Merged revisions 5875,5878-5895,5903-5905,5910,5912-5914,5928-5929,5931-5991 via svnmerge from

svn+ssh://yanb123@svn.code.sf.net/p/scst/svn/trunk

........
  r5875 | bvassche | 2014-11-16 19:58:07 +0200 (Sun, 16 Nov 2014) | 1 line
  
  nightly build: Update kernel versions
........
  r5878 | bvassche | 2014-11-19 02:17:41 +0200 (Wed, 19 Nov 2014) | 1 line
  
  srpt/Makefile: Add double quotes around a path
........
  r5879 | bvassche | 2014-11-19 02:20:20 +0200 (Wed, 19 Nov 2014) | 1 line
  
  scripts/generate-release-archive: Accept an optional list of file names
........
  r5880 | bvassche | 2014-11-22 13:12:29 +0200 (Sat, 22 Nov 2014) | 1 line
  
  nightly build: Update kernel versions
........
  r5881 | bvassche | 2014-11-24 19:59:14 +0200 (Mon, 24 Nov 2014) | 4 lines
  
  ib_srpt: Add support for HCA's that do not support SRQ
  
  Based on a patch provided by Parav Pandit <Parav.Pandit@Emulex.Com>
........
  r5882 | vlnb | 2014-11-26 09:02:17 +0200 (Wed, 26 Nov 2014) | 3 lines
  
  Update for kernels 3.17.x
........
  r5883 | bvassche | 2014-11-26 10:05:09 +0200 (Wed, 26 Nov 2014) | 1 line
  
  Add kernel 3.17 build infrastructure
........
  r5884 | bvassche | 2014-11-26 10:07:08 +0200 (Wed, 26 Nov 2014) | 1 line
  
  nightly build: Add kernel 3.17
........
  r5885 | bvassche | 2014-11-26 10:16:44 +0200 (Wed, 26 Nov 2014) | 6 lines
  
  Fix kernel 3.17 checkpatch warnings about 'long long unsigned'
  
  Avoid that checkpatch reports the following warning:
  
  WARNING: type 'long long unsigned' should be specified in 'unsigned long long' order.
........
  r5886 | bvassche | 2014-11-26 15:38:52 +0200 (Wed, 26 Nov 2014) | 1 line
  
  Build fixes for RHEL 6.6 kernel 2.6.32-504
........
  r5887 | bvassche | 2014-11-26 16:39:51 +0200 (Wed, 26 Nov 2014) | 1 line
  
  ib_srpt: Make the send queue full messages more informational
........
  r5888 | bvassche | 2014-11-26 18:25:57 +0200 (Wed, 26 Nov 2014) | 1 line
  
  scripts/specialize-patch: Support blanks around numbers inside parentheses
........
  r5889 | bvassche | 2014-11-26 21:42:10 +0200 (Wed, 26 Nov 2014) | 1 line
  
  scripts/specialize-patch: Reduce noise in nightly build output
........
  r5890 | vlnb | 2014-11-27 06:36:33 +0200 (Thu, 27 Nov 2014) | 3 lines
  
  Cleanup
........
  r5891 | bvassche | 2014-11-27 17:18:58 +0200 (Thu, 27 Nov 2014) | 1 line
  
  scst.h: Add uintptr_t
........
  r5892 | bvassche | 2014-11-27 17:19:21 +0200 (Thu, 27 Nov 2014) | 1 line
  
  ib_srpt: Add support for immediate data
........
  r5893 | bvassche | 2014-11-27 17:24:17 +0200 (Thu, 27 Nov 2014) | 1 line
  
  ib_srpt: Log reject reason
........
  r5894 | bvassche | 2014-11-27 17:29:29 +0200 (Thu, 27 Nov 2014) | 1 line
  
  ib_srpt: Rework the max_sge computation changes from r5795
........
  r5895 | bvassche | 2014-11-28 11:16:37 +0200 (Fri, 28 Nov 2014) | 1 line
  
  scst: Add scripts/rebuild-rhel-kernel-rpm to the SCST release archive
........
  r5903 | bvassche | 2014-12-03 13:50:06 +0200 (Wed, 03 Dec 2014) | 4 lines
  
  scripts/rebuild-rhel-kernel-rpm: Fix an error message
  
  Reported-by: Hiroyuki Sato <hiroysato@gmail.com>
........
  r5904 | bvassche | 2014-12-03 19:06:57 +0200 (Wed, 03 Dec 2014) | 1 line
  
  iscsi-scst/kernel/patches/rhel/put_page_callback-2.6.32-504.patch: Add
........
  r5905 | bvassche | 2014-12-03 19:07:31 +0200 (Wed, 03 Dec 2014) | 1 line
  
  scripts/rebuild-rhel-kernel-rpm: Add support for RHEL 6.6
........
  r5910 | bvassche | 2014-12-04 13:50:58 +0200 (Thu, 04 Dec 2014) | 1 line
  
  scripts/generate-kernel-patch: Swap two filters
........
  r5912 | bvassche | 2014-12-04 14:19:56 +0200 (Thu, 04 Dec 2014) | 4 lines
  
  /etc/init.d/scst: Exit with status code 0 upon 'start' if already running
  
  Reported-by: Dimitar Tanev <dimitar@linuxdevgroup.org>
........
  r5913 | vlnb | 2014-12-05 01:41:52 +0200 (Fri, 05 Dec 2014) | 3 lines
  
  FORMAT commands should be strictly serialized
........
  r5914 | vlnb | 2014-12-05 01:43:51 +0200 (Fri, 05 Dec 2014) | 3 lines
  
  Oops, fix for the previous commit
........
  r5928 | vlnb | 2014-12-06 07:02:27 +0200 (Sat, 06 Dec 2014) | 3 lines
  
  Web updates
........
  r5929 | bvassche | 2014-12-09 14:33:16 +0200 (Tue, 09 Dec 2014) | 1 line
  
  rpm build: Add support for qla2x00t driver in QLogic git repository
........
  r5931 | vlnb | 2014-12-11 06:27:17 +0200 (Thu, 11 Dec 2014) | 3 lines
  
  Docs update
........
  r5932 | vlnb | 2014-12-11 06:34:36 +0200 (Thu, 11 Dec 2014) | 8 lines
  
  scst_vdisk: Increase virtual device name length
  
  This change makes integration with OpenStack easier since OpenStack GUIDs
  are 36 characters long: 32 hex characters and four dashes.
  
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5933 | vlnb | 2014-12-11 06:38:04 +0200 (Thu, 11 Dec 2014) | 11 lines
  
  vdisk_blockio: Report invalid scatterlists
  
  It is possible for a target driver to pass a scatterlist via
  scst_cmd_set_tgt_sg() that is valid for the vdisk_fileio handler
  but not for the vdisk_blockio handler. Complain loudly if an invalid
  scatterlist is passed to vdisk_blockio because such scatterlists
  cause silent data corruption with most Linux block drivers.
  
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5934 | bvassche | 2014-12-11 14:31:03 +0200 (Thu, 11 Dec 2014) | 1 line
  
  scst_vdisk: Follow-up for r5932
........
  r5935 | bvassche | 2014-12-11 14:37:02 +0200 (Thu, 11 Dec 2014) | 1 line
  
  ib_srpt: Log P_Key during login
........
  r5936 | bvassche | 2014-12-12 11:29:42 +0200 (Fri, 12 Dec 2014) | 1 line
  
  scripts/generate-kernel-patch: Include scst_pg.sgml instead of sgv_cache.sgml
........
  r5937 | bvassche | 2014-12-12 11:34:55 +0200 (Fri, 12 Dec 2014) | 1 line
  
  doc/scst_pg.sgml: Remove trailing whitespace
........
  r5938 | bvassche | 2014-12-17 09:48:40 +0200 (Wed, 17 Dec 2014) | 1 line
  
  nightly build: Update kernel versions
........
  r5939 | vlnb | 2014-12-19 05:50:58 +0200 (Fri, 19 Dec 2014) | 3 lines
  
  Fallback to the old qla driver if the git one not detected
........
  r5940 | vlnb | 2014-12-19 05:55:14 +0200 (Fri, 19 Dec 2014) | 7 lines
  
  Replace in cases, where sporadic failures are possible, HARDWARE ERROR
  by INTERNAL TARGET FAILURE, which is retriable (some OS'es don't retry
  HARDWARE ERROR)
  
  Reported and suggested by Shahar Salzman <shahar.salzman@kaminario.com>
........
  r5941 | vlnb | 2014-12-20 05:48:07 +0200 (Sat, 20 Dec 2014) | 7 lines
  
  scst_vdisk: Only accept NAA IDs allowed by SPC
  
  See also paragraph 7.8.6.6 NAA designator format in SPC-4.
  
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5942 | vlnb | 2014-12-20 05:49:23 +0200 (Sat, 20 Dec 2014) | 11 lines
  
  scst_vdisk: Remove superfluous llseek() calls
  
  vfs_read() and vfs_write() ignore the file offset set by llseek().
  Hence remove the llseek() calls that occur just before vfs_read() and
  vfs_write(). See also the implementation in the Linux kernel of the
  pread64() and pwrite64() system calls for examples of code that uses
  vfs_read() and vfs_write().
  
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5943 | bvassche | 2014-12-22 14:28:13 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code spelling fix: Equivilant -> Equivalent
........
  r5944 | bvassche | 2014-12-22 14:28:56 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code spelling fix: accesss -> access
........
  r5945 | bvassche | 2014-12-22 14:29:51 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code spelling fix: addres -> address
........
  r5946 | bvassche | 2014-12-22 14:31:08 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code spelling fix: authentification -> authentication
........
  r5947 | bvassche | 2014-12-22 14:32:30 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code comment spelling fix: explicitely -> explicitly
........
  r5948 | bvassche | 2014-12-22 14:33:06 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code comment spelling fix: hander -> handler
........
  r5949 | bvassche | 2014-12-22 14:33:37 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code comment spelling fix: loosing -> losing
........
  r5950 | bvassche | 2014-12-22 14:35:00 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Spelling fix: occured -> occurred
........
  r5951 | bvassche | 2014-12-22 14:35:51 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Source code comment spelling fix: refering -> referring
........
  r5952 | bvassche | 2014-12-22 14:36:47 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Spelling fix: shrinked -> shrunk
........
  r5953 | bvassche | 2014-12-22 15:08:34 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Spelling fix: choosen -> chosen
........
  r5954 | bvassche | 2014-12-22 15:09:20 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Spelling fix: existant -> existent
........
  r5955 | bvassche | 2014-12-22 15:10:41 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Update for kernel 3.18
........
  r5956 | bvassche | 2014-12-22 15:15:55 +0200 (Mon, 22 Dec 2014) | 1 line
  
  Spelling fix: immediatelly -> immediately
........
  r5957 | bvassche | 2014-12-24 16:28:36 +0200 (Wed, 24 Dec 2014) | 1 line
  
  nightly build: Add kernel 3.18
........
  r5958 | bvassche | 2014-12-29 14:14:52 +0200 (Mon, 29 Dec 2014) | 1 line
  
  scst_lib: Convert spaces into tabs (reported by checkpatch)
........
  r5959 | bvassche | 2015-01-06 15:25:28 +0200 (Tue, 06 Jan 2015) | 1 line
  
  scst_calc_block_shift: Log block shift and sector size upon mismatch
........
  r5960 | bvassche | 2015-01-07 11:20:06 +0200 (Wed, 07 Jan 2015) | 4 lines
  
  scst_local: Fix unique per session sas address
  
  Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
........
  r5961 | bvassche | 2015-01-09 14:23:25 +0200 (Fri, 09 Jan 2015) | 4 lines
  
  scst_sysfs: return EINVAL on too big LUN
  
  Signed-off-by: Sebastian Herbszt <herbszt@gmx.de>
........
  r5962 | bvassche | 2015-01-10 17:52:57 +0200 (Sat, 10 Jan 2015) | 1 line
  
  nightly build: Update kernel versions
........
  r5963 | bvassche | 2015-01-13 10:42:28 +0200 (Tue, 13 Jan 2015) | 10 lines
  
  scst: Switch to thread context before executing a reservation command
  
  Persistent reservation commands need thread context because
  scst_pr_is_cmd_allowed() locks the PR mutex. Reservation commands
  either need BH or thread context. Hence switch from atomic to
  thread context before processing such commands.
  
  Reported-by: Shahar Salzman <shahar.salzman@kaminario.com>
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5964 | bvassche | 2015-01-13 10:51:08 +0200 (Tue, 13 Jan 2015) | 5 lines
  
  scst_parse_unmap_descriptors(): Avoid using GFP_KERNEL in atomic context
  
  Reported-by: Shahar Salzman <shahar.salzman@kaminario.com>
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5965 | bvassche | 2015-01-13 10:55:46 +0200 (Tue, 13 Jan 2015) | 68 lines
  
  qla2x00t: Copy entire SCST sense buffer to q2x ctio
  
  There seems to be a bug in passing sense information to QLA HBAs, where 
  the last 2 bytes of the sense data (ASC, ASCQ) are not copied to the low 
  level sense buffer.
  We encountered this in ESX, which relies on these 2 bytes to parse the 
  MISCOMPARE sense code (0xE1, 0x1D, 0x00).
  Bellow is a simple test to recreate this issue, but during vMotion 
  operations (where VMs are moved from one host to another), this may 
  cause the operation to fail leaving the VM in an inconsistent state.
  
  The test I ran to verify that we are indeed missing the bytes is the 
  following:
  1. Create a SCST based device
  2. Expose the device to 2 ESX hosts
  3. Format the device as VMFS5, create a test directory
  4. From both hosts, I start writing to this directory (no VMs involved, 
  just write normal files)
  
  At this stage, both ESX hosts try to take access to the directory.
  The VMFS filesystem contains a per-directory lock which is managed by 
  COMPARE AND WRITE command.
  Each ESX will attempt to change the VMFS lock location from unlocked to 
  locked to create the new file.
  
  Obviously there are bound to be failures (which are equivalent to 
  programming locking conflicts), these are reported by the MISCOMPARE 
  sense code.
  Upon these MISCOMPARE errors, the host will re-try taking the lock until 
  it succeeds, and will then proceed to perform the write operation on the 
  directory.
  
  Due to the bug in copying the sense buffer from the SCST core to the QLA 
  ctio, instead of the full sense code, only the key (0xE) is sent, and 
  ESX does not know how to handle it resulting in IO error.
  
  Here are the errors as they appear on the command line:
  /vmfs/volumes/54a297c4-ca5af1cc-7f94-002219d20f28/ats_test # 
  ./open_close_test-esx2.sh
  ./open_close_test-esx2.sh: line 8: can't create 
  ats_fileoptest-esx2_1.txt: Input/output error
  ./open_close_test-esx2.sh: line 8: can't create 
  ats_fileoptest-esx2_21.txt: Input/output error
  ./open_close_test-esx2.sh: line 8: can't create 
  ats_fileoptest-esx2_110.txt: Input/output error
  ./open_close_test-esx2.sh: line 8: can't create 
  ats_fileoptest-esx2_111.txt: Input/output error
  
  In the /var/log/vmkernel.log, we can see that the sense information is 
  missing (0xE, 0x0, 0x0) instead of (0xE, 0x1D, 0x0).
  2014-12-30T12:13:20.714Z cpu6:33519)ScsiDeviceIO: 2338: 
  Cmd(0x412e84f957c0) 0x89, CmdSN 0x234d from world 519051 to dev 
  "eui.0024f400d5020007" failed H:0x0 D:0x2 P:0x0 Valid sense data: 0xe 0x0 0x0.
  2014-12-30T12:13:20.766Z cpu6:33519)ScsiDeviceIO: 2338: 
  Cmd(0x412e84f91d00) 0x89, CmdSN 0x2350 from world 519051 to dev 
  "eui.0024f400d5020007" failed H:0x0 D:0x2 P:0x0 Valid sense data: 0xe 0x0 0x0.
  2014-12-30T12:13:20.766Z cpu6:33519)ScsiDeviceIO: 2338: 
  Cmd(0x412e80449fc0) 0x89, CmdSN 0x234f from world 519051 to dev 
  "eui.0024f400d5020007" failed H:0x0 D:0x2 P:0x0 Valid sense data: 0xe 0x0 0x0.
  
  This patch fixes this issue, the test will run without a problem with the
  fix (no IO errors, all the files are properly written to the directory).
  
  Signed-off-by: Shahar Salzman <shahar.salzman@kaminario.com>
  Reviewed-by: Eran Mann <eran.mann@kaminario.com>
  [bvanassche: simplified implementation]
  Signed-off-by: Bart Van Assche <bvanassche@acm.org>
........
  r5966 | bvassche | 2015-01-13 11:38:09 +0200 (Tue, 13 Jan 2015) | 5 lines
  
  qla2x00t: Register for RSCNs in target mode
  
  The QLogic firmware and qla2xxx do not register for RSCNs in
  target-only mode, so do that explicitly.
........
  r5967 | bvassche | 2015-01-14 10:06:12 +0200 (Wed, 14 Jan 2015) | 1 line
  
  scst_targ: Use tabs instead of spaces for indentation (detected by checkpatch)
........
  r5968 | bvassche | 2015-01-15 10:58:39 +0200 (Thu, 15 Jan 2015) | 4 lines
  
  scst_targ: Avoid triggering a kernel panic if dev_user_parse() returns SCST_CMD_STATE_STOP
  
  Reported-by: Ilan Steinberg <ilan.steinberg@kaminario.com>
........
  r5969 | vlnb | 2015-01-16 03:21:10 +0200 (Fri, 16 Jan 2015) | 3 lines
  
  Fix READ BUFFER and WRITE BUFFER commands
........
  r5970 | vlnb | 2015-01-16 05:16:26 +0200 (Fri, 16 Jan 2015) | 3 lines
  
  Follow up for r5968
........
  r5971 | vlnb | 2015-01-16 05:53:29 +0200 (Fri, 16 Jan 2015) | 5 lines
  
  Report during user devices unjam LUN NOT SUPPORTED sense
  
  Reported-By: shahar.salzman <shahar.salzman@kaminario.com>
........
  r5972 | bvassche | 2015-01-16 15:01:58 +0200 (Fri, 16 Jan 2015) | 2 lines
  
  scst.spec.in: Rename variable kver into kversion
........
  r5973 | bvassche | 2015-01-16 15:12:22 +0200 (Fri, 16 Jan 2015) | 2 lines
  
  scst.spec.in: Pass kernel version via RPM-variable %{kversion} instead of shell variable ${KVER}
........
  r5974 | bvassche | 2015-01-16 15:16:06 +0200 (Fri, 16 Jan 2015) | 6 lines
  
  scst.spec.in: Determine version number correctly on a koji server
  
  This patch has been tested on a koji build server and also on four
  different RPM-based distributions (CentOS 7, Fedora 20, openSuSE 13.2
  and SLES 11 SP3).
........
  r5975 | bvassche | 2015-01-16 18:12:38 +0200 (Fri, 16 Jan 2015) | 1 line
  
  scst.spec.in: Leave out kernel version from RPM name
........
  r5976 | bvassche | 2015-01-16 18:20:10 +0200 (Fri, 16 Jan 2015) | 1 line
  
  scst.spec.in: Add DKMS support
........
  r5977 | vlnb | 2015-01-20 06:18:07 +0200 (Tue, 20 Jan 2015) | 3 lines
  
  Revert r5964 as not needed
........
  r5978 | vlnb | 2015-01-20 06:20:13 +0200 (Tue, 20 Jan 2015) | 3 lines
  
  Revert r5963 as not needed
........
  r5979 | bvassche | 2015-01-20 17:04:23 +0200 (Tue, 20 Jan 2015) | 13 lines
  
  scst: Rework SCSI pass-through support for kernel versions >= 2.6.30
  
  Changes in this patch:
  - Rework the SCSI pass-through code such that for kernel versions
    >= 2.6.30 the scst_exec_req_fifo patch is no longer needed.
  - Modify the pass-through code such that blk_rq_append_bio() is only
    called for kernel version 2.6.30. For later kernel versions
    blk_make_request() is called instead.
  - Rework scst_scsi_exec_async().
  - Add debug tracing of SCSI pass-through result status.
  - Add a lockdep_assert_held() call in scsi_end_async().
........
  r5980 | bvassche | 2015-01-20 19:13:13 +0200 (Tue, 20 Jan 2015) | 1 line
  
  nightly build: Update kernel versions
........
  r5981 | vlnb | 2015-01-21 06:15:42 +0200 (Wed, 21 Jan 2015) | 3 lines
  
  Follow up for r5979
........
  r5982 | vlnb | 2015-01-21 06:20:53 +0200 (Wed, 21 Jan 2015) | 5 lines
  
  Fix returning changeable values for caching mode page
  
  Reported by Consus <consus@gmx.com>
........
  r5983 | bvassche | 2015-01-21 15:11:56 +0200 (Wed, 21 Jan 2015) | 1 line
  
  scst.h: Fix a sparse warning for kernels 2.6.29..2.6.31
........
  r5984 | vlnb | 2015-01-22 07:03:17 +0200 (Thu, 22 Jan 2015) | 9 lines
  
  [PATCH] scst_local: Fix bidirectional command support
  
  scsi_setup_cmnd() sets sc_data_direction to DMA_TO_DEVICE for bidirectional
  commands. Hence test SCpnt->request->next_rq instead of sc_data_direction
  to figure out whether or not a command is bidirectional.
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5985 | vlnb | 2015-01-22 07:06:45 +0200 (Thu, 22 Jan 2015) | 12 lines
  
  [PATCH] scst_main: Suppress a checkpatch warning triggered by INIT_CACHEP{,_ALIGN}
  
  Avoid that checkpatch v3.18 reports the following warning for these
  two macros:
  
  WARNING: Macros with flow control statements should be avoided
  
  This patch does not change any functionality.
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5986 | vlnb | 2015-01-22 07:09:17 +0200 (Thu, 22 Jan 2015) | 9 lines
  
  scst_vdisk: Micro-optimize vdisk_caching_pg
  
  This patch does not change any behavior but micro-optimizes
  vdisk_caching_pg(). Declaring the array caching_pg[] const reduces
  11 bytes from the assembler code of this function.
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5987 | vlnb | 2015-01-22 07:10:42 +0200 (Thu, 22 Jan 2015) | 10 lines
  
  scst: Suppress a smatch warning in vdisk_unmap_range()
  
  Avoid that the static source code analysis tool 'smatch' reports
  the following warning:
  
  vdisk_unmap_range() warn: should 'blocks << cmd->dev->block_shift' be a 64 bit type?
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5988 | vlnb | 2015-01-22 07:13:59 +0200 (Thu, 22 Jan 2015) | 27 lines
  
  scst_vdisk: Fix zero-copy read for tmpfs
  
  For some filesystems, e.g. tmpfs, address_space.readpage is NULL.
  Disable zero-copy reading for such filesystems. See also shmem_aops
  in mm/shmem.c. See also inode_init_always() and empty_aops in fs/inode.c.
  
  This patch avoids that the following call trace is triggered:
  
  BUG: unable to handle kernel NULL pointer dereference at (null)
  Call Trace:
   [<ffffffffa0547d66>] prepare_read+0x106/0x1d0 [scst_vdisk]
   [<ffffffffa0547f20>] fileio_alloc_data_buf+0xf0/0x330 [scst_vdisk]
   [<ffffffffa046fc9b>] scst_prepare_space+0x9b/0x6e0 [scst]
   [<ffffffffa047d4d5>] scst_process_active_cmd+0x545/0x840 [scst]
   [<ffffffffa047dad2>] scst_cmd_init_done+0x302/0x5d0 [scst]
   [<ffffffffa0563ab2>] scst_cmd_init_stage1_done.constprop.37+0x12/0x20 [iscsi_scst]
   [<ffffffffa056a9ea>] scsi_cmnd_start+0x25a/0x550 [iscsi_scst]
   [<ffffffffa056b4a8>] cmnd_rx_start+0x148/0x1a0 [iscsi_scst]
   [<ffffffffa056e4f8>] process_read_io+0x3b8/0x800 [iscsi_scst]
   [<ffffffffa056ea07>] scst_do_job_rd+0xc7/0x220 [iscsi_scst]
   [<ffffffffa056efed>] istrd+0x16d/0x2e0 [iscsi_scst]
   [<ffffffff81079efd>] kthread+0xed/0x110
   [<ffffffff817227fc>] ret_from_fork+0x7c/0xb0
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5989 | vlnb | 2015-01-24 07:37:57 +0200 (Sat, 24 Jan 2015) | 5 lines
  
  scst_local: Rework data direction detection code
  
  Signed-off-by: Bart Van Assche <bart.vanassche@sandisk.com>
........
  r5990 | bvassche | 2015-01-26 13:32:32 +0200 (Mon, 26 Jan 2015) | 1 line
  
  ib_srpt: Detect Mellanox OFED 2.3 correctly
........
  r5991 | vlnb | 2015-01-28 07:07:46 +0200 (Wed, 28 Jan 2015) | 3 lines
  
  Cleanups
........


git-svn-id: http://svn.code.sf.net/p/scst/svn/branches/iser@5993 d57e44dd-8a1f-0410-8b47-8ef2f437770f
This commit is contained in:
Yan Burman
2015-01-28 12:12:32 +00:00
parent e6e1752b8f
commit bb7f5caef2
114 changed files with 4515 additions and 18152 deletions
+2 -2
View File
@@ -43,7 +43,7 @@ SRC_FILES=$(wildcard */*.[ch])
# The file Modules.symvers has been renamed in the 2.6.18 kernel to
# Module.symvers. Find out which name to use by looking in $(KDIR).
MODULE_SYMVERS:=$(shell if [ -e $(KDIR)/Module.symvers ]; then \
MODULE_SYMVERS:=$(shell if [ -e "$(KDIR)/Module.symvers" ]; then \
echo Module.symvers; else echo Modules.symvers; fi)
# Name of the OFED kernel RPM.
@@ -52,7 +52,7 @@ OFED_KERNEL_IB_RPM:=$(shell for r in mlnx-ofa_kernel compat-rdma kernel-ib; do r
# Name of the OFED kernel development RPM.
OFED_KERNEL_IB_DEVEL_RPM:=$(shell for r in mlnx-ofa_kernel-devel compat-rdma-devel kernel-ib-devel; do rpm -q $$r 2>/dev/null | grep -q "^$$r" && echo $$r && break; done)
OFED_FLAVOR=$(shell /usr/bin/ofed_info 2>/dev/null | head -n1 | sed -n 's/^MLNX_OFED.*/MOFED/p;s/^OFED-.*/OFED/p')
OFED_FLAVOR=$(shell /usr/bin/ofed_info 2>/dev/null | head -n1 | sed -n 's/^\(MLNX_OFED\|OFED-internal\).*/MOFED/p;s/^OFED-.*/OFED/p')
ifneq ($(OFED_KERNEL_IB_RPM),)
ifeq ($(OFED_KERNEL_IB_RPM),compat-rdma)
+4 -4
View File
@@ -56,10 +56,10 @@ The ib_srpt kernel module supports the following parameters:
GUID (e.g. 0002:c903:0005:f34a).
3. Access control configuration per HCA port and referring to a HCA via its
port GID (e.g. fe80:0000:0000:0000:0002:c903:0005:f34b).
Mode (1) is choosen if both one_target_per_port and
use_node_guid_in_target_name are false. Mode (2) is choosen if
Mode (1) is chosen if both one_target_per_port and
use_node_guid_in_target_name are false. Mode (2) is chosen if
one_target_per_port is false and use_node_guid_in_target_name is true. Mode
(3) is choosen if one_target_per_port is true. This last mode is the
(3) is chosen if one_target_per_port is true. This last mode is the
default mode.
* rdma_cm_port (number)
A 16-bit number that specifies the port number to be registered via the
@@ -362,7 +362,7 @@ Performance Notes - Target Side
improves performance compared to debug mode.
* When using high-latency storage devices (hard disks), the default value
choosen by SCST for DEVICE.threads_num should be fine. When using
chosen by SCST for DEVICE.threads_num should be fine. When using
low-latency storage devices though (SSDs), DEVICE.threads_num should be set
to 1 or 2 in /etc/scst.conf in order to reach optimal performance for small
block sizes (e.g. 4 KB).
+12
View File
@@ -0,0 +1,12 @@
diff --git a/Makefile b/Makefile
index 540f7b2..078307f 100644
--- a/Makefile
+++ b/Makefile
@@ -361,6 +361,7 @@ USERINCLUDE := \
# Use LINUXINCLUDE when you must reference the include/ directory.
# Needed to be compatible with the O= option
LINUXINCLUDE := \
+ $(PRE_CFLAGS) \
-I$(srctree)/arch/$(hdr-arch)/include \
-Iarch/$(hdr-arch)/include/generated \
$(if $(KBUILD_SRC), -I$(srctree)/include) \
+12
View File
@@ -0,0 +1,12 @@
diff --git a/Makefile b/Makefile
index fd80c6e..09ca4ea 100644
--- a/Makefile
+++ b/Makefile
@@ -390,6 +390,7 @@ USERINCLUDE := \
# Use LINUXINCLUDE when you must reference the include/ directory.
# Needed to be compatible with the O= option
LINUXINCLUDE := \
+ $(PRE_CFLAGS) \
-I$(srctree)/arch/$(hdr-arch)/include \
-Iarch/$(hdr-arch)/include/generated \
$(if $(KBUILD_SRC), -I$(srctree)/include) \
+268 -84
View File
@@ -50,6 +50,7 @@
#endif
#endif
#include "ib_srpt.h"
#include "srp-ext.h"
#define LOG_PREFIX "ib_srpt" /* Prefix for SCST tracing macros. */
#if defined(INSIDE_KERNEL_TREE)
#include <scst/scst_debug.h>
@@ -118,6 +119,16 @@ module_param(srp_max_rsp_size, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(srp_max_rsp_size,
"Maximum size of SRP response messages in bytes.");
#if LINUX_VERSION_CODE < KERNEL_VERSION(2, 6, 31) \
|| defined(RHEL_MAJOR) && RHEL_MAJOR -0 <= 5
static int use_srq = true;
#else
static bool use_srq = true;
#endif
module_param(use_srq, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(use_srq,
"Whether or not to use SRQ");
static int srpt_srq_size = DEFAULT_SRPT_SRQ_SIZE;
module_param(srpt_srq_size, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(srpt_srq_size,
@@ -459,6 +470,7 @@ static void srpt_get_ioc(struct srpt_device *sdev, u32 slot,
struct ib_dm_mad *mad)
{
struct ib_dm_ioc_profile *iocp;
int send_queue_depth;
iocp = (struct ib_dm_ioc_profile *)mad->data;
@@ -472,6 +484,11 @@ static void srpt_get_ioc(struct srpt_device *sdev, u32 slot,
return;
}
if (sdev->use_srq)
send_queue_depth = sdev->srq_size;
else
send_queue_depth = min(SRPT_RQ_SIZE, sdev->dev_attr.max_qp_wr);
memset(iocp, 0, sizeof(*iocp));
strcpy(iocp->id_string, SRPT_ID_STRING);
iocp->guid = cpu_to_be64(srpt_service_guid);
@@ -484,7 +501,8 @@ static void srpt_get_ioc(struct srpt_device *sdev, u32 slot,
iocp->io_subclass = cpu_to_be16(SRP_IO_SUBCLASS);
iocp->protocol = cpu_to_be16(SRP_PROTOCOL);
iocp->protocol_version = cpu_to_be16(SRP_PROTOCOL_VERSION);
iocp->send_queue_depth = cpu_to_be16(sdev->srq_size);
iocp->send_queue_depth = cpu_to_be16(send_queue_depth);
iocp->rdma_read_depth = 4;
iocp->send_size = cpu_to_be32(srp_max_req_size);
iocp->rdma_size = cpu_to_be32(min(max(srp_max_rdma_size, 256U),
@@ -772,21 +790,27 @@ static void srpt_unregister_mad_agent(struct srpt_device *sdev)
*/
static struct srpt_ioctx *srpt_alloc_ioctx(struct srpt_device *sdev,
int ioctx_size, int dma_size,
int alignment_offset,
enum dma_data_direction dir)
{
struct srpt_ioctx *ioctx;
ioctx = kmalloc(ioctx_size, GFP_KERNEL);
ioctx = kzalloc(ioctx_size, GFP_KERNEL);
if (!ioctx)
goto err;
ioctx->buf = kmalloc(dma_size, GFP_KERNEL);
ioctx->buf = kmalloc(dma_size + alignment_offset, GFP_KERNEL);
if (!ioctx->buf)
goto err_free_ioctx;
ioctx->dma = ib_dma_map_single(sdev->device, ioctx->buf, dma_size, dir);
/* Complain if it is not safe to use zero-copy */
WARN_ON_ONCE(alignment_offset && ((uintptr_t)ioctx->buf & 511));
ioctx->dma = ib_dma_map_single(sdev->device, ioctx->buf,
dma_size + alignment_offset, dir);
if (ib_dma_mapping_error(sdev->device, ioctx->dma))
goto err_free_buf;
ioctx->offset = alignment_offset;
return ioctx;
@@ -822,7 +846,8 @@ static void srpt_free_ioctx(struct srpt_device *sdev, struct srpt_ioctx *ioctx,
*/
static struct srpt_ioctx **srpt_alloc_ioctx_ring(struct srpt_device *sdev,
int ring_size, int ioctx_size,
int dma_size, enum dma_data_direction dir)
int dma_size, int alignment_offset,
enum dma_data_direction dir)
{
struct srpt_ioctx **ring;
int i;
@@ -836,7 +861,8 @@ static struct srpt_ioctx **srpt_alloc_ioctx_ring(struct srpt_device *sdev,
if (!ring)
goto out;
for (i = 0; i < ring_size; ++i) {
ring[i] = srpt_alloc_ioctx(sdev, ioctx_size, dma_size, dir);
ring[i] = srpt_alloc_ioctx(sdev, ioctx_size, dma_size,
alignment_offset, dir);
if (!ring[i])
goto err;
ring[i]->index = i;
@@ -845,7 +871,7 @@ static struct srpt_ioctx **srpt_alloc_ioctx_ring(struct srpt_device *sdev,
err:
while (--i >= 0)
srpt_free_ioctx(sdev, ring[i], dma_size, dir);
srpt_free_ioctx(sdev, ring[i], dma_size + ring[i]->offset, dir);
kfree(ring);
ring = NULL;
out:
@@ -862,8 +888,12 @@ static void srpt_free_ioctx_ring(struct srpt_ioctx **ioctx_ring,
{
int i;
if (!ioctx_ring)
return;
for (i = 0; i < ring_size; ++i)
srpt_free_ioctx(sdev, ioctx_ring[i], dma_size, dir);
srpt_free_ioctx(sdev, ioctx_ring[i],
dma_size + ioctx_ring[i]->offset, dir);
kfree(ioctx_ring);
}
@@ -913,16 +943,17 @@ static bool srpt_test_and_set_cmd_state(struct srpt_send_ioctx *ioctx,
/**
* srpt_post_recv() - Post an IB receive request.
*/
static int srpt_post_recv(struct srpt_device *sdev,
static int srpt_post_recv(struct srpt_device *sdev, struct srpt_rdma_ch *ch,
struct srpt_recv_ioctx *ioctx)
{
struct ib_sge list;
struct ib_recv_wr wr, *bad_wr;
int status;
BUG_ON(!sdev);
wr.wr_id = encode_wr_id(SRPT_RECV, ioctx->ioctx.index);
list.addr = ioctx->ioctx.dma;
list.addr = ioctx->ioctx.dma + ioctx->ioctx.offset;
list.length = srp_max_req_size;
list.lkey = sdev->mr->lkey;
@@ -930,10 +961,14 @@ static int srpt_post_recv(struct srpt_device *sdev,
wr.sg_list = &list;
wr.num_sge = 1;
return ib_post_srq_recv(sdev->srq, &wr, &bad_wr);
if (sdev->use_srq)
status = ib_post_srq_recv(sdev->srq, &wr, &bad_wr);
else
status = ib_post_recv(ch->qp, &wr, &bad_wr);
return status;
}
static int srpt_adjust_srq_wr_avail(struct srpt_rdma_ch *ch, int delta)
static int srpt_adjust_sq_wr_avail(struct srpt_rdma_ch *ch, int delta)
{
return atomic_add_return(delta, &ch->sq_wr_avail);
}
@@ -952,8 +987,9 @@ static int srpt_post_send(struct srpt_rdma_ch *ch,
int ret;
ret = -ENOMEM;
if (srpt_adjust_srq_wr_avail(ch, -1) < 0) {
PRINT_WARNING("IB send queue full (needed 1)");
if (srpt_adjust_sq_wr_avail(ch, -1) < 0) {
PRINT_WARNING("ch %s-%d send queue full (needed 1)",
ch->sess_name, ch->qp->qp_num);
goto out;
}
@@ -975,7 +1011,7 @@ static int srpt_post_send(struct srpt_rdma_ch *ch,
out:
if (ret < 0)
srpt_adjust_srq_wr_avail(ch, 1);
srpt_adjust_sq_wr_avail(ch, 1);
return ret;
}
@@ -1012,7 +1048,8 @@ static int srpt_zerolength_write(struct srpt_rdma_ch *ch)
* Returns -EINVAL when the SRP_CMD request contains inconsistent descriptors;
* -ENOMEM when memory allocation fails and zero upon success.
*/
static int srpt_get_desc_tbl(struct srpt_send_ioctx *ioctx,
static int srpt_get_desc_tbl(struct srpt_recv_ioctx *recv_ioctx,
struct srpt_send_ioctx *ioctx,
struct srp_cmd *srp_cmd,
scst_data_direction *dir, u64 *data_len)
{
@@ -1064,7 +1101,38 @@ static int srpt_get_desc_tbl(struct srpt_send_ioctx *ioctx,
* is four times the value specified in bits 3..7. Hence the "& ~3".
*/
add_cdb_offset = srp_cmd->add_cdb_len & ~3;
if (fmt == SRP_DATA_DESC_DIRECT) {
if (fmt == SRP_DATA_DESC_IMM) {
struct srp_imm_buf *imm_buf = (void *)(srp_cmd->add_data
+ add_cdb_offset);
void *data;
uint32_t header_size;
uint64_t req_size;
header_size = be32_to_cpu(imm_buf->offset);
*data_len = be32_to_cpu(imm_buf->len);
req_size = header_size + *data_len;
data = (void *)srp_cmd + header_size;
if (req_size > srp_max_req_size) {
PRINT_ERROR("Immediate data (length %d + %lld) exceeds"
" request size %d", header_size, *data_len,
srp_max_req_size);
ret = -EINVAL;
goto out;
}
if (WARN_ONCE(recv_ioctx->byte_len < req_size,
"received too few data - %d < %lld\n",
recv_ioctx->byte_len, req_size)) {
print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16,
1, srp_cmd, recv_ioctx->byte_len, 1);
ret = -EIO;
}
ioctx->imm_data = data;
ioctx->recv_ioctx = recv_ioctx;
if (((uintptr_t)data & 511) == 0) {
sg_init_one(&ioctx->imm_sg, ioctx->imm_data, *data_len);
scst_cmd_set_tgt_sg(&ioctx->scmnd, &ioctx->imm_sg, 1);
}
} else if (fmt == SRP_DATA_DESC_DIRECT) {
ioctx->n_rbuf = 1;
ioctx->rbufs = &ioctx->single_rbuf;
@@ -1260,8 +1328,10 @@ static struct srpt_send_ioctx *srpt_get_send_ioctx(struct srpt_rdma_ch *ch)
BUG_ON(ioctx->ch != ch);
spin_lock_init(&ioctx->spinlock);
ioctx->state = SRPT_STATE_NEW;
EXTRACHECKS_WARN_ON(ioctx->recv_ioctx);
ioctx->n_rbuf = 0;
ioctx->rbufs = NULL;
ioctx->imm_data = NULL;
ioctx->n_rdma = 0;
ioctx->n_rdma_ius = 0;
ioctx->rdma_ius = NULL;
@@ -1276,12 +1346,15 @@ static struct srpt_send_ioctx *srpt_get_send_ioctx(struct srpt_rdma_ch *ch)
*/
static void srpt_put_send_ioctx(struct srpt_send_ioctx *ioctx)
{
struct srpt_rdma_ch *ch;
struct srpt_rdma_ch *ch = ioctx->ch;
struct srpt_recv_ioctx *recv_ioctx = ioctx->recv_ioctx;
unsigned long flags;
BUG_ON(!ioctx);
ch = ioctx->ch;
BUG_ON(!ch);
if (recv_ioctx) {
EXTRACHECKS_WARN_ON(!list_empty(&recv_ioctx->wait_list));
ioctx->recv_ioctx = NULL;
srpt_post_recv(ch->sport->sdev, ch, recv_ioctx);
}
/*
* If the WARN_ON() below gets triggered this means that
@@ -1411,7 +1484,7 @@ static void srpt_handle_send_err_comp(struct srpt_rdma_ch *ch, u64 wr_id,
struct srpt_send_ioctx *ioctx = ch->ioctx_ring[index];
enum srpt_command_state state = ioctx->state;
srpt_adjust_srq_wr_avail(ch, 1);
srpt_adjust_sq_wr_avail(ch, 1);
switch (state) {
case SRPT_STATE_NEED_DATA:
@@ -1442,7 +1515,7 @@ static void srpt_handle_send_comp(struct srpt_rdma_ch *ch,
struct srpt_send_ioctx *ioctx,
enum scst_exec_context context)
{
srpt_adjust_srq_wr_avail(ch, 1);
srpt_adjust_sq_wr_avail(ch, 1);
switch (srpt_set_cmd_state(ioctx, SRPT_STATE_DONE)) {
case SRPT_STATE_CMD_RSP_SENT:
@@ -1472,7 +1545,7 @@ static void srpt_handle_rdma_comp(struct srpt_rdma_ch *ch,
struct scst_cmd *scmnd = &ioctx->scmnd;
EXTRACHECKS_WARN_ON(ioctx->n_rdma <= 0);
srpt_adjust_srq_wr_avail(ch, ioctx->n_rdma);
srpt_adjust_sq_wr_avail(ch, ioctx->n_rdma);
if (opcode == SRPT_RDMA_READ_LAST && scmnd) {
if (srpt_test_and_set_cmd_state(ioctx, SRPT_STATE_NEED_DATA,
@@ -1507,7 +1580,7 @@ static void srpt_handle_rdma_err_comp(struct srpt_rdma_ch *ch,
ioctx->ioctx.index);
break;
}
srpt_adjust_srq_wr_avail(ch, ioctx->n_rdma);
srpt_adjust_sq_wr_avail(ch, ioctx->n_rdma);
if (state == SRPT_STATE_NEED_DATA)
srpt_abort_cmd(ioctx, context);
else
@@ -1661,7 +1734,7 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
BUG_ON(!send_ioctx);
srp_cmd = recv_ioctx->ioctx.buf;
srp_cmd = recv_ioctx->ioctx.buf + recv_ioctx->ioctx.offset;
scmnd = &send_ioctx->scmnd;
ret = scst_rx_cmd_prealloced(scmnd, ch->scst_sess, (u8 *) &srp_cmd->lun,
@@ -1673,7 +1746,8 @@ static int srpt_handle_cmd(struct srpt_rdma_ch *ch,
goto err;
}
ret = srpt_get_desc_tbl(send_ioctx, srp_cmd, &dir, &data_len);
ret = srpt_get_desc_tbl(recv_ioctx, send_ioctx, srp_cmd, &dir,
&data_len);
if (ret) {
PRINT_ERROR("0x%llx: parsing SRP descriptor table failed.",
srp_cmd->tag);
@@ -1739,7 +1813,7 @@ static void srpt_handle_tsk_mgmt(struct srpt_rdma_ch *ch,
srpt_set_cmd_state(send_ioctx, SRPT_STATE_MGMT);
srp_tsk = recv_ioctx->ioctx.buf;
srp_tsk = recv_ioctx->ioctx.buf + recv_ioctx->ioctx.offset;
TRACE_DBG("recv_tsk_mgmt= %d for task_tag= %lld"
" using tag= %lld ch= %p sess= %p",
@@ -1829,10 +1903,11 @@ srpt_handle_new_iu(struct srpt_rdma_ch *ch,
goto push;
ib_dma_sync_single_for_cpu(ch->sport->sdev->device,
recv_ioctx->ioctx.dma, srp_max_req_size,
recv_ioctx->ioctx.dma,
recv_ioctx->ioctx.offset + srp_max_req_size,
DMA_FROM_DEVICE);
srp_cmd = recv_ioctx->ioctx.buf;
srp_cmd = recv_ioctx->ioctx.buf + recv_ioctx->ioctx.offset;
opcode = srp_cmd->opcode;
if (opcode == SRP_CMD || opcode == SRP_TSK_MGMT) {
send_ioctx = srpt_get_send_ioctx(ch);
@@ -1867,7 +1942,8 @@ srpt_handle_new_iu(struct srpt_rdma_ch *ch,
break;
}
srpt_post_recv(ch->sport->sdev, recv_ioctx);
if (!send_ioctx || !send_ioctx->recv_ioctx)
srpt_post_recv(ch->sport->sdev, ch, recv_ioctx);
out:
return send_ioctx;
@@ -1883,7 +1959,6 @@ static void srpt_process_rcv_completion(struct ib_cq *cq,
struct srpt_rdma_ch *ch,
struct ib_wc *wc)
{
struct srpt_device *sdev = ch->sport->sdev;
struct srpt_recv_ioctx *ioctx;
u32 index;
@@ -1894,7 +1969,11 @@ static void srpt_process_rcv_completion(struct ib_cq *cq,
req_lim = srpt_adjust_req_lim(ch, -1, 0);
if (unlikely(req_lim < 0))
PRINT_ERROR("req_lim = %d < 0", req_lim);
ioctx = sdev->ioctx_ring[index];
if (ch->sport->sdev->use_srq)
ioctx = ch->sport->sdev->ioctx_ring[index];
else
ioctx = ch->ioctx_recv_ring[index];
ioctx->byte_len = wc->byte_len;
srpt_handle_new_iu(ch, ioctx, srpt_new_iu_context);
} else {
PRINT_INFO("receiving failed for idx %u with status %d",
@@ -2057,6 +2136,10 @@ static void srpt_unreg_sess(struct scst_session *scst_sess)
sdev, ch->rq_size,
ch->max_rsp_size, DMA_TO_DEVICE);
srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring,
sdev, ch->rq_size,
srp_max_req_size, DMA_FROM_DEVICE);
/* Wait until CM callbacks have finished and prevent new callbacks. */
if (ch->using_rdma_cm)
rdma_destroy_id(ch->rdma_cm.cm_id);
@@ -2122,7 +2205,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
{
struct ib_qp_init_attr *qp_init;
struct srpt_device *sdev = ch->sport->sdev;
int ret;
int i, ret;
EXTRACHECKS_WARN_ON(ch->rq_size < 1);
@@ -2151,12 +2234,25 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
= (void(*)(struct ib_event *, void*))srpt_qp_event;
qp_init->send_cq = ch->cq;
qp_init->recv_cq = ch->cq;
qp_init->srq = sdev->srq;
qp_init->sq_sig_type = IB_SIGNAL_REQ_WR;
qp_init->qp_type = IB_QPT_RC;
qp_init->cap.max_send_wr = srpt_sq_size;
ch->max_sge = max_t(int, 1, sdev->dev_attr.max_sge - max_sge_delta);
/*
* For max_sge values > 2 * max_sge_delta, subtract max_sge_delta. For
* max_sge values < max_sge_delta, use max_sge. For intermediate
* max_sge values, use max_sge_delta.
*/
ch->max_sge = sdev->dev_attr.max_sge -
min(max_sge_delta,
max_t(unsigned, 0, sdev->dev_attr.max_sge - max_sge_delta));
qp_init->cap.max_send_sge = ch->max_sge;
qp_init->cap.max_recv_sge = ch->max_sge;
if (sdev->use_srq) {
qp_init->srq = sdev->srq;
} else {
qp_init->cap.max_recv_wr = ch->rq_size;
qp_init->cap.max_recv_sge = ch->max_sge;
}
if (ch->using_rdma_cm) {
ret = rdma_create_qp(ch->rdma_cm.cm_id, sdev->pd, qp_init);
@@ -2182,6 +2278,10 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
TRACE_DBG("qp_num = %#x", ch->qp->qp_num);
if (!sdev->use_srq)
for (i = 0; i < ch->rq_size; i++)
srpt_post_recv(sdev, ch, ch->ioctx_recv_ring[i]);
atomic_set(&ch->sq_wr_avail, qp_init->cap.max_send_wr);
TRACE_DBG("%s: max_cqe= %d max_sge= %d sq_size = %d ch= %p", __func__,
@@ -2465,7 +2565,8 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
" %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x,"
" t_port_id %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x and"
" it_iu_len %d on port %d"
" (guid=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x)",
" (guid=%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x);"
" pkey %#04x",
be16_to_cpu(*(__be16 *)&req->initiator_port_id[0]),
be16_to_cpu(*(__be16 *)&req->initiator_port_id[2]),
be16_to_cpu(*(__be16 *)&req->initiator_port_id[4]),
@@ -2491,7 +2592,8 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
be16_to_cpu(raw_port_gid[4]),
be16_to_cpu(raw_port_gid[5]),
be16_to_cpu(raw_port_gid[6]),
be16_to_cpu(raw_port_gid[7]));
be16_to_cpu(raw_port_gid[7]),
be16_to_cpu(pkey));
nexus = srpt_get_nexus(srpt_tgt, req->initiator_port_id,
req->target_port_id);
@@ -2568,8 +2670,10 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
ch->ioctx_ring = (struct srpt_send_ioctx **)
srpt_alloc_ioctx_ring(ch->sport->sdev, ch->rq_size,
sizeof(*ch->ioctx_ring[0]),
ch->max_rsp_size, DMA_TO_DEVICE);
ch->max_rsp_size, 0, DMA_TO_DEVICE);
if (!ch->ioctx_ring) {
PRINT_ERROR("rejected SRP_LOGIN_REQ because creating"
" a new QP SQ ring failed.");
rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
goto free_ch;
}
@@ -2579,6 +2683,23 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
ch->ioctx_ring[i]->ch = ch;
list_add_tail(&ch->ioctx_ring[i]->free_list, &ch->free_list);
}
if (!sdev->use_srq) {
ch->ioctx_recv_ring = (struct srpt_recv_ioctx **)
srpt_alloc_ioctx_ring(ch->sport->sdev, ch->rq_size,
sizeof(*ch->ioctx_recv_ring[0]),
srp_max_req_size,
DATA_ALIGNMENT_OFFSET,
DMA_FROM_DEVICE);
if (!ch->ioctx_recv_ring) {
PRINT_ERROR("rejected SRP_LOGIN_REQ because creating"
" a new QP RQ ring failed.");
rej->reason =
cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
goto free_ring;
}
for (i = 0; i < ch->rq_size; i++)
INIT_LIST_HEAD(&ch->ioctx_recv_ring[i]->wait_list);
}
ch->comp_vector = srpt_next_comp_vector(srpt_tgt);
@@ -2587,7 +2708,7 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
PRINT_ERROR("rejected SRP_LOGIN_REQ because creating"
" a new RDMA channel failed.");
goto free_ring;
goto free_recv_ring;
}
if (one_target_per_port) {
@@ -2683,11 +2804,12 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
/* create srp_login_response */
rsp->opcode = SRP_LOGIN_RSP;
rsp->tag = req->tag;
rsp->max_it_iu_len = req->req_it_iu_len;
rsp->max_it_iu_len = cpu_to_be32(srp_max_req_size);
rsp->max_ti_iu_len = req->req_it_iu_len;
ch->max_ti_iu_len = it_iu_len;
rsp->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT |
SRP_BUF_FORMAT_INDIRECT);
SRP_BUF_FORMAT_INDIRECT |
SRP_BUF_FORMAT_IMM);
rsp->req_lim_delta = cpu_to_be32(ch->rq_size);
ch->req_lim = ch->rq_size;
ch->req_lim_delta = 0;
@@ -2747,6 +2869,11 @@ unreg_ch:
destroy_ib:
srpt_destroy_ch_ib(ch);
free_recv_ring:
srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_recv_ring,
ch->sport->sdev, ch->rq_size,
srp_max_req_size, DMA_FROM_DEVICE);
free_ring:
srpt_free_ioctx_ring((struct srpt_ioctx **)ch->ioctx_ring,
ch->sport->sdev, ch->rq_size,
@@ -2859,10 +2986,22 @@ static int srpt_rdma_cm_req_recv(struct rdma_cm_id *cm_id,
cm_id->route.path_rec->pkey, &req, src_addr);
}
static void srpt_cm_rej_recv(struct srpt_rdma_ch *ch)
static void srpt_cm_rej_recv(struct srpt_rdma_ch *ch,
enum ib_cm_rej_reason reason,
const u8 *private_data,
u8 private_data_len)
{
PRINT_INFO("Received CM REJ for ch %s-%d.", ch->sess_name,
ch->qp->qp_num);
char *priv = kmalloc(private_data_len * 3 + 1, GFP_KERNEL);
int i;
if (priv) {
priv[0] = '\0';
for (i = 0; i < private_data_len; i++)
sprintf(priv + 3 * i, "%02x ", private_data[i]);
}
PRINT_INFO("Received CM REJ for ch %s-%d; reason %d; private data %s.",
ch->sess_name, ch->qp->qp_num, reason, priv ? : "(?)");
kfree(priv);
}
static void srpt_check_timeout(struct srpt_rdma_ch *ch)
@@ -2989,7 +3128,9 @@ static int srpt_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
event->private_data);
break;
case IB_CM_REJ_RECEIVED:
srpt_cm_rej_recv(ch);
srpt_cm_rej_recv(ch, event->param.rej_rcvd.reason,
event->private_data,
IB_CM_REJ_PRIVATE_DATA_SIZE);
break;
case IB_CM_RTU_RECEIVED:
case IB_CM_USER_ESTABLISHED:
@@ -3033,7 +3174,9 @@ static int srpt_rdma_cm_handler(struct rdma_cm_id *cm_id,
ret = srpt_rdma_cm_req_recv(cm_id, event);
break;
case RDMA_CM_EVENT_REJECTED:
srpt_cm_rej_recv(ch);
srpt_cm_rej_recv(ch, event->status,
event->param.conn.private_data,
event->param.conn.private_data_len);
break;
case RDMA_CM_EVENT_ESTABLISHED:
srpt_cm_rtu_recv(ch);
@@ -3201,7 +3344,7 @@ static int srpt_map_sg_to_ib_sge(struct srpt_rdma_ch *ch,
dma_len = ib_sg_dma_len(dev, &sg[0]);
dma_addr = ib_sg_dma_address(dev, &sg[0]);
/* this second loop is really mapped sg_addres to rdma_iu->ib_sge */
/* this second loop is really mapped sg_address to rdma_iu->ib_sge */
for (i = 0, j = 0, cur_sg = sg;
j < count && i < ioctx->n_rbuf && tsize > 0; ++i, ++riu, ++db) {
rsize = be32_to_cpu(db->len);
@@ -3266,6 +3409,10 @@ static void srpt_unmap_sg_to_ib_sge(struct srpt_rdma_ch *ch,
EXTRACHECKS_BUG_ON(!ch);
EXTRACHECKS_BUG_ON(!ioctx);
if (ioctx->imm_data)
return;
EXTRACHECKS_BUG_ON(ioctx->n_rdma && !ioctx->rdma_ius);
if (ioctx->rdma_ius != (void *)ioctx->rdma_ius_buf)
@@ -3305,10 +3452,10 @@ static int srpt_perform_rdmas(struct srpt_rdma_ch *ch,
if (dir == SCST_DATA_WRITE) {
ret = -ENOMEM;
sq_wr_avail = srpt_adjust_srq_wr_avail(ch, -n_rdma);
sq_wr_avail = srpt_adjust_sq_wr_avail(ch, -n_rdma);
if (sq_wr_avail < 0) {
PRINT_WARNING("IB send queue full (needed %d)",
n_rdma);
PRINT_WARNING("ch %s-%d send queue full (needed %d)",
ch->sess_name, ch->qp->qp_num, n_rdma);
goto out;
}
}
@@ -3374,7 +3521,7 @@ static int srpt_perform_rdmas(struct srpt_rdma_ch *ch,
out:
if (unlikely(dir == SCST_DATA_WRITE && ret < 0))
srpt_adjust_srq_wr_avail(ch, n_rdma);
srpt_adjust_sq_wr_avail(ch, n_rdma);
return ret;
}
@@ -3391,6 +3538,30 @@ static int srpt_xfer_data(struct srpt_rdma_ch *ch,
{
int ret;
if (ioctx->imm_data) {
BUG_ON(!srpt_test_and_set_cmd_state(ioctx, SRPT_STATE_NEED_DATA,
SRPT_STATE_DATA_IN));
if (unlikely(!scst_cmd_get_tgt_data_buff_alloced(scmnd))) {
unsigned offset = 0, len;
uint8_t *buf;
len = scst_get_buf_first(scmnd, &buf);
while (len > 0) {
memcpy(buf, ioctx->imm_data + offset, len);
offset += len;
len = scst_get_buf_next(scmnd, &buf);
}
WARN_ON_ONCE(offset !=
scst_cmd_get_expected_transfer_len(scmnd));
}
scst_rx_data(scmnd, SCST_RX_STATUS_SUCCESS,
in_irq() ? SCST_CONTEXT_TASKLET :
in_softirq() ? SCST_CONTEXT_DIRECT_ATOMIC :
SCST_CONTEXT_DIRECT);
ret = SCST_TGT_RES_SUCCESS;
goto out;
}
ret = srpt_map_sg_to_ib_sge(ch, ioctx, scmnd);
if (ret) {
PRINT_ERROR("%s[%d] ret=%d", __func__, __LINE__, ret);
@@ -4173,14 +4344,37 @@ static void srpt_add_one(struct ib_device *device)
srq_attr.srq_type = IB_SRQT_BASIC;
#endif
sdev->srq = ib_create_srq(sdev->pd, &srq_attr);
sdev->srq = use_srq ? ib_create_srq(sdev->pd, &srq_attr) :
ERR_PTR(-ENOSYS);
if (IS_ERR(sdev->srq)) {
PRINT_ERROR("ib_create_srq() failed: %ld", PTR_ERR(sdev->srq));
goto err_mr;
}
TRACE_DBG("%s: ib_create_srq() failed: %ld", __func__,
PTR_ERR(sdev->srq));
TRACE_DBG("%s: create SRQ #wr= %d max_allow=%d dev= %s", __func__,
sdev->srq_size, sdev->dev_attr.max_srq_wr, device->name);
/* SRQ not supported. */
sdev->use_srq = false;
} else {
TRACE_DBG("%s: create SRQ #wr= %d max_allow=%d dev= %s",
__func__, sdev->srq_size, sdev->dev_attr.max_srq_wr,
device->name);
sdev->use_srq = true;
sdev->ioctx_ring = (struct srpt_recv_ioctx **)
srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
sizeof(*sdev->ioctx_ring[0]),
srp_max_req_size,
DATA_ALIGNMENT_OFFSET,
DMA_FROM_DEVICE);
if (!sdev->ioctx_ring) {
PRINT_ERROR("srpt_alloc_ioctx_ring() failed");
goto err_mr;
}
for (i = 0; i < sdev->srq_size; ++i) {
INIT_LIST_HEAD(&sdev->ioctx_ring[i]->wait_list);
srpt_post_recv(sdev, NULL, sdev->ioctx_ring[i]);
}
}
if (!srpt_service_guid)
srpt_service_guid = be64_to_cpu(device->node_guid) &
@@ -4189,7 +4383,7 @@ static void srpt_add_one(struct ib_device *device)
cm_id = ib_create_cm_id(device, srpt_cm_handler, sdev);
if (IS_ERR(cm_id)) {
PRINT_ERROR("ib_create_cm_id() failed: %ld", PTR_ERR(cm_id));
goto err_srq;
goto err_ring;
}
sdev->cm_id = cm_id;
@@ -4220,20 +4414,6 @@ static void srpt_add_one(struct ib_device *device)
goto err_cm;
}
sdev->ioctx_ring = (struct srpt_recv_ioctx **)
srpt_alloc_ioctx_ring(sdev, sdev->srq_size,
sizeof(*sdev->ioctx_ring[0]),
srp_max_req_size, DMA_FROM_DEVICE);
if (!sdev->ioctx_ring) {
PRINT_ERROR("srpt_alloc_ioctx_ring() failed");
goto err_event;
}
for (i = 0; i < sdev->srq_size; ++i) {
INIT_LIST_HEAD(&sdev->ioctx_ring[i]->wait_list);
srpt_post_recv(sdev, sdev->ioctx_ring[i]);
}
WARN_ON(sdev->device->phys_port_cnt > ARRAY_SIZE(sdev->port));
for (i = 1; i <= sdev->device->phys_port_cnt; i++) {
@@ -4254,7 +4434,7 @@ static void srpt_add_one(struct ib_device *device)
if (srpt_refresh_port(sport)) {
PRINT_ERROR("MAD registration failed for %s-%d.",
sdev->device->name, i);
goto err_ring;
goto err_event;
}
}
@@ -4265,16 +4445,16 @@ out:
TRACE_EXIT();
return;
err_ring:
srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
sdev->srq_size, srp_max_req_size,
DMA_FROM_DEVICE);
err_event:
ib_unregister_event_handler(&sdev->event_handler);
err_cm:
ib_destroy_cm_id(sdev->cm_id);
err_srq:
ib_destroy_srq(sdev->srq);
err_ring:
srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
sdev->srq_size, srp_max_req_size,
DMA_FROM_DEVICE);
if (sdev->use_srq)
ib_destroy_srq(sdev->srq);
err_mr:
ib_dereg_mr(sdev->mr);
err_pd:
@@ -4347,13 +4527,15 @@ static void srpt_remove_one(struct ib_device *device)
sdev->srpt_tgt.scst_tgt = NULL;
}
ib_destroy_srq(sdev->srq);
ib_dereg_mr(sdev->mr);
ib_dealloc_pd(sdev->pd);
srpt_free_ioctx_ring((struct srpt_ioctx **)sdev->ioctx_ring, sdev,
sdev->srq_size, srp_max_req_size, DMA_FROM_DEVICE);
sdev->ioctx_ring = NULL;
if (sdev->use_srq)
ib_destroy_srq(sdev->srq);
ib_dereg_mr(sdev->mr);
ib_dealloc_pd(sdev->pd);
kfree(sdev);
TRACE_EXIT();
@@ -4428,6 +4610,8 @@ static int __init srpt_init_module(void)
{
int ret;
BUILD_BUG_ON(sizeof(struct srp_imm_buf) != 8);
ret = -EINVAL;
if (srp_max_req_size < MIN_MAX_REQ_SIZE) {
PRINT_ERROR("invalid value %d for kernel module parameter"
+20 -7
View File
@@ -56,6 +56,7 @@
#endif
#include <linux/rtnetlink.h>
#include <rdma/rdma_cm.h>
#include "srp-ext.h"
#include "ib_dm_mad.h"
/*
@@ -128,10 +129,9 @@ enum {
MAX_SRPT_SRQ_SIZE = 65535,
MIN_MAX_REQ_SIZE = 996,
DEFAULT_MAX_REQ_SIZE
= sizeof(struct srp_cmd)/*48*/
+ sizeof(struct srp_indirect_buf)/*20*/
+ 255 * sizeof(struct srp_direct_buf)/*16*/,
SRP_IMM_DATA_OUT_OFFSET = 80,
DEFAULT_MAX_REQ_SIZE = SRP_IMM_DATA_OUT_OFFSET + 8192,
DATA_ALIGNMENT_OFFSET = 512 - SRP_IMM_DATA_OUT_OFFSET,
MIN_MAX_RSP_SIZE = sizeof(struct srp_rsp)/*36*/ + 4,
DEFAULT_MAX_RSP_SIZE = 256, /* leaves 220 bytes for sense data */
@@ -207,13 +207,15 @@ enum srpt_command_state {
/**
* struct srpt_ioctx - Shared SRPT I/O context information.
* @buf: Pointer to the buffer.
* @dma: DMA address of the buffer.
* @index: Index of the I/O context in its ioctx_ring array.
* @buf: Pointer to the buffer.
* @dma: DMA address of the buffer.
* @offset: Offset of the first byte in @buf and @dma that is actually used.
* @index: Index of the I/O context in its ioctx_ring array.
*/
struct srpt_ioctx {
void *buf;
dma_addr_t dma;
uint32_t offset;
uint32_t index;
};
@@ -221,10 +223,12 @@ struct srpt_ioctx {
* struct srpt_recv_ioctx - SRPT receive I/O context.
* @ioctx: See above.
* @wait_list: Node for insertion in srpt_rdma_ch.cmd_wait_list.
* @byte_len: Number of bytes in @ioctx.buf.
*/
struct srpt_recv_ioctx {
struct srpt_ioctx ioctx;
struct list_head wait_list;
int byte_len;
};
/**
@@ -239,7 +243,10 @@ struct srpt_tsk_mgmt {
* struct srpt_send_ioctx - SRPT send I/O context.
* @ioctx: See above.
* @ch: Channel pointer.
* @recv_ioctx: Receive I/O context associated with this send I/O context.
* @rdma_ius: Array with information about the RDMA mapping.
* @imm_data: Pointer to immediate data when using the immediate data format.
* @imm_sg: Scatterlist for immediate data.
* @rbufs: Pointer to SRP data buffer array.
* @single_rbuf: SRP data buffer if the command has only a single buffer.
* @sg: Pointer to sg-list associated with this I/O context.
@@ -263,7 +270,10 @@ struct srpt_tsk_mgmt {
struct srpt_send_ioctx {
struct srpt_ioctx ioctx;
struct srpt_rdma_ch *ch;
struct srpt_recv_ioctx *recv_ioctx;
struct rdma_iu *rdma_ius;
void *imm_data;
struct scatterlist imm_sg;
struct srp_direct_buf *rbufs;
struct srp_direct_buf single_rbuf;
struct scatterlist *sg;
@@ -366,6 +376,7 @@ struct srpt_rdma_ch {
spinlock_t spinlock;
struct list_head free_list;
struct srpt_send_ioctx **ioctx_ring;
struct srpt_recv_ioctx **ioctx_recv_ring;
struct ib_wc wc[16];
enum rdma_ch_state state;
struct list_head list;
@@ -448,6 +459,7 @@ struct srpt_port {
* @dev_attr: Attributes of the InfiniBand device as obtained during the
* ib_client.add() callback.
* @srq_size: SRQ size.
* @use_srq: Whether or not to use SRQ.
* @ioctx_ring: Per-HCA SRQ.
* @port: Information about the ports owned by this HCA.
* @event_handler: Per-HCA asynchronous IB event handler.
@@ -462,6 +474,7 @@ struct srpt_device {
struct ib_cm_id *cm_id;
struct ib_device_attr dev_attr;
int srq_size;
bool use_srq;
struct srpt_recv_ioctx **ioctx_ring;
struct srpt_port port[2];
struct ib_event_handler event_handler;
+22
View File
@@ -0,0 +1,22 @@
/*
* Extensions to the SRPr16a protocol
*
* Copyright (C) 2013 Fusion-io, Inc. All rights reserved.
*/
#ifndef _SRP_EXT_H_
#define _SRP_EXT_H_
/*
* Data is present as immediate data instead of being referred to via a
* descriptor.
*/
enum { SRP_DATA_DESC_IMM = 3 };
enum { SRP_BUF_FORMAT_IMM = 1 << 3 };
struct srp_imm_buf {
__be32 len;
__be32 offset;
};
#endif /* _SRP_EXT_H_ */