These methods don't make sense for iWARP devices, so rather than
forcing them to implement stubs, just return -ENOSYS in the core if
the hardware driver doesn't set .modify_device and/or .modify_port.
Signed-off-by: Roland Dreier <[email protected]>
SCSI scanning of a channel:id:lun triplet in Linux works as follows
(function scsi_scan_target() in drivers/scsi/scsi_scan.c):
- If lun == SCAN_WILD_CARD, send a REPORT LUNS command to the target
and process the result.
- If lun != SCAN_WILD_CARD, send an INQUIRY command to the LUN
corresponding to the specified channel:id:lun triplet to verify
whether the LUN exists.
So a SCSI driver must either take the channel and target id values in
account in its quecommand() function or it should declare that it only
supports one channel and one target id.
Currently the ib_srp driver does neither. As a result scanning the
SCSI bus via e.g. rescan-scsi-bus.sh causes many duplicate SCSI
devices to be created. For each 0:0:L device, several duplicates are
created with the same LUN number and with (C:I) != (0:0). Fix this by
declaring that the ib_srp driver only supports one channel and one
target id.
Signed-off-by: Bart Van Assche <[email protected]>
Cc: <[email protected]>
Acked-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Add flags that allow the user to specify via debugfs whether or not the
module name, function name, line number and/or thread ID have to be
included in the printed message.
Signed-off-by: Bart Van Assche <[email protected]>
Cc: Greg Banks <[email protected]>
Cc: Konrad Rzeszutek Wilk <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
Several functions in <linux/kobject.h> accept printf-style arguments.
Some of these functions have been annotated with a format attribute
declaration while others have not been annotated. Add a format attribute
specification where it is missing.
Signed-off-by: Bart Van Assche <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
Since snprintf() may return a value that exceeds its second argument,
show() methods should use scnprintf() instead of snprintf(). This patch
updates the example in the sysfs documentation accordingly.
Signed-off-by: Bart Van Assche <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Dmitry Torokhov <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
Some time ago the way how sysfs stores a pointer to a kobject
corresponding to a directory was modified. This patch brings the
documentation again in sync with the implementation.
Signed-off-by: Bart Van Assche <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Dmitry Torokhov <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
Merge the two tests in srp_queuecommand() of whether information unit
allocation succeeded into one. An intended side effect of this change
is that we fix the warning:
drivers/infiniband/ulp/srp/ib_srp.c: In function 'srp_queuecommand':
drivers/infiniband/ulp/srp/ib_srp.c:1116: warning: 'req' may be used uninitialized in this function
(seen with CONFIG_CC_OPTIMIZE_FOR_SIZE=y at least with gcc 4.4.4)
Signed-off-by: Bart Van Assche <[email protected]>
Acked-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
We don't need protection against the SCSI stack, so use our own lock to
allow parallel progress on separate CPUs.
Signed-off-by: Bart Van Assche <[email protected]>
[ broken out and small cleanups by David Dillow ]
Signed-off-by: David Dillow <[email protected]>
We only need the lock to cover list and credit manipulations, so push
those into srp_remove_req() and update the call chains.
We reorder the request removal and command completion in
srp_process_rsp() to avoid the SCSI mid-layer sending another command
before we've released our request and added any credits returned by the
target. This prevents us from returning HOST_BUSY unneccesarily.
Signed-off-by: Bart Van Assche <[email protected]>
[ broken out, small cleanups, and modified to avoid potential extraneous
HOST_BUSY returns by David Dillow ]
Signed-off-by: David Dillow <[email protected]>
We only need locks to protect our lists and number of credits available.
By pre-consuming the credit for the request, we can reduce our lock
coverage to just those areas. If we don't actually send the request,
we'll need to put the credit back into the pool.
Signed-off-by: Bart Van Assche <[email protected]>
[ broken out and small cleanups by David Dillow ]
Signed-off-by: David Dillow <[email protected]>
We use req->scmnd != NULL to indicate an active request, so there's no
need to keep a separate list for them. We can afford the array iteration
during error handling, and dropping it gives us one less item that needs
lock protection.
Signed-off-by: Bart Van Assche <[email protected]>
[ broken out and small cleanups by David Dillow ]
Signed-off-by: David Dillow <[email protected]>
Only one CPU at a time will own an RX IU, so using the address of the IU
as the work request cookie allows us to avoid taking a lock. We can
similarly prepare the TX path for lockless posting by moving the free TX
IUs to a list. This also removes the requirement that the queue sizes be
a power of 2.
Signed-off-by: Bart Van Assche <[email protected]>
[ broken out, small cleanups, and modified to avoid needing an extra field
in the IU by David Dillow]
Signed-off-by: David Dillow <[email protected]>
This patch fixes a spelling error in a source code comment and removes
superfluous braces in the function exit_io_context().
Signed-off-by: Bart Van Assche <[email protected]>
Cc: Jens Axboe <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Use the list_first_entry() macro in ib_srp instead of open-coding the equivalent,
which makes the source code slightly more descriptive. The list_first_entry()
macro itself was introduced in kernel 2.6.22.
Signed-off-by: Bart Van Assche <[email protected]>
Signed-off-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
As proposed by the SRP (draft) standard, ib_srp reserves one ring
element for SRP_TSK_MGMT requests. This patch makes sure that the SCSI
mid-layer never tries to queue more than (SRP request limit) - 1 SCSI
commands to ib_srp. This improves performance for targets whose request
limit is less than or equal to SRP_NORMAL_REQ_SQ_SIZE by reducing the
number of BUSY responses reported by ib_srp to the SCSI mid-layer.
Signed-off-by: Bart Van Assche <[email protected]>
Signed-off-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
The transmit ring in ib_srp (srp_target.tx_ring) is currently only used
for allocating requests sent by the initiator to the target. This patch
prepares using that ring for allocation of both requests and responses.
Also, this patch differentiates the uses of SRP_SQ_SIZE, increases the
size of the IB send completion queue by one element and reserves one
transmit ring slot for SRP_TSK_MGMT requests.
Signed-off-by: Bart Van Assche <[email protected]>
Signed-off-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Fix all discrepancies I know of between the sysfs implementation and its
documentation.
Signed-off-by: Bart Van Assche <[email protected]>
Cc: Randy Dunlap <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
The current strategy in ib_srp for posting receive buffers is:
* Post one buffer after channel establishment.
* Post one buffer before sending an SRP_CMD or SRP_TSK_MGMT to the target.
As a result, only the first non-SRP_RSP information unit from the
target will be processed. If that first information unit is an
SRP_T_LOGOUT, it will be processed. On the other hand, if the
initiator receives an SRP_CRED_REQ or SRP_AER_REQ before it receives a
SRP_T_LOGOUT, the SRP_T_LOGOUT won't be processed.
We can fix this inconsistency by changing the strategy for posting
receive buffers to:
* Post all receive buffers after channel establishment.
* After a receive buffer has been consumed and processed, post it again.
A side effect is that the ib_post_recv() call is moved out of the SCSI
command processing path. Since __srp_post_recv() is not called
directly any more, get rid of it and move the code directly into
srp_post_recv(). Also, move srp_post_recv() up in the file to avoid a
forward declaration.
Signed-off-by: Bart Van Assche <[email protected]>
Acked-by: David Dillow <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Replace an open-coded dump of the receive buffer with a call to
print_hex_dump().
Signed-off-by: Bart Van Assche <[email protected]>
Signed-off-by: Roland Dreier <[email protected]>
Analyzing fcoe with sparse currently fails. This is because struct
fcoe_rcv_info contains two enum members that have been declared with
__attribute__((packed)). Apparently gcc honors this attribute while sparse
ignores it. The result is that sizeof(struct fcoe_rcv_info)
== sizeof(struct sk_buff::cb) == 48 on a 64-bit system according to gcc, but
not according to sparse. The patch below modifies the definition of
struct fcoe_rcv_info such that gcc and sparse interpret this structure
definition in the same way. The current sparse output is as follows:
$ cd linux-2.6.34
$ make C=2 M=drivers/scsi/fcoe modules
CHECK drivers/scsi/fcoe/fcoe.c
include/scsi/fc_frame.h:81:9: error: invalid bitfield width, -1.
CC [M] drivers/scsi/fcoe/fcoe.o
CHECK drivers/scsi/fcoe/libfcoe.c
include/scsi/fc_frame.h:81:9: error: invalid bitfield width, -1.
drivers/scsi/fcoe/libfcoe.c:56:37: error: invalid initializer
Signed-off-by: Bart Van Assche <[email protected]>
Cc: [email protected]
Signed-off-by: Robert Love <[email protected]>
Signed-off-by: James Bottomley <[email protected]>
Bart Van Assche