In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can tget driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in <30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* |head -1 |xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in< 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/*| head -1| xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the followingvulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter inblk_mq_mark_tag_wait() and wake upnothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue canbereproduced by runningthe following test in loop,andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1| xargs basename`fio --filename=/dev/ $dev--direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100--numjobs=40 --time_based --name=test --ioengine=libaioFixthe issue by adding oneexplicit barrier in blk_mq_mark_tag_wait(),whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
IntheLinuxkernel,thefollowingvulnerability has been resolved:blk-mq: fixIO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing,meantimeblk_mq_mark_tag_wait() cant get driver tag successfully.This issue can be reproduced by running the following testinloop, andfio hang canbe observed in < 30min whenrunning it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based--name=test --ioengine=libaioFix the issue by addingone explicit barrier inblk_mq_mark_tag_wait(),whichis just fine in case of running out oftag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop. modprobe -r scsi_debug modprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4 dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename` fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
| linux | | https://git.kernel.org/linus/5266caaf5660529e3da53004b8b7174cab6374ed | https://git.kernel.org/linus/1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 | ubuntu |
</details>
二、漏洞分析结构反馈
影响性分析说明：
In the Linux kernel, the following vulnerability has been resolved:blk-mq: fix IO hang from sbitmap wakeup raceIn blk_mq_mark_tag_wait(), __add_wait_queue() may be re-orderedwith the following blk_mq_get_driver_tag() in case of getting drivertag failure.Then in __sbitmap_queue_wake_up(), waitqueue_active() may not observethe added waiter in blk_mq_mark_tag_wait() and wake up nothing, meantimeblk_mq_mark_tag_wait() can t get driver tag successfully.This issue can be reproduced by running the following test in loop, andfio hang can be observed in < 30min when running it on my test VMin laptop.modprobe -r scsi_debugmodprobe scsi_debug delay=0 dev_size_mb=4096 max_queue=1 host_max_queue=1 submit_queues=4dev=`ls -d /sys/bus/pseudo/drivers/scsi_debug/adapter*/host*/target*/*/block/* | head -1 | xargs basename`fio --filename=/dev/ $dev --direct=1 --rw=randrw --bs=4k --iodepth=1 --runtime=100 --numjobs=40 --time_based --name=test --ioengine=libaioFix the issue by adding one explicit barrier in blk_mq_mark_tag_wait(), whichis just fine in case of running out of tag.
