/asm/irq.h | 2 +- arch/x86/kernel/apic/hw_nmi.c | 18 ++++++++++++++---- include/linux/nmi.h | 11 ++++++++++- 5 files changed, 38 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h index 375cffcf7dbd..91d219381306 100644 --- a/arch/sparc/include/asm/irq_64.h +++ b/arch/sparc/include/asm/irq_64.h @@ -89,7 +89,7 @@ static inline unsigned long get_softint(void) return retval; } -void arch_trigger_all_cpu_backtrace(void); +void arch_trigger_all_cpu_backtrace(bool); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace extern void *hardirq_stack[NR_CPUS]; diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index b2988f25e230..027e09986194 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -239,7 +239,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp) } } -void arch_trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(bool include_self) { struct thread_info *tp = current_thread_info(); struct pt_regs *regs = get_irq_regs(); @@ -251,16 +251,22 @@ void arch_trigger_all_cpu_backtrace(void) spin_lock_irqsave(&global_cpu_snapshot_lock, flags); - memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); - this_cpu = raw_smp_processor_id(); - __global_reg_self(tp, regs, this_cpu); + memset(global_cpu_snapshot, 0, sizeof(global_cpu_snapshot)); + + if (include_self) + __global_reg_self(tp, regs, this_cpu); smp_fetch_global_regs(); for_each_online_cpu(cpu) { - struct global_reg_snapshot *gp = &global_cpu_snapshot[cpu].reg; + struct global_reg_snapshot *gp; + + if (!include_self && cpu == this_cpu) + continue; + + gp = &global_cpu_snapshot[cpu].reg; __global_reg_poll(gp); @@ -292,7 +298,7 @@ void arch_trigger_all_cpu_backtrace(void) static void sysrq_handle_globreg(int key) { - arch_trigger_all_cpu_backtrace(); + arch_trigger_all_cpu_backtrace(true); } static struct sysrq_key_op sparc_globalreg_op = { diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index cb6cfcd034cf..a80cbb88ea91 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -43,7 +43,7 @@ extern int vector_used_by_percpu_irq(unsigned int vector); extern void init_ISA_irqs(void); #ifdef CONFIG_X86_LOCAL_APIC -void arch_trigger_all_cpu_backtrace(void); +void arch_trigger_all_cpu_backtrace(bool); #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace #endif diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index c3fcb5de5083..6a1e71bde323 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -33,31 +33,41 @@ static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly; /* "in progress" flag of arch_trigger_all_cpu_backtrace */ static unsigned long backtrace_flag; -void arch_trigger_all_cpu_backtrace(void) +void arch_trigger_all_cpu_backtrace(bool include_self) { int i; + int cpu = get_cpu(); - if (test_and_set_bit(0, &backtrace_flag)) + if (test_and_set_bit(0, &backtrace_flag)) { /* * If there is already a trigger_all_cpu_backtrace() in progress * (backtrace_flag == 1), don't output double cpu dump infos. */ + put_cpu(); return; + } cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask); + if (!include_self) + cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask)); - printk(KERN_INFO "sending NMI to all CPUs:\n"); - apic->send_IPI_all(NMI_VECTOR); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { + pr_info("sending NMI to %s CPUs:\n", + (include_self ? "all" : "other")); + apic->send_IPI_mask(to_cpumask(backtrace_mask), NMI_VECTOR); + } /* Wait for up to 10 seconds for all CPUs to do the backtrace */ for (i = 0; i < 10 * 1000; i++) { if (cpumask_empty(to_cpumask(backtrace_mask))) break; mdelay(1); + touch_softlockup_watchdog(); } clear_bit(0, &backtrace_flag); smp_mb__after_atomic(); + put_cpu(); } static int diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 6a45fb583ff1..a17ab6398d7c 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -32,15 +32,24 @@ static inline void touch_nmi_watchdog(void) #ifdef arch_trigger_all_cpu_backtrace static inline bool trigger_all_cpu_backtrace(void) { - arch_trigger_all_cpu_backtrace(); + arch_trigger_all_cpu_backtrace(true); return true; } +static inline bool trigger_allbutself_cpu_backtrace(void) +{ + arch_trigger_all_cpu_backtrace(false); + return true; +} #else static inline bool trigger_all_cpu_backtrace(void) { return false; } +static inline bool trigger_allbutself_cpu_backtrace(void) +{ + return false; +} #endif #ifdef CONFIG_LOCKUP_DETECTOR -- cgit v1.2.3 From ed235875e2ca983197831337a986f0517074e1a0 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 23 Jun 2014 13:22:05 -0700 Subject: kernel/watchdog.c: print traces for all cpus on lockup detection A 'softlockup' is defined as a bug that causes the kernel to loop in kernel mode for more than a predefined period to time, without giving other tasks a chance to run. Currently, upon detection of this condition by the per-cpu watchdog task, debug information (including a stack trace) is sent to the system log. On some occasions, we have observed that the "victim" rather than the actual "culprit" (i.e. the owner/holder of the contended resource) is reported to the user. Often this information has proven to be insufficient to assist debugging efforts. To avoid loss of useful debug information, for architectures which support NMI, this patch makes it possible to improve soft lockup reporting. This is accomplished by issuing an NMI to each cpu to obtain a stack trace. If NMI is not supported we just revert back to the old method. A sysctl and boot-time parameter is available to toggle this feature. [dzickus@redhat.com: add CONFIG_SMP in certain areas] [akpm@linux-foundation.org: additional CONFIG_SMP=n optimisations] [mq@suse.cz: fix warning] Signed-off-by: Aaron Tomlin Signed-off-by: Don Zickus Cc: David S. Miller Cc: Mateusz Guzik Cc: Oleg Nesterov Signed-off-by: Jan Moskyto Matejka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 5 +++++ Documentation/sysctl/kernel.txt | 17 ++++++++++++++++ include/linux/nmi.h | 1 + kernel/sysctl.c | 11 +++++++++++ kernel/watchdog.c | 39 +++++++++++++++++++++++++++++++++++++ 5 files changed, 73 insertions(+) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 884904975d0b..c1b9aa8c5a52 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3130,6 +3130,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. [KNL] Should the soft-lockup detector generate panics. Format: + softlockup_all_cpu_backtrace= + [KNL] Should the soft-lockup detector generate + backtraces on all cpus. + Format: + sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/laptops/sonypi.txt diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 708bb7f1b7e0..c14374e71775 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -75,6 +75,7 @@ show up in /proc/sys/kernel: - shmall - shmmax [ sysv ipc ] - shmmni +- softlockup_all_cpu_backtrace - stop-a [ SPARC only ] - sysrq ==> Documentation/sysrq.txt - sysctl_writes_strict @@ -783,6 +784,22 @@ via the /proc/sys interface: ============================================================== +softlockup_all_cpu_backtrace: + +This value controls the soft lockup detector thread's behavior +when a soft lockup condition is detected as to whether or not +to gather further debug information. If enabled, each cpu will +be issued an NMI and instructed to capture stack trace. + +This feature is only applicable for architectures which support +NMI. + +0: do nothing. This is the default behavior. + +1: on detection capture more debug information. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which diff --git a/include/linux/nmi.h b/include/linux/nmi.h index a17ab6398d7c..447775ee2c4b 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -57,6 +57,7 @@ int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(int watchdog_thresh); extern int watchdog_user_enabled; extern int watchdog_thresh; +extern int sysctl_softlockup_all_cpu_backtrace; struct ctl_table; extern int proc_dowatchdog(struct ctl_table *, int , void __user *, size_t *, loff_t *); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 075d1903138f..75b22e22a72c 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -860,6 +860,17 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#ifdef CONFIG_SMP + { + .procname = "softlockup_all_cpu_backtrace", + .data = &sysctl_softlockup_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SMP */ { .procname = "nmi_watchdog", .data = &watchdog_user_enabled, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 30e482240dae..c3319bd1b040 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -31,6 +31,12 @@ int watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; +#ifdef CONFIG_SMP +int __read_mostly sysctl_softlockup_all_cpu_backtrace; +#else +#define sysctl_softlockup_all_cpu_backtrace 0 +#endif + static int __read_mostly watchdog_running; static u64 __read_mostly sample_period; @@ -47,6 +53,7 @@ static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif +static unsigned long soft_lockup_nmi_warn; /* boot commands */ /* @@ -95,6 +102,15 @@ static int __init nosoftlockup_setup(char *str) } __setup("nosoftlockup", nosoftlockup_setup); /* */ +#ifdef CONFIG_SMP +static int __init softlockup_all_cpu_backtrace_setup(char *str) +{ + sysctl_softlockup_all_cpu_backtrace = + !!simple_strtol(str, NULL, 0); + return 1; +} +__setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); +#endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- @@ -271,6 +287,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; + int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; /* kick the hardlockup detector */ watchdog_interrupt_count(); @@ -317,6 +334,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) if (__this_cpu_read(soft_watchdog_warn) == true) return HRTIMER_RESTART; + if (softlockup_all_cpu_backtrace) { + /* Prevent multiple soft-lockup reports if one cpu is already + * engaged in dumping cpu back traces + */ + if (test_and_set_bit(0, &soft_lockup_nmi_warn)) { + /* Someone else will report us. Let's give up */ + __this_cpu_write(soft_watchdog_warn, true); + return HRTIMER_RESTART; + } + } + printk(KERN_EMERG "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); @@ -327,6 +355,17 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) else dump_stack(); + if (softlockup_all_cpu_backtrace) { + /* Avoid generating two back traces for current + * given that one is already made above + */ + trigger_allbutself_cpu_backtrace(); + + clear_bit(0, &soft_lockup_nmi_warn); + /* Barrier to sync with other cpus */ + smp_mb__after_atomic(); + } + if (softlockup_panic) panic("softlockup: hung tasks"); __this_cpu_write(soft_watchdog_warn, true); -- cgit v1.2.3 From 3a4b0eda8e4b27e6aca86f9f4d327c1070815e30 Mon Sep 17 00:00:00 2001 From: Gu Zheng Date: Tue, 24 Jun 2014 18:10:26 +0800 Subject: bio: remove unused macro bip_vec_idx() Macro bip_vec_idx() was used by bio integrity originally, but no longer used now. So remove it. Signed-off-by: Gu Zheng Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 5a645769f020..f91decbca96b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -644,10 +644,6 @@ struct biovec_slab { #if defined(CONFIG_BLK_DEV_INTEGRITY) - - -#define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) - #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) -- cgit v1.2.3 From 66cb45aa41315d1d9972cada354fbdf7870d7714 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 24 Jun 2014 16:22:24 -0600 Subject: block: add support for limiting gaps in SG lists Another restriction inherited for NVMe - those devices don't support SG lists that have "gaps" in them. Gaps refers to cases where the previous SG entry doesn't end on a page boundary. For NVMe, all SG entries must start at offset 0 (except the first) and end on a page boundary (except the last). Signed-off-by: Jens Axboe --- block/bio.c | 8 ++++++++ block/blk-merge.c | 10 ++++++++++ include/linux/bio.h | 9 +++++++++ include/linux/blkdev.h | 1 + 4 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 8c2e55e39a1b..0ec61c9e536c 100644 --- a/block/bio.c +++ b/block/bio.c @@ -746,6 +746,14 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page goto done; } + + /* + * If the queue doesn't support SG gaps and adding this + * offset would create a gap, disallow it. + */ + if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS) && + bvec_gap_to_prev(prev, offset)) + return 0; } if (bio->bi_vcnt >= bio->bi_max_vecs) diff --git a/block/blk-merge.c b/block/blk-merge.c index b3bf0df0f4c2..54535831f1e1 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -568,6 +568,8 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq, bool blk_rq_merge_ok(struct request *rq, struct bio *bio) { + struct request_queue *q = rq->q; + if (!rq_mergeable(rq) || !bio_mergeable(bio)) return false; @@ -591,6 +593,14 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) !blk_write_same_mergeable(rq->bio, bio)) return false; + if (q->queue_flags & (1 << QUEUE_FLAG_SG_GAPS)) { + struct bio_vec *bprev; + + bprev = &rq->biotail->bi_io_vec[bio->bi_vcnt - 1]; + if (bvec_gap_to_prev(bprev, bio->bi_io_vec[0].bv_offset)) + return false; + } + return true; } diff --git a/include/linux/bio.h b/include/linux/bio.h index f91decbca96b..d2633ee099d9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -186,6 +186,15 @@ static inline void *bio_data(struct bio *bio) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) +/* + * Check if adding a bio_vec after bprv with offset would create a gap in + * the SG list. Most drivers don't care about this, but some do. + */ +static inline bool bvec_gap_to_prev(struct bio_vec *bprv, unsigned int offset) +{ + return offset || ((bprv->bv_offset + bprv->bv_len) & (PAGE_SIZE - 1)); +} + #define bio_io_error(bio) bio_endio((bio), -EIO) /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 713f8b62b435..8699bcf5f099 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -512,6 +512,7 @@ struct request_queue { #define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ #define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ +#define QUEUE_FLAG_SG_GAPS 22 /* queue doesn't support SG gaps */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ -- cgit v1.2.3 From 0b86dbf675e0170a191a9ca18e5e99fd39a678c0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 23 Jun 2014 08:44:40 +0100 Subject: Fix 32-bit regression in block device read(2) blkdev_read_iter() wants to cap the iov_iter by the amount of data remaining to the end of device. That's what iov_iter_truncate() is for (trim iter->count if it's above the given limit). So far, so good, but the argument of iov_iter_truncate() is size_t, so on 32bit boxen (in case of a large device) we end up with that upper limit truncated down to 32 bits *before* comparing it with iter->count. Easily fixed by making iov_iter_truncate() take 64bit argument - it does the right thing after such change (we only reach the assignment in there when the current value of iter->count is greater than the limit, i.e. for anything that would get truncated we don't reach the assignment at all) and that argument is not the new value of iter->count - it's an upper limit for such. The overhead of passing u64 is not an issue - the thing is inlined, so callers passing size_t won't pay any penalty. Reported-and-tested-by: Theodore Tso Signed-off-by: Al Viro Tested-by: Alan Cox Tested-by: Bruno Wolff III Signed-off-by: Linus Torvalds --- include/linux/uio.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index e2231e47cec1..d54985e0705e 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -94,8 +94,20 @@ static inline size_t iov_iter_count(struct iov_iter *i) return i->count; } -static inline void iov_iter_truncate(struct iov_iter *i, size_t count) +/* + * Cap the iov_iter by given limit; note that the second argument is + * *not* the new size - it's upper limit for such. Passing it a value + * greater than the amount of data in iov_iter is fine - it'll just do + * nothing in that case. + */ +static inline void iov_iter_truncate(struct iov_iter *i, u64 count) { + /* + * count doesn't have to fit in size_t - comparison extends both + * operands to u64 here and any value that would be truncated by + * conversion in assignement is by definition greater than all + * values of size_t, including old i->count. + */ if (i->count > count) i->count = count; } -- cgit v1.2.3 From ac5ccdba3a1659b3517e7e99ef7d35a6a2d77cf4 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 19 Jun 2014 21:22:56 +0300 Subject: iovec: move memcpy_from/toiovecend to lib/iovec.c ERROR: "memcpy_fromiovecend" [drivers/vhost/vhost_scsi.ko] undefined! commit 9f977ef7b671f6169eca78bf40f230fe84b7c7e5 vhost-scsi: Include prot_bytes into expected data transfer length in target-pending makes drivers/vhost/scsi.c call memcpy_fromiovecend(). This function is not available when CONFIG_NET is not enabled. socket.h already includes uio.h, so no callers need updating. Reported-by: Randy Dunlap Cc: Stephen Rothwell Cc: "David S. Miller" Signed-off-by: David S. Miller Signed-off-by: Michael S. Tsirkin Signed-off-by: Nicholas Bellinger --- include/linux/socket.h | 4 ---- include/linux/uio.h | 5 ++++- lib/iovec.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++ net/core/iovec.c | 55 -------------------------------------------------- 4 files changed, 59 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 8e98297f1388..ec538fc287a6 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -305,8 +305,6 @@ struct ucred { /* IPX options */ #define IPX_TYPE 1 -extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len); extern int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov, int offset, @@ -315,8 +313,6 @@ extern unsigned long iov_pages(const struct iovec *iov, int offset, unsigned long nr_segs); extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode); -extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, - int offset, int len); extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); diff --git a/include/linux/uio.h b/include/linux/uio.h index e2231e47cec1..04c8c4bb4927 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -111,6 +111,9 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); - +int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len); +int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, + int offset, int len); #endif diff --git a/lib/iovec.c b/lib/iovec.c index 454baa88bf27..7a7c2da4cddf 100644 --- a/lib/iovec.c +++ b/lib/iovec.c @@ -51,3 +51,58 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) return 0; } EXPORT_SYMBOL(memcpy_toiovec); + +/* + * Copy kernel to iovec. Returns -EFAULT on error. + */ + +int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, + int offset, int len) +{ + int copy; + for (; len > 0; ++iov) { + /* Skip over the finished iovecs */ + if (unlikely(offset >= iov->iov_len)) { + offset -= iov->iov_len; + continue; + } + copy = min_t(unsigned int, iov->iov_len - offset, len); + if (copy_to_user(iov->iov_base + offset, kdata, copy)) + return -EFAULT; + offset = 0; + kdata += copy; + len -= copy; + } + + return 0; +} +EXPORT_SYMBOL(memcpy_toiovecend); + +/* + * Copy iovec to kernel. Returns -EFAULT on error. + */ + +int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len) +{ + /* Skip over the finished iovecs */ + while (offset >= iov->iov_len) { + offset -= iov->iov_len; + iov++; + } + + while (len > 0) { + u8 __user *base = iov->iov_base + offset; + int copy = min_t(unsigned int, len, iov->iov_len - offset); + + offset = 0; + if (copy_from_user(kdata, base, copy)) + return -EFAULT; + len -= copy; + kdata += copy; + iov++; + } + + return 0; +} +EXPORT_SYMBOL(memcpy_fromiovecend); diff --git a/net/core/iovec.c b/net/core/iovec.c index b61869429f4c..827dd6beb49c 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -74,61 +74,6 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *a return err; } -/* - * Copy kernel to iovec. Returns -EFAULT on error. - */ - -int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, - int offset, int len) -{ - int copy; - for (; len > 0; ++iov) { - /* Skip over the finished iovecs */ - if (unlikely(offset >= iov->iov_len)) { - offset -= iov->iov_len; - continue; - } - copy = min_t(unsigned int, iov->iov_len - offset, len); - if (copy_to_user(iov->iov_base + offset, kdata, copy)) - return -EFAULT; - offset = 0; - kdata += copy; - len -= copy; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovecend); - -/* - * Copy iovec to kernel. Returns -EFAULT on error. - */ - -int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, - int offset, int len) -{ - /* Skip over the finished iovecs */ - while (offset >= iov->iov_len) { - offset -= iov->iov_len; - iov++; - } - - while (len > 0) { - u8 __user *base = iov->iov_base + offset; - int copy = min_t(unsigned int, len, iov->iov_len - offset); - - offset = 0; - if (copy_from_user(kdata, base, copy)) - return -EFAULT; - len -= copy; - kdata += copy; - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_fromiovecend); - /* * And now for the all-in-one: copy and checksum from a user iovec * directly to a datagram -- cgit v1.2.3 From 6955b58254c2bcee8a7b55ce06468a645dc98ec5 Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 19 Apr 2014 11:18:01 +0100 Subject: component: add support for component match array Add support for generating a set of component matches at master probe time, and submitting them to the component layer. This allows the component layer to perform the matches internally without needing to call into the master driver, and allows for further restructuring of the component helper. Acked-by: Laurent Pinchart Signed-off-by: Russell King --- drivers/base/component.c | 120 ++++++++++++++++++++++++++++++++++++++++++++-- include/linux/component.h | 7 +++ 2 files changed, 124 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/component.c b/drivers/base/component.c index 55813e91bf0d..b4236daed4fa 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -18,6 +18,15 @@ #include #include +struct component_match { + size_t alloc; + size_t num; + struct { + void *data; + int (*fn)(struct device *, void *); + } compare[0]; +}; + struct master { struct list_head node; struct list_head components; @@ -25,6 +34,7 @@ struct master { const struct component_master_ops *ops; struct device *dev; + struct component_match *match; }; struct component { @@ -96,6 +106,34 @@ int component_master_add_child(struct master *master, } EXPORT_SYMBOL_GPL(component_master_add_child); +static int find_components(struct master *master) +{ + struct component_match *match = master->match; + size_t i; + int ret = 0; + + if (!match) { + /* + * Search the list of components, looking for components that + * belong to this master, and attach them to the master. + */ + return master->ops->add_components(master->dev, master); + } + + /* + * Scan the array of match functions and attach + * any components which are found to this master. + */ + for (i = 0; i < match->num; i++) { + ret = component_master_add_child(master, + match->compare[i].fn, + match->compare[i].data); + if (ret) + break; + } + return ret; +} + /* Detach all attached components from this master */ static void master_remove_components(struct master *master) { @@ -128,7 +166,7 @@ static int try_to_bring_up_master(struct master *master, * Search the list of components, looking for components that * belong to this master, and attach them to the master. */ - if (master->ops->add_components(master->dev, master)) { + if (find_components(master)) { /* Failed to find all components */ ret = 0; goto out; @@ -186,18 +224,87 @@ static void take_down_master(struct master *master) master_remove_components(master); } -int component_master_add(struct device *dev, - const struct component_master_ops *ops) +static size_t component_match_size(size_t num) +{ + return offsetof(struct component_match, compare[num]); +} + +static struct component_match *component_match_realloc(struct device *dev, + struct component_match *match, size_t num) +{ + struct component_match *new; + + if (match && match->alloc == num) + return match; + + new = devm_kmalloc(dev, component_match_size(num), GFP_KERNEL); + if (!new) + return ERR_PTR(-ENOMEM); + + if (match) { + memcpy(new, match, component_match_size(min(match->num, num))); + devm_kfree(dev, match); + } else { + new->num = 0; + } + + new->alloc = num; + + return new; +} + +/* + * Add a component to be matched. + * + * The match array is first created or extended if necessary. + */ +void component_match_add(struct device *dev, struct component_match **matchptr, + int (*compare)(struct device *, void *), void *compare_data) +{ + struct component_match *match = *matchptr; + + if (IS_ERR(match)) + return; + + if (!match || match->num == match->alloc) { + size_t new_size = match ? match->alloc + 16 : 15; + + match = component_match_realloc(dev, match, new_size); + + *matchptr = match; + + if (IS_ERR(match)) + return; + } + + match->compare[match->num].fn = compare; + match->compare[match->num].data = compare_data; + match->num++; +} +EXPORT_SYMBOL(component_match_add); + +int component_master_add_with_match(struct device *dev, + const struct component_master_ops *ops, + struct component_match *match) { struct master *master; int ret; + if (ops->add_components && match) + return -EINVAL; + + /* Reallocate the match array for its true size */ + match = component_match_realloc(dev, match, match->num); + if (IS_ERR(match)) + return PTR_ERR(match); + master = kzalloc(sizeof(*master), GFP_KERNEL); if (!master) return -ENOMEM; master->dev = dev; master->ops = ops; + master->match = match; INIT_LIST_HEAD(&master->components); /* Add to the list of available masters. */ @@ -215,6 +322,13 @@ int component_master_add(struct device *dev, return ret < 0 ? ret : 0; } +EXPORT_SYMBOL_GPL(component_master_add_with_match); + +int component_master_add(struct device *dev, + const struct component_master_ops *ops) +{ + return component_master_add_with_match(dev, ops, NULL); +} EXPORT_SYMBOL_GPL(component_master_add); void component_master_del(struct device *dev, diff --git a/include/linux/component.h b/include/linux/component.h index 68870182ca1e..c00dcc302611 100644 --- a/include/linux/component.h +++ b/include/linux/component.h @@ -29,4 +29,11 @@ void component_master_del(struct device *, int component_master_add_child(struct master *master, int (*compare)(struct device *, void *), void *compare_data); +struct component_match; + +int component_master_add_with_match(struct device *, + const struct component_master_ops *, struct component_match *); +void component_match_add(struct device *, struct component_match **, + int (*compare)(struct device *, void *), void *compare_data); + #endif -- cgit v1.2.3