When the last packet of a RDMA write with immediate is received, the
next receive work queue entry ID should be used to generate a completion
entry. The code was incorrectly resetting part of the state used to copy
the last packet.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The code to set the source LID in the sent LRH was not setting the low
bits if LMC != 0 for RC/UC QPs.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch adds support for the IB "base memory management extension"
(BMME) and the equivalent iWARP operations (which the iWARP verbs
mandates all devices must implement). The new operations are:
- Allocate an ib_mr for use in fast register work requests.
- Allocate/free a physical buffer lists for use in fast register work
requests. This allows device drivers to allocate this memory as
needed for use in posting send requests (eg via dma_alloc_coherent).
- New send queue work requests:
* send with remote invalidate
* fast register memory region
* local invalidate memory region
* RDMA read with invalidate local memory region (iWARP only)
Consumer interface details:
- A new device capability flag IB_DEVICE_MEM_MGT_EXTENSIONS is added
to indicate device support for these features.
- New send work request opcodes IB_WR_FAST_REG_MR, IB_WR_LOCAL_INV,
IB_WR_RDMA_READ_WITH_INV are added.
- A new consumer API function, ib_alloc_mr() is added to allocate
fast register memory regions.
- New consumer API functions, ib_alloc_fast_reg_page_list() and
ib_free_fast_reg_page_list() are added to allocate and free
device-specific memory for fast registration page lists.
- A new consumer API function, ib_update_fast_reg_key(), is added to
allow the key portion of the R_Key and L_Key of a fast registration
MR to be updated. Consumers call this if desired before posting
a IB_WR_FAST_REG_MR work request.
Consumers can use this as follows:
- MR is allocated with ib_alloc_mr().
- Page list memory is allocated with ib_alloc_fast_reg_page_list().
- MR R_Key/L_Key "key" field is updated with ib_update_fast_reg_key().
- MR made VALID and bound to a specific page list via
ib_post_send(IB_WR_FAST_REG_MR)
- MR made INVALID via ib_post_send(IB_WR_LOCAL_INV),
ib_post_send(IB_WR_RDMA_READ_WITH_INV) or an incoming send with
invalidate operation.
- MR is deallocated with ib_dereg_mr()
- page lists dealloced via ib_free_fast_reg_page_list().
Applications can allocate a fast register MR once, and then can
repeatedly bind the MR to different physical block lists (PBLs) via
posting work requests to a send queue (SQ). For each outstanding
MR-to-PBL binding in the SQ pipe, a fast_reg_page_list needs to be
allocated (the fast_reg_page_list is owned by the low-level driver
from the consumer posting a work request until the request completes).
Thus pipelining can be achieved while still allowing device-specific
page_list processing.
The 32-bit fast register memory key/STag is composed of a 24-bit index
and an 8-bit key. The application can change the key each time it
fast registers thus allowing more control over the peer's use of the
key/STag (ie it can effectively be changed each time the rkey is
rebound to a page list).
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The send DMA hardware queue voided a number of prior assumptions about
when a send is complete which led to completions being generated out of
order. There were also a number of locking issues when switching the QP
to the error or reset states, and we implement the IB_QPS_SQD state.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
When errors are detected in RC, the QP should transition to the
IB_QPS_ERR state, not the IB_QPS_SQE state. Also, when the error is on
the responder side, the receive work completion error was incorrect
(remote vs. local).
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Now that we always use PIO for vl15 on 7220, we could get stuck forever
if we happened to run out of PIO buffers from the verbs code, because
the setup code wouldn't run; the interrupt was also ignored if SDMA was
supported. We also have to reduce the pio update threshold if we have
fewer kernel buffers than the existing threshold.
Clean up the initialization a bit to get ordering safer and more
sensible, and use the existing ipath_chg_kernavail call to do init,
rather than doing it separately.
Drop unnecessary clearing of pio buffer on pio parity error.
Drop incorrect updating of pioavailshadow when exitting freeze mode
(software state may not match chip state if buffer has been allocated
and not yet written).
If we couldn't get a kernel buffer for a while, make sure we are
in sync with hardware, mainly to handle the exitting freeze case.
Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add a new IB_WR_SEND_WITH_INV send opcode that can be used to mark a
"send with invalidate" work request as defined in the iWARP verbs and
the InfiniBand base memory management extensions. Also put "imm_data"
and a new "invalidate_rkey" member in a new "ex" union in struct
ib_send_wr. The invalidate_rkey member can be used to pass in an
R_Key/STag to be invalidated. Add this new union to struct
ib_uverbs_send_wr. Add code to copy the invalidate_rkey field in
ib_uverbs_post_send().
Fix up low-level drivers to deal with the change to struct ib_send_wr,
and just remove the imm_data initialization from net/sunrpc/xprtrdma/,
since that code never does any send with immediate operations.
Also, move the existing IB_DEVICE_SEND_W_INV flag to a new bit, since
the iWARP drivers currently in the tree set the bit. The amso1100
driver at least will silently fail to honor the IB_SEND_INVALIDATE bit
if passed in as part of userspace send requests (since it does not
implement kernel bypass work request queueing). Remove the flag from
all existing drivers that set it until we know which ones are OK.
The values chosen for the new flag is not consecutive to avoid clashing
with flags defined in the XRC patches, which are not merged yet but
which are already in use and are likely to be merged soon.
This resurrects a patch sent long ago by Mikkel Hagen <mhagen@iol.unh.edu>.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch adds the initialization calls into the new 7220 HCA files,
changes the Makefile to compile and link the new files, and code to
handle send DMA.
Signed-off-by: Dave Olson <dave.olson@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch fixes a couple of minor problems with RNR NAK handling:
- The insertion sort was causing extra delay when inserting ahead
vs. behind an existing entry on the list.
- A resend of a first packet of a message which is still not ready,
needs another RNR NAK (i.e., it was suppressed when it shouldn't).
- Also, the resend tasklet doesn't need to be woken up unless the
ACK/NAK actually indicates progress has been made.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Code review pointed out that the locking around uses of ipath_sendctrl
and kr_sendctrl were, in several places, incorrect and/or inconsistent.
Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
There is a small window where a send work queue entry could be
overwritten by ib_post_send() because s_last is updated before the
entry is read.
This patch closes the window by acquiring the lock and updating
the last send work queue entry index after reading the wr_id.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The code to post UD sends tried to process work requests at the time
ib_post_send() is called without using a WQE queue. This was fine as
long as HW resources were available for sending a packet. This patch
changes UD to be handled more like RC and UC and shares more code.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Make some functions that are only used in a single .c file static. In
addition to being a cleanup, this shrinks the generated code. On x86_64:
add/remove: 1/3 grow/shrink: 2/1 up/down: 4777/-4956 (-179)
function old new delta
handle_errors - 3994 +3994
__verbs_timer 42 710 +668
ipath_do_ruc_send 2131 2246 +115
ipath_no_bufs_available 136 - -136
ipath_disarm_senderrbufs 639 - -639
ipath_ib_timer 658 - -658
ipath_intr 5878 2355 -3523
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Add a barrier to make sure the CPU doesn't reorder writes to memory,
since user programs can be polling on the head index update and the
entry should be written before that.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Now that it's June, it's about time to update
the copyright notices of files that have changed.
Signed-off-by: John Gregor <john.gregor@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The IB specification ch. 9.9.3 table 58 says that a QP which isn't set
up for the operation should return a NAK invalid request.
Signed-off-by: Robert Walsh <robert.walsh@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The code to copy data from the receive queue buffers to the IB SGEs
doesn't check the SGE length, only the memory region/page length when
copying data. This could overwrite parts of the user's memory that
were not intended to be written. It can only happen if multiple SGEs
are used to describe a receive buffer which almost never happens in
practice.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
The send function is called when posting new send work requests.
There is no point in trying to send a packet if the QP is already
waiting for a HW send buffer so don't clear the busy bit until the
buffer available interrupt happens.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch fixes a minor bug where the wrong QP was checked for a send
work request that should wait for an RNR timeout.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
This patch adds support for multiple RDMA reads and atomics to be sent
before an ACK is required to be seen by the requester.
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If a post send is done in loopback and there is no receive queue
entry, the sending QP is put on a timeout list for a while so the
receiver has a chance to post a receive buffer. If the another post
send is done, the code incorrectly tried to put the QP on the timeout
list again an corrupted the timeout list. This eventually leads to a
spin lock deadlock NMI due to the timer function looping forever with
the lock held.
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
A silly programming error causes a CQ entry to not be generated if a
SRQ limit event is generated.
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
struct ib_wc currently only includes the local QP number: this matches
the IB spec, but seems mostly useless. The following patch replaces
this with the pointer to qp itself, and updates all low level drivers
and all users.
This has the following advantages:
- Ability to get a per-qp context through wc->qp->qp_context
- Existing drivers already have the qp pointer ready in poll cq, so
this change actually saves a tiny bit (extra memory read) on data path
(for ehca it would actually be expensive to find the QP pointer when
polling a CQ, but ehca does not support SRQ so we can leave wc->qp as
NULL for ehca)
- Users that need the QP number can still get it through wc->qp->qp_num
Use case:
In IPoIB connected mode code, I have a common CQ shared by multiple
QPs. To track connection usage, I need a way to get at some per-QP
context upon the completion, and I would like to avoid allocating
context object per work request just to stick a QP pointer into it.
With this code, I can just use wc->qp->qp_context.
Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
If the receiver goes into the error state, we need to flush the
posted receive WQEs.
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
A lot of ipath layer code was only called in one place. Now that the
ipath_core and ib_ipath drivers are merged, it's more sensible to simply
inline the simple stuff that the layer code was doing.
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Improve performance of userspace post receive, post SRQ receive, and
poll CQ operations for ipath by allowing userspace to directly mmap()
receive queues and completion queues. This eliminates the copying
between userspace and the kernel in the data path.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Remove ips namespace from infinipath drivers. This renames ips_common.h to
ipath_common.h. Definitions, data structures, etc. that were not used by
kernel modules have moved to user-only headers. All names including ips have
been renamed to ipath. Some names have had an ipath prefix added.
Signed-off-by: Christian Bell <christian.bell@qlogic.com>
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Cc: "Michael S. Tsirkin" <mst@mellanox.co.il>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This patch separates QP state used for sending and receiving RC packets so the
processing in the receive interrupt handler can be done mostly without locks
being held. ACK packets are now sent without requiring synchronization with
the send tasklet.
Signed-off-by: Ralph Campbell <ralph.campbell@qlogic.com>
Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com>
Cc: "Michael S. Tsirkin" <mst@mellanox.co.il>
Cc: Roland Dreier <rolandd@cisco.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Ralph Campbell