From b6f8fec4448aa52a8c36a392aa1ca2ea99acd460 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Mar 2017 17:48:31 +0100 Subject: block: Allow bdi re-registration SCSI can call device_add_disk() several times for one request queue when a device in unbound and bound, creating new gendisk each time. This will lead to bdi being repeatedly registered and unregistered. This was not a big problem until commit 165a5e22fafb "block: Move bdi_unregister() to del_gendisk()" since bdi was only registered repeatedly (bdi_register() handles repeated calls fine, only we ended up leaking reference to gendisk due to overwriting bdi->owner) but unregistered only in blk_cleanup_queue() which didn't get called repeatedly. After 165a5e22fafb we were doing correct bdi_register() - bdi_unregister() cycles however bdi_unregister() is not prepared for it. So make sure bdi_unregister() cleans up bdi in such a way that it is prepared for a possible following bdi_register() call. An easy way to provoke this behavior is to enable CONFIG_DEBUG_TEST_DRIVER_REMOVE and use scsi_debug driver to create a scsi disk which immediately hangs without this fix. Fixes: 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 Signed-off-by: Jan Kara Tested-by: Omar Sandoval Signed-off-by: Jens Axboe --- mm/backing-dev.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'mm') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6d861d090e9f..6ac932210f56 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -710,6 +710,11 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi) */ atomic_dec(&bdi->usage_cnt); wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); + /* + * Grab back our reference so that we hold it when @bdi gets + * re-registered. + */ + atomic_inc(&bdi->usage_cnt); } /** @@ -857,6 +862,8 @@ int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner) MINOR(owner->devt)); if (rc) return rc; + /* Leaking owner reference... */ + WARN_ON(bdi->owner); bdi->owner = owner; get_device(owner); return 0; -- cgit v1.2.3-59-g8ed1b From df23de55615fa7a190a85f49a950ccecdd9102f3 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 8 Mar 2017 17:48:32 +0100 Subject: bdi: Fix use-after-free in wb_congested_put() bdi_writeback_congested structures get created for each blkcg and bdi regardless whether bdi is registered or not. When they are created in unregistered bdi and the request queue (and thus bdi) is then destroyed while blkg still holds reference to bdi_writeback_congested structure, this structure will be referencing freed bdi and last wb_congested_put() will try to remove the structure from already freed bdi. With commit 165a5e22fafb "block: Move bdi_unregister() to del_gendisk()", SCSI started to destroy bdis without calling bdi_unregister() first (previously it was calling bdi_unregister() even for unregistered bdis) and thus the code detaching bdi_writeback_congested in cgwb_bdi_destroy() was not triggered and we started hitting this use-after-free bug. It is enough to boot a KVM instance with virtio-scsi device to trigger this behavior. Fix the problem by detaching bdi_writeback_congested structures in bdi_exit() instead of bdi_unregister(). This is also more logical as they can get attached to bdi regardless whether it ever got registered or not. Fixes: 165a5e22fafb127ecb5914e12e8c32a1f0d3f820 Signed-off-by: Jan Kara Tested-by: Omar Sandoval Signed-off-by: Jens Axboe --- mm/backing-dev.c | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'mm') diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6ac932210f56..c6f2a37028c2 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -683,30 +683,18 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { struct radix_tree_iter iter; - struct rb_node *rbn; void **slot; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); - radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); - - while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { - struct bdi_writeback_congested *congested = - rb_entry(rbn, struct bdi_writeback_congested, rb_node); - - rb_erase(rbn, &bdi->cgwb_congested_tree); - congested->bdi = NULL; /* mark @congested unlinked */ - } - spin_unlock_irq(&cgwb_lock); /* - * All cgwb's and their congested states must be shutdown and - * released before returning. Drain the usage counter to wait for - * all cgwb's and cgwb_congested's ever created on @bdi. + * All cgwb's must be shutdown and released before returning. Drain + * the usage counter to wait for all cgwb's ever created on @bdi. */ atomic_dec(&bdi->usage_cnt); wait_event(cgwb_release_wait, !atomic_read(&bdi->usage_cnt)); @@ -754,6 +742,21 @@ void wb_blkcg_offline(struct blkcg *blkcg) spin_unlock_irq(&cgwb_lock); } +static void cgwb_bdi_exit(struct backing_dev_info *bdi) +{ + struct rb_node *rbn; + + spin_lock_irq(&cgwb_lock); + while ((rbn = rb_first(&bdi->cgwb_congested_tree))) { + struct bdi_writeback_congested *congested = + rb_entry(rbn, struct bdi_writeback_congested, rb_node); + + rb_erase(rbn, &bdi->cgwb_congested_tree); + congested->bdi = NULL; /* mark @congested unlinked */ + } + spin_unlock_irq(&cgwb_lock); +} + #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) @@ -774,7 +777,9 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) return 0; } -static void cgwb_bdi_destroy(struct backing_dev_info *bdi) +static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { } + +static void cgwb_bdi_exit(struct backing_dev_info *bdi) { wb_congested_put(bdi->wb_congested); } @@ -905,6 +910,7 @@ static void bdi_exit(struct backing_dev_info *bdi) { WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); + cgwb_bdi_exit(bdi); } static void release_bdi(struct kref *ref) -- cgit v1.2.3-59-g8ed1b