[PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[Tom Tucker]

This patchset implements support for Fast Memory Registration in the
NFS server.  Fast Memory Regstration is the ability to quickly map a
kernel memory page list as a logically contiguous memory region from
the perspective of the adapter. This mapping is created and
invalidated using work requests posted on the SQ. This allows for
large amounts of data to transferred between the client and server
with a single work request as well as the ability to invalidate a
previously mapped memory region. For iWARP, this allows for "one-shot"
memory regions to be mapped for a single NFS-RDMA data transfer. This
improves security since a byzantine app listening on the net will have
a very short window during which the RKEY is valid.

This capability is only enabled if the underlying device advertises
that it is supported.

This patches are also available here:
git://git.linux-nfs.org/projects/tomtucker/xprt-switch-2.6.git

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>

 include/linux/sunrpc/svc_rdma.h |   27 ++++++++++++++++++++++++++-
 1 files changed, 26 insertions(+), 1 deletions(-)

[PATCH 02/09] svcrdma: Add FRMR get/put services

 include/linux/sunrpc/svc_rdma.h          |    3 +
 net/sunrpc/xprtrdma/svc_rdma_transport.c |  125 ++++++++++++++++++++++++++++-
 2 files changed, 123 insertions(+), 5 deletions(-)

[PATCH 03/09] svcrdma: Query device for Fast Reg support during connection setup

 net/sunrpc/xprtrdma/svc_rdma_transport.c |   86 +++++++++++++++++++++++++++--
 1 files changed, 80 insertions(+), 6 deletions(-)

[PATCH 04/09] svcrdma: Add a service to register a Fast Reg MR with the device

 include/linux/sunrpc/svc_rdma.h          |    1 +
 net/sunrpc/xprtrdma/svc_rdma_transport.c |   53 ++++++++++++++++++++++++++---
 2 files changed, 48 insertions(+), 6 deletions(-)

[PATCH 05/09] svcrdma: Modify post recv path to use local dma key

 net/sunrpc/xprtrdma/svc_rdma_transport.c |   10 +++++++---
 1 files changed, 7 insertions(+), 3 deletions(-)

[PATCH 06/09] svcrdma: Add support to svc_rdma_send to handle chained WR

 net/sunrpc/xprtrdma/svc_rdma_transport.c |   29 +++++++++++++++++++++--------
 1 files changed, 21 insertions(+), 8 deletions(-)

[PATCH 07/09] svcrdma: Modify the RPC recv path to use FRMR when available

 include/linux/sunrpc/svc_rdma.h          |    1 +
 net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  |  187 ++++++++++++++++++++++++++----
 net/sunrpc/xprtrdma/svc_rdma_transport.c |    5 +-
 3 files changed, 171 insertions(+), 22 deletions(-)

[PATCH 08/09] svcrdma: Modify the RPC reply path to use FRMR when available

 net/sunrpc/xprtrdma/svc_rdma_sendto.c    |  263 +++++++++++++++++++++++++-----
 net/sunrpc/xprtrdma/svc_rdma_transport.c |    2 +
 2 files changed, 225 insertions(+), 40 deletions(-)

[PATCH 09/09] svcrdma: Update svc_rdma_send_error to use DMA LKEY

 net/sunrpc/xprtrdma/svc_rdma_transport.c |   11 +++++++++--
 1 files changed, 9 insertions(+), 2 deletions(-)

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[J. Bruce Fields]

On Wed, Aug 13, 2008 at 11:06:29AM -0500, Tom Tucker wrote:
>
> This patchset implements support for Fast Memory Registration in the
> NFS server.  Fast Memory Regstration is the ability to quickly map a
> kernel memory page list as a logically contiguous memory region from
> the perspective of the adapter. This mapping is created and
> invalidated using work requests posted on the SQ. This allows for
> large amounts of data to transferred between the client and server
> with a single work request as well as the ability to invalidate a
> previously mapped memory region. For iWARP, this allows for "one-shot"
> memory regions to be mapped for a single NFS-RDMA data transfer. This
> improves security since a byzantine app listening on the net will have
> a very short window during which the RKEY is valid.
>
> This capability is only enabled if the underlying device advertises
> that it is supported.

Thanks for your continuing work on this.

I think we really need to document the security assumptions, though.

(Currently is your entire memory at the mercy of anyone on the same
local network as your rdma adapter?  If so, fixing that would certainly
make this stuff useful in more situations, but language like "a very
short window" doesn't sound promising.  Also, we've got to make sure
users understand where it's safe to use this stuff....)

--b.

>
> This patches are also available here:
> git://git.linux-nfs.org/projects/tomtucker/xprt-switch-2.6.git
>
> Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
>
> include/linux/sunrpc/svc_rdma.h |   27 ++++++++++++++++++++++++++-
> 1 files changed, 26 insertions(+), 1 deletions(-)
>
> [PATCH 02/09] svcrdma: Add FRMR get/put services
>
> include/linux/sunrpc/svc_rdma.h          |    3 +
> net/sunrpc/xprtrdma/svc_rdma_transport.c |  125 ++++++++++++++++++++++++++++-
> 2 files changed, 123 insertions(+), 5 deletions(-)
>
> [PATCH 03/09] svcrdma: Query device for Fast Reg support during connection setup
>
> net/sunrpc/xprtrdma/svc_rdma_transport.c |   86 +++++++++++++++++++++++++++--
> 1 files changed, 80 insertions(+), 6 deletions(-)
>
> [PATCH 04/09] svcrdma: Add a service to register a Fast Reg MR with the device
>
> include/linux/sunrpc/svc_rdma.h          |    1 +
> net/sunrpc/xprtrdma/svc_rdma_transport.c |   53 ++++++++++++++++++++++++++---
> 2 files changed, 48 insertions(+), 6 deletions(-)
>
> [PATCH 05/09] svcrdma: Modify post recv path to use local dma key
>
> net/sunrpc/xprtrdma/svc_rdma_transport.c |   10 +++++++---
> 1 files changed, 7 insertions(+), 3 deletions(-)
>
> [PATCH 06/09] svcrdma: Add support to svc_rdma_send to handle chained WR
>
> net/sunrpc/xprtrdma/svc_rdma_transport.c |   29 +++++++++++++++++++++--------
> 1 files changed, 21 insertions(+), 8 deletions(-)
>
> [PATCH 07/09] svcrdma: Modify the RPC recv path to use FRMR when available
>
> include/linux/sunrpc/svc_rdma.h          |    1 +
> net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  |  187 ++++++++++++++++++++++++++----
> net/sunrpc/xprtrdma/svc_rdma_transport.c |    5 +-
> 3 files changed, 171 insertions(+), 22 deletions(-)
>
> [PATCH 08/09] svcrdma: Modify the RPC reply path to use FRMR when available
>
> net/sunrpc/xprtrdma/svc_rdma_sendto.c    |  263 +++++++++++++++++++++++++-----
> net/sunrpc/xprtrdma/svc_rdma_transport.c |    2 +
> 2 files changed, 225 insertions(+), 40 deletions(-)
>
> [PATCH 09/09] svcrdma: Update svc_rdma_send_error to use DMA LKEY
>
> net/sunrpc/xprtrdma/svc_rdma_transport.c |   11 +++++++++--
> 1 files changed, 9 insertions(+), 2 deletions(-)
>

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[Tom Tucker]

J. Bruce Fields wrote:
> On Wed, Aug 13, 2008 at 11:06:29AM -0500, Tom Tucker wrote:
>> This patchset implements support for Fast Memory Registration in the
>> NFS server.  Fast Memory Regstration is the ability to quickly map a
>> kernel memory page list as a logically contiguous memory region from
>> the perspective of the adapter. This mapping is created and
>> invalidated using work requests posted on the SQ. This allows for
>> large amounts of data to transferred between the client and server
>> with a single work request as well as the ability to invalidate a
>> previously mapped memory region. For iWARP, this allows for "one-shot"
>> memory regions to be mapped for a single NFS-RDMA data transfer. This
>> improves security since a byzantine app listening on the net will have
>> a very short window during which the RKEY is valid.
>>
>> This capability is only enabled if the underlying device advertises
>> that it is supported.
> 
> Thanks for your continuing work on this.
> 
> I think we really need to document the security assumptions, though.
> 

Yes, that's a good idea. Maybe a file in Documentation/svcrdma?

> (Currently is your entire memory at the mercy of anyone on the same
> local network as your rdma adapter?

------------------------------------------------------------------------

A principal exploit is that a node listening on a mirror port of a switch
could snoop RDMA packets containing RKEY and then forge a packet with this
RKEY to write or read the memory of the peer to which the RKEY referred.

The NFSRDMA protocol is defined such that a) only the server initiates
RDMA, and b) only the client's memory is exposed via RKEY. This is why
the server reads to fetch RPC data from the client even though it would
be more efficient for the client to write the data to the server's memory.

The above design goal is not entirely realized with iWARP, however, because
the RKEY (called an STag on iWARP) for the data sink of an RDMA_READ is
actually placed on the wire! Not only that, iWARP (RDDP) requires that this
RKEY have Remote Write! This means that the server's memory is exposed by
virtue of having placed the RKEY for it's local memory on the wire in order
to receive the result of the RDMA_READ. By contrast, IB uses an opaque
transaction ID# to associate the READ_RPL with the READ_REQ _and_ the data
sink of an RDMA_READ does not require remote access. That said, the evil node
in question, for example, could potentially forge a packet with this
transaction ID and corrupt the target memory, however, the duration
of the exploit is this single READ_REQ.

The newer RDMA adapters (both iWARP and IB) support "Fast Memory Registration".
This capability allows memory to be quickly registered and
de-registered by submitting WR on the SQ. So the idea is to create an RKEY
that ONLY maps the single RPC. So the WR sequence is post_map,
post_rdma_read, post_invalidate. This has two benefits, a) it restricts the
domain of the exploit to the memory of a single RPC, and b) it limits the
duration of the exploit to the time it takes to satisfy the RDMA_READ.

   If so, fixing that would certainly
> make this stuff useful in more situations, but language like "a very
> short window" doesn't sound promising.  Also, we've got to make sure
> users understand where it's safe to use this stuff....)
> 

There are those who argue that a one-shot STag/RKEY is no less secure than TCP.
Consider that the exact same evil application could more easily corrupt RPC
payload by simply forging a packet with the correct TCP sequence number --
in fact it's easier than the RDMA exploit because the RDMA exploit requires
that you correctly forge both the TCP packet _and_ the RDMA payload. In
addition the duration of the TCP exploit is the lifetime of the connection, not
the lifetime of a single WR.

So if you buy the argument above, RDMA on IB or iWARP using Fast Reg is no
less secure than TCP. That is the goal of this patch series.

Tom

> --b.
> 
>> This patches are also available here:
>> git://git.linux-nfs.org/projects/tomtucker/xprt-switch-2.6.git
>>
>> Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
>>
>> include/linux/sunrpc/svc_rdma.h |   27 ++++++++++++++++++++++++++-
>> 1 files changed, 26 insertions(+), 1 deletions(-)
>>
>> [PATCH 02/09] svcrdma: Add FRMR get/put services
>>
>> include/linux/sunrpc/svc_rdma.h          |    3 +
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |  125 ++++++++++++++++++++++++++++-
>> 2 files changed, 123 insertions(+), 5 deletions(-)
>>
>> [PATCH 03/09] svcrdma: Query device for Fast Reg support during connection setup
>>
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |   86 +++++++++++++++++++++++++++--
>> 1 files changed, 80 insertions(+), 6 deletions(-)
>>
>> [PATCH 04/09] svcrdma: Add a service to register a Fast Reg MR with the device
>>
>> include/linux/sunrpc/svc_rdma.h          |    1 +
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |   53 ++++++++++++++++++++++++++---
>> 2 files changed, 48 insertions(+), 6 deletions(-)
>>
>> [PATCH 05/09] svcrdma: Modify post recv path to use local dma key
>>
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |   10 +++++++---
>> 1 files changed, 7 insertions(+), 3 deletions(-)
>>
>> [PATCH 06/09] svcrdma: Add support to svc_rdma_send to handle chained WR
>>
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |   29 +++++++++++++++++++++--------
>> 1 files changed, 21 insertions(+), 8 deletions(-)
>>
>> [PATCH 07/09] svcrdma: Modify the RPC recv path to use FRMR when available
>>
>> include/linux/sunrpc/svc_rdma.h          |    1 +
>> net/sunrpc/xprtrdma/svc_rdma_recvfrom.c  |  187 ++++++++++++++++++++++++++----
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |    5 +-
>> 3 files changed, 171 insertions(+), 22 deletions(-)
>>
>> [PATCH 08/09] svcrdma: Modify the RPC reply path to use FRMR when available
>>
>> net/sunrpc/xprtrdma/svc_rdma_sendto.c    |  263 +++++++++++++++++++++++++-----
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |    2 +
>> 2 files changed, 225 insertions(+), 40 deletions(-)
>>
>> [PATCH 09/09] svcrdma: Update svc_rdma_send_error to use DMA LKEY
>>
>> net/sunrpc/xprtrdma/svc_rdma_transport.c |   11 +++++++++--
>> 1 files changed, 9 insertions(+), 2 deletions(-)
>>

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[J. Bruce Fields]

On Wed, Aug 13, 2008 at 05:28:20PM -0500, Tom Tucker wrote:
> J. Bruce Fields wrote:
>> On Wed, Aug 13, 2008 at 11:06:29AM -0500, Tom Tucker wrote:
>>> This patchset implements support for Fast Memory Registration in the
>>> NFS server.  Fast Memory Regstration is the ability to quickly map a
>>> kernel memory page list as a logically contiguous memory region from
>>> the perspective of the adapter. This mapping is created and
>>> invalidated using work requests posted on the SQ. This allows for
>>> large amounts of data to transferred between the client and server
>>> with a single work request as well as the ability to invalidate a
>>> previously mapped memory region. For iWARP, this allows for "one-shot"
>>> memory regions to be mapped for a single NFS-RDMA data transfer. This
>>> improves security since a byzantine app listening on the net will have
>>> a very short window during which the RKEY is valid.
>>>
>>> This capability is only enabled if the underlying device advertises
>>> that it is supported.
>>
>> Thanks for your continuing work on this.
>>
>> I think we really need to document the security assumptions, though.
>>
>
> Yes, that's a good idea. Maybe a file in Documentation/svcrdma?

That would be great!  (Actually Documentation/filesystems/nfs-something
might be good.  Adding it to nfs-rdma.txt would be ideal.)

>
>> (Currently is your entire memory at the mercy of anyone on the same
>> local network as your rdma adapter?
>
> ------------------------------------------------------------------------
>
> A principal exploit is that a node listening on a mirror port of a switch
> could snoop RDMA packets containing RKEY and then forge a packet with this
> RKEY to write or read the memory of the peer to which the RKEY referred.

RKEY?  Apologies, I've been avoiding up till now asking about every bit
of jargon in hopes I could still get the gist, but I think I have to
give up and learn it.  Remind me what I need to read?

> The NFSRDMA protocol is defined such that a) only the server initiates
> RDMA, and b) only the client's memory is exposed via RKEY. This is why
> the server reads to fetch RPC data from the client even though it would
> be more efficient for the client to write the data to the server's memory.
>
> The above design goal is not entirely realized with iWARP, however, because
> the RKEY (called an STag on iWARP) for the data sink of an RDMA_READ is
> actually placed on the wire!

So "data sink" here means the server memory that the data's being copied
to?  OK.

> Not only that, iWARP (RDDP) requires that this
> RKEY have Remote Write! This means that the server's memory is exposed by
> virtue of having placed the RKEY for it's local memory on the wire in order
> to receive the result of the RDMA_READ.

Got it.

> By contrast, IB uses an opaque
> transaction ID# to associate the READ_RPL with the READ_REQ _and_ the data

Google gives only two hits for READ_RPL.  Help!

> sink of an RDMA_READ does not require remote access. That said, the evil node
> in question, for example, could potentially forge a packet with this
> transaction ID and corrupt the target memory, however, the duration
> of the exploit is this single READ_REQ.

OK.  So what would be the effect of the forged packet?

> The newer RDMA adapters (both iWARP and IB) support "Fast Memory Registration".
> This capability allows memory to be quickly registered and
> de-registered by submitting WR on the SQ. So the idea is to create an RKEY
> that ONLY maps the single RPC. So the WR sequence is post_map,
> post_rdma_read, post_invalidate. This has two benefits, a) it restricts the
> domain of the exploit to the memory of a single RPC,

So the only server-side memory that can be remotely written to is the
pages that will hold the write data?

> and b) it limits the
> duration of the exploit to the time it takes to satisfy the RDMA_READ.

OK.

>   If so, fixing that would certainly
>> make this stuff useful in more situations, but language like "a very
>> short window" doesn't sound promising.  Also, we've got to make sure
>> users understand where it's safe to use this stuff....)
>>
>
> There are those who argue that a one-shot STag/RKEY is no less secure than TCP.

If the attacker is limited to corrupting some write data, then, yes,
that doesn't sound so different from nfs/rcp with auth_unix.

> Consider that the exact same evil application could more easily corrupt RPC
> payload by simply forging a packet with the correct TCP sequence number --
> in fact it's easier than the RDMA exploit because the RDMA exploit requires
> that you correctly forge both the TCP packet _and_ the RDMA payload. In
> addition the duration of the TCP exploit is the lifetime of the connection, not
> the lifetime of a single WR.
>
> So if you buy the argument above, RDMA on IB or iWARP using Fast Reg is no
> less secure than TCP. That is the goal of this patch series.

OK, thanks.

--b.

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[Tom Tucker]

J. Bruce Fields wrote:
> On Wed, Aug 13, 2008 at 05:28:20PM -0500, Tom Tucker wrote:
>> J. Bruce Fields wrote:
>>> On Wed, Aug 13, 2008 at 11:06:29AM -0500, Tom Tucker wrote:
>>>> This patchset implements support for Fast Memory Registration in the
>>>> NFS server.  Fast Memory Regstration is the ability to quickly map a
>>>> kernel memory page list as a logically contiguous memory region from
>>>> the perspective of the adapter. This mapping is created and
>>>> invalidated using work requests posted on the SQ. This allows for
>>>> large amounts of data to transferred between the client and server
>>>> with a single work request as well as the ability to invalidate a
>>>> previously mapped memory region. For iWARP, this allows for "one-shot"
>>>> memory regions to be mapped for a single NFS-RDMA data transfer. This
>>>> improves security since a byzantine app listening on the net will have
>>>> a very short window during which the RKEY is valid.
>>>>
>>>> This capability is only enabled if the underlying device advertises
>>>> that it is supported.
>>> Thanks for your continuing work on this.
>>>
>>> I think we really need to document the security assumptions, though.
>>>
>> Yes, that's a good idea. Maybe a file in Documentation/svcrdma?
> 
> That would be great!  (Actually Documentation/filesystems/nfs-something
> might be good.  Adding it to nfs-rdma.txt would be ideal.)
> 
>>> (Currently is your entire memory at the mercy of anyone on the same
>>> local network as your rdma adapter?
>> ------------------------------------------------------------------------
>>
>> A principal exploit is that a node listening on a mirror port of a switch
>> could snoop RDMA packets containing RKEY and then forge a packet with this
>> RKEY to write or read the memory of the peer to which the RKEY referred.
> 
> RKEY?  Apologies, I've been avoiding up till now asking about every bit
> of jargon in hopes I could still get the gist, but I think I have to
> give up and learn it.  Remind me what I need to read?

Erf. You can read the IBTA/IETF specs. (see below), but that's overkill. 
Here's brief cheat-sheet:

- MR - Memory Region. A region of memory registered with the adapter and 
referred to with an identifier. For iWARP, the identifier is called an 
STag (Steering Tag). For IB, it's called an [L|R]KEY.

- RKEY	- Remote Key. A MR identifier exchanged on the wire between peers 
that allows the remote peer to access the issuing peer's memory. The 
permissions (REMOTE_READ, REMOTE_WRITE, LOCAL_READ, LOCAL_WRITE) are 
assigned at the time the MR is created/registered

- LKEY - Local Key. A MR identifer used locally to refer to an MR 
registered with the adapter. Can only the have local access rights above.

- STag - Steering Tag, can have both local and remote access rights.

For the OFA verbs, we refer to everything as an LKEY/RKEY.

FastReg adds the feature that an STag/RKEY can be created and then 
iteratively registered/invalidated.

> 
>> The NFSRDMA protocol is defined such that a) only the server initiates
>> RDMA, and b) only the client's memory is exposed via RKEY. This is why
>> the server reads to fetch RPC data from the client even though it would
>> be more efficient for the client to write the data to the server's memory.
>>
>> The above design goal is not entirely realized with iWARP, however, because
>> the RKEY (called an STag on iWARP) for the data sink of an RDMA_READ is
>> actually placed on the wire!
> 
> So "data sink" here means the server memory that the data's being copied
> to?  OK.

Yes.

> 
>> Not only that, iWARP (RDDP) requires that this
>> RKEY have Remote Write! This means that the server's memory is exposed by
>> virtue of having placed the RKEY for it's local memory on the wire in order
>> to receive the result of the RDMA_READ.
> 
> Got it.
> 
>> By contrast, IB uses an opaque
>> transaction ID# to associate the READ_RPL with the READ_REQ _and_ the data
> 
> Google gives only two hits for READ_RPL.  Help!

Sorry, I'm trying to generalize and glossing over details trying to get 
to the meat of it...

The verbs request (WR) is an RDMA_READ. On the wire, this becomes 
READ_REQ (read-request, ask the peer to read its memory), followed by 
some number of READ_RPL (read replies, # depends on amount read/mtu). 
The READ_REQ contains the RKEY from which you wish to read, the READ_RPL 
contains the target buffer spec + data. For iWARP this READ_RPL message 
contains a local memory ID (i.e. LKEY) + payload. For IB it contains the 
transaction ID + payload.

> 
>> sink of an RDMA_READ does not require remote access. That said, the evil node
>> in question, for example, could potentially forge a packet with this
>> transaction ID and corrupt the target memory, however, the duration
>> of the exploit is this single READ_REQ.
> 
> OK.  So what would be the effect of the forged packet?
> 

Corrupting the local memory that you are reading the remote payload 
into. So I try to read "hello" from the peer, but the troll under the 
bridge writes "goodbye" into this buffer.

The scope of the corruption depends on the amount of local memory 
exposed by the LKEY. This goal of the patches is to minimize this memory 
footprint to just the RPC memory into which we're reading.

>> The newer RDMA adapters (both iWARP and IB) support "Fast Memory Registration".
>> This capability allows memory to be quickly registered and
>> de-registered by submitting WR on the SQ. So the idea is to create an RKEY
>> that ONLY maps the single RPC. So the WR sequence is post_map,
>> post_rdma_read, post_invalidate. This has two benefits, a) it restricts the
>> domain of the exploit to the memory of a single RPC,
> 
> So the only server-side memory that can be remotely written to is the
> pages that will hold the write data?
> 
>> and b) it limits the
>> duration of the exploit to the time it takes to satisfy the RDMA_READ.
> 
> OK.
> 
>>   If so, fixing that would certainly
>>> make this stuff useful in more situations, but language like "a very
>>> short window" doesn't sound promising.  Also, we've got to make sure
>>> users understand where it's safe to use this stuff....)
>>>
>> There are those who argue that a one-shot STag/RKEY is no less secure than TCP.
> 
> If the attacker is limited to corrupting some write data, then, yes,
> that doesn't sound so different from nfs/rcp with auth_unix.
> 
>> Consider that the exact same evil application could more easily corrupt RPC
>> payload by simply forging a packet with the correct TCP sequence number --
>> in fact it's easier than the RDMA exploit because the RDMA exploit requires
>> that you correctly forge both the TCP packet _and_ the RDMA payload. In
>> addition the duration of the TCP exploit is the lifetime of the connection, not
>> the lifetime of a single WR.
>>
>> So if you buy the argument above, RDMA on IB or iWARP using Fast Reg is no
>> less secure than TCP. That is the goal of this patch series.
> 
> OK, thanks.
>

Here are the relevant specs:

Unfortunately, the IB specs are private to the IBTA.
http://www.infinibandta.org/home

The OFA verbs most closely resemble IB verbs.

Here are the iWARP protocol specs:

http://www.ietf.org/rfc/rfc5040.txt
http://www.ietf.org/rfc/rfc5041.txt
http://www.ietf.org/rfc/rfc5044.txt

Here are the iWARP verbs specs. This is what the adapters where written to.

http://www.rdmaconsortium.org/home/RNIC_Verbs_Overview2.pdf
http://www.rdmaconsortium.org/home/draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf

Tom

> --b.

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[J. Bruce Fields]

On Thu, Aug 14, 2008 at 04:23:09PM -0500, Tom Tucker wrote:
> Here are the relevant specs:
>
> Unfortunately, the IB specs are private to the IBTA.
> http://www.infinibandta.org/home
>
> The OFA verbs most closely resemble IB verbs.
>
> Here are the iWARP protocol specs:
>
> http://www.ietf.org/rfc/rfc5040.txt
> http://www.ietf.org/rfc/rfc5041.txt
> http://www.ietf.org/rfc/rfc5044.txt
>
> Here are the iWARP verbs specs. This is what the adapters where written to.
>
> http://www.rdmaconsortium.org/home/RNIC_Verbs_Overview2.pdf
> http://www.rdmaconsortium.org/home/draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf

OK, thanks very much to you and James for all the explanation.  And
actually the IB specs do appear to be available if you give them your
name and address?

So could one of you add some of this (the explanation of the security
issues, at least) to Documentation/filesystems/nfs-rdma.txt?

I'm worried about the fact that the amount of trust required in the
network will vary so much depending on exactly which hardware and kernel
version the user has.

As long as this is relatively specialized hardware, perhaps it's not
such a big deal....  But at the very least I think we should make sure
this is carefully documented.

--b.

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[Tom Tucker]

J. Bruce Fields wrote:
> On Thu, Aug 14, 2008 at 04:23:09PM -0500, Tom Tucker wrote:
>> Here are the relevant specs:
>>
>> Unfortunately, the IB specs are private to the IBTA.
>> http://www.infinibandta.org/home
>>
>> The OFA verbs most closely resemble IB verbs.
>>
>> Here are the iWARP protocol specs:
>>
>> http://www.ietf.org/rfc/rfc5040.txt
>> http://www.ietf.org/rfc/rfc5041.txt
>> http://www.ietf.org/rfc/rfc5044.txt
>>
>> Here are the iWARP verbs specs. This is what the adapters where written to.
>>
>> http://www.rdmaconsortium.org/home/RNIC_Verbs_Overview2.pdf
>> http://www.rdmaconsortium.org/home/draft-hilland-iwarp-verbs-v1.0-RDMAC.pdf
> 
> OK, thanks very much to you and James for all the explanation.  And
> actually the IB specs do appear to be available if you give them your
> name and address?
> 
> So could one of you add some of this (the explanation of the security
> issues, at least) to Documentation/filesystems/nfs-rdma.txt?
> 
> I'm worried about the fact that the amount of trust required in the
> network will vary so much depending on exactly which hardware and kernel
> version the user has.
> 
> As long as this is relatively specialized hardware, perhaps it's not
> such a big deal....  But at the very least I think we should make sure
> this is carefully documented.
> 

ok. will do.

> --b.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH,RFC 00/09] svcrdma: Fast Memory Registration Support

[James Lentini]

On Thu, 14 Aug 2008, J. Bruce Fields wrote:

> On Wed, Aug 13, 2008 at 05:28:20PM -0500, Tom Tucker wrote:
> > J. Bruce Fields wrote:
> >> On Wed, Aug 13, 2008 at 11:06:29AM -0500, Tom Tucker wrote:
> >>> This patchset implements support for Fast Memory Registration in the
> >>> NFS server.  Fast Memory Regstration is the ability to quickly map a
> >>> kernel memory page list as a logically contiguous memory region from
> >>> the perspective of the adapter. This mapping is created and
> >>> invalidated using work requests posted on the SQ. This allows for
> >>> large amounts of data to transferred between the client and server
> >>> with a single work request as well as the ability to invalidate a
> >>> previously mapped memory region. For iWARP, this allows for "one-shot"
> >>> memory regions to be mapped for a single NFS-RDMA data transfer. This
> >>> improves security since a byzantine app listening on the net will have
> >>> a very short window during which the RKEY is valid.
> >>>
> >>> This capability is only enabled if the underlying device advertises
> >>> that it is supported.
> >>
> >> Thanks for your continuing work on this.
> >>
> >> I think we really need to document the security assumptions, though.
> >>
> >
> > Yes, that's a good idea. Maybe a file in Documentation/svcrdma?
> 
> That would be great!  (Actually Documentation/filesystems/nfs-something
> might be good.  Adding it to nfs-rdma.txt would be ideal.)
> 
> >
> >> (Currently is your entire memory at the mercy of anyone on the same
> >> local network as your rdma adapter?
> >
> > ------------------------------------------------------------------------
> >
> > A principal exploit is that a node listening on a mirror port of a switch
> > could snoop RDMA packets containing RKEY and then forge a packet with this
> > RKEY to write or read the memory of the peer to which the RKEY referred.
> 
> RKEY?  Apologies, I've been avoiding up till now asking about every bit
> of jargon in hopes I could still get the gist, but I think I have to
> give up and learn it.  Remind me what I need to read?

The IBTA InfiniBand spec (http://www.infinibandta.org) and the IETF 
iWARP specs, RDMAP (RFC5040), DDP (RFC5041), and MPA (RFC5044), are 
good places to start.

> > The NFSRDMA protocol is defined such that a) only the server initiates
> > RDMA, and b) only the client's memory is exposed via RKEY. This is why
> > the server reads to fetch RPC data from the client even though it would
> > be more efficient for the client to write the data to the server's memory.
> >
> > The above design goal is not entirely realized with iWARP, however, because
> > the RKEY (called an STag on iWARP) for the data sink of an RDMA_READ is
> > actually placed on the wire!
> 
> So "data sink" here means the server memory that the data's being copied
> to?  OK.

Yes.

> > Not only that, iWARP (RDDP) requires that this
> > RKEY have Remote Write! This means that the server's memory is exposed by
> > virtue of having placed the RKEY for it's local memory on the wire in order
> > to receive the result of the RDMA_READ.
> 
> Got it.
> 
> > By contrast, IB uses an opaque
> > transaction ID# to associate the READ_RPL with the READ_REQ _and_ the data
> 
> Google gives only two hits for READ_RPL.  Help!

READ reply. This is the ack of the READ_REQ that contains the data 
that was read.

> 
> > sink of an RDMA_READ does not require remote access. That said, 
> > the evil node in question, for example, could potentially forge a 
> > packet with this transaction ID and corrupt the target memory, 
> > however, the duration of the exploit is this single READ_REQ.
> 
> OK.  So what would be the effect of the forged packet?

The data sink of the RDMA read would have bogus data.

> 
> > The newer RDMA adapters (both iWARP and IB) support "Fast Memory Registration".
> > This capability allows memory to be quickly registered and
> > de-registered by submitting WR on the SQ. So the idea is to create an RKEY
> > that ONLY maps the single RPC. So the WR sequence is post_map,
> > post_rdma_read, post_invalidate. This has two benefits, a) it restricts the
> > domain of the exploit to the memory of a single RPC,
> 
> So the only server-side memory that can be remotely written to is the
> pages that will hold the write data?


For iWARP yes.

As Tom described, an InfiniBand RDMA Read operations doesn't require 
the data sink of the RDMA Read to be remotely writable.

> 
> > and b) it limits the
> > duration of the exploit to the time it takes to satisfy the RDMA_READ.
> 
> OK.
> 
> >   If so, fixing that would certainly
> >> make this stuff useful in more situations, but language like "a very
> >> short window" doesn't sound promising.  Also, we've got to make sure
> >> users understand where it's safe to use this stuff....)
> >>
> >
> > There are those who argue that a one-shot STag/RKEY is no less secure than TCP.
> 
> If the attacker is limited to corrupting some write data, then, yes,
> that doesn't sound so different from nfs/rcp with auth_unix.
> 
> > Consider that the exact same evil application could more easily corrupt RPC
> > payload by simply forging a packet with the correct TCP sequence number --
> > in fact it's easier than the RDMA exploit because the RDMA exploit requires
> > that you correctly forge both the TCP packet _and_ the RDMA payload. In
> > addition the duration of the TCP exploit is the lifetime of the connection, not
> > the lifetime of a single WR.
> >
> > So if you buy the argument above, RDMA on IB or iWARP using Fast Reg is no
> > less secure than TCP. That is the goal of this patch series.
> 
> OK, thanks.
> 
> --b.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>