- Linux-stable-mirror - lists.linaro.org

FAILED: patch "[PATCH] bcache: set max writeback rate when I/O request is idle" failed to apply to 4.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From ea8c5356d39048bc94bae068228f51ddbecc6b89 Mon Sep 17 00:00:00 2001 From: Coly Li <colyli(a)suse.de> Date: Thu, 9 Aug 2018 15:48:49 +0800 Subject: [PATCH] bcache: set max writeback rate when I/O request is idle Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle") allows the writeback rate to be faster if there is no I/O request on a bcache device. It works well if there is only one bcache device attached to the cache set. If there are many bcache devices attached to a cache set, it may introduce performance regression because multiple faster writeback threads of the idle bcache devices will compete the btree level locks with the bcache device who have I/O requests coming. This patch fixes the above issue by only permitting fast writebac when all bcache devices attached on the cache set are idle. And if one of the bcache devices has new I/O request coming, minimized all writeback throughput immediately and let PI controller __update_writeback_rate() to decide the upcoming writeback rate for each bcache device. Also when all bcache devices are idle, limited wrieback rate to a small number is wast of thoughput, especially when backing devices are slower non-rotation devices (e.g. SATA SSD). This patch sets a max writeback rate for each backing device if the whole cache set is idle. A faster writeback rate in idle time means new I/Os may have more available space for dirty data, and people may observe a better write performance then. Please note bcache may change its cache mode in run time, and this patch still works if the cache mode is switched from writeback mode and there is still dirty data on cache. Fixes: Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle") Cc: stable(a)vger.kernel.org #4.16+ Signed-off-by: Coly Li <colyli(a)suse.de> Tested-by: Kai Krakow <kai(a)kaishome.de> Tested-by: Stefan Priebe <s.priebe(a)profihost.ag> Cc: Michael Lyle <mlyle(a)lyle.org> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index b393b3fd06b6..05f82ff6f016 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -328,13 +328,6 @@ struct cached_dev { */ atomic_t has_dirty; - /* - * Set to zero by things that touch the backing volume-- except - * writeback. Incremented by writeback. Used to determine when to - * accelerate idle writeback. - */ - atomic_t backing_idle; - struct bch_ratelimit writeback_rate; struct delayed_work writeback_rate_update; @@ -515,6 +508,8 @@ struct cache_set { struct cache_accounting accounting; unsigned long flags; + atomic_t idle_counter; + atomic_t at_max_writeback_rate; struct cache_sb sb; @@ -524,6 +519,7 @@ struct cache_set { struct bcache_device **devices; unsigned devices_max_used; + atomic_t attached_dev_nr; struct list_head cached_devs; uint64_t cached_dev_sectors; atomic_long_t flash_dev_dirty_sectors; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 914d501ad1e0..7dbe8b6316a0 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1103,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio) generic_make_request(bio); } +static void quit_max_writeback_rate(struct cache_set *c, + struct cached_dev *this_dc) +{ + int i; + struct bcache_device *d; + struct cached_dev *dc; + + /* + * mutex bch_register_lock may compete with other parallel requesters, + * or attach/detach operations on other backing device. Waiting to + * the mutex lock may increase I/O request latency for seconds or more. + * To avoid such situation, if mutext_trylock() failed, only writeback + * rate of current cached device is set to 1, and __update_write_back() + * will decide writeback rate of other cached devices (remember now + * c->idle_counter is 0 already). + */ + if (mutex_trylock(&bch_register_lock)) { + for (i = 0; i < c->devices_max_used; i++) { + if (!c->devices[i]) + continue; + + if (UUID_FLASH_ONLY(&c->uuids[i])) + continue; + + d = c->devices[i]; + dc = container_of(d, struct cached_dev, disk); + /* + * set writeback rate to default minimum value, + * then let update_writeback_rate() to decide the + * upcoming rate. + */ + atomic_long_set(&dc->writeback_rate.rate, 1); + } + mutex_unlock(&bch_register_lock); + } else + atomic_long_set(&this_dc->writeback_rate.rate, 1); +} + /* Cached devices - read & write stuff */ static blk_qc_t cached_dev_make_request(struct request_queue *q, @@ -1120,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q, return BLK_QC_T_NONE; } - atomic_set(&dc->backing_idle, 0); - generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0); + if (likely(d->c)) { + if (atomic_read(&d->c->idle_counter)) + atomic_set(&d->c->idle_counter, 0); + /* + * If at_max_writeback_rate of cache set is true and new I/O + * comes, quit max writeback rate of all cached devices + * attached to this cache set, and set at_max_writeback_rate + * to false. + */ + if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) { + atomic_set(&d->c->at_max_writeback_rate, 0); + quit_max_writeback_rate(d->c, dc); + } + } + + generic_start_io_acct(q, + bio_op(bio), + bio_sectors(bio), + &d->disk->part0); bio_set_dev(bio, dc->bdev); bio->bi_iter.bi_sector += dc->sb.data_offset; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 1e85cbb4c159..55a37641aa95 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -696,6 +696,8 @@ static void bcache_device_detach(struct bcache_device *d) { lockdep_assert_held(&bch_register_lock); + atomic_dec(&d->c->attached_dev_nr); + if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) { struct uuid_entry *u = d->c->uuids + d->id; @@ -1144,6 +1146,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, bch_cached_dev_run(dc); bcache_device_link(&dc->disk, c, "bdev"); + atomic_inc(&c->attached_dev_nr); /* Allow the writeback thread to proceed */ up_write(&dc->writeback_lock); @@ -1696,6 +1699,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->block_bits = ilog2(sb->block_size); c->nr_uuids = bucket_bytes(c) / sizeof(struct uuid_entry); c->devices_max_used = 0; + atomic_set(&c->attached_dev_nr, 0); c->btree_pages = bucket_pages(c); if (c->btree_pages > BTREE_MAX_PAGES) c->btree_pages = max_t(int, c->btree_pages / 4, diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 3e9d3459a224..6e88142514fb 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -171,7 +171,8 @@ SHOW(__bch_cached_dev) var_printf(writeback_running, "%i"); var_print(writeback_delay); var_print(writeback_percent); - sysfs_hprint(writeback_rate, wb ? dc->writeback_rate.rate << 9 : 0); + sysfs_hprint(writeback_rate, + wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0); sysfs_hprint(io_errors, atomic_read(&dc->io_errors)); sysfs_printf(io_error_limit, "%i", dc->error_limit); sysfs_printf(io_disable, "%i", dc->io_disable); @@ -193,7 +194,9 @@ SHOW(__bch_cached_dev) * Except for dirty and target, other values should * be 0 if writeback is not running. */ - bch_hprint(rate, wb ? dc->writeback_rate.rate << 9 : 0); + bch_hprint(rate, + wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 + : 0); bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9); bch_hprint(target, dc->writeback_rate_target << 9); bch_hprint(proportional, @@ -261,8 +264,12 @@ STORE(__cached_dev) sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40); - sysfs_strtoul_clamp(writeback_rate, - dc->writeback_rate.rate, 1, INT_MAX); + if (attr == &sysfs_writeback_rate) { + int v; + + sysfs_strtoul_clamp(writeback_rate, v, 1, INT_MAX); + atomic_long_set(&dc->writeback_rate.rate, v); + } sysfs_strtoul_clamp(writeback_rate_update_seconds, dc->writeback_rate_update_seconds, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index fc479b026d6d..b15256bcf0e7 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); - d->next += div_u64(done * NSEC_PER_SEC, d->rate); + d->next += div_u64(done * NSEC_PER_SEC, atomic_long_read(&d->rate)); /* Bound the time. Don't let us fall further than 2 seconds behind * (this prevents unnecessary backlog that would make it impossible diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index cced87f8eb27..f7b0133c9d2f 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -442,7 +442,7 @@ struct bch_ratelimit { * Rate at which we want to do work, in units per second * The units here correspond to the units passed to bch_next_delay() */ - uint32_t rate; + atomic_long_t rate; }; static inline void bch_ratelimit_reset(struct bch_ratelimit *d) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 912e969fedba..481d4cf38ac0 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -104,11 +104,56 @@ static void __update_writeback_rate(struct cached_dev *dc) dc->writeback_rate_proportional = proportional_scaled; dc->writeback_rate_integral_scaled = integral_scaled; - dc->writeback_rate_change = new_rate - dc->writeback_rate.rate; - dc->writeback_rate.rate = new_rate; + dc->writeback_rate_change = new_rate - + atomic_long_read(&dc->writeback_rate.rate); + atomic_long_set(&dc->writeback_rate.rate, new_rate); dc->writeback_rate_target = target; } +static bool set_at_max_writeback_rate(struct cache_set *c, + struct cached_dev *dc) +{ + /* + * Idle_counter is increased everytime when update_writeback_rate() is + * called. If all backing devices attached to the same cache set have + * identical dc->writeback_rate_update_seconds values, it is about 6 + * rounds of update_writeback_rate() on each backing device before + * c->at_max_writeback_rate is set to 1, and then max wrteback rate set + * to each dc->writeback_rate.rate. + * In order to avoid extra locking cost for counting exact dirty cached + * devices number, c->attached_dev_nr is used to calculate the idle + * throushold. It might be bigger if not all cached device are in write- + * back mode, but it still works well with limited extra rounds of + * update_writeback_rate(). + */ + if (atomic_inc_return(&c->idle_counter) < + atomic_read(&c->attached_dev_nr) * 6) + return false; + + if (atomic_read(&c->at_max_writeback_rate) != 1) + atomic_set(&c->at_max_writeback_rate, 1); + + atomic_long_set(&dc->writeback_rate.rate, INT_MAX); + + /* keep writeback_rate_target as existing value */ + dc->writeback_rate_proportional = 0; + dc->writeback_rate_integral_scaled = 0; + dc->writeback_rate_change = 0; + + /* + * Check c->idle_counter and c->at_max_writeback_rate agagain in case + * new I/O arrives during before set_at_max_writeback_rate() returns. + * Then the writeback rate is set to 1, and its new value should be + * decided via __update_writeback_rate(). + */ + if ((atomic_read(&c->idle_counter) < + atomic_read(&c->attached_dev_nr) * 6) || + !atomic_read(&c->at_max_writeback_rate)) + return false; + + return true; +} + static void update_writeback_rate(struct work_struct *work) { struct cached_dev *dc = container_of(to_delayed_work(work), @@ -136,13 +181,20 @@ static void update_writeback_rate(struct work_struct *work) return; } - down_read(&dc->writeback_lock); - - if (atomic_read(&dc->has_dirty) && - dc->writeback_percent) - __update_writeback_rate(dc); + if (atomic_read(&dc->has_dirty) && dc->writeback_percent) { + /* + * If the whole cache set is idle, set_at_max_writeback_rate() + * will set writeback rate to a max number. Then it is + * unncessary to update writeback rate for an idle cache set + * in maximum writeback rate number(s). + */ + if (!set_at_max_writeback_rate(c, dc)) { + down_read(&dc->writeback_lock); + __update_writeback_rate(dc); + up_read(&dc->writeback_lock); + } + } - up_read(&dc->writeback_lock); /* * CACHE_SET_IO_DISABLE might be set via sysfs interface, @@ -422,27 +474,6 @@ static void read_dirty(struct cached_dev *dc) delay = writeback_delay(dc, size); - /* If the control system would wait for at least half a - * second, and there's been no reqs hitting the backing disk - * for awhile: use an alternate mode where we have at most - * one contiguous set of writebacks in flight at a time. If - * someone wants to do IO it will be quick, as it will only - * have to contend with one operation in flight, and we'll - * be round-tripping data to the backing disk as quickly as - * it can accept it. - */ - if (delay >= HZ / 2) { - /* 3 means at least 1.5 seconds, up to 7.5 if we - * have slowed way down. - */ - if (atomic_inc_return(&dc->backing_idle) >= 3) { - /* Wait for current I/Os to finish */ - closure_sync(&cl); - /* And immediately launch a new set. */ - delay = 0; - } - } - while (!kthread_should_stop() && !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) && delay) { @@ -741,7 +772,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc) dc->writeback_running = true; dc->writeback_percent = 10; dc->writeback_delay = 30; - dc->writeback_rate.rate = 1024; + atomic_long_set(&dc->writeback_rate.rate, 1024); dc->writeback_rate_minimum = 8; dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;

6 years, 10 months

1
0
0 0

WTF: patch "[PATCH] bcache: do not check return value of debugfs_create_dir()" was seriously submitted to be applied to the 4.18-stable tree?

by gregkh＠linuxfoundation.org

The patch below was submitted to be applied to the 4.18-stable tree. I fail to see how this patch meets the stable kernel rules as found at Documentation/process/stable-kernel-rules.rst. I could be totally wrong, and if so, please respond to <stable(a)vger.kernel.org> and let me know why this patch should be applied. Otherwise, it is now dropped from my patch queues, never to be seen again. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 78ac2107176baa0daf65b0fb8e561d2ed14c83ca Mon Sep 17 00:00:00 2001 From: Coly Li <colyli(a)suse.de> Date: Thu, 9 Aug 2018 15:48:42 +0800 Subject: [PATCH] bcache: do not check return value of debugfs_create_dir() Greg KH suggests that normal code should not care about debugfs. Therefore no matter successful or failed of debugfs_create_dir() execution, it is unncessary to check its return value. There are two functions called debugfs_create_dir() and check the return value, which are bch_debug_init() and closure_debug_init(). This patch changes these two functions from int to void type, and ignore return values of debugfs_create_dir(). This patch does not fix exact bug, just makes things work as they should. Signed-off-by: Coly Li <colyli(a)suse.de> Suggested-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Cc: stable(a)vger.kernel.org Cc: Kai Krakow <kai(a)kaishome.de> Cc: Kent Overstreet <kent.overstreet(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 872ef4d67711..0a3e82b0876d 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -1001,7 +1001,7 @@ void bch_open_buckets_free(struct cache_set *); int bch_cache_allocator_start(struct cache *ca); void bch_debug_exit(void); -int bch_debug_init(struct kobject *); +void bch_debug_init(struct kobject *kobj); void bch_request_exit(void); int bch_request_init(void); diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c index 0e14969182c6..618253683d40 100644 --- a/drivers/md/bcache/closure.c +++ b/drivers/md/bcache/closure.c @@ -199,11 +199,16 @@ static const struct file_operations debug_ops = { .release = single_release }; -int __init closure_debug_init(void) +void __init closure_debug_init(void) { - closure_debug = debugfs_create_file("closures", - 0400, bcache_debug, NULL, &debug_ops); - return IS_ERR_OR_NULL(closure_debug); + if (!IS_ERR_OR_NULL(bcache_debug)) + /* + * it is unnecessary to check return value of + * debugfs_create_file(), we should not care + * about this. + */ + closure_debug = debugfs_create_file( + "closures", 0400, bcache_debug, NULL, &debug_ops); } #endif diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h index 71427eb5fdae..7c2c5bc7c88b 100644 --- a/drivers/md/bcache/closure.h +++ b/drivers/md/bcache/closure.h @@ -186,13 +186,13 @@ static inline void closure_sync(struct closure *cl) #ifdef CONFIG_BCACHE_CLOSURES_DEBUG -int closure_debug_init(void); +void closure_debug_init(void); void closure_debug_create(struct closure *cl); void closure_debug_destroy(struct closure *cl); #else -static inline int closure_debug_init(void) { return 0; } +static inline void closure_debug_init(void) {} static inline void closure_debug_create(struct closure *cl) {} static inline void closure_debug_destroy(struct closure *cl) {} diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 04d146711950..12034c07257b 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -252,11 +252,12 @@ void bch_debug_exit(void) debugfs_remove_recursive(bcache_debug); } -int __init bch_debug_init(struct kobject *kobj) +void __init bch_debug_init(struct kobject *kobj) { - if (!IS_ENABLED(CONFIG_DEBUG_FS)) - return 0; - + /* + * it is unnecessary to check return value of + * debugfs_create_file(), we should not care + * about this. + */ bcache_debug = debugfs_create_dir("bcache", NULL); - return IS_ERR_OR_NULL(bcache_debug); } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index e0a92104ca23..c7ffa6ef3f82 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2345,10 +2345,12 @@ static int __init bcache_init(void) goto err; if (bch_request_init() || - bch_debug_init(bcache_kobj) || closure_debug_init() || sysfs_create_files(bcache_kobj, files)) goto err; + bch_debug_init(bcache_kobj); + closure_debug_init(); + return 0; err: bcache_exit();

6 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the" failed to apply to 3.18-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 3.18-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 54648cf1ec2d7f4b6a71767799c45676a138ca24 Mon Sep 17 00:00:00 2001 From: xiao jin <jin.xiao(a)intel.com> Date: Mon, 30 Jul 2018 14:11:12 +0800 Subject: [PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the fail case We find the memory use-after-free issue in __blk_drain_queue() on the kernel 4.14. After read the latest kernel 4.18-rc6 we think it has the same problem. Memory is allocated for q->fq in the blk_init_allocated_queue(). If the elevator init function called with error return, it will run into the fail case to free the q->fq. Then the __blk_drain_queue() uses the same memory after the free of the q->fq, it will lead to the unpredictable event. The patch is to set q->fq as NULL in the fail case of blk_init_allocated_queue(). Fixes: commit 7c94e1c157a2 ("block: introduce blk_flush_queue to drive flush machinery") Cc: <stable(a)vger.kernel.org> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche(a)wdc.com> Signed-off-by: xiao jin <jin.xiao(a)intel.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-core.c b/block/blk-core.c index 03a4ea93a5f3..23cd1b7770e7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1184,6 +1184,7 @@ int blk_init_allocated_queue(struct request_queue *q) q->exit_rq_fn(q, q->fq->flush_rq); out_free_flush_queue: blk_free_flush_queue(q->fq); + q->fq = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_init_allocated_queue);

6 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 54648cf1ec2d7f4b6a71767799c45676a138ca24 Mon Sep 17 00:00:00 2001 From: xiao jin <jin.xiao(a)intel.com> Date: Mon, 30 Jul 2018 14:11:12 +0800 Subject: [PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the fail case We find the memory use-after-free issue in __blk_drain_queue() on the kernel 4.14. After read the latest kernel 4.18-rc6 we think it has the same problem. Memory is allocated for q->fq in the blk_init_allocated_queue(). If the elevator init function called with error return, it will run into the fail case to free the q->fq. Then the __blk_drain_queue() uses the same memory after the free of the q->fq, it will lead to the unpredictable event. The patch is to set q->fq as NULL in the fail case of blk_init_allocated_queue(). Fixes: commit 7c94e1c157a2 ("block: introduce blk_flush_queue to drive flush machinery") Cc: <stable(a)vger.kernel.org> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche(a)wdc.com> Signed-off-by: xiao jin <jin.xiao(a)intel.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-core.c b/block/blk-core.c index 03a4ea93a5f3..23cd1b7770e7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1184,6 +1184,7 @@ int blk_init_allocated_queue(struct request_queue *q) q->exit_rq_fn(q, q->fq->flush_rq); out_free_flush_queue: blk_free_flush_queue(q->fq); + q->fq = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_init_allocated_queue);

6 years, 10 months

1
0
0 0

FAILED: patch "[PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 54648cf1ec2d7f4b6a71767799c45676a138ca24 Mon Sep 17 00:00:00 2001 From: xiao jin <jin.xiao(a)intel.com> Date: Mon, 30 Jul 2018 14:11:12 +0800 Subject: [PATCH] block: blk_init_allocated_queue() set q->fq as NULL in the fail case We find the memory use-after-free issue in __blk_drain_queue() on the kernel 4.14. After read the latest kernel 4.18-rc6 we think it has the same problem. Memory is allocated for q->fq in the blk_init_allocated_queue(). If the elevator init function called with error return, it will run into the fail case to free the q->fq. Then the __blk_drain_queue() uses the same memory after the free of the q->fq, it will lead to the unpredictable event. The patch is to set q->fq as NULL in the fail case of blk_init_allocated_queue(). Fixes: commit 7c94e1c157a2 ("block: introduce blk_flush_queue to drive flush machinery") Cc: <stable(a)vger.kernel.org> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Reviewed-by: Bart Van Assche <bart.vanassche(a)wdc.com> Signed-off-by: xiao jin <jin.xiao(a)intel.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> diff --git a/block/blk-core.c b/block/blk-core.c index 03a4ea93a5f3..23cd1b7770e7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1184,6 +1184,7 @@ int blk_init_allocated_queue(struct request_queue *q) q->exit_rq_fn(q, q->fq->flush_rq); out_free_flush_queue: blk_free_flush_queue(q->fq); + q->fq = NULL; return -ENOMEM; } EXPORT_SYMBOL(blk_init_allocated_queue);

6 years, 10 months

1
0
0 0

[PATCH] clk: sunxi-ng: sun4i: Set VCO and PLL bias current to lowest setting

by Chen-Yu Tsai

The default mid-level PLL bias current setting interferes with sigma delta modulation. This manifests as decreased audio quality at lower sampling rates, which sounds like radio broadcast quality, and distortion noises at sampling rates at 48 kHz or above. Changing the bias current settings to the lowest gets rid of the noise. Fixes: de3448519194 ("clk: sunxi-ng: sun4i: Use sigma-delta modulation for audio PLL") Cc: <stable(a)vger.kernel.org> # 4.15.x Signed-off-by: Chen-Yu Tsai <wens(a)csie.org> --- drivers/clk/sunxi-ng/ccu-sun4i-a10.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/clk/sunxi-ng/ccu-sun4i-a10.c b/drivers/clk/sunxi-ng/ccu-sun4i-a10.c index ffa5dac221e4..129ebd2588fd 100644 --- a/drivers/clk/sunxi-ng/ccu-sun4i-a10.c +++ b/drivers/clk/sunxi-ng/ccu-sun4i-a10.c @@ -1434,8 +1434,16 @@ static void __init sun4i_ccu_init(struct device_node *node, return; } - /* Force the PLL-Audio-1x divider to 1 */ val = readl(reg + SUN4I_PLL_AUDIO_REG); + + /* + * Force VCO and PLL bias current to lowest setting. Higher + * settings interfere with sigma-delta modulation and result + * in audible noise and distortions when using SPDIF or I2S. + */ + val &= ~GENMASK(25, 16); + + /* Force the PLL-Audio-1x divider to 1 */ val &= ~GENMASK(29, 26); writel(val | (1 << 26), reg + SUN4I_PLL_AUDIO_REG); -- 2.19.0.rc1

6 years, 10 months

2
1
0 0

rcu: Make expedited GPs handle CPU 0 being offline

by Paul E. McKenney

Hello! Please apply the following commit to the v4.18 -stable tree: rcu: Make expedited GPs handle CPU 0 being offline fcc63543650150629c8a873cbef3578770acecd9 This patch fixes a v4.18 regression that is causing the RISC-V people (CCed) some trouble. It is a small patch and has been tested in the failing situation running v4.18 by Atish Patra and Andreas Schwab (both CCed). Please let me know if more information is required. Thanx, Paul

6 years, 10 months

2
1
0 0

[PATCH AUTOSEL 4.4 01/30] usb: usbtest: use irqsave() in USB's complete callback

by Sasha Levin

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> [ Upstream commit 6f3fde684d0232e66ada3410f016a58e09a87689 ] The USB completion callback does not disable interrupts while acquiring the lock. We want to remove the local_irq_disable() invocation from __usb_hcd_giveback_urb() and therefore it is required for the callback handler to disable the interrupts while acquiring the lock. The callback may be invoked either in IRQ or BH context depending on the USB host controller. Use the _irqsave() variant of the locking primitives. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <alexander.levin(a)microsoft.com> --- drivers/usb/misc/usbtest.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index bc92a498ec03..4632a29d5403 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -1053,11 +1053,12 @@ static void ctrl_complete(struct urb *urb) struct usb_ctrlrequest *reqp; struct subcase *subcase; int status = urb->status; + unsigned long flags; reqp = (struct usb_ctrlrequest *)urb->setup_packet; subcase = container_of(reqp, struct subcase, setup); - spin_lock(&ctx->lock); + spin_lock_irqsave(&ctx->lock, flags); ctx->count--; ctx->pending--; @@ -1156,7 +1157,7 @@ static void ctrl_complete(struct urb *urb) /* signal completion when nothing's queued */ if (ctx->pending == 0) complete(&ctx->complete); - spin_unlock(&ctx->lock); + spin_unlock_irqrestore(&ctx->lock, flags); } static int @@ -1832,8 +1833,9 @@ struct transfer_context { static void complicated_callback(struct urb *urb) { struct transfer_context *ctx = urb->context; + unsigned long flags; - spin_lock(&ctx->lock); + spin_lock_irqsave(&ctx->lock, flags); ctx->count--; ctx->packet_count += urb->number_of_packets; @@ -1873,7 +1875,7 @@ static void complicated_callback(struct urb *urb) complete(&ctx->done); } done: - spin_unlock(&ctx->lock); + spin_unlock_irqrestore(&ctx->lock, flags); } static struct urb *iso_alloc_urb( -- 2.17.1

6 years, 10 months

2
30
0 0

[PATCH AUTOSEL 4.9 01/43] usb: usbtest: use irqsave() in USB's complete callback

by Sasha Levin

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> [ Upstream commit 6f3fde684d0232e66ada3410f016a58e09a87689 ] The USB completion callback does not disable interrupts while acquiring the lock. We want to remove the local_irq_disable() invocation from __usb_hcd_giveback_urb() and therefore it is required for the callback handler to disable the interrupts while acquiring the lock. The callback may be invoked either in IRQ or BH context depending on the USB host controller. Use the _irqsave() variant of the locking primitives. Cc: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Acked-by: Alan Stern <stern(a)rowland.harvard.edu> Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Sasha Levin <alexander.levin(a)microsoft.com> --- drivers/usb/misc/usbtest.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index e31f72b3a22c..cc1dad83ec1d 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -1080,11 +1080,12 @@ static void ctrl_complete(struct urb *urb) struct usb_ctrlrequest *reqp; struct subcase *subcase; int status = urb->status; + unsigned long flags; reqp = (struct usb_ctrlrequest *)urb->setup_packet; subcase = container_of(reqp, struct subcase, setup); - spin_lock(&ctx->lock); + spin_lock_irqsave(&ctx->lock, flags); ctx->count--; ctx->pending--; @@ -1183,7 +1184,7 @@ static void ctrl_complete(struct urb *urb) /* signal completion when nothing's queued */ if (ctx->pending == 0) complete(&ctx->complete); - spin_unlock(&ctx->lock); + spin_unlock_irqrestore(&ctx->lock, flags); } static int @@ -1859,8 +1860,9 @@ struct transfer_context { static void complicated_callback(struct urb *urb) { struct transfer_context *ctx = urb->context; + unsigned long flags; - spin_lock(&ctx->lock); + spin_lock_irqsave(&ctx->lock, flags); ctx->count--; ctx->packet_count += urb->number_of_packets; @@ -1900,7 +1902,7 @@ static void complicated_callback(struct urb *urb) complete(&ctx->done); } done: - spin_unlock(&ctx->lock); + spin_unlock_irqrestore(&ctx->lock, flags); } static struct urb *iso_alloc_urb( -- 2.17.1

6 years, 10 months

2
43
0 0

[PATCH AUTOSEL 3.18 01/19] ALSA: msnd: Fix the default sample sizes

by Sasha Levin

From: Takashi Iwai <tiwai(a)suse.de> [ Upstream commit 7c500f9ea139d0c9b80fdea5a9c911db3166ea54 ] The default sample sizes set by msnd driver are bogus; it sets ALSA PCM format, not the actual bit width. Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Signed-off-by: Sasha Levin <alexander.levin(a)microsoft.com> --- sound/isa/msnd/msnd_pinnacle.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c index cf70dba80124..741714332365 100644 --- a/sound/isa/msnd/msnd_pinnacle.c +++ b/sound/isa/msnd/msnd_pinnacle.c @@ -82,10 +82,10 @@ static void set_default_audio_parameters(struct snd_msnd *chip) { - chip->play_sample_size = DEFSAMPLESIZE; + chip->play_sample_size = snd_pcm_format_width(DEFSAMPLESIZE); chip->play_sample_rate = DEFSAMPLERATE; chip->play_channels = DEFCHANNELS; - chip->capture_sample_size = DEFSAMPLESIZE; + chip->capture_sample_size = snd_pcm_format_width(DEFSAMPLESIZE); chip->capture_sample_rate = DEFSAMPLERATE; chip->capture_channels = DEFCHANNELS; } -- 2.17.1

6 years, 10 months

1
18
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror