Re: [Qemu-devel] [PATCH for-2.7 v2 05/17] raw-posix: Implement .bdrv_lockf

["Denis V. Lunev" <den@openvz.org>]

On 04/18/2016 04:12 AM, Fam Zheng wrote:
> On Sat, 04/16 16:29, Denis V. Lunev wrote:
>> On 04/15/2016 06:27 AM, Fam Zheng wrote:
>>> virtlockd in libvirt locks the first byte, we lock byte 1 to avoid
>>> the intervene.
>>>
>>> Suggested-by: "Daniel P. Berrange" <berrange@redhat.com>
>>> Signed-off-by: Fam Zheng <famz@redhat.com>
>>> ---
>>>   block/raw-posix.c | 35 +++++++++++++++++++++++++++++++++++
>>>   1 file changed, 35 insertions(+)
>>>
>>> diff --git a/block/raw-posix.c b/block/raw-posix.c
>>> index 906d5c9..3a2c17f 100644
>>> --- a/block/raw-posix.c
>>> +++ b/block/raw-posix.c
>>> @@ -35,6 +35,7 @@
>>>   #include "raw-aio.h"
>>>   #include "qapi/util.h"
>>>   #include "qapi/qmp/qstring.h"
>>> +#include "glib.h"
>>>   #if defined(__APPLE__) && (__MACH__)
>>>   #include <paths.h>
>>> @@ -397,6 +398,38 @@ static void raw_attach_aio_context(BlockDriverState *bs,
>>>   #endif
>>>   }
>>> +static int raw_lockf(BlockDriverState *bs, BdrvLockfCmd cmd)
>>> +{
>>> +
>>> +    BDRVRawState *s = bs->opaque;
>>> +    int ret;
>>> +    struct flock fl = (struct flock) {
>>> +        .l_whence  = SEEK_SET,
>>> +        /* Locking byte 1 avoids interfereing with virtlockd. */
>>> +        .l_start = 1,
>>> +        .l_len = 1,
>>> +    };
>>> +
>>> +    switch (cmd) {
>>> +    case BDRV_LOCKF_RWLOCK:
>>> +        fl.l_type = F_WRLCK;
>>> +        break;
>>> +    case BDRV_LOCKF_ROLOCK:
>>> +        fl.l_type = F_RDLCK;
>>> +        break;
>>> +    case BDRV_LOCKF_UNLOCK:
>>> +        fl.l_type = F_UNLCK;
>>> +        break;
>>> +    default:
>>> +        abort();
>>> +    }
>>> +    ret = fcntl(s->fd, F_SETLK, &fl);
>>> +    if (ret) {
>>> +        ret = -errno;
>>> +    }
>>> +    return ret;
>>> +}
>>> +
>>>   #ifdef CONFIG_LINUX_AIO
>>>   static int raw_set_aio(void **aio_ctx, int *use_aio, int bdrv_flags)
>>>   {
>>> @@ -1960,6 +1993,8 @@ BlockDriver bdrv_file = {
>>>       .bdrv_detach_aio_context = raw_detach_aio_context,
>>>       .bdrv_attach_aio_context = raw_attach_aio_context,
>>> +    .bdrv_lockf = raw_lockf,
>>> +
>>>       .create_opts = &raw_create_opts,
>>>   };
>> would it be better to use
>>
>>         int flock(int fd, int operation);
>>
>> DESCRIPTION
>>         Apply or remove an advisory lock on the open file specified by fd.
>> The
>>         argument operation is one of the following:
>>
>>             LOCK_SH  Place a shared lock.  More than one  process may  hold
>> a
>>                      shared lock for a given file at a given time.
>>
>>             LOCK_EX  Place  an  exclusive  lock.   Only one process may hold
>> an
>>                      exclusive lock for a given file at a given time.
>>
>>             LOCK_UN  Remove an existing lock held by this process.
>>
>> for this purpose?
>>
>> Sorry that missed this point in the initial review...
>> We will not intersect with libvirt for the case.
>>
> As noted in the cover letter, flock() is nop on NFS mount points on Linux, so
> fcntl is safer.
>
> Fam
>
that seems STRANGE to me. For the time being flock() was
working for Linux NFS server. Here is the implementation.

int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
{
         struct inode *inode = filp->f_mapping->host;
         int is_local = 0;

         dprintk("NFS: flock(%pD2, t=%x, fl=%x)\n",
                         filp, fl->fl_type, fl->fl_flags);

         if (!(fl->fl_flags & FL_FLOCK))
                 return -ENOLCK;

         /*
          * The NFSv4 protocol doesn't support LOCK_MAND, which is not 
part of
          * any standard. In principle we might be able to support LOCK_MAND
          * on NFSv2/3 since NLMv3/4 support DOS share modes, but for 
now the
          * NFS code is not set up for it.
          */
         if (fl->fl_type & LOCK_MAND)
                 return -EINVAL;

         if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
                 is_local = 1;

         /* We're simulating flock() locks using posix locks on the 
server */
         if (fl->fl_type == F_UNLCK)
                 return do_unlk(filp, cmd, fl, is_local);
         return do_setlk(filp, cmd, fl, is_local);
}

Den