Drivers may override the WCE flag, in which case the DPOFUA flag in
MODE SENSE might differ from the check used to reject invalid FUA
bits in sbc_check_dpofua.  Also now that we reject invalid FUA
bits early there is no need to duplicate the same buggy check
down in the fileio code.

As the DPOFUA flag controls th support for FUA bits on read and
write commands as well as DPO key off all the checks off a single
helper, and deprecate the emulate_dpo and emulate_fua_read attributs.

This fixes various failures in the libiscsi testsuite.

Personally I'd prefer to also remove the emulate_fua_write attribute
as there is no good reason to disable it, but I'll leave that for
a separate discussion.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Support for markers is currently broken because of a bug in
iscsi_enforce_integrity_rules(): the "IFMarkInt_Reject" and
"OFMarkInt_Reject" variables are always equal to 1 in
iscsi_enforce_integrity_rules().

Moreover, fixed interval markers keys (IFMarker, OFMarker, IFMarkInt
and OFMarkInt) are obsolete according to iSCSI RFC 7143:

>From http://tools.ietf.org/html/rfc7143#section-13.25:

   13.25.  Obsoleted Keys

   This document obsoletes the following keys defined in [RFC3720]:
   IFMarker, OFMarker, OFMarkInt, and IFMarkInt.  However, iSCSI
   implementations compliant to this document may still receive these
   obsoleted keys -- i.e., in a responder role -- in a text negotiation.

   When an IFMarker or OFMarker key is received, a compliant iSCSI
   implementation SHOULD respond with the constant "Reject" value.  The
   implementation MAY alternatively respond with a "No" value.

   However, the implementation MUST NOT respond with a "NotUnderstood"
   value for either of these keys.

   When an IFMarkInt or OFMarkInt key is received, a compliant iSCSI
   implementation MUST respond with the constant "Reject" value.  The
   implementation MUST NOT respond with a "NotUnderstood" value for
   either of these keys.

This patch disables markers by turning the corresponding parameters to
read-only. The default value of IFMarker and OFMarker remains "No" but
the user cannot change it to "Yes" anymore. The new value of IFMarkInt
and OFMarkInt is "Reject".

(Drop left-over iscsi_get_value_from_number_range + make configfs
 parameters attrs R/W nops - nab)
Signed-off-by: NChristophe Vu-Brugier <cvubrugier@fastmail.fm>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Fix map/unmap consistency and get rid of a redundant
local variable psg.
Reported-by: NAkinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The reason this bounce buffer exists is to allow code
reuse between rd_mcp and fileio in DIF mode. But the fact is,
that this bounce is really not needed at all, we can simply call
sbc_dif_verify on cmd->t_prot_sg and use it for file IO.

This also removes fd_do_prot_rw as fd_do_rw was generalised
to receive file pointer, block size (8 bytes for DIF data) and
total data length.

(Fix apply breakage from commit c8367778 - nab)
Tested-by: NAkinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Instead of providing DIF verify routines for read/write
that are almost identical and conditionally copy protection
information, just let the caller do the right thing.

Have a single sbc_dif_verify that handles an sgl (that
does NOT copy any data) and a protection information copy
routine used by rd_mcp and fileio backend.

In the WRITE case, call sbc_dif_verify with cmd->t_prot_sg
and then do the copy from it to local sgl (assuming the verify
succeeded of course). In the READ case, call sbc_dif_verify
with the local sgl and if it succeeds, copy it to t_prot_sg (or
not if we are stripping it).

(Fix apply breakage from commit c8367778 - nab)
Tested-by: NAkinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

It seems like we only care if a transport is passthrough or not. Convert
transport_type to a flags field and replace TRANSPORT_PLUGIN_* with a
flag, TRANSPORT_FLAG_PASSTHROUGH.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Aside from whether they handle BIDI ops or not, parsing of the CDB by
kernel and user SCSI passthrough modules should be identical. Move this
into a new passthrough_parse_cdb() and call it from tcm-pscsi and tcm-user.
Reported-by: NChristoph Hellwig <hch@lst.de>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NAndy Grover <agrover@redhat.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

After much discussion, give up on only passing a subset of SCSI commands
to userspace and pass them all. Based on what pscsi is doing, make sure
to set SCF_SCSI_DATA_CDB for I/O ops, and define attributes identical to
pscsi.

Make hw_block_size configurable via dev param.

Remove mention of command filtering from tcmu-design.txt.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

See https://bugzilla.redhat.com/show_bug.cgi?id=1025672

We need to put() the reference to the scsi host that we got in
pscsi_configure_device(). In VIRTUAL_HOST mode it is associated with
the dev_virt, not the hba_virt.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Cc: stable@vger.kernel.org # 2.6.38+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

There is just one configfs subsystem in the target code, so we might as
well add two helpers to reference / unreference it from the core code
instead of passing pointers to it around.

This fixes a regression introduced for v4.1-rc1 with commit 9ac8928e,
where configfs_depend_item() callers using se_tpg_tfo->tf_subsys would
fail, because the assignment from the original target_core_subsystem[]
is no longer happening at target_register_template() time.

(Fix target_core_exit_configfs pointer dereference - Sagi)
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Reported-by: NHimanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Once upon a time, iscsit_get_tpg() was using an un-interruptible
lock.  The signal_pending() usage was a check to allow userspace
to break out of the operation with SIGINT.

AFAICT, there's no reason why this is necessary anymore, and as
reported by Alexey can be potentially dangerous.  Also, go ahead
and drop the other two problematic cases within iscsit_access_np()
and sbc_compare_and_write() as well.

Found by Linux Driver Verification project (linuxtesting.org).
Reported-by: NAlexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Code like " &= ~CMD_T_BUSY | ..." only clears CMD_T_BUSY but not
the other flag. Modify these statements such that both flags are
cleared.

(Fix fuzz for target_write_prot_action code in mainline - nab)
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The function transport_complete_qf() must call either
queue_data_in() or queue_status() but not both.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

TCMU requires more work to correctly handle both user handlers that want
all SCSI commands (pass_level=0) for a se_device, and also handlers that
just want I/O commands and let the others be emulated by the kernel
(pass_level=1). Only support the latter for now.

For full passthrough, we will need to support a second se_subsystem_api
template, due to configfs attributes being different between the two modes.
Thus pass_level is extraneous, and we can remove it.

The ABI break for TCMU v2 is already applied for this release, so it's
best to do this now to avoid another ABI break in the future.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch adds a missing kfree for sess->sess_ops memory upon
transport_init_session() failure.
Signed-off-by: NEvgenii Lepikhin <johnlepikhin@gmail.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Conceptually version 2 should be viewed as an entirely new, incompatible
version of TCMU, so emphasize this by changing the config option and
Kconfig text.
Signed-off-by: NAndy Grover <agrover@redhat.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The initial version of TCMU (in 3.18) does not properly handle
bidirectional SCSI commands -- those with both an in and out buffer. In
looking to fix this it also became clear that TCMU's support for adding
new types of entries (opcodes) to the command ring was broken. We need
to fix this now, so that future issues can be handled properly by adding
new opcodes.

We make the most of this ABI break by enabling bidi cmd handling within
TCMP_OP_CMD opcode. Add an iov_bidi_cnt field to tcmu_cmd_entry.req.
This enables TCMU to describe bidi commands, but further kernel work is
needed for full bidi support.

Enlarge tcmu_cmd_entry_hdr by 32 bits by pulling in cmd_id and __pad1. Turn
__pad1 into two 8 bit flags fields, for kernel-set and userspace-set flags,
"kflags" and "uflags" respectively.

Update version fields so userspace can tell the interface is changed.

Update tcmu-design.txt with details of how new stuff works:
- Specify an additional requirement for userspace to set UNKNOWN_OP
  (bit 0) in hdr.uflags for unknown/unhandled opcodes.
- Define how Data-In and Data-Out fields are described in req.iov[]

Changed in v2:
- Change name of SKIPPED bit to UNKNOWN bit
- PAD op does not set the bit any more
- Change len_op helper functions to take just len_op, not the whole struct
- Change version to 2 in missed spots, and use defines
- Add 16 unused bytes to cmd_entry.req, in case additional SAM cmd
  parameters need to be included
- Add iov_dif_cnt field to specify buffers used for DIF info in iov[]
- Rearrange fields to naturally align cdb_off
- Handle if userspace sets UNKNOWN_OP by indicating failure of the cmd
- Wrap some overly long UPDATE_HEAD lines

(Add missing req.iov_bidi_cnt + req.iov_dif_cnt zeroing - Ilias)
Signed-off-by: NAndy Grover <agrover@redhat.com>
Reviewed-by: NIlias Tsitsimpis <iliastsi@arrikto.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

When UNMAP command is issued with DIF protection support enabled,
the protection info for the unmapped region is remain unchanged.
So READ command for the region causes data integrity failure.

This fixes it by invalidating protection info for the unmapped region
by filling with 0xff pattern.  This change also adds helper function
fd_do_prot_fill() in order to reduce code duplication with existing
fd_format_prot().
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Reviewed-by: N"Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

In fd_do_prot_rw(), it allocates prot_buf which is used to copy from
se_cmd->t_prot_sg by sbc_dif_copy_prot().  The SG table for prot_buf
is also initialized by allocating 'se_cmd->t_prot_nents' entries of
scatterlist and setting the data length of each entry to PAGE_SIZE
at most.

However if se_cmd->t_prot_sg contains a clustered entry (i.e.
sg->length > PAGE_SIZE), the SG table for prot_buf can't be
initialized correctly and sbc_dif_copy_prot() can't copy to prot_buf.
(This actually happened with TCM loopback fabric module)

As prot_buf is allocated by kzalloc() and it's physically contiguous,
we only need a single scatterlist entry.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

When CONFIG_DEBUG_SG=y and DIF protection support enabled, kernel
BUG()s are triggered due to the following two issues:

1) prot_sg is not initialized by sg_init_table().

When CONFIG_DEBUG_SG=y, scatterlist helpers check sg entry has a
correct magic value.

2) vmalloc'ed buffer is passed to sg_set_buf().

sg_set_buf() uses virt_to_page() to convert virtual address to struct
page, but it doesn't work with vmalloc address.  vmalloc_to_page()
should be used instead.  As prot_buf isn't usually too large, so
fix it by allocating prot_buf by kmalloc instead of vmalloc.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: <stable@vger.kernel.org> # v3.14+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The loop in core_tmr_abort_task() iterates over sess_cmd_list.
That list is a list of regular commands and task management
functions (TMFs). Skip TMFs in this loop instead of letting
the target drivers filter out TMFs in their get_task_tag()
callback function.

(Drop bogus check removal in tcm_qla2xxx_get_task_tag - nab)
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Andy Grover <agrover@redhat.com>
Cc: <qla2xxx-upstream@qlogic.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Now that sbc_dif_generate can also be called for READ_INSERT, update
the debugging message accordingly.
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The internal DIF emulation was not honoring se_cmd->prot_checks for
the WRPROTECT/RDPROTECT == 0x3 case, so sbc_dif_v1_verify() has been
updated to follow which checks have been calculated based on
WRPROTECT/RDPROTECT in sbc_set_prot_op_checks().
Reviewed-by: NMartin Petersen <martin.petersen@oracle.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

In sbc_check_prot(), if PROTECT is non-zero for a backend device with
DIF disabled, and sess_prot_type is not set go ahead and return
INVALID_CDB_FIELD.
Reviewed-by: NMartin Petersen <martin.petersen@oracle.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The following incremental patch saves the current sess_prot_type into
se_node_acl, and will always reset sess_prot_type if a previous saved
value exists.  So the PI setting for the fabric's session with backend
devices not supporting PI is persistent across session restart.

(Fix se_node_acl dereference for discovery sessions - DanCarpenter)
Reviewed-by: NMartin Petersen <martin.petersen@oracle.com>
Reviewed-by: NSagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The scatterlist for protection information which is passed to
sbc_dif_verify_read() or sbc_dif_verify_write() requires that
neighboring scatterlist entries are contiguous or chained so that they
can be iterated by sg_next().

However, the protection information for RD-MCP backends could be located
in the multiple scatterlist arrays when the ramdisk space is too large.
So if the read/write request straddles this boundary, sbc_dif_verify_read()
or sbc_dif_verify_write() can't iterate all scatterlist entries.

This problem can be fixed by chaining protection information scatterlist
at creation time.  For the architectures which don't support sg chaining
(i.e. !CONFIG_ARCH_HAS_SG_CHAIN), fix it by allocating temporary
scatterlist if needed.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Nicholas Bellinger <nab@linux-iscsi.org>
Cc: Sagi Grimberg <sagig@dev.mellanox.co.il>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: target-devel@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

The flag SCF_ACK_KREF is only set but never tested. Hence remove
this flag.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Avoid that sparse complains about context imbalances.
Signed-off-by: NBart Van Assche <bart.vanassche@sandisk.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch fixes a bug for COMPARE_AND_WRITE handling with
fabrics using SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC.

It adds the missing allocation for cmd->t_bidi_data_sg within
transport_generic_new_cmd() that is used by COMPARE_AND_WRITE
for the initial READ payload, even if the fabric is already
providing a pre-allocated buffer for cmd->t_data_sg.

Also, fix zero-length COMPARE_AND_WRITE handling within the
compare_and_write_callback() and target_complete_ok_work()
to queue the response, skipping the initial READ.

This fixes COMPARE_AND_WRITE emulation with loopback, vhost,
and xen-backend fabric drivers using SG_TO_MEM_NOALLOC.
Reported-by: NChristoph Hellwig <hch@lst.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: <stable@vger.kernel.org> # v3.12+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Instead of calling target_fabric_configfs_init() +
target_fabric_configfs_register() / target_fabric_configfs_deregister()
target_fabric_configfs_free() from every target driver, rewrite the API
so that we have simple register/unregister functions that operate on
a const operations vector.

This patch also fixes a memory leak in several target drivers. Several
target drivers namely called target_fabric_configfs_deregister()
without calling target_fabric_configfs_free().

A large part of this patch is based on earlier changes from
Bart Van Assche <bart.vanassche@sandisk.com>.

(v2: Add a new TF_CIT_SETUP_DRV macro so that the core configfs code
can declare attributes as either core only or for drivers)
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This fixes a oops due to a double list add when adding a reject PDU for
iscsit_allocate_iovecs allocation failures. The cmd has already been
added to the conn_cmd_list in iscsit_setup_scsi_cmd, so this has us call
iscsit_reject_cmd.

Note that for ERL0 the reject PDU is not actually sent, so this patch
is not completely tested. Just verified we do not oops. The problem is the
add reject functions return -1 which is returned all the way up to
iscsi_target_rx_thread which for ERL0 will drop the connection.
Signed-off-by: NMike Christie <michaelc@cs.wisc.edu>
Cc: <stable@vger.kernel.org> # v3.10+
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Drop unused argument & return value and consolidate a duplicate assignment.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Factor out code duplication in rd_execute_rw() into a helper function
rd_do_prot_rw().  This change is required to minimize the forthcoming
fix in rd_do_prot_rw().

(Fix up v4.1 for-next fuzz - nab)
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Sagi Grimberg <sagig@dev.mellanox.co.il>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
Cc: target-devel@vger.kernel.org
Cc: linux-scsi@vger.kernel.org
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Currently, for example, mkdir "tpgt_xyz" doesn't return error.
mkdir /sys/kernel/config/target/loopback/naa.60014055f195952b/tpgt_xyz

Replace obsoleted simple_strtoul with kstrtoul and check the conversion.
Signed-off-by: NMing Lin <mlin@kernel.org>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch updates iscsi/iser-target to add a new fabric_prot_type
TPG attribute for iser-target, used for controlling LLD level
protection into LIO when the backend device does not support T10-PI.

This is required for ib_isert to enable WRITE_STRIP + READ_INSERT
hardware offloads.

It's disabled by default and controls which se_sesion->sess_prot_type
are set at iscsi_target_locate_portal() session registration time.

Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Martin Petersen <martin.petersen@oracle.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

This patch updates loopback to add a new fabric_prot_type TPG attribute,
used for controlling LLD level protection into LIO when the backend
device does not support T10-PI.

Also, go ahead and set DIN_PASS + DOUT_PASS so target-core knows that
it will be doing any WRITE_STRIP and READ_INSERT operations.

Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Hannes Reinecke <hare@suse.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Make sure that RAMDISK only attempts to use backend DIF emulation
when it's actually enabled at device level.

Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Make sure that IBLOCK only attempts to use backend DIF emulation
when it's actually enabled at device level.

Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>

Make sure that FILEIO only attempts to use backend DIF emulation
when it's actually enabled at device level.

Cc: Martin Petersen <martin.petersen@oracle.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: NNicholas Bellinger <nab@linux-iscsi.org>