This patch split up struct ib_send_wr so that all non-trivial verbs
use their own structure which embedds struct ib_send_wr. This dramaticly
shrinks the size of a WR for most common operations:
sizeof(struct ib_send_wr) (old): 96
sizeof(struct ib_send_wr): 48
sizeof(struct ib_rdma_wr): 64
sizeof(struct ib_atomic_wr): 96
sizeof(struct ib_ud_wr): 88
sizeof(struct ib_fast_reg_wr): 88
sizeof(struct ib_bind_mw_wr): 96
sizeof(struct ib_sig_handover_wr): 80
And with Sagi's pending MR rework the fast registration WR will also be
down to a reasonable size:
sizeof(struct ib_fastreg_wr): 64
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@sandisk.com> [srp, srpt]
Reviewed-by: Chuck Lever <chuck.lever@oracle.com> [sunrpc]
Tested-by: Haggai Eran <haggaie@mellanox.com>
Tested-by: Sagi Grimberg <sagig@mellanox.com>
Tested-by: Steve Wise <swise@opengridcomputing.com>
Kernel coding conventions frown upon having large nontrivial
functions in header files, and the preference these days is to
allow the compiler to make inlining decisions if possible.
As these functions are re-homed into a .c file, be sure that
comparisons with fields in struct rpcrdma_msg are with be32
constants.
This is a refactoring change; no behavior change is intended.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The Linux NFS server returns garbage in the data payload of inline
NFS/RDMA READ replies. These are READs of under 1000 bytes or so
where the client has not provided either a reply chunk or a write
list.
The NFS server delivers the data payload for an NFS READ reply to
the transport in an xdr_buf page list. If the NFS client did not
provide a reply chunk or a write list, send_reply() is supposed to
set up a separate sge for the page containing the READ data, and
another sge for XDR padding if needed, then post all of the sges via
a single SEND Work Request.
The problem is send_reply() does not advance through the xdr_buf
when setting up scatter/gather entries for SEND WR. It always calls
dma_map_xdr with xdr_off set to zero. When there's more than one
sge, dma_map_xdr() sets up the SEND sge's so they all point to the
xdr_buf's head.
The current Linux NFS/RDMA client always provides a reply chunk or
a write list when performing an NFS READ over RDMA. Therefore, it
does not exercise this particular case. The Linux server has never
had to use more than one extra sge for building RPC/RDMA replies
with a Linux client.
However, an NFS/RDMA client _is_ allowed to send small NFS READs
without setting up a write list or reply chunk. The NFS READ reply
fits entirely within the inline reply buffer in this case. This is
perhaps a more efficient way of performing NFS READs that the Linux
NFS/RDMA client may some day adopt.
Fixes: b432e6b3d9 ('svcrdma: Change DMA mapping logic to . . .')
BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=285
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
At the 2015 LSF/MM, it was requested that memory allocation
call sites that request GFP_KERNEL allocations in a loop should be
annotated with __GFP_NOFAIL.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
In send_write_chunks(), we have:
for (xdr_off = rqstp->rq_res.head[0].iov_len, chunk_no = 0;
xfer_len && chunk_no < arg_ary->wc_nchunks;
chunk_no++) {
. . .
}
Note that arg_ary->wc_nchunk is in network byte-order. For the
comparison to work correctly, both have to be in native byte-order.
In send_reply_chunks, we have:
write_len = min(xfer_len, htonl(ch->rs_length));
xfer_len is in native byte-order, and ch->rs_length is in
network byte-order. be32_to_cpu() is the correct byte swap
for ch->rs_length.
As an additional clean up, replace ntohl() with be32_to_cpu() in
a few other places.
This appears to address a problem with large rsize hangs while
using PHYSICAL memory registration. I suspect that is the only
registration mode that uses more than one chunk element.
BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=248
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
xdr_start() can return the wrong rmsgp address if an assumption
about how the xdr_buf was constructed changes. When it gets it
wrong, the client receives a reply that has gibberish in the
RPC/RDMA header, preventing it from matching a waiting RPC request.
Instead, make (and document) just one assumption: that the RDMA
header for the client's RPC call is at the start of the first page
in rq_pages.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Current convention is to avoid using BUG_ON() in places where an
oops could cause complete system failure.
Replace BUG_ON() call sites in svcrdma with an assertion error
message and allow execution to continue safely.
Some BUG_ON() calls are removed because they have never fired in
production (that we are aware of).
Some WARN_ON() calls are also replaced where a back trace is not
helpful; e.g., in a workqueue task.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Function send_write() must stop creating sges when it reaches the device
max and return the amount sent in the RDMA Write to the caller.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
This patch refactors the NFSRDMA server marshalling logic to
remove the intermediary map structures. It also fixes an existing bug
where the NFSRDMA server was not minding the device fast register page
list length limitations.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
The xdr_off value in dma_map_xdr gets passed to ib_dma_map_page as the
offset into the page to be mapped. This calculation does not correctly
take into account the case where the data starts at some offset into
the page. Increment the xdr_off by the page_base to ensure that it is
respected.
Cc: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The server regression was caused by the addition of rq_next_page
(afc59400d6). There were a few places that
were missed with the update of the rq_respages array.
Signed-off-by: Tom Tucker <tom@ogc.us>
Tested-by: Steve Wise <swise@ogc.us>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The svcrdma transport was un-marshalling requests in-place. This resulted
in sparse warnings due to __beXX data containing both NBO and HBO data.
The code has been restructured to do byte-swapping as the header is
parsed instead of when the header is validated immediately after receipt.
Also moved extern declarations for the workqueue and memory pools to the
private header file.
Signed-off-by: Tom Tucker <tom@ogc.us>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
There are several error paths in the code that do not unmap DMA. This
patch adds calls to svc_rdma_unmap_dma to free these DMA contexts.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
There was logic in the send path that assumed that a page containing data
to send to the client has a KVA. This is not always the case and can result
in data corruption when page_address returns zero and we end up DMA mapping
zero.
This patch changes the bus mapping logic to avoid page_address() where
necessary and converts all calls from ib_dma_map_single to ib_dma_map_page
in order to keep the map/unmap calls symmetric.
Signed-off-by: Tom Tucker <tom@ogc.us>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
The svcrdma module was incorrectly unmapping the RPCRDMA header page.
On IBM pserver systems this causes a resource leak that results in
running out of bus address space (10 cthon iterations will reproduce it).
The code was mapping the full page but only unmapping the actual header
length. The fix is to only map the header length.
I also cleaned up the use of ib_dma_map_page() calls since the unmap
logic always uses ib_dma_unmap_single(). I made these symmetrical.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
These fixes resolved crashes due to resource leak BUG_ON checks. The
resource leaks were detected by introducing asynchronous transport errors.
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
printk formats in prior commit were reversed/incorrect.
Compiled without warning on x86 and x86_64, but detected on ppc.
Signed-off-by: Tom Talpey <tmtalpey@gmail.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Certain client-provided RPCRDMA chunk alignments result in an
additional scatter/gather entry, which triggered nfs/rdma server
assertions incorrectly. OpenSolaris nfs/rdma client connectathon
testing was blocked by these in the special/locking section.
Signed-off-by: Tom Talpey <tmtalpey@gmail.com>
Cc: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Use FRMR to map local RPC reply data. This allows RDMA_WRITE to send reply
data using a single WR. The FRMR is invalidated by linking the LOCAL_INV WR
to the RDMA_SEND message used to complete the reply.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER
architecture does:
This enables us to cleanly fix the Calgary IOMMU issue that some devices
are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423).
I think that per-device dma_mapping_ops support would be also helpful for
KVM people to support PCI passthrough but Andi thinks that this makes it
difficult to support the PCI passthrough (see the above thread). So I
CC'ed this to KVM camp. Comments are appreciated.
A pointer to dma_mapping_ops to struct dev_archdata is added. If the
pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's
NULL, the system-wide dma_ops pointer is used as before.
If it's useful for KVM people, I plan to implement a mechanism to register
a hook called when a new pci (or dma capable) device is created (it works
with hot plugging). It enables IOMMUs to set up an appropriate
dma_mapping_ops per device.
The major obstacle is that dma_mapping_error doesn't take a pointer to the
device unlike other DMA operations. So x86 can't have dma_mapping_ops per
device. Note all the POWER IOMMUs use the same dma_mapping_error function
so this is not a problem for POWER but x86 IOMMUs use different
dma_mapping_error functions.
The first patch adds the device argument to dma_mapping_error. The patch
is trivial but large since it touches lots of drivers and dma-mapping.h in
all the architecture.
This patch:
dma_mapping_error() doesn't take a pointer to the device unlike other DMA
operations. So we can't have dma_mapping_ops per device.
Note that POWER already has dma_mapping_ops per device but all the POWER
IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device
argument.
[akpm@linux-foundation.org: fix sge]
[akpm@linux-foundation.org: fix svc_rdma]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix bnx2x]
[akpm@linux-foundation.org: fix s2io]
[akpm@linux-foundation.org: fix pasemi_mac]
[akpm@linux-foundation.org: fix sdhci]
[akpm@linux-foundation.org: build fix]
[akpm@linux-foundation.org: fix sparc]
[akpm@linux-foundation.org: fix ibmvscsi]
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Muli Ben-Yehuda <muli@il.ibm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Avi Kivity <avi@qumranet.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a dma map count in order to verify that all DMA mapping resources
have been freed when the transport is closed.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Use the new svc_rdma_req_map data type for mapping the client side memory
to the server side memory. Move the DMA mapping to the context pointed to
by each WR individually so that it is unmapped after the WR completes.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
If an error is encountered trying to post a recv buffer in send_reply,
free the passed in context. Return an error to the caller so it is
aware that the request was not posted.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
The svcrdma transport provider currently allocates receive buffers
to the RQ through the xpo_release_rqst method. This approach is overly
complicated since it means that the rqstp rq_xprt_ctxt has to be
selectively set based on whether the RPC is going to be processed
immediately or deferred. Instead, just post the receive buffer when
we are certain that we are replying in the send_reply function.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
The assertion that checks for sge context overflow is
incorrectly hard-coded to 32. This causes a kernel bug
check when using big-data mounts. Changed the BUG_ON to
use the computed value RPCSVC_MAXPAGES.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
net/sunrpc/xprtrdma/svc_rdma_sendto.c:160: warning: format '%llx'
expects type 'long long unsigned int', but argument 3 has type 'u64'
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
This file implements the RDMA transport sendto function. A RPC reply
on an RDMA transport consists of some number of RDMA_WRITE requests
followed by an RDMA_SEND request. The sendto function parses the
ONCRPC RDMA reply header to determine how to send the reply back to
the client. The send queue is sized so as to be able to send complete
replies for requests in most cases. In the event that there are not
enough SQ WR slots to reply, e.g. big data, the send will block the
NFSD thread. The I/O callback functions in svc_rdma_transport.c that
reap WR completions wake any waiters blocked on the SQ. In general,
the goal is not to block NFSD threads and the has_wspace method
stall requests when the SQ is nearly full.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Acked-by: Neil Brown <neilb@suse.de>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
