Re: [PATCH] virtio pmem: fix async flush ordering

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



> 
> >  Remove logic to create child bio in the async flush function which
> >  causes child bio to get executed after parent bio 'pmem_make_request'
> >  completes. This resulted in wrong ordering of REQ_PREFLUSH with the
> >  data write request.
> >
> >  Instead we are performing flush from the parent bio to maintain the
> >  correct order. Also, returning from function 'pmem_make_request' if
> >  REQ_PREFLUSH returns an error.
> >
> > Reported-by: Jeff Moyer <jmoyer@xxxxxxxxxx>
> > Signed-off-by: Pankaj Gupta <pagupta@xxxxxxxxxx>
> 
> There's a slight change in behavior for the error path in the
> virtio_pmem driver.  Previously, all errors from virtio_pmem_flush were
> converted to -EIO.  Now, they are reported as-is.  I think this is
> actually an improvement.

yes.

> 
> I'll also note that the current behavior can result in data corruption,
> so this should be tagged for stable.

Agree.

> 
> The patch looks good to me.
> 
> Thanks!
> 
> Reviewed-by: Jeff Moyer <jmoyer@xxxxxxxxxx>

Thank you!

Pankaj

> 
> > ---
> >  drivers/acpi/nfit/core.c     |  4 ++--
> >  drivers/nvdimm/claim.c       |  2 +-
> >  drivers/nvdimm/nd.h          |  2 +-
> >  drivers/nvdimm/nd_virtio.c   | 29 ++---------------------------
> >  drivers/nvdimm/pmem.c        | 14 ++++++++++----
> >  drivers/nvdimm/region_devs.c |  6 +++---
> >  drivers/nvdimm/virtio_pmem.c |  2 +-
> >  drivers/nvdimm/virtio_pmem.h |  2 +-
> >  include/linux/libnvdimm.h    |  4 ++--
> >  9 files changed, 23 insertions(+), 42 deletions(-)
> >
> > diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> > index 14e68f202f81..afbd5e2b2ea8 100644
> > --- a/drivers/acpi/nfit/core.c
> > +++ b/drivers/acpi/nfit/core.c
> > @@ -2426,7 +2426,7 @@ static void write_blk_ctl(struct nfit_blk *nfit_blk,
> > unsigned int bw,
> >                  offset = to_interleave_offset(offset, mmio);
> >  
> >          writeq(cmd, mmio->addr.base + offset);
> > -        nvdimm_flush(nfit_blk->nd_region, NULL);
> > +        nvdimm_flush(nfit_blk->nd_region);
> >  
> >          if (nfit_blk->dimm_flags & NFIT_BLK_DCR_LATCH)
> >                  readq(mmio->addr.base + offset);
> > @@ -2475,7 +2475,7 @@ static int acpi_nfit_blk_single_io(struct nfit_blk
> > *nfit_blk,
> >          }
> >  
> >          if (rw)
> > -                nvdimm_flush(nfit_blk->nd_region, NULL);
> > +                nvdimm_flush(nfit_blk->nd_region);
> >  
> >          rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
> >          return rc;
> > diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
> > index 2985ca949912..0fedb2fbfcbe 100644
> > --- a/drivers/nvdimm/claim.c
> > +++ b/drivers/nvdimm/claim.c
> > @@ -293,7 +293,7 @@ static int nsio_rw_bytes(struct nd_namespace_common
> > *ndns,
> >          }
> >  
> >          memcpy_flushcache(nsio->addr + offset, buf, size);
> > -        ret = nvdimm_flush(to_nd_region(ndns->dev.parent), NULL);
> > +        ret = nvdimm_flush(to_nd_region(ndns->dev.parent));
> >          if (ret)
> >                  rc = ret;
> >  
> > diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
> > index ee5c04070ef9..77d8b9f0c34a 100644
> > --- a/drivers/nvdimm/nd.h
> > +++ b/drivers/nvdimm/nd.h
> > @@ -155,7 +155,7 @@ struct nd_region {
> >          struct badblocks bb;
> >          struct nd_interleave_set *nd_set;
> >          struct nd_percpu_lane __percpu *lane;
> > -        int (*flush)(struct nd_region *nd_region, struct bio *bio);
> > +        int (*flush)(struct nd_region *nd_region);
> >          struct nd_mapping mapping[0];
> >  };
> >  
> > diff --git a/drivers/nvdimm/nd_virtio.c b/drivers/nvdimm/nd_virtio.c
> > index 10351d5b49fa..9604ba08a68a 100644
> > --- a/drivers/nvdimm/nd_virtio.c
> > +++ b/drivers/nvdimm/nd_virtio.c
> > @@ -35,7 +35,7 @@ void virtio_pmem_host_ack(struct virtqueue *vq)
> >  EXPORT_SYMBOL_GPL(virtio_pmem_host_ack);
> >  
> >   /* The request submission function */
> > -static int virtio_pmem_flush(struct nd_region *nd_region)
> > +int virtio_pmem_flush(struct nd_region *nd_region)
> >  {
> >          struct virtio_device *vdev = nd_region->provider_data;
> >          struct virtio_pmem *vpmem  = vdev->priv;
> > @@ -96,30 +96,5 @@ static int virtio_pmem_flush(struct nd_region
> > *nd_region)
> >          kfree(req_data);
> >          return err;
> >  };
> > -
> > -/* The asynchronous flush callback function */
> > -int async_pmem_flush(struct nd_region *nd_region, struct bio *bio)
> > -{
> > -        /*
> > -         * Create child bio for asynchronous flush and chain with
> > -         * parent bio. Otherwise directly call nd_region flush.
> > -         */
> > -        if (bio && bio->bi_iter.bi_sector != -1) {
> > -                struct bio *child = bio_alloc(GFP_ATOMIC, 0);
> > -
> > -                if (!child)
> > -                        return -ENOMEM;
> > -                bio_copy_dev(child, bio);
> > -                child->bi_opf = REQ_PREFLUSH;
> > -                child->bi_iter.bi_sector = -1;
> > -                bio_chain(child, bio);
> > -                submit_bio(child);
> > -                return 0;
> > -        }
> > -        if (virtio_pmem_flush(nd_region))
> > -                return -EIO;
> > -
> > -        return 0;
> > -};
> > -EXPORT_SYMBOL_GPL(async_pmem_flush);
> > +EXPORT_SYMBOL_GPL(virtio_pmem_flush);
> >  MODULE_LICENSE("GPL");
> > diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> > index f9f76f6ba07b..b3ca641668a2 100644
> > --- a/drivers/nvdimm/pmem.c
> > +++ b/drivers/nvdimm/pmem.c
> > @@ -194,7 +194,13 @@ static blk_qc_t pmem_make_request(struct request_queue
> > *q, struct bio *bio)
> >          struct nd_region *nd_region = to_region(pmem);
> >  
> >          if (bio->bi_opf & REQ_PREFLUSH)
> > -                ret = nvdimm_flush(nd_region, bio);
> > +                ret = nvdimm_flush(nd_region);
> > +
> > +        if (ret) {
> > +                bio->bi_status = errno_to_blk_status(ret);
> > +                bio_endio(bio);
> > +                return BLK_QC_T_NONE;
> > +        }
> >  
> >          do_acct = nd_iostat_start(bio, &start);
> >          bio_for_each_segment(bvec, bio, iter) {
> > @@ -209,7 +215,7 @@ static blk_qc_t pmem_make_request(struct request_queue
> > *q, struct bio *bio)
> >                  nd_iostat_end(bio, start);
> >  
> >          if (bio->bi_opf & REQ_FUA)
> > -                ret = nvdimm_flush(nd_region, bio);
> > +                ret = nvdimm_flush(nd_region);
> >  
> >          if (ret)
> >                  bio->bi_status = errno_to_blk_status(ret);
> > @@ -549,14 +555,14 @@ static int nd_pmem_remove(struct device *dev)
> >                  sysfs_put(pmem->bb_state);
> >                  pmem->bb_state = NULL;
> >          }
> > -        nvdimm_flush(to_nd_region(dev->parent), NULL);
> > +        nvdimm_flush(to_nd_region(dev->parent));
> >  
> >          return 0;
> >  }
> >  
> >  static void nd_pmem_shutdown(struct device *dev)
> >  {
> > -        nvdimm_flush(to_nd_region(dev->parent), NULL);
> > +        nvdimm_flush(to_nd_region(dev->parent));
> >  }
> >  
> >  static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
> > diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
> > index ef423ba1a711..cfd96a0d52f2 100644
> > --- a/drivers/nvdimm/region_devs.c
> > +++ b/drivers/nvdimm/region_devs.c
> > @@ -287,7 +287,7 @@ static ssize_t deep_flush_store(struct device *dev,
> > struct device_attribute *att
> >                  return rc;
> >          if (!flush)
> >                  return -EINVAL;
> > -        rc = nvdimm_flush(nd_region, NULL);
> > +        rc = nvdimm_flush(nd_region);
> >          if (rc)
> >                  return rc;
> >  
> > @@ -1079,14 +1079,14 @@ struct nd_region
> > *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
> >  }
> >  EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
> >  
> > -int nvdimm_flush(struct nd_region *nd_region, struct bio *bio)
> > +int nvdimm_flush(struct nd_region *nd_region)
> >  {
> >          int rc = 0;
> >  
> >          if (!nd_region->flush)
> >                  rc = generic_nvdimm_flush(nd_region);
> >          else {
> > -                if (nd_region->flush(nd_region, bio))
> > +                if (nd_region->flush(nd_region))
> >                          rc = -EIO;
> >          }
> >  
> > diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c
> > index 5e3d07b47e0c..a6234466674d 100644
> > --- a/drivers/nvdimm/virtio_pmem.c
> > +++ b/drivers/nvdimm/virtio_pmem.c
> > @@ -80,7 +80,7 @@ static int virtio_pmem_probe(struct virtio_device *vdev)
> >  
> >          ndr_desc.res = &res;
> >          ndr_desc.numa_node = nid;
> > -        ndr_desc.flush = async_pmem_flush;
> > +        ndr_desc.flush = virtio_pmem_flush;
> >          set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
> >          set_bit(ND_REGION_ASYNC, &ndr_desc.flags);
> >          nd_region = nvdimm_pmem_region_create(vpmem->nvdimm_bus, &ndr_desc);
> > diff --git a/drivers/nvdimm/virtio_pmem.h b/drivers/nvdimm/virtio_pmem.h
> > index 0dddefe594c4..4f9ee19aad90 100644
> > --- a/drivers/nvdimm/virtio_pmem.h
> > +++ b/drivers/nvdimm/virtio_pmem.h
> > @@ -51,5 +51,5 @@ struct virtio_pmem {
> >  };
> >  
> >  void virtio_pmem_host_ack(struct virtqueue *vq);
> > -int async_pmem_flush(struct nd_region *nd_region, struct bio *bio);
> > +int virtio_pmem_flush(struct nd_region *nd_region);
> >  #endif
> > diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
> > index b6eddf912568..211c87edb4eb 100644
> > --- a/include/linux/libnvdimm.h
> > +++ b/include/linux/libnvdimm.h
> > @@ -130,7 +130,7 @@ struct nd_region_desc {
> >          int target_node;
> >          unsigned long flags;
> >          struct device_node *of_node;
> > -        int (*flush)(struct nd_region *nd_region, struct bio *bio);
> > +        int (*flush)(struct nd_region *nd_region);
> >  };
> >  
> >  struct device;
> > @@ -261,7 +261,7 @@ unsigned long nd_blk_memremap_flags(struct
> > nd_blk_region *ndbr);
> >  unsigned int nd_region_acquire_lane(struct nd_region *nd_region);
> >  void nd_region_release_lane(struct nd_region *nd_region, unsigned int
> >  lane);
> >  u64 nd_fletcher64(void *addr, size_t len, bool le);
> > -int nvdimm_flush(struct nd_region *nd_region, struct bio *bio);
> > +int nvdimm_flush(struct nd_region *nd_region);
> >  int generic_nvdimm_flush(struct nd_region *nd_region);
> >  int nvdimm_has_flush(struct nd_region *nd_region);
> >  int nvdimm_has_cache(struct nd_region *nd_region);
> 





[Index of Archives]     [Linux IBM ACPI]     [Linux Power Management]     [Linux Kernel]     [Linux Laptop]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Samba]     [Video 4 Linux]     [Device Mapper]     [Linux Resources]

  Powered by Linux