If userspace reads the buffer via blockdev while mounting,
sb_getblk()+modify can race with buffer read via blockdev.
For example,
FS userspace
bh = sb_getblk()
modify bh->b_data
read
Some devices may skip blk_pm_runtime_init() and have null pointer
in its request_queue->dev. For example, SCSI devices of UFS Well-Known
LUNs.
Currently the null pointer is checked by the user of
blk_set_runtime_active(), i.e., scsi_dev_type_resume(). It is better to
check it by blk_set_runtime_ac
Some devices may skip blk_pm_runtime_init() and have null pointer
in its request_queue->dev. For example, SCSI devices of UFS Well-Known
LUNs.
Currently the null pointer is checked by the user of
blk_set_runtime_active(), i.e., scsi_dev_type_resume(). It is better to
check it by blk_set_runtime_ac
Currently blk_set_runtime_active() is checking if q->dev is null by
itself, thus remove the same checking in its user: scsi_dev_type_resume().
Signed-off-by: Stanley Chu
---
drivers/scsi/scsi_pm.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/scsi/scsi_pm.c b/driv
Max,
> I guess Type 1 and Type 3 mirrors can work because Type 3 doesn't have
> a ref tag, right ?
It will work but you'll lose ref tag checking on the Type 3 side of the
mirror. So not exactly desirable. And in our experience, the ref tag is
hugely important.
Also, there are probably some hea
On 2019/9/10 23:56, Mike Christie wrote:
On 09/10/2019 01:36 AM, xiu...@redhat.com wrote:
From: Xiubo Li
The followed code will do the same check, and this part is redandant.
Signed-off-by: Xiubo Li
---
drivers/block/nbd.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/bloc
On Wed, Sep 11, 2019 at 07:12:06AM +0900, Tetsuo Handa wrote:
> >> +static ssize_t memalloc_write(struct file *file, const char __user *buf,
> >> +size_t count, loff_t *ppos)
> >> +{
> >> + struct task_struct *task;
> >> + char buffer[5];
> >> + int rc = count;
> >> +
> >
On Tue, Sep 10 2019, Guoqing Jiang wrote:
> On 9/10/19 5:45 PM, Song Liu wrote:
>>
>>
>>> On Sep 10, 2019, at 12:33 AM, NeilBrown wrote:
>>>
>>> On Mon, Sep 09 2019, Song Liu wrote:
>>>
Hi Neil,
> On Sep 9, 2019, at 7:57 AM, NeilBrown wrote:
>
>
> If the drives in a R
On 9/10/2019 5:29 AM, Martin K. Petersen wrote:
Max,
Hi Martin,
thanks for the great explanation !
maybe we can add profiles to type0 and type2 in the future and have
more readable code.
It's a deliberate feature that we treat DIX Type 0, 1, and 2 the
same. It's very common to mix and m
On 2019/09/10 3:26, Mike Christie wrote:
> Forgot to cc linux-mm.
>
> On 09/09/2019 11:28 AM, Mike Christie wrote:
>> There are several storage drivers like dm-multipath, iscsi, and nbd that
>> have userspace components that can run in the IO path. For example,
>> iscsi and nbd's userspace deamons
On 9/4/19 1:45 PM, Tejun Heo wrote:
> Currently, when a given cgroup doesn't have enough budget, a forced or
> merged bio will advance the cgroup's vtime by the cost calculated
> according to the hierarchical weight at the time of issue. Once vtime
> is advanced, how the cgroup's weight changes do
On 9/10/19 10:15 AM, Tejun Heo wrote:
> ioc_pd_free() first cancels the hrtimers and then deactivates the
> iocg. However, the iocg timer can run inbetween and reschedule the
> hrtimers which will end up running after the iocg is freed leading to
> crashes like the following.
>
>general prote
XFS/ext4/others all need to lock the inode for buffered writes. Since
io_uring handles any IO in an async manner, this means that for higher
queue depth buffered write workloads, we have a lot of workers
hammering on the same mutex.
Running a QD=32 random write workload on my test box yields about
Add a helper for queueing a request for async execution, in preparation
for optimizing it.
No functional change in this patch.
Signed-off-by: Jens Axboe
---
fs/io_uring.c | 16 +++-
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b2
All the popular filesystems need to grab the inode lock for buffered
writes. With io_uring punting buffered writes to async context, we
observe a lot of contention with all workers hamming this mutex.
For buffered writes, we generally don't need a lot of parallelism on
the submission side, as the
- Original Message -
> Jan Stancek writes:
>
> >> Using the device while mounting same device doesn't work reliably like
> >> this race. (getblk() is intentionally used to get the buffer to write
> >> new data.)
> >
> > Are you saying this is expected even if 'usage' is just read?
>
>
ioc_pd_free() first cancels the hrtimers and then deactivates the
iocg. However, the iocg timer can run inbetween and reschedule the
hrtimers which will end up running after the iocg is freed leading to
crashes like the following.
general protection fault: [#1] SMP
...
RIP: 0010:iocg_k
Hello, Michal.
On Tue, Sep 10, 2019 at 02:55:14PM +0200, Michal Koutný wrote:
> This adds the generic io.weight attribute. How will this compose with
> the weight from IO schedulers? (AFAIK, only BFQ allows proportional
> control as of now. +CC Paolo.)
The two being enabled at the same time doesn
On 09/10/2019 05:00 AM, Kirill A. Shutemov wrote:
> On Mon, Sep 09, 2019 at 11:28:04AM -0500, Mike Christie wrote:
>> There are several storage drivers like dm-multipath, iscsi, and nbd that
>> have userspace components that can run in the IO path. For example,
>> iscsi and nbd's userspace deamons
On 9/10/19 5:45 PM, Song Liu wrote:
On Sep 10, 2019, at 12:33 AM, NeilBrown wrote:
On Mon, Sep 09 2019, Song Liu wrote:
Hi Neil,
On Sep 9, 2019, at 7:57 AM, NeilBrown wrote:
If the drives in a RAID0 are not all the same size, the array is
divided into zones.
The first zone covers a
On 09/10/2019 01:36 AM, xiu...@redhat.com wrote:
> From: Xiubo Li
>
> The followed code will do the same check, and this part is redandant.
>
> Signed-off-by: Xiubo Li
> ---
> drivers/block/nbd.c | 3 ---
> 1 file changed, 3 deletions(-)
>
> diff --git a/drivers/block/nbd.c b/drivers/block/nb
> On Sep 10, 2019, at 12:33 AM, NeilBrown wrote:
>
> On Mon, Sep 09 2019, Song Liu wrote:
>
>> Hi Neil,
>>
>>> On Sep 9, 2019, at 7:57 AM, NeilBrown wrote:
>>>
>>>
>>> If the drives in a RAID0 are not all the same size, the array is
>>> divided into zones.
>>> The first zone covers all dr
+ Miklos
On 2019/09/10 13:41, Kirill A. Shutemov wrote:
> On Tue, Sep 10, 2019 at 12:05:33PM +, Damien Le Moal wrote:
>> On 2019/09/10 11:00, Kirill A. Shutemov wrote:
>>> On Mon, Sep 09, 2019 at 11:28:04AM -0500, Mike Christie wrote:
There are several storage drivers like dm-multipath, i
Hello.
On Wed, Aug 28, 2019 at 03:05:58PM -0700, Tejun Heo wrote:
> diff --git a/block/blk-iocost.c b/block/blk-iocost.c
> [...]
> +static struct cftype ioc_files[] = {
> + .name = "weight",
> [...]
This adds the generic io.weight attribute. How will this compose with
the weight from
On Tue, Sep 10, 2019 at 12:05:33PM +, Damien Le Moal wrote:
> On 2019/09/10 11:00, Kirill A. Shutemov wrote:
> > On Mon, Sep 09, 2019 at 11:28:04AM -0500, Mike Christie wrote:
> >> There are several storage drivers like dm-multipath, iscsi, and nbd that
> >> have userspace components that can r
On 2019/09/10 11:00, Kirill A. Shutemov wrote:
> On Mon, Sep 09, 2019 at 11:28:04AM -0500, Mike Christie wrote:
>> There are several storage drivers like dm-multipath, iscsi, and nbd that
>> have userspace components that can run in the IO path. For example,
>> iscsi and nbd's userspace deamons may
(Just stumbled upon this patch when link to it came with a CVE bug report.)
On Mon, Jul 29, 2019 at 11:42:26AM -0500, Navid Emamdoost wrote:
> nla_nest_start may fail and return NULL. The check is inserted, and
> errno is selected based on other call sites within the same source code.
> Update: re
Hi Jens, Ming,
Do you have any thoughts about this patch?
Thanks,
Martijn
On Wed, Sep 4, 2019 at 9:49 PM Martijn Coenen wrote:
>
> The loop driver assumes that if the passed in fd is opened with
> O_DIRECT, the caller wants to use direct I/O on the loop device.
> However, if the underlying bloc
On Mon, Sep 09, 2019 at 11:28:04AM -0500, Mike Christie wrote:
> There are several storage drivers like dm-multipath, iscsi, and nbd that
> have userspace components that can run in the IO path. For example,
> iscsi and nbd's userspace deamons may need to recreate a socket and/or
> send IO on it, a
Mike,
On 2019/09/09 19:26, Mike Christie wrote:
> Forgot to cc linux-mm.
>
> On 09/09/2019 11:28 AM, Mike Christie wrote:
>> There are several storage drivers like dm-multipath, iscsi, and nbd that
>> have userspace components that can run in the IO path. For example,
>> iscsi and nbd's userspace
On Tue, Sep 10, 2019 at 08:13:48AM +0200, Christoph Hellwig wrote:
> On Tue, Sep 10, 2019 at 02:03:17AM +, Yoshihiro Shimoda wrote:
> > I'm sorry for causing this trouble on your environment. I have a proposal to
> > resolve this issue. The mmc_host struct will have a new caps2 flag
> > like MM
On Tue, Sep 10, 2019 at 02:03:17AM +, Yoshihiro Shimoda wrote:
> Hi Thierry,
>
> > From: Thierry Reding, Sent: Tuesday, September 10, 2019 4:19 AM
> >
> > On Mon, Sep 09, 2019 at 06:13:31PM +0200, Christoph Hellwig wrote:
> > > On Mon, Sep 09, 2019 at 02:56:56PM +0200, Thierry Reding wrote:
>
32 matches
Mail list logo
