From 23e018a1b083ecb4b8bb2fb43d58e7c19b5d7959 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 5 Oct 2009 08:52:35 +0200 Subject: block: get rid of kblock_schedule_delayed_work() It was briefly introduced to allow CFQ to to delayed scheduling, but we ended up removing that feature again. So lets kill the function and export, and just switch CFQ back to the normal work schedule since it is now passing in a '0' delay from all call sites. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25119041e034..221cecd86bd3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1172,11 +1172,7 @@ static inline void put_dev_sector(Sector p) } struct work_struct; -struct delayed_work; int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, - struct delayed_work *work, - unsigned long delay); #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) -- cgit From 316d315bffa4026f28085f6b24ebcebede370ac7 Mon Sep 17 00:00:00 2001 From: Nikanth Karthikesan Date: Tue, 6 Oct 2009 20:16:55 +0200 Subject: block: Seperate read and write statistics of in_flight requests v2 Commit a9327cac440be4d8333bba975cbbf76045096275 added seperate read and write statistics of in_flight requests. And exported the number of read and write requests in progress seperately through sysfs. But Corrado Zoccolo reported getting strange output from "iostat -kx 2". Global values for service time and utilization were garbage. For interval values, utilization was always 100%, and service time is higher than normal. So this was reverted by commit 0f78ab9899e9d6acb09d5465def618704255963b The problem was in part_round_stats_single(), I missed the following: if (now == part->stamp) return; - if (part->in_flight) { + if (part_in_flight(part)) { __part_stat_add(cpu, part, time_in_queue, part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); With this chunk included, the reported regression gets fixed. Signed-off-by: Nikanth Karthikesan -- Signed-off-by: Jens Axboe --- block/blk-core.c | 8 ++++---- block/blk-merge.c | 2 +- block/genhd.c | 4 +++- drivers/md/dm.c | 16 ++++++++++------ fs/partitions/check.c | 12 +++++++++++- include/linux/genhd.h | 21 ++++++++++++++------- 6 files changed, 43 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 73ecbed02605..ac0fa10f8fa5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -70,7 +70,7 @@ static void drive_stat_acct(struct request *rq, int new_io) part_stat_inc(cpu, part, merges[rw]); else { part_round_stats(cpu, part); - part_inc_in_flight(part); + part_inc_in_flight(part, rw); } part_stat_unlock(); @@ -1030,9 +1030,9 @@ static void part_round_stats_single(int cpu, struct hd_struct *part, if (now == part->stamp) return; - if (part->in_flight) { + if (part_in_flight(part)) { __part_stat_add(cpu, part, time_in_queue, - part->in_flight * (now - part->stamp)); + part_in_flight(part) * (now - part->stamp)); __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } part->stamp = now; @@ -1739,7 +1739,7 @@ static void blk_account_io_done(struct request *req) part_stat_inc(cpu, part, ios[rw]); part_stat_add(cpu, part, ticks[rw], duration); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rw); part_stat_unlock(); } diff --git a/block/blk-merge.c b/block/blk-merge.c index b0de8574fdc8..99cb5cf1f447 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -351,7 +351,7 @@ static void blk_account_io_merge(struct request *req) part = disk_map_sector_rcu(req->rq_disk, blk_rq_pos(req)); part_round_stats(cpu, part); - part_dec_in_flight(part); + part_dec_in_flight(part, rq_data_dir(req)); part_stat_unlock(); } diff --git a/block/genhd.c b/block/genhd.c index 5a0861da324d..517e4332cb37 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -869,6 +869,7 @@ static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, disk_alignment_offset_show, NULL); static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -888,6 +889,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_alignment_offset.attr, &dev_attr_capability.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif @@ -1053,7 +1055,7 @@ static int diskstats_show(struct seq_file *seqf, void *v) part_stat_read(hd, merges[1]), (unsigned long long)part_stat_read(hd, sectors[1]), jiffies_to_msecs(part_stat_read(hd, ticks[1])), - hd->in_flight, + part_in_flight(hd), jiffies_to_msecs(part_stat_read(hd, io_ticks)), jiffies_to_msecs(part_stat_read(hd, time_in_queue)) ); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 23e76fe0d359..376f1ab48a24 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -130,7 +130,7 @@ struct mapped_device { /* * A list of ios that arrived while we were suspended. */ - atomic_t pending; + atomic_t pending[2]; wait_queue_head_t wait; struct work_struct work; struct bio_list deferred; @@ -453,13 +453,14 @@ static void start_io_acct(struct dm_io *io) { struct mapped_device *md = io->md; int cpu; + int rw = bio_data_dir(io->bio); io->start_time = jiffies; cpu = part_stat_lock(); part_round_stats(cpu, &dm_disk(md)->part0); part_stat_unlock(); - dm_disk(md)->part0.in_flight = atomic_inc_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = atomic_inc_return(&md->pending[rw]); } static void end_io_acct(struct dm_io *io) @@ -479,8 +480,9 @@ static void end_io_acct(struct dm_io *io) * After this is decremented the bio must not be touched if it is * a barrier. */ - dm_disk(md)->part0.in_flight = pending = - atomic_dec_return(&md->pending); + dm_disk(md)->part0.in_flight[rw] = pending = + atomic_dec_return(&md->pending[rw]); + pending += atomic_read(&md->pending[rw^0x1]); /* nudge anyone waiting on suspend queue */ if (!pending) @@ -1785,7 +1787,8 @@ static struct mapped_device *alloc_dev(int minor) if (!md->disk) goto bad_disk; - atomic_set(&md->pending, 0); + atomic_set(&md->pending[0], 0); + atomic_set(&md->pending[1], 0); init_waitqueue_head(&md->wait); INIT_WORK(&md->work, dm_wq_work); init_waitqueue_head(&md->eventq); @@ -2088,7 +2091,8 @@ static int dm_wait_for_completion(struct mapped_device *md, int interruptible) break; } spin_unlock_irqrestore(q->queue_lock, flags); - } else if (!atomic_read(&md->pending)) + } else if (!atomic_read(&md->pending[0]) && + !atomic_read(&md->pending[1])) break; if (interruptible == TASK_INTERRUPTIBLE && diff --git a/fs/partitions/check.c b/fs/partitions/check.c index f38fee0311a7..7b685e10cbad 100644 --- a/fs/partitions/check.c +++ b/fs/partitions/check.c @@ -248,11 +248,19 @@ ssize_t part_stat_show(struct device *dev, part_stat_read(p, merges[WRITE]), (unsigned long long)part_stat_read(p, sectors[WRITE]), jiffies_to_msecs(part_stat_read(p, ticks[WRITE])), - p->in_flight, + part_in_flight(p), jiffies_to_msecs(part_stat_read(p, io_ticks)), jiffies_to_msecs(part_stat_read(p, time_in_queue))); } +ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct hd_struct *p = dev_to_part(dev); + + return sprintf(buf, "%8u %8u\n", p->in_flight[0], p->in_flight[1]); +} + #ifdef CONFIG_FAIL_MAKE_REQUEST ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -281,6 +289,7 @@ static DEVICE_ATTR(start, S_IRUGO, part_start_show, NULL); static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL); static DEVICE_ATTR(alignment_offset, S_IRUGO, part_alignment_offset_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); +static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -292,6 +301,7 @@ static struct attribute *part_attrs[] = { &dev_attr_size.attr, &dev_attr_alignment_offset.attr, &dev_attr_stat.attr, + &dev_attr_inflight.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7beaa21b3880..297df45ffd0a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -98,7 +98,7 @@ struct hd_struct { int make_it_fail; #endif unsigned long stamp; - int in_flight; + int in_flight[2]; #ifdef CONFIG_SMP struct disk_stats *dkstats; #else @@ -322,18 +322,23 @@ static inline void free_part_stats(struct hd_struct *part) #define part_stat_sub(cpu, gendiskp, field, subnd) \ part_stat_add(cpu, gendiskp, field, -subnd) -static inline void part_inc_in_flight(struct hd_struct *part) +static inline void part_inc_in_flight(struct hd_struct *part, int rw) { - part->in_flight++; + part->in_flight[rw]++; if (part->partno) - part_to_disk(part)->part0.in_flight++; + part_to_disk(part)->part0.in_flight[rw]++; } -static inline void part_dec_in_flight(struct hd_struct *part) +static inline void part_dec_in_flight(struct hd_struct *part, int rw) { - part->in_flight--; + part->in_flight[rw]--; if (part->partno) - part_to_disk(part)->part0.in_flight--; + part_to_disk(part)->part0.in_flight[rw]--; +} + +static inline int part_in_flight(struct hd_struct *part) +{ + return part->in_flight[0] + part->in_flight[1]; } /* block/blk-core.c */ @@ -546,6 +551,8 @@ extern ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t part_stat_show(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t part_inflight_show(struct device *dev, + struct device_attribute *attr, char *buf); #ifdef CONFIG_FAIL_MAKE_REQUEST extern ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); -- cgit From d308e38fa5467fbb523fc13e4b984375c2198c3d Mon Sep 17 00:00:00 2001 From: Wolfram Sang Date: Wed, 7 Oct 2009 13:53:11 -0700 Subject: include/linux/netdevice.h: fix nanodoc mismatch nanodoc was missing an ndo_-prefix. Signed-off-by: Wolfram Sang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 94958c109761..812a5f3c2abe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -557,7 +557,7 @@ struct netdev_queue { * Callback uses when the transmitter has not made any progress * for dev->watchdog ticks. * - * struct net_device_stats* (*get_stats)(struct net_device *dev); + * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. If not defined, the counters in dev->stats will * be used. -- cgit From c01226c3145d173a0d38f9d5b4f229cc23d99ae2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 21 Sep 2009 16:37:12 +0200 Subject: warn about use of uninstalled kernel headers User applications frequently hit problems when they try to use the kernel headers directly, rather than the exported headers. This adds an explicit warning for this case, and points to a URL holding an explanation of why this is wrong and what to do about it. Signed-off-by: Arnd Bergmann Signed-off-by: Sam Ravnborg --- include/linux/kernel.h | 6 ++++++ scripts/headers_install.pl | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d3cd23f30039..f4e3184fa054 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -659,6 +659,12 @@ extern int do_sysinfo(struct sysinfo *info); #endif /* __KERNEL__ */ +#ifndef __EXPORTED_HEADERS__ +#ifndef __KERNEL__ +#warning Attempt to use kernel headers from user space, see http://kernelnewbies.org/KernelHeaders +#endif /* __KERNEL__ */ +#endif /* __EXPORTED_HEADERS__ */ + #define SI_LOAD_SHIFT 16 struct sysinfo { long uptime; /* Seconds since boot */ diff --git a/scripts/headers_install.pl b/scripts/headers_install.pl index c6ae4052ab43..b89ca2c58fdb 100644 --- a/scripts/headers_install.pl +++ b/scripts/headers_install.pl @@ -20,7 +20,7 @@ use strict; my ($readdir, $installdir, $arch, @files) = @ARGV; -my $unifdef = "scripts/unifdef -U__KERNEL__"; +my $unifdef = "scripts/unifdef -U__KERNEL__ -D__EXPORTED_HEADERS__"; foreach my $file (@files) { local *INFILE; -- cgit From 43046b606673c9c991919ff75b980b72541e9ede Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 14 Oct 2009 09:16:42 -0700 Subject: workqueue: add 'flush_delayed_work()' to run and wait for delayed work It basically turns a delayed work into an immediate work, and then waits for it to finish. --- include/linux/workqueue.h | 1 + kernel/workqueue.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 7ef0c7b94f31..cf24c20de9e4 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -207,6 +207,7 @@ extern int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, extern void flush_workqueue(struct workqueue_struct *wq); extern void flush_scheduled_work(void); +extern void flush_delayed_work(struct delayed_work *work); extern int schedule_work(struct work_struct *work); extern int schedule_work_on(int cpu, struct work_struct *work); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index addfe2df93b1..ccefe574dcf7 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -639,6 +639,24 @@ int schedule_delayed_work(struct delayed_work *dwork, } EXPORT_SYMBOL(schedule_delayed_work); +/** + * flush_delayed_work - block until a dwork_struct's callback has terminated + * @dwork: the delayed work which is to be flushed + * + * Any timeout is cancelled, and any pending work is run immediately. + */ +void flush_delayed_work(struct delayed_work *dwork) +{ + if (del_timer(&dwork->timer)) { + struct cpu_workqueue_struct *cwq; + cwq = wq_per_cpu(keventd_wq, get_cpu()); + __queue_work(cwq, &dwork->work); + put_cpu(); + } + flush_work(&dwork->work); +} +EXPORT_SYMBOL(flush_delayed_work); + /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use -- cgit