Commit 7e3e888d authored by Dan Williams's avatar Dan Williams Committed by Linus Torvalds
Browse files

libnvdimm/pfn: fix fsdax-mode namespace info-block zero-fields 

At namespace creation time there is the potential for the "expected to
be zero" fields of a 'pfn' info-block to be filled with indeterminate
data.  While the kernel buffer is zeroed on allocation it is immediately
overwritten by nd_pfn_validate() filling it with the current contents of
the on-media info-block location.  For fields like, 'flags' and the
'padding' it potentially means that future implementations can not rely on
those fields being zero.

In preparation to stop using the 'start_pad' and 'end_trunc' fields for
section alignment, arrange for fields that are not explicitly
initialized to be guaranteed zero.  Bump the minor version to indicate
it is safe to assume the 'padding' and 'flags' are zero.  Otherwise,
this corruption is expected to benign since all other critical fields
are explicitly initialized.

Note The cc: stable is about spreading this new policy to as many
kernels as possible not fixing an issue in those kernels.  It is not
until the change titled "libnvdimm/pfn: Stop padding pmem namespaces to
section alignment" where this improper initialization becomes a problem.
So if someone decides to backport "libnvdimm/pfn: Stop padding pmem
namespaces to section alignment" (which is not tagged for stable), make
sure this pre-requisite is flagged.

Link: http://lkml.kernel.org/r/156092356065.979959.6681003754765958296.stgit@dwillia2-desk3.amr.corp.intel.com


Fixes: 32ab0a3f ("libnvdimm, pmem: 'struct page' for pmem")
Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>	[ppc64]
Cc: <stable@vger.kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Logan Gunthorpe <logang@deltatee.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Cc: Jason Gunthorpe <jgg@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 7cc7867f

drivers/nvdimm/dax_devs.c

+1 −1
Original line number Original line Diff line number Diff line
@@ -118,7 +118,7 @@ int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns) 
	nvdimm_bus_unlock(&ndns->dev);

	nvdimm_bus_unlock(&ndns->dev);

	if (!dax_dev)

	if (!dax_dev)

		return -ENOMEM;

		return -ENOMEM;

	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);

	pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);

	nd_pfn->pfn_sb = pfn_sb;

	nd_pfn->pfn_sb = pfn_sb;

	rc = nd_pfn_validate(nd_pfn, DAX_SIG);

	rc = nd_pfn_validate(nd_pfn, DAX_SIG);

	dev_dbg(dev, "dax: %s\n", rc == 0 ? dev_name(dax_dev) : "<none>");

	dev_dbg(dev, "dax: %s\n", rc == 0 ? dev_name(dax_dev) : "<none>");

drivers/nvdimm/pfn.h

+1 −0
Original line number Original line Diff line number Diff line
@@ -28,6 +28,7 @@ struct nd_pfn_sb { 
	__le32 end_trunc;

	__le32 end_trunc;

	/* minor-version-2 record the base alignment of the mapping */

	/* minor-version-2 record the base alignment of the mapping */

	__le32 align;

	__le32 align;

	/* minor-version-3 guarantee the padding and flags are zero */

	u8 padding[4000];

	u8 padding[4000];

	__le64 checksum;

	__le64 checksum;

};

};

drivers/nvdimm/pfn_devs.c

+15 −3
Original line number Original line Diff line number Diff line
@@ -412,6 +412,15 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn) 
	return 0;

	return 0;

}

}





/**

 * nd_pfn_validate - read and validate info-block

 * @nd_pfn: fsdax namespace runtime state / properties

 * @sig: 'devdax' or 'fsdax' signature

 *

 * Upon return the info-block buffer contents (->pfn_sb) are

 * indeterminate when validation fails, and a coherent info-block

 * otherwise.

 */

int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)

int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)

{

{

	u64 checksum, offset;

	u64 checksum, offset;
@@ -557,7 +566,7 @@ int nd_pfn_probe(struct device *dev, struct nd_namespace_common *ndns) 
	nvdimm_bus_unlock(&ndns->dev);

	nvdimm_bus_unlock(&ndns->dev);

	if (!pfn_dev)

	if (!pfn_dev)

		return -ENOMEM;

		return -ENOMEM;

	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);

	pfn_sb = devm_kmalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);

	nd_pfn = to_nd_pfn(pfn_dev);

	nd_pfn = to_nd_pfn(pfn_dev);

	nd_pfn->pfn_sb = pfn_sb;

	nd_pfn->pfn_sb = pfn_sb;

	rc = nd_pfn_validate(nd_pfn, PFN_SIG);

	rc = nd_pfn_validate(nd_pfn, PFN_SIG);
@@ -693,7 +702,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) 
	u64 checksum;

	u64 checksum;

	int rc;

	int rc;





	pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);

	pfn_sb = devm_kmalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);

	if (!pfn_sb)

	if (!pfn_sb)

		return -ENOMEM;

		return -ENOMEM;
@@ -702,11 +711,14 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) 
		sig = DAX_SIG;

		sig = DAX_SIG;

	else

	else

		sig = PFN_SIG;

		sig = PFN_SIG;



	rc = nd_pfn_validate(nd_pfn, sig);

	rc = nd_pfn_validate(nd_pfn, sig);

	if (rc != -ENODEV)

	if (rc != -ENODEV)

		return rc;

		return rc;





	/* no info block, do init */;

	/* no info block, do init */;

	memset(pfn_sb, 0, sizeof(*pfn_sb));



	nd_region = to_nd_region(nd_pfn->dev.parent);

	nd_region = to_nd_region(nd_pfn->dev.parent);

	if (nd_region->ro) {

	if (nd_region->ro) {

		dev_info(&nd_pfn->dev,

		dev_info(&nd_pfn->dev,
@@ -759,7 +771,7 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) 
	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);

	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);

	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);

	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);

	pfn_sb->version_major = cpu_to_le16(1);

	pfn_sb->version_major = cpu_to_le16(1);

	pfn_sb->version_minor = cpu_to_le16(2);

	pfn_sb->version_minor = cpu_to_le16(3);

	pfn_sb->start_pad = cpu_to_le32(start_pad);

	pfn_sb->start_pad = cpu_to_le32(start_pad);

	pfn_sb->end_trunc = cpu_to_le32(end_trunc);

	pfn_sb->end_trunc = cpu_to_le32(end_trunc);

	pfn_sb->align = cpu_to_le32(nd_pfn->align);

	pfn_sb->align = cpu_to_le32(nd_pfn->align);

CRA Git | Maintained and supported by SUSTech CRA and CCSE