The IB SA tracks multicast join/leave requests on a per port basis and
does not do any reference counting: if two users of the same port join
the same group, and one leaves that group, then the SA will remove the
port from the group even though there is one user who wants to stay a
member left. Therefore, in order to support multiple users of the
same multicast group from the same port, we need to perform reference
counting locally.
To do this, add an multicast submodule to ib_sa to perform reference
counting of multicast join/leave operations. Modify ib_ipoib (the
only in-kernel user of multicast) to use the new interface.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
ipoib_cm_alloc_rx_skb() might be called from IRQ context, so it must
use dev_kfree_skb_any(), not kfree_skb().
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
* 'for-linus' of master.kernel.org:/pub/scm/linux/kernel/git/roland/infiniband:
IB/mthca: Always fill MTTs from CPU
IB/mthca: Merge MR and FMR space on 64-bit systems
IB/mthca: Fix access to MTT and MPT tables on non-cache-coherent CPUs
IB/mthca: Give reserved MTTs a separate cache line
IB/mthca: Fix reserved MTTs calculation on mem-free HCAs
RDMA/cxgb3: Add driver for Chelsio T3 RNIC
IB: Remove redundant "_wq" from workqueue names
RDMA/cma: Increment port number after close to avoid re-use
IB/ehca: Fix memleak on module unloading
IB/mthca: Work around gcc bug on sparc64
IPoIB: Connected mode experimental support
IB/core: Use ARRAY_SIZE macro for mandatory_table
IB/mthca: Use correct structure size in call to memset()
Many struct file_operations in the kernel can be "const". Marking them const
moves these to the .rodata section, which avoids false sharing with potential
dirty data. In addition it'll catch accidental writes at compile time to
these shared resources.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The following patch adds experimental support for IPoIB connected
mode, as defined by the draft from the IETF ipoib working group. The
idea is to increase performance by increasing the MTU from the maximum
of 2K (theoretically 4K) supported by IPoIB on top of UD. With this
code, I'm able to get 800MByte/sec or more with netperf without
options on a Mellanox 4x back-to-back DDR system.
Some notes on code:
1. SRQ is used for scalability to large cluster sizes
2. Only RC connections are used (UC does not support SRQ now)
3. Retry count is set to 0 since spec draft warns against retries
4. Each connection is used for data transfers in only 1 direction, so
each connection is either active(TX) or passive (RX). 2 sides that
want to communicate create 2 connections.
5. Each active (TX) connection has a separate CQ for send completions -
this keeps the code simple without CQ resize and other tricks
6. To detect stale passive side connections (where the remote side is
down), we keep an LRU list of passive connections (updated once per
second per connection) and destroy a connection after it has been
unused for several seconds. The LRU rule makes it possible to avoid
scanning connections that have recently been active.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This lets the network core have the ability to handle suspend/resume
issues, if it wants to.
Thanks to Frederik Deweerdt <frederik.deweerdt@gmail.com> for the arm
driver fixes.
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
When there is a call to send_tsk_mgmt SRP posts a send and waits for 5
seconds to get a response.
When the QP is in the error state it is obvious that there will be no
response so it is quite useless to wait. In fact, the timeout causes
SRP to wait a long time to reconnect when a QP error occurs. (Each
abort and each reset_device calls send_tsk_mgmt, which waits for the
timeout). The following patch solves this problem by identifying the
failure and returning an immediate error code.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Checks if the kmalloc in match_strdup() was successful, and bail out
on looking at the token if it failed.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
iSER limits the number of outstanding PDUs to send. When this threshold
is reached, it should return an error code (-ENOBUFS) instead of setting
the suspend_tx bit (which should be used only by libiscsi).
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
struct srp_device.fmr_page_mask was unsigned long, which means that
the top part of addresses above 4G was being chopped off on 32-bit
architectures. Of course nothing good happens when data from SRP
targets is DMAed to the wrong place.
Fix this by changing fmr_page_mask to u64, to match the addresses
actually used by IB devices.
Thanks to Brian Cain <Brian.Cain@ge.com> and David McMillen
<davem@systemfabricworks.com> for help diagnosing the bug and testing
the fix.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Move the initialization of ipoib_neigh's skb_queue into
ipoib_neigh_alloc(), since commit 2745b5b7 ("IPoIB: Fix skb leak when
freeing neighbour") will make iterate over the skb_queue to free any
packets left over when freeing the ipoib_neigh structure.
This fixes a crash when freeing ipoib_neigh structures allocated in
ipoib_mcast_send(), which otherwise don't have their skb_queue
initialized.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Convert iSER to use the new verbs DMA mapping functions for kernel
verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Convert SRP to use the new verbs DMA mapping functions for kernel
verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Convert IPoIB to use the new DMA mapping functions
for kernel verbs consumers.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Remove variables that are set but then never looked at in the iSER
initiator. These cleanups came from David Binderman's list of "set
but never used" warnings from icc.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This facility provides three entry points:
ilog2() Log base 2 of unsigned long
ilog2_u32() Log base 2 of u32
ilog2_u64() Log base 2 of u64
These facilities can either be used inside functions on dynamic data:
int do_something(long q)
{
...;
y = ilog2(x)
...;
}
Or can be used to statically initialise global variables with constant values:
unsigned n = ilog2(27);
When performing static initialisation, the compiler will report "error:
initializer element is not constant" if asked to take a log of zero or of
something not reducible to a constant. They treat negative numbers as
unsigned.
When not dealing with a constant, they fall back to using fls() which permits
them to use arch-specific log calculation instructions - such as BSR on
x86/x86_64 or SCAN on FRV - if available.
[akpm@osdl.org: MMC fix]
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: David Howells <dhowells@redhat.com>
Cc: Wojtek Kaniewski <wojtekka@toxygen.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Conflicts:
drivers/ata/libata-scsi.c
include/linux/libata.h
Futher merge of Linus's head and compilation fixups.
Signed-Off-By: David Howells <dhowells@redhat.com>
Conflicts:
drivers/infiniband/core/iwcm.c
drivers/net/chelsio/cxgb2.c
drivers/net/wireless/bcm43xx/bcm43xx_main.c
drivers/net/wireless/prism54/islpci_eth.c
drivers/usb/core/hub.h
drivers/usb/input/hid-core.c
net/core/netpoll.c
Fix up merge failures with Linus's head and fix new compilation failures.
Signed-Off-By: David Howells <dhowells@redhat.com>
ipoib_neigh_free() is sometimes called while neighbour is still alive,
so it might still have queued skbs. Fix skb leak in this case.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
SRP reallocates the IU buffers for tx_ring and rx_ring without freeing
the old buffers when it reconnects to a target. Fix this by keeping
the old IU buffers around.
Signed-off-by: Vu Pham <vu@mellanox.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Set the Scsi_Host's max_cmd_len from 12 (default) to 16 for
SRP. Otherwise scsi_dispatch_cmd() won't pass down certain commands
such as READ CAPACITY 16, required for supporting disks > 2TB.
Signed-off-by: Arne Redlich <arne.redlich@xiranet.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
IPoIB assumes that high (reserved) octet in the hardware address is 0,
and copies it into the QPN. This violates RFC 4391 (which requires
that the high 8 bits are ignored on receive), and will result in an
invalid QPN being used when interoperating with IPoIB connected mode.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When a connection is started (a new connection or a recovered one),
iSER should prepare its resources for full-featured mode and only then
notify the iSCSI layer that it is ready to start queueing commands.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Enable multiple concurrent connections to the same SRP target:
1) Use port GUID instead of node GUID in the initiator port
identifier. This allows connections to be made from multiple HCA
ports at the same time.
2) Let the user specify the identifier extention when adding the
device. This allows userspace to make multiple connections even
from the same port, if it wants too.
Without this, only one connection can be made from any given HCA, even
if it has multiple ports, because we don't use multi-channel mode, so
targets will only allow one connection from a given initiator port ID.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
scsi_host_alloc() already allocates with kzalloc(), so the struct Scsi_Host
is zeroed out, including the private data portion. Remove the redundant
memset that zeros this out again in the SRP initiator.
Signed-off-by: Ishai Rabinovitz <ishai@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fix the description of iSER in Kconfig. It is not accurate.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
iSER uses the DMA mapping api to map the page holding the
SCSI command data to the HCA DMA address space. When the
command data is not aligned for RDMA, the data is copied
to/from an allocated buffer which in turn is used for
executing this command. The pages associated with the
command must be unmapped before being touched.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
iSER uses a data transaction object (struct iser_dto) as part
of its IB data descriptors (struct iser_desc) management.
It also uses a hierarchy of connection structures pointing to
each other. A DTO may exist even after the iscsi_iser connection
pointed by it is destroyed (eg one that is bound to a post
receive buffer which was flushed by the IB HW). Hence DTOs need
point to the lowest connection, which is struct iser_conn.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The following patches reduce the size of the VFS inode structure by 28 bytes
on a UP x86. (It would be more on an x86_64 system). This is a 10% reduction
in the inode size on a UP kernel that is configured in a production mode
(i.e., with no spinlock or other debugging functions enabled; if you want to
save memory taken up by in-core inodes, the first thing you should do is
disable the debugging options; they are responsible for a huge amount of bloat
in the VFS inode structure).
This patch:
The filesystem or device-specific pointer in the inode is inside a union,
which is pretty pointless given that all 30+ users of this field have been
using the void pointer. Get rid of the union and rename it to i_private, with
a comment to explain who is allowed to use the void pointer. This is just a
cleanup, but it allows us to reuse the union 'u' for something something where
the union will actually be used.
[judith@osdl.org: powerpc build fix]
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Judith Lebzelter <judith@osdl.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
IPoIB doesn't use anything from <linux/vmalloc.h>, so don't include it.
Signed-off-by: Dotan Barak <dotanb@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When ipoib_ib_dev_flush() is called because of a port event, the
driver needs to rejoin all multicast groups, since the flush will call
ipoib_mcast_dev_flush() (via ipoib_ib_dev_down()). Otherwise no
(non-broadcast) multicast groups will be rejoined until the networking
core calls ->set_multicast_list again, and so multicast reception will
be broken for potentially a long time.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
RFC 4391 ("Transmission of IP over InfiniBand (IPoIB)") says:
If the IB multicast group does not already exist, one must be
created first with the IPoIB link MTU. The MGID MUST use the same
P_Key, Q_Key, SL, MTU, and HopLimit as those used in the
broadcast-GID. The rest of attributes SHOULD follow the values used
in the broadcast-GID as well.
However, the current IPoIB driver is only setting the attributes
required by the InfiniBand spec to create a multicast group, so in
particular the MTU and HopLimit are not being set. Add these
attributes when creating MCGs, and also set the Rate attribute, since
IPoIB pays attention to that attribute as well.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Require users to register with SA module, to prevent the sa_query
module text from going away while an SA query callback is still
running. Update all in-tree users for the new interface.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Split up ipoib_ib_handle_wc() into ipoib_ib_handle_rx_wc() and
ipoib_ib_handle_tx_wc() to make the code easier to read. This will
also help implement NAPI in the future.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Fast Memory Registration (fmr) is used to register for rdma an sg whose
elements are not linearly sequential after dma mapping.
The IB verbs layer provides an "all dma memory MR (memory region)" which
can be used for RDMA-ing a dma linearly sequential buffer.
Change the code to use the dma mr instead of doing fmr when dma mapping
produces a single dma entry sg.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
fix and add some debug prints related to iser
handling of memory for rdma.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
As iser is able to use at most one rdma operation for the
execution of a scsi command, and registration of the sg
associated with scsi command has its restrictions, the code
checks if an sg is "aligned for rdma".
Alignment for rdma is measured in "fmr page" units whose
possible resolutions are different between HCAs and can be
smaller, equal or bigger to the system page size.
When the system page size is bigger than 4KB (eg the default
with ia64 kernels) there a bigger chance that an sg would be
aligned for rdma if the fmr page size is 4KB.
Change the code to create FMR whose pages are of size 4KB
and to take that into account when processing the sg.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Currently, the data length of a command coming down from scsi-ml
is limited only by the size of its sg list (sg_tablesize). The
max data length may be different for different page size values.
By setting max_sectors, we limit the data length to
max_sectors*512 bytes.
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
dma mapping may include a "compaction" of the sg associated with scsi command.
Hence, the size of the maximal prefix of the SG which is aligned for rdma must be
compared against the length of the dma mapped sg (mem->dma_nents) and not against
the size of it before it was mapped (mem->size).
Signed-off-by: Erez Zilber <erezz@voltaire.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Modifications to the existing rdma header files, core files, drivers,
and ulp files to support iWARP, including:
- Hook iWARP CM into the build system and use it in rdma_cm.
- Convert enum ib_node_type to enum rdma_node_type, which includes
the possibility of RDMA_NODE_RNIC, and update everything for this.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
